WEBVTT
Language: en-US

1
00:00:01.279 --> 00:00:05.030
<v Speaker 1>Welcome to the trend detection podcast
powered by Siemens.

2
00:00:05.199 --> 00:00:06.820
<v Speaker 1>And now your host.

3
00:00:08.670 --> 00:00:12.619
<v Speaker 2>I am your host, Sia, and today we are
diving into a hot topic, predictive

4
00:00:12.619 --> 00:00:14.930
<v Speaker 2>maintenance, and the tech that powers it.

5
00:00:15.189 --> 00:00:19.930
<v Speaker 2>From AI analytics to service contracts,
how is Siemens helping automotive companies

6
00:00:19.930 --> 00:00:22.920
<v Speaker 2>reduce downtime, cut costs, and improve
performance?

7
00:00:23.389 --> 00:00:28.030
<v Speaker 2>Joining us today is Anton Zirin, lead
business development and sales for digital

8
00:00:28.030 --> 00:00:29.190
<v Speaker 2>portfolio at Siemens.

9
00:00:29.389 --> 00:00:30.229
<v Speaker 2>Welcome, Anton.

10
00:00:31.930 --> 00:00:34.569
<v Anton Siering>Hi, thanks for having me there.

11
00:00:34.810 --> 00:00:35.650
<v Anton Siering>Great to be there.

12
00:00:36.819 --> 00:00:42.139
<v Speaker 2>So before we dive into today's topic,
would you like to start by telling us a little

13
00:00:42.139 --> 00:00:44.720
<v Speaker 2>bit about yourself and your old Siemens?

14
00:00:46.810 --> 00:00:48.430
<v Anton Siering>Yeah, yeah, sure, sure.

15
00:00:49.409 --> 00:00:53.610
<v Anton Siering>So I think there are two major aspects to
my position customer focus and

16
00:00:53.610 --> 00:00:54.830
<v Anton Siering>digitalization.

17
00:00:56.209 --> 00:01:00.799
<v Anton Siering>Being a part of a vertical management
team, whereas a team have a clear focus on

18
00:01:00.799 --> 00:01:05.269
<v Anton Siering>vertical customers, so different
industries and different customers within those

19
00:01:06.050 --> 00:01:11.889
<v Anton Siering>industries, specifically in the automotive
sector, we have been working for the past

20
00:01:11.889 --> 00:01:12.750
<v Anton Siering>several years.

21
00:01:13.230 --> 00:01:17.760
<v Anton Siering>Um, being responsible for digitalization,
which is the second aspect of my position,

22
00:01:18.129 --> 00:01:23.410
<v Anton Siering>I'm in charge of tailoring our sales
activities for digital services actually

23
00:01:23.830 --> 00:01:28.099
<v Anton Siering>towards vertical specific needs, towards
customer requirements, so to say.

24
00:01:28.389 --> 00:01:34.989
<v Anton Siering>This means I work closely with automotive
manufacturers, customers, um, OEMs to

25
00:01:34.989 --> 00:01:38.029
<v Anton Siering>understand their unique challenges.

26
00:01:38.730 --> 00:01:44.769
<v Anton Siering>Whereby those challenges, they might vary
from production line complexity to quality

27
00:01:44.769 --> 00:01:50.489
<v Anton Siering>requirements, um, and then, um, by the end
of the day, we need to match our digital

28
00:01:50.489 --> 00:01:55.650
<v Anton Siering>solutions, um, in order to solve those
specific pain points and challenges and

29
00:01:55.650 --> 00:01:56.169
<v Anton Siering>requirements.

30
00:01:57.099 --> 00:01:57.519
<v Speaker 2>Oh wow.

31
00:01:57.669 --> 00:02:01.440
<v Speaker 2>So you are really bridging both the
business and digital side then.

32
00:02:02.709 --> 00:02:08.550
<v Anton Siering>Well, exactly, uh, it is a fascinating
role, um, because I get to see firsthand how

33
00:02:08.550 --> 00:02:14.509
<v Anton Siering>digital transformation is reshaping,
especially automotive, uh, manufacturing, uh,

34
00:02:14.589 --> 00:02:16.050
<v Anton Siering>vertical or industry.

35
00:02:17.899 --> 00:02:18.139
<v Speaker 2>Great.

36
00:02:18.259 --> 00:02:20.020
<v Speaker 2>So, yeah, thanks for the intro.

37
00:02:20.179 --> 00:02:23.960
<v Speaker 2>It sounds like you are in the perfect
position to guide us through today's topic.

