WEBVTT
Language: en-US

1
00:00:02.329 --> 00:00:06.510
<v Tom Jacques>We know in the future, you know, what is
indicative of a failure about to happen,

2
00:00:06.849 --> 00:00:08.560
<v Tom Jacques>and we can, we can look out for it.

3
00:00:09.090 --> 00:00:11.930
<v Tom Jacques>But really it comes when you've, you've
had that first success, you've caught that

4
00:00:11.930 --> 00:00:16.489
<v Tom Jacques>first breakdown, or you've seen the first
instances of, of a, a case being raised in

5
00:00:16.489 --> 00:00:21.200
<v Tom Jacques>Sensei before the system's failed, and
then you realize, you know, this is not just

6
00:00:21.200 --> 00:00:22.479
<v Tom Jacques>a condition monitoring tool.

7
00:00:22.569 --> 00:00:26.969
<v Tom Jacques>It's, it sees really deeply into the, the
behaviors of your machines and Sensei is

8
00:00:26.969 --> 00:00:28.500
<v Tom Jacques>really powerful in that sense.

9
00:00:29.200 --> 00:00:34.400
<v Speaker 2>Welcome to the trend detection podcast
powered by Siemens, and now your host, Nel

10
00:00:34.400 --> 00:00:35.060
<v Speaker 2>Sullivan.

11
00:00:35.619 --> 00:00:39.220
<v Niall Sullivan>Hello and welcome to the latest episode of
the trend detection podcast.

12
00:00:39.599 --> 00:00:43.919
<v Niall Sullivan>I'm, I'm really pleased to be joined once
again by my colleague Tom, and he's been

13
00:00:43.919 --> 00:00:45.119
<v Niall Sullivan>on the podcast many a time.

14
00:00:45.319 --> 00:00:49.520
<v Niall Sullivan>Uh, the last time was actually in the
studio, but we're, we're remote this time, but

15
00:00:49.520 --> 00:00:50.819
<v Niall Sullivan>really pleased to have you back, Tom.

16
00:00:51.159 --> 00:00:51.490
<v Tom Jacques>Brilliant.

17
00:00:51.560 --> 00:00:52.659
<v Tom Jacques>Hi Nia, good afternoon.

18
00:00:53.700 --> 00:00:58.779
<v Niall Sullivan>Good afternoon, and so today we're gonna
be talking about predictive maintenance in,

19
00:00:58.889 --> 00:01:01.380
<v Niall Sullivan>in practice, and I guess what we, or what
I mean.

20
00:01:01.840 --> 00:01:06.000
<v Niall Sullivan>By that is sort of in the real world, and
I know, you know, all the episodes we've

21
00:01:06.000 --> 00:01:09.760
<v Niall Sullivan>done together and, you know, lots of other
guests as well, providing their own

22
00:01:09.760 --> 00:01:11.959
<v Niall Sullivan>perspective, and you've got a fantastic
one, of course.

23
00:01:12.279 --> 00:01:16.629
<v Niall Sullivan>But yeah, we're gonna go into the detail,
each step of the process, um, and the

24
00:01:16.629 --> 00:01:19.180
<v Niall Sullivan>process, of course, starts with a project
kickoff.

25
00:01:19.400 --> 00:01:24.279
<v Niall Sullivan>Um, so, if we start there, Tom, so what
actually happens, or usually happens in the

26
00:01:24.279 --> 00:01:26.410
<v Niall Sullivan>first sort of 30 to 60 days.

27
00:01:26.930 --> 00:01:31.010
<v Niall Sullivan>And is there sort of a, a difference
between what we do and what the customer thinks

28
00:01:31.010 --> 00:01:32.019
<v Niall Sullivan>might happen in that period?

29
00:01:33.029 --> 00:01:36.510
<v Tom Jacques>Yeah, I think sometimes there is, um,
yeah, so I'll gladly go into it.

30
00:01:36.610 --> 00:01:40.089
<v Tom Jacques>I mean, uh, for anyone who's not listened,
um, to me on the podcast before, my

31
00:01:40.089 --> 00:01:42.650
<v Tom Jacques>name's Tom, um, solutions engineering for
Sensei.

32
00:01:43.230 --> 00:01:46.919
<v Tom Jacques>You know, covering really that first part
of a project, so what we call scope when

33
00:01:46.919 --> 00:01:50.800
<v Tom Jacques>we do a predictive maintenance project,
and of course within that you have to

34
00:01:50.800 --> 00:01:54.279
<v Tom Jacques>understand first of all, you know, what
kind of project, um, are you looking for?

35
00:01:54.400 --> 00:01:56.300
<v Tom Jacques>Is this a downtime avoidance project?

36
00:01:56.440 --> 00:01:59.919
<v Tom Jacques>Are you perhaps over maintaining the
system and that's something you need to look to

37
00:01:59.919 --> 00:02:04.269
<v Tom Jacques>mitigate, you're spending lots on, on
spare parts or you're doing lots of time-based

38
00:02:04.269 --> 00:02:07.019
<v Tom Jacques>maintenance, perhaps, you know, quite
often unnecessarily.

39
00:02:07.410 --> 00:02:11.369
<v Tom Jacques>Um, but equally you could be GXP compliant
and you need to do certain, you know,

40
00:02:11.440 --> 00:02:15.479
<v Tom Jacques>regu regulatory changes and repairs and so
on to keep things operational.

41
00:02:15.649 --> 00:02:19.520
<v Tom Jacques>Things like food and beverage, you'll need
to keep things clean, so there's cleaning

42
00:02:19.520 --> 00:02:22.710
<v Tom Jacques>windows, those are often also very good
maintenance windows.

43
00:02:23.330 --> 00:02:26.270
<v Tom Jacques>We often see different customers with
different requirements.

44
00:02:26.740 --> 00:02:30.339
<v Tom Jacques>And I think really when we kick a project
off, the first thing we need to do is, is

45
00:02:30.339 --> 00:02:34.979
<v Tom Jacques>just get alignment, make sure we all
understand what the objective um is going to be

46
00:02:34.979 --> 00:02:38.770
<v Tom Jacques>for the project, make sure we're, we're
capturing data, make sure we've got the

47
00:02:38.770 --> 00:02:42.899
<v Tom Jacques>right sensors and things in place and
really just, you know, look at the sensors and

48
00:02:42.899 --> 00:02:46.860
<v Tom Jacques>the assets and the kind of hardware that
we've got available to us, if we've got,

49
00:02:47.130 --> 00:02:50.779
<v Tom Jacques>you know, motors and pumps and gearboxes
or, or whatever the assets are that we're

50
00:02:50.779 --> 00:02:52.660
<v Tom Jacques>looking at, again sens size covering.

51
00:02:53.250 --> 00:02:55.100
<v Tom Jacques>Rotating, non-rotating assets.

52
00:02:55.199 --> 00:02:59.720
<v Tom Jacques>I think the first thing is, is really look
at what assets we need, look at where the

53
00:02:59.720 --> 00:03:04.440
<v Tom Jacques>downtime is most impactful or where the,
you know, where the, the problems lie, and,

54
00:03:04.479 --> 00:03:09.660
<v Tom Jacques>and figure out how we're gonna get that
data through to, to, uh, the Suni platform,

55
00:03:09.800 --> 00:03:13.210
<v Tom Jacques>which is all cloud-based, and then how are
we gonna see success.

56
00:03:13.639 --> 00:03:18.130
<v Tom Jacques>Um, so make sure that we're set up in the
right way for, for practical delivery of

57
00:03:18.130 --> 00:03:18.660
<v Tom Jacques>the project.

58
00:03:19.279 --> 00:03:24.389
<v Tom Jacques>And also just understand if there's, you
know, a, a, a historian in place already,

59
00:03:24.520 --> 00:03:26.179
<v Tom Jacques>the data capture is already there.

