WEBVTT
Language: en-US

1
00:00:02.690 --> 00:00:06.170
<v Speaker 1>Welcome to the trend detection podcast
powered by Siemens.

2
00:00:09.140 --> 00:00:09.939
<v Speaker 2>Welcome everybody.

3
00:00:10.140 --> 00:00:14.140
<v Speaker 2>Uh, we're here in the, uh, wonderful Brew
Lab Innovation Center.

4
00:00:14.579 --> 00:00:19.319
<v Speaker 2>Uh, our backdrop is our automated craft
brewery, and it's all about innovation here,

5
00:00:19.340 --> 00:00:24.579
<v Speaker 2>and, uh, we're very privileged today to
have, uh, some visitors, uh, from the

6
00:00:24.579 --> 00:00:30.100
<v Speaker 2>Siemens Sensai, uh, business, and, uh, to
my right is uh Alex Hill, founder of

7
00:00:30.100 --> 00:00:34.880
<v Speaker 2>Sensai and, uh, head of AI for the Siemens
business globally.

8
00:00:35.689 --> 00:00:38.279
<v Speaker 2>Uh, and to his right, Nick King from NZ
Controls.

9
00:00:38.950 --> 00:00:44.360
<v Speaker 2>And Nick is a solution partner we work
with here for local implementation of the AI

10
00:00:44.360 --> 00:00:44.840
<v Speaker 2>solutions.

11
00:00:45.869 --> 00:00:49.740
<v Speaker 2>So I guess let's just start with a little
bit of a, a broader introduction, uh, for

12
00:00:49.740 --> 00:00:50.360
<v Speaker 2>the both of you.

13
00:00:50.819 --> 00:00:52.700
<v Speaker 2>Nick, perhaps from your side, right,

14
00:00:52.799 --> 00:00:56.479
<v Speaker 3>so we do uh system integration and we're
working with the customers in New Zealand

15
00:00:56.479 --> 00:01:00.659
<v Speaker 3>and around the world, but here in New
Zealand, and we're looking For tools all the

16
00:01:00.659 --> 00:01:04.730
<v Speaker 3>time to add value to data and to try to
really help them move forward and in New

17
00:01:04.730 --> 00:01:09.739
<v Speaker 3>Zealand I think it's well, well known
we've got this um productivity problem and I

18
00:01:09.739 --> 00:01:13.260
<v Speaker 3>think um there's, there's a lot of tools
out there like Sensei that can really make

19
00:01:13.260 --> 00:01:15.239
<v Speaker 3>a difference, um, and scale.

20
00:01:15.480 --> 00:01:18.529
<v Speaker 3>So quite excited to, to be part of the
team with Sens.

21
00:01:19.870 --> 00:01:21.739
<v Speaker 2>And Alex, you're normally based in the

22
00:01:21.739 --> 00:01:26.120
<v Speaker 4>US, as you can hear by my accent, yeah,
there's a deep southern accent there,

23
00:01:26.349 --> 00:01:27.150
<v Speaker 4>usually based in the US.

24
00:01:27.269 --> 00:01:32.319
<v Speaker 4>I spent a lot of my time in the UK and
since I was originally founded in the UK and

25
00:01:32.319 --> 00:01:35.680
<v Speaker 4>now I get to spend my time coming and
meeting wonderful partners like you, they can

26
00:01:35.680 --> 00:01:38.459
<v Speaker 4>help us accelerate what we're trying to
do, which is ultimately.

27
00:01:38.910 --> 00:01:43.120
<v Speaker 4>Predictive maintenance at enterprise
scale, and when we say enterprise, tens of

28
00:01:43.120 --> 00:01:46.319
<v Speaker 4>thousands of machines, things that people
have never really considered possible

29
00:01:46.319 --> 00:01:46.500
<v Speaker 4>before.

30
00:01:46.800 --> 00:01:50.160
<v Speaker 4>And just a minor correction, I'm, I'm one
of, one of the co-founders, uh, so

31
00:01:50.160 --> 00:01:54.480
<v Speaker 4>there's, there's a, there's a, there's a
couple of others, and uh, we are, we are

32
00:01:54.480 --> 00:01:57.599
<v Speaker 4>leading the charge for predictive
maintenance AI within Siemens.

33
00:01:58.480 --> 00:02:02.760
<v Speaker 2>So where we are here is all about
innovation and thought leadership, and I guess you

34
00:02:02.760 --> 00:02:07.919
<v Speaker 2>can't find a more bleeding edge topic than
AI at the moment, but it's also a scary

35
00:02:07.919 --> 00:02:08.240
<v Speaker 2>topic.

36
00:02:08.440 --> 00:02:14.320
<v Speaker 2>So, uh, what are the tools, I guess, in
general life that you are seeing out there

37
00:02:14.320 --> 00:02:14.880
<v Speaker 2>in AI?

38
00:02:16.119 --> 00:02:17.270
<v Speaker 4>That's a broad topic, isn't it?

39
00:02:17.539 --> 00:02:20.630
<v Speaker 4>That's, um, I mean, AI is touching
literally every single thing.

40
00:02:20.839 --> 00:02:26.910
<v Speaker 4>I think it's Unimaginable, it was
unimaginable two years ago that AI is going to

41
00:02:26.910 --> 00:02:31.190
<v Speaker 4>start affecting the creative industries,
for example, and now, any of us can log in

42
00:02:31.190 --> 00:02:36.270
<v Speaker 4>and, you know, I want a video of a cat
eating a rose and, you know, flying into

43
00:02:36.270 --> 00:02:36.679
<v Speaker 4>space.

44
00:02:37.550 --> 00:02:41.229
<v Speaker 4>Something that would take a creative team
really quite a long time to do, and now

45
00:02:41.229 --> 00:02:43.089
<v Speaker 4>you can get something pretty decent
immediately.

46
00:02:43.339 --> 00:02:47.360
<v Speaker 4>And we can take that kind of concept and
that creativity into spaces that have

47
00:02:47.360 --> 00:02:50.910
<v Speaker 4>generally not seen a tremendous amount of
creativity, um.

