WEBVTT
Language: en-US

1
00:00:00.129 --> 00:00:04.949
<v Speaker 1>One final point to your question is we've
got far more success cases now than we had

2
00:00:04.949 --> 00:00:10.449
<v Speaker 1>234 years ago because of how many
different types of assets we monitor, how many

3
00:00:10.449 --> 00:00:14.729
<v Speaker 1>different types of industry we're now
working in, um, which is still, you know,

4
00:00:14.859 --> 00:00:21.170
<v Speaker 1>it's, it's been many for a long time, but
now we start to, to really, um, really get

5
00:00:21.170 --> 00:00:23.430
<v Speaker 1>deeply involved in, in different types of
assets.

6
00:00:24.520 --> 00:00:29.719
<v Speaker 2>Welcome to the trend detection podcast
powered by Siemens, and now your host, Nel

7
00:00:29.719 --> 00:00:30.239
<v Speaker 2>Sullivan.

8
00:00:32.340 --> 00:00:36.330
<v Speaker 3>Hello and welcome to the latest episode of
the Trend detection podcast.

9
00:00:36.950 --> 00:00:42.110
<v Speaker 3>Um, I'm really pleased to welcome back Tom
to the podcast, who's been on, I don't

10
00:00:42.110 --> 00:00:44.830
<v Speaker 3>know how many it's been now, Tom, but, um,
it's a pleasure to have you back.

11
00:00:44.950 --> 00:00:45.529
<v Speaker 3>Welcome back.

12
00:00:45.669 --> 00:00:46.869
<v Speaker 3>How are you, how are you doing?

13
00:00:47.229 --> 00:00:47.790
<v Speaker 1>Thank you, Noel.

14
00:00:47.909 --> 00:00:49.130
<v Speaker 1>Yeah, pleasure to be here.

15
00:00:49.310 --> 00:00:52.630
<v Speaker 1>I think this is probably our 6th or 7th,
something along, along that line.

16
00:00:54.139 --> 00:00:55.500
<v Speaker 3>Yeah, and this one's gonna be the most
memorable.

17
00:00:55.540 --> 00:00:56.419
<v Speaker 3>I can, I can feel it.

18
00:00:59.099 --> 00:00:59.439
<v Speaker 3>Exactly.

19
00:00:59.659 --> 00:01:04.519
<v Speaker 3>I mean, today, today, yeah, today's a
really cool, um, topic actually, um, and it's,

20
00:01:04.620 --> 00:01:08.610
<v Speaker 3>it's really at the heart of the podcast
actually, cos my, my, um, when we launched

21
00:01:08.610 --> 00:01:13.180
<v Speaker 3>this podcast however many years ago, it's
all about sort of capturing the insights

22
00:01:13.180 --> 00:01:17.279
<v Speaker 3>of all fantastic colleagues within Vince
Sensei, now Siemens, um.

23
00:01:17.849 --> 00:01:20.489
<v Speaker 3>You know, you guys have all the knowledge,
you speak to customers every day, all

24
00:01:20.489 --> 00:01:24.370
<v Speaker 3>these different conversations, and it's
basically, I want to share some of that

25
00:01:24.370 --> 00:01:28.449
<v Speaker 3>insight, or, a lot of that insight with
the world, um, and we do that anyway across

26
00:01:28.449 --> 00:01:32.730
<v Speaker 3>all of our episodes, hopefully, but, um,
for this episode, we're, we're sort of

27
00:01:32.730 --> 00:01:34.290
<v Speaker 3>digging into that a lot more.

28
00:01:34.410 --> 00:01:38.290
<v Speaker 3>We're actually thinking exactly what is
affecting the customer in the field, what

29
00:01:38.290 --> 00:01:41.370
<v Speaker 3>are their thought process, what are their,
their challenges, and it should always be

30
00:01:41.370 --> 00:01:44.449
<v Speaker 3>around the customer as well, um, of
course, um.

31
00:01:45.199 --> 00:01:49.519
<v Speaker 3>So yeah, so I guess to open the
conversation, um, let's start with those common

32
00:01:49.519 --> 00:01:50.519
<v Speaker 3>challenges customers face.

33
00:01:50.599 --> 00:01:53.120
<v Speaker 3>What, what are customers saying to you at
the moment, Tom?

34
00:01:53.209 --> 00:01:55.260
<v Speaker 3>What, what are the big challenges they're
facing?

35
00:01:55.879 --> 00:01:59.839
<v Speaker 1>Well, this is an interesting question
because, you know, in terms of what my job is,

36
00:01:59.959 --> 00:02:04.230
<v Speaker 1>it's really to break down for customers
what it means, how it can impact your

37
00:02:04.230 --> 00:02:06.000
<v Speaker 1>maintenance, how it can impact your
production.

38
00:02:06.889 --> 00:02:11.259
<v Speaker 1>And then to talk about this now on a
podcast is brilliant because it helps me get,

39
00:02:11.380 --> 00:02:15.360
<v Speaker 1>get the stage to talk about how many
buzzwords there are, how many different

40
00:02:15.899 --> 00:02:20.110
<v Speaker 1>confusing elements there are to this, but
actually at the crux of it, it's, is the

41
00:02:20.110 --> 00:02:21.679
<v Speaker 1>machine doing what the machine should be
doing?

42
00:02:22.179 --> 00:02:24.630
<v Speaker 1>Is the process outputting what it should
be?

43
00:02:24.740 --> 00:02:27.139
<v Speaker 1>Are you getting lots of downtime or lots
of over maintenance issues?

44
00:02:28.940 --> 00:02:33.580
<v Speaker 1>I think quite often the challenge becomes
you get too wrapped up in, in, in the

45
00:02:33.580 --> 00:02:36.979
<v Speaker 1>complexities of it and you lose sight of,
of what you're actually trying to achieve.

46
00:02:37.100 --> 00:02:41.460
<v Speaker 1>So the first thing I would typically say
is that you, you just look at the data

47
00:02:41.460 --> 00:02:45.929
<v Speaker 1>you've got, you look at what, what gaps
you've got and then really try and

48
00:02:45.929 --> 00:02:49.899
<v Speaker 1>understand what exactly are you trying to
achieve and that's the first step in any

49
00:02:49.899 --> 00:02:50.899
<v Speaker 1>part of these processes.

50
00:02:53.820 --> 00:02:57.789
<v Speaker 3>But in I guess in terms of the challenges
though, what, what are sort of customers

51
00:02:57.789 --> 00:03:01.300
<v Speaker 3>really, you know, saying to you, you know,
when you first have these initial sort of

52
00:03:01.300 --> 00:03:03.449
<v Speaker 3>conversations, what, what are the things
that are really sort of, you know,

53
00:03:03.869 --> 00:03:07.990
<v Speaker 1>I think the first, the first challenge to,
to that point, the first challenge is

54
00:03:07.990 --> 00:03:12.820
<v Speaker 1>often that can't possibly be real, you
know, that you've got a piece of software

55
00:03:12.820 --> 00:03:16.130
<v Speaker 1>that can learn my asset in 2 to 5 days
normal operation.

56
00:03:16.770 --> 00:03:22.330
<v Speaker 1>It can basically understand what the asset
should do effectively on its own with a

57
00:03:22.330 --> 00:03:27.250
<v Speaker 1>few prompts and the ability to, to have
parameters set at the right sensitivities

58
00:03:27.250 --> 00:03:28.070
<v Speaker 1>and so forth.

59
00:03:28.649 --> 00:03:31.009
<v Speaker 1>And then from there, it, it has user
input.

60
00:03:31.210 --> 00:03:35.729
<v Speaker 1>Every time something gets changed or
something gets fixed, it will incorporate that

61
00:03:35.729 --> 00:03:36.750
<v Speaker 1>piece of information.

62
00:03:37.169 --> 00:03:39.149
<v Speaker 1>It, it all sounds too good to be true.

63
00:03:39.210 --> 00:03:43.449
<v Speaker 1>I think that challenge, the, the ability
to understand that and see it for yourself

64
00:03:43.449 --> 00:03:45.809
<v Speaker 1>is, is the biggest hurdle that we face.

65
00:03:46.350 --> 00:03:51.070
<v Speaker 1>I think selling a product that sounds like
I mentioned it too good to be true is

66
00:03:51.070 --> 00:03:54.490
<v Speaker 1>probably the biggest difficulty I think
to, to what we do.

67
00:03:58.380 --> 00:04:01.649
<v Speaker 3>And, uh, and it's, yeah, and it's, it's
interesting.

68
00:04:01.699 --> 00:04:05.529
<v Speaker 3>I mean, we always, we always talk about on
here about, um, you know, the dialogue

69
00:04:05.529 --> 00:04:08.539
<v Speaker 3>with the customer and it's, you know, you
know, you look at sort of vendor customer

70
00:04:08.539 --> 00:04:10.580
<v Speaker 3>relationships, so it really is a
partnership.

71
00:04:10.690 --> 00:04:13.160
<v Speaker 3>I know it can be a bit of a cliche
sometimes as well.

72
00:04:13.630 --> 00:04:17.899
<v Speaker 3>But I mean, I guess you've seen, uh, have
you seen examples of where the feedback

73
00:04:17.899 --> 00:04:22.230
<v Speaker 3>for customers has been sort of, you know,
directly influenced Sensii, I think we

74
00:04:22.230 --> 00:04:24.329
<v Speaker 3>could probably talk about specifically
today, right?

