WEBVTT
Language: en-US

1
00:00:03.250 --> 00:00:09.220
<v Speaker 1>Yeah, I mean, we are looking at normally
for our customers into certain areas, which

2
00:00:09.220 --> 00:00:15.460
<v Speaker 1>is around reliability and as you
mentioned, cost in terms of preventing the

3
00:00:15.460 --> 00:00:21.620
<v Speaker 1>downtime, downtime cost, and there's a
huge potential to address those two main

4
00:00:21.620 --> 00:00:23.520
<v Speaker 1>drivers or KPIs.

5
00:00:25.370 --> 00:00:26.149
<v Speaker 1>Welcome to the

6
00:00:26.149 --> 00:00:29.120
<v Speaker 2>trend detection podcast powered by
Siemens.

7
00:00:29.450 --> 00:00:33.439
<v Speaker 3>Hello, my name is Pate Perina and I'm the
host of today's episode of the Trend

8
00:00:33.439 --> 00:00:34.509
<v Speaker 3>detection podcast.

9
00:00:35.369 --> 00:00:40.000
<v Speaker 3>I have here with me a special guest, Louis
Marlow, who is the product and portfolio

10
00:00:40.000 --> 00:00:45.009
<v Speaker 3>manager for IoT and Analytics within the
digital drive train at Siemens, and he's

11
00:00:45.009 --> 00:00:47.520
<v Speaker 3>also leading the cloud portfolio there.

12
00:00:47.810 --> 00:00:49.310
<v Speaker 3>Hello and welcome, Lewis.

13
00:00:49.770 --> 00:00:51.490
<v Speaker 1>Hi Matte, thanks for having me.

14
00:00:52.500 --> 00:00:53.180
<v Speaker 3>Thanks for coming.

15
00:00:53.340 --> 00:00:57.139
<v Speaker 3>To kick things off, could you please
explain to our listeners what it is that you do

16
00:00:57.139 --> 00:01:00.340
<v Speaker 3>as product and portfolio manager and how
you came about it?

17
00:01:01.169 --> 00:01:01.659
<v Speaker 1>Yeah, sure.

18
00:01:01.819 --> 00:01:07.250
<v Speaker 1>So I'm within the digital industry motion
Control in the digital drivechain

19
00:01:07.569 --> 00:01:12.760
<v Speaker 1>organization leading the cloud portfolio,
and we are looking at digitalization

20
00:01:12.760 --> 00:01:18.660
<v Speaker 1>solutions around the drivetrain technology
within the field of IoT and analytics, as

21
00:01:18.660 --> 00:01:19.180
<v Speaker 1>we call it.

22
00:01:19.339 --> 00:01:24.059
<v Speaker 1>So this is kind of the value stream, and
the product and portfolio manager role, we

23
00:01:24.059 --> 00:01:28.720
<v Speaker 1>often refer to as the entrepreneur of, of
the kind of product, solution.

24
00:01:29.589 --> 00:01:31.199
<v Speaker 1>Driving the success in the market.

25
00:01:31.309 --> 00:01:37.300
<v Speaker 1>And yeah, I mean, I'm within theigchain
team and family since the beginning, so

26
00:01:37.580 --> 00:01:44.500
<v Speaker 1>roughly around 3.5, 4 years ago, the
organization was formed to centralize and bring

27
00:01:44.500 --> 00:01:50.660
<v Speaker 1>the power of our digital solutions in
different segments together and really driving

28
00:01:50.660 --> 00:01:55.419
<v Speaker 1>the future in terms of digitalization
technology around a drivetrain.

29
00:01:55.809 --> 00:02:02.379
<v Speaker 1>Together forward and yeah, since then it
happens a lot when I think about it, 3, 3.5

30
00:02:02.379 --> 00:02:07.800
<v Speaker 1>years ago, how we shaped the portfolio,
how we incorporated new, new trend,

31
00:02:07.819 --> 00:02:13.360
<v Speaker 1>technology like AI and very, very glad
and, and honored to, to be part of this great

32
00:02:13.500 --> 00:02:13.820
<v Speaker 1>team.

33
00:02:14.169 --> 00:02:18.479
<v Speaker 3>Bryland, could you shed more light on how
you became a portfolio manager?

34
00:02:18.610 --> 00:02:19.639
<v Speaker 3>What, what's your background?

35
00:02:20.220 --> 00:02:21.399
<v Speaker 3>What, what did you study?

36
00:02:21.720 --> 00:02:22.410
<v Speaker 1>Yeah, sure.

37
00:02:22.490 --> 00:02:26.149
<v Speaker 1>I mean, of course, you're not leaving
university and saying, yeah, I want to lead a

38
00:02:26.279 --> 00:02:31.529
<v Speaker 1>cloud portfolio of IoT Analytics in in the
digital driver organization, even though

39
00:02:31.529 --> 00:02:33.419
<v Speaker 1>that back then it didn't even exist.

40
00:02:33.639 --> 00:02:40.410
<v Speaker 1>Therefore, I mean, I started after my
engineering degree, so I studied mechanical

41
00:02:40.410 --> 00:02:44.699
<v Speaker 1>engineering at the Technology University
in Munich and Siemens with different areas.

42
00:02:44.929 --> 00:02:48.889
<v Speaker 1>Before, maybe a bit to my background, I, I
mean, in the mechanical engineering

43
00:02:48.889 --> 00:02:55.490
<v Speaker 1>studies, you, you do math, physics, you
really design gearboxes and really

44
00:02:55.490 --> 00:02:58.529
<v Speaker 1>understand the machining part of it and
really.

45
00:02:59.154 --> 00:03:03.735
<v Speaker 1>The physical world around it is, is
straightforward, being explained, and you,

46
00:03:03.854 --> 00:03:06.654
<v Speaker 1>you're driving that and digging deeper
into it.

47
00:03:06.975 --> 00:03:13.455
<v Speaker 1>And in the end of my studies, I focused
then more on what then comes up with

48
00:03:13.455 --> 00:03:14.815
<v Speaker 1>industry 4.0.

49
00:03:14.934 --> 00:03:18.804
<v Speaker 1>So, um, industry fear punk null and the
digitalization was there.

50
00:03:19.134 --> 00:03:26.000
<v Speaker 1>The, the new trend which is coming up and
So I had a chance to be part of a

51
00:03:26.000 --> 00:03:31.860
<v Speaker 1>project which then came also to my master
thesis to incorporate digital twins in the

52
00:03:32.000 --> 00:03:36.720
<v Speaker 1>area of medium sized companies, family run
companies, the hidden champions of

53
00:03:36.720 --> 00:03:42.380
<v Speaker 1>Germany, so to say, and that was a very,
very interesting project where at first,

54
00:03:42.720 --> 00:03:48.399
<v Speaker 1>the time that they're coming really from
this physical understanding machine side of

55
00:03:48.399 --> 00:03:48.559
<v Speaker 1>thing

56
00:03:48.559 --> 00:03:51.759
<v Speaker 1>and saw the digitalization in action.

