WEBVTT
Language: en-US

1
00:00:01.299 --> 00:00:04.070
<v Speaker 1>The industrial data starts at the plant
floor.

2
00:00:04.309 --> 00:00:08.619
<v Speaker 1>And so, again, we can obviously spend a
lot of time discussing the, the different

3
00:00:08.619 --> 00:00:13.260
<v Speaker 1>formats, but you have your analog and
digital data that is collected by your

4
00:00:13.260 --> 00:00:16.979
<v Speaker 1>machine, then it is usually sent to your
PLCs for control.

5
00:00:17.215 --> 00:00:18.504
<v Speaker 1>Systems purposes, right?

6
00:00:18.715 --> 00:00:23.514
<v Speaker 1>And so this is where we can have like, I
guess like deeper conversations as to what

7
00:00:23.514 --> 00:00:27.514
<v Speaker 1>is control system data, what is data that
will be used to make decisions, but

8
00:00:27.514 --> 00:00:32.955
<v Speaker 1>ultimately, it gets, um, it gets used
primarily for controlling the equipment.

9
00:00:34.049 --> 00:00:39.250
<v Speaker 2>Welcome to the trend detection podcast
powered by Siemens, and now your host, Nel

10
00:00:39.250 --> 00:00:39.810
<v Speaker 2>Sullivan.

11
00:00:42.119 --> 00:00:46.020
<v Niall Sullivan>Hello and welcome to the latest episode of
the Trend detection podcast.

12
00:00:46.560 --> 00:00:51.319
<v Niall Sullivan>I'm really pleased to be joined by, uh,
Vlad Rinov, um, and we're gonna be talking

13
00:00:51.319 --> 00:00:55.740
<v Niall Sullivan>today about industrial data, um, from
sensors to strategy.

14
00:00:55.959 --> 00:00:57.560
<v Niall Sullivan>So it's a, it's a really interesting
topic.

15
00:00:57.630 --> 00:01:02.299
<v Niall Sullivan>I mean, we've covered sensors in detail,
we've covered strategy in detail, but maybe

16
00:01:02.439 --> 00:01:05.940
<v Niall Sullivan>not in between as much, so I'm really
excited for this, um, session today.

17
00:01:06.599 --> 00:01:10.470
<v Niall Sullivan>Um, I'm gonna make a confession to start
with, because we have already had this

18
00:01:10.470 --> 00:01:10.750
<v Niall Sullivan>conversation.

19
00:01:10.919 --> 00:01:13.720
<v Niall Sullivan>Um, Vlad has very kindly agreed to
re-record.

20
00:01:13.760 --> 00:01:17.599
<v Niall Sullivan>We had a bit of a technical issue where
the recording corrupted or, you know,

21
00:01:17.760 --> 00:01:19.120
<v Niall Sullivan>didn't, didn't come through properly.

22
00:01:19.209 --> 00:01:23.629
<v Niall Sullivan>So unfortunately, our fantastic
conversation we had before is lost forever, but I'm

23
00:01:23.629 --> 00:01:25.760
<v Niall Sullivan>sure we'll do a better job this time
either way, Vlad.

24
00:01:25.839 --> 00:01:28.779
<v Niall Sullivan>So welcome back and thank you for your,
for your patience.

25
00:01:29.440 --> 00:01:32.470
<v Speaker 1>No, absolutely, thank you, thank you so
much for having me.

26
00:01:32.519 --> 00:01:36.440
<v Speaker 1>I think it's an important conversation to
have in our industry, so.

27
00:01:36.769 --> 00:01:39.760
<v Speaker 1>Um, happy to be back and, uh, let's make
it happen.

28
00:01:40.489 --> 00:01:41.610
<v Niall Sullivan>Fantastic, fantastic.

29
00:01:41.730 --> 00:01:45.930
<v Niall Sullivan>So, I mean, that's, you know, right at the
start, I'd be, it'd be great if, um, we

30
00:01:45.930 --> 00:01:48.809
<v Niall Sullivan>could find out a little bit more about
you, lads, your role, what kind of things

31
00:01:48.809 --> 00:01:51.589
<v Niall Sullivan>you're working on at the minute and all of
that good stuff.

32
00:01:52.290 --> 00:01:59.129
<v Speaker 1>Sure, so formal education in electrical
engineering as well as an MBA from Canadian

33
00:01:59.129 --> 00:01:59.889
<v Speaker 1>universities.

34
00:02:00.010 --> 00:02:05.769
<v Speaker 1>I have spent over a decade of my career in
manufacturing and industrial automation

35
00:02:05.769 --> 00:02:06.309
<v Speaker 1>settings.

36
00:02:06.690 --> 00:02:11.490
<v Speaker 1>I worked for very large end users to start
my career, Procter and Gamble, Kraft

37
00:02:11.490 --> 00:02:17.009
<v Speaker 1>Heinz, Post Holdings, again, very plant
floor heavy, so, you know, setting up

38
00:02:17.009 --> 00:02:23.330
<v Speaker 1>machines, programming PLCs, HMIs, Scata
platforms before making a transition to a

39
00:02:23.330 --> 00:02:23.410
<v Speaker 1>system.

40
00:02:23.779 --> 00:02:29.100
<v Speaker 1>Integrator where I learned a lot more
about industrial data, what it takes to create

41
00:02:29.100 --> 00:02:33.779
<v Speaker 1>enterprise networks, what it takes to, you
know, extract, basically store and

42
00:02:33.779 --> 00:02:38.940
<v Speaker 1>synthesize information for various
stakeholders in manufacturing, and we'll get into

43
00:02:38.940 --> 00:02:40.559
<v Speaker 1>some of those details a little bit later.

44
00:02:40.899 --> 00:02:46.020
<v Speaker 1>Um, I've been in both, like I said, very
large environments, but also in startups.

45
00:02:46.100 --> 00:02:49.240
<v Speaker 1>I spent a couple of years building a
DevOps solution.

46
00:02:49.539 --> 00:02:55.089
<v Speaker 1>So I've also gained an appreciation not
only um again from my earlier years,

47
00:02:55.270 --> 00:03:00.000
<v Speaker 1>spending a lot more time on the OT side
but also learning about IT in a lot more

48
00:03:00.000 --> 00:03:04.949
<v Speaker 1>depth than I would say a lot of the
manufacturing teams have the capability, at

49
00:03:04.949 --> 00:03:10.070
<v Speaker 1>least in my experience and so currently I
work on a variety of different projects.

50
00:03:10.149 --> 00:03:15.910
<v Speaker 1>I still do a lot of very traditional
integration and sort of modernization.

51
00:03:16.339 --> 00:03:20.429
<v Speaker 1>Uh, type of initiatives, you know, pretty
much starting with a plant assessment and

52
00:03:20.429 --> 00:03:25.259
<v Speaker 1>then going through projects of upgrading
whether that's PLC systems, servers,

53
00:03:25.750 --> 00:03:31.539
<v Speaker 1>networks, tying in all of that data back
into an on-prem database or a cloud

54
00:03:31.539 --> 00:03:36.750
<v Speaker 1>database and then obviously funneling that
into a scale MES type of a solution that

55
00:03:36.750 --> 00:03:37.330
<v Speaker 1>allows.

56
00:03:38.119 --> 00:03:41.490
<v Speaker 1>Basically manufacturing personnel to to
drive better decisions.

57
00:03:41.800 --> 00:03:46.520
<v Speaker 1>Um, I also have a few other projects, um,
you know, on the consulting side and

58
00:03:46.520 --> 00:03:52.720
<v Speaker 1>private equity type of due diligence work
again based on my financial and business

59
00:03:52.720 --> 00:03:58.199
<v Speaker 1>knowledge gained primarily from the MBA,
um, again, happy to, to discuss any and all

60
00:03:58.199 --> 00:04:00.080
<v Speaker 1>of those, uh, angles with you today.

61
00:04:01.199 --> 00:04:04.059
<v Niall Sullivan>Fantastic, and thank you for such a
comprehensive introduction.

62
00:04:04.089 --> 00:04:07.979
<v Niall Sullivan>I think we might need about 3 podcasts to
cover all of that, but no, we'll see,

63
00:04:08.169 --> 00:04:11.729
<v Niall Sullivan>we'll see how we go, but in a good way, I
mean, so you'll be definitely invited back

64
00:04:11.729 --> 00:04:11.910
<v Niall Sullivan>again.

65
00:04:12.289 --> 00:04:16.429
<v Niall Sullivan>But, um, but, I mean, let's start at the
basics, and this might seem quite basic to

66
00:04:16.630 --> 00:04:19.559
<v Niall Sullivan>people listening, maybe, because we're
gonna, I'm gonna sort of ask you to start by

67
00:04:19.559 --> 00:04:24.369
<v Niall Sullivan>defining industrial data, which everyone
may have their own view or opinion on, but

68
00:04:24.369 --> 00:04:27.609
<v Niall Sullivan>from obviously your, your perspective, but
also that, how that's sort of changed

69
00:04:27.609 --> 00:04:29.450
<v Niall Sullivan>over the past sort of 10 years or so.

70
00:04:30.640 --> 00:04:35.359
<v Speaker 1>Yeah, so starting with, I guess, the plant
floor, right, uh, again, those that

71
00:04:35.359 --> 00:04:41.000
<v Speaker 1>operate machines will usually notice the
sensors that are present for detecting

72
00:04:41.000 --> 00:04:45.559
<v Speaker 1>various, I would say, materials on the
conveyor belts.

73
00:04:45.640 --> 00:04:50.399
<v Speaker 1>Inside the machines during the
transformation, so the industrial data starts at the

74
00:04:50.399 --> 00:04:51.140
<v Speaker 1>plant floor.

75
00:04:51.399 --> 00:04:55.720
<v Speaker 1>And so again, we can obviously spend a lot
of time discussing the, the different

76
00:04:55.720 --> 00:05:00.320
<v Speaker 1>formats, but you have your analog and
digital data that is collected by your

77
00:05:00.320 --> 00:05:00.459
<v Speaker 1>machine.