38
00:02:24.509 --> 00:02:26.919
<v Speaker 2>And let's kick things off with a simple
question.

39
00:02:27.300 --> 00:02:32.179
<v Speaker 2>Can you explain to our new listeners what
predictive maintenance actually is and how

40
00:02:32.179 --> 00:02:34.820
<v Speaker 2>it's different from the more traditional
maintenance approaches?

41
00:02:35.649 --> 00:02:37.050
<v Anton Siering>Sure, no problem with that.

42
00:02:37.210 --> 00:02:39.570
<v Anton Siering>So, predictive maintenance, what is that?

43
00:02:39.929 --> 00:02:45.869
<v Anton Siering>Um, how does it work and, um, how, which
data it, um, actually uses.

44
00:02:45.929 --> 00:02:51.529
<v Anton Siering>So predictive maintenance uses real-time
data coming from sensors, um, and actors,

45
00:02:51.570 --> 00:02:53.850
<v Anton Siering>um, and coming from the shop floor itself.

46
00:02:54.220 --> 00:03:00.690
<v Anton Siering>Further on, um, um, it has AI analytics to
identify potential equipment failures.

47
00:03:01.119 --> 00:03:05.839
<v Anton Siering>Um, and those failures, they will be
identified before they actually happen, which

48
00:03:05.839 --> 00:03:08.720
<v Anton Siering>is really great benefit, I guess.

49
00:03:09.039 --> 00:03:15.850
<v Anton Siering>Unlike reactive maintenance, which is
another, um, maintenance approach, um, Uh,

50
00:03:16.029 --> 00:03:20.949
<v Anton Siering>it's, it's better because, uh, reactive
maintenance happens actually after the

51
00:03:20.949 --> 00:03:21.449
<v Anton Siering>breakdown.

52
00:03:21.639 --> 00:03:28.139
<v Anton Siering>Preventive maintenance, which follows a
fixed, um, fixed schedules, um,

53
00:03:28.429 --> 00:03:35.389
<v Anton Siering>will perhaps not really see the, the, the
failure, so to say, before it happens, but

54
00:03:35.389 --> 00:03:37.419
<v Anton Siering>predictive maintenance is very dynamic.

55
00:03:37.509 --> 00:03:42.429
<v Anton Siering>It helps automotive manufacturers act at
the real, uh, at the right time, not too

56
00:03:42.429 --> 00:03:44.509
<v Anton Siering>early, but also not too late.

57
00:03:45.880 --> 00:03:50.960
<v Speaker 2>Perhaps you can give to me and to our
listeners a simple analogy to understand it

58
00:03:50.960 --> 00:03:51.520
<v Speaker 2>better.

59
00:03:53.270 --> 00:03:55.139
<v Anton Siering>Uh, sure, let me, um.

60
00:03:56.139 --> 00:03:57.940
<v Anton Siering>Well let me try to explain this.

61
00:03:58.330 --> 00:04:00.500
<v Anton Siering>Think of it's like this.

62
00:04:00.580 --> 00:04:05.220
<v Anton Siering>Reactive maintenance is like waiting for
your car to break down on the highway.

63
00:04:05.380 --> 00:04:11.720
<v Anton Siering>Preventive maintenance is like changing
your oil every 3000 miles,

64
00:04:12.179 --> 00:04:17.399
<v Anton Siering>regardless actually of condition of the
car or the oil or the motor itself.

65
00:04:17.859 --> 00:04:20.920
<v Anton Siering>But predictive maintenance is something
completely different, right?

66
00:04:21.140 --> 00:04:23.619
<v Anton Siering>Predictive maintenance is like having
sensors.

67
00:04:24.079 --> 00:04:30.359
<v Anton Siering>That will tell you exactly when that oil
needs

68
00:04:31.209 --> 00:04:33.899
<v Anton Siering>changing based on actual degradation.

69
00:04:34.140 --> 00:04:39.339
<v Anton Siering>In automotive manufacturing, where a
single hour of the downturn can cost hundreds

70
00:04:39.339 --> 00:04:43.279
<v Anton Siering>of thousands of dollars, this precision
and timing is absolutely critical.

71
00:04:45.109 --> 00:04:50.190
<v Speaker 2>And as we know, automotive production
lines are some of the most complex, right?

72
00:04:50.809 --> 00:04:54.920
<v Speaker 2>Uh, where do you typically see the most
critical failure risks?

73
00:04:55.480 --> 00:05:00.130
<v Anton Siering>Um, that's a good question actually, um,
and you're absolutely right.