57
00:03:52.199 --> 00:03:58.850
<v Speaker 1>By really understanding how this change
also the work, yeah, by introducing back

58
00:03:58.850 --> 00:04:04.169
<v Speaker 1>then digital twins were were kind of a new
concept coming from more the aerospace

59
00:04:04.169 --> 00:04:10.649
<v Speaker 1>engineering side of things, really
bringing this new technology in and having really

60
00:04:10.649 --> 00:04:16.290
<v Speaker 1>an impact also how people work, yeah, so
the control system engineering department I

61
00:04:16.290 --> 00:04:16.869
<v Speaker 1>was in.

62
00:04:17.589 --> 00:04:22.839
<v Speaker 1>Needed to link them to other departments
more and this impact also shaped me to, to

63
00:04:22.839 --> 00:04:29.279
<v Speaker 1>say, OK, it's not only interesting to
design certain parts of a machine and optimize

64
00:04:29.279 --> 00:04:34.559
<v Speaker 1>performance, but it's really also
interesting to be on the software side, on the

65
00:04:34.750 --> 00:04:38.040
<v Speaker 1>digital side of things, and, and
connecting this somehow, yeah.

66
00:04:38.119 --> 00:04:41.940
<v Speaker 1>So the physical and, and the digital world
coming together.

67
00:04:42.390 --> 00:04:45.269
<v Speaker 1>Yeah, as I said, back then it was all
around industry punk.

68
00:04:46.220 --> 00:04:51.589
<v Speaker 1>Then later on, when I joined Siemens, that
was also my, my drive, uh, within the

69
00:04:51.589 --> 00:04:53.350
<v Speaker 1>different roles I, I could take on.

70
00:04:53.429 --> 00:04:55.829
<v Speaker 1>So, I went through a management program.

71
00:04:55.910 --> 00:05:00.670
<v Speaker 1>I had the chance to work then in
mechanical engineering department in the low

72
00:05:00.670 --> 00:05:01.869
<v Speaker 1>voltage motor area.

73
00:05:01.980 --> 00:05:06.630
<v Speaker 1>So drive technology was very close to my
heart at the beginning of my career at

74
00:05:06.630 --> 00:05:07.299
<v Speaker 1>Siemens.

75
00:05:07.739 --> 00:05:11.890
<v Speaker 1>Then I was within the digital
manufacturing, so driving digitalization.

76
00:05:12.480 --> 00:05:18.730
<v Speaker 1>Within our own factories and had also the
chance to be part of a market push of

77
00:05:18.730 --> 00:05:24.209
<v Speaker 1>digitalization in the US so I spent some
time in the States and looking at the North

78
00:05:24.209 --> 00:05:24.929
<v Speaker 1>American market.

79
00:05:25.279 --> 00:05:30.369
<v Speaker 1>Which is, by the way, very differently
functioning when you, when you are looking at

80
00:05:30.369 --> 00:05:35.489
<v Speaker 1>Europe or Asia, and we see it there
actually right now that it is completely working

81
00:05:35.489 --> 00:05:40.010
<v Speaker 1>different also for Siemens and yeah, then
coming back, worked then in the product

82
00:05:40.010 --> 00:05:44.160
<v Speaker 1>and portfolio management area for some
time and then joined the digital Drive

83
00:05:44.160 --> 00:05:44.170
<v Speaker 1>organization.

84
00:05:46.010 --> 00:05:52.929
<v Speaker 1>So overall ari right through, so to say,
coming from physics and ending up in,

85
00:05:53.010 --> 00:05:55.089
<v Speaker 1>in the digitalization area.

86
00:05:55.739 --> 00:05:56.290
<v Speaker 3>Wow, cool.

87
00:05:56.339 --> 00:06:00.459
<v Speaker 3>That's pretty diverse and extensive
experience that you have.

88
00:06:00.619 --> 00:06:05.160
<v Speaker 3>So would you help our listeners understand
what exactly a digital drivetrain entails

89
00:06:05.450 --> 00:06:08.000
<v Speaker 3>and how it connects with predictive
maintenance?

90
00:06:08.100 --> 00:06:13.429
<v Speaker 3>So what's the fundamental idea behind
bringing these two powerful concepts together?

91
00:06:14.140 --> 00:06:16.269
<v Speaker 1>Yeah, so I think digital drivetrain.

92
00:06:16.649 --> 00:06:23.100
<v Speaker 1>As the name already says, digitalization
of the drive technology, first of all, it's

93
00:06:23.100 --> 00:06:27.329
<v Speaker 1>probably good to understand what is
actually a drive train or what we understand it.

94
00:06:27.859 --> 00:06:34.049
<v Speaker 1>So most of the time consists of a motor,
kind of the muscle frequency converter,

95
00:06:34.059 --> 00:06:35.339
<v Speaker 1>which controls the speed.

96
00:06:35.609 --> 00:06:41.239
<v Speaker 1>And a certain application, so it could be
continuous motion pump fan, compressor,

97
00:06:41.529 --> 00:06:45.350
<v Speaker 1>but also dynamic motions around a press.

98
00:06:45.570 --> 00:06:50.489
<v Speaker 1>So there are many different applications
which relying on drive trench in general.

99
00:06:50.679 --> 00:06:55.290
<v Speaker 1>So we refer to them as kind of the muscle
and brain of motion in the industry.

100
00:06:55.369 --> 00:06:57.429
<v Speaker 1>So everything which moves somehow.

101
00:06:57.809 --> 00:07:03.779
<v Speaker 1>In the discrete or process industry, you
have a drivetrain involved and this already

102
00:07:03.779 --> 00:07:09.410
<v Speaker 1>leads to the question, OK, so if
drivetrains really bringing this, this kind of

103
00:07:09.410 --> 00:07:15.720
<v Speaker 1>foundation of the industry, it makes also
sense in terms of control the entire what

104
00:07:15.720 --> 00:07:22.359
<v Speaker 1>we call drivetrain value chain, and that's
what we do with our digitalization

105
00:07:22.359 --> 00:07:27.450
<v Speaker 1>approach coming really from The early
stages

106
00:07:27.450 --> 00:07:32.769
<v Speaker 1>drive train design, dimensioning,
simulating the drive train to be accurate in

107
00:07:32.769 --> 00:07:37.690
<v Speaker 1>motion, to be fast in motion, that is one
part of the side of things we are looking

108
00:07:37.690 --> 00:07:38.010
<v Speaker 1>at.

109
00:07:38.279 --> 00:07:44.410
<v Speaker 1>And then also being what we call drive
chain health area, so connecting the drive

110
00:07:44.410 --> 00:07:51.029
<v Speaker 1>trains which are in the field and
optimizing them to be better in motion, to be

111
00:07:51.149 --> 00:07:53.720
<v Speaker 1>accurate in motion in terms of also.

112
00:07:54.489 --> 00:07:58.429
<v Speaker 1>Capturing the data and understanding what
is actually happening with the physical

113
00:07:58.980 --> 00:08:00.579
<v Speaker 1>drive train components in the field.