60
00:03:26.559 --> 00:03:30.899
<v Tom Jacques>um, also what the workflow looks like, is
there already a CMMS solution in place.

61
00:03:31.300 --> 00:03:34.929
<v Tom Jacques>Do we plan to integrate those two things
and really how is it gonna impact the

62
00:03:34.929 --> 00:03:35.619
<v Tom Jacques>maintenance team?

63
00:03:35.779 --> 00:03:40.020
<v Tom Jacques>So Sensei is inherently a maintenance
product and that is really the team that's

64
00:03:40.020 --> 00:03:40.940
<v Tom Jacques>gonna impact the most.

65
00:03:41.059 --> 00:03:44.419
<v Tom Jacques>It will change the way operations are, are
currently run.

66
00:03:45.020 --> 00:03:48.539
<v Tom Jacques>And to be honest, Noel, we've, we've seen
customers where it even might be a, you

67
00:03:48.539 --> 00:03:50.479
<v Tom Jacques>know, a paper-based process still.

68
00:03:51.380 --> 00:03:55.380
<v Tom Jacques>We just wanna make sure that the process
from whatever is currently there to Sensei

69
00:03:55.380 --> 00:03:59.679
<v Tom Jacques>is also mapped out and, and the
expectations are, are sort of laid out correctly.

70
00:04:00.449 --> 00:04:05.100
<v Niall Sullivan>And in, in those sort of various different
sort of phases and parts of the process,

71
00:04:05.220 --> 00:04:11.059
<v Niall Sullivan>is there a place where projects, uh,
commonly stall or slow down in particular?

72
00:04:11.139 --> 00:04:12.740
<v Niall Sullivan>Is there something that sort of holds
things up?

73
00:04:13.100 --> 00:04:13.220
<v Niall Sullivan>Yeah,

74
00:04:13.300 --> 00:04:17.619
<v Tom Jacques>I think making sure you've got the right
resource, um, and also making sure

75
00:04:17.619 --> 00:04:21.500
<v Tom Jacques>everybody on the, the Siemens side, also
when there's partners involved, the partner

76
00:04:21.500 --> 00:04:23.119
<v Tom Jacques>side right the way through to the end
customer.

77
00:04:23.630 --> 00:04:24.600
<v Tom Jacques>That the resource is there.

78
00:04:24.709 --> 00:04:28.670
<v Tom Jacques>Now that could be financial, it could be
skill sets, it could be time, you know,

79
00:04:28.940 --> 00:04:32.390
<v Tom Jacques>sometimes, especially in maintenance
teams, you're, you're pressed for time, you've

80
00:04:32.390 --> 00:04:35.149
<v Tom Jacques>got lots of things to fix and, and keep
running.

81
00:04:35.540 --> 00:04:39.549
<v Tom Jacques>Start in a pilot with a, with a predictive
maintenance product sometimes isn't the,

82
00:04:39.660 --> 00:04:41.829
<v Tom Jacques>the top priority, you know, we see that
quite often.

83
00:04:42.410 --> 00:04:47.089
<v Tom Jacques>And it's making sure that the resources
are in place before that then slows you down

84
00:04:47.089 --> 00:04:48.149
<v Tom Jacques>at a later stage.

85
00:04:48.649 --> 00:04:53.489
<v Tom Jacques>Really, as well, from my perspective in
solutions engineering is that we, we scope

86
00:04:53.489 --> 00:04:57.290
<v Tom Jacques>the project properly so that we make sure
that whatever it is that you're looking to

87
00:04:57.290 --> 00:05:00.269
<v Tom Jacques>solve, we're going to be able to do that
and we're not missing anything.

88
00:05:00.730 --> 00:05:04.279
<v Tom Jacques>So, if we're going to monitor a certain
drive, we know that drive can Output, the

89
00:05:04.279 --> 00:05:05.820
<v Tom Jacques>values that we need, for example.

90
00:05:06.109 --> 00:05:09.549
<v Tom Jacques>All of these things need to be thought
about, and the better job we do of a scope

91
00:05:09.549 --> 00:05:14.239
<v Tom Jacques>phase of understanding the assets and
really working together with the customer to

92
00:05:14.239 --> 00:05:17.500
<v Tom Jacques>make sure we get the project right, the
better the project tends to run.

93
00:05:17.760 --> 00:05:22.359
<v Tom Jacques>Um, you know, you could easily halve the
length of project or shave many weeks off a

94
00:05:22.359 --> 00:05:25.179
<v Tom Jacques>project just by, just by doing the scope
phase correctly.

95
00:05:25.809 --> 00:05:28.980
<v Niall Sullivan>Uh, I was wondering, because when you say
the right resources, I imagine that across

96
00:05:28.980 --> 00:05:32.320
<v Niall Sullivan>a lot of projects, it'd be, you know,
similar roles or similar departments, but

97
00:05:32.320 --> 00:05:32.540
<v Niall Sullivan>then.

98
00:05:32.859 --> 00:05:36.850
<v Niall Sullivan>In others, it might be different, whether
it's due to culture or the size of

99
00:05:36.850 --> 00:05:37.170
<v Niall Sullivan>organization.

100
00:05:37.500 --> 00:05:41.459
<v Niall Sullivan>And it also just reminded me of, um, our
colleague, Natalie, who was on the podcast,

101
00:05:41.540 --> 00:05:45.660
<v Niall Sullivan>we recorded a podcast last week, and she
said that actually joining the case review

102
00:05:45.660 --> 00:05:49.220
<v Niall Sullivan>calls was a, the CEO of this particular
company, right?

103
00:05:49.339 --> 00:05:52.500
<v Niall Sullivan>Which is, I, I, I still can't believe
that, that they're so.

104
00:05:52.584 --> 00:05:52.975
<v Niall Sullivan>Involved in it.

105
00:05:53.144 --> 00:05:57.345
<v Niall Sullivan>I mean, that's quite rare, but it does it
vary between different companies, what

106
00:05:57.345 --> 00:06:01.345
<v Niall Sullivan>resources are required, or is it quite
sort of standardized, those certain roles

107
00:06:01.345 --> 00:06:01.584
<v Niall Sullivan>which.

108
00:06:01.625 --> 00:06:02.445
<v Tom Jacques>It can vary.

109
00:06:02.545 --> 00:06:06.614
<v Tom Jacques>I mean, that example from Natalie, is, is
a very good one because it's about

110
00:06:06.614 --> 00:06:07.725
<v Tom Jacques>stakeholder management.

111
00:06:08.345 --> 00:06:12.345
<v Tom Jacques>So perhaps from the bottom level, there's
a team that want to push this, but you

112
00:06:12.345 --> 00:06:15.945
<v Tom Jacques>know, in some cases, management don't
understand it, they don't see where this is

113
00:06:15.945 --> 00:06:17.125
<v Tom Jacques>going to benefit the business.

114
00:06:17.505 --> 00:06:19.334
<v Tom Jacques>So stakeholder management's really
important.

115
00:06:19.545 --> 00:06:21.524
<v Tom Jacques>Make sure the sponsors who might pay for
the project.

116
00:06:22.119 --> 00:06:25.200
<v Tom Jacques>They understand the benefits, how is this
gonna pay for itself?

117
00:06:25.529 --> 00:06:27.029
<v Tom Jacques>What is the objective of the project.

118
00:06:27.369 --> 00:06:31.329
<v Tom Jacques>Also, we call them pilots, but we're not
testing that the, the product works.

119
00:06:31.410 --> 00:06:34.410
<v Tom Jacques>We know Sensei is a very powerful tool.

120
00:06:34.720 --> 00:06:39.209
<v Tom Jacques>We know that it can do what it says on the
tin, um, for want of a better phrase, but

121
00:06:39.209 --> 00:06:42.600
<v Tom Jacques>really it's making sure that messaging is
passed across to the, to the people that

122
00:06:42.600 --> 00:06:43.910
<v Tom Jacques>will be involved, um.

