WEBVTT
Language: en-US

1
00:00:03.910 --> 00:00:09.109
<v Speaker 1>Welcome to the trend detection podcast
powered by Siemens, and now your host, Nel

2
00:00:09.109 --> 00:00:09.670
<v Speaker 1>Sullivan.

3
00:00:10.340 --> 00:00:14.409
<v Niall Sullivan>So welcome to this 3rd and final episode
in our series looking at some industry

4
00:00:14.409 --> 00:00:16.610
<v Niall Sullivan>highlights related to predictive
maintenance.

5
00:00:16.799 --> 00:00:22.139
<v Niall Sullivan>I'm really pleased to invite Alex Hill,
our global head of business development at

6
00:00:22.139 --> 00:00:23.860
<v Niall Sullivan>MI Predictive Maintenance here again.

7
00:00:24.059 --> 00:00:24.659
<v Niall Sullivan>Hi Alex.

8
00:00:24.920 --> 00:00:25.420
<v Niall Sullivan>Bit of a mouthful.

9
00:00:25.569 --> 00:00:26.889
<v Alex Hill>I know it is.

10
00:00:26.940 --> 00:00:29.250
<v Niall Sullivan>You need to shorten that title, I think,
but it's fun.

11
00:00:29.309 --> 00:00:29.680
<v Niall Sullivan>It's fine.

12
00:00:29.940 --> 00:00:33.819
<v Niall Sullivan>But no, we've, we've, um, we've previously
talked about automotive industry and the

13
00:00:33.819 --> 00:00:35.040
<v Niall Sullivan>food and beverage industry.

14
00:00:35.369 --> 00:00:38.770
<v Niall Sullivan>But today in our final episode, we're
actually going to focus on the heavy industry,

15
00:00:38.849 --> 00:00:44.090
<v Niall Sullivan>so metals, mining, which I know is a, uh,
let's say, we've got lots of great use

16
00:00:44.090 --> 00:00:46.689
<v Niall Sullivan>cases in, in that area to, to talk
through.

17
00:00:47.090 --> 00:00:50.970
<v Niall Sullivan>But I guess we've started the previous
episodes, and it's looking at the challenges

18
00:00:50.970 --> 00:00:51.090
<v Niall Sullivan>again.

19
00:00:51.209 --> 00:00:53.529
<v Niall Sullivan>So it'd be a bit remiss not to, to not do
so again.

20
00:00:53.610 --> 00:00:58.349
<v Niall Sullivan>So can we start by looking at the the
unique challenges to the, to those industries?

21
00:00:59.459 --> 00:01:04.279
<v Alex Hill>I think one of the, one of the primary
unique challenges is it's a dirty industry,

22
00:01:04.779 --> 00:01:06.040
<v Alex Hill>and I mean that in every sense.

23
00:01:06.260 --> 00:01:11.779
<v Alex Hill>So politically, environmentally, uh,
technologically, everything is, is, it has some

24
00:01:11.779 --> 00:01:14.940
<v Alex Hill>bad connotations around it, and it'd be
wrong of us not to address that elephant in

25
00:01:14.940 --> 00:01:15.339
<v Alex Hill>the room.

26
00:01:16.349 --> 00:01:20.580
<v Alex Hill>But the fact is that our technology can
help that industry to be less dirty, to be

27
00:01:20.790 --> 00:01:24.449
<v Alex Hill>more sustainable, to be more
environmentally friendly, and so there's a huge amount

28
00:01:24.449 --> 00:01:25.559
<v Alex Hill>of opportunities to do that.

29
00:01:26.199 --> 00:01:30.879
<v Alex Hill>And the companies that operate in that
area are actually very committed to making

30
00:01:30.879 --> 00:01:34.989
<v Alex Hill>sure that they can operate sustainably
sustainably and in an environmentally

31
00:01:34.989 --> 00:01:39.680
<v Alex Hill>friendly way and in a way that's
respectful to the earth and people, because if they

32
00:01:39.680 --> 00:01:43.260
<v Alex Hill>don't, they won't be in business because
people care about that kind of thing now

33
00:01:43.519 --> 00:01:46.449
<v Alex Hill>and these companies are ultimately run by
people.

34
00:01:46.919 --> 00:01:49.440
<v Alex Hill>So that's one of the first challenges.

35
00:01:49.480 --> 00:01:54.680
<v Alex Hill>How can they operate in a way that is
respectful to people and the environment and

36
00:01:54.680 --> 00:01:55.470
<v Alex Hill>continue to do that.

37
00:01:56.910 --> 00:02:01.989
<v Alex Hill>Then you get into the classical areas of
from a machinery point of view, their

38
00:02:01.989 --> 00:02:03.269
<v Alex Hill>environment is dirty.

39
00:02:03.430 --> 00:02:05.230
<v Alex Hill>It's incredibly hard on the machinery.

40
00:02:06.309 --> 00:02:10.869
<v Alex Hill>Things break all the time, there's
contamination, there's, it, it's, it's, it's one

41
00:02:10.869 --> 00:02:12.910
<v Alex Hill>of the most challenging environments that
a machine can be in.

42
00:02:13.639 --> 00:02:18.440
<v Alex Hill>And so how can you make sure that you can
operate this machinery and make money with

43
00:02:18.440 --> 00:02:22.470
<v Alex Hill>it whilst not spending all of your time
buying new machinery and maintaining it.