114
00:08:00.929 --> 00:08:05.609
<v Speaker 1>So this is the, what we say digital drive
train value chain.

115
00:08:06.049 --> 00:08:10.089
<v Speaker 1>We want to kind of bring value along these
phases.

116
00:08:10.450 --> 00:08:12.829
<v Speaker 1>In each and every part of it.

117
00:08:13.170 --> 00:08:19.529
<v Speaker 1>And when we're looking now at the
predictive maintenance use case and concept, we

118
00:08:19.529 --> 00:08:26.429
<v Speaker 1>are then at the driveframe health cluster,
as I mentioned, connecting the drives

119
00:08:26.429 --> 00:08:28.589
<v Speaker 1>and optimizing the drives in the field.

120
00:08:29.369 --> 00:08:30.209
<v Speaker 3>All right.

121
00:08:31.000 --> 00:08:34.760
<v Speaker 3>So, we touched upon it a bit, but what are
the core technologies that make the

122
00:08:34.760 --> 00:08:37.789
<v Speaker 3>digital drivetrains and predictive
maintenance possible?

123
00:08:38.159 --> 00:08:43.549
<v Speaker 3>So, are we talking about sensors, IOT, AI,
cloud computing?

124
00:08:43.679 --> 00:08:47.960
<v Speaker 3>How do these pieces fit together to create
a a cohesive system?

125
00:08:48.679 --> 00:08:49.010
<v Speaker 1>Yeah.

126
00:08:49.150 --> 00:08:56.010
<v Speaker 1>So, I mean, first of all, um, digital
drive train technology in the context of the

127
00:08:56.010 --> 00:09:01.239
<v Speaker 1>predictive maintenance is really driving
or want to come to the predictive part,

128
00:09:01.309 --> 00:09:01.489
<v Speaker 1>right?

129
00:09:01.570 --> 00:09:06.010
<v Speaker 1>So, just to understand before that, I
mean, there's the different phases, probably

130
00:09:06.010 --> 00:09:08.210
<v Speaker 1>also often discussed here in this podcast.

131
00:09:08.330 --> 00:09:10.559
<v Speaker 1>So, coming from reactive to prevent.

132
00:09:10.989 --> 00:09:17.799
<v Speaker 1>to predictive and predictive is then where
we say, OK, we identify problems

133
00:09:17.799 --> 00:09:23.419
<v Speaker 1>before they cause any damage, any downtime
in the operation.

134
00:09:23.440 --> 00:09:29.479
<v Speaker 1>And as I mentioned before, driveres then
play a lot, a lot of industries is a really

135
00:09:29.479 --> 00:09:34.809
<v Speaker 1>key role in driving the industry and
therefore that is the target.

136
00:09:35.119 --> 00:09:39.520
<v Speaker 1>Yeah, so not when something is already
damaged and you repair it.

137
00:09:40.080 --> 00:09:45.090
<v Speaker 1>Maybe sometimes you're in the field of
preventive where you say, OK, I do that

138
00:09:45.090 --> 00:09:45.919
<v Speaker 1>frequently.

139
00:09:46.229 --> 00:09:51.989
<v Speaker 1>And I deliver at least transparency with
the data of the digital drivetrain in this

140
00:09:51.989 --> 00:09:55.190
<v Speaker 1>field, but we want to get to the
predictive part.

141
00:09:55.590 --> 00:10:00.309
<v Speaker 1>That's been said, you already mentioned a
couple of, of, yeah, components, I would

142
00:10:00.309 --> 00:10:01.750
<v Speaker 1>say, which need to come together.

143
00:10:01.780 --> 00:10:04.750
<v Speaker 1>And let me make maybe one example.

144
00:10:04.859 --> 00:10:09.929
<v Speaker 1>So we, we have a motor in one of our own
factories which is driving a F application.

145
00:10:10.190 --> 00:10:13.609
<v Speaker 1>So it's a motor direct online driving.

146
00:10:13.960 --> 00:10:19.479
<v Speaker 1>The fan and the fan is part of a painting
system, and this painting system is

147
00:10:19.599 --> 00:10:25.770
<v Speaker 1>overall the last step of a process in the
factory, and in the past

148
00:10:26.820 --> 00:10:29.960
<v Speaker 1>this fan made trouble, it stopped working
at a certain time.

149
00:10:30.409 --> 00:10:33.969
<v Speaker 1>As suddenly, and the whole painting system
stopped and the production stopped.

150
00:10:34.049 --> 00:10:36.729
<v Speaker 1>So this is the part where you have
downtime.

151
00:10:36.849 --> 00:10:38.530
<v Speaker 1>So how can you prevent this now?

152
00:10:38.869 --> 00:10:42.349
<v Speaker 1>So first of all, you need to connect the
drive.

153
00:10:42.409 --> 00:10:47.969
<v Speaker 1>In this case, you need to connect this
motor with the fan to understand, OK, what

154
00:10:47.969 --> 00:10:53.929
<v Speaker 1>and how is the, the, the, the motor
behaving or at at first understanding, getting

155
00:10:53.929 --> 00:10:55.780
<v Speaker 1>transparency, the right data out of it.

156
00:10:55.890 --> 00:10:59.809
<v Speaker 1>So we have a smart sensor connection motor
IoT.

157
00:11:00.270 --> 00:11:06.469
<v Speaker 1>Which you plug and play on the ripping
cool on, on the motor, so that is a key,

158
00:11:06.669 --> 00:11:08.419
<v Speaker 1>that's a very important part of it.

159
00:11:08.510 --> 00:11:13.750
<v Speaker 1>We want to make it easy for our customers,
so to mount it on the outside, you have

160
00:11:13.750 --> 00:11:19.140
<v Speaker 1>then vibration, magnetic flux,
temperature, so different parameters which this

161
00:11:19.140 --> 00:11:24.400
<v Speaker 1>sensor measures, and this sensor is then
sent it to the cloud directly.

162
00:11:24.549 --> 00:11:27.070
<v Speaker 1>So this is one part of it where you
connect.

163
00:11:27.400 --> 00:11:28.280
<v Speaker 1>Now the motor.

164
00:11:28.640 --> 00:11:32.159
<v Speaker 1>Now comes the second part where, as you
mentioned, cloud computing.

165
00:11:32.400 --> 00:11:38.989
<v Speaker 1>We have a digital twin model of this motor
which the customer in this case

166
00:11:38.989 --> 00:11:44.960
<v Speaker 1>in our factory is kind of configuring, so
giving mechanical and electrical

167
00:11:44.960 --> 00:11:50.190
<v Speaker 1>parameters of the motor based on the
rating plate information into it.

168
00:11:50.479 --> 00:11:54.159
<v Speaker 1>Then the digital twin model is created and
with this.