48
00:02:51.350 --> 00:02:54.860
<v Speaker 4>Which I've got an argument against
actually, I, I think engineering should be

49
00:02:54.860 --> 00:03:00.529
<v Speaker 4>tremendously creative, but AI is
disrupting everything, um, and you guys are, are,

50
00:03:00.550 --> 00:03:03.800
<v Speaker 4>are at the forefront of implementing it,
so I think the question is actually better

51
00:03:03.800 --> 00:03:04.720
<v Speaker 4>turned around on you.

52
00:03:05.529 --> 00:03:08.970
<v Speaker 3>Yeah, so for me it's about finding tools
that are real and practical that I can

53
00:03:08.970 --> 00:03:11.369
<v Speaker 3>deploy, um, and you know that's been a
challenge.

54
00:03:11.449 --> 00:03:13.369
<v Speaker 3>Like there's a lot of hype out there and a
lot of excitement.

55
00:03:13.610 --> 00:03:16.490
<v Speaker 3>We use it every day for little bits and
pieces, and we're using it more and more and

56
00:03:16.490 --> 00:03:18.929
<v Speaker 3>we're seeking new opportunities with it.

57
00:03:19.289 --> 00:03:23.369
<v Speaker 3>But, um, you know, the likes of um Sight
gives us a really powerful tool, real boots

58
00:03:23.369 --> 00:03:24.440
<v Speaker 3>on the ground application.

59
00:03:24.690 --> 00:03:29.020
<v Speaker 3>You can see value being derived from it
really quickly now, so it's really exciting.

60
00:03:30.050 --> 00:03:31.149
<v Speaker 2>So speaking of scale.

61
00:03:31.910 --> 00:03:36.229
<v Speaker 2>You can go huge, you can go multiple
countries, all of that sort of stuff is pretty

62
00:03:36.229 --> 00:03:36.550
<v Speaker 2>clear.

63
00:03:36.990 --> 00:03:38.809
<v Speaker 2>But when does it become viable?

64
00:03:38.910 --> 00:03:42.470
<v Speaker 2>How, how, um, accessible is this for a
smaller business?

65
00:03:42.710 --> 00:03:46.710
<v Speaker 2>You know, New Zealand has got a lot of
small to medium enterprises with one factory

66
00:03:46.710 --> 00:03:48.270
<v Speaker 2>or a small collection of factories.

67
00:03:49.029 --> 00:03:50.149
<v Speaker 2>How accessible is it for them?

68
00:03:51.380 --> 00:03:55.190
<v Speaker 4>Scale is something we'd like to talk about
at the enterprise level of the 10s of

69
00:03:55.190 --> 00:03:56.880
<v Speaker 4>thousands of machines, and that's really
exciting.

70
00:03:57.919 --> 00:04:03.130
<v Speaker 4>But it's also exciting for those smaller
organizations, where as a predominantly an

71
00:04:03.130 --> 00:04:07.770
<v Speaker 4>AI focused organization, we're learning a
tremendous amount from all kinds of

72
00:04:07.770 --> 00:04:08.479
<v Speaker 4>different places.

73
00:04:08.770 --> 00:04:11.570
<v Speaker 4>We don't share that learning amongst
customers, it's very important that we have

74
00:04:11.570 --> 00:04:14.750
<v Speaker 4>that data sovereignty, and we protect that
customer information.

75
00:04:15.580 --> 00:04:19.679
<v Speaker 4>But we are ultimately maintenance and
predictive maintenance experts.

76
00:04:20.559 --> 00:04:23.929
<v Speaker 4>And so we can help these small
organizations become more efficient.

77
00:04:24.279 --> 00:04:29.160
<v Speaker 4>Typically we say that uh from an
engagement point of view, start with 50 machines or

78
00:04:29.160 --> 00:04:33.399
<v Speaker 4>so, and you can start to see a real return
on investment within 6 months on that

79
00:04:33.399 --> 00:04:35.600
<v Speaker 4>time and hopefully we can achieve a full
ROI.

80
00:04:35.920 --> 00:04:37.880
<v Speaker 3>So, so for the audience benefit, what's a
machine?

81
00:04:38.000 --> 00:04:39.079
<v Speaker 3>We've got the brewla behind us.

82
00:04:39.119 --> 00:04:40.339
<v Speaker 3>Is that a machine or

83
00:04:40.679 --> 00:04:41.660
<v Speaker 4>that's a really good question.

84
00:04:41.880 --> 00:04:43.320
<v Speaker 4>So yeah, we have the brewer behind us.

85
00:04:43.540 --> 00:04:48.220
<v Speaker 4>And, and one of our um pain points with
predictive maintenance has always been that

86
00:04:48.220 --> 00:04:52.019
<v Speaker 4>it's typically been very model based, and
so that means you need to sit down, you're

87
00:04:52.019 --> 00:04:56.070
<v Speaker 4>gonna need to get a, you know, do a full
um failure mode analysis and understand

88
00:04:56.070 --> 00:05:00.529
<v Speaker 4>that machine, and is that going to be
worth it for your $100 valve or drive that,

89
00:05:00.859 --> 00:05:05.339
<v Speaker 4>that could fail, but also could also bring
down your, your whole piece of equipment

90
00:05:05.339 --> 00:05:10.619
<v Speaker 4>or or facility, but traditionally the
answer has been no, this is a $100 drive, I'll

91
00:05:10.619 --> 00:05:11.619
<v Speaker 4>just replace it instead.

92
00:05:12.140 --> 00:05:17.200
<v Speaker 4>With Sensei and in a scale, we can go from
that $10,000 sorry, $10,000 machine view

93
00:05:17.779 --> 00:05:22.000
<v Speaker 4>down to the single component and make it
worthwhile because we are learning

94
00:05:22.410 --> 00:05:24.459
<v Speaker 4>individual machine behavior based on the
data.

95
00:05:24.739 --> 00:05:27.640
<v Speaker 4>So something like this little, uh, I don't
even know what this is to be

96
00:05:27.640 --> 00:05:29.260
<v Speaker 2>like mess

97
00:05:29.260 --> 00:05:29.700
<v Speaker 4>flow meter

98
00:05:29.700 --> 00:05:30.959
<v Speaker 2>mass flow meters.