78
00:05:01.040 --> 00:05:05.519
<v Speaker 1>Then it is usually sent to your PLCs for
control systems purposes, right?

79
00:05:05.799 --> 00:05:10.600
<v Speaker 1>And so this is where we can have like, I
guess like deeper conversations as to what

80
00:05:10.600 --> 00:05:14.600
<v Speaker 1>is control system data, what is data that
will be used to make decisions, but

81
00:05:14.600 --> 00:05:20.079
<v Speaker 1>ultimately, it gets, um, it gets used
primarily for controlling the equipment.

82
00:05:20.559 --> 00:05:25.429
<v Speaker 1>Secondarily, it is used to to be funneled,
as I mentioned, to make decisions, and

83
00:05:25.429 --> 00:05:31.480
<v Speaker 1>that can be your, again, your Edge IPC,
your Edge solution that will synthesize or I

84
00:05:31.480 --> 00:05:36.119
<v Speaker 1>guess collect a portion of that control
system data, store it for historical.

85
00:05:36.295 --> 00:05:42.464
<v Speaker 1>Purposes, uh, draw certain, I would say,
maybe definitions based on that

86
00:05:42.464 --> 00:05:44.394
<v Speaker 1>information, add time stamps, right?

87
00:05:44.434 --> 00:05:49.075
<v Speaker 1>So usually your control systems are going
to be cyclical, whereas you want to make

88
00:05:49.075 --> 00:05:50.644
<v Speaker 1>decisions based on a time period.

89
00:05:50.875 --> 00:05:51.994
<v Speaker 1>So you need to create.

90
00:05:52.390 --> 00:05:56.220
<v Speaker 1>Um, more information than what the control
systems generally provide.

91
00:05:56.480 --> 00:06:01.640
<v Speaker 1>And so if I want to take a step back maybe
and define what is industrial data, I

92
00:06:01.640 --> 00:06:08.600
<v Speaker 1>would say that it is the umbrella term
used for any and all information

93
00:06:08.880 --> 00:06:14.959
<v Speaker 1>that will ultimately touch or have an
impact on the plant floor, but me as La, I

94
00:06:14.959 --> 00:06:19.440
<v Speaker 1>would take that a step further and say
that there is maybe control system data that

95
00:06:19.440 --> 00:06:21.440
<v Speaker 1>is used to run the actual equipment.

96
00:06:21.679 --> 00:06:26.359
<v Speaker 1>And there is data that is used to make
decisions, and we can get into the

97
00:06:26.359 --> 00:06:31.640
<v Speaker 1>distinctions of both, but ultimately they
will be from a technical and a business

98
00:06:31.640 --> 00:06:34.179
<v Speaker 1>perspective, uh, somewhat different.

99
00:06:34.640 --> 00:06:39.880
<v Speaker 1>Um, to your question on how do things
change, well, I would say that there was

100
00:06:39.880 --> 00:06:42.290
<v Speaker 1>always an appetite for data.

101
00:06:42.399 --> 00:06:47.200
<v Speaker 1>I think that, you know, scata systems have
existed for many years and decades.

102
00:06:47.470 --> 00:06:54.390
<v Speaker 1>And in a very broad sense, every
manufacturer has always captured the

103
00:06:54.390 --> 00:06:56.589
<v Speaker 1>information on how productive they are,
right?

104
00:06:56.630 --> 00:07:01.670
<v Speaker 1>And so in the early years, that would be
maybe using a clipboard or a whiteboard, so

105
00:07:01.670 --> 00:07:05.589
<v Speaker 1>a lot of times you go to a plant, they
would have sort of a sensor at the end of the

106
00:07:05.589 --> 00:07:05.850
<v Speaker 1>line.

107
00:07:06.309 --> 00:07:10.350
<v Speaker 1>They would read how many cases are coming
through in let's say an hour or a shift.

108
00:07:10.429 --> 00:07:11.950
<v Speaker 1>They would write that down on the
whiteboard.

109
00:07:12.190 --> 00:07:17.149
<v Speaker 1>I think that the major change, of course,
and I would say since COVID because

110
00:07:17.149 --> 00:07:22.109
<v Speaker 1>everyone wanted to work more remotely or
couldn't be at the facilities, everyone is

111
00:07:22.109 --> 00:07:25.619
<v Speaker 1>trying to get as digital as possible,
right?

112
00:07:25.709 --> 00:07:30.769
<v Speaker 1>So now we see a lot more implementations
of SCATA systems that are properly.

113
00:07:31.170 --> 00:07:35.809
<v Speaker 1>I would say digitalized, a lot of um MES
types of application manufacturing

114
00:07:35.809 --> 00:07:39.970
<v Speaker 1>execution systems that allow you to again
take that a step further and provide

115
00:07:39.970 --> 00:07:40.790
<v Speaker 1>insights.

116
00:07:41.130 --> 00:07:46.220
<v Speaker 1>Um, so industrial data, like I said, was
always there in a general sense.

117
00:07:46.450 --> 00:07:52.369
<v Speaker 1>It's just been a lot more digitized, I
would say in the last probably 6 or so years

118
00:07:52.369 --> 00:07:53.089
<v Speaker 1>at this point.

119
00:07:54.779 --> 00:07:58.779
<v Niall Sullivan>And I guess maybe let's start there, you
know, you know, you know, why has the, you

120
00:07:58.779 --> 00:08:03.000
<v Niall Sullivan>know, digitizing started in the last 6
years, cause I mean that seems quite recent

121
00:08:03.000 --> 00:08:06.899
<v Niall Sullivan>to me actually, but is there a reason why,
why then it's the right time?

122
00:08:07.059 --> 00:08:08.760
<v Niall Sullivan>Maybe it's a difficult one to answer, but.

123
00:08:09.119 --> 00:08:11.760
<v Speaker 1>Yeah, so, so, so look, let me, I guess,
take a step back, right?

124
00:08:11.880 --> 00:08:18.380
<v Speaker 1>So I think in our industry there's quite a
wide gap between sort of the cutting edge

125
00:08:18.380 --> 00:08:23.480
<v Speaker 1>and bleeding edge, if you will, companies
versus I would say the medium to small

126
00:08:23.480 --> 00:08:24.600
<v Speaker 1>manufacturers, right?

127
00:08:24.920 --> 00:08:28.700
<v Speaker 1>So it's not to say that there was never
digital solutions.

128
00:08:29.000 --> 00:08:31.040
<v Speaker 1>I just, I guess from what I've witnessed.

129
00:08:31.709 --> 00:08:36.070
<v Speaker 1>During the time of COVID, at least, so
I've been to, uh, as a result of COVID to

130
00:08:36.070 --> 00:08:39.059
<v Speaker 1>many facilities during those two years,
right?

131
00:08:39.109 --> 00:08:44.109
<v Speaker 1>And of course we can talk about sort of
the career shifts that people have made, we

132
00:08:44.109 --> 00:08:48.869
<v Speaker 1>can talk about the fact that, you know, it
was very difficult to get inside of a

133
00:08:48.869 --> 00:08:51.599
<v Speaker 1>plant without proper clearance, proper
checks.

134
00:08:51.909 --> 00:08:55.950
<v Speaker 1>Again, they were maybe looser or more
restrictive depending on the region and the

135
00:08:55.950 --> 00:08:58.950
<v Speaker 1>world that you were in, but ultimately,
um.

136
00:08:59.479 --> 00:09:02.849
<v Speaker 1>Manufacturing needed to keep going, right?

137
00:09:02.919 --> 00:09:07.840
<v Speaker 1>You had no choice but to manufacture, and
I do a lot of uh food and beverage and CPG

138
00:09:07.840 --> 00:09:13.500
<v Speaker 1>type of facilities, so as you can imagine,
there was a lot of pressure to continue

139
00:09:13.919 --> 00:09:17.239
<v Speaker 1>working while all of these shutdowns are
happening.

140
00:09:17.359 --> 00:09:19.599
<v Speaker 1>So of course personnel needed to be able
to eva.

141
00:09:19.770 --> 00:09:24.619
<v Speaker 1>Evaluate how well are we producing, where
are the deficiencies, uh, where do we

142
00:09:24.619 --> 00:09:25.669
<v Speaker 1>invest our Capital, right?

143
00:09:25.739 --> 00:09:30.500
<v Speaker 1>So there were a lot of, there was a lot of
pressure to make those decisions, um, and

144
00:09:30.500 --> 00:09:35.830
<v Speaker 1>it was more difficult to access data that
was manually created.

145
00:09:36.219 --> 00:09:40.070
<v Speaker 1>So therefore I believe we saw this sort of
roll up from.

146
00:09:40.450 --> 00:09:45.729
<v Speaker 1>Uh, medium, at least manufacturers that
didn't have or didn't have a big incentive

147
00:09:45.729 --> 00:09:49.650
<v Speaker 1>to have a lot of those digital solutions
to roll them out.

148
00:09:50.099 --> 00:09:50.890
<v Speaker 1>Does that make sense?

149
00:09:52.289 --> 00:09:53.450
<v Niall Sullivan>No, it does, it does.

150
00:09:53.530 --> 00:09:58.690
<v Niall Sullivan>I think, I think it leads, it leads quite
nicely onto sort of my next question, and

151
00:09:58.690 --> 00:10:00.330
<v Niall Sullivan>it, and actually what you were talking
about before.

152
00:10:00.450 --> 00:10:03.809
<v Niall Sullivan>So you talked about, you know, different,
you know, the flow of data from the shop

153
00:10:03.809 --> 00:10:07.729
<v Niall Sullivan>floor, from sensors, you know, all the way
up to sort of strategic or enterprise

154
00:10:07.729 --> 00:10:08.690
<v Niall Sullivan>level decision making.

155
00:10:08.760 --> 00:10:11.929
<v Niall Sullivan>But could, I mean, could you describe that
in a bit more detail, because it seems

156
00:10:11.929 --> 00:10:12.489
<v Niall Sullivan>quite, you know.