169
00:11:54.530 --> 00:12:00.849
<v Speaker 1>Parameters you measure from the smart
sensor, the multi-sensor inputs you have like

170
00:12:00.849 --> 00:12:06.599
<v Speaker 1>vibration, like magnetic field, we are
calculating all the relevant KPIs.

171
00:12:06.809 --> 00:12:12.369
<v Speaker 1>And now comes the trending part which you
mentioned before to have a complete system

172
00:12:12.369 --> 00:12:16.179
<v Speaker 1>and to be able to do predictive
maintenance at the end.

173
00:12:16.570 --> 00:12:21.250
<v Speaker 1>You need then to understand how this motor
is behaving over time.

174
00:12:21.570 --> 00:12:23.150
<v Speaker 1>In this case with the fan.

175
00:12:23.609 --> 00:12:30.530
<v Speaker 1>So the fan has certain particles which
from the painting comes, which is kind of

176
00:12:30.530 --> 00:12:33.250
<v Speaker 1>the weight of the blades are different.

177
00:12:33.489 --> 00:12:38.890
<v Speaker 1>You have a misalignment and you have a
different pattern in the vibration signals.

178
00:12:39.270 --> 00:12:45.530
<v Speaker 1>So we do all this analysis and all this
intelligence in the cloud to analyze and

179
00:12:45.530 --> 00:12:50.650
<v Speaker 1>then say in this case for our factory
here, look, there is a problem.

180
00:12:51.010 --> 00:12:56.349
<v Speaker 1>With your motor or with the misalignment,
so please check it.

181
00:12:56.530 --> 00:13:03.210
<v Speaker 1>And that is happening before then really
the motor breaks down and that is a

182
00:13:03.210 --> 00:13:07.690
<v Speaker 1>simple example where you can see already a
lot of pieces need to come together from

183
00:13:07.690 --> 00:13:13.530
<v Speaker 1>the connectivity in this case with our
smart sensors, so much connectivity of

184
00:13:13.530 --> 00:13:16.049
<v Speaker 1>bringing the data into the cloud, bringing
this.

185
00:13:16.385 --> 00:13:22.335
<v Speaker 1>Data into context analyzing it and then
being able to feed our models

186
00:13:23.664 --> 00:13:28.505
<v Speaker 1>to predict a failure and that is kind of
the chain which we are offering to our

187
00:13:28.505 --> 00:13:35.114
<v Speaker 1>customers and in this case with our in our
own factory we could shift kind

188
00:13:35.114 --> 00:13:41.104
<v Speaker 1>of the phases from the preventive
maintenance approach to a predictive part.

189
00:13:41.510 --> 00:13:46.390
<v Speaker 1>So the, at the end, the maintenance team
doesn't need to do the weekly checks they

190
00:13:46.390 --> 00:13:48.950
<v Speaker 1>have scheduled before.

191
00:13:49.309 --> 00:13:51.090
<v Speaker 1>Now they look into.

192
00:13:51.729 --> 00:13:57.719
<v Speaker 1>What we say digital drive train in our
case, in this case a drive and analyzer

193
00:13:57.719 --> 00:14:03.369
<v Speaker 1>application and sees if there is a
misalignment, a bearing problem, or any vibration

194
00:14:03.369 --> 00:14:06.469
<v Speaker 1>patterns which are kind of critical.

195
00:14:06.849 --> 00:14:09.929
<v Speaker 1>And yeah, so it changed also at the end.

196
00:14:10.020 --> 00:14:13.299
<v Speaker 1>The way how the maintenance team now is
working.

197
00:14:13.580 --> 00:14:14.080
<v Speaker 1>All right,

198
00:14:14.219 --> 00:14:20.539
<v Speaker 3>so could you maybe sum it up for us to
understand what the general benefits are?

199
00:14:20.700 --> 00:14:26.380
<v Speaker 3>I, I see that it's all about preventing
bad things before they happen, but I guess

200
00:14:26.380 --> 00:14:28.280
<v Speaker 3>there's, there's a bit more to it.

201
00:14:28.580 --> 00:14:32.489
<v Speaker 1>Yeah, I mean, we are looking at normally
for our customers.

202
00:14:32.830 --> 00:14:39.549
<v Speaker 1>Into certain areas which is around
reliability and as you mentioned, cost in terms

203
00:14:39.549 --> 00:14:45.270
<v Speaker 1>of preventing the downtime, downtime cost
and there is a huge potential to to

204
00:14:45.270 --> 00:14:48.950
<v Speaker 1>address those two main drivers or KPIs.

205
00:14:49.309 --> 00:14:56.039
<v Speaker 1>The other part of the challenge we see is
this topic of sustainability, so half of

206
00:14:56.039 --> 00:15:01.340
<v Speaker 1>the electrical wire consumption is kind of
caused or connected with drive trains, so

207
00:15:01.340 --> 00:15:03.979
<v Speaker 1>there's a huge potential to reduce that as
well.

208
00:15:04.380 --> 00:15:11.090
<v Speaker 1>And with our data we get from the drive
and also with our smart digital

209
00:15:11.090 --> 00:15:17.770
<v Speaker 1>motor model, we can calculate energy
consumptions and understand where to start in

210
00:15:17.770 --> 00:15:21.280
<v Speaker 1>order to reduce the consumption in your
fleet.

211
00:15:21.820 --> 00:15:26.140
<v Speaker 1>So especially when we look at customers in
the water and wastewater industry, we

212
00:15:26.140 --> 00:15:29.419
<v Speaker 1>have a great example where we can see.

213
00:15:30.059 --> 00:15:36.530
<v Speaker 1>We are reducing cost of repairing and
maintenance immediately by 10 to

214
00:15:36.530 --> 00:15:37.440
<v Speaker 1>15%.

215
00:15:38.130 --> 00:15:45.049
<v Speaker 1>We are extending the lifetime of the asset
up to 15% and as I said, also the energy

216
00:15:45.049 --> 00:15:51.280
<v Speaker 1>consumption is reduced dramatically and
overall that is the that is the goal, yeah,

217
00:15:51.409 --> 00:15:58.250
<v Speaker 1>so to reduce the risk and the OPEC for our
customers and yeah,

218
00:15:58.409 --> 00:16:04.750
<v Speaker 1>so there are many different And so to say,
industries and examples where we see we

219
00:16:04.750 --> 00:16:07.080
<v Speaker 1>have an immediate impact and return on
investment.

220
00:16:07.400 --> 00:16:11.679
<v Speaker 3>That sounds pretty impressive, but
adopting new technologies may come with its

221
00:16:11.679 --> 00:16:12.500
<v Speaker 3>hurdles.

222
00:16:13.119 --> 00:16:17.559
<v Speaker 3>What would be the biggest challenges
companies face when implementing digital drive

223
00:16:17.559 --> 00:16:19.359
<v Speaker 3>trains and predictive maintenance?

224
00:16:19.919 --> 00:16:22.780
<v Speaker 3>Would you have any tips or suggestions for
overcoming them?