75
00:04:24.950 --> 00:04:25.589
<v Speaker 1>Yeah, definitely.

76
00:04:25.670 --> 00:04:29.649
<v Speaker 1>I think when you've got different
graphics, different methods of showing that data,

77
00:04:30.029 --> 00:04:33.549
<v Speaker 1>um, different interfaces that the customer
wants to see, you know, you could have

78
00:04:33.549 --> 00:04:38.269
<v Speaker 1>the smartest algorithms in the world, but
if you can't then interpret that

79
00:04:38.269 --> 00:04:40.609
<v Speaker 1>information in an interesting way or a
simple way.

80
00:04:41.089 --> 00:04:44.049
<v Speaker 1>You know, having a traffic light system to
start with is, is something that

81
00:04:44.049 --> 00:04:47.970
<v Speaker 1>customers love having, so you can see, is
it in a status of red or orange or yellow.

82
00:04:48.540 --> 00:04:49.640
<v Speaker 1>That's very simple.

83
00:04:49.739 --> 00:04:53.380
<v Speaker 1>It's something that we use pretty much
unanimously across industry for different

84
00:04:53.380 --> 00:04:58.500
<v Speaker 1>software, so something that aligns with
that is standard, but then having reports is

85
00:04:58.500 --> 00:05:02.369
<v Speaker 1>a pretty new feature of Sensei, so all of
this stuff can be shown to you in a

86
00:05:02.369 --> 00:05:05.679
<v Speaker 1>report, you can see different areas of the
plant, different types of machine,

87
00:05:06.019 --> 00:05:10.940
<v Speaker 1>different fleets of assets, all sort of
bundled together in whatever kind of report

88
00:05:10.940 --> 00:05:17.820
<v Speaker 1>you want, plus cases, open cases, closed
cases, um, you can chat to copilot.

89
00:05:18.660 --> 00:05:22.260
<v Speaker 1>All these things have been driven by what
customers want to see, so this is the

90
00:05:22.260 --> 00:05:23.600
<v Speaker 1>direct feedback that you mention.

91
00:05:24.559 --> 00:05:28.730
<v Speaker 1>And I think that's crucial cos it shows
customers that we'll work together on this.

92
00:05:29.170 --> 00:05:33.529
<v Speaker 1>um, you know, typically the way many of
our customers would shout in a certain

93
00:05:33.529 --> 00:05:33.989
<v Speaker 1>direction.

94
00:05:34.459 --> 00:05:36.839
<v Speaker 1>That's the direction that we would then
engineer the product.

95
00:05:37.100 --> 00:05:41.640
<v Speaker 1>So that's how SensorR has evolved into
something that's very user-friendly, very,

96
00:05:41.940 --> 00:05:46.500
<v Speaker 1>um, well suited to industrial
environments, and that could be in pharmaceuticals, it

97
00:05:46.500 --> 00:05:47.440
<v Speaker 1>could be in steel.

98
00:05:47.779 --> 00:05:51.579
<v Speaker 1>These environments are different, but
obviously maintenance at the core is, is

99
00:05:51.579 --> 00:05:52.799
<v Speaker 1>effectively the same process.

100
00:05:52.940 --> 00:05:54.940
<v Speaker 1>Is this part degrading?

101
00:05:55.059 --> 00:05:56.179
<v Speaker 1>Does it need to be changed?

102
00:05:56.420 --> 00:05:57.420
<v Speaker 1>Has it been changed?

103
00:05:57.890 --> 00:06:02.459
<v Speaker 1>And then making sure as well that that
integrates with existing workflows, so that's

104
00:06:02.459 --> 00:06:04.880
<v Speaker 1>another key part of, of what Sensi is very
good at.

105
00:06:06.059 --> 00:06:10.579
<v Speaker 3>And I guess, again bringing it back to
your specific role, Tom, I guess how do you

106
00:06:10.579 --> 00:06:15.339
<v Speaker 3>sort of interface with um with, with the
product team and making sure you know, some

107
00:06:15.339 --> 00:06:18.839
<v Speaker 3>of these communicate, you know, some of
these, some of these feedback's fed between

108
00:06:19.339 --> 00:06:21.359
<v Speaker 3>both um both sort of departments.

109
00:06:21.899 --> 00:06:26.019
<v Speaker 1>So one of the latest features we've had is
the ability, I say latest, it's been

110
00:06:26.019 --> 00:06:30.690
<v Speaker 1>around for months already, is to have,
have spectra be visible in Sensei.

111
00:06:30.739 --> 00:06:33.640
<v Speaker 1>You can, you can make very good use of
data that's come to you.

112
00:06:34.140 --> 00:06:38.940
<v Speaker 1>At 10,000 Hz frequency or, or 46,000 Hz
frequency, whatever it might be, depending

113
00:06:38.940 --> 00:06:39.619
<v Speaker 1>on sensors.

114
00:06:40.399 --> 00:06:43.970
<v Speaker 1>We can, we can ingest that, we can do very
clever things with it, you can see the

115
00:06:43.970 --> 00:06:46.429
<v Speaker 1>FFT of that, so the Fast Fourier
transform.

116
00:06:47.549 --> 00:06:49.029
<v Speaker 1>This is something that customers wanted.

117
00:06:49.839 --> 00:06:54.769
<v Speaker 1>Oftentimes you have vibration analysis
that's done as a, a manual measurement, maybe

118
00:06:54.769 --> 00:06:58.809
<v Speaker 1>it's a monthly check, someone will come in
and do that inspection, they'll come and,

119
00:06:58.890 --> 00:07:02.690
<v Speaker 1>and, and kind of do all these measurements
and leave, leave and come back to you

120
00:07:02.690 --> 00:07:06.410
<v Speaker 1>with a report of which bearings are
failing, which shafts are starting to oscillate

121
00:07:06.410 --> 00:07:10.440
<v Speaker 1>more than they should and effectively give
you a, a strategy, a plan that you should

122
00:07:10.440 --> 00:07:11.049
<v Speaker 1>now follow.

123
00:07:12.279 --> 00:07:16.640
<v Speaker 1>Now one of the things customers wanted was
to have that in the same piece of

124
00:07:16.640 --> 00:07:21.640
<v Speaker 1>software that's telling them of tank level
of, you know, motor vibration, uh you

125
00:07:21.640 --> 00:07:24.940
<v Speaker 1>know, generically from a, you know, from a
memSense or something like that.

126
00:07:25.739 --> 00:07:30.459
<v Speaker 1>And now the ability to, to pull that back
in, and my role then is to feed that right

127
00:07:30.459 --> 00:07:33.700
<v Speaker 1>the way through, but customers want to see
more of that, they want us to develop

128
00:07:33.700 --> 00:07:39.739
<v Speaker 1>that tool, um, and this is really where,
where we're going because if you can start

129
00:07:39.739 --> 00:07:44.200
<v Speaker 1>to take in manual measurements, things
like oil samples and all the rest of it,

130
00:07:44.380 --> 00:07:49.359
<v Speaker 1>which are from complex sensors online that
would typically have been offline.

131
00:07:49.890 --> 00:07:56.320
<v Speaker 1>You can start to completely remove manual
checks that are, are to do, you know, oil

132
00:07:56.320 --> 00:08:01.250
<v Speaker 1>contamination or to do, you know, things
like spectra analysis and feed all of that

133
00:08:01.250 --> 00:08:06.649
<v Speaker 1>stuff in, which is, which is complex
information into a, into a, a piece of software

134
00:08:06.649 --> 00:08:07.269
<v Speaker 1>effectively.

135
00:08:07.730 --> 00:08:10.390
<v Speaker 1>And to do that is, is really difficult.

136
00:08:10.739 --> 00:08:15.049
<v Speaker 1>And to build a product around all of that
stuff is also quite difficult because it's

137
00:08:15.049 --> 00:08:19.649
<v Speaker 1>lots and lots of different variables all
culminating together, as we've said in the

138
00:08:19.649 --> 00:08:22.029
<v Speaker 1>past, plus PDF documents and so forth.

139
00:08:22.809 --> 00:08:26.929
<v Speaker 1>So, I, I think quite often I, I end up
being the voice of the customer because it's

140
00:08:26.929 --> 00:08:32.250
<v Speaker 1>my role to explain the latest
conversations we've had, questions about can the

141
00:08:32.250 --> 00:08:37.409
<v Speaker 1>software do X, Y, and Z, and just making
sure that comes back to the, to the team

142
00:08:37.409 --> 00:08:38.150
<v Speaker 1>developing the product.

143
00:08:38.690 --> 00:08:41.770
<v Speaker 1>And that's part of the, part of the way
we've developed such a good product because.

144
00:08:42.559 --> 00:08:47.130
<v Speaker 1>It shows us what the industry wants to
have, what it, what it wishes it could do

145
00:08:47.130 --> 00:08:50.469
<v Speaker 1>already, and, and that's the direction
we've gone in, you know.