157
00:10:12.674 --> 00:10:15.724
<v Niall Sullivan>Someone like me, maybe a little bit on the
outside, a little disconnected, right,

158
00:10:16.094 --> 00:10:20.275
<v Niall Sullivan>you know, you've got data here, which at
the end of the day should inform strategic

159
00:10:20.275 --> 00:10:21.994
<v Niall Sullivan>decisions at board level, for example.

160
00:10:22.114 --> 00:10:22.544
<v Niall Sullivan>So how,

161
00:10:22.794 --> 00:10:27.474
<v Speaker 1>sure, so I, I like to use, I guess, like
props maybe a little bit to, to answer that

162
00:10:27.474 --> 00:10:27.715
<v Speaker 1>question, right?

163
00:10:27.755 --> 00:10:31.715
<v Speaker 1>And you see behind me there's, there's a
couple of PLCs, there's one from Siemens,

164
00:10:31.825 --> 00:10:32.994
<v Speaker 1>Alan Bradley, there's some.

165
00:10:33.260 --> 00:10:38.669
<v Speaker 1>IPC from Siemens, there's basically a
non-industrial computer, right, and so to

166
00:10:38.669 --> 00:10:43.549
<v Speaker 1>paint you a clear picture of an
architecture, and let's start maybe with a simple

167
00:10:43.549 --> 00:10:43.809
<v Speaker 1>example.

168
00:10:44.030 --> 00:10:49.219
<v Speaker 1>So when you have a stand-alone machine,
You will typically have your sensors tied to

169
00:10:49.219 --> 00:10:52.780
<v Speaker 1>a PLC and then that PLC talks to an HMI,
right?

170
00:10:52.849 --> 00:10:57.260
<v Speaker 1>So that data in a, in a sense is contained
without that piece of equipment, right?

171
00:10:57.299 --> 00:11:01.940
<v Speaker 1>And of course when I say a machine, that
could be as simple as a, as a palletizing

172
00:11:01.940 --> 00:11:05.460
<v Speaker 1>machine, a case packing machine, but it
could be an entire process, right?

173
00:11:05.530 --> 00:11:10.460
<v Speaker 1>So for some facilities, you will have a
larger sort of quote unquote machine or.

174
00:11:10.580 --> 00:11:14.340
<v Speaker 1>Area that is going to be controlled by
that standalone type of system.

175
00:11:14.380 --> 00:11:19.820
<v Speaker 1>And so in that case, your data is
basically going from your sensors that are your

176
00:11:19.820 --> 00:11:26.140
<v Speaker 1>outputs and inputs on the PLC side, and
it's controlling your motors, it's

177
00:11:26.140 --> 00:11:30.700
<v Speaker 1>controlling your different valves, it's
actuators, there's going to be specialty

178
00:11:30.700 --> 00:11:34.469
<v Speaker 1>modules, right, so your data is basically
contained within that system.

179
00:11:34.900 --> 00:11:40.219
<v Speaker 1>As you start basically growing those
operations, you're looking to make decisions on

180
00:11:40.219 --> 00:11:45.700
<v Speaker 1>a slightly higher scale, and as I
mentioned before, you're looking to control more

181
00:11:45.700 --> 00:11:49.179
<v Speaker 1>pieces of equipment, but you're also
looking to understand more pieces of equipment,

182
00:11:49.260 --> 00:11:49.419
<v Speaker 1>right?

183
00:11:49.500 --> 00:11:51.340
<v Speaker 1>So this is where, and again there's a lot.

184
00:11:51.450 --> 00:11:56.039
<v Speaker 1>of debates in our industry between let's
say SCAta function versus MES functions,

185
00:11:56.289 --> 00:12:01.770
<v Speaker 1>but basically picture a production line
where you have a sequential step of

186
00:12:01.770 --> 00:12:06.250
<v Speaker 1>processes where you want to see what is
the filler doing, what is the case backer

187
00:12:06.250 --> 00:12:10.049
<v Speaker 1>doing, what is the palletizer doing, and
you're trying to understand.

188
00:12:10.309 --> 00:12:14.039
<v Speaker 1>Um, at the end of the day you're trying to
understand how can we better the

189
00:12:14.039 --> 00:12:18.659
<v Speaker 1>throughput of the finished product, right,
because if we take a step back, what is

190
00:12:19.119 --> 00:12:21.539
<v Speaker 1>paying the, the salaries and the.

191
00:12:21.809 --> 00:12:26.369
<v Speaker 1>Um, how would I say it, the making the
incentives for any of these types of

192
00:12:26.369 --> 00:12:30.289
<v Speaker 1>projects, it's obviously product created
by the manufacturer, right?

193
00:12:30.609 --> 00:12:35.650
<v Speaker 1>And so when we talk about data, we're
trying to understand, well, where is first and

194
00:12:35.650 --> 00:12:37.590
<v Speaker 1>foremost the bottleneck on our line?

195
00:12:38.010 --> 00:12:39.409
<v Speaker 1>Why is that a bottleneck?

196
00:12:39.450 --> 00:12:41.289
<v Speaker 1>Is it because it's going down?

197
00:12:41.330 --> 00:12:42.789
<v Speaker 1>Is it because it's breaking?

198
00:12:42.909 --> 00:12:47.210
<v Speaker 1>Is it because, you know, the operator is
not loading the raw materials fast enough,

199
00:12:47.710 --> 00:12:53.070
<v Speaker 1>so data allows you to start understanding
that from an enterprise level, right?

200
00:12:53.109 --> 00:12:58.469
<v Speaker 1>And so as we take another layer up right
when we again talk about plant maturity,

201
00:12:58.710 --> 00:13:02.789
<v Speaker 1>now you're trying to understand not only a
single line, you're trying to understand

202
00:13:02.789 --> 00:13:03.869
<v Speaker 1>the entire facility.

203
00:13:04.320 --> 00:13:09.760
<v Speaker 1>So depending on whom you visit, they may
have an area that runs a specific SKU that

204
00:13:09.760 --> 00:13:13.719
<v Speaker 1>might be a lot more critical for that
specific business unit, right?

205
00:13:13.760 --> 00:13:16.119
<v Speaker 1>And so now you're trying to understand
where do we invest.

206
00:13:16.159 --> 00:13:20.989
<v Speaker 1>Do we invest in this specific line that
runs SKUW X, Y, Z, or do we invest in a

207
00:13:20.989 --> 00:13:21.859
<v Speaker 1>secondary line.

208
00:13:22.460 --> 00:13:26.630
<v Speaker 1>That runs perhaps some different products
and so then you're starting to again

209
00:13:26.630 --> 00:13:32.260
<v Speaker 1>funnel that data from the plant floor into
these, I would say more cloud native but

210
00:13:32.260 --> 00:13:37.469
<v Speaker 1>ultimately more consolidated types of
solutions where you're not looking at the

211
00:13:37.469 --> 00:13:42.229
<v Speaker 1>sensor on the machine, you're now looking
at how is my line performing, how is this

212
00:13:42.229 --> 00:13:43.030
<v Speaker 1>side doing, right?

213
00:13:43.109 --> 00:13:49.989
<v Speaker 1>So you're starting to have a much more
higher level view of your entire operation on

214
00:13:49.989 --> 00:13:51.630
<v Speaker 1>a multi-site basis.

215
00:13:53.880 --> 00:13:57.940
<v Niall Sullivan>And I guess another sort of aspect of
this, with all those different sort of data

216
00:13:57.940 --> 00:14:01.789
<v Niall Sullivan>sources, what we're talking about is, you
know, data integration between IT and OT

217
00:14:02.059 --> 00:14:06.210
<v Niall Sullivan>systems, which is, of course, always sort
of top of mind during sort of these large,

218
00:14:06.710 --> 00:14:11.820
<v Niall Sullivan>um, well, large and small, um, projects,
but, you know, how can organizations sort

219
00:14:11.820 --> 00:14:14.669
<v Niall Sullivan>of, how should they approach that and, you
know, what are some of the common

220
00:14:14.669 --> 00:14:17.669
<v Niall Sullivan>pitfalls around integrating those
different data sources?

221
00:14:18.669 --> 00:14:23.770
<v Speaker 1>That is, that is the very difficult
question, right, uh, for, for, for many years

222
00:14:23.770 --> 00:14:26.890
<v Speaker 1>I've had conversations on, on both sides.

223
00:14:27.309 --> 00:14:32.539
<v Speaker 1>And I simply believe that there is a
difference in in and it's a generalization,

224
00:14:32.669 --> 00:14:32.799
<v Speaker 1>right?

225
00:14:32.840 --> 00:14:39.080
<v Speaker 1>There's generally a difference in KPIs
associated for both teams, and you will

226
00:14:39.080 --> 00:14:45.440
<v Speaker 1>generally see, again, engineers on the IT
side have a different perspective on

227
00:14:45.440 --> 00:14:47.739
<v Speaker 1>what's important versus the OT side.

228
00:14:47.960 --> 00:14:50.559
<v Speaker 1>And there's not necessarily anything wrong
with that.

229
00:14:50.799 --> 00:14:55.840
<v Speaker 1>I just think that there's a, There's
generally a need to orchestrate so that they

230
00:14:55.840 --> 00:14:58.969
<v Speaker 1>don't clash during the implementation,
right?

231
00:14:59.070 --> 00:15:04.539
<v Speaker 1>And what I mean by that is the OT side
usually prioritizes, like I've mentioned a

232
00:15:04.539 --> 00:15:06.599
<v Speaker 1>little bit earlier, product out the door.

233
00:15:06.919 --> 00:15:07.929
<v Speaker 1>So if you've ever been.

234
00:15:08.309 --> 00:15:13.599
<v Speaker 1>In any commissioning project, you will
very quickly find out that there's a very

235
00:15:13.599 --> 00:15:19.119
<v Speaker 1>strict timeline, we only have access to,
let's say the line being down for a very

236
00:15:19.119 --> 00:15:24.320
<v Speaker 1>specific number of hours or days to
implement whatever change, and you have a lot of

237
00:15:24.320 --> 00:15:26.919
<v Speaker 1>pressure to make sure that product gets
made.