225
00:16:23.260 --> 00:16:29.989
<v Speaker 1>Yeah, I, I think what I see out of our
customer projects, and of course, not, not

226
00:16:29.989 --> 00:16:35.000
<v Speaker 1>every project has this return on invest to
be honest, and, and sometimes they're

227
00:16:35.000 --> 00:16:41.359
<v Speaker 1>stuck in, in certain phases and, and you
don't, can leverage this value and What,

228
00:16:41.460 --> 00:16:47.239
<v Speaker 1>what I see out of many different customer
projects and, and also pilot projects,

229
00:16:47.609 --> 00:16:50.929
<v Speaker 1>first of all, there are probably 3 areas.

230
00:16:51.010 --> 00:16:57.609
<v Speaker 1>The first is that the customer
underestimates or the partner underestimates all this

231
00:16:57.609 --> 00:17:03.869
<v Speaker 1>chain we have looked at, so the complexity
of turning really data into value and

232
00:17:04.319 --> 00:17:07.890
<v Speaker 1>There are many different stages where a
customer can be in there, right?

233
00:17:08.040 --> 00:17:12.760
<v Speaker 1>So, you have sometimes customers say, oh I
heard about this AI I want to use it as

234
00:17:12.760 --> 00:17:13.800
<v Speaker 1>well, let's go.

235
00:17:14.119 --> 00:17:19.119
<v Speaker 1>And you say, OK, where is your, your data
of the drive or the motors or the complete

236
00:17:19.119 --> 00:17:19.780
<v Speaker 1>drive train.

237
00:17:20.170 --> 00:17:24.849
<v Speaker 1>And so this is probably the base ground to
say, OK, first you need to connect your

238
00:17:24.849 --> 00:17:28.290
<v Speaker 1>assets in order to get data or the right
data.

239
00:17:28.849 --> 00:17:33.010
<v Speaker 1>So sometimes you have data but not the
right one, missing, for instance, vibration

240
00:17:33.010 --> 00:17:38.270
<v Speaker 1>inputs to, to really detect problems in
the overall mechanical setup.

241
00:17:38.800 --> 00:17:45.099
<v Speaker 1>But, so what I want to say is, you see,
That from connecting the assets,

242
00:17:45.469 --> 00:17:51.069
<v Speaker 1>getting the data, interpreting the data,
and then having insights which are then

243
00:17:51.069 --> 00:17:57.510
<v Speaker 1>used accordingly, changing also the way
how how maintenance is done, that

244
00:17:57.510 --> 00:18:03.790
<v Speaker 1>is a long process, a step, and sometimes
Uh, customer underestimates.

245
00:18:03.839 --> 00:18:07.959
<v Speaker 1>So they say, OK, um, we had one example of
a customer which started to come to us

246
00:18:07.959 --> 00:18:13.739
<v Speaker 1>and say, OK, your, your analytics
software, I don't need, I, I just need the, the

247
00:18:13.739 --> 00:18:14.079
<v Speaker 1>data.

248
00:18:14.199 --> 00:18:20.680
<v Speaker 1>So give me the connectors for, for my
drives or the CMIOT which is, by the way, open

249
00:18:20.680 --> 00:18:21.390
<v Speaker 1>MQTT.

250
00:18:21.439 --> 00:18:22.619
<v Speaker 1>You can get the data.

251
00:18:23.170 --> 00:18:26.780
<v Speaker 1>And I have my own guys uh interpreting the
data.

252
00:18:27.119 --> 00:18:31.910
<v Speaker 1>The same customer came back half a year
later and said, OK, well, Uh, I see you have

253
00:18:31.910 --> 00:18:38.739
<v Speaker 1>a point in interpreting data and knowing
when a bearing fails is not so easy, so you

254
00:18:38.739 --> 00:18:44.989
<v Speaker 1>need to interpret and combined vibration
with speed, knowing what the FFT is really

255
00:18:44.989 --> 00:18:49.709
<v Speaker 1>saying to you, and also bringing this into
context, how the motor is operated.

256
00:18:49.989 --> 00:18:55.630
<v Speaker 1>So this is complex and therefore this
domain knowledge we have, we incorporate in

257
00:18:55.630 --> 00:18:56.650
<v Speaker 1>our software.

258
00:18:56.930 --> 00:19:03.890
<v Speaker 1>And I see often in these processes from I
capture the data, I have the right

259
00:19:03.890 --> 00:19:10.849
<v Speaker 1>data, and bring the insights or I derive
insights out of it is sometimes more

260
00:19:10.849 --> 00:19:12.290
<v Speaker 1>complex than you think.

261
00:19:12.729 --> 00:19:18.369
<v Speaker 1>So that is one core challenge I see or
heard so often in the customer projects.

262
00:19:19.000 --> 00:19:25.270
<v Speaker 1>Secondly, I think, yeah, I mean, often you
start with a pilot and the pilots stuck

263
00:19:25.640 --> 00:19:30.880
<v Speaker 1>somewhere because it is not looked at the
scalability at an early stage.

264
00:19:30.959 --> 00:19:36.119
<v Speaker 1>So of course, I understand you first and
want to understand what is the value for

265
00:19:36.119 --> 00:19:38.040
<v Speaker 1>you and how is the return on invest.

266
00:19:38.119 --> 00:19:44.040
<v Speaker 1>So you said, OK, we have certain area
where we want to test your solution to see if

267
00:19:44.040 --> 00:19:45.099
<v Speaker 1>it brings value.

268
00:19:45.560 --> 00:19:52.349
<v Speaker 1>But you can see in customer successful
stories where they already fought at the

269
00:19:52.349 --> 00:19:59.280
<v Speaker 1>early stage on two scale, and you see
others which are maybe just stuck in this

270
00:19:59.280 --> 00:20:04.719
<v Speaker 1>pile of phase because nobody takes on it
and really want to drive it.

271
00:20:05.000 --> 00:20:10.199
<v Speaker 1>So one example of a very successful story
was in the waterwayste industry again.

272
00:20:10.790 --> 00:20:16.010
<v Speaker 1>Where they looked at, OK, what are my all
my assets, my fleet, what is critical,

273
00:20:16.189 --> 00:20:21.479
<v Speaker 1>what is not so critical, which processes I
need to do, which kind of system, and

274
00:20:21.479 --> 00:20:27.390
<v Speaker 1>with that early on they started on one
side and extended it across many multiple

275
00:20:27.390 --> 00:20:31.140
<v Speaker 1>sites today of hundreds of different
assets.

276
00:20:31.390 --> 00:20:33.189
<v Speaker 1>So they started small.

277
00:20:33.295 --> 00:20:39.454
<v Speaker 1>But thought at the beginning big, and I
think that is one core challenge or hurdle I

278
00:20:39.454 --> 00:20:45.255
<v Speaker 1>see that often pilots just stuck because
they don't look at the scalability, um, and

279
00:20:45.255 --> 00:20:47.834
<v Speaker 1>the overall return on the vest they want
to reach.