99
00:05:31.100 --> 00:05:31.619
<v Speaker 4>So I'm

100
00:05:31.619 --> 00:05:31.750
<v Speaker 2>happy

101
00:05:31.750 --> 00:05:31.790
<v Speaker 4>you know.

102
00:05:34.859 --> 00:05:36.049
<v Speaker 4>I mean you can tell that we're not.

103
00:05:37.089 --> 00:05:41.529
<v Speaker 4>So we can now monitor something like that,
and we don't have to spend $50,000 making

104
00:05:41.529 --> 00:05:45.519
<v Speaker 4>a model and then tweaking it and then
passing the cost of maintaining that to

105
00:05:45.519 --> 00:05:46.049
<v Speaker 4>someone else.

106
00:05:46.250 --> 00:05:47.029
<v Speaker 4>It's automatic.

107
00:05:47.609 --> 00:05:50.190
<v Speaker 4>You have the data, bring it in, great.

108
00:05:50.529 --> 00:05:55.769
<v Speaker 4>Since I will look at it, and every other
single component within this machine.

109
00:05:56.209 --> 00:05:59.739
<v Speaker 4>You ask what an asset is, and it's really
actually our, our definition is whatever

110
00:05:59.739 --> 00:06:00.350
<v Speaker 4>you call it.

111
00:06:00.809 --> 00:06:04.619
<v Speaker 3>Yes, so it's part of the design phase or
the the journey you go on is to define the

112
00:06:04.619 --> 00:06:07.200
<v Speaker 3>assets and what is what is an asset, yeah.

113
00:06:08.399 --> 00:06:14.269
<v Speaker 2>And if I've got an existing system I'm
using for managing my maintenance or you

114
00:06:14.269 --> 00:06:16.899
<v Speaker 2>know, the, the traditional rules-based
maintenance program.

115
00:06:17.670 --> 00:06:18.829
<v Speaker 2>Can I still work with that?

116
00:06:19.429 --> 00:06:24.429
<v Speaker 4>Absolutely, and again a core philosophy of
ours is we want to work with what you

117
00:06:24.429 --> 00:06:27.570
<v Speaker 4>have, we don't want to throw away any of
those existing investments.

118
00:06:28.109 --> 00:06:33.130
<v Speaker 4>What we also do accept is that
traditionally a maintenance management system, um,

119
00:06:33.429 --> 00:06:36.799
<v Speaker 4>the quality of data in there is, Not good.

120
00:06:37.589 --> 00:06:40.570
<v Speaker 4>People will often put, yeah, you know,
last week, I fixed it.

121
00:06:41.640 --> 00:06:45.170
<v Speaker 4>And the failuremo was other, and, and
that's the bare minimum that they've needed to

122
00:06:45.170 --> 00:06:50.329
<v Speaker 4>get through, and there's a part of the
human element to this, and, and relying on

123
00:06:50.329 --> 00:06:54.690
<v Speaker 4>partners to come in and lead these
workshops is helping people to understand, OK,

124
00:06:54.809 --> 00:06:58.209
<v Speaker 4>well you might have done it in the past,
but now that we're using AI it's wanting to

125
00:06:58.209 --> 00:07:02.519
<v Speaker 4>learn from what you did, and that's a
core, uh, part of how we scale.

126
00:07:02.649 --> 00:07:04.489
<v Speaker 3>The more you feed it, the more it's going
to give you back.

127
00:07:04.579 --> 00:07:08.089
<v Speaker 4>Yeah, so the better quality information
you put in, the better quality information

128
00:07:08.089 --> 00:07:12.290
<v Speaker 4>you'll get out, and there's a lot of work
that we do to help improve the contextual

129
00:07:12.290 --> 00:07:13.079
<v Speaker 4>information around that.

130
00:07:13.450 --> 00:07:17.450
<v Speaker 4>But now we're starting to see, well, if we
can educate a reliability engineer to

131
00:07:17.450 --> 00:07:21.929
<v Speaker 4>say, OK, I've fixed it in this way, and I,
I'm tighter now in how I record this in

132
00:07:21.929 --> 00:07:23.309
<v Speaker 4>my maintenance management system.

133
00:07:23.779 --> 00:07:28.410
<v Speaker 4>The AI will give me better results, so
that I can be better and more efficient at my

134
00:07:28.410 --> 00:07:32.529
<v Speaker 4>role, and that's a really nice powerful
story that often people don't fully

135
00:07:32.529 --> 00:07:34.989
<v Speaker 4>appreciate, but they, they understand once
we educate them.

136
00:07:35.529 --> 00:07:40.089
<v Speaker 2>So the, the, uh, we talked earlier about
being able to upload, for example,

137
00:07:40.170 --> 00:07:45.809
<v Speaker 2>instruction manuals uh from the OEM uh
and, and SI will automatically look through

138
00:07:45.809 --> 00:07:49.649
<v Speaker 2>that and feed up the data, feed up the
information to uh to the repairer.

139
00:07:50.049 --> 00:07:54.100
<v Speaker 2>Um, you mentioned a feature earlier when
we were talking about the ability now to

140
00:07:54.100 --> 00:07:58.140
<v Speaker 2>make a video, like a how-to video, or
perhaps that engineer that's been there a

141
00:07:58.140 --> 00:08:02.519
<v Speaker 2>million years, take a photo he's doing and
take the photo.

142
00:08:02.980 --> 00:08:07.859
<v Speaker 2>So all that is also ingestible by the by
the Sensi tool, and it will feed that up

143
00:08:07.859 --> 00:08:08.380
<v Speaker 2>here.

144
00:08:08.549 --> 00:08:11.380
<v Speaker 2>Potentially all of the sites around the
world and in

145
00:08:11.380 --> 00:08:13.640
<v Speaker 4>particular is this institutional knowledge
capture.

146
00:08:13.720 --> 00:08:16.739
<v Speaker 4>What happens when your highly experienced
maintainers leave?