146
00:08:51.330 --> 00:08:55.929
<v Speaker 1>So in a very long answer to your question,
it's, it's important that we capture

147
00:08:55.929 --> 00:09:00.640
<v Speaker 1>those feedbacks, so we, we don't just
spend 6 months developing something and then

148
00:09:00.640 --> 00:09:01.460
<v Speaker 1>deploy it.

149
00:09:01.780 --> 00:09:05.580
<v Speaker 1>I think, I don't know how many years ago
that would have been, but maybe 5, 10 years

150
00:09:05.580 --> 00:09:06.710
<v Speaker 1>ago, that was the method.

151
00:09:07.450 --> 00:09:10.989
<v Speaker 1>And there's very few gaps within that for
a feedback cycle.

152
00:09:11.700 --> 00:09:15.419
<v Speaker 1>So the goal now is to constantly keep
understanding, are we going in the right

153
00:09:15.419 --> 00:09:15.799
<v Speaker 1>direction?

154
00:09:16.340 --> 00:09:19.880
<v Speaker 1>Are we, are we iterating this in the
direction that customers want us to?

155
00:09:20.140 --> 00:09:23.979
<v Speaker 1>Is it, is it a big customer or a small
customer or a, uh, you know, generically

156
00:09:23.979 --> 00:09:28.440
<v Speaker 1>across the board, many, many customers
want the same feature or functionality.

157
00:09:29.150 --> 00:09:32.830
<v Speaker 1>And you have to listen to customers, I
think that's really, really important and we

158
00:09:32.830 --> 00:09:33.729
<v Speaker 1>do that really well.

159
00:09:35.289 --> 00:09:37.440
<v Speaker 3>And, yeah, and of course, yeah, I
completely agree.

160
00:09:37.489 --> 00:09:39.950
<v Speaker 3>I mean, listen, listening to customers is
key.

161
00:09:40.049 --> 00:09:44.239
<v Speaker 3>Um, I guess 11 other way to look at it as
well though is when you've got lots of

162
00:09:44.239 --> 00:09:45.929
<v Speaker 3>customers asking for lots of different
functionality.

163
00:09:45.969 --> 00:09:49.609
<v Speaker 3>I know it's more of a product team, you
know, prioritization in terms of the roadmap

164
00:09:49.609 --> 00:09:50.669
<v Speaker 3>and etc.

165
00:09:50.849 --> 00:09:55.450
<v Speaker 3>but I guess from in, again, specifically
to your role, Tom, how you sort of manage

166
00:09:55.450 --> 00:09:58.260
<v Speaker 3>expectations and find, I mean, the, it's
in your title, right?

167
00:09:58.340 --> 00:10:01.469
<v Speaker 3>Solutions engineering, how you find
solutions to things that.

168
00:10:01.989 --> 00:10:04.549
<v Speaker 3>Might not be possible now in the app, but
it could be in the future or it might not

169
00:10:04.549 --> 00:10:07.510
<v Speaker 3>be possible in the future because other
priorities, etc.

170
00:10:09.150 --> 00:10:12.909
<v Speaker 1>Yeah, and I think we, we've definitely
touched on that in the past, and I think

171
00:10:12.909 --> 00:10:15.059
<v Speaker 1>that's really the crucial part of it.

172
00:10:15.390 --> 00:10:16.590
<v Speaker 1>No, I think that's a great question.

173
00:10:17.450 --> 00:10:22.369
<v Speaker 1>So what we typically would say is, is
common is things like MTVF, so meantime

174
00:10:22.369 --> 00:10:23.210
<v Speaker 1>between failures.

175
00:10:24.400 --> 00:10:28.309
<v Speaker 1>But I think more and more as we go on now
we start to see customers looking at

176
00:10:28.679 --> 00:10:32.549
<v Speaker 1>things like unplanned versus planned
maintenance ratios, how much time do they spend

177
00:10:33.250 --> 00:10:38.409
<v Speaker 1>maybe fixing things that shouldn't be
breaking down, so very reactive or or kind of

178
00:10:38.409 --> 00:10:39.270
<v Speaker 1>doing too much.

179
00:10:39.909 --> 00:10:45.229
<v Speaker 1>And then another emerging one is how
effective are technicians and maintenance

180
00:10:45.229 --> 00:10:46.690
<v Speaker 1>engineers when things break down.

181
00:10:47.070 --> 00:10:51.260
<v Speaker 1>So, I think some of, some of the
unexpected metrics that, that are starting to

182
00:10:51.260 --> 00:10:56.169
<v Speaker 1>emerge are things like, OK, it's taken us
this long to determine there's a problem

183
00:10:56.739 --> 00:11:00.590
<v Speaker 1>because Sensize helped us really speed
that process up to, to troubleshooting a

184
00:11:00.590 --> 00:11:00.989
<v Speaker 1>problem.

185
00:11:01.760 --> 00:11:05.299
<v Speaker 1>And then actually how fast can we, can we
understand what's going wrong.

186
00:11:06.880 --> 00:11:13.080
<v Speaker 1>So you don't just have a, an increased,
you know, um an improved process to

187
00:11:13.080 --> 00:11:16.679
<v Speaker 1>understand what's going wrong and when and
capturing it before you otherwise would

188
00:11:16.679 --> 00:11:21.039
<v Speaker 1>have, but because of all the knowledge
capture, you're now able to determine much

189
00:11:21.039 --> 00:11:24.539
<v Speaker 1>faster uh or much more quickly what's
actually going wrong.

190
00:11:25.590 --> 00:11:27.179
<v Speaker 1>Uh, and what you need to do to fix it.

191
00:11:27.469 --> 00:11:31.630
<v Speaker 1>So if you needed to get a spare part
ordered and, and into stock, that's what you

192
00:11:31.630 --> 00:11:32.289
<v Speaker 1>can now do.

193
00:11:32.440 --> 00:11:38.590
<v Speaker 1>Um, and again this goes down the road of,
you know, that sounds almost too good to

194
00:11:38.590 --> 00:11:39.210
<v Speaker 1>be true.

195
00:11:39.510 --> 00:11:41.809
<v Speaker 1>I think we've, we've talked about that a
lot in the past.

196
00:11:43.280 --> 00:11:47.789
<v Speaker 3>No, exactly, yeah, um, a victim of its own
success in a, in a way, right?

197
00:11:47.859 --> 00:11:52.880
<v Speaker 3>Um, and that, and, yeah, and I mean, now
we've got, you know, look, we've got so

198
00:11:52.880 --> 00:11:54.679
<v Speaker 3>many great, um, public case studies.

199
00:11:54.719 --> 00:11:58.679
<v Speaker 3>I mean, Bluescope Steel, I always mention
Bluescope Steel, um, Saxon Mills in

200
00:11:58.679 --> 00:11:59.679
<v Speaker 3>Germany as well.

201
00:11:59.880 --> 00:12:01.789
<v Speaker 3>Check those out on, on the website.

202
00:12:01.840 --> 00:12:06.229
<v Speaker 3>They are, they really are sort of
fascinating stories, great examples of, of what,

203
00:12:06.440 --> 00:12:08.200
<v Speaker 3>what's actually possible, um.

204
00:12:08.549 --> 00:12:12.380
<v Speaker 3>But I mean, I mean, you, you mentioned
there are a lot of different things, a lot of

205
00:12:12.380 --> 00:12:16.510
<v Speaker 3>different areas that predictive
maintenance can influence, but is there often sort

206
00:12:16.510 --> 00:12:20.950
<v Speaker 3>of misconceptions about what can be
achieved for predictive maintenance, or, but it

207
00:12:20.950 --> 00:12:24.270
<v Speaker 3>could be in terms of what could be
achieved or the timescales in which it can be

208
00:12:24.270 --> 00:12:24.659
<v Speaker 3>achieved.

209
00:12:24.830 --> 00:12:28.450
<v Speaker 3>Is there, Still varying expectations on
that level, would you say?

210
00:12:28.530 --> 00:12:33.489
<v Speaker 1>I would, I would love to say that we're
very much at the point of plug and play, and

211
00:12:33.489 --> 00:12:37.289
<v Speaker 1>you could just, you could just set some
sensors up or plug some data in and it, it

212
00:12:37.289 --> 00:12:38.979
<v Speaker 1>all just works effectively on its own.

213
00:12:39.969 --> 00:12:43.770
<v Speaker 1>Now because of the the the nuance, the
different asset types, the different

214
00:12:43.770 --> 00:12:47.210
<v Speaker 1>industries, I mean you know how many
different types of customers we're working

215
00:12:47.210 --> 00:12:47.510
<v Speaker 1>with.

216
00:12:48.330 --> 00:12:50.250
<v Speaker 1>And there's, there's differences across
the board.

217
00:12:50.330 --> 00:12:53.609
<v Speaker 1>There's different types of machine,
there's different data frequencies and all the

218
00:12:53.609 --> 00:12:54.369
<v Speaker 1>rest of it, so.

219
00:12:55.590 --> 00:13:00.030
<v Speaker 1>We have to first of all put a project
together that can factor that stuff in, and I

220
00:13:00.030 --> 00:13:04.450
<v Speaker 1>think customers more often than not are
happy to work with us on that scope phase

221
00:13:04.619 --> 00:13:08.630
<v Speaker 1>because at the end of it, you end up with
a project very quickly, you know, within

222
00:13:08.630 --> 00:13:12.510
<v Speaker 1>just a few weeks if we can get on site and
have a look at the machines or, or

223
00:13:12.510 --> 00:13:16.070
<v Speaker 1>someone else can take photographs and
really explain to us what's going wrong, how

224
00:13:16.070 --> 00:13:16.969
<v Speaker 1>the machines work.