280
00:20:48.094 --> 00:20:54.814
<v Speaker 1>And I think last part of it, I touched it
maybe already a bit is, is us, as the

281
00:20:54.814 --> 00:20:55.435
<v Speaker 1>people, right?

282
00:20:55.574 --> 00:20:59.214
<v Speaker 1>So you can have the best system, the best
insights.

283
00:20:59.719 --> 00:21:06.400
<v Speaker 1>If you not also take that in terms of
changing, and this brings me maybe also back

284
00:21:06.400 --> 00:21:11.599
<v Speaker 1>to my story with the master thesis where I
could really see digital twin change the

285
00:21:11.599 --> 00:21:16.719
<v Speaker 1>way how people work, that's the same thing
here, yeah, so if you have the right

286
00:21:16.719 --> 00:21:22.079
<v Speaker 1>insights, the people need to take that on
and you also need to change the process of

287
00:21:22.079 --> 00:21:25.160
<v Speaker 1>how you do maintenance maybe from today
on.

288
00:21:25.599 --> 00:21:31.459
<v Speaker 1>And that, yeah, is, is an important part
of it, so it's also part of skills and

289
00:21:32.040 --> 00:21:37.839
<v Speaker 1>change, change management and, and
involving the right people into, into these

290
00:21:37.839 --> 00:21:38.329
<v Speaker 1>projects.

291
00:21:38.719 --> 00:21:40.699
<v Speaker 1>Otherwise it's stuck somewhere.

292
00:21:41.069 --> 00:21:45.560
<v Speaker 3>Would you say that a lack of talent
nowadays would fill into this, this part as well

293
00:21:45.560 --> 00:21:47.430
<v Speaker 3>or into this challenge as well.

294
00:21:47.680 --> 00:21:49.060
<v Speaker 1>Yeah, I, I think.

295
00:21:49.430 --> 00:21:55.349
<v Speaker 1>That is definitely one part of it,
especially when we look at digital drivetrain or

296
00:21:55.349 --> 00:21:57.010
<v Speaker 1>the drivetrain technology itself.

297
00:21:57.589 --> 00:22:02.750
<v Speaker 1>There are less and less experts out there
to understand really what's what's going

298
00:22:02.750 --> 00:22:04.189
<v Speaker 1>on with the drivetrain.

299
00:22:04.430 --> 00:22:10.189
<v Speaker 1>And also, even you have these experts,
they are not everywhere in your different

300
00:22:10.189 --> 00:22:11.189
<v Speaker 1>production sites, right?

301
00:22:11.400 --> 00:22:17.880
<v Speaker 1>And therefore I think AI is really helping
us in a way or

302
00:22:17.880 --> 00:22:24.719
<v Speaker 1>combining the knowledge which we have from
the industry with AI is one part of it.

303
00:22:25.000 --> 00:22:29.560
<v Speaker 1>So that's what we're trying to address
also with our industrial co-pilot and, and

304
00:22:29.560 --> 00:22:36.160
<v Speaker 1>what we have with our operations co-pilot
for Bright and Analyzer, because here we

305
00:22:36.160 --> 00:22:38.119
<v Speaker 1>are looking at a solution.

306
00:22:38.449 --> 00:22:45.089
<v Speaker 1>Where we incorporate our domain know-how
and the, the Industrial-Copilot is aware of

307
00:22:45.089 --> 00:22:50.569
<v Speaker 1>the data and analytics we have on the
software and bring this then to the customer.

308
00:22:50.650 --> 00:22:57.089
<v Speaker 1>So we have a very big change in how we can
bring in

309
00:22:57.489 --> 00:23:04.170
<v Speaker 1>really specific industry knowledge towards
our customers and combining

310
00:23:04.170 --> 00:23:11.160
<v Speaker 1>it with our analytics we have there and,
Analysis itself is impacted by, by

311
00:23:11.160 --> 00:23:13.199
<v Speaker 1>AI, by our industrial co-pilots.

312
00:23:13.319 --> 00:23:19.959
<v Speaker 1>So I think that is definitely one part of
the hurdles, but also something we want to

313
00:23:19.959 --> 00:23:26.119
<v Speaker 1>address now with the, the new technology,
which is, and the new possibility which

314
00:23:26.119 --> 00:23:29.160
<v Speaker 1>brings AI or what we say industrial AI.

315
00:23:29.435 --> 00:23:29.574
<v Speaker 3>Hm.

316
00:23:29.915 --> 00:23:35.834
<v Speaker 3>I think we are hearing nowadays a lot of
about co-pilots, industrial AI, AI in

317
00:23:35.834 --> 00:23:36.305
<v Speaker 3>general.

318
00:23:36.714 --> 00:23:41.474
<v Speaker 3>But could you perhaps explain how it
actually works in connection with Drivetrain

319
00:23:41.474 --> 00:23:41.994
<v Speaker 3>analyzer?

320
00:23:42.074 --> 00:23:47.234
<v Speaker 3>So you have the co-pilot, you have
Drivetrain analyzer, and how does it bring value

321
00:23:47.234 --> 00:23:47.994
<v Speaker 3>to the customer?

322
00:23:48.760 --> 00:23:49.439
<v Speaker 1>Yeah, sure.

323
00:23:49.560 --> 00:23:54.969
<v Speaker 1>I mean, at the moment, it is an integrated
part of our solution.

324
00:23:55.079 --> 00:24:01.439
<v Speaker 1>So for drive and analyzer, we have our
operations co-pilot and to give you an

325
00:24:01.439 --> 00:24:07.520
<v Speaker 1>example, so we have, for instance, A
failure code popping up 7015 from the drive,

326
00:24:07.540 --> 00:24:13.579
<v Speaker 1>and today you can now ask our operations
copilot, which is an integrated part of the

327
00:24:13.579 --> 00:24:19.180
<v Speaker 1>software, what does it mean, and it will
immediately give you an answer about what

328
00:24:19.180 --> 00:24:19.660
<v Speaker 1>it means.

329
00:24:19.739 --> 00:24:24.739
<v Speaker 1>So back then you might have to go to the
drive type manual and look it up in the

330
00:24:24.739 --> 00:24:25.280
<v Speaker 1>table.

331
00:24:25.839 --> 00:24:29.780
<v Speaker 1>But here you'd immediately get it from our
industrial co-pilot.

332
00:24:29.989 --> 00:24:34.089
<v Speaker 1>So this is kind of one to make things
explainable.

333
00:24:34.630 --> 00:24:41.510
<v Speaker 1>The second level is the all the analytics,
what I said before and the analysis also

334
00:24:41.510 --> 00:24:46.949
<v Speaker 1>here the industrial co-pilot can go into
and helps you to also understand what to

335
00:24:46.949 --> 00:24:47.250
<v Speaker 1>do.

336
00:24:47.430 --> 00:24:52.989
<v Speaker 1>So coming back to the F example, if you
have misalignment, first of all, you can

337
00:24:53.069 --> 00:24:54.949
<v Speaker 1>interact with the co-pilot.

338
00:24:55.260 --> 00:24:57.569
<v Speaker 1>And ask, OK, what, what does it mean now?