123
00:06:44.570 --> 00:06:48.089
<v Tom Jacques>Yeah, and, and again, that's part of
speeding up the project, if you, if you explain

124
00:06:48.089 --> 00:06:51.279
<v Tom Jacques>all that stuff in the first instance and
you get buy-in from the right people.

125
00:06:51.730 --> 00:06:52.709
<v Tom Jacques>Yeah, absolutely.

126
00:06:53.209 --> 00:06:57.369
<v Niall Sullivan>I guess amongst those different roles as
well, I mean, how does, how does that

127
00:06:57.369 --> 00:07:01.170
<v Niall Sullivan>transition between, you know, the initial
sort of excitement of getting the project

128
00:07:01.170 --> 00:07:05.040
<v Niall Sullivan>up and running and looking at assets and
all that kind of thing to actually handing

129
00:07:05.040 --> 00:07:06.880
<v Niall Sullivan>over to sort of the, the operational side.

130
00:07:06.929 --> 00:07:09.489
<v Niall Sullivan>So we've set everything up now, off you
go.

131
00:07:10.279 --> 00:07:13.959
<v Niall Sullivan>It's time to use this day to day, and I
know it's not just a seamless handover and

132
00:07:13.959 --> 00:07:14.359
<v Niall Sullivan>that's it.

133
00:07:14.410 --> 00:07:17.600
<v Niall Sullivan>Obviously there's continuing support, but
yeah, how, how does that work from a

134
00:07:17.600 --> 00:07:18.739
<v Niall Sullivan>customer perspective?

135
00:07:18.959 --> 00:07:19.609
<v Tom Jacques>Good question.

136
00:07:19.799 --> 00:07:24.119
<v Tom Jacques>I think when customers have expectations
in the first instance, the goal will of

137
00:07:24.119 --> 00:07:27.380
<v Tom Jacques>course be, we need a tool that's gonna
help us with the maintenance.

138
00:07:27.519 --> 00:07:31.640
<v Tom Jacques>We, we need a, at the minute we're very
reactive, we find ourselves chasing our tail

139
00:07:31.640 --> 00:07:36.279
<v Tom Jacques>quite a lot, um, especially when you then
need spare parts that you might not have

140
00:07:36.279 --> 00:07:37.320
<v Tom Jacques>in stock or you.

141
00:07:37.640 --> 00:07:40.920
<v Tom Jacques>You know, for whatever reason, there's
there's other delays throughout any

142
00:07:40.920 --> 00:07:45.600
<v Tom Jacques>maintenance process and to be able to
anticipate what's gonna happen is really

143
00:07:45.600 --> 00:07:46.100
<v Tom Jacques>important.

144
00:07:46.200 --> 00:07:50.880
<v Tom Jacques>I would say, you know, just being able to
determine there's anomalous behavior or

145
00:07:50.880 --> 00:07:55.630
<v Tom Jacques>trending behavior, you know, moving away
from a, a baseline, increases in vibration,

146
00:07:55.869 --> 00:07:57.200
<v Tom Jacques>increases in temperature and so on.

147
00:07:57.510 --> 00:08:02.070
<v Tom Jacques>Again, just as one reference point on a
motor, uh, that's a, a very typical rotating

148
00:08:02.070 --> 00:08:02.609
<v Tom Jacques>asset.

149
00:08:02.709 --> 00:08:07.149
<v Tom Jacques>A large part of industry is kind of built
on, on motors, three-phase motors and so

150
00:08:07.149 --> 00:08:07.510
<v Tom Jacques>forth.

151
00:08:08.029 --> 00:08:09.829
<v Tom Jacques>But really that the expectation is there.

152
00:08:09.950 --> 00:08:13.420
<v Tom Jacques>So if, if you say we want to capture
failures, OK, but how?

153
00:08:13.510 --> 00:08:14.940
<v Tom Jacques>So what data have we got available?

154
00:08:15.230 --> 00:08:16.929
<v Tom Jacques>Do we need to make some data available?

155
00:08:17.149 --> 00:08:21.549
<v Tom Jacques>Is there a methodology here where we can
implement IOT sensors to extract, you know,

156
00:08:21.790 --> 00:08:25.929
<v Tom Jacques>additional insight, vibration sensors
there have been a really, really useful one.

157
00:08:26.440 --> 00:08:29.440
<v Tom Jacques>You know, new features and functionalities
of SenseI where you can look at the

158
00:08:29.440 --> 00:08:34.119
<v Tom Jacques>spectra in Sensei and get it to really do
the analytics for you in the tool rather

159
00:08:34.119 --> 00:08:39.179
<v Tom Jacques>than having to get uh a manual report done
on 100 motors that you've got in place.

160
00:08:39.770 --> 00:08:43.109
<v Tom Jacques>And then look to the future and you say,
well, OK, if we implement it on these

161
00:08:43.109 --> 00:08:46.690
<v Tom Jacques>assets, you know, we've got 10 of those,
but actually, if we implemented it on these

162
00:08:46.690 --> 00:08:51.000
<v Tom Jacques>conveyors, for example, we've got 1000 of
those, perhaps in the logistics facility

163
00:08:51.000 --> 00:08:55.030
<v Tom Jacques>or other, other customers where you might
see big mining operations.

164
00:08:55.440 --> 00:09:00.034
<v Tom Jacques>Sensor is really scalable, so the tool can
learn and And that data can be shared

165
00:09:00.034 --> 00:09:01.914
<v Tom Jacques>across fleets and groups of assets.

166
00:09:02.195 --> 00:09:05.864
<v Tom Jacques>I think really when the project starts,
looking at how you foresee it moving

167
00:09:05.864 --> 00:09:10.155
<v Tom Jacques>forward, basically, and there's always the
outlay of, well, these assets would be

168
00:09:10.155 --> 00:09:12.755
<v Tom Jacques>better, but we're gonna have to pull lots
of extra data.

169
00:09:12.835 --> 00:09:16.275
<v Tom Jacques>We're gonna have to really do a hardware
install project, you know, to pepper this

170
00:09:16.275 --> 00:09:17.135
<v Tom Jacques>thing with sensors.

171
00:09:17.500 --> 00:09:21.500
<v Tom Jacques>But actually over here, we've got loads of
data in the drives already in a sense I

172
00:09:21.500 --> 00:09:22.090
<v Tom Jacques>can leverage.

173
00:09:22.260 --> 00:09:26.059
<v Tom Jacques>We just need to make sure we can capture
that data, pull it from a historian, and

174
00:09:26.059 --> 00:09:27.380
<v Tom Jacques>really then just leverage that.

175
00:09:27.609 --> 00:09:32.380
<v Tom Jacques>Start there, start basically where the low
hanging fruit is and make sure that the

176
00:09:32.380 --> 00:09:34.200
<v Tom Jacques>team are, you know, fully on board with
that.

177
00:09:34.789 --> 00:09:37.830
<v Niall Sullivan>That's an interesting point about sort of
looking to the future, but what I think

178
00:09:37.830 --> 00:09:42.419
<v Niall Sullivan>inspires that is these sort of aha
moments, you know, where I'm not saying people

179
00:09:42.419 --> 00:09:45.830
<v Niall Sullivan>will, or maybe you do have some people who
are skeptical to start with, but even

180
00:09:45.830 --> 00:09:48.830
<v Niall Sullivan>people who aren't skeptical, they're
waiting for that moment where they're like, oh

181
00:09:48.830 --> 00:09:51.210
<v Niall Sullivan>my word, that's amazing, it's completely.

182
00:09:51.900 --> 00:09:52.780
<v Niall Sullivan>This is going to change everything.

183
00:09:52.820 --> 00:09:57.340
<v Niall Sullivan>I need to apply this to every asset or as
many assets as we can, but what, what

184
00:09:57.340 --> 00:10:00.799
<v Niall Sullivan>triggers those moments from your
perspective, Tom, from your experience?