225
00:13:17.989 --> 00:13:23.580
<v Speaker 1>As soon as we understand what the machines
do, what sensors are, are in uh in

226
00:13:23.580 --> 00:13:28.309
<v Speaker 1>position, what data is available, we can
build a project that's about as close to

227
00:13:28.309 --> 00:13:29.609
<v Speaker 1>plug and play as you can get.

228
00:13:30.559 --> 00:13:34.809
<v Speaker 1>And then from there we can deploy the
project, set it, um, running and do the

229
00:13:34.809 --> 00:13:39.150
<v Speaker 1>operate and refine part of our process to
really work together, um.

230
00:13:40.099 --> 00:13:46.539
<v Speaker 1>I think some of, some of the
misconceptions might also be that, that PDM eliminates

231
00:13:46.539 --> 00:13:47.359
<v Speaker 1>all failure.

232
00:13:48.099 --> 00:13:52.330
<v Speaker 1>Now I would always say until we remove
friction, which is, as far as I'm concerned,

233
00:13:52.369 --> 00:13:57.780
<v Speaker 1>impossible, we're always gonna get
mechanical degradation, so bearings are pretty

234
00:13:57.780 --> 00:14:00.340
<v Speaker 1>much the closest thing we get to
frictionless.

235
00:14:01.330 --> 00:14:04.460
<v Speaker 1>But still within that, they break down,
they degrade, they get hot.

236
00:14:04.719 --> 00:14:08.599
<v Speaker 1>You have to keep them lubricated, you
know, and there's also debris and all the rest

237
00:14:08.599 --> 00:14:09.400
<v Speaker 1>of it that gets in there.

238
00:14:09.479 --> 00:14:13.599
<v Speaker 1>They can be overloaded, they can be, uh,
warped, whatever it might be, these things

239
00:14:13.599 --> 00:14:14.559
<v Speaker 1>will degrade.

240
00:14:14.760 --> 00:14:16.880
<v Speaker 1>If you look after them, they last a lot
longer.

241
00:14:17.729 --> 00:14:21.539
<v Speaker 1>But they're still gonna have a, a
lifetime, they are still gonna need replacement at

242
00:14:21.539 --> 00:14:23.140
<v Speaker 1>some stage now.

243
00:14:23.869 --> 00:14:27.880
<v Speaker 1>If the bearing is still fine, every 6
months you don't need to change it, and in

244
00:14:27.880 --> 00:14:33.919
<v Speaker 1>some cases, if you need to open something,
get inside, uh, allow debris and, and

245
00:14:33.919 --> 00:14:38.539
<v Speaker 1>other contaminants to get in, you, you're
actually making the problem worse.

246
00:14:40.380 --> 00:14:44.419
<v Speaker 1>So having a system that's got sensors and
it tells you, you know, at exactly the

247
00:14:44.419 --> 00:14:48.809
<v Speaker 1>right time, the bearing now is coming
towards end of life, maybe based on all

248
00:14:48.809 --> 00:14:52.500
<v Speaker 1>telemetries and what we know about this
bearing, maybe you've got another month

249
00:14:52.500 --> 00:14:53.039
<v Speaker 1>left.

250
00:14:53.380 --> 00:14:56.140
<v Speaker 1>You can start to plan all of your
operations around that.

251
00:14:56.940 --> 00:15:01.909
<v Speaker 1>And I think Uh, maybe a misconception is
that that's now gonna, that's never gonna

252
00:15:01.909 --> 00:15:02.570
<v Speaker 1>be needed.

253
00:15:02.950 --> 00:15:06.309
<v Speaker 1>What we're doing is we're optimizing the
moment when it's needed.

254
00:15:06.469 --> 00:15:10.830
<v Speaker 1>So it, it, it comes down to really
forecasting and, and predicting.

255
00:15:10.950 --> 00:15:12.010
<v Speaker 1>That's the name of the product, right?

256
00:15:12.179 --> 00:15:16.830
<v Speaker 1>So it's predicting effectively when
something's gonna be needed, and that's based on

257
00:15:16.989 --> 00:15:19.770
<v Speaker 1>anomalies and trends and other metrics
from the system.

258
00:15:20.869 --> 00:15:25.270
<v Speaker 1>Um, I always tell customers it's not about
predicting everything, it's about

259
00:15:25.270 --> 00:15:26.989
<v Speaker 1>reducing that surprise element.

260
00:15:28.969 --> 00:15:32.270
<v Speaker 3>Exactly, and I, and I guess the other, the
other layer I'd maybe add into it as

261
00:15:32.270 --> 00:15:36.239
<v Speaker 3>well, because in it, especially when you
talk, talk about AI and, and gen AI as

262
00:15:36.239 --> 00:15:41.359
<v Speaker 3>well, it's, it's also, it's a, well, and
decision support tool is another phrase

263
00:15:41.359 --> 00:15:44.280
<v Speaker 3>that, that often comes up and it's a good
way to sort of describe things.

264
00:15:44.359 --> 00:15:47.820
<v Speaker 3>It's not, you know, the AI is not
replacing anyone, it's not being.

265
00:15:49.000 --> 00:15:52.880
<v Speaker 3>You know, replace this this exact moment
and takes the human decision out of it.

266
00:15:52.960 --> 00:15:56.359
<v Speaker 3>It, it's very important to emphasize the
human element of this.

267
00:15:56.400 --> 00:16:01.539
<v Speaker 3>It's advising humans to decide themselves
what they, what action they need to take,

268
00:16:01.640 --> 00:16:01.880
<v Speaker 3>right?

269
00:16:02.039 --> 00:16:04.200
<v Speaker 3>That's, that's what we're saying here as
well.

270
00:16:04.270 --> 00:16:05.830
<v Speaker 1>That's, that's another good misconception.

271
00:16:06.039 --> 00:16:07.299
<v Speaker 1>No, I, I completely agree.

272
00:16:08.130 --> 00:16:13.169
<v Speaker 1>And how often do we see it where if it's
got AI effectively it can take over and do

273
00:16:13.169 --> 00:16:13.950
<v Speaker 1>all these things?

274
00:16:14.609 --> 00:16:18.789
<v Speaker 1>Maybe one day, maybe, but I'm happy at the
minute to say we're not at that stage

275
00:16:18.969 --> 00:16:19.469
<v Speaker 1>just yet.

276
00:16:20.130 --> 00:16:25.169
<v Speaker 1>And where we currently are is having a
very, very clever piece of software, which I

277
00:16:25.169 --> 00:16:26.229
<v Speaker 1>think is ahead of the curve.

278
00:16:26.359 --> 00:16:30.409
<v Speaker 1>It's, it's definitely far, far removed
from a condition monitoring piece of software

279
00:16:30.409 --> 00:16:34.590
<v Speaker 1>that tells you, you know, you've reached
80%, therefore equals alert.

280
00:16:35.090 --> 00:16:37.750
<v Speaker 1>It's a, it's a very incredibly clever
system.

281
00:16:37.929 --> 00:16:41.250
<v Speaker 1>Uh, you know, I love working for
Sentenceive for that reason because this product is

282
00:16:41.250 --> 00:16:47.010
<v Speaker 1>so, so versatile and it's got the ability
to continuously learn stuff, so.

283
00:16:47.659 --> 00:16:52.859
<v Speaker 1>Maybe, maybe some of the, the
misconceptions are that it's fixed, and that product

284
00:16:52.859 --> 00:16:57.049
<v Speaker 1>is then just set up for that machine, but
it's, it's not the case, it, it learns and

285
00:16:57.049 --> 00:17:02.070
<v Speaker 1>develops and if the if the asset changes
or if you replace, If you, if you change

286
00:17:02.070 --> 00:17:05.930
<v Speaker 1>the bearings for example, from a, a, a
rubbish quality bearing to better quality,

287
00:17:06.390 --> 00:17:09.949
<v Speaker 1>you're gonna expect different, um,
patterns of vibration, different harmonic

288
00:17:09.949 --> 00:17:14.189
<v Speaker 1>signatures, and also a very different
lifespan, that bearing should last you quite a

289
00:17:14.189 --> 00:17:14.729
<v Speaker 1>lot longer.

290
00:17:15.560 --> 00:17:19.609
<v Speaker 1>And that's where as well you wanna make
sure customers understand, you know, that's

291
00:17:19.609 --> 00:17:24.329
<v Speaker 1>the same, um, bearing housing, it's the
same shaft, it's the same machine, but we're

292
00:17:24.329 --> 00:17:25.810
<v Speaker 1>gonna expect different results from that.

293
00:17:25.890 --> 00:17:30.530
<v Speaker 1>So we can, we can tell the system to
expect, uh, a different outcome, to, to perhaps

294
00:17:30.530 --> 00:17:36.369
<v Speaker 1>relearn something or to, um, factor in
spin speed of the shaft in addition to

295
00:17:36.369 --> 00:17:37.750
<v Speaker 1>temperatures and so forth.