339
00:24:57.579 --> 00:25:02.020
<v Speaker 1>or what is the biggest risk I have at the
moment here and what are the action

340
00:25:02.020 --> 00:25:02.219
<v Speaker 1>points?

341
00:25:02.270 --> 00:25:04.760
<v Speaker 1>So it consults you along the way.

342
00:25:04.859 --> 00:25:09.540
<v Speaker 1>So before you might just look at the
traffic light and seeing, OK, there is

343
00:25:09.540 --> 00:25:15.780
<v Speaker 1>something critical in your, your eye, you,
you see this message or the notification

344
00:25:15.780 --> 00:25:21.520
<v Speaker 1>popping up that the misalignment is more
probable to, to, to occur.

345
00:25:21.930 --> 00:25:27.810
<v Speaker 1>And how you can really interact and I
think Cedric Nike said it also from the

346
00:25:27.810 --> 00:25:33.369
<v Speaker 1>digital industry overall perspective, we
are seeing that Siemens

347
00:25:33.369 --> 00:25:39.290
<v Speaker 1>Industrial-Copilot makes it not possible
that the machines speak our language, yeah,

348
00:25:39.329 --> 00:25:41.170
<v Speaker 1>and this is, this is what we do now.

349
00:25:41.280 --> 00:25:46.989
<v Speaker 1>So that you can speak basically with the
drive or the driveling insights you, you

350
00:25:46.989 --> 00:25:48.910
<v Speaker 1>get from our software.

351
00:25:49.140 --> 00:25:50.969
<v Speaker 1>So it is an integrated part of it.

352
00:25:51.329 --> 00:25:56.979
<v Speaker 1>And uh Siemens overall drives this topic
more and more to have all these different,

353
00:25:57.050 --> 00:26:03.770
<v Speaker 1>let's say, experts, digital companions
communicating across the different use

354
00:26:03.770 --> 00:26:09.670
<v Speaker 1>cases and this is also in my perspective
where the future goes, yeah, so really

355
00:26:10.089 --> 00:26:13.689
<v Speaker 1>driving these different areas together in.

356
00:26:14.010 --> 00:26:20.209
<v Speaker 1>You have a drive train expert co-pilot and
you have an co-pilot which is helping you

357
00:26:20.209 --> 00:26:26.119
<v Speaker 1>to engineer your automation setup, so this
comes more and more together also with

358
00:26:26.119 --> 00:26:28.449
<v Speaker 1>the AII technology.

359
00:26:28.839 --> 00:26:34.170
<v Speaker 3>OK, so that sounds like you would have
your own expert on the drive train at your

360
00:26:34.170 --> 00:26:35.280
<v Speaker 3>very fingertips.

361
00:26:35.810 --> 00:26:36.489
<v Speaker 1>Exactly, yeah.

362
00:26:36.959 --> 00:26:43.250
<v Speaker 3>OK, so from your perspective as a
portfolio manager, what is new and upcoming in

363
00:26:43.250 --> 00:26:45.319
<v Speaker 3>specifically in your product portfolio?

364
00:26:45.729 --> 00:26:51.030
<v Speaker 1>Yeah, I mean, it's very dynamic at the
moment and it's, it's very interesting times.

365
00:26:51.209 --> 00:26:57.530
<v Speaker 1>So if you look at we now already touched
on on AI I think there's also no, no

366
00:26:57.530 --> 00:27:02.489
<v Speaker 1>podcast at the moment in the industrial
world which, which is not touching on this

367
00:27:02.489 --> 00:27:02.989
<v Speaker 1>topic.

368
00:27:03.829 --> 00:27:10.719
<v Speaker 1>For us, we are strongly collaborating in,
in terms of the predictive, what we

369
00:27:10.719 --> 00:27:14.040
<v Speaker 1>call Siemens holistic predictive
maintenance ecosystem.

370
00:27:14.479 --> 00:27:20.420
<v Speaker 1>So we have many different strong solution
offerings at Siemens, as mentioned,

371
00:27:20.560 --> 00:27:26.069
<v Speaker 1>digital drivetrain very much focused on
the drive train domain and and knowledge and

372
00:27:26.069 --> 00:27:26.800
<v Speaker 1>leverage that.

373
00:27:27.260 --> 00:27:32.540
<v Speaker 1>And and we are feeding that into this
overall predictive maintenance ecosystem,

374
00:27:32.589 --> 00:27:34.199
<v Speaker 1>yeah, so we're collaborating.

375
00:27:34.579 --> 00:27:38.959
<v Speaker 1>With colleagues, for instance, with Sense
Eye to bringing really this powerhouse we

376
00:27:38.959 --> 00:27:44.400
<v Speaker 1>have as Siemens in the different areas
together to solve at the end the problems

377
00:27:44.780 --> 00:27:47.020
<v Speaker 1>from our customers in this space.

378
00:27:47.479 --> 00:27:53.959
<v Speaker 1>And so that is a core focus also in our,
in our portfolio to jointly driving

379
00:27:54.459 --> 00:27:59.660
<v Speaker 1>the, these use cases and these problems to
solve these problems from the customer we

380
00:27:59.660 --> 00:28:03.800
<v Speaker 1>see and doing that in the different
industries.

381
00:28:04.160 --> 00:28:10.859
<v Speaker 1>And that is also what we working on in
terms of cross-use case sections.

382
00:28:10.959 --> 00:28:12.880
<v Speaker 1>So I mentioned it with the co-pilot.

383
00:28:13.000 --> 00:28:19.709
<v Speaker 1>So it's not only then within one area, but
bringing this all over together in the

384
00:28:19.709 --> 00:28:21.880
<v Speaker 1>different use cases in the different
domains.

385
00:28:22.680 --> 00:28:29.000
<v Speaker 1>And that, that also kind of shapes at the
moment our drive with, of course, all this

386
00:28:29.000 --> 00:28:35.760
<v Speaker 1>new, new kind of trends coming up and
technology we are, we are also testing out.

387
00:28:36.319 --> 00:28:41.260
<v Speaker 1>So the, the operations copilot for drive
and analyzer, so your drive and companion

388
00:28:41.520 --> 00:28:43.319
<v Speaker 1>is, is one part of it.

389
00:28:43.849 --> 00:28:47.329
<v Speaker 1>But we're also already working on, on new
things here.

390
00:28:47.459 --> 00:28:53.250
<v Speaker 1>So, therefore, yeah, I, I think it's, it's
very, very interesting times and Siemens

391
00:28:53.250 --> 00:28:59.280
<v Speaker 1>really comes together in this one tech
initiative and, and, and sees that we can

392
00:28:59.290 --> 00:29:05.050
<v Speaker 1>have of these different areas really
balancing it out by bringing it together for

393
00:29:05.050 --> 00:29:05.920
<v Speaker 1>our customers.

394
00:29:06.709 --> 00:29:07.459
<v Speaker 3>Very well.