147
00:08:17.140 --> 00:08:22.799
<v Speaker 4>Uh, how can we start to, as an
organization, help our customers not lose all of that

148
00:08:22.799 --> 00:08:25.059
<v Speaker 4>information, and it could be videos, it
could be photos, it could be somebody

149
00:08:25.059 --> 00:08:29.410
<v Speaker 4>saying, I fixed the thing, but now we have
more contextual information that we can

150
00:08:29.410 --> 00:08:33.799
<v Speaker 4>wrap around that and use AI to augment
that, and that becomes much more powerful.

151
00:08:34.369 --> 00:08:38.549
<v Speaker 4>And that helps the new generation of
maintainers who can't come in to a facility and

152
00:08:38.549 --> 00:08:42.289
<v Speaker 4>put their hand on something, or just here
and OK, well I know exactly what I need to

153
00:08:42.289 --> 00:08:42.570
<v Speaker 4>do.

154
00:08:43.588 --> 00:08:48.908
<v Speaker 4>We need to use AI now to help augment
their roles, and we have the solution to do

155
00:08:48.908 --> 00:08:51.948
<v Speaker 4>that, it's proven, it's deployed, and we
can do it at scale.

156
00:08:52.609 --> 00:08:56.080
<v Speaker 2>And that information stays locked down
within the organization.

157
00:08:56.130 --> 00:08:57.909
<v Speaker 2>It's not shared to other customers.

158
00:08:58.650 --> 00:09:01.789
<v Speaker 2>So, and it's a software as a service, uh,
solution.

159
00:09:02.450 --> 00:09:08.289
<v Speaker 2>One of the barriers to assess model is
often security, uh, data sovereignty, those

160
00:09:08.289 --> 00:09:08.729
<v Speaker 2>sorts of things.

161
00:09:08.849 --> 00:09:09.929
<v Speaker 2>So how do we address that?

162
00:09:10.780 --> 00:09:12.780
<v Speaker 4>That's again a very important question.

163
00:09:12.859 --> 00:09:17.900
<v Speaker 4>Um, as a startup, and, and there was a
significant cost to us for doing that, we had

164
00:09:17.900 --> 00:09:23.299
<v Speaker 4>our own ISO 27,0001 certification, as well
as 9,0001, and we contracted, and we

165
00:09:23.299 --> 00:09:27.729
<v Speaker 4>still do, an independent third party to
come in and try to break it, try to do some

166
00:09:27.729 --> 00:09:29.440
<v Speaker 4>penetration testing every year.

167
00:09:29.900 --> 00:09:31.900
<v Speaker 4>We published those results to all of our
customers.

168
00:09:32.140 --> 00:09:34.150
<v Speaker 4>We've never had any significant issues.

169
00:09:34.419 --> 00:09:38.659
<v Speaker 4>Uh, the, you know, the most we've got is
like two medium things which are, Pretty

170
00:09:38.659 --> 00:09:41.229
<v Speaker 4>easy to fix, and we fix those in a week
and, and that's done.

171
00:09:41.590 --> 00:09:44.679
<v Speaker 4>So that data sovereignty is extremely
important.

172
00:09:44.950 --> 00:09:47.789
<v Speaker 4>We isolate everything, it's encrypted in
transit and at rest.

173
00:09:48.260 --> 00:09:52.849
<v Speaker 4>There is not, and we spend a lot of time
thinking about how we engineer this so that

174
00:09:52.849 --> 00:09:55.450
<v Speaker 4>there's no potential crossover of customer
information.

175
00:09:55.909 --> 00:09:58.020
<v Speaker 4>And you touched on an interesting point
when we started Sensei.

176
00:09:58.539 --> 00:10:01.750
<v Speaker 4>Part of it was how can we help the little
guy compete with the big guy.

177
00:10:02.109 --> 00:10:06.169
<v Speaker 4>Maybe we can use that data to, to help,
and, and I love the story.

178
00:10:07.299 --> 00:10:11.619
<v Speaker 4>But humanity or people or whatever,
they're not ready for it because ultimately

179
00:10:11.619 --> 00:10:15.700
<v Speaker 4>customers say this is my data, and you
must protect it, and I understand that, I get

180
00:10:15.700 --> 00:10:15.940
<v Speaker 4>it.

181
00:10:16.210 --> 00:10:20.460
<v Speaker 4>You know, there's this dream of what we
could achieve, and then what we also need to

182
00:10:20.460 --> 00:10:24.659
<v Speaker 4>achieve from a business perspective, and
we respect the need of the business to be

183
00:10:24.659 --> 00:10:25.739
<v Speaker 4>private and secure.

184
00:10:27.159 --> 00:10:32.840
<v Speaker 2>So we're here in our innovation center,
which is uh our investment in thought

185
00:10:32.840 --> 00:10:36.489
<v Speaker 2>leadership and innovation, and we're
always trying to show people what's possible.

186
00:10:36.729 --> 00:10:39.090
<v Speaker 2>With Sensi, how do we show people this?

187
00:10:39.280 --> 00:10:40.729
<v Speaker 2>What's the best way to demonstrate it?

188
00:10:42.070 --> 00:10:47.150
<v Speaker 2>If someone out there today is interested
to know more and wants us to get in touch.

189
00:10:48.340 --> 00:10:50.640
<v Speaker 3>I guess, I mean, I guess we're talking to
a New Zealand audience.

190
00:10:51.140 --> 00:10:52.820
<v Speaker 3>I mean, reach out to see to see yourself.

191
00:10:53.340 --> 00:10:58.580
<v Speaker 3>um, we're um like set myself up here to to
help deliver the projects, but we're here

192
00:10:58.580 --> 00:11:01.330
<v Speaker 3>to talk about what it can do, what it
can't do, how it might work for you.

193
00:11:01.690 --> 00:11:02.979
<v Speaker 3>So, you know, give us a call, you know.

194
00:11:03.085 --> 00:11:03.885
<v Speaker 3>It's as simple as that.

195
00:11:03.965 --> 00:11:04.044
<v Speaker 3>And

196
00:11:04.044 --> 00:11:07.085
<v Speaker 4>that's what comes with scalability, this
recognition that look, we can't do this

197
00:11:07.085 --> 00:11:07.385
<v Speaker 4>alone.