296
00:17:38.250 --> 00:17:38.569
<v Speaker 1>So.

297
00:17:39.130 --> 00:17:43.969
<v Speaker 1>It's a very, very clever system, so making
sure that customers fully understand, um,

298
00:17:44.449 --> 00:17:49.569
<v Speaker 1>how, how intelligent it is and how we also
don't have to have a knowledge of that

299
00:17:49.569 --> 00:17:51.430
<v Speaker 1>machine prior to, to monitoring it.

300
00:17:52.030 --> 00:17:55.430
<v Speaker 1>Yeah, uh, often we get asked, you know,
I've got a big bucket of data, do you want

301
00:17:55.430 --> 00:17:56.150
<v Speaker 1>to see that first?

302
00:17:57.030 --> 00:18:02.349
<v Speaker 1>It's helpful, maybe in some cases we see
particular high spikes or, or deviations

303
00:18:02.349 --> 00:18:06.770
<v Speaker 1>away from baseline that could be
indicative of a failure, that's useful.

304
00:18:07.540 --> 00:18:12.449
<v Speaker 1>But equally, we don't necessarily need
that, we can, we can monitor a gearbox for

305
00:18:12.449 --> 00:18:17.030
<v Speaker 1>about a week, let's say, with a few
variables if it, if it has them, different

306
00:18:17.530 --> 00:18:21.079
<v Speaker 1>products might be produced on that
production line, we can factor that in as

307
00:18:21.079 --> 00:18:26.369
<v Speaker 1>context, but then from there we see, we
see a, a, a baseline, we see a, a

308
00:18:26.369 --> 00:18:30.770
<v Speaker 1>fingerprint is what we call it, and that's
something that I think is sometimes a

309
00:18:30.770 --> 00:18:33.829
<v Speaker 1>misconception, you know, how can you
possibly have a model for.

310
00:18:34.349 --> 00:18:37.329
<v Speaker 1>Um, all of my 100 different asset types.

311
00:18:38.079 --> 00:18:42.170
<v Speaker 1>Um, if you need to, you can speak to, like
you mentioned, Saxon Mill, Blue Scope

312
00:18:42.170 --> 00:18:46.810
<v Speaker 1>Steel, cust customers like this who have
many, many, many different asset types.

313
00:18:47.010 --> 00:18:50.869
<v Speaker 1>And the same is true in, in pharmaceutical
and automotive and food and beverage,

314
00:18:51.369 --> 00:18:53.329
<v Speaker 1>and, uh, it's nice now.

315
00:18:53.390 --> 00:18:58.170
<v Speaker 1>I think we have a lot of customers with,
with the, the, the use cases, with the case

316
00:18:58.170 --> 00:18:59.229
<v Speaker 1>studies that we've got.

317
00:18:59.770 --> 00:19:02.449
<v Speaker 1>Um, I'll leave it to you to point people
in those directions.

318
00:19:03.069 --> 00:19:04.750
<v Speaker 3>No, no, exactly, exactly.

319
00:19:04.910 --> 00:19:08.229
<v Speaker 3>And what, and what's interesting about
these different industries is there, and, and

320
00:19:08.229 --> 00:19:11.459
<v Speaker 3>I guess again, specifically to your role
in your, the conversations you have, Tom,

321
00:19:11.750 --> 00:19:16.500
<v Speaker 3>how do you draw together the different,
the different experiences, the different

322
00:19:16.500 --> 00:19:19.449
<v Speaker 3>conversations you have with customers from
farma, from food and beverage and.

323
00:19:20.530 --> 00:19:22.670
<v Speaker 3>Yeah, you know, and bring it into your day
to day role.

324
00:19:22.869 --> 00:19:25.709
<v Speaker 3>So, you know, you might think a food and
beverage customer doesn't have anything to

325
00:19:25.709 --> 00:19:29.099
<v Speaker 3>do with a, although an automotive
customer, but is there, is there things that you

326
00:19:29.099 --> 00:19:32.650
<v Speaker 3>could bring into conversations with
different customers in different industries?

327
00:19:33.109 --> 00:19:35.410
<v Speaker 1>The similarity is remarkable, I would say.

328
00:19:35.869 --> 00:19:39.380
<v Speaker 1>And sometimes you think, well, here's a
robot arm doing, doing something, just to

329
00:19:39.380 --> 00:19:40.729
<v Speaker 1>take one asset as an example.

330
00:19:41.880 --> 00:19:45.319
<v Speaker 1>And you might think that if it's doing
something in an automotive factory, it's,

331
00:19:45.380 --> 00:19:49.329
<v Speaker 1>it's very unique and specific to that, but
actually the patterns of behavior are,

332
00:19:49.400 --> 00:19:50.459
<v Speaker 1>are quite similar.

333
00:19:51.180 --> 00:19:55.739
<v Speaker 1>The maintenance that goes alongside that
is often basically the same.

334
00:19:56.439 --> 00:19:59.829
<v Speaker 1>You know, you still need to change things
as they degrade, you still need to keep

335
00:19:59.829 --> 00:20:03.140
<v Speaker 1>things clean, make sure you don't overload
a piece of equipment.

336
00:20:03.280 --> 00:20:07.599
<v Speaker 1>If you do, you know, the steps that you
take to mitigate that, to, to swap it out of

337
00:20:07.599 --> 00:20:11.680
<v Speaker 1>production at, at the right times, often
the lines are so busy that you can't just

338
00:20:11.680 --> 00:20:15.640
<v Speaker 1>do that change on the line, you have
replacement assets that could be swapped in and

339
00:20:15.640 --> 00:20:17.109
<v Speaker 1>out if, if necessary.

340
00:20:18.329 --> 00:20:22.689
<v Speaker 1>And it's nice to see customers when they
speak to each other um at different events

341
00:20:22.689 --> 00:20:26.439
<v Speaker 1>that we've had some of the, some of the
podcasts and and different uh webinars that

342
00:20:26.439 --> 00:20:27.030
<v Speaker 1>you've done.

343
00:20:27.770 --> 00:20:32.569
<v Speaker 1>I think are very good for bringing
different customers together who do actually

344
00:20:32.569 --> 00:20:36.089
<v Speaker 1>share the same uh the same experience um.

345
00:20:36.859 --> 00:20:40.229
<v Speaker 1>You know, I used to be working on
production lines, fixing them, making sure that

346
00:20:40.229 --> 00:20:41.750
<v Speaker 1>they, they don't break down.

347
00:20:42.109 --> 00:20:46.280
<v Speaker 1>I've worked in the hydraulic space and,
and seen how hydraulic lubrication systems

348
00:20:46.280 --> 00:20:51.489
<v Speaker 1>can break down and degrade and just small,
small elements of contamination or even,

349
00:20:51.699 --> 00:20:54.449
<v Speaker 1>you know, with hydraulic fluid, it's
things like getting water in the oil.

350
00:20:55.550 --> 00:21:00.089
<v Speaker 1>It's amazing how that's the same, you
know, the outcome of that in any industry

351
00:21:00.310 --> 00:21:04.869
<v Speaker 1>leads to the same, uh, degradation, the
same, the same sort of negative outcomes.

352
00:21:05.640 --> 00:21:11.569
<v Speaker 1>Um, I think one of the things we can talk
about is how does that then impact if

353
00:21:11.569 --> 00:21:17.089
<v Speaker 1>it's, if it's a short, short term thing or
a long term thing, so so how do you, how

354
00:21:17.089 --> 00:21:20.650
<v Speaker 1>do you react if it's something that's
gonna cause you a problem in the next week or

355
00:21:20.650 --> 00:21:25.219
<v Speaker 1>the next couple of months uh and what
would you typically monitor and equally if

356
00:21:25.219 --> 00:21:29.650
<v Speaker 1>it's something that, you know, oh that's
our, our largest, most expensive machine,

357
00:21:29.770 --> 00:21:32.569
<v Speaker 1>it basically never breaks down, right?

358
00:21:33.300 --> 00:21:36.410
<v Speaker 1>And that's where we can start to look at,
OK, what are the variables?

359
00:21:36.619 --> 00:21:41.260
<v Speaker 1>If it were to break down, what impact is
that gonna have on manufacturing these cars

360
00:21:41.260 --> 00:21:45.540
<v Speaker 1>or these tablets or, or this, you know,
this paint or whatever it might be.

361
00:21:46.770 --> 00:21:50.270
<v Speaker 1>And if you can start to see that, you
start to see, well, right, if you've got.

362
00:21:51.380 --> 00:21:56.300
<v Speaker 1>A machine, it could have that one
breakdown every year, but when it breaks down,

363
00:21:56.339 --> 00:22:00.250
<v Speaker 1>that costs you 6 weeks of, of operational
production.

364
00:22:00.660 --> 00:22:04.780
<v Speaker 1>That's complete line stoppage, it could be
plant shutdown, send everybody home.

365
00:22:05.739 --> 00:22:10.380
<v Speaker 1>Maybe you've got redundancy, maybe you
haven't, and these are all things that I have

366
00:22:10.380 --> 00:22:14.739
<v Speaker 1>to factor in when we do scope workshops to
make sure that we, we select the right

367
00:22:14.739 --> 00:22:15.319
<v Speaker 1>assets.