395
00:29:07.670 --> 00:29:12.400
<v Speaker 3>Suppose you have a crystal ball, Louis,
where do you see the digital drive trains

396
00:29:12.400 --> 00:29:17.310
<v Speaker 3>and predictive maintenance evolving in the
next 5 to 10 years when you would be

397
00:29:17.310 --> 00:29:19.619
<v Speaker 3>looking in that crystal ball of yours?

398
00:29:19.949 --> 00:29:25.750
<v Speaker 1>Yeah, I mean, it's so hard to say and
predict at the moment as, as I said, there's

399
00:29:25.750 --> 00:29:31.150
<v Speaker 1>so many happenings, so if you look at,
yeah, now the new possibilities, new models,

400
00:29:31.229 --> 00:29:35.410
<v Speaker 1>AI models which are just out and what you
can do with that already.

401
00:29:35.790 --> 00:29:41.560
<v Speaker 1>It's crazy, and that is maybe only half a
year of time where we have this big boost

402
00:29:41.560 --> 00:29:45.250
<v Speaker 1>and, and, and new insights you can derive
out of it.

403
00:29:45.829 --> 00:29:51.989
<v Speaker 1>I would say looking ahead, I see more or
less 3 areas evolving and and being more

404
00:29:51.989 --> 00:29:52.640
<v Speaker 1>and more strong.

405
00:29:52.750 --> 00:29:59.489
<v Speaker 1>So one is definitely that in the
predictive maintenance field we see more and more

406
00:30:00.150 --> 00:30:03.130
<v Speaker 1>prescriptive and collaborative approaches.

407
00:30:03.619 --> 00:30:08.540
<v Speaker 1>I think that is a logic step and that is
even not within 5 or 10 years, this is, I

408
00:30:08.540 --> 00:30:10.109
<v Speaker 1>think happening already.

409
00:30:10.660 --> 00:30:17.640
<v Speaker 1>So really coming to this very prescriptive
recommendations in all kinds of

410
00:30:17.979 --> 00:30:24.619
<v Speaker 1>problems the customer has in the field and
using the fleet's intelligence out of so

411
00:30:24.619 --> 00:30:28.619
<v Speaker 1>many different sources by having more and
more assets connected.

412
00:30:29.060 --> 00:30:34.140
<v Speaker 1>That also plays into what I mentioned
before with the overall predictive maintenance

413
00:30:34.140 --> 00:30:39.579
<v Speaker 1>ecosystem or the holistic maintenance
approach from Siemens overall, yeah, so

414
00:30:39.579 --> 00:30:43.439
<v Speaker 1>collaborating and bringing, let's say, the
best together.

415
00:30:43.900 --> 00:30:50.260
<v Speaker 1>I think what is also coming up, and this
is maybe a bit more into the future, but

416
00:30:50.260 --> 00:30:55.459
<v Speaker 1>definitely on the horizon is autonomous
drive trains powered by AI.

417
00:30:55.660 --> 00:30:56.500
<v Speaker 1>So what does it mean?

418
00:30:56.819 --> 00:30:57.859
<v Speaker 1>I see that.

419
00:30:58.439 --> 00:31:04.599
<v Speaker 1>Being self-optimized and self-corrective
systems and there the drive then is part of

420
00:31:04.599 --> 00:31:11.439
<v Speaker 1>this more and more into autonomous systems
overall in the factory and being part

421
00:31:11.439 --> 00:31:13.729
<v Speaker 1>of the automated factory.

422
00:31:14.119 --> 00:31:17.140
<v Speaker 1>That is something which I see is coming
up.

423
00:31:17.560 --> 00:31:24.199
<v Speaker 1>So really the self diagnostic, adjusting
it accordingly and yeah, as I said, the

424
00:31:24.199 --> 00:31:29.439
<v Speaker 1>drive trains or the digital drivetrain is
probably one part of it, but that enabled

425
00:31:29.439 --> 00:31:36.319
<v Speaker 1>by AI is, is going to a clear direction
and I don't know when it happens, but we

426
00:31:36.319 --> 00:31:42.069
<v Speaker 1>already see this is the direction to have
really a fully automated factory with

427
00:31:42.069 --> 00:31:43.640
<v Speaker 1>autonomous interacting.

428
00:31:44.219 --> 00:31:46.310
<v Speaker 1>We will probably not have that in all
areas.

429
00:31:46.500 --> 00:31:52.020
<v Speaker 1>In, in some areas, probably in the process
industry, it will happen earlier, but

430
00:31:52.020 --> 00:31:53.459
<v Speaker 1>that is a clear tent.

431
00:31:53.619 --> 00:31:56.420
<v Speaker 1>So autonomous drive and powered by AI.

432
00:31:57.020 --> 00:32:02.660
<v Speaker 1>And third, probably, which is also already
started is this.

433
00:32:03.430 --> 00:32:07.469
<v Speaker 1>Different fields I described before,
they're coming more and more together.

434
00:32:07.949 --> 00:32:14.109
<v Speaker 1>We looked at it, digitaltrichain with what
we call the the design and the health

435
00:32:14.109 --> 00:32:15.130
<v Speaker 1>areas, right?

436
00:32:15.469 --> 00:32:20.790
<v Speaker 1>But overall, it's the engineering software
and the industrial automation will

437
00:32:20.790 --> 00:32:22.520
<v Speaker 1>convert more and more.

438
00:32:22.630 --> 00:32:28.035
<v Speaker 1>So you have engineering software,
industrial The automation and operations, which,

439
00:32:28.114 --> 00:32:32.734
<v Speaker 1>which more and more come together, all
boosted, accelerated by AI.

440
00:32:33.114 --> 00:32:38.964
<v Speaker 1>So that is a third part of what I see is,
is, is coming up and, and more and more

441
00:32:38.964 --> 00:32:44.155
<v Speaker 1>shaping now the new landscape where the
digital drive train and predictive

442
00:32:44.155 --> 00:32:46.755
<v Speaker 1>maintenance is, is, is in.

443
00:32:47.405 --> 00:32:50.974
<v Speaker 3>Oh, so it seems very exciting future lies
ahead of us.

444
00:32:53.025 --> 00:32:53.035
<v Speaker 3>Yeah.

445
00:32:53.750 --> 00:32:58.060
<v Speaker 3>Thank you very much, Lez for the insights
and thanks a lot.

446
00:32:58.510 --> 00:33:01.300
<v Speaker 1>Yeah, thanks Matteo, thanks for having me
and see you.

447
00:33:01.579 --> 00:33:02.150
<v Speaker 1>Bye bye.

448
00:33:02.540 --> 00:33:02.670
<v Speaker 1>Bye

449
00:33:02.670 --> 00:33:03.209
<v Speaker 3>bye.

450
00:33:03.910 --> 00:33:08.869
<v Speaker 2>Please like and subscribe on all major
podcast channels and find out more about

451
00:33:08.869 --> 00:33:12.390
<v Speaker 2>Sensi predictive maintenance at
Siemens.com.