185
00:10:01.099 --> 00:10:04.780
<v Tom Jacques>Usually that comes when you've started the
project and you start to see success

186
00:10:04.780 --> 00:10:08.380
<v Tom Jacques>somewhere, or you think if we just, you
know, if we just modify the parameters on

187
00:10:08.380 --> 00:10:11.900
<v Tom Jacques>this slightly, we've just seen a bearing
failure or we've, you know, we've just seen

188
00:10:11.900 --> 00:10:15.659
<v Tom Jacques>a system breakdown because of poor oil
quality or something like that in a, in a

189
00:10:15.659 --> 00:10:16.359
<v Tom Jacques>loop system.

190
00:10:16.950 --> 00:10:20.520
<v Tom Jacques>As soon as you can start to capture that
data and maybe you've just missed the

191
00:10:20.520 --> 00:10:25.650
<v Tom Jacques>failure, but then of course the work that
we do together, you modify those um

192
00:10:25.650 --> 00:10:30.000
<v Tom Jacques>settings, increase, decrease sensitivities
of certain measures and so on, that

193
00:10:30.000 --> 00:10:34.750
<v Tom Jacques>allows us to really ensure that we can sta
you know, effectively stand a much better

194
00:10:34.750 --> 00:10:36.820
<v Tom Jacques>chance of capturing that failure in the
future.

195
00:10:37.200 --> 00:10:40.619
<v Tom Jacques>And then once we know what that failure
looks like, we can match against that.

196
00:10:41.090 --> 00:10:45.809
<v Tom Jacques>So we know in future, you know, what is
indicative of a failure about to happen and

197
00:10:45.809 --> 00:10:49.010
<v Tom Jacques>we can, we can look out for it, but really
it comes when you've, you've had that

198
00:10:49.010 --> 00:10:53.169
<v Tom Jacques>first success, you've caught that first
breakdown, um, or you've seen the first

199
00:10:53.169 --> 00:10:58.450
<v Tom Jacques>instances of, of a, a case being raised in
Sensi before the system has failed, and

200
00:10:58.450 --> 00:11:02.250
<v Tom Jacques>then you realize, you know, this is not
just a condition monitoring tool, it doesn't

201
00:11:02.250 --> 00:11:02.570
<v Tom Jacques>just.

202
00:11:02.979 --> 00:11:07.070
<v Tom Jacques>Alert you to a, a, a violated threshold on
a measurement of, of temperature, for

203
00:11:07.070 --> 00:11:12.780
<v Tom Jacques>example, sensor is really powerful in that
sense to have the intelligence to see,

204
00:11:13.390 --> 00:11:16.750
<v Tom Jacques>you know, I really wanna get sort of
philosophical about it, but it sees really

205
00:11:16.750 --> 00:11:19.049
<v Tom Jacques>deeply into the, the behaviors of your
machines.

206
00:11:19.409 --> 00:11:23.929
<v Tom Jacques>And then with copilot, you can start to
ask questions to the motors and pumps

207
00:11:23.929 --> 00:11:24.409
<v Tom Jacques>themselves.

208
00:11:24.650 --> 00:11:27.960
<v Tom Jacques>It sounds crazy, but really that is as
good as I can explain it.

209
00:11:28.169 --> 00:11:32.440
<v Tom Jacques>It's the same as being able to then speak
to the asset and ask it, you know, what

210
00:11:32.440 --> 00:11:35.330
<v Tom Jacques>happened, you know, how did that happen,
why did that happen?

211
00:11:35.770 --> 00:11:40.570
<v Tom Jacques>and it will then give you all those
recommended actions based on we saw this, this

212
00:11:40.570 --> 00:11:43.030
<v Tom Jacques>was indicative of this type of failure on
this asset.

213
00:11:43.500 --> 00:11:48.270
<v Tom Jacques>If it's, let's say a loop system, you can
see that it's based on a high isocode in

214
00:11:48.270 --> 00:11:52.690
<v Tom Jacques>the oil quality, really degrading, so you
can see that isocode's increased.

215
00:11:52.950 --> 00:11:56.909
<v Tom Jacques>That's then indicative of, you know, you
need better filtration, you need, you need

216
00:11:56.909 --> 00:12:00.650
<v Tom Jacques>to find ways of mitigating that in future,
um, so it doesn't happen again.

217
00:12:00.830 --> 00:12:04.059
<v Tom Jacques>And then it learns from all that stuff
that you do, so every time you've fixed a

218
00:12:04.059 --> 00:12:08.229
<v Tom Jacques>problem, you fill into the tool what
you've done to fix it, and that's then used as

219
00:12:08.229 --> 00:12:09.109
<v Tom Jacques>suggestive action in the future.

220
00:12:09.244 --> 00:12:14.534
<v Tom Jacques>Um, and pulling data from PDF documents
and so on, so it can troubleshoot the system

221
00:12:14.534 --> 00:12:15.354
<v Tom Jacques>for you as well.

222
00:12:15.525 --> 00:12:19.854
<v Tom Jacques>But yeah, I think when, when it really
comes down to some of the challenges, I think

223
00:12:19.854 --> 00:12:23.015
<v Tom Jacques>one of the things we have to make sure is
that we're, we're not over egging the

224
00:12:23.015 --> 00:12:23.335
<v Tom Jacques>pudding.

225
00:12:23.494 --> 00:12:26.875
<v Tom Jacques>We, we really have to make sure that we
set the expectations correctly.

226
00:12:27.015 --> 00:12:31.695
<v Tom Jacques>If it's a small data set or you, you know,
you maybe make 100 different products on

227
00:12:31.695 --> 00:12:34.794
<v Tom Jacques>the same production line, that's gonna
take longer to understand.

228
00:12:35.080 --> 00:12:39.559
<v Tom Jacques>Um, normal operation for each of those
different batches or products, and it's, it's

229
00:12:39.559 --> 00:12:43.080
<v Tom Jacques>essential there that we set expectations
correctly, depending on what we're looking

230
00:12:43.080 --> 00:12:43.340
<v Tom Jacques>at.

231
00:12:43.400 --> 00:12:47.309
<v Niall Sullivan>It's, it's funny, Tom, when you were
saying about talking to motors, imagine like,

232
00:12:47.320 --> 00:12:48.799
<v Niall Sullivan>they're, they're like your best friends,
right?

233
00:12:48.919 --> 00:12:53.070
<v Niall Sullivan>So you, I don't know why that, that, that
appeared in my head when you're using the

234
00:12:53.070 --> 00:12:55.039
<v Niall Sullivan>co-pilot to understand them a lot more.

235
00:12:55.159 --> 00:12:55.640
<v Niall Sullivan>But I mean,

236
00:12:55.799 --> 00:12:58.109
<v Tom Jacques>it's almost like it reaches out to you and
says, I've, I've, I've had a

237
00:12:58.109 --> 00:12:58.789
<v Tom Jacques>misalignment.

238
00:12:58.840 --> 00:13:00.840
<v Tom Jacques>I really need you to, you know, come and
support me.

239
00:13:00.945 --> 00:13:02.844
<v Tom Jacques>That that is effectively what it's doing.

240
00:13:03.104 --> 00:13:04.664
<v Niall Sullivan>No, but I, I completely get it.

241
00:13:04.784 --> 00:13:09.104
<v Niall Sullivan>I, I guess what I wanted to sort of add on
to that point is also, you, you talked

242
00:13:09.104 --> 00:13:12.304
<v Niall Sullivan>about Sensai and the, we talked about our
hard moments, but of course, for an

243
00:13:12.304 --> 00:13:15.794
<v Niall Sullivan>insight to be really useful is someone to
actually act on it, right?

244
00:13:16.544 --> 00:13:21.224
<v Niall Sullivan>And so, what usually determines whether
maintenance teams act on something, you

245
00:13:21.224 --> 00:13:22.614
<v Niall Sullivan>know, what gives them the urge to do it?