238
00:15:27.400 --> 00:15:33.150
<v Speaker 1>So of course you're going to not
necessarily cut corners, but you're going to do

239
00:15:33.150 --> 00:15:36.640
<v Speaker 1>whatever is necessary to make sure that
equipment runs.

240
00:15:37.229 --> 00:15:42.200
<v Speaker 1>On the IT side, the priorities are
different for again different reasons, but

241
00:15:42.200 --> 00:15:48.679
<v Speaker 1>usually they are trained to mitigate risk
from external cyberattacks or ransomware.

242
00:15:48.780 --> 00:15:52.479
<v Speaker 1>They're, you know, they're used to manage
access to those systems.

243
00:15:52.590 --> 00:15:56.130
<v Speaker 1>They want to make sure that everything is
secure on the data side.

244
00:15:56.320 --> 00:15:56.520
<v Speaker 1>They want.

245
00:15:56.614 --> 00:16:00.854
<v Speaker 1>To audit, you know, the protocols that
allow you to pass different data and so of

246
00:16:00.854 --> 00:16:07.575
<v Speaker 1>course the two priorities need to align in
a project that's going to touch both

247
00:16:07.575 --> 00:16:07.974
<v Speaker 1>sides.

248
00:16:08.335 --> 00:16:12.614
<v Speaker 1>So usually again going back to the point
of data, if it's a stand-alone machine that

249
00:16:12.614 --> 00:16:16.054
<v Speaker 1>gets deployed on the plant floor and it
doesn't need to communicate.

250
00:16:16.479 --> 00:16:20.679
<v Speaker 1>Anything outside of that environment,
usually OT will be more than capable of

251
00:16:20.679 --> 00:16:27.119
<v Speaker 1>handling that project, but as soon as it
touches yoursCATA and MES layers, and again

252
00:16:27.119 --> 00:16:31.159
<v Speaker 1>there's going to be, of course, a lot of
auxiliary things, it could be on the

253
00:16:31.159 --> 00:16:35.359
<v Speaker 1>quality side, it could be on the
laboratory testing side, right, so there's going to

254
00:16:35.359 --> 00:16:37.780
<v Speaker 1>be a lot of sort of like gray areas as
well.

255
00:16:38.280 --> 00:16:38.880
<v Speaker 1>IT needs.

256
00:16:39.025 --> 00:16:39.744
<v Speaker 1>Get involved, right?

257
00:16:39.784 --> 00:16:44.864
<v Speaker 1>And so usually they will provision
hardware, so your servers, they will provision

258
00:16:44.864 --> 00:16:49.585
<v Speaker 1>your virtual machines upon which, you
know, a lot of the software is going to run,

259
00:16:49.825 --> 00:16:54.784
<v Speaker 1>and so they primarily from their
standpoint, they don't need to understand what the

260
00:16:54.784 --> 00:16:59.184
<v Speaker 1>data delivers to the plant floor, but they
need to understand how it's going to be

261
00:16:59.184 --> 00:17:01.544
<v Speaker 1>secure, who, who's going to have access.

262
00:17:01.979 --> 00:17:07.380
<v Speaker 1>Um, a lot of times, who is going to from
the outside be allowed to remote in, you

263
00:17:07.380 --> 00:17:08.329
<v Speaker 1>know, and make changes.

264
00:17:08.420 --> 00:17:10.260
<v Speaker 1>How are they going to make those changes?

265
00:17:10.619 --> 00:17:14.880
<v Speaker 1>How are we going to, uh, I've, I've been
through these conversations many times, but

266
00:17:14.880 --> 00:17:17.619
<v Speaker 1>who's going to upgrade your Microsoft.

267
00:17:17.864 --> 00:17:22.943
<v Speaker 1>You know, directory service, uh, who's
going to upgrade the server instances, so

268
00:17:22.943 --> 00:17:28.093
<v Speaker 1>there's going to be a lot of questions
that again concern IT, whereas again OT is

269
00:17:28.093 --> 00:17:33.463
<v Speaker 1>usually not going to be trained on the
server architecture of a facility.

270
00:17:35.339 --> 00:17:38.260
<v Niall Sullivan>And I guess in amongst all that, because
of course there's a lot of technical

271
00:17:38.260 --> 00:17:41.819
<v Niall Sullivan>considerations, but what I sort of noted
down, I was writing down there is more

272
00:17:41.819 --> 00:17:45.949
<v Niall Sullivan>around that, you know, the, there's a lot
of cultural differences, you know, maybe

273
00:17:45.949 --> 00:17:48.839
<v Niall Sullivan>differences, but approaches, I'm gonna
say, because neither approach is wrong,

274
00:17:48.939 --> 00:17:52.859
<v Niall Sullivan>right, but it's just different mindsets,
different goals, and I guess it's trying to

275
00:17:52.859 --> 00:17:55.160
<v Niall Sullivan>align some of those goals together, I
guess.

276
00:17:56.280 --> 00:18:01.839
<v Speaker 1>I, I think for me it's um to be honest
with you, over over communicate your

277
00:18:01.839 --> 00:18:02.790
<v Speaker 1>objectives, right?

278
00:18:02.880 --> 00:18:07.599
<v Speaker 1>So like I said, I believe that both groups
are trained in to some extent like

279
00:18:07.599 --> 00:18:12.560
<v Speaker 1>different disciplines ultimately they do
have an aligned objective for the business,

280
00:18:12.640 --> 00:18:12.760
<v Speaker 1>right?

281
00:18:12.839 --> 00:18:17.239
<v Speaker 1>They are trying to make sure that the
business will continue to function as

282
00:18:17.239 --> 00:18:17.780
<v Speaker 1>expected.

283
00:18:17.959 --> 00:18:23.239
<v Speaker 1>I think it's just maybe a misunderstanding
of what the other is trying to do that

284
00:18:23.239 --> 00:18:24.479
<v Speaker 1>scares the other group.

285
00:18:24.660 --> 00:18:29.719
<v Speaker 1>Right, so if I'm putting on my OT boots
and I'm just trying to funnel data,

286
00:18:30.060 --> 00:18:34.099
<v Speaker 1>obviously I'm trying to understand how the
machines are running and I'm trying to,

287
00:18:34.380 --> 00:18:39.859
<v Speaker 1>you know, basically have a good overview
of the, the plant floor, but that scares

288
00:18:39.859 --> 00:18:42.640
<v Speaker 1>the IT team if I don't explicitly.

289
00:18:43.010 --> 00:18:46.819
<v Speaker 1>Uh, tell them what I'm looking to have
access to, how it's going to be stored,

290
00:18:46.859 --> 00:18:52.619
<v Speaker 1>right, and having those conversations is
going to help solidify some of that

291
00:18:52.619 --> 00:18:53.050
<v Speaker 1>understanding.

292
00:18:53.380 --> 00:18:58.660
<v Speaker 1>Similarly, if I'm on the, um, again on the
IT side, I need to be very clear.

293
00:18:59.140 --> 00:19:02.569
<v Speaker 1>What does it mean to have access, have
permissions?

294
00:19:02.780 --> 00:19:07.089
<v Speaker 1>How do I access different layers of the
servers, because again, people on the OT

295
00:19:07.089 --> 00:19:12.219
<v Speaker 1>side usually are not trained there, and
they get worried when, you know, it becomes

296
00:19:12.219 --> 00:19:16.380
<v Speaker 1>way too troublesome to support equipment
that, you know, was deployed in a facility

297
00:19:16.380 --> 00:19:22.939
<v Speaker 1>30 years ago and requires a parallel port
to connect to, and the IT is

298
00:19:22.939 --> 00:19:24.130
<v Speaker 1>revoking that access, right?

299
00:19:24.180 --> 00:19:25.780
<v Speaker 1>So I think it's being very explicit.

300
00:19:26.119 --> 00:19:31.709
<v Speaker 1>Um, on both sides in those conversations
that can and sometimes does solve some of

301
00:19:31.709 --> 00:19:32.510
<v Speaker 1>the conflicts.

302
00:19:33.540 --> 00:19:38.300
<v Niall Sullivan>And, and do you think that that
relationship is maybe stronger compared to previous

303
00:19:38.300 --> 00:19:42.319
<v Niall Sullivan>years or, you know, I know it's a general
question cos it differs across

304
00:19:42.319 --> 00:19:43.540
<v Niall Sullivan>organizations, industries, etc.

305
00:19:43.660 --> 00:19:46.900
<v Niall Sullivan>but is that, do you feel that's stronger
for those reasons you, you mentioned there?

306
00:19:48.079 --> 00:19:54.569
<v Speaker 1>To be honest with you, I wish I could say
yes, um, but what I see is I believe that

307
00:19:54.569 --> 00:20:00.209
<v Speaker 1>the technical complexity is increasing on
both sides, right, and we, we can talk as

308
00:20:00.209 --> 00:20:04.160
<v Speaker 1>to, uh, as to why that is maybe in a in a
separate question, but I believe that

309
00:20:04.160 --> 00:20:09.280
<v Speaker 1>there's a technical complexity increase in
both OT as well as IT environments.

310
00:20:09.560 --> 00:20:15.520
<v Speaker 1>And at least from what I have seen, the
projects are having a harder time now

311
00:20:15.520 --> 00:20:20.140
<v Speaker 1>because of that, uh, sort of like mesh
well, uh, between the two teams.

312
00:20:22.270 --> 00:20:22.469
<v Niall Sullivan>Exactly.

313
00:20:22.670 --> 00:20:26.859
<v Niall Sullivan>And maybe, and maybe this is a good time,
um, to sort of look at, you know, tangible

314
00:20:26.859 --> 00:20:27.550
<v Niall Sullivan>examples as well.

315
00:20:27.630 --> 00:20:30.270
<v Niall Sullivan>So you've obviously worked with, you know,
I mean, you mentioned you've worked at,

316
00:20:30.449 --> 00:20:33.550
<v Niall Sullivan>but also with, um, sort of huge
manufacturers.