198
00:11:07.604 --> 00:11:11.684
<v Speaker 4>We need partners, we need people who have
that deep relationship with the customer,

199
00:11:11.765 --> 00:11:16.325
<v Speaker 4>who can do the integration, the
connectivity, and ultimately, at Sensai, we, we're

200
00:11:16.325 --> 00:11:18.104
<v Speaker 4>focusing on how do we solve this.

201
00:11:18.669 --> 00:11:24.340
<v Speaker 4>This um grand problem and philosophy, and
then we need the implementers and people

202
00:11:24.340 --> 00:11:24.940
<v Speaker 4>like you guys.

203
00:11:25.450 --> 00:11:25.460
<v Speaker 4>Yes,

204
00:11:25.570 --> 00:11:28.580
<v Speaker 3>there's quite a few steps and there's a
model to follow that you've developed and

205
00:11:28.580 --> 00:11:32.909
<v Speaker 3>it's well proven, but um there's that's
there for us to help take your our combined

206
00:11:32.909 --> 00:11:36.280
<v Speaker 3>customers on a journey and help, help
guide them right the way through the process,

207
00:11:36.659 --> 00:11:40.010
<v Speaker 3>right through to getting, making sure they
get value for their investment, you know.

208
00:11:40.739 --> 00:11:41.169
<v Speaker 3>So

209
00:11:41.169 --> 00:11:46.039
<v Speaker 2>I think that's super important, you know,
the, the The amount of time we've spent

210
00:11:46.039 --> 00:11:49.539
<v Speaker 2>talking with customers about this solution
until now it's quite clear that unless

211
00:11:49.539 --> 00:11:53.979
<v Speaker 2>you have a local team that can actually
implement it, then you're a long way from

212
00:11:54.549 --> 00:11:56.510
<v Speaker 2>Uh, you know, where it all happens, I
guess

213
00:11:56.510 --> 00:11:57.940
<v Speaker 4>it's all philosophical, isn't it?

214
00:11:57.960 --> 00:11:58.369
<v Speaker 4>It's a long flight.

215
00:12:00.250 --> 00:12:02.549
<v Speaker 3>Yeah, but there's a, there's a big,
there's a whole team there, like, so we can call

216
00:12:02.549 --> 00:12:04.250
<v Speaker 3>you, you'll help us, but we can also be
like,

217
00:12:04.380 --> 00:12:07.070
<v Speaker 4>it's about looking at local to local
support because ultimately we're talking about

218
00:12:07.070 --> 00:12:11.070
<v Speaker 4>AI, we're talking about automation of
these things, but this is again about people.

219
00:12:11.219 --> 00:12:15.750
<v Speaker 4>It's about making sure that when we work
with the reliability team, we're showcasing

220
00:12:15.750 --> 00:12:18.869
<v Speaker 4>them and we're doing that with local
support and building on those human

221
00:12:18.869 --> 00:12:19.460
<v Speaker 4>relationships.

222
00:12:19.750 --> 00:12:22.270
<v Speaker 4>There's a lot of fear about AI replacing
people.

223
00:12:22.659 --> 00:12:23.500
<v Speaker 4>It's not about that.

224
00:12:23.700 --> 00:12:27.539
<v Speaker 4>It's about AI helping people and how we've
really build people up to say, you did a

225
00:12:27.539 --> 00:12:27.729
<v Speaker 4>great job.

226
00:12:28.580 --> 00:12:32.219
<v Speaker 2>And that, that productivity that you've
talked about is, is really where it's at for

227
00:12:32.400 --> 00:12:33.250
<v Speaker 2>for New Zealand Inc.

228
00:12:33.330 --> 00:12:33.820
<v Speaker 2>I guess.

229
00:12:35.750 --> 00:12:36.530
<v Speaker 3>That was my phone.

230
00:12:38.960 --> 00:12:39.099
<v Speaker 3>Always listening, right?

231
00:12:42.880 --> 00:12:47.320
<v Speaker 2>So I guess in practical terms if someone
wants to see it in operation, we do have a

232
00:12:47.320 --> 00:12:51.260
<v Speaker 2>demo, uh, ability to log into a demo set
of data that's looking at real.

233
00:12:51.789 --> 00:12:55.109
<v Speaker 2>Uh, a blend of real and simulated data
across different industries.

234
00:12:55.510 --> 00:13:00.030
<v Speaker 2>Uh, so it is something we'll have here in,
in Brew Lab and have access to, uh, to

235
00:13:00.030 --> 00:13:03.049
<v Speaker 2>take customers through and show them what
it, what it looks like in real practical,

236
00:13:03.219 --> 00:13:04.080
<v Speaker 2>uh, terms.

237
00:13:04.630 --> 00:13:05.049
<v Speaker 2>Um,

238
00:13:05.789 --> 00:13:09.270
<v Speaker 4>come, come to the Brew lab and we can show
you running on Brewabb and, and it's a

239
00:13:09.270 --> 00:13:09.599
<v Speaker 4>cool

240
00:13:09.599 --> 00:13:09.809
<v Speaker 2>story.

241
00:13:09.960 --> 00:13:14.489
<v Speaker 2>We have cold beer, freshly brewed beer,
um, which are off camera, by the way.

242
00:13:17.599 --> 00:13:19.450
<v Speaker 2>Is there anything else, Alex?

243
00:13:21.679 --> 00:13:22.820
<v Speaker 2>You put me on the spot now.

244
00:13:24.059 --> 00:13:24.979
<v Speaker 2>I ran out of questions.

245
00:13:25.059 --> 00:13:25.799
<v Speaker 2>Yeah, I mean.

246
00:13:26.849 --> 00:13:30.530
<v Speaker 4>What I really want to emphasize is, is
this is about people, and, and we talk about

247
00:13:30.530 --> 00:13:34.330
<v Speaker 4>AI, we talk about machines, we talk about
condition monitoring, but this is about

248
00:13:34.330 --> 00:13:40.849
<v Speaker 4>showcasing how people and teams can
improve the efficiency of an organization, and

249
00:13:40.849 --> 00:13:46.929
<v Speaker 4>building up that story and making it easy
for often engineers are, and I'm, I'm an

250
00:13:46.929 --> 00:13:50.770
<v Speaker 4>engineer by training and background, so I
don't feel too bad saying this, Engineers

251
00:13:50.770 --> 00:13:54.510
<v Speaker 4>are very bad at communicating, how they
add value.