44
00:02:22.839 --> 00:02:27.520
<v Alex Hill>So first of all, machinery is quite tough,
and you then need to monitor it and have

45
00:02:27.520 --> 00:02:32.160
<v Alex Hill>some more sophisticated understanding of
where to go and fix and when to fix it at

46
00:02:32.160 --> 00:02:36.119
<v Alex Hill>just the right time so that you're not
spending too much because.

47
00:02:36.970 --> 00:02:42.570
<v Alex Hill>The the margins in actually extracting uh
minerals and things might be quite low, so

48
00:02:42.570 --> 00:02:45.210
<v Alex Hill>you've got to do it at quite a high
volume, which means you need to keep doing

49
00:02:45.210 --> 00:02:50.169
<v Alex Hill>things, uh, often through a number of
shifts and through a large amount of

50
00:02:50.169 --> 00:02:50.610
<v Alex Hill>machinery.

51
00:02:52.110 --> 00:02:55.360
<v Alex Hill>And so downtime becomes very important.

52
00:02:55.520 --> 00:03:00.639
<v Alex Hill>How can you avoid unplanned downtime,
particularly in areas where if you're

53
00:03:00.639 --> 00:03:06.039
<v Alex Hill>processing and refining some form of ore
and producing steel or aluminum, that's a

54
00:03:06.039 --> 00:03:10.279
<v Alex Hill>continuous process, and you have something
that is hot and effectively live going

55
00:03:10.279 --> 00:03:11.559
<v Alex Hill>through your entire factory.

56
00:03:11.880 --> 00:03:16.520
<v Alex Hill>If something fails during that point, you
could waste all of that product, damage

57
00:03:16.520 --> 00:03:17.479
<v Alex Hill>all of that machinery.

58
00:03:17.800 --> 00:03:23.360
<v Alex Hill>And it might take you uh over a week to
reheat that material, to reheat the furnaces

59
00:03:23.360 --> 00:03:26.759
<v Alex Hill>and things, and, and the energy costs
involved in that are, are phenomenal as well.

60
00:03:27.080 --> 00:03:31.559
<v Alex Hill>So unplanned downtime through every part
of that industry becomes really, really

61
00:03:31.559 --> 00:03:31.960
<v Alex Hill>important.

62
00:03:32.740 --> 00:03:36.860
<v Alex Hill>I think unplanned downtime,
sustainability, safety of course is massively important,

63
00:03:36.979 --> 00:03:41.779
<v Alex Hill>making sure that these things are done in
a safe manner and making sure that they're

64
00:03:41.779 --> 00:03:43.779
<v Alex Hill>not spending money where it doesn't need
to be done.

65
00:03:45.289 --> 00:03:49.009
<v Niall Sullivan>And you've also, I mean, I like your, I
like your reference to a sort of dirty

66
00:03:49.009 --> 00:03:53.139
<v Niall Sullivan>environment, but it's also, it's, it also
requires sort of rugged technology in

67
00:03:53.139 --> 00:03:55.619
<v Niall Sullivan>terms of, I know we're sort of moving away
from software to look towards the

68
00:03:55.619 --> 00:03:59.259
<v Niall Sullivan>hardware side, but is that a challenge as
well in that industry to use, you know,

69
00:03:59.649 --> 00:04:00.619
<v Niall Sullivan>hardware sensors, etc.

70
00:04:00.729 --> 00:04:05.600
<v Niall Sullivan>which actually can withstand the pressures
that you sort of mentioned before

71
00:04:07.350 --> 00:04:07.419
<v Alex Hill>can be.

72
00:04:08.160 --> 00:04:13.119
<v Alex Hill>The heavy or the mining metals industries,
there's actually quite a lot in common in

73
00:04:13.119 --> 00:04:16.959
<v Alex Hill>terms of monitoring with oil and gas,
where they've got a quite a deep culture and

74
00:04:16.959 --> 00:04:21.559
<v Alex Hill>deep understanding of how to use condition
monitoring to optimize how they perform

75
00:04:21.559 --> 00:04:22.079
<v Alex Hill>their maintenance.

76
00:04:22.279 --> 00:04:23.470
<v Alex Hill>So they already understand it quite well.

77
00:04:23.559 --> 00:04:26.399
<v Alex Hill>We don't need to explain what condition
monitoring is, what predictive maintenance

78
00:04:26.399 --> 00:04:26.600
<v Alex Hill>is.

79
00:04:26.760 --> 00:04:29.519
<v Alex Hill>They get it already, they know it, they're
probably already doing it.

80
00:04:29.859 --> 00:04:34.700
<v Alex Hill>The challenge they have is how can they
not just be looking at these 10 or 50, 20

81
00:04:34.700 --> 00:04:39.170
<v Alex Hill>critical machines, how can they now be
looking at all of the machines on this site,

82
00:04:39.450 --> 00:04:41.899
<v Alex Hill>and that could be thousands just in a
single site.

83
00:04:42.559 --> 00:04:44.070
<v Alex Hill>And that's, that's really challenging to
do.

84
00:04:44.809 --> 00:04:50.130
<v Alex Hill>The actual sensing equipment itself is
often built into the uh the machinery that

85
00:04:50.130 --> 00:04:54.730
<v Alex Hill>they're buying, or they're already
collecting process data that we can use as

86
00:04:54.730 --> 00:04:55.609
<v Alex Hill>condition monitoring data.

87
00:04:56.049 --> 00:05:00.329
<v Alex Hill>One of the really good things about the
metals and mining industry is they, they

88
00:05:00.329 --> 00:05:06.489
<v Alex Hill>centralized on or they, they adopted the
idea of collecting interesting and useful

89
00:05:06.489 --> 00:05:10.369
<v Alex Hill>data quite some time ago, so that they're
decades ahead of some other industries.