368
00:22:15.699 --> 00:22:21.250
<v Speaker 1>And also if the data quality is there, do
we need additional um IOT sensors like

369
00:22:21.250 --> 00:22:25.260
<v Speaker 1>vibration or current or something else
that might help us to really see a

370
00:22:25.260 --> 00:22:26.729
<v Speaker 1>fingerprint of, of those assets.

371
00:22:27.650 --> 00:22:32.719
<v Speaker 1>And that's what, that's what our role has
to be, we have to be the, the kind of.

372
00:22:33.430 --> 00:22:38.609
<v Speaker 1>The experienced maintenance engineer slash
IOT engineer slash reliability person

373
00:22:39.310 --> 00:22:44.109
<v Speaker 1>with a, with the ability to make sense of
this, all with the, with the business case

374
00:22:44.109 --> 00:22:49.790
<v Speaker 1>in mind, right, so we have to make sure
that all of this stuff is going to deliver

375
00:22:49.790 --> 00:22:50.449
<v Speaker 1>return on investment.

376
00:22:50.550 --> 00:22:55.510
<v Speaker 1>It's, it's gonna give you back what you
invest and far more and, and we see that in

377
00:22:55.510 --> 00:22:58.069
<v Speaker 1>our biggest customers where they've really
doubled down on it.

378
00:22:58.489 --> 00:23:02.410
<v Speaker 1>And now they have, you know, 10s and 10s
of thousands of assets on board, on, on

379
00:23:02.410 --> 00:23:03.530
<v Speaker 1>boarded with Sensei.

380
00:23:05.099 --> 00:23:08.510
<v Speaker 3>And if, and if we go back, you know, like
I said, to those initial scoping workshops

381
00:23:08.510 --> 00:23:12.380
<v Speaker 3>where conversations around which assets to
select and that, and that kind of thing,

382
00:23:12.550 --> 00:23:17.260
<v Speaker 3>I'm just interested to know, is there
often, um, early agreement on the types of

383
00:23:17.260 --> 00:23:20.489
<v Speaker 3>assets to monitor, you know, when you both
come into the room, both with your own.

384
00:23:21.189 --> 00:23:24.109
<v Speaker 3>You know, diff differing opinions and
different viewpoints on things, but you know,

385
00:23:24.270 --> 00:23:28.819
<v Speaker 3>I, I mean between, say yourself and, and
the customer, is there general agreement or

386
00:23:28.819 --> 00:23:32.989
<v Speaker 3>is there often a bit of a debate about, oh
no, we think this asset requires, you

387
00:23:32.989 --> 00:23:34.449
<v Speaker 3>know, monitoring versus this?

388
00:23:34.459 --> 00:23:38.689
<v Speaker 1>I love that question because that really
focuses on if we make chocolate.

389
00:23:39.920 --> 00:23:43.099
<v Speaker 1>Right, you've got all these different
assets that help you make chocolate, but then

390
00:23:43.479 --> 00:23:44.209
<v Speaker 1>what are the problems?

391
00:23:44.319 --> 00:23:48.599
<v Speaker 1>Like, often when you speak to customers,
when I speak to different people, you, you,

392
00:23:48.680 --> 00:23:53.180
<v Speaker 1>you see very quickly that they know the
main problem, they know the impact it has.

393
00:23:53.640 --> 00:23:56.640
<v Speaker 1>They just wish they knew the solution and
they've been maybe trying to find the

394
00:23:56.640 --> 00:24:00.380
<v Speaker 1>solution for a long time, whether it's
mechanical or perhaps over maintenance.

395
00:24:01.469 --> 00:24:07.530
<v Speaker 1>Um, getting a third party company to come
in and do various inspections or whatever.

396
00:24:08.510 --> 00:24:13.800
<v Speaker 1>And, and when it breaks down, you can
sometimes sense in the room, people think, oh

397
00:24:13.800 --> 00:24:16.380
<v Speaker 1>God, when that breaks down we're, we're
really in trouble.

398
00:24:17.579 --> 00:24:21.540
<v Speaker 1>And I think this is, this is what we have
to try and do first of all is understand

399
00:24:21.540 --> 00:24:23.160
<v Speaker 1>what pain points have customers got.

400
00:24:23.660 --> 00:24:27.579
<v Speaker 1>And that comes down to the kind of
questions that we ask, the, the, the way that you

401
00:24:27.579 --> 00:24:32.699
<v Speaker 1>can break down what's the thing here that
if we monitored it would have the biggest

402
00:24:32.699 --> 00:24:33.719
<v Speaker 1>transformational impact.

403
00:24:34.420 --> 00:24:37.459
<v Speaker 1>And that's what, that's what Sensei's for,
that's why Sensei is a part of the

404
00:24:37.459 --> 00:24:42.300
<v Speaker 1>Siemens portfolio because you couple that
together with a good edge system, some

405
00:24:42.300 --> 00:24:45.890
<v Speaker 1>good sensors, some good methods of
collecting data from a, from a Scada network.

406
00:24:47.099 --> 00:24:51.910
<v Speaker 1>And and pulling that through to a cloud
platform, maybe with the additional other

407
00:24:51.910 --> 00:24:55.050
<v Speaker 1>connections, so you might have wireless
sensors also feeding into that.

408
00:24:56.040 --> 00:25:02.410
<v Speaker 1>Um, you might have, uh, an integration to
CMMS, so an SAP solution or or IBM Maximo,

409
00:25:02.479 --> 00:25:04.099
<v Speaker 1>something like that, that, that
integrates.

410
00:25:05.140 --> 00:25:09.329
<v Speaker 1>And this is really where customers start
to break that down and, and they know what

411
00:25:09.380 --> 00:25:10.550
<v Speaker 1>knock-on effects that has.

412
00:25:10.750 --> 00:25:15.569
<v Speaker 1>So how does that impact production or what
kind of secondary damage would be caused,

413
00:25:15.790 --> 00:25:19.829
<v Speaker 1>what kind of scrappage would be, would,
would happen if, if this line stopped

414
00:25:19.829 --> 00:25:20.670
<v Speaker 1>mid-process?

415
00:25:20.750 --> 00:25:21.750
<v Speaker 1>Would you have to throw that away?

416
00:25:21.829 --> 00:25:24.250
<v Speaker 1>That's typically a problem from
pharmaceutical.

417
00:25:25.119 --> 00:25:30.300
<v Speaker 1>Um, and my advice would be to speak to us,
involve us, to chat about the machine,

418
00:25:30.599 --> 00:25:34.189
<v Speaker 1>how it breaks down, how often, how, when
have you tried to fix it, what have you

419
00:25:34.189 --> 00:25:34.780
<v Speaker 1>tried to do?

420
00:25:35.489 --> 00:25:40.410
<v Speaker 1>Um, and I think with our knowledge and our
experience, together with yours, you

421
00:25:40.410 --> 00:25:42.050
<v Speaker 1>know, this is to any customer.

422
00:25:43.000 --> 00:25:47.959
<v Speaker 1>Um, we can deploy the software to learn
the moments of, of prime machine health and

423
00:25:47.959 --> 00:25:52.160
<v Speaker 1>learn where it deviates, and that's the
canary in the mine, that's the early warning

424
00:25:52.160 --> 00:25:54.599
<v Speaker 1>system, um, that you wish you had.

425
00:25:54.660 --> 00:25:58.180
<v Speaker 1>So that removes again that element of
surprise.

426
00:25:59.619 --> 00:26:02.510
<v Speaker 3>And that's really interesting what you're
saying there, Tom, about how much detail

427
00:26:02.510 --> 00:26:05.979
<v Speaker 3>you go into the, into the asset, you know,
some of those examples, you know, what's

428
00:26:05.979 --> 00:26:08.030
<v Speaker 3>happened with it, what, what maintenance
has been done in it.

429
00:26:08.099 --> 00:26:12.430
<v Speaker 3>So you really go into that sort of level
of detail about when selecting assets.

430
00:26:12.589 --> 00:26:17.469
<v Speaker 1>Yes, yeah, it, we have to because
sometimes you might find the most expensive

431
00:26:17.469 --> 00:26:20.189
<v Speaker 1>machine that you think is the thing you
need to monitor.

432
00:26:20.839 --> 00:26:23.780
<v Speaker 1>Is actually not really a problem at all.

433
00:26:24.199 --> 00:26:29.000
<v Speaker 1>There's a conveyor sitting in the middle
of production that's only €2000 and that's

434
00:26:29.000 --> 00:26:33.839
<v Speaker 1>the real problem child of everything, and
it keeps breaking down and you maybe don't

435
00:26:33.839 --> 00:26:36.260
<v Speaker 1>have the full oversight of what that's
causing you.

436
00:26:36.390 --> 00:26:41.810
<v Speaker 1>Um, in some cases as well, you might find
the, the management say to the team,

437
00:26:42.319 --> 00:26:44.020
<v Speaker 1>everything good, you're keeping everything
running.

438
00:26:44.750 --> 00:26:49.869
<v Speaker 1>The answer could be yes, but as far as we
see, there's, there's no breakdowns that

439
00:26:49.869 --> 00:26:51.790
<v Speaker 1>really cause any significant problems.