317
00:20:33.589 --> 00:20:37.790
<v Niall Sullivan>I'm not sure you've mentioned names, but
are there sort of examples where, you know,

318
00:20:37.910 --> 00:20:42.180
<v Niall Sullivan>data's really transformed the way they
work from the plant floor, you know, upwards,

319
00:20:42.229 --> 00:20:42.550
<v Niall Sullivan>right?

320
00:20:43.530 --> 00:20:48.180
<v Speaker 1>Yeah, so I guess let me start maybe with
uh sort of a few examples earlier in my

321
00:20:48.180 --> 00:20:48.670
<v Speaker 1>career, right?

322
00:20:48.780 --> 00:20:54.969
<v Speaker 1>So I started out of university to work for
Procter and Gamble, uh, where I learned

323
00:20:54.969 --> 00:21:00.770
<v Speaker 1>pretty much a lot of the foundational
knowledge A to Z when it comes to data,

324
00:21:01.459 --> 00:21:07.400
<v Speaker 1>operations, industrial automation, and I
can tell you, bar none, uh, that they have

325
00:21:07.410 --> 00:21:09.839
<v Speaker 1>some of the best, I would say,
engineering.

326
00:21:10.209 --> 00:21:15.890
<v Speaker 1>Um, at least within the facilities that I
was at, where data is leveraged to a great

327
00:21:15.890 --> 00:21:18.380
<v Speaker 1>extent, and I'll give you a couple of
tangible examples.

328
00:21:18.459 --> 00:21:24.099
<v Speaker 1>So we utilized a software and this is
public information called Prophecy by General

329
00:21:24.099 --> 00:21:29.060
<v Speaker 1>Electric for our MES manufacturing
execution systems layer.

330
00:21:29.369 --> 00:21:35.130
<v Speaker 1>And basically what that meant is we would
get very granular information on the types

331
00:21:35.130 --> 00:21:39.130
<v Speaker 1>of faults that would happen on the lines,
the duration of those faults.

332
00:21:39.410 --> 00:21:43.079
<v Speaker 1>We would obviously get OEE, but typically
again on the engineering we would be

333
00:21:43.079 --> 00:21:49.160
<v Speaker 1>concerned about mean time to repair, mean
time to failure, and so we would have very

334
00:21:49.160 --> 00:21:53.050
<v Speaker 1>specific meetings with the operational
team that would conduct.

335
00:21:53.194 --> 00:21:57.824
<v Speaker 1>Them on a shift basis, but we would check
in with them usually on a weekly basis, on

336
00:21:57.824 --> 00:22:04.545
<v Speaker 1>a monthly basis to figure out how do we
allocate Capital and resources to eliminate

337
00:22:04.545 --> 00:22:06.155
<v Speaker 1>some of those failures, right?

338
00:22:06.185 --> 00:22:11.584
<v Speaker 1>And so PNG was very strong on the cultural
side as well as the technical sides to

339
00:22:11.584 --> 00:22:15.875
<v Speaker 1>drive changes through the data that was
available on the plant floor.

340
00:22:16.104 --> 00:22:16.805
<v Speaker 1>Now again.

341
00:22:18.109 --> 00:22:23.920
<v Speaker 1>Just to add to that maybe point, a lot of
that infrastructure was already in place,

342
00:22:24.400 --> 00:22:25.390
<v Speaker 1>uh, when I came in.

343
00:22:25.569 --> 00:22:31.020
<v Speaker 1>So in hindsight, right, and now having
seen, I would say like hundreds of other

344
00:22:31.020 --> 00:22:35.699
<v Speaker 1>different facilities, I can tell you that
it is very difficult to create that

345
00:22:35.699 --> 00:22:40.319
<v Speaker 1>environment to be able to leverage that
data, and I will say that in more recent

346
00:22:40.319 --> 00:22:44.459
<v Speaker 1>years again to talk about some of the
initiatives in plants that are not.

347
00:22:44.839 --> 00:22:48.060
<v Speaker 1>I would say or do not have a system of
that caliber.

348
00:22:48.349 --> 00:22:54.030
<v Speaker 1>A lot of time is spent, at least by me, is
going to the plant floor, understanding

349
00:22:54.030 --> 00:22:54.829
<v Speaker 1>the assets, right?

350
00:22:54.910 --> 00:22:59.630
<v Speaker 1>So doing a full audit of what do we
currently have there, understanding first and

351
00:22:59.630 --> 00:23:03.729
<v Speaker 1>foremost, can we extract data in its
current state?

352
00:23:03.989 --> 00:23:09.520
<v Speaker 1>And the answer is, again, usually from a
consulting standpoint is it depends, right?

353
00:23:09.550 --> 00:23:11.130
<v Speaker 1>And of course it depends on.

354
00:23:11.430 --> 00:23:15.479
<v Speaker 1>How old is the control system, what is
available at the plant layer?

355
00:23:15.829 --> 00:23:19.709
<v Speaker 1>How can we actually communicate via those
protocols, and that's a whole other, you

356
00:23:19.709 --> 00:23:25.469
<v Speaker 1>know, technical, maybe conversation, but
you start piece by piece extracting the

357
00:23:25.469 --> 00:23:29.150
<v Speaker 1>information from, like I mentioned, a
filling machine, your case backer, your

358
00:23:29.150 --> 00:23:32.790
<v Speaker 1>capper, your labeler, uh, your process
side, you're trying to understand.

359
00:23:32.939 --> 00:23:37.699
<v Speaker 1>On the batch, then you're starting to get
into, I would say, foundational or

360
00:23:37.699 --> 00:23:43.500
<v Speaker 1>fundamental metrics like OEE just to try
and understand the baseline and then you

361
00:23:43.500 --> 00:23:47.329
<v Speaker 1>start to drill in a little bit deeper what
kind of fault codes are you getting,

362
00:23:47.619 --> 00:23:51.219
<v Speaker 1>what's stopping or what's preventing the
machine from running, and like I said, it,

363
00:23:51.300 --> 00:23:57.140
<v Speaker 1>it goes facility by facility in certain
cases, the problem lies in the equipment.

364
00:23:57.829 --> 00:24:03.180
<v Speaker 1>In certain cases it runs, uh, it, it lies
in the way it is being operated, right?

365
00:24:03.229 --> 00:24:08.229
<v Speaker 1>So like I mentioned, if the operator
doesn't load, for example, the cases for the

366
00:24:08.229 --> 00:24:12.900
<v Speaker 1>case backer to, you know, encase the
product and ship them to the palletizer, well,

367
00:24:12.989 --> 00:24:17.670
<v Speaker 1>you need to create better, I would say,
uh, systems for your people to make sure

368
00:24:17.670 --> 00:24:18.510
<v Speaker 1>that happens, right?

369
00:24:18.550 --> 00:24:22.339
<v Speaker 1>So there's gonna be a lot of different
examples how it is leveraged, uh, to get

370
00:24:22.339 --> 00:24:23.390
<v Speaker 1>tangible results.

371
00:24:25.020 --> 00:24:28.109
<v Niall Sullivan>Yeah, and maybe you could sort of
summarize some of, some of that a little bit in

372
00:24:28.109 --> 00:24:32.060
<v Niall Sullivan>terms of some of the key, you know, is
there sort of common themes which, you know,

373
00:24:32.589 --> 00:24:36.790
<v Niall Sullivan>which have led to success, you know, that
across those different examples, if that

374
00:24:36.790 --> 00:24:40.170
<v Niall Sullivan>makes sense, just to a you out and dive
into them a little bit.

375
00:24:40.630 --> 00:24:46.030
<v Speaker 1>Yeah, so, so, so what leads to success, I
would say like number one, have a good

376
00:24:46.030 --> 00:24:47.790
<v Speaker 1>mindset when it comes to data.

377
00:24:48.260 --> 00:24:53.180
<v Speaker 1>I, you know, like I said, I do a lot of
plant assessments, and I almost always can

378
00:24:53.180 --> 00:24:59.290
<v Speaker 1>feel when the team is on one side is
excited to see more insights and information so

379
00:24:59.290 --> 00:25:00.699
<v Speaker 1>that they can make changes, right?

380
00:25:00.739 --> 00:25:07.300
<v Speaker 1>So basically, the team is very uh CI
focused, so continuous improvement focused, but

381
00:25:07.300 --> 00:25:08.130
<v Speaker 1>lacks the information.

382
00:25:08.530 --> 00:25:10.689
<v Speaker 1>From the plant floor to make certain
decisions, right?

383
00:25:10.729 --> 00:25:15.250
<v Speaker 1>They simply, they don't know how well the,
the performance, uh, or how, how poorly

384
00:25:15.250 --> 00:25:16.130
<v Speaker 1>the performance was.

385
00:25:16.459 --> 00:25:20.729
<v Speaker 1>On the other side, right, for teams that
are unsuccessful, um, you know, a lot of

386
00:25:20.729 --> 00:25:25.969
<v Speaker 1>data gets questioned, whether you come
from the plant floor or the executive side.

387
00:25:26.290 --> 00:25:28.250
<v Speaker 1>The reality is a lot of that work.

388
00:25:28.359 --> 00:25:35.079
<v Speaker 1>Is fairly complex, so a lot of teams, uh,
simply give up too quickly before they get

389
00:25:35.079 --> 00:25:40.550
<v Speaker 1>to a state where the data is reliable and
like I said, I spent many, uh, months,

390
00:25:40.640 --> 00:25:46.479
<v Speaker 1>even years going to plant floors, sitting
next to the machines, understanding what

391
00:25:46.479 --> 00:25:51.670
<v Speaker 1>kind of information we can extract so that
it actually is meaningful for that

392
00:25:51.670 --> 00:25:51.839
<v Speaker 1>specific team.

393
00:25:51.920 --> 00:25:52.640
<v Speaker 1>So I think that.

394
00:25:52.930 --> 00:25:58.270
<v Speaker 1>You know, having the approach of we're
going to take this time to learn what we can

395
00:25:58.650 --> 00:26:03.530
<v Speaker 1>to again have maybe this iterative
feedback loop where, you know, in this cycle

396
00:26:03.530 --> 00:26:08.569
<v Speaker 1>we've done our best, but maybe we have
some inconsistencies versus the the data that

397
00:26:08.569 --> 00:26:09.589
<v Speaker 1>we would like to see.