90
00:05:11.000 --> 00:05:15.559
<v Alex Hill>They almost ubiquitously use a data
historian.

91
00:05:16.609 --> 00:05:20.029
<v Alex Hill>Which means that you get all kinds of
interesting process data being collected

92
00:05:20.029 --> 00:05:23.170
<v Alex Hill>because the process needs to be very
tightly controlled, particularly when you're

93
00:05:23.170 --> 00:05:26.510
<v Alex Hill>you're actually refining something and and
putting something out at the end.

94
00:05:27.609 --> 00:05:31.929
<v Alex Hill>And that process data can actually be used
for condition monitoring, and people

95
00:05:31.929 --> 00:05:32.489
<v Alex Hill>don't think about it.

96
00:05:32.609 --> 00:05:35.470
<v Alex Hill>When people think about condition
monitoring, they think about vibration, going

97
00:05:35.470 --> 00:05:37.230
<v Alex Hill>installing and retrofitting lots of
things.

98
00:05:37.609 --> 00:05:41.850
<v Alex Hill>And yeah, there are certainly some cases
where the equipment you install needs to

99
00:05:41.850 --> 00:05:46.769
<v Alex Hill>be, needs to withstand very high
temperatures, for example, in a pot room where

100
00:05:46.769 --> 00:05:48.250
<v Alex Hill>you're melting these, these metals.

101
00:05:49.140 --> 00:05:50.760
<v Alex Hill>But there's a different way to do it.

102
00:05:51.109 --> 00:05:54.989
<v Alex Hill>You can start to use that process data
that's maybe just looking purely at the

103
00:05:54.989 --> 00:05:59.309
<v Alex Hill>timing of things and start to use that for
content monitoring purposes, because if

104
00:05:59.309 --> 00:06:04.549
<v Alex Hill>something is starting to degrade, those
timing intervals are going to change, and

105
00:06:04.549 --> 00:06:08.750
<v Alex Hill>that gives you that very early warning,
essentially for free, that that machine is

106
00:06:08.750 --> 00:06:10.619
<v Alex Hill>not behaving quite in the way that you
want it to.

107
00:06:10.869 --> 00:06:14.709
<v Alex Hill>And that allows you to flag up, this is
what deserves my attention, and the other

108
00:06:14.709 --> 00:06:15.390
<v Alex Hill>things don't.

109
00:06:15.980 --> 00:06:20.190
<v Alex Hill>So we have some fantastic case studies
with companies, and there's one in particular

110
00:06:20.190 --> 00:06:25.609
<v Alex Hill>with a global aluminum company, and we
managed to achieve a full ROI at a site

111
00:06:26.059 --> 00:06:29.989
<v Alex Hill>within less than 6 months, and we managed
to enable them to reduce their maintenance

112
00:06:29.989 --> 00:06:35.070
<v Alex Hill>spending by about 20% without installing
any sensors, so they have no specific

113
00:06:35.070 --> 00:06:36.029
<v Alex Hill>condition monitoring sensors.

114
00:06:36.190 --> 00:06:40.709
<v Alex Hill>They weren't doing anything, but they were
collecting process data that happened to

115
00:06:40.709 --> 00:06:44.190
<v Alex Hill>be the right kinds of things, current,
temperature, torque.

116
00:06:45.079 --> 00:06:49.839
<v Alex Hill>Timing, things that are free from a
process control point of view, they had already

117
00:06:49.839 --> 00:06:50.369
<v Alex Hill>stored it.

118
00:06:50.799 --> 00:06:54.970
<v Alex Hill>We really, I don't say we merely connected
things and and and it just happened.

119
00:06:55.410 --> 00:06:58.279
<v Alex Hill>There's still quite a lot of work to be
done in terms of making sure we're looking

120
00:06:58.279 --> 00:07:03.160
<v Alex Hill>at the right things, but they had that
infrastructure in place already just as a

121
00:07:03.160 --> 00:07:07.480
<v Alex Hill>result of, of them being able to do normal
business operation, and they could

122
00:07:07.480 --> 00:07:12.559
<v Alex Hill>repurpose that investment and
infrastructure for predictor maintenance purposes, and

123
00:07:12.559 --> 00:07:13.160
<v Alex Hill>that was awesome.

124
00:07:14.529 --> 00:07:18.230
<v Niall Sullivan>And is there a reason why these, you, you
mentioned these companies were more, you

125
00:07:18.230 --> 00:07:20.250
<v Niall Sullivan>know, light years ahead of other
industries?

126
00:07:20.290 --> 00:07:24.570
<v Niall Sullivan>Is there, is there a reason for that, or
is it just based on those, you know, a

127
00:07:24.570 --> 00:07:28.250
<v Niall Sullivan>massive list of challenges you listed at
the start that they, you know, they're, you

128
00:07:28.250 --> 00:07:31.929
<v Niall Sullivan>know, they're just looking for solutions
and technology seemed like the, the

129
00:07:31.929 --> 00:07:34.790
<v Niall Sullivan>logical, what is so, I'm just trying to
dive into that a little bit.

130
00:07:35.760 --> 00:07:39.720
<v Alex Hill>I think for one reason or another, there's
quite a lot of crossover between oil and

131
00:07:39.720 --> 00:07:43.450
<v Alex Hill>gas and the technologies and the
approaches and, and mining and metals.

132
00:07:43.720 --> 00:07:47.459
<v Alex Hill>And, and heavy industry is not just mining
metals, but other things like concrete,

133
00:07:47.839 --> 00:07:48.799
<v Alex Hill>pulp and paper, and so on.