246
00:13:22.664 --> 00:13:26.625
<v Niall Sullivan>You know, we've got lots of examples where
Sensai spotted things and people shrug

247
00:13:26.625 --> 00:13:26.744
<v Niall Sullivan>their.

248
00:13:26.809 --> 00:13:30.450
<v Niall Sullivan>Shoulders, something's broken down and
then it's, oh, you know, what happened here,

249
00:13:30.609 --> 00:13:32.090
<v Niall Sullivan>you know, those kinds of scenarios.

250
00:13:32.469 --> 00:13:33.989
<v Tom Jacques>Fundamentally, it comes down to trust.

251
00:13:34.250 --> 00:13:38.609
<v Tom Jacques>You, if someone who's very knowledgeable
and says, you know, I can hear that

252
00:13:38.609 --> 00:13:42.280
<v Tom Jacques>machine's clunking and making strange
sounds, I think that is about to fail, and,

253
00:13:42.289 --> 00:13:44.969
<v Tom Jacques>you know, it, that is indicative of a
bearing that's about to collapse.

254
00:13:45.010 --> 00:13:49.130
<v Tom Jacques>It's only subtle hints, but that's for
decades, of, you know, a very tried and

255
00:13:49.130 --> 00:13:49.830
<v Tom Jacques>tested method.

256
00:13:49.849 --> 00:13:52.570
<v Tom Jacques>If, if it starts to sound different or you
see very similar.

257
00:13:52.715 --> 00:13:54.205
<v Tom Jacques>Simple sensors that tell you it's getting
hot.

258
00:13:54.515 --> 00:13:57.474
<v Tom Jacques>As soon as you see a bearing that starts
to get hot, you can see there's increases

259
00:13:57.474 --> 00:13:58.034
<v Tom Jacques>in friction.

260
00:13:58.234 --> 00:13:59.994
<v Tom Jacques>That bearing's not doing what it should be
doing.

261
00:14:00.234 --> 00:14:04.104
<v Tom Jacques>What we try and do is look out for, um,
culmination of different things.

262
00:14:04.234 --> 00:14:08.455
<v Tom Jacques>You can compile that, you can have
correlations between measures and so on, um,

263
00:14:08.994 --> 00:14:10.234
<v Tom Jacques>control parameters and so on.

264
00:14:10.594 --> 00:14:14.775
<v Tom Jacques>What the software needs to do once it's
all been set up is prove to the customer

265
00:14:14.775 --> 00:14:17.344
<v Tom Jacques>that it can, it can actually do what we
say it can.

266
00:14:17.515 --> 00:14:18.474
<v Tom Jacques>If it's gonna indicate to you.

267
00:14:18.609 --> 00:14:21.390
<v Tom Jacques>That there's a failure, that really is
true.

268
00:14:21.580 --> 00:14:25.460
<v Tom Jacques>Um, of course, when you close a case, it
gives you the option to say, you know, this

269
00:14:25.460 --> 00:14:29.739
<v Tom Jacques>was very helpful, excellent, very, very
useful, equally no use at all, you know,

270
00:14:29.820 --> 00:14:35.090
<v Tom Jacques>maybe there's a, a process change that's
caused strange behaviors or wildly high

271
00:14:35.090 --> 00:14:39.179
<v Tom Jacques>ambient temperatures has, you know,
indicated that the bearing is hot, but actually

272
00:14:39.179 --> 00:14:43.419
<v Tom Jacques>it's just a very, very hot day, so making
sure we've got other measures in there to

273
00:14:43.419 --> 00:14:44.239
<v Tom Jacques>pick that stuff up.

274
00:14:44.710 --> 00:14:49.390
<v Tom Jacques>Um, we've, we've factored in maybe a delta
between two temperatures so that we know

275
00:14:49.390 --> 00:14:50.559
<v Tom Jacques>it's just the difference.

276
00:14:50.940 --> 00:14:54.700
<v Tom Jacques>Making sure that the system is set up
correctly so that we capture, and of course we

277
00:14:54.700 --> 00:14:57.849
<v Tom Jacques>do this on many thousands of assets, so we
know what we're talking about.

278
00:14:58.190 --> 00:15:03.070
<v Tom Jacques>But making sure we can build the trust
because if you have a team of people who

279
00:15:03.070 --> 00:15:03.909
<v Tom Jacques>don't believe it.

280
00:15:04.250 --> 00:15:08.849
<v Tom Jacques>The alert will pop up exactly as a
condition monitoring software did 10 years ago to

281
00:15:08.849 --> 00:15:12.599
<v Tom Jacques>say, oh, I think this is a, a failure, you
need to go and have a look at it, or you

282
00:15:12.599 --> 00:15:15.849
<v Tom Jacques>get nuisance alerts where it just keeps
bouncing off a limiter to tell you, you need

283
00:15:15.849 --> 00:15:16.880
<v Tom Jacques>to go and have a look at something.

284
00:15:17.330 --> 00:15:21.210
<v Tom Jacques>Sometimes previous bad experiences with
old software in the quote.

285
00:15:21.349 --> 00:15:26.630
<v Tom Jacques>Unquote, predictive maintenance space has
built that negative, um, negative image of

286
00:15:26.630 --> 00:15:27.969
<v Tom Jacques>what the software is capable of.

287
00:15:28.150 --> 00:15:31.289
<v Tom Jacques>That's probably one of the biggest hurdles
we have to overcome at Sensei, because

288
00:15:31.289 --> 00:15:36.010
<v Tom Jacques>Sensei is, as far as I see it, the only
tool that can really, really do this with

289
00:15:36.109 --> 00:15:38.289
<v Tom Jacques>enormous amounts of analytics in the
background.

290
00:15:38.840 --> 00:15:40.479
<v Tom Jacques>Yeah, it's, it's just about building
trust.

291
00:15:40.599 --> 00:15:45.640
<v Tom Jacques>It's making sure that when there's an
indication that the team then realize, OK,

292
00:15:45.799 --> 00:15:47.919
<v Tom Jacques>that's sensor, we know this isn't a false
alarm.

293
00:15:48.000 --> 00:15:52.200
<v Tom Jacques>We know it's based on, you know, good
data, good historical information.

294
00:15:52.520 --> 00:15:54.200
<v Tom Jacques>Uh, we know that it really has seen
something.

295
00:15:54.280 --> 00:15:57.919
<v Tom Jacques>We need to go and do some checks, do those
things, and then you think, wow,

296
00:15:58.109 --> 00:16:02.440
<v Tom Jacques>brilliant, that's just saved us 10 hours
of stoppage in whatever facility, a steel

297
00:16:02.440 --> 00:16:05.799
<v Tom Jacques>plant or a, a, a chocolate making
facility, whatever we're looking at.

298
00:16:06.330 --> 00:16:10.080
<v Niall Sullivan>And that, I, I call it confusion, you
know, the market confusion, let's call it,

299
00:16:10.140 --> 00:16:14.659
<v Niall Sullivan>where predictive maintenance is applied to
so many different products and companies

300
00:16:14.659 --> 00:16:17.010
<v Niall Sullivan>and stuff, so no wonder people are so
confused.

301
00:16:17.099 --> 00:16:20.859
<v Niall Sullivan>I guess that, does that sort of lead
sometimes, you know, building of trust is one

302
00:16:20.859 --> 00:16:25.140
<v Niall Sullivan>thing, but where you have customers who
move from, say, a proof of value position

303
00:16:25.140 --> 00:16:29.140
<v Niall Sullivan>to, you know, using it day to day and
operations and scaling and off they go to the

304
00:16:29.140 --> 00:16:30.200
<v Niall Sullivan>ones who get stuck.

305
00:16:30.840 --> 00:16:34.539
<v Niall Sullivan>You know, in this cycle of proof of value,
is there something that sort of separates

306
00:16:34.880 --> 00:16:39.719
<v Niall Sullivan>the two, the mindset beyond the market
inflating expectations, let's say.