398
00:26:09.729 --> 00:26:10.750
<v Speaker 1>Let's iterate again.

399
00:26:11.015 --> 00:26:14.334
<v Speaker 1>Iterrate again and slowly but surely you
will see those gains.

400
00:26:14.415 --> 00:26:18.614
<v Speaker 1>So I, I would say that that is by far the
main success factor is sort of the

401
00:26:18.614 --> 00:26:23.334
<v Speaker 1>attitude the team has towards being uh
data driven.

402
00:26:23.645 --> 00:26:28.875
<v Speaker 1>Number 2, and uh, and of course there's
going to be a lot of fairly old facilities,

403
00:26:29.405 --> 00:26:35.194
<v Speaker 1>um, so when you start your audit or
assessment of the facility.

404
00:26:35.500 --> 00:26:41.910
<v Speaker 1>Um, it is very easy to get discouraged by,
by the price tag when the facility has

405
00:26:41.910 --> 00:26:43.849
<v Speaker 1>been neglected for decades.

406
00:26:44.189 --> 00:26:49.209
<v Speaker 1>And again, to give you a tangible example,
um, I have been to a couple of facilities

407
00:26:49.359 --> 00:26:54.589
<v Speaker 1>as early as last year where they have the
entire architecture on.

408
00:26:55.030 --> 00:26:59.030
<v Speaker 1>Um, you know, it's PLC 5s, so in North
America, a lot of Rockwell equipment, but

409
00:26:59.030 --> 00:27:06.020
<v Speaker 1>it's PLC 5s on data highway plus protocols
using RSU 32, uh, skater

410
00:27:06.020 --> 00:27:11.859
<v Speaker 1>systems and running servers and, uh, you
know, PCs basically for some of those

411
00:27:11.859 --> 00:27:14.989
<v Speaker 1>applications as far back as Windows NT.

412
00:27:15.900 --> 00:27:22.109
<v Speaker 1>And so of course when you know the
manufacturer is presented with a strategic plan

413
00:27:22.109 --> 00:27:27.869
<v Speaker 1>of action for that specific facility
versus a facility that is a little bit more

414
00:27:27.869 --> 00:27:33.030
<v Speaker 1>modern, there's quite a few steps that you
need to take before you can extract and

415
00:27:33.030 --> 00:27:34.670
<v Speaker 1>use any of that information.

416
00:27:35.229 --> 00:27:39.219
<v Speaker 1>Right, and, and again, we can get into the
complexities of, of getting data out of,

417
00:27:39.270 --> 00:27:42.439
<v Speaker 1>uh, you know, PLCs older than you and I.

418
00:27:42.750 --> 00:27:45.430
<v Speaker 1>Uh, it is obviously possible, but it's
very expensive.

419
00:27:45.510 --> 00:27:50.660
<v Speaker 1>So usually you need to go through a number
of steps to modernize not only the

420
00:27:50.660 --> 00:27:53.469
<v Speaker 1>control system, but also the architecture,
the networks.

421
00:27:53.834 --> 00:27:59.834
<v Speaker 1>Your server architecture before you even
get to collect any information in any

422
00:27:59.834 --> 00:28:05.724
<v Speaker 1>meaningful way and so I think that is sort
of also the other benchmark of success or

423
00:28:05.724 --> 00:28:07.454
<v Speaker 1>failure that I have seen in facilities,
right?

424
00:28:07.525 --> 00:28:13.785
<v Speaker 1>They simply see this very large, um, I
would say technical debt, uh, type of a bill

425
00:28:13.785 --> 00:28:17.055
<v Speaker 1>and they get discouraged from going down
the data path.

426
00:28:18.349 --> 00:28:18.819
<v Niall Sullivan>Yeah.

427
00:28:19.069 --> 00:28:19.699
<v Niall Sullivan>No, that makes sense.

428
00:28:19.750 --> 00:28:21.790
<v Niall Sullivan>I guess it can be quite overwhelming.

429
00:28:21.900 --> 00:28:24.349
<v Niall Sullivan>And I guess a lot of it, a lot of it has
to be done sort of step by step as well,

430
00:28:24.430 --> 00:28:24.630
<v Niall Sullivan>right?

431
00:28:24.750 --> 00:28:28.119
<v Niall Sullivan>It's not, you know, to, to stop it from
being necessarily that overwhelming.

432
00:28:28.180 --> 00:28:32.229
<v Niall Sullivan>You could put the foundations in place,
build on top of that, and then my next

433
00:28:32.229 --> 00:28:36.489
<v Niall Sullivan>question was actually going to be towards
where AI and machine learning then sits

434
00:28:36.709 --> 00:28:38.290
<v Niall Sullivan>amongst everything we've talked about so
far.

435
00:28:38.589 --> 00:28:38.709
<v Niall Sullivan>Yeah.

436
00:28:39.719 --> 00:28:44.489
<v Speaker 1>So, so look, I guess like to finish the, I
guess to answer your earlier comment and

437
00:28:44.489 --> 00:28:49.569
<v Speaker 1>the previous train of thought, right, is
um a lot of that work needs to be done in

438
00:28:49.569 --> 00:28:54.170
<v Speaker 1>sequence, exactly as you, as you said it,
you cannot skip some of those steps, and

439
00:28:54.170 --> 00:28:59.290
<v Speaker 1>more so, you know, everyone would like for
that work to be done over, again, plants

440
00:28:59.290 --> 00:29:04.290
<v Speaker 1>have shutdown periods, right, so everyone
would like for that work to be done within

441
00:29:04.290 --> 00:29:04.910
<v Speaker 1>a weekend.

442
00:29:05.420 --> 00:29:09.750
<v Speaker 1>Come in, you know, retrofit all the PLCs
and servers, everything is good to go.

443
00:29:10.150 --> 00:29:15.430
<v Speaker 1>The reality is that you, you still need
that physical labor component where you're

444
00:29:15.430 --> 00:29:16.089
<v Speaker 1>actually.

445
00:29:16.560 --> 00:29:21.369
<v Speaker 1>Obviously managing a team of electricians
that will touch a lot of those systems and

446
00:29:21.369 --> 00:29:25.849
<v Speaker 1>then you start getting into, well, you
know, this system talks to this system via

447
00:29:25.849 --> 00:29:30.369
<v Speaker 1>this specific server, so now you're
starting to touch so many different areas that

448
00:29:30.369 --> 00:29:36.849
<v Speaker 1>it becomes almost impossible to uh
piecemeal it together over, you know, many, many

449
00:29:36.849 --> 00:29:37.969
<v Speaker 1>different initiatives.

450
00:29:38.430 --> 00:29:42.699
<v Speaker 1>So where does AI and machine learning come
into all of this?

451
00:29:42.949 --> 00:29:44.810
<v Speaker 1>Well, I, I do have a few thoughts.

452
00:29:45.150 --> 00:29:52.150
<v Speaker 1>So I think it's, it is fairly good for
knowledgeable engineers that do have access,

453
00:29:52.229 --> 00:29:56.469
<v Speaker 1>or I would say that have spent quite a few
years on the plant floor where you can

454
00:29:56.469 --> 00:30:01.030
<v Speaker 1>query of a specific problem and you can
generally get a good answer.

455
00:30:01.479 --> 00:30:06.410
<v Speaker 1>Um, and this is maybe we also want to
separate sort of machine learning and LLMs,

456
00:30:06.420 --> 00:30:09.949
<v Speaker 1>which is, uh, I guess what a lot of people
are discussing.

457
00:30:10.170 --> 00:30:16.920
<v Speaker 1>I think that there's still a challenge in
getting very accurate answers from the

458
00:30:16.969 --> 00:30:20.849
<v Speaker 1>Current state of LLMs in the industrial
automation space, right?

459
00:30:20.890 --> 00:30:26.160
<v Speaker 1>And what I mean by that is if we look at
the software industry, if we look at the,

460
00:30:26.439 --> 00:30:31.880
<v Speaker 1>you know, software as a service
development space, there's been just countless not

461
00:30:31.880 --> 00:30:37.770
<v Speaker 1>only white papers, but also very solid
websites with, uh, like stack overflow, I

462
00:30:37.770 --> 00:30:42.310
<v Speaker 1>guess with tutorials on how to program,
how to utilize data, how to.

463
00:30:42.609 --> 00:30:48.739
<v Speaker 1>Um, you know, create something in a
variety of different languages, and I would say

464
00:30:48.739 --> 00:30:54.660
<v Speaker 1>that, you know, JavaScript, Python, uh,
anything that's front-end, HTML, CSS is

465
00:30:54.660 --> 00:30:58.500
<v Speaker 1>extremely well documented in our space
that is manufacturing.

466
00:30:58.579 --> 00:31:02.900
<v Speaker 1>If we talk about using AI and machine
learning for development of some of these

467
00:31:02.900 --> 00:31:08.900
<v Speaker 1>systems, it becomes quite tricky because
number 1, there's very little

468
00:31:08.900 --> 00:31:10.010
<v Speaker 1>documentation.

469
00:31:10.420 --> 00:31:11.900
<v Speaker 1>There is 2.

470
00:31:12.250 --> 00:31:16.020
<v Speaker 1>Uh, companies are generally very secretive
with, uh, what they develop.

471
00:31:16.060 --> 00:31:20.380
<v Speaker 1>It becomes to an extent their IP, so
there's just not enough information being

472
00:31:20.380 --> 00:31:22.510
<v Speaker 1>shared for AI to be useful on that site.

473
00:31:22.979 --> 00:31:27.339
<v Speaker 1>But where AI, like I said, where AI does
come in is if you're an experienced

474
00:31:27.339 --> 00:31:32.359
<v Speaker 1>engineer and you're looking to query or
understand maybe the state of certain

475
00:31:32.660 --> 00:31:36.760
<v Speaker 1>hardware or processes, I think it's a,
it's a really good tool.