134
00:07:48.839 --> 00:07:54.320
<v Alex Hill>But for us we do see the most growth and
the most adoption in mining and metals

135
00:07:54.320 --> 00:07:58.399
<v Alex Hill>specifically, and, and that's, that's
because they they actually have that whole

136
00:07:58.399 --> 00:08:03.119
<v Alex Hill>culture of safety and appreciating that
they don't want to be up against these

137
00:08:03.119 --> 00:08:03.799
<v Alex Hill>machines all the time.

138
00:08:04.250 --> 00:08:08.260
<v Alex Hill>That they need to be continuously running
and that they need to be monitoring and

139
00:08:08.260 --> 00:08:13.100
<v Alex Hill>that, that culture is is really carried
over from oil and gas.

140
00:08:13.980 --> 00:08:14.720
<v Alex Hill>I don't know why.

141
00:08:15.500 --> 00:08:18.260
<v Alex Hill>I've not really explored that too much,
but it's, it's something interesting to look

142
00:08:18.260 --> 00:08:18.820
<v Alex Hill>further into.

143
00:08:19.920 --> 00:08:23.279
<v Niall Sullivan>And I guess another aspects as well, which
we haven't touched on in the previous

144
00:08:23.279 --> 00:08:24.799
<v Niall Sullivan>series, but you mentioned health and
safety.

145
00:08:24.869 --> 00:08:29.679
<v Niall Sullivan>So I guess the fact that it could be
monitored remotely as well, the machinery could

146
00:08:29.679 --> 00:08:34.070
<v Niall Sullivan>be, you don't have to be on site to
monitor in these dangerous or, you know,

147
00:08:34.760 --> 00:08:35.820
<v Niall Sullivan>environments, I guess.

148
00:08:35.919 --> 00:08:36.919
<v Alex Hill>That's actually a really good point.

149
00:08:36.929 --> 00:08:40.440
<v Alex Hill>And one of the things that we focus on
quite a lot as a business outcome, the fact

150
00:08:40.440 --> 00:08:46.140
<v Alex Hill>that Even before the Coronavirus and the
fact that we had to spend 2 years indoors.

151
00:08:47.000 --> 00:08:51.119
<v Alex Hill>Maintenance is changing, it's no longer
about going up to something and resting your

152
00:08:51.119 --> 00:08:53.229
<v Alex Hill>hand on it and understanding what you need
to do.

153
00:08:53.479 --> 00:08:55.679
<v Alex Hill>The people who can do that are, are quite
rare.

154
00:08:55.919 --> 00:09:00.809
<v Alex Hill>They don't scale very well, because you
can't scale people like that, and, The new

155
00:09:00.809 --> 00:09:03.270
<v Alex Hill>maintainers coming in are used to
technology.

156
00:09:03.690 --> 00:09:06.090
<v Alex Hill>They're used to doing things more
remotely, and they have their colleagues who are

157
00:09:06.090 --> 00:09:07.969
<v Alex Hill>sitting in an office and being quite
relaxed.

158
00:09:07.979 --> 00:09:13.000
<v Alex Hill>And do you want to be sending people up
against a, a machine that is a noisy,

159
00:09:13.049 --> 00:09:15.849
<v Alex Hill>dangerous, difficult environment if you,
if you can avoid it?

160
00:09:15.969 --> 00:09:16.359
<v Alex Hill>No.

161
00:09:16.809 --> 00:09:18.570
<v Alex Hill>So maintenance is becoming more and more
remote.

162
00:09:18.679 --> 00:09:22.969
<v Alex Hill>The fact is that you can do a lot of your
diagnostic and, and planning and

163
00:09:22.969 --> 00:09:25.090
<v Alex Hill>preparatory work completely remotely.

164
00:09:25.630 --> 00:09:29.479
<v Alex Hill>By looking at the data that's coming
through and having a system that guides you as

165
00:09:29.479 --> 00:09:31.760
<v Alex Hill>to what you need to go and look at and.

166
00:09:32.669 --> 00:09:33.750
<v Alex Hill>The workplace is changing.

167
00:09:34.140 --> 00:09:40.070
<v Alex Hill>Mining and metals is still seen or
perceived as a dirty industry, but the fact is

168
00:09:40.070 --> 00:09:46.669
<v Alex Hill>that they go to extreme lengths to make it
safe and clean and and have a

169
00:09:46.669 --> 00:09:51.909
<v Alex Hill>minimal impact on the environment and
humans, and technology absolutely helps them

170
00:09:51.909 --> 00:09:52.270
<v Alex Hill>do that.

171
00:09:53.710 --> 00:09:57.750
<v Niall Sullivan>No, actually, because I know we've done in
the past, in the past year or so, done a

172
00:09:57.750 --> 00:10:01.909
<v Niall Sullivan>few podcasts around this topic with, you
know, experts in the industry, and from

173
00:10:01.909 --> 00:10:06.590
<v Niall Sullivan>what, what I gather, there's another
reason why, you know, technology might be more

174
00:10:06.590 --> 00:10:09.369
<v Niall Sullivan>widespread is that there's a lot of sort
of knowledge sharing.

175
00:10:09.469 --> 00:10:13.349
<v Niall Sullivan>I know we've talked on previous episodes
about is knowledge shared, but I, I sort of

176
00:10:13.349 --> 00:10:17.469
<v Niall Sullivan>understand that there's, In, in mining or
metal, in particular, every industry in

177
00:10:17.469 --> 00:10:18.739
<v Niall Sullivan>particular, it's more not sharing.