307
00:16:40.080 --> 00:16:43.840
<v Tom Jacques>I think, I think once it becomes embedded
in daily operations, it becomes very easy

308
00:16:43.840 --> 00:16:44.580
<v Tom Jacques>to trust it.

309
00:16:44.919 --> 00:16:49.469
<v Tom Jacques>In the first couple of instances, we do
see this with, with sort of fledgling

310
00:16:49.469 --> 00:16:52.539
<v Tom Jacques>customers, they've got their 1st 100 asset
project, let's say.

311
00:16:53.049 --> 00:16:57.049
<v Tom Jacques>And then they get an alert, they'll tell
the system, yeah, we've been to have a look

312
00:16:57.049 --> 00:17:01.409
<v Tom Jacques>at it, we don't think there's a problem,
and maybe 2 or 3 weeks down the line, you

313
00:17:01.409 --> 00:17:05.369
<v Tom Jacques>get what I would class as a catastrophic
failure, you know, serious damage in your

314
00:17:05.369 --> 00:17:07.150
<v Tom Jacques>gearbox or something else goes wrong.

315
00:17:07.849 --> 00:17:12.560
<v Tom Jacques>And the signs of uh, of that failing and
breaking down were highlighted 2 weeks ago,

316
00:17:12.729 --> 00:17:14.930
<v Tom Jacques>but you don't realize the sensitivities of
it.

317
00:17:15.060 --> 00:17:19.839
<v Tom Jacques>That you don't realize perhaps it's seen
something that another software or maybe

318
00:17:19.979 --> 00:17:21.410
<v Tom Jacques>nothing has ever seen before.

319
00:17:21.579 --> 00:17:25.079
<v Tom Jacques>You have to learn to work together and it
really is like that because it becomes

320
00:17:25.250 --> 00:17:28.219
<v Tom Jacques>like a watchdog that's looking at the
system 24/7.

321
00:17:28.619 --> 00:17:31.660
<v Tom Jacques>I think most people that are listening to
this, you know, more than understand that.

322
00:17:31.739 --> 00:17:36.420
<v Tom Jacques>I, I'm not gonna dumb it down to any
stupid levels, but I think really it's, it's

323
00:17:36.420 --> 00:17:37.020
<v Tom Jacques>important that.

324
00:17:37.459 --> 00:17:41.449
<v Tom Jacques>It alerts to something, maybe once you get
to that stage of having a work order

325
00:17:41.449 --> 00:17:45.939
<v Tom Jacques>integration, it's raising that and it's
not just raising loads of unnecessary stuff

326
00:17:45.939 --> 00:17:51.250
<v Tom Jacques>that's just realistically gonna annoy you,
it's designed to work together, it's like

327
00:17:51.250 --> 00:17:56.329
<v Tom Jacques>a symbiosis of, of man and machine working
together to, to capture stuff, um,

328
00:17:56.339 --> 00:17:59.219
<v Tom Jacques>because very often it's, we do this for
the maintenance team, but it's the

329
00:17:59.219 --> 00:18:02.660
<v Tom Jacques>production teams at the end of the day
that are in short that you know, they are

330
00:18:02.660 --> 00:18:06.660
<v Tom Jacques>looking, looking to the maintenance team
to say, You know, we're expected to produce

331
00:18:06.949 --> 00:18:07.439
<v Tom Jacques>X, Y, and

332
00:18:07.439 --> 00:18:11.160
<v Tom Jacques>Z, but you guys need to give us the
machines, the production lines to make that

333
00:18:11.160 --> 00:18:11.640
<v Tom Jacques>possible.

334
00:18:12.099 --> 00:18:17.250
<v Tom Jacques>If we don't have that, realistically, we
can't do our job, that's gonna annoy senior

335
00:18:17.250 --> 00:18:21.260
<v Tom Jacques>leadership, also end customers and, you
know, contracts that need fulfilling to

336
00:18:21.260 --> 00:18:22.510
<v Tom Jacques>output certain products.

337
00:18:22.660 --> 00:18:25.939
<v Tom Jacques>And, and that means there's huge pressure
on maintenance teams to keep everything

338
00:18:25.939 --> 00:18:30.219
<v Tom Jacques>running, often on a shoestring budget with
limited resource, limited training,

339
00:18:30.300 --> 00:18:34.780
<v Tom Jacques>limited skill sets, and Sensei really
helps to fill in all of those blanks, and

340
00:18:34.780 --> 00:18:40.020
<v Tom Jacques>that's a, that's a huge sales pitch, of
course, but we see this at scale, we see how

341
00:18:40.020 --> 00:18:40.660
<v Tom Jacques>successful it is.

342
00:18:41.130 --> 00:18:44.859
<v Tom Jacques>Um, yeah, if anybody ever wants to speak
to me about this, I'd, I'd happily have a

343
00:18:44.859 --> 00:18:48.550
<v Tom Jacques>call with anybody, give a, give a demo of
the tool and, and share how this works,

344
00:18:48.579 --> 00:18:51.619
<v Tom Jacques>and our teams across, across the globe can
also do the same.

345
00:18:51.699 --> 00:18:54.969
<v Tom Jacques>So to anybody listening to this in, in any
corner of the world, we can share this

346
00:18:54.969 --> 00:18:58.819
<v Tom Jacques>with you, we can share successes of how it
works and, and that it's not rubbish

347
00:18:58.819 --> 00:19:01.199
<v Tom Jacques>basically and, and prove what we're
saying.

348
00:19:01.849 --> 00:19:03.420
<v Niall Sullivan>Absolutely, and um.

349
00:19:03.849 --> 00:19:07.810
<v Niall Sullivan>You know, how long does it take for PDM to
become sort of business as usual, and

350
00:19:07.810 --> 00:19:12.729
<v Niall Sullivan>again it's gonna depend on size of
deployment, customer, industry, but is there a

351
00:19:12.729 --> 00:19:15.680
<v Niall Sullivan>sort of a rough sort of rule of thumb you
could point to, Tom?

352
00:19:16.170 --> 00:19:17.010
<v Tom Jacques>Uh, I would say yeah.

353
00:19:17.089 --> 00:19:20.160
<v Tom Jacques>I mean it depends on the assets of the
industry exactly as you just said it.

354
00:19:20.329 --> 00:19:24.849
<v Tom Jacques>And I'm not, I'm not gonna say how long is
a piece of string to be flippant, but I

355
00:19:24.849 --> 00:19:28.689
<v Tom Jacques>think you need to give the tool a little
bit of time to understand the asset,

356
00:19:29.089 --> 00:19:30.989
<v Tom Jacques>understand what normal behavior looks
like.

357
00:19:31.780 --> 00:19:35.859
<v Tom Jacques>One of the main questions we get asked, we
do get asked quite often, um, is there a

358
00:19:35.859 --> 00:19:39.219
<v Tom Jacques>chance that we're actually on board in
this motor in a failed state or a failing

359
00:19:39.219 --> 00:19:40.010
<v Tom Jacques>state already?

360
00:19:40.369 --> 00:19:44.619
<v Tom Jacques>It's 80%, um, of its remaining useful
lifetime is gone.

361
00:19:44.810 --> 00:19:47.119
<v Tom Jacques>It's, it's really weeks away from failing.

362
00:19:47.459 --> 00:19:49.010
<v Tom Jacques>So you're gonna learn that as normal
operation.

363
00:19:49.449 --> 00:19:54.180
<v Tom Jacques>The answer is we'll learn it as behavior,
then we, we give obviously the engineers

364
00:19:54.180 --> 00:19:58.219
<v Tom Jacques>the chance to, to explain what happened,
that it broke down, and that what we saw

365
00:19:58.219 --> 00:20:00.880
<v Tom Jacques>there is already indicative of, of a
failing asset.