252
00:13:54.979 --> 00:13:58.940
<v Speaker 4>And what that means to the organization
and ultimately what we're doing is a beer

253
00:13:58.940 --> 00:14:02.950
<v Speaker 3>they'll probably complain about no one
listening to them, but you know,

254
00:14:03.270 --> 00:14:06.070
<v Speaker 4>and then we're really about helping them
illustrate that story.

255
00:14:06.559 --> 00:14:09.409
<v Speaker 3>Yeah, yeah, for me, for me in working in
the industry.

256
00:14:09.940 --> 00:14:13.890
<v Speaker 3>And why I really, uh, was really excited
when I saw Sensi is because, you know, I'm

257
00:14:13.890 --> 00:14:17.859
<v Speaker 3>always looking for that, um, application
that's very real and very deployable and

258
00:14:17.859 --> 00:14:21.820
<v Speaker 3>will get value quickly or have real value
to my customers because I don't want to go

259
00:14:21.820 --> 00:14:25.179
<v Speaker 3>and sell them, you know, sell them or tell
them about something that doesn't add

260
00:14:25.179 --> 00:14:29.859
<v Speaker 3>value, you know, it's gotta be, it's gotta
be a win-win, you know, um, so, you know,

261
00:14:29.909 --> 00:14:33.219
<v Speaker 3>I was really stoked to see that and for
me, the New Zealand productivity problem is

262
00:14:33.219 --> 00:14:33.619
<v Speaker 3>my problem.

263
00:14:33.700 --> 00:14:35.750
<v Speaker 3>I feel like, you know, I want to help
solve that problem.

264
00:14:36.140 --> 00:14:39.239
<v Speaker 3>So, you know, the likes of Sside there is
just like a great tool, you know.

265
00:14:39.669 --> 00:14:41.340
<v Speaker 3>So thank you, you know, for bringing it to
us.

266
00:14:41.520 --> 00:14:45.900
<v Speaker 4>Thank you for, for believing and, and,
and, and you know, focusing on, on the, you

267
00:14:45.900 --> 00:14:48.260
<v Speaker 4>understand the people element, you
understand what we're trying to do here, which is

268
00:14:48.260 --> 00:14:53.250
<v Speaker 4>not replace people, it's augment people,
help people, stop people focusing on the

269
00:14:53.250 --> 00:14:55.140
<v Speaker 4>things that really aren't that
interesting.

270
00:14:55.260 --> 00:14:58.900
<v Speaker 4>Do you want to spend your, you know, 8
hours a day looking at squiggly lines, trying

271
00:14:58.900 --> 00:15:00.809
<v Speaker 4>to figure out what to look at and what
that means?

272
00:15:01.260 --> 00:15:01.919
<v Speaker 4>Probably not.

273
00:15:02.539 --> 00:15:04.119
<v Speaker 4>Humans are much better at understanding.

274
00:15:04.489 --> 00:15:09.570
<v Speaker 4>Um, very complex, very strange problems,
very, uh, unusual situations.

275
00:15:09.900 --> 00:15:13.070
<v Speaker 4>AI is very good at understanding very well
defined problems.

276
00:15:13.340 --> 00:15:19.179
<v Speaker 4>And we've spent 10 years very expertly
defining condition monitoring and how you

277
00:15:19.179 --> 00:15:20.659
<v Speaker 4>relate that to predictive maintenance.

278
00:15:20.979 --> 00:15:25.969
<v Speaker 4>So let us take care of the mundanity of
things, and you, as an expert reliability

279
00:15:25.969 --> 00:15:29.900
<v Speaker 4>engineer, can focus on the really complex,
really interesting problems that deserve

280
00:15:29.900 --> 00:15:30.440
<v Speaker 4>your attention.

281
00:15:31.179 --> 00:15:35.299
<v Speaker 2>Well, I guess the core benefit of AI is
that it's monitoring everything all the

282
00:15:35.299 --> 00:15:35.700
<v Speaker 2>time.

283
00:15:36.119 --> 00:15:39.109
<v Speaker 2>So it's not a snapshot in time where a
guy's coming in and doing a vibration

284
00:15:39.109 --> 00:15:42.789
<v Speaker 2>analysis on an IR, uh, thermography survey
or something like that.

285
00:15:42.830 --> 00:15:44.739
<v Speaker 2>It's being monitored continuously.

286
00:15:44.979 --> 00:15:48.630
<v Speaker 2>And so your focus moves to the important
things and actually acting on some of

287
00:15:48.630 --> 00:15:48.900
<v Speaker 2>those.

288
00:15:49.320 --> 00:15:52.989
<v Speaker 4>Actually, you hit an interesting point
there that, um, often when people talk about

289
00:15:52.989 --> 00:15:55.859
<v Speaker 4>predictive maintenance or condition
monitoring, they think vibration, they think

290
00:15:55.859 --> 00:16:00.630
<v Speaker 4>rotational machinery, and they think
complex, expensive data capture.

291
00:16:00.969 --> 00:16:05.500
<v Speaker 4>It doesn't need to be, because when you're
using an AI that has been specifically

292
00:16:05.500 --> 00:16:09.419
<v Speaker 4>developed to understand condition
monitoring and predictive maintenance, it's very

293
00:16:09.419 --> 00:16:11.450
<v Speaker 4>good at taking inherently bad data.

294
00:16:12.330 --> 00:16:17.820
<v Speaker 4>So, if a reliability engineer was to come
along and take a snapshot of this and say,

295
00:16:17.859 --> 00:16:21.059
<v Speaker 4>well, this is the current, this is the
torque, this is the timing.

296
00:16:21.630 --> 00:16:25.969
<v Speaker 4>In isolation, it doesn't really mean much,
but when there's an AI looking at that

297
00:16:26.080 --> 00:16:31.109
<v Speaker 4>all of the time, it's able to notice
fractions of a percentage of change that will

298
00:16:31.109 --> 00:16:33.140
<v Speaker 4>have meaning, and it can add context.

299
00:16:33.429 --> 00:16:35.349
<v Speaker 4>And now it's able to say, well, Mr.