178
00:10:18.770 --> 00:10:20.669
<v Niall Sullivan>Is that your sort of experience too?

179
00:10:21.090 --> 00:10:24.809
<v Alex Hill>It is, and I think it's because the
longevity of these sites is, is measured in

180
00:10:24.809 --> 00:10:28.479
<v Alex Hill>decades, not, you know, they're not buying
a site and and working at it for six

181
00:10:28.479 --> 00:10:29.090
<v Alex Hill>months or something.

182
00:10:29.369 --> 00:10:33.719
<v Alex Hill>They're committing to that site, to that
area for decades, and so the technology

183
00:10:33.719 --> 00:10:34.549
<v Alex Hill>needs to be.

184
00:10:35.020 --> 00:10:37.659
<v Alex Hill>Uh, suitable for that and they can grow
with that.

185
00:10:38.020 --> 00:10:41.130
<v Alex Hill>And then when they have these sites,
they've been monitoring for decades and working

186
00:10:41.130 --> 00:10:41.909
<v Alex Hill>with them for decades.

187
00:10:42.219 --> 00:10:45.349
<v Alex Hill>How can they start to optimize, how can
they start to share this learning, make sure

188
00:10:45.349 --> 00:10:49.919
<v Alex Hill>that they are getting the product for, for
the best price and the best way.

189
00:10:51.159 --> 00:10:56.840
<v Alex Hill>And, and so we see a lot of, uh, probably
higher than, than most other industries.

190
00:10:57.080 --> 00:11:03.780
<v Alex Hill>We see a lot of connected thinking and and
knowledge sharing and uh connected tools

191
00:11:04.039 --> 00:11:07.219
<v Alex Hill>where you can start to monitor sites
across the world.

192
00:11:07.859 --> 00:11:11.640
<v Alex Hill>Um, I don't want to say easily, but with,
with a relative ease, there's there's

193
00:11:11.640 --> 00:11:16.530
<v Alex Hill>quite some um commonality and it might not
be exactly the same things.

194
00:11:16.880 --> 00:11:19.489
<v Alex Hill>There's at least going to be a
commonality, a common language, a common way of doing

195
00:11:19.489 --> 00:11:19.700
<v Alex Hill>things.

196
00:11:20.369 --> 00:11:24.809
<v Alex Hill>And we're starting to see more and more
infrastructure and investment in truly

197
00:11:24.809 --> 00:11:26.530
<v Alex Hill>making those tools ubiquitous.

198
00:11:26.809 --> 00:11:28.570
<v Alex Hill>Let's use the same instance of something.

199
00:11:29.210 --> 00:11:33.250
<v Alex Hill>Uh, previously that wasn't possible
because often these assets are very remote, uh,

200
00:11:33.580 --> 00:11:38.409
<v Alex Hill>very difficult to get data from them, very
difficult to in, in the past, very

201
00:11:38.409 --> 00:11:41.890
<v Alex Hill>difficult to, to connect the database
that's in Australia with one that's in

202
00:11:41.890 --> 00:11:43.369
<v Alex Hill>Ireland, maybe, um.

203
00:11:43.969 --> 00:11:48.020
<v Alex Hill>But we've seen that happen now in previous
examples where we had a customer in

204
00:11:48.020 --> 00:11:52.239
<v Alex Hill>Thailand streaming data to Australia and
then processed an island in a data center

205
00:11:52.510 --> 00:11:56.460
<v Alex Hill>and and accessed all around the world, and
the technology has made that kind of

206
00:11:56.460 --> 00:11:56.940
<v Alex Hill>thing possible.

207
00:11:58.380 --> 00:12:01.619
<v Niall Sullivan>And actually it's, it's an interesting
point to touch upon because in terms of

208
00:12:01.619 --> 00:12:04.940
<v Niall Sullivan>assets, obviously cent predictive
maintenance come on to we say many, any, any type

209
00:12:04.940 --> 00:12:09.539
<v Niall Sullivan>of asset, any type of industry, but it, I
guess it's the nuances between the type,

210
00:12:09.659 --> 00:12:13.780
<v Niall Sullivan>what type of assets, particularly in
metals and mining are most prevalent and like

211
00:12:13.780 --> 00:12:17.020
<v Niall Sullivan>you say, more mobile assets, I guess is
the big difference compared to other

212
00:12:17.020 --> 00:12:18.320
<v Niall Sullivan>industries we work in.

213
00:12:18.659 --> 00:12:22.059
<v Alex Hill>Mobile assets is is really interesting and
that's, that's been a challenge as well.

214
00:12:22.260 --> 00:12:24.400
<v Alex Hill>A lot of these, uh, trucks.

215
00:12:25.000 --> 00:12:29.159
<v Alex Hill>You know, the size of a house or a decent
sized palace, they already have very

216
00:12:29.159 --> 00:12:32.559
<v Alex Hill>sophisticated monitoring, but that
monitoring's been really for a, for a dashboard

217
00:12:32.559 --> 00:12:36.830
<v Alex Hill>for the driver to say, hey, something's
really, really bad, you need to stop, uh, a

218
00:12:36.830 --> 00:12:39.760
<v Alex Hill>much more sophisticated version of the
check engine light that we all have in our

219
00:12:39.760 --> 00:12:40.219
<v Alex Hill>cars.

220
00:12:40.679 --> 00:12:46.280
<v Alex Hill>But now, now that we actually can have
internet access, 5G, whatever, pretty much

221
00:12:46.280 --> 00:12:50.440
<v Alex Hill>everywhere, you have the ability to stream
that data out and to centralize the

222
00:12:50.440 --> 00:12:51.299
<v Alex Hill>analysis of that.