366
00:20:01.150 --> 00:20:03.609
<v Tom Jacques>And it knows that for, for future
reference.

367
00:20:04.430 --> 00:20:07.869
<v Tom Jacques>And our delivery teams and all the rest of
it can make sure that that is built into

368
00:20:07.869 --> 00:20:08.439
<v Tom Jacques>the tool.

369
00:20:09.310 --> 00:20:13.829
<v Tom Jacques>In the future, when it happens again,
maybe within the next 2 months or 3 months,

370
00:20:14.069 --> 00:20:17.979
<v Tom Jacques>whatever it might be, it really, really
does there depend on what the asset is, um,

371
00:20:18.229 --> 00:20:22.229
<v Tom Jacques>how often it's running, so it might be
running 24/7, it might be running 6 hours a

372
00:20:22.229 --> 00:20:27.810
<v Tom Jacques>day, you can imagine there that's gonna
take, you know, 4 times longer respectively,

373
00:20:27.989 --> 00:20:30.849
<v Tom Jacques>um, if it's the same asset, let's say with
all the same variables.

374
00:20:31.319 --> 00:20:35.160
<v Tom Jacques>But yeah, I think most of our customers
will say they start to trust the tool within

375
00:20:35.160 --> 00:20:40.479
<v Tom Jacques>6 months or, you know, 6 months to a year
just to be really sure I'm not being too

376
00:20:40.479 --> 00:20:41.859
<v Tom Jacques>overly optimistic on that one.

377
00:20:42.280 --> 00:20:43.800
<v Niall Sullivan>We won't hold you to it, Tom.

378
00:20:44.400 --> 00:20:48.079
<v Tom Jacques>Yeah, and that, that's the thing, isn't
it, like if it's set up correctly, I would

379
00:20:48.079 --> 00:20:52.359
<v Tom Jacques>always say, you know, 6 to 12 months,
you're gonna see real big benefit, you know,

380
00:20:52.469 --> 00:20:53.199
<v Tom Jacques>and you'll get analytic.

381
00:20:53.349 --> 00:20:55.890
<v Tom Jacques>Analytics done on that asset that have
never before been possible.

382
00:20:56.430 --> 00:20:57.650
<v Niall Sullivan>Awesome, awesome.

383
00:20:58.030 --> 00:21:01.349
<v Niall Sullivan>What I didn't warn you about before,
before this, Tom, is we now have a lightning

384
00:21:01.349 --> 00:21:03.479
<v Niall Sullivan>round, so there'll be, there'll be some
questions.

385
00:21:04.229 --> 00:21:07.910
<v Niall Sullivan>Just to, you know, just brief quickfire
questions, but before, before we get to

386
00:21:07.910 --> 00:21:12.609
<v Niall Sullivan>that, I just wanted to ask a couple more
questions and going back to where we start

387
00:21:12.609 --> 00:21:17.060
<v Niall Sullivan>about customers' expectations, what they
expect to happen, but what's one sort of

388
00:21:17.060 --> 00:21:20.829
<v Niall Sullivan>assumption customers always have or
regularly have that.

389
00:21:21.260 --> 00:21:24.540
<v Niall Sullivan>You know, turns out to be wrong, you know,
from, let's say from the early sort of

390
00:21:24.540 --> 00:21:29.060
<v Niall Sullivan>kickoff and scoping meetings, is there
something where assumption has proved to be

391
00:21:29.060 --> 00:21:29.880
<v Niall Sullivan>incorrect?

392
00:21:30.579 --> 00:21:32.699
<v Tom Jacques>I, that's a that is a great question.

393
00:21:32.780 --> 00:21:37.900
<v Tom Jacques>If, if I was to answer that question
really as well as I can, I would say it's not

394
00:21:37.900 --> 00:21:38.439
<v Tom Jacques>magic.

395
00:21:39.239 --> 00:21:43.630
<v Tom Jacques>Sensei is not magic, sometimes it can feel
really clever, it can feel a little bit

396
00:21:43.810 --> 00:21:48.890
<v Tom Jacques>um like magic, but you have to really fill
it in and give it feedback and help it

397
00:21:48.890 --> 00:21:49.560
<v Tom Jacques>along the way.

398
00:21:49.810 --> 00:21:53.530
<v Tom Jacques>You have to do the work mechanically, you
have to highlight what you've done to fix

399
00:21:53.530 --> 00:21:58.770
<v Tom Jacques>problems, um, it will still find things,
so all you're doing there is increasing the

400
00:21:58.770 --> 00:21:58.969
<v Tom Jacques>chance.

401
00:21:59.069 --> 00:22:02.609
<v Tom Jacques>Is improving, um, the, the intelligence of
the tool.

402
00:22:02.829 --> 00:22:07.219
<v Tom Jacques>Also when you upload PDF documents and so
on, so it's got that extra knowledge and

403
00:22:07.219 --> 00:22:11.489
<v Tom Jacques>information of how to fix a bearing or a
pump or whatever asset we look at.

404
00:22:11.709 --> 00:22:14.199
<v Tom Jacques>And I would just say, make sure everyone's
aligned on it.

405
00:22:14.510 --> 00:22:16.130
<v Tom Jacques>So it's a cultural thing more than
anything.

406
00:22:16.189 --> 00:22:20.750
<v Tom Jacques>It is a technical thing, we're, we're
changing the way we extract data, the way we

407
00:22:20.750 --> 00:22:22.989
<v Tom Jacques>do the analytics of a motor or whatever.

408
00:22:23.449 --> 00:22:28.530
<v Tom Jacques>But really there, you need to make sure
when Sensite alerts you to something, what's

409
00:22:28.530 --> 00:22:30.739
<v Tom Jacques>the cultural process that you're gonna
follow?

410
00:22:30.890 --> 00:22:32.430
<v Tom Jacques>Is there a proactive approach?

411
00:22:32.680 --> 00:22:38.089
<v Tom Jacques>Everyone will sit together and 9 times out
of 10, if not 10 out of 10, it changes

412
00:22:38.089 --> 00:22:42.760
<v Tom Jacques>the culture positively for the customers
that use Sensei because they start to trust

413
00:22:42.760 --> 00:22:44.119
<v Tom Jacques>it, it starts to help them.

414
00:22:44.479 --> 00:22:48.650
<v Tom Jacques>It's a tool that of course costs money,
but it saves you even more, so it's a tool

415
00:22:48.650 --> 00:22:49.849
<v Tom Jacques>that's designed to.

416
00:22:50.229 --> 00:22:55.479
<v Tom Jacques>Um, to really positively change the way
you go to work, um, and I think to be able

417
00:22:55.479 --> 00:23:00.839
<v Tom Jacques>to sort of proactively look at a tool,
react to that thing that's gonna tell you of

418
00:23:00.839 --> 00:23:05.560
<v Tom Jacques>a bearing failure, that's much more fun
than than reacting to bearing breakdowns

419
00:23:05.560 --> 00:23:08.479
<v Tom Jacques>that have already happened, lines have
already stopped and so on, so.

420
00:23:09.219 --> 00:23:13.550
<v Niall Sullivan>Even me, you know, nowhere near sort of
that world or level of expertise, that

421
00:23:13.550 --> 00:23:19.959
<v Niall Sullivan>could, could tell that as well, so much
more to spot it ahead of time, um, and I,

422
00:23:20.170 --> 00:23:24.640
<v Niall Sullivan>and I guess also, so if a customer asked
you one piece of advice before.

423
00:23:25.119 --> 00:23:29.560
<v Niall Sullivan>Sorry, after the contract is signed, but
before the kickoff of the meeting, what

424
00:23:29.560 --> 00:23:32.469
<v Niall Sullivan>would you tell them to focus on first or
think about first?