440
00:26:52.750 --> 00:26:56.359
<v Speaker 1>But then you start to look through the
system, you look back through the history of

441
00:26:56.359 --> 00:27:00.099
<v Speaker 1>an asset, you say this motor has been
changed every 7 weeks.

442
00:27:00.800 --> 00:27:01.270
<v Speaker 1>Why?

443
00:27:01.599 --> 00:27:03.569
<v Speaker 1>Why are we changing this motor every 7
weeks?

444
00:27:03.670 --> 00:27:06.420
<v Speaker 1>It, it's, it should be lasting us at least
6 months.

445
00:27:06.839 --> 00:27:08.859
<v Speaker 1>You know, it's a, it's a pretty big piece
of kit.

446
00:27:09.859 --> 00:27:14.780
<v Speaker 1>And if you don't have that oversight, you
might not understand or maybe every time

447
00:27:14.780 --> 00:27:17.500
<v Speaker 1>it breaks, the job is just to fix it, just
to keep the line running.

448
00:27:17.540 --> 00:27:22.540
<v Speaker 1>If that's your job, you just, you do that
and that's, that's a really honorable job.

449
00:27:22.619 --> 00:27:25.819
<v Speaker 1>The goal is to keep manufacturing
chocolate or tablets or whatever it is.

450
00:27:27.030 --> 00:27:31.589
<v Speaker 1>But then you, you really have to break
down, are we doing stupid things that aren't

451
00:27:31.589 --> 00:27:31.949
<v Speaker 1>needed?

452
00:27:32.069 --> 00:27:36.150
<v Speaker 1>Is there something inherently misaligned
or is there something that's really

453
00:27:36.150 --> 00:27:37.430
<v Speaker 1>overstressing the system?

454
00:27:38.130 --> 00:27:41.119
<v Speaker 1>Um, and maybe something's been designed
wrong, right?

455
00:27:41.189 --> 00:27:45.270
<v Speaker 1>You might look at a part of the process
and, uh, a chain that's supposed to lift

456
00:27:45.270 --> 00:27:49.150
<v Speaker 1>something keeps stretching, and then
you've, you finally go through all the

457
00:27:49.150 --> 00:27:52.910
<v Speaker 1>calculations and someone designed it
wrong, and that chain is only half the

458
00:27:52.910 --> 00:27:55.790
<v Speaker 1>thickness it should be, and it keeps
degrading.

459
00:27:56.729 --> 00:27:59.849
<v Speaker 1>You know, we could monitor that all day
long, but if it's designed wrong, like

460
00:27:59.849 --> 00:28:04.660
<v Speaker 1>inherently there's a mechanical flaw
there, we need to also factor that in as well.

461
00:28:04.810 --> 00:28:07.839
<v Speaker 1>So any of the pre-sales team would start
to look at that.

462
00:28:07.969 --> 00:28:10.910
<v Speaker 1>We can start to assess that with, with
previous things we've seen.

463
00:28:12.469 --> 00:28:14.310
<v Speaker 1>And, and yeah, go into that detail.

464
00:28:14.390 --> 00:28:16.329
<v Speaker 1>I think that's, that's really crucial,
that's what we do.

465
00:28:17.569 --> 00:28:22.530
<v Speaker 3>Yeah, it's just interesting for me to know
as well, yeah, how, but you, you, yeah,

466
00:28:22.609 --> 00:28:25.609
<v Speaker 3>you've explained very well how, you know,
how crucial that is, yeah, really

467
00:28:25.609 --> 00:28:25.849
<v Speaker 3>interesting.

468
00:28:26.209 --> 00:28:27.849
<v Speaker 1>You're more than welcome to come on a skip
workshop whenever you want.

469
00:28:28.719 --> 00:28:30.650
<v Speaker 3>I know, I know, I know, I, I need to.

470
00:28:30.689 --> 00:28:35.050
<v Speaker 3>I think there was one, not too far away
from me recently I was going to attend, but

471
00:28:35.050 --> 00:28:39.209
<v Speaker 3>unfortunately, other things, other things
came up, but, um, definitely, definitely

472
00:28:39.209 --> 00:28:41.050
<v Speaker 3>in the future, definitely, um.

473
00:28:41.760 --> 00:28:45.319
<v Speaker 3>But, um, I guess as, as we sort of sort of
come towards the end, I wanted to sort of

474
00:28:45.319 --> 00:28:49.640
<v Speaker 3>finish on, um, usually we look at like,
you know, a summary of the, of what we're

475
00:28:49.640 --> 00:28:52.939
<v Speaker 3>talking about or key takeaways, but we it
sort of end it in a slightly different,

476
00:28:53.239 --> 00:28:56.660
<v Speaker 3>um, way and just sort of reflect on the
conversation because we're talking about

477
00:28:56.660 --> 00:28:59.760
<v Speaker 3>what, you know, what customers are talking
about, the customers you're talking to,

478
00:28:59.839 --> 00:29:01.699
<v Speaker 3>what do they really want for predicting
maintenance.

479
00:29:02.400 --> 00:29:04.260
<v Speaker 3>Um, I think this is quite an interesting
way to finish.

480
00:29:04.560 --> 00:29:06.760
<v Speaker 3>Um, sorry, I'm building it up quite a lot,
but, uh.

481
00:29:07.270 --> 00:29:11.109
<v Speaker 3>Um, but the, the, I'm just wondering in
terms of, we know how much the market's

482
00:29:11.109 --> 00:29:15.810
<v Speaker 3>changed over the past 234, you know, 5
years, you know, about Sisi, Siemens now for

483
00:29:16.010 --> 00:29:18.170
<v Speaker 3>what, 4 years now, and things have changed
massively.

484
00:29:18.630 --> 00:29:22.780
<v Speaker 3>But in terms of the conversations you're
having even a year ago, Tom, with

485
00:29:22.780 --> 00:29:28.750
<v Speaker 3>customers, how much have they changed from
a year ago to now or even further back to

486
00:29:28.750 --> 00:29:29.099
<v Speaker 3>now?

487
00:29:29.270 --> 00:29:31.250
<v Speaker 3>Um, I'm just your reflections on that.

488
00:29:32.260 --> 00:29:38.150
<v Speaker 1>I think Industry 4 Industry 4.0 is
starting to come to fruition.

489
00:29:38.300 --> 00:29:45.260
<v Speaker 1>I think the, the risk averse customer is
starting to really see, um, perhaps over

490
00:29:45.260 --> 00:29:49.459
<v Speaker 1>the fence at other companies, what, what
difference it's made, where they've made a

491
00:29:49.459 --> 00:29:53.939
<v Speaker 1>digital transformation and what's
possible, you know, you could do that wrong, but

492
00:29:53.939 --> 00:29:58.520
<v Speaker 1>equally you could do it right and you
could start to see real impact where different

493
00:29:58.699 --> 00:30:01.479
<v Speaker 1>pieces of software work together in a good
workflow.

494
00:30:01.969 --> 00:30:06.410
<v Speaker 1>You have good procurement processes, you
have good maintenance management processes

495
00:30:06.410 --> 00:30:07.189
<v Speaker 1>and all the rest of it.

496
00:30:08.510 --> 00:30:11.890
<v Speaker 1>And when you start to do that with a piece
of predictive maintenance in the middle,

497
00:30:12.630 --> 00:30:17.150
<v Speaker 1>especially where systems are already
digitalized, perhaps more than they were 1 year

498
00:30:17.150 --> 00:30:18.150
<v Speaker 1>ago or 2 years ago.

499
00:30:19.469 --> 00:30:24.859
<v Speaker 1>To your point, Noel, it, it gets easier
now to, to show, well this is Sensi, this is

500
00:30:24.859 --> 00:30:26.599
<v Speaker 1>how it could impact the maintenance.

501
00:30:26.699 --> 00:30:30.160
<v Speaker 1>In the same way that you've got this other
piece of software doing something else,

502
00:30:30.699 --> 00:30:35.890
<v Speaker 1>this is gonna be the watchdog that watches
over, um, you know, like a doctor

503
00:30:35.890 --> 00:30:38.359
<v Speaker 1>watching over all of your assets to make
sure they're all healthy.

504
00:30:38.920 --> 00:30:43.520
<v Speaker 1>To really know at the exact moment when
they're, when they're becoming unhealthy and

505
00:30:43.520 --> 00:30:48.839
<v Speaker 1>to alert you ahead of time uh what you
need to do and also where perhaps you're

506
00:30:48.839 --> 00:30:54.579
<v Speaker 1>doing too much maintenance, so I think how
it's changed is, Is it's getting easier,

507
00:30:55.040 --> 00:31:01.000
<v Speaker 1>the, the idea of digital transformation
is, is far more talked about, um, and I

508
00:31:01.000 --> 00:31:06.239
<v Speaker 1>think it's also making customers more
confident to step, to make that step into, OK,

509
00:31:06.319 --> 00:31:08.880
<v Speaker 1>I don't know how this is gonna work for my
production, but

510
00:31:08.880 --> 00:31:13.239
<v Speaker 1>I, you know, you've shown me all these
cases, we've spoken to customers who've had

511
00:31:13.239 --> 00:31:14.160
<v Speaker 1>previous successes.