223
00:12:51.650 --> 00:12:55.599
<v Alex Hill>And that gets even more interesting, how
can you start to monitor and optimize not

224
00:12:55.599 --> 00:12:59.669
<v Alex Hill>just the vehicle, but the whole fleet,
your whole usage of the fleet, and, and.

225
00:13:00.739 --> 00:13:04.979
<v Alex Hill>Combine that understanding of how the
fleet is behaving with how your crusher and

226
00:13:04.979 --> 00:13:09.580
<v Alex Hill>how your uh grinders and how your conveyor
systems are operating and put that all

227
00:13:09.580 --> 00:13:14.940
<v Alex Hill>together, that hasn't been possible before
from a connectivity point of view and

228
00:13:14.940 --> 00:13:16.520
<v Alex Hill>from a processing point of view because.

229
00:13:17.460 --> 00:13:22.119
<v Alex Hill>Since I predict Mason takes that very
data-centric point of view, we can start to

230
00:13:22.260 --> 00:13:26.489
<v Alex Hill>combine the data from these mobile assets
with fixed assets, and, and people always

231
00:13:26.489 --> 00:13:29.460
<v Alex Hill>ask us, well, you know, you can do these
conveyors and things, but can you do mobile

232
00:13:29.460 --> 00:13:29.989
<v Alex Hill>assets?

233
00:13:30.340 --> 00:13:36.109
<v Alex Hill>And really it doesn't make any difference
for us as long as the data represents the,

234
00:13:37.559 --> 00:13:42.340
<v Alex Hill>it starts to represent some sort of
degradation or condition of that machinery and a

235
00:13:42.340 --> 00:13:45.500
<v Alex Hill>human, if a human were to look at that
data and they can't see anything.

236
00:13:46.219 --> 00:13:49.929
<v Alex Hill>We won't be able to, it's not magic, but
as long as it's valid condition monitoring

237
00:13:49.929 --> 00:13:54.780
<v Alex Hill>data, we can automate the analysis of
that, and then you can have your mobile

238
00:13:54.780 --> 00:13:59.789
<v Alex Hill>machines as well as your fixed plant in
the same area, and it gets to be a really

239
00:13:59.789 --> 00:14:01.099
<v Alex Hill>nice holistic view.

240
00:14:02.179 --> 00:14:05.869
<v Niall Sullivan>Yeah, I guess the other thing we haven't
touched upon in, in the previous episodes

241
00:14:05.869 --> 00:14:09.429
<v Niall Sullivan>either, but one thing we talk about a lot,
it's not just the data condition

242
00:14:09.429 --> 00:14:12.190
<v Niall Sullivan>monitoring data and the data from the
machines and assets, but it's actually also

243
00:14:12.190 --> 00:14:16.469
<v Niall Sullivan>the human input as well from the the
people who know that asset, we work with that

244
00:14:16.469 --> 00:14:17.229
<v Niall Sullivan>asset every day.

245
00:14:17.349 --> 00:14:22.349
<v Niall Sullivan>Could you sort of just explain a little
bit how Sensei uses the human input and

246
00:14:22.349 --> 00:14:25.390
<v Niall Sullivan>aspect as well, because I think that's
really interesting to cover.

247
00:14:25.940 --> 00:14:29.080
<v Alex Hill>So the traditional method is very good,
very appropriate in some industries.

248
00:14:29.500 --> 00:14:35.179
<v Alex Hill>The problem is, if you want to expand that
to 500 machines, 5000, 50,000 across an

249
00:14:35.179 --> 00:14:35.799
<v Alex Hill>entire enterprise.

250
00:14:36.770 --> 00:14:42.580
<v Alex Hill>You need to be doing a lot of manual human
understanding of failure modes and

251
00:14:42.580 --> 00:14:43.739
<v Alex Hill>building and maintaining models.

252
00:14:44.099 --> 00:14:45.169
<v Alex Hill>That's incredibly expensive.

253
00:14:45.539 --> 00:14:48.539
<v Alex Hill>So whatever money you save in the
maintenance of something, you're going to be

254
00:14:48.539 --> 00:14:52.500
<v Alex Hill>spending tenfold in the actual data
analytics, and that's not a viable way to

255
00:14:52.500 --> 00:14:53.020
<v Alex Hill>approach things.

256
00:14:54.000 --> 00:14:57.580
<v Alex Hill>With Sensii predictive maintenance, we,
we, we turn that approach on its head.

257
00:14:57.919 --> 00:15:00.880
<v Alex Hill>We accept that the data that we're looking
at is going to be poor.

258
00:15:01.880 --> 00:15:05.640
<v Alex Hill>It's low context, it's, it's noisy because
that's what environment, that's what

259
00:15:05.640 --> 00:15:06.989
<v Alex Hill>indus industrial data looks like.

260
00:15:07.200 --> 00:15:08.700
<v Alex Hill>Things are never perfect as we want them.

261
00:15:08.919 --> 00:15:11.940
<v Alex Hill>So we have to accept that, and that's,
that's one of our fundamental principles.

262
00:15:13.020 --> 00:15:17.330
<v Alex Hill>Then we have to understand that the, the
data we get is actually quite low context

263
00:15:17.330 --> 00:15:17.809
<v Alex Hill>as well.

264
00:15:18.299 --> 00:15:20.979
<v Alex Hill>So what I mean by that is we don't know
everything that the machine is doing.