476
00:31:37.099 --> 00:31:38.000
<v Speaker 1>I've also.

477
00:31:38.760 --> 00:31:43.969
<v Speaker 1>I've done quite a few of initiatives on
the cybersecurity side and again maybe to

478
00:31:43.969 --> 00:31:48.369
<v Speaker 1>take a step back so when you do an
assessment there's going to be a lot of pressure

479
00:31:48.369 --> 00:31:54.130
<v Speaker 1>to understand sort of the networks and the
server architecture, and that's a result

480
00:31:54.130 --> 00:31:58.609
<v Speaker 1>of some of the regulations that we've seen
in the European Union that are coming to

481
00:31:58.609 --> 00:31:59.369
<v Speaker 1>North America.

482
00:31:59.680 --> 00:32:04.410
<v Speaker 1>So a lot of plants are also looking to
modernize their, um, you know, like I said,

483
00:32:04.689 --> 00:32:05.540
<v Speaker 1>network infrastructure.

484
00:32:05.630 --> 00:32:11.170
<v Speaker 1>So AI is quite good at, hey, we have this
inventory list of different assets we know

485
00:32:11.170 --> 00:32:15.579
<v Speaker 1>that that is the current state of our uh
infrastructure networks.

486
00:32:15.810 --> 00:32:21.689
<v Speaker 1>We can now plug that into AI and allow it
to basically find all the loose ends and

487
00:32:21.689 --> 00:32:22.530
<v Speaker 1>prioritize.

488
00:32:22.983 --> 00:32:27.583
<v Speaker 1>Some of those tasks and equipment, right,
so to give you a tangible example, if you

489
00:32:27.583 --> 00:32:34.302
<v Speaker 1>have a Cisco switch of a model that's been
obsolete by 10 years, usually

490
00:32:34.302 --> 00:32:39.133
<v Speaker 1>Cisco will have some kind of a PDF or
migration guide that will tell you, well, to

491
00:32:39.133 --> 00:32:43.812
<v Speaker 1>move from that switch to, you know, a
switch on the Meraki platform as an example,

492
00:32:44.072 --> 00:32:45.223
<v Speaker 1>here are the steps you need to take.

493
00:32:45.635 --> 00:32:50.595
<v Speaker 1>A human or for an engineer, you will have
to manually do that research in in most

494
00:32:50.595 --> 00:32:56.436
<v Speaker 1>cases, whereas AI can scan through a lot
of those documents and recommend changes

495
00:32:56.436 --> 00:32:58.005
<v Speaker 1>for the manufacturer to follow, right?

496
00:32:58.036 --> 00:33:04.436
<v Speaker 1>So you're going to shorten a lot of your,
uh, sort of project times by utilizing

497
00:33:04.436 --> 00:33:09.475
<v Speaker 1>LLMs in their current state to do a lot of
that legwork and research in the

498
00:33:09.475 --> 00:33:10.956
<v Speaker 1>industrial automation space.

499
00:33:11.316 --> 00:33:14.956
<v Speaker 1>There's, there's a few other, you know,
use cases, but happy to, uh, happy to

500
00:33:14.956 --> 00:33:15.395
<v Speaker 1>expand.

501
00:33:17.050 --> 00:33:18.449
<v Niall Sullivan>No, exactly, exactly.

502
00:33:18.609 --> 00:33:22.890
<v Niall Sullivan>I think, and do you see, I mean, the
people, you know, the organizations you speak

503
00:33:22.890 --> 00:33:26.729
<v Niall Sullivan>to, I mean, what's their view on AI first
of all, and again, I know, generalized

504
00:33:26.729 --> 00:33:31.270
<v Niall Sullivan>question, different, different views, but,
you know, are most sort of embracing it,

505
00:33:31.290 --> 00:33:34.930
<v Niall Sullivan>or are some, you know, cautious about it,
or, you know, what's.

506
00:33:35.060 --> 00:33:37.359
<v Niall Sullivan>The general sort of feeling for that from
your perspective.

507
00:33:37.699 --> 00:33:37.819
<v Niall Sullivan>So,

508
00:33:38.020 --> 00:33:41.579
<v Speaker 1>so look, I guess we need to maybe split
that a little bit.

509
00:33:41.699 --> 00:33:47.339
<v Speaker 1>So almost every large organization has
rolled out a flavor of a of a co-pilot,

510
00:33:47.420 --> 00:33:47.540
<v Speaker 1>right?

511
00:33:47.780 --> 00:33:52.140
<v Speaker 1>A lot of them are in Microsoft, so it's
going to be a co-pilot license for pretty

512
00:33:52.140 --> 00:33:55.099
<v Speaker 1>much everybody at the organization.

513
00:33:55.500 --> 00:33:59.660
<v Speaker 1>How it is used, of course, is the, is the
big question, and what kind of tools they

514
00:33:59.660 --> 00:34:02.300
<v Speaker 1>use for specifically manufacturing is the
big question.

515
00:34:02.760 --> 00:34:07.329
<v Speaker 1>Um, I think there's, there's no doubt in
most people's minds that AI can write,

516
00:34:07.410 --> 00:34:12.050
<v Speaker 1>let's say, a better email, can pick up
tonality within an email, can help you, you

517
00:34:12.050 --> 00:34:18.399
<v Speaker 1>know, maybe do sales outreach is probably
better in certain cases in, in marketing,

518
00:34:18.530 --> 00:34:18.699
<v Speaker 1>right?

519
00:34:18.800 --> 00:34:24.689
<v Speaker 1>And again, when I say it's better, it's
usually better than someone with very little

520
00:34:24.689 --> 00:34:29.209
<v Speaker 1>experience, right, but probably struggles,
uh, to compete with someone who has a lot

521
00:34:29.209 --> 00:34:30.979
<v Speaker 1>of experience, it just becomes a tool.

522
00:34:31.270 --> 00:34:36.659
<v Speaker 1>Um, in the industrial automation sense,
again, I've seen engineers get access, like

523
00:34:36.659 --> 00:34:41.100
<v Speaker 1>I've said, to either co-pilot or it could
be Gemini or it could be chat GPT from

524
00:34:41.100 --> 00:34:47.060
<v Speaker 1>their organization, and of course they
will query, um, using the information that

525
00:34:47.060 --> 00:34:48.399
<v Speaker 1>they have from the plant floor.

526
00:34:48.669 --> 00:34:52.860
<v Speaker 1>Um, again, to give you a very basic
example, hey, I have this specific fault code on

527
00:34:52.860 --> 00:34:53.479
<v Speaker 1>this machine.

528
00:34:53.969 --> 00:34:57.239
<v Speaker 1>What can I do to remediate that uh that
problem?

529
00:34:57.639 --> 00:35:00.449
<v Speaker 1>Um, my experience has been, like I said, a
little bit mixed.

530
00:35:00.570 --> 00:35:05.929
<v Speaker 1>I would say that the senior engineers,
when they get a false positive, right, so AI

531
00:35:05.929 --> 00:35:11.129
<v Speaker 1>will confidently tell you, here's what you
should be doing, they will take a moment

532
00:35:11.129 --> 00:35:16.129
<v Speaker 1>and reflect on the output and basically
say like, yes, this is, this is what I'm

533
00:35:16.129 --> 00:35:20.889
<v Speaker 1>gonna do, or maybe this is not right, I
need to prompt further, whereas more junior

534
00:35:20.889 --> 00:35:25.489
<v Speaker 1>engineers don't have that sense of, of
systems yet, so it is quite difficult for

535
00:35:25.489 --> 00:35:26.850
<v Speaker 1>them to draw that line.

536
00:35:27.280 --> 00:35:32.320
<v Speaker 1>Um, when it comes to actual plant floor
data, there's quite a few groups who are

537
00:35:32.320 --> 00:35:38.330
<v Speaker 1>trying to, um, I would say they're less
end users, they're more again SASS-based

538
00:35:38.330 --> 00:35:43.600
<v Speaker 1>companies in our space who are trying to
again draw insights based on their

539
00:35:43.600 --> 00:35:44.020
<v Speaker 1>information.

540
00:35:44.679 --> 00:35:51.320
<v Speaker 1>Um, my current opinion is that number one,
it is very difficult

541
00:35:51.320 --> 00:35:55.919
<v Speaker 1>to get tangible insights using AI.

542
00:35:56.379 --> 00:36:00.669
<v Speaker 1>Uh, from the raw plant floor data, so
there's gonna be a lot of, again, we talked

543
00:36:00.669 --> 00:36:05.149
<v Speaker 1>about this, a lot of legwork that needs to
be done before the data is in a form that

544
00:36:05.149 --> 00:36:12.070
<v Speaker 1>makes sense, uh, but also number 2, almost
every manufacturer is extremely cautious.

545
00:36:12.479 --> 00:36:16.449
<v Speaker 1>Um, you know, because again, we're not
dealing with a, with a web application in

546
00:36:16.449 --> 00:36:19.620
<v Speaker 1>this, this case, we're dealing with
physical machines.

547
00:36:19.969 --> 00:36:25.250
<v Speaker 1>So when you give insights to make changes
on the plant floor, uh, you need to make

548
00:36:25.250 --> 00:36:29.050
<v Speaker 1>sure that validation or at least like
specific guard rails are in place.

549
00:36:29.409 --> 00:36:33.330
<v Speaker 1>So there's, there are pilots, there are
companies who are trying to.

550
00:36:33.659 --> 00:36:39.159
<v Speaker 1>Um, I would say R&amp;D, some of the
tools, um, engineers will themselves, like I said,

551
00:36:39.270 --> 00:36:43.919
<v Speaker 1>query and put that data like, hey, I have
this, this line OEE, uh, for these

552
00:36:43.919 --> 00:36:44.110
<v Speaker 1>machines.

553
00:36:44.199 --> 00:36:49.600
<v Speaker 1>What do you recommend, um, but I've not
seen, at least I've not witnessed yet, um,

554
00:36:49.719 --> 00:36:55.679
<v Speaker 1>kind of true ROI proven initiatives that
have been like documented or I guess like

555
00:36:55.679 --> 00:36:56.699
<v Speaker 1>more explicitly.