300
00:16:35.390 --> 00:16:36.349
<v Speaker 4>Reliability or Mrs.

301
00:16:36.429 --> 00:16:40.020
<v Speaker 4>Reliability Engineer, you need to come in
and pay attention to this because it's

302
00:16:40.020 --> 00:16:41.049
<v Speaker 4>changing in these ways.

303
00:16:41.489 --> 00:16:44.940
<v Speaker 4>And if you were just to take an
instantaneous look at that, it wouldn't be valuable,

304
00:16:45.179 --> 00:16:49.580
<v Speaker 4>but the AI can come in and really help to
prioritize your workload.

305
00:16:49.780 --> 00:16:50.820
<v Speaker 3>So it's an interesting point.

306
00:16:50.900 --> 00:16:54.700
<v Speaker 3>Like, uh, would you, if you go into a
customer site or a site and they, they only

307
00:16:54.700 --> 00:16:58.619
<v Speaker 3>have a certain number of instrumentation,
they don't have as much as you might like,

308
00:16:58.979 --> 00:17:02.659
<v Speaker 3>but do you just deploy it and find out, do
we get good data, or do you ask them to

309
00:17:02.659 --> 00:17:03.469
<v Speaker 3>start putting sensors in?

310
00:17:04.020 --> 00:17:05.089
<v Speaker 4>That's a really good question.

311
00:17:05.339 --> 00:17:09.810
<v Speaker 4>Um, in the past, and the dream was, uh,
just give us your, your data that looks like

312
00:17:09.810 --> 00:17:11.079
<v Speaker 4>a time series data and we can relate to
it.

313
00:17:11.489 --> 00:17:15.650
<v Speaker 4>And we, we found some failures there, uh,
often people want to experience something

314
00:17:15.650 --> 00:17:19.680
<v Speaker 4>immediately, so we come in with solution
partners, and we usually then put in some

315
00:17:19.680 --> 00:17:23.959
<v Speaker 4>sensors, so that we can get you playing
with it and working with it in a really just

316
00:17:23.959 --> 00:17:29.489
<v Speaker 4>a quick way and get you some quick wins,
and then, working together, we can do the

317
00:17:29.489 --> 00:17:33.969
<v Speaker 4>integration with the complex historians,
and the maintenance management system, and

318
00:17:33.969 --> 00:17:38.040
<v Speaker 4>that's the really powerful thing where,
Look, it's, it's not worth your time and

319
00:17:38.040 --> 00:17:41.380
<v Speaker 4>effort as an organization to put a
vibration sensor on

320
00:17:41.599 --> 00:17:43.380
<v Speaker 4>really, well, any of this.

321
00:17:44.040 --> 00:17:45.420
<v Speaker 4>But you're already capturing this data.

322
00:17:45.719 --> 00:17:49.439
<v Speaker 4>The PFCs controlling it can already tell
you the timing and the torque and the

323
00:17:49.439 --> 00:17:53.260
<v Speaker 4>current, and previously that wasn't used
for condition monitoring.

324
00:17:53.790 --> 00:17:56.239
<v Speaker 4>But with AI and with Senseii, we can do
that.

325
00:17:56.560 --> 00:18:00.349
<v Speaker 4>And so it's, it's the real dream of we can
come in, we can instrument things that

326
00:18:00.349 --> 00:18:04.479
<v Speaker 4>are really critical immediately, get you
some value immediately, and then you can

327
00:18:04.479 --> 00:18:08.359
<v Speaker 4>bring in all of this other information
that traditionally wasn't thought of as

328
00:18:08.359 --> 00:18:10.699
<v Speaker 4>condition monitoring information, but now
can be.

329
00:18:11.040 --> 00:18:14.739
<v Speaker 4>And some of our most successful customers
have never installed an extra sensor.

330
00:18:15.040 --> 00:18:19.050
<v Speaker 4>They've just queried the PLCs and they
don't necessarily need to be seen as PLCs.

331
00:18:19.459 --> 00:18:21.670
<v Speaker 4>Uh, you know, we have all kinds of
different manufacturers.

332
00:18:22.060 --> 00:18:26.979
<v Speaker 4>As long as you have some form of
automation installed in the last 20 years, you have

333
00:18:26.979 --> 00:18:28.540
<v Speaker 4>benefit to be gained from Sensai.

334
00:18:29.640 --> 00:18:29.770
<v Speaker 2>Hm.

335
00:18:31.449 --> 00:18:31.750
<v Speaker 2>2.

336
00:18:32.770 --> 00:18:33.140
<v Speaker 4>It's, right?

337
00:18:34.260 --> 00:18:38.550
<v Speaker 2>It sounds like a no-brainer to me, um,
obviously, but, uh, let's talk a little bit

338
00:18:38.550 --> 00:18:42.119
<v Speaker 2>about, uh, cost, price, value.

339
00:18:43.140 --> 00:18:44.739
<v Speaker 2>A lot of people are gonna go, yeah, but
how much?

340
00:18:45.310 --> 00:18:49.109
<v Speaker 2>And I don't want a price, but how, how
accessible is it from a from a value

341
00:18:49.109 --> 00:18:49.750
<v Speaker 2>perspective?

342
00:18:50.060 --> 00:18:50.849
<v Speaker 2>Like how quick is the ROI?

343
00:18:50.859 --> 00:18:51.550
<v Speaker 2>I guess it's probably

344
00:18:51.550 --> 00:18:53.420
<v Speaker 4>the best way to look at it.

345
00:18:53.589 --> 00:18:59.430
<v Speaker 4>Typically we aim for achieving ROI with
the customer 3 to 6 months, which is

346
00:18:59.430 --> 00:19:00.280
<v Speaker 4>phenomenally.

347
00:19:00.790 --> 00:19:01.930
<v Speaker 2>3 to 6 months

348
00:19:06.989 --> 00:19:08.030
<v Speaker 4>we want this to be a no brainer.

349
00:19:08.150 --> 00:19:08.969
<v Speaker 4>We want this to be easy.

350
00:19:09.660 --> 00:19:12.770
<v Speaker 4>It is not easy, and I'm not going to
pretend it is because there's a lot of

351
00:19:12.770 --> 00:19:13.160
<v Speaker 4>integration.