265
00:15:21.059 --> 00:15:24.010
<v Alex Hill>We don't know everything that the company
is producing, how they're doing it.

266
00:15:24.210 --> 00:15:25.030
<v Alex Hill>We also don't want to know.

267
00:15:25.179 --> 00:15:29.700
<v Alex Hill>Some of that's their IP and, and to get
them to share all of that, it's, it's just

268
00:15:29.700 --> 00:15:32.400
<v Alex Hill>not, not a really viable way of running
our business.

269
00:15:32.979 --> 00:15:34.919
<v Alex Hill>We want to focus on, on the machine.

270
00:15:35.950 --> 00:15:38.909
<v Alex Hill>And then What humans do about that.

271
00:15:39.119 --> 00:15:41.969
<v Alex Hill>And so when people talk about predictive
maintenance, they get all excited about

272
00:15:41.969 --> 00:15:43.039
<v Alex Hill>machines and they focus on machines.

273
00:15:44.210 --> 00:15:48.049
<v Alex Hill>We want to focus on what those machines
mean to the business.

274
00:15:48.669 --> 00:15:50.030
<v Alex Hill>And the business is about humans.

275
00:15:51.830 --> 00:15:55.789
<v Alex Hill>So really what we're focusing on is the
humans, we're using machine data to help

276
00:15:55.789 --> 00:15:56.179
<v Alex Hill>that.

277
00:15:56.750 --> 00:16:01.229
<v Alex Hill>So rather than saying that we know
everything about this machine, and we're going to

278
00:16:01.229 --> 00:16:05.900
<v Alex Hill>uh tell a maintainer that the bearing is
spoiling in a particular way and blah blah

279
00:16:05.900 --> 00:16:11.190
<v Alex Hill>blah, what the maintainer probably wants
to know is the bearing's going bad, I need

280
00:16:11.190 --> 00:16:12.369
<v Alex Hill>to do something about it.

281
00:16:12.830 --> 00:16:16.190
<v Alex Hill>And the fact is I have all of these other
machines with bearings that aren't going

282
00:16:16.190 --> 00:16:16.469
<v Alex Hill>bad.

283
00:16:17.030 --> 00:16:21.070
<v Alex Hill>So I'm going to focus my attention on this
one that actually is, and do something in

284
00:16:21.070 --> 00:16:24.510
<v Alex Hill>an efficient manner that saves the company
money, rather than having to go and check

285
00:16:24.510 --> 00:16:28.250
<v Alex Hill>things all the time and, and, and do
things just because the manufacturer says so.

286
00:16:29.650 --> 00:16:35.729
<v Alex Hill>So by that, We, our currency of how we
work is human attention,

287
00:16:36.229 --> 00:16:37.250
<v Alex Hill>not machine health.

288
00:16:37.469 --> 00:16:39.510
<v Alex Hill>And that, that flips this whole thing on
its, on its head.

289
00:16:39.780 --> 00:16:42.820
<v Alex Hill>We're looking at machine data, we're
working with machines, we're, we're, we're

290
00:16:42.820 --> 00:16:46.229
<v Alex Hill>guiding people about where to pay
attention with the machines, but actually what we

291
00:16:46.229 --> 00:16:47.229
<v Alex Hill>care about is human attention.

292
00:16:47.390 --> 00:16:48.549
<v Alex Hill>That's, that's our currency.

293
00:16:49.940 --> 00:16:56.140
<v Alex Hill>We take the data from machines, and we
direct human attention to where our

294
00:16:56.140 --> 00:16:58.179
<v Alex Hill>algorithms believe it is most warranted.

295
00:16:58.830 --> 00:17:03.270
<v Alex Hill>And then we learn from what the human
does, because our data is inherently actually

296
00:17:03.270 --> 00:17:07.410
<v Alex Hill>quite poor, because we're looking at very
simple condition indicators, things like

297
00:17:07.709 --> 00:17:11.829
<v Alex Hill>current, torque, temperature, pressure,
things that actually by themselves, they're

298
00:17:11.829 --> 00:17:12.810
<v Alex Hill>not very interesting.

299
00:17:13.270 --> 00:17:17.099
<v Alex Hill>But when you start to look at them over a
length of time, and you start to combine

300
00:17:17.099 --> 00:17:20.229
<v Alex Hill>them with other things, and you start to
combine them with data sets that you feel

301
00:17:20.229 --> 00:17:23.989
<v Alex Hill>are also similar, then you start to build
quite an interesting picture, then you

302
00:17:23.989 --> 00:17:26.329
<v Alex Hill>start to build context that becomes more
meaningful.

303
00:17:26.838 --> 00:17:30.598
<v Alex Hill>And one of the best ways to build that
context is by learning from what the humans

304
00:17:30.598 --> 00:17:30.859
<v Alex Hill>do.

305
00:17:31.540 --> 00:17:32.910
<v Alex Hill>They, they know this job already.

306
00:17:33.469 --> 00:17:36.729
<v Alex Hill>Why sit them down in a, in a room and get
them to spell out everything when actually

307
00:17:36.869 --> 00:17:37.930
<v Alex Hill>we can learn on the job?

308
00:17:38.109 --> 00:17:38.449
<v Alex Hill>Yeah.

309
00:17:38.869 --> 00:17:39.849
<v Alex Hill>So that's what we do.

310
00:17:40.189 --> 00:17:44.810
<v Alex Hill>As people interact with the application,
as people go and perform work, we learn

311
00:17:44.810 --> 00:17:45.430
<v Alex Hill>from that as well.