512
00:31:15.930 --> 00:31:19.930
<v Speaker 1>Uh, and actually just one final point to
your question is we've got far more success

513
00:31:19.930 --> 00:31:25.849
<v Speaker 1>cases now than we had 234 years ago
because of how many different types of assets we

514
00:31:25.849 --> 00:31:29.150
<v Speaker 1>monitor, how many different types of
industry we're now working in.

515
00:31:29.739 --> 00:31:34.739
<v Speaker 1>Um, which is still, you know, it's, it's
been many for a long time, but now we start

516
00:31:34.739 --> 00:31:40.119
<v Speaker 1>to, to really, um, really get deeply
involved in, in different types of assets.

517
00:31:41.170 --> 00:31:46.180
<v Speaker 1>Um, Yeah, I'm interested to see where we
go next actually.

518
00:31:47.530 --> 00:31:52.300
<v Speaker 3>Yeah, and that's, yeah, and that's maybe
a, a cliffhanger to leave this, um, the,

519
00:31:52.459 --> 00:31:53.000
<v Speaker 3>this episode on.

520
00:31:53.180 --> 00:31:57.780
<v Speaker 3>We've talked, yeah, looked, um, a lot
about the current state of it, and that's

521
00:31:57.780 --> 00:32:00.140
<v Speaker 3>really interesting what you're saying
about Industry 4.0, because it's one of those

522
00:32:00.140 --> 00:32:04.459
<v Speaker 3>terms that's thrown around a lot that we
know in this, um, in this industry, and

523
00:32:04.459 --> 00:32:08.500
<v Speaker 3>it's always seems to be on the horizon,
but that's, that's the takeaway for me from

524
00:32:08.500 --> 00:32:12.280
<v Speaker 3>that, that you're seeing it now actually
here and now.

525
00:32:13.410 --> 00:32:16.300
<v Speaker 3>And in customers' hands and they're seeing
success on the back of it, which is

526
00:32:16.300 --> 00:32:17.729
<v Speaker 3>obviously what, what we want to see.

527
00:32:18.219 --> 00:32:20.619
<v Speaker 1>And it's the same as what we see at
exhibitions as well, isn't it, Noel?

528
00:32:20.660 --> 00:32:24.459
<v Speaker 1>We see the, the latest, greatest
technology, and you think, oh, that's, you know,

529
00:32:24.530 --> 00:32:27.599
<v Speaker 1>that's months, if not years away from
reality.

530
00:32:28.140 --> 00:32:32.500
<v Speaker 1>And one of my favorite things about, about
Sensei, I think we had the co-pilot at

531
00:32:32.500 --> 00:32:38.729
<v Speaker 1>Hanover Messa 2024, and within just a few
months after that, it was in customers'

532
00:32:38.729 --> 00:32:40.719
<v Speaker 1>hands, deployed as a piece of the
software.

533
00:32:41.270 --> 00:32:46.839
<v Speaker 1>Um, so we've had that in place now for
well over a year, um, being used, being tried

534
00:32:46.839 --> 00:32:48.500
<v Speaker 1>and tested, being improved.

535
00:32:49.079 --> 00:32:54.270
<v Speaker 1>Um, so I love the, the methods that we've
got as a, as a team at Sensei to come up

536
00:32:54.270 --> 00:32:56.680
<v Speaker 1>with something new and get it deployed
quickly.

537
00:32:56.800 --> 00:32:58.550
<v Speaker 1>Don't, don't wait to the perfect moment.

538
00:32:58.760 --> 00:33:01.459
<v Speaker 1>Just get it out there, get it monitoring
some assets.

539
00:33:02.170 --> 00:33:07.050
<v Speaker 1>Um, it can already do the job, but it's
now a case of, of how can we really make

540
00:33:07.050 --> 00:33:11.630
<v Speaker 1>that a powerful, um, sidekick, let's call
it, to, to maintenance engineers.

541
00:33:13.520 --> 00:33:14.979
<v Speaker 3>And what a lovely way to finish.

542
00:33:15.160 --> 00:33:17.040
<v Speaker 3>Um, thank you, Tom.

543
00:33:17.160 --> 00:33:20.000
<v Speaker 3>It was, I mean, as usual, our
conversations, it just sort of flies by.

544
00:33:20.359 --> 00:33:21.119
<v Speaker 3>I can't believe

545
00:33:21.400 --> 00:33:22.459
<v Speaker 1>it's always a pleasure.

546
00:33:22.890 --> 00:33:27.579
<v Speaker 3>But, um, no, and like I said, both, it's a
pleasure to speak to you both, but both

547
00:33:27.719 --> 00:33:29.939
<v Speaker 3>for the fact, you know, you're speaking to
customers every day and to bring that

548
00:33:30.239 --> 00:33:33.319
<v Speaker 3>onto the podcast, but it's also, like I
said, your previous experience, like

549
00:33:33.319 --> 00:33:34.359
<v Speaker 3>pre-Siemens.

550
00:33:35.030 --> 00:33:39.180
<v Speaker 3>Pre Sensai, um, you know, actually, you
know, on the, on the shop floor, you know,

551
00:33:39.300 --> 00:33:41.819
<v Speaker 3>doing, doing all this stuff you talk
about, so you can, you're the perfect person to

552
00:33:41.819 --> 00:33:46.300
<v Speaker 3>talk about both sides of the coin, as it
were, um, and that's why it's great to have

553
00:33:46.300 --> 00:33:48.180
<v Speaker 3>you on, but, um, thank you.

554
00:33:48.619 --> 00:33:49.630
<v Speaker 3>But yes, fantastic.

555
00:33:49.699 --> 00:33:51.719
<v Speaker 3>But yeah, thank you for your
contributions, Tom.

556
00:33:51.859 --> 00:33:56.060
<v Speaker 3>Um, we'll certainly invite you back,
especially about that future piece, um.

557
00:33:56.489 --> 00:33:59.339
<v Speaker 3>And I was even thinking we could talk
about this a bit more regularly, because

558
00:33:59.339 --> 00:34:01.739
<v Speaker 3>obviously, you know, you're continuously
having conversation with customers.

559
00:34:01.780 --> 00:34:06.800
<v Speaker 3>It's not, it's an infinite number of
conversations, so we should continue to dive it

560
00:34:06.800 --> 00:34:10.719
<v Speaker 3>back in and see what's changing and how
things are evolving to help other, other,

561
00:34:10.939 --> 00:34:13.899
<v Speaker 3>um, companies that are going through or
considering predicting maintenance.

562
00:34:14.120 --> 00:34:15.919
<v Speaker 3>Or other digital transformation as well.

563
00:34:16.280 --> 00:34:19.239
<v Speaker 1>Well, I'm, I'm glad we do this for that
reason, to be honest, Noel, because it

564
00:34:19.239 --> 00:34:23.429
<v Speaker 1>gives, it gives someone like me the chance
to be enthusiastic about something that,

565
00:34:23.669 --> 00:34:25.300
<v Speaker 1>that really is transformative.

566
00:34:25.600 --> 00:34:29.750
<v Speaker 1>I think when you look at different
technologies that have come and, and changed the

567
00:34:29.750 --> 00:34:34.600
<v Speaker 1>world, I think predictive maintenance, it,
it, it has a, it has the, the ability to

568
00:34:34.600 --> 00:34:35.800
<v Speaker 1>have a huge, huge impact.

569
00:34:35.919 --> 00:34:37.820
<v Speaker 1>We, we're seeing it with customers we've
got already.

570
00:34:38.540 --> 00:34:40.419
<v Speaker 1>Um, and I just love talking about it.

571
00:34:40.469 --> 00:34:44.629
<v Speaker 1>I think it's, it's really amazing what you
can do with a piece of software that,

572
00:34:44.729 --> 00:34:49.669
<v Speaker 1>that monitors effectively mechanical
machinery, and we can, we can anticipate when

573
00:34:49.669 --> 00:34:50.449
<v Speaker 1>it's gonna break down.

574
00:34:50.790 --> 00:34:55.229
<v Speaker 1>You know, that was, that was a dream to,
to many engineers, uh, just a couple of

575
00:34:55.229 --> 00:34:55.909
<v Speaker 1>decades ago.

576
00:34:57.439 --> 00:35:01.709
<v Speaker 3>Well, I'm pleased you like talking about
it cos then that you fit very well into the

577
00:35:01.709 --> 00:35:02.719
<v Speaker 3>podcast world.

578
00:35:03.399 --> 00:35:04.139
<v Speaker 3>Uh, no, that's great.

579
00:35:04.310 --> 00:35:09.219
<v Speaker 3>No, and thank you, Tom, uh, again for your
contributions, um, and yes, and thank you

580
00:35:09.229 --> 00:35:13.229
<v Speaker 3>everyone for listening, wherever you are
in the world, um, and we'll see you on the

581
00:35:13.229 --> 00:35:13.850
<v Speaker 3>next episode.

582
00:35:14.510 --> 00:35:14.729
<v Speaker 3>Thank you very much.

583
00:35:15.629 --> 00:35:16.330
<v Speaker 1>Cheers, Noel.

584
00:35:19.139 --> 00:35:24.100
<v Speaker 2>Please like and subscribe on all major
podcast channels and find out more about

585
00:35:24.100 --> 00:35:27.479
<v Speaker 2>Sensei predictive maintenance at
Siemens.com.