352
00:19:13.699 --> 00:19:15.020
<v Speaker 4>There's there's complexity in that.

353
00:19:15.260 --> 00:19:17.140
<v Speaker 4>There's training, there's the methodology.

354
00:19:17.459 --> 00:19:18.459
<v Speaker 4>There's some commitment required.

355
00:19:18.540 --> 00:19:19.180
<v Speaker 4>There's some commitment.

356
00:19:19.300 --> 00:19:20.099
<v Speaker 4>I would love it to be easy.

357
00:19:20.219 --> 00:19:21.050
<v Speaker 4>That, that's still my vision.

358
00:19:21.060 --> 00:19:22.609
<v Speaker 4>It's still what I'm pushing the team for.

359
00:19:22.869 --> 00:19:23.800
<v Speaker 4>Just make it easy.

360
00:19:24.420 --> 00:19:26.300
<v Speaker 4>But we have to still operate in the real
world.

361
00:19:26.579 --> 00:19:31.339
<v Speaker 4>There, there is this commitment, time,
effort, uh, human resources that are still

362
00:19:31.339 --> 00:19:31.880
<v Speaker 4>needed.

363
00:19:32.180 --> 00:19:36.400
<v Speaker 4>And even with that, we can achieve an ROI
3 to 6 months vibration.

364
00:19:38.219 --> 00:19:39.099
<v Speaker 2>What even is that?

365
00:19:40.550 --> 00:19:41.439
<v Speaker 4>A mystery machine,

366
00:19:45.030 --> 00:19:45.859
<v Speaker 2>speaking of vibration.

367
00:19:48.030 --> 00:19:54.390
<v Speaker 2>So 3 to 6 months seems like an incredible
return on investment, a very short time.

368
00:19:54.719 --> 00:19:58.189
<v Speaker 4>Yeah, and, and that's that's why again we,
we say scale.

369
00:19:58.540 --> 00:20:02.560
<v Speaker 4>A lot of customers often will say, well,
can I bring in my, my critical machines to

370
00:20:02.560 --> 00:20:03.010
<v Speaker 4>test you out?

371
00:20:03.199 --> 00:20:03.839
<v Speaker 4>Just 1 or 2.

372
00:20:04.030 --> 00:20:08.829
<v Speaker 4>Yeah, and our argument will be, well, you
can, but you will not see value and your

373
00:20:08.829 --> 00:20:11.550
<v Speaker 4>project will fail because your critical
machines.

374
00:20:12.349 --> 00:20:15.310
<v Speaker 4>Are critical, you're already monitoring
them, you're already looking at them,

375
00:20:15.589 --> 00:20:16.910
<v Speaker 4>they're not going to fail in that
timeframe.

376
00:20:17.819 --> 00:20:21.219
<v Speaker 4>I would love to be able to sit here and
say we've never had any failures, and it's

377
00:20:21.219 --> 00:20:23.839
<v Speaker 4>been amazing and you know, we're just
perfect, but we're not.

378
00:20:24.060 --> 00:20:27.880
<v Speaker 4>We have had failed projects, and many of
those have been where the customer says,

379
00:20:28.760 --> 00:20:32.140
<v Speaker 4>I've got my 20 critical assets, you
monitor these, so we do.

380
00:20:32.969 --> 00:20:34.560
<v Speaker 4>And we can't say anything interesting
about them.

381
00:20:34.810 --> 00:20:35.770
<v Speaker 4>They're expecting magic.

382
00:20:35.930 --> 00:20:40.209
<v Speaker 3>Right, so you, so it's magic, but they,
they must be, they might can't be surprised

383
00:20:40.209 --> 00:20:43.089
<v Speaker 3>what you actually come up with, like
what's insight tells them they didn't know

384
00:20:43.089 --> 00:20:43.400
<v Speaker 3>about.

385
00:20:43.849 --> 00:20:44.030
<v Speaker 3>Sometimes,

386
00:20:44.329 --> 00:20:47.560
<v Speaker 4>but often because it's a critical machine,
it's, it's, it's fine.

387
00:20:47.969 --> 00:20:50.670
<v Speaker 4>Because you've already got some really
good scheduled maintenance on that.

388
00:20:51.050 --> 00:20:54.520
<v Speaker 4>And actually to relate back to an earlier
point of yours, we do not advocate getting

389
00:20:54.520 --> 00:20:56.609
<v Speaker 4>rid of your existing maintenance
practices.

390
00:20:56.989 --> 00:20:59.099
<v Speaker 4>This is a journey that you must go on.

391
00:20:59.430 --> 00:21:03.130
<v Speaker 4>This is something that we developed the
sense night maintenance methodology around

392
00:21:03.390 --> 00:21:09.229
<v Speaker 4>of take what you have and build upon that,
and as you trust the system more, you can

393
00:21:09.229 --> 00:21:12.790
<v Speaker 4>get more and more value from it, and you
can start to save money in your scheduled

394
00:21:12.790 --> 00:21:16.589
<v Speaker 4>maintenance practices, but again, it's a
journey, we're never going to say, you wind

395
00:21:16.589 --> 00:21:17.390
<v Speaker 4>it back over time.

396
00:21:17.550 --> 00:21:21.010
<v Speaker 4>Yeah, yeah, we're not gonna say rip it
out, and there will always be a blend.

397
00:21:21.310 --> 00:21:23.569
<v Speaker 4>We'll never say it, well, maybe.

398
00:21:24.750 --> 00:21:29.069
<v Speaker 4>I would love to get to 100% predict
maintenance, but realistically, you have safety

399
00:21:29.069 --> 00:21:33.449
<v Speaker 4>cases, business cases, some areas are
safety critical, you need to do these things.

400
00:21:33.630 --> 00:21:36.489
<v Speaker 4>And so it's a blend of technologies, it's
a blend of methodologies.

401
00:21:38.459 --> 00:21:43.400
<v Speaker 1>Please like and subscribe on all major
podcast channels and find out more about

402
00:21:43.400 --> 00:21:46.780
<v Speaker 1>Sensi predictive maintenance at
Siemens.com.