312
00:17:45.550 --> 00:17:46.310
<v Alex Hill>What do they do?

313
00:17:46.630 --> 00:17:47.469
<v Alex Hill>Why did they do it?

314
00:17:47.829 --> 00:17:51.510
<v Alex Hill>That's recorded in the maintenance
management system, or within sense I predict the

315
00:17:51.510 --> 00:17:52.209
<v Alex Hill>maintenance itself.

316
00:17:52.800 --> 00:17:57.160
<v Alex Hill>And we combine those two things, we
combine this industrial machine data, as well as

317
00:17:57.160 --> 00:18:01.920
<v Alex Hill>this human data, and that helps us build
context automatically by people just

318
00:18:01.920 --> 00:18:05.300
<v Alex Hill>performing their normal roles, and it
helps the algorithms become more and more

319
00:18:05.719 --> 00:18:11.469
<v Alex Hill>effective, more and more efficient, and it
helps people ultimately zero in on, More

320
00:18:11.469 --> 00:18:15.229
<v Alex Hill>and more, what they need to be doing and
relate that to a business outcome.

321
00:18:16.209 --> 00:18:19.410
<v Alex Hill>So we're matching all of these things in
the background.

322
00:18:20.089 --> 00:18:24.089
<v Alex Hill>And then learning from what people do
about it, think of it as a, almost like a

323
00:18:24.089 --> 00:18:27.489
<v Alex Hill>music recommendation algorithm, but it's
focused on machines.

324
00:18:28.719 --> 00:18:29.839
<v Niall Sullivan>We use that on the website.

325
00:18:30.000 --> 00:18:31.479
<v Niall Sullivan>Yeah, we'll update the website with that.

326
00:18:32.000 --> 00:18:33.229
<v Niall Sullivan>Um, no, it's really great.

327
00:18:33.280 --> 00:18:37.719
<v Niall Sullivan>I mean, so just, just to finish off,
because I know we've got a lot of, a lot of

328
00:18:37.719 --> 00:18:40.959
<v Niall Sullivan>customers in it, in this particular area,
and you've sort of, I guess covered a lot

329
00:18:40.959 --> 00:18:45.380
<v Niall Sullivan>of the reasons why, you know, you know,
how advanced they are in terms of, um,

330
00:18:45.400 --> 00:18:47.800
<v Niall Sullivan>technology and culture, mindset, etc.

331
00:18:47.949 --> 00:18:52.920
<v Niall Sullivan>But is there, just to finish, is there
just one reason we can pinpoint why sense our

332
00:18:52.920 --> 00:18:56.140
<v Niall Sullivan>predictctor Matenance has been so
successful in the heavy industry.

333
00:18:56.900 --> 00:18:57.609
<v Alex Hill>Save the money.

334
00:18:57.969 --> 00:19:02.670
<v Alex Hill>Uh, we, we wouldn't be where we are if we
didn't have solid use cases of companies.

335
00:19:03.500 --> 00:19:06.650
<v Alex Hill>Actually saving money using Sensi predict
maintenance.

336
00:19:07.050 --> 00:19:11.839
<v Alex Hill>And the fact is, we can leverage their
existing investments, we can repurpose that

337
00:19:12.290 --> 00:19:17.270
<v Alex Hill>without them really doing much at all, and
give them so much more capability to

338
00:19:17.270 --> 00:19:22.489
<v Alex Hill>improve their efficiency, to do it in a
safe and sustainable manner, and to improve

339
00:19:22.489 --> 00:19:26.130
<v Alex Hill>their bottom line in a really very
measurable way.

340
00:19:26.780 --> 00:19:30.939
<v Alex Hill>And, and, and the, the return on
investment is, you know, typically 6 months or so,

341
00:19:31.099 --> 00:19:32.459
<v Alex Hill>so it becomes a no-brainer.

342
00:19:33.640 --> 00:19:34.599
<v Niall Sullivan>Yeah, fantastic.

343
00:19:34.719 --> 00:19:35.760
<v Niall Sullivan>Well summarized as well.

344
00:19:35.839 --> 00:19:39.319
<v Niall Sullivan>I think, and that's a great way to end our
three part series as well.

345
00:19:39.439 --> 00:19:43.760
<v Niall Sullivan>So, um, I'd like to thank everyone for
listening out there and also obviously thank

346
00:19:43.760 --> 00:19:46.280
<v Niall Sullivan>you to Alex again for taking part in this
series.

347
00:19:46.479 --> 00:19:46.599
<v Niall Sullivan>Thanks

348
00:19:46.599 --> 00:19:47.079
<v Alex Hill>for having me, Nia.

349
00:19:47.160 --> 00:19:47.560
<v Alex Hill>It's been fun.

350
00:19:47.829 --> 00:19:49.020
<v Niall Sullivan>Yeah, been really fascinating.

351
00:19:49.239 --> 00:19:54.079
<v Niall Sullivan>So, um, so yeah, so obviously there'll be
plenty of trend detection, um, episodes to

352
00:19:54.079 --> 00:19:54.199
<v Niall Sullivan>come.

353
00:19:54.319 --> 00:19:58.170
<v Niall Sullivan>So please subscribe in your usual channels
and we'll catch you on the next episode.

354
00:19:58.400 --> 00:19:59.339
<v Niall Sullivan>Thank you very much.

355
00:20:04.829 --> 00:20:09.790
<v Speaker 1>Please like and subscribe on all major
podcast channels and find out more about

356
00:20:09.790 --> 00:20:13.310
<v Speaker 1>Sensi predictive maintenance at
Siemens.com.