556
00:36:57.060 --> 00:37:02.360
<v Speaker 1>Explained and to, to be honest with you, I
would assume that the top organizations

557
00:37:02.580 --> 00:37:08.459
<v Speaker 1>in the world probably are doing a lot more
R&amp;D uh and are simply not, uh, you know,

558
00:37:08.620 --> 00:37:14.219
<v Speaker 1>disclosing what has been done or what
hasn't worked, um, so I, I am very curious on

559
00:37:14.219 --> 00:37:17.840
<v Speaker 1>that side there haven't been that many,
uh, white papers published yet.

560
00:37:18.729 --> 00:37:19.370
<v Niall Sullivan>No, exactly.

561
00:37:19.479 --> 00:37:22.830
<v Niall Sullivan>And I think, and I, I think the general
message is there's a lot more to come, and

562
00:37:22.830 --> 00:37:27.330
<v Niall Sullivan>things are changing, Conte, we'll talk in
6 months' time and, you know, it'll be a

563
00:37:27.330 --> 00:37:30.050
<v Niall Sullivan>completely different picture then, of
course, we have to acknowledge.

564
00:37:30.169 --> 00:37:36.550
<v Niall Sullivan>But, um, but no, as we, as we, um, I guess
we come towards the end, um, it's been,

565
00:37:37.010 --> 00:37:39.649
<v Niall Sullivan>yeah, really, really great to sort of pick
your mind on this.

566
00:37:39.699 --> 00:37:44.050
<v Niall Sullivan>Like I said, I think there's about 34
other episodes we could, we could talk about

567
00:37:44.370 --> 00:37:46.889
<v Niall Sullivan>and go into more detail, which I'd love to
do, um.

568
00:37:47.379 --> 00:37:52.250
<v Niall Sullivan>Um, in the future, but I guess just to
round off our sort of discussion today, um,

569
00:37:52.459 --> 00:37:56.260
<v Niall Sullivan>lads, and it's the usual end of the
podcast for regular listeners, it's.

570
00:37:57.050 --> 00:37:59.330
<v Niall Sullivan>You know, what does the future look like?

571
00:37:59.489 --> 00:38:01.770
<v Niall Sullivan>You know, what can we say about the future
industrial data?

572
00:38:01.850 --> 00:38:03.090
<v Niall Sullivan>Where, where's the next horizon?

573
00:38:03.169 --> 00:38:06.689
<v Niall Sullivan>AI, machine learning, LLMs, exactly, you
know, we all know that.

574
00:38:06.810 --> 00:38:10.649
<v Niall Sullivan>There's a, maybe aside from that, um, but
I don't want to put words into your mouth,

575
00:38:10.770 --> 00:38:12.510
<v Niall Sullivan>so maybe I should just leave you to
answer.

576
00:38:13.260 --> 00:38:16.419
<v Speaker 1>Yeah, that, that is, that is the million
dollar question.

577
00:38:16.580 --> 00:38:22.610
<v Speaker 1>So I, like, again, I've had a few
conversations with groups that are pioneering, uh,

578
00:38:22.620 --> 00:38:24.139
<v Speaker 1>lights out manufacturing, right?

579
00:38:24.219 --> 00:38:27.919
<v Speaker 1>And I've always been a believer in that
concept.

580
00:38:28.179 --> 00:38:32.219
<v Speaker 1>And lights out manufacture, I guess if, if
any of the listeners or viewers are not

581
00:38:32.219 --> 00:38:37.100
<v Speaker 1>aware, basically, it is the concept of
having absolutely no human intervention.

582
00:38:37.375 --> 00:38:39.274
<v Speaker 1>Within a manufacturing facility.

583
00:38:39.574 --> 00:38:42.334
<v Speaker 1>I believe it is still very challenging.

584
00:38:42.455 --> 00:38:49.375
<v Speaker 1>I think it is very diff difficult, uh, but
I truly hope that we, as again, as not

585
00:38:49.375 --> 00:38:54.574
<v Speaker 1>necessarily humanity, right, but maybe as
like industry leaders are striving to make

586
00:38:54.574 --> 00:39:00.054
<v Speaker 1>plants better, um, in terms of operating
as efficiently as possible from an

587
00:39:00.054 --> 00:39:01.195
<v Speaker 1>automation standpoint.

588
00:39:01.639 --> 00:39:07.360
<v Speaker 1>And um we can obviously discuss the the
different markets, but I believe that in

589
00:39:07.360 --> 00:39:13.659
<v Speaker 1>order to compete in a general sense, Uh,
with, uh, the generally higher cost of

590
00:39:13.659 --> 00:39:19.739
<v Speaker 1>labor, we need to automate more, so I
think that with the rise or I guess the

591
00:39:19.739 --> 00:39:25.260
<v Speaker 1>decrease in cost of automation again for a
variety of factors, we're going to

592
00:39:25.260 --> 00:39:31.580
<v Speaker 1>continue to see plants pushing higher and
higher the barrier towards uh lights out

593
00:39:31.580 --> 00:39:32.379
<v Speaker 1>manufacturing.

594
00:39:32.760 --> 00:39:35.280
<v Speaker 1>I, I don't believe that we will ever
achieve it.

595
00:39:35.360 --> 00:39:40.000
<v Speaker 1>I think it's still to an extent like an
asymptote right, where the cost gets

596
00:39:40.000 --> 00:39:45.719
<v Speaker 1>prohibitively or exponentially higher the
closer we get to a complete lights out

597
00:39:45.719 --> 00:39:51.199
<v Speaker 1>manufacturing, but I do believe that uh
groups will continue to get closer and

598
00:39:51.199 --> 00:39:52.479
<v Speaker 1>closer to that barrier.

599
00:39:54.699 --> 00:39:58.939
<v Niall Sullivan>Oh fantastic, and it, and it sort of look,
and you know, rounds off our chat today

600
00:39:58.939 --> 00:40:03.080
<v Niall Sullivan>nicely and actually points to a, to again
a lot of future episodes and future

601
00:40:03.379 --> 00:40:04.419
<v Niall Sullivan>discussion points we could.

602
00:40:04.800 --> 00:40:08.639
<v Niall Sullivan>Go into, but, um, but no, for today, lads,
it's been a real pleasure to speak to

603
00:40:08.639 --> 00:40:08.909
<v Niall Sullivan>you.

604
00:40:09.199 --> 00:40:14.000
<v Niall Sullivan>This has been recorded, I can confirm, so
that we will be hearing this episode, the

605
00:40:14.000 --> 00:40:18.060
<v Niall Sullivan>world out there will be listening to this
episode, so I'm really pleased you, um,

606
00:40:18.070 --> 00:40:19.800
<v Niall Sullivan>you came back to re-record.

607
00:40:19.919 --> 00:40:20.780
<v Niall Sullivan>We have done a better job.

608
00:40:21.080 --> 00:40:25.840
<v Niall Sullivan>I've, I've got a feeling that we've done a
better job than last time, um, but no,

609
00:40:25.879 --> 00:40:28.580
<v Niall Sullivan>it's been a real pleasure and look forward
to having you on again hopefully.

610
00:40:29.280 --> 00:40:31.000
<v Speaker 1>Absolutely, thank you so much for having
me.

611
00:40:31.110 --> 00:40:32.060
<v Speaker 1>I really appreciate it.

612
00:40:33.020 --> 00:40:37.350
<v Niall Sullivan>Oh, of course, sorry, one thing I forgot,
oh, yeah, because obviously I'd like, you

613
00:40:37.350 --> 00:40:41.550
<v Niall Sullivan>know, people be fascinate what you've
discussed today, and where can they find out

614
00:40:41.550 --> 00:40:44.209
<v Niall Sullivan>more about you and what you're, you're
doing?

615
00:40:44.830 --> 00:40:48.330
<v Speaker 1>I would say the easiest place to reach me
is uh LinkedIn.

616
00:40:48.639 --> 00:40:53.530
<v Speaker 1>Um, I do have my profile open, so if you
want to send me a message, have a

617
00:40:53.620 --> 00:40:56.790
<v Speaker 1>conversation around manufacturing,
industrial automation, happy to.

618
00:40:57.110 --> 00:40:59.260
<v Speaker 1>Answer any and all questions.

619
00:40:59.590 --> 00:41:04.699
<v Speaker 1>Um, I do have my own website which is
joltech.com where you can find a bit more, uh,

620
00:41:04.709 --> 00:41:08.330
<v Speaker 1>about myself, some of the projects, some
of the initiatives, the things that I'm

621
00:41:08.709 --> 00:41:09.310
<v Speaker 1>working on.

622
00:41:09.429 --> 00:41:13.540
<v Speaker 1>So, I'm happy to connect with everyone and
like I said, have a conversation around,

623
00:41:13.550 --> 00:41:15.510
<v Speaker 1>uh, manufacturing and industrial
automation.

624
00:41:16.570 --> 00:41:17.110
<v Niall Sullivan>Fantastic.

625
00:41:17.250 --> 00:41:20.530
<v Niall Sullivan>So yeah, we'll make sure those links are
in the, in the show notes as well for

626
00:41:20.530 --> 00:41:25.159
<v Niall Sullivan>people, so um, but yes, thank you again
lads, and thank you everyone out there,

627
00:41:25.169 --> 00:41:29.689
<v Niall Sullivan>wherever you are um around the world um
for listening to this episode and we'll see

628
00:41:29.689 --> 00:41:30.449
<v Niall Sullivan>you on the next one.

629
00:41:30.610 --> 00:41:31.449
<v Niall Sullivan>Thank you very much.

630
00:41:31.729 --> 00:41:33.189
<v Speaker 1>Awesome, thank you so much everyone.

631
00:41:35.370 --> 00:41:40.330
<v Speaker 2>Please like and subscribe on all major
podcast channels and find out more about

632
00:41:40.330 --> 00:41:43.709
<v Speaker 2>Sensei predictive maintenance at
Siemens.com.