425
00:23:32.560 --> 00:23:32.650
<v Niall Sullivan>Oh,

426
00:23:33.520 --> 00:23:38.939
<v Tom Jacques>what I would say, and what we see often,
uh, Scope workshops and beyond is make sure

427
00:23:39.199 --> 00:23:43.920
<v Tom Jacques>everyone's on the right page, so the teams
that are all maybe in separate

428
00:23:43.920 --> 00:23:47.390
<v Tom Jacques>departments, maybe they already work very
closely together, but they will still end

429
00:23:47.390 --> 00:23:49.000
<v Tom Jacques>up working more closely together.

430
00:23:49.489 --> 00:23:52.530
<v Tom Jacques>Um, make sure that there's really
alignment between the expectations.

431
00:23:52.819 --> 00:23:58.260
<v Tom Jacques>The maintenance team will, will implement
this, um, with the support of IT teams and

432
00:23:58.260 --> 00:24:03.699
<v Tom Jacques>anyone who works, you know, OT to IT,
including the IT team that can, um, support

433
00:24:03.699 --> 00:24:08.060
<v Tom Jacques>with data transmission and so on,
automation teams, Industry 4 teams that you see in

434
00:24:08.060 --> 00:24:08.619
<v Tom Jacques>these different.

435
00:24:09.000 --> 00:24:09.619
<v Tom Jacques>Facilities.

436
00:24:09.869 --> 00:24:13.189
<v Tom Jacques>It's crazy when you look at how
industries's changed in the last 20 or 30 years.

437
00:24:13.310 --> 00:24:16.989
<v Tom Jacques>I say that as a 30 year old, but still for
me, even in the last 10, it's quite

438
00:24:16.989 --> 00:24:22.390
<v Tom Jacques>ridiculous, um, how digitalized
everything's becoming and, and how much data is now

439
00:24:22.390 --> 00:24:26.790
<v Tom Jacques>available, sometimes you have too much,
and it's making sure that all the way from

440
00:24:26.790 --> 00:24:31.109
<v Tom Jacques>leadership down through to technicians,
you've got a, a, a really solid

441
00:24:31.109 --> 00:24:34.630
<v Tom Jacques>understanding of, of how we're all gonna
work together and just set yourselves up

442
00:24:34.630 --> 00:24:38.670
<v Tom Jacques>for success, and we, we do see a
difference between customers who get that right.

443
00:24:38.979 --> 00:24:43.630
<v Tom Jacques>And customers who perhaps in the early
stages have struggled and how that impacts um

444
00:24:43.630 --> 00:24:44.369
<v Tom Jacques>the project.

445
00:24:44.869 --> 00:24:48.229
<v Tom Jacques>Yeah, I think just get those things really
clear and you'll move twice as fast.

446
00:24:49.459 --> 00:24:51.030
<v Niall Sullivan>Yeah, I guess it, it's a ban smokes.

447
00:24:51.099 --> 00:24:54.709
<v Niall Sullivan>There's certain things a vendor like
Siemens can, you know, can help with and

448
00:24:54.709 --> 00:24:56.229
<v Niall Sullivan>support with as part of that process.

449
00:24:56.349 --> 00:25:00.430
<v Niall Sullivan>There has to be effort, let's say, from
the, from the customer side as well to do

450
00:25:00.430 --> 00:25:00.709
<v Niall Sullivan>this right.

451
00:25:00.859 --> 00:25:01.069
<v Niall Sullivan>Absolutely,

452
00:25:01.229 --> 00:25:05.060
<v Tom Jacques>absolutely, and it really is, uh, you
know, a great example of the more you put in,

453
00:25:05.189 --> 00:25:05.930
<v Tom Jacques>the more you get out.

454
00:25:06.150 --> 00:25:06.729
<v Niall Sullivan>Absolutely.

455
00:25:06.869 --> 00:25:10.189
<v Niall Sullivan>So, we've reached the promise lightning
rounds.

456
00:25:10.310 --> 00:25:14.349
<v Niall Sullivan>Um, I haven't shared these with you
before, Tom, so it's gonna be a little bit of a

457
00:25:14.349 --> 00:25:14.910
<v Niall Sullivan>surprise, but.

458
00:25:15.479 --> 00:25:20.199
<v Niall Sullivan>Again, very short, succinct answer, well,
even one word answers in some cases, so

459
00:25:20.199 --> 00:25:21.469
<v Niall Sullivan>let's, let's go for a first.

460
00:25:21.890 --> 00:25:26.540
<v Niall Sullivan>The first one is pilot or scale first,
what, what's the Sparta instinct?

461
00:25:26.880 --> 00:25:31.280
<v Tom Jacques>Pilot, I would make sure you get that
right in the first instance, and from there

462
00:25:31.280 --> 00:25:32.510
<v Tom Jacques>you can scale it afterwards.

463
00:25:33.000 --> 00:25:37.780
<v Niall Sullivan>Um, bigger risk in predictive maintenance,
bad data or slow decisions.

464
00:25:38.800 --> 00:25:41.310
<v Tom Jacques>I would say bad data, really that's
fundamental.

465
00:25:41.380 --> 00:25:46.000
<v Tom Jacques>I think if you get data right in the first
place, even if you don't have much, you

466
00:25:46.000 --> 00:25:49.030
<v Tom Jacques>can still do a lot more with, with good
data, so bad data.

467
00:25:49.319 --> 00:25:49.329
<v Tom Jacques>Mhm.

468
00:25:49.800 --> 00:25:54.750
<v Niall Sullivan>Excellent, and finally, so if you could
fix just one thing on day one, what would

469
00:25:54.750 --> 00:25:56.160
<v Niall Sullivan>move the needle fastest?

470
00:25:56.319 --> 00:25:58.160
<v Niall Sullivan>I know we're sort of a bit more um.

471
00:25:59.489 --> 00:26:02.449
<v Niall Sullivan>Open that one, but yeah, what springs to
mind?

472
00:26:03.270 --> 00:26:08.310
<v Tom Jacques>First thing to get done, I would say
cultural alignment with the team, make sure

473
00:26:08.310 --> 00:26:12.709
<v Tom Jacques>everybody understands the objective and
what are we trying to solve and achieve

474
00:26:12.709 --> 00:26:14.390
<v Tom Jacques>with, with a tool like Senseiye.

475
00:26:15.300 --> 00:26:17.189
<v Niall Sullivan>Fantastic, fantastic, there we go.

476
00:26:17.430 --> 00:26:21.569
<v Niall Sullivan>But that's all we're, we've got time for
today, so, um, I'd like to thank you, Tom,

477
00:26:21.750 --> 00:26:26.660
<v Niall Sullivan>for joining us again, and you'll no doubt
be um recording again with us in the

478
00:26:26.660 --> 00:26:26.969
<v Niall Sullivan>future.

479
00:26:27.670 --> 00:26:28.469
<v Tom Jacques>Yeah, it's been a pleasure.

480
00:26:28.670 --> 00:26:31.020
<v Tom Jacques>Thanks for, thanks for having me again and
obviously everyone.

481
00:26:31.344 --> 00:26:35.185
<v Tom Jacques>Thanks for listening and if anyone's got
any further questions, er hopefully my

482
00:26:35.185 --> 00:26:36.505
<v Tom Jacques>contact details will be at the end of
this.

483
00:26:36.625 --> 00:26:37.425
<v Niall Sullivan>It will, it will.

484
00:26:37.535 --> 00:26:42.864
<v Niall Sullivan>We'll add Tom's LinkedIn um details to the
show notes, but yes, thank you, everyone

485
00:26:42.864 --> 00:26:46.045
<v Niall Sullivan>out there for listening wherever you are,
and we'll see you on the next episode.

486
00:26:46.584 --> 00:26:47.324
<v Niall Sullivan>Thank you very much.

487
00:26:48.469 --> 00:26:53.430
<v Speaker 2>Please like and subscribe on all major
podcast channels and find out more about

488
00:26:53.430 --> 00:26:56.810
<v Speaker 2>Sensei predictive maintenance at
Siemens.com.