74
00:05:00.209 --> 00:05:05.630
<v Anton Siering>Automotive plants are the perfect storm of
fast moving equipment operations which

75
00:05:06.290 --> 00:05:11.649
<v Anton Siering>last, um, 24/7 and just in time production
is extremely critical and extremely

76
00:05:11.649 --> 00:05:12.010
<v Anton Siering>important.

77
00:05:12.559 --> 00:05:19.190
<v Anton Siering>Some of the highest risk areas we do see
around robotic

78
00:05:19.190 --> 00:05:25.149
<v Anton Siering>arms, paint, shops, conveyor systems, but
also automated presses.

79
00:05:25.230 --> 00:05:29.609
<v Anton Siering>So those are the main focus assets for us.

80
00:05:30.839 --> 00:05:35.420
<v Speaker 2>And so when one of those goes down,
everything downstream is also impacted.

81
00:05:36.320 --> 00:05:38.160
<v Anton Siering>That's correct, absolutely correct.

82
00:05:38.640 --> 00:05:43.399
<v Anton Siering>Um, there are tightly synchronized, all of
the assets, all of the production lines,

83
00:05:43.660 --> 00:05:49.079
<v Anton Siering>so all of the processes, um, very tightly
synchronized with, um, with a very small,

84
00:05:49.160 --> 00:05:52.269
<v Anton Siering>actually, with a minimal buffer of time.

85
00:05:52.760 --> 00:05:59.679
<v Anton Siering>Um, so even a, a, a short, unplanned stop
can actually, um, affect downstream

86
00:05:59.679 --> 00:06:01.440
<v Anton Siering>operations or entire shifts.

87
00:06:01.750 --> 00:06:08.630
<v Anton Siering>So for example, in body shops, we often
see critical risks in spot welding robots.

88
00:06:08.910 --> 00:06:13.119
<v Anton Siering>A single robot failure can halt an entire
production line actually, right?

89
00:06:13.230 --> 00:06:19.329
<v Anton Siering>So paint shops, another example, are
particularly sensitive because they involve

90
00:06:19.869 --> 00:06:25.239
<v Anton Siering>complex chemical processes and given
those.

91
00:06:25.920 --> 00:06:31.700
<v Anton Siering>Complex chemical processes, also a lot of
environmental controls around those

92
00:06:31.700 --> 00:06:31.940
<v Anton Siering>processes.

93
00:06:32.059 --> 00:06:38.339
<v Anton Siering>So even something, um, as simple as a F,
um, motor starting to fail can lead to

94
00:06:38.339 --> 00:06:44.320
<v Anton Siering>quality defects that might not be
discovered until the final injection.

95
00:06:44.940 --> 00:06:48.279
<v Anton Siering>Um, and so this failure.

96
00:06:48.609 --> 00:06:55.170
<v Anton Siering>Um, can result, um, finally in, in a very
costly rework and, and, and

97
00:06:55.170 --> 00:06:56.839
<v Anton Siering>quality, um, effects.

98
00:06:57.130 --> 00:07:03.929
<v Anton Siering>So predictive maintenance here helps
manufacturers to detect very early, um, the

99
00:07:03.929 --> 00:07:10.170
<v Anton Siering>first signs of failure, unusual vibration,
temperature, spikes, pressure, perhaps,

100
00:07:10.250 --> 00:07:14.769
<v Anton Siering>um, and so it gives an opportunity for the
operations.

101
00:07:15.070 --> 00:07:21.570
<v Anton Siering>Um, uh, for the operator itself to
intervene before things escalate into major

102
00:07:21.570 --> 00:07:22.130
<v Anton Siering>breakdown.

103
00:07:23.640 --> 00:07:28.029
<v Speaker 2>Yeah, that makes total sense, especially
knowing how tightly integrated everything

104
00:07:28.029 --> 00:07:28.450
<v Speaker 2>is.

105
00:07:28.959 --> 00:07:34.880
<v Speaker 2>But now perhaps just let's get more
specific and let's talk about the assets, yeah.

106
00:07:35.200 --> 00:07:40.600
<v Speaker 2>So how does predictive maintenance apply
to assets like robotic arms, for example?

107
00:07:41.380 --> 00:07:41.390
<v Anton Siering>Hm.

108
00:07:42.220 --> 00:07:44.420
<v Anton Siering>All right, so let's get a little bit
technical, right?

109
00:07:44.549 --> 00:07:49.649
<v Anton Siering>So each of those assets has a unique
behaviors and, um, also unique failure modes,

110
00:07:49.670 --> 00:07:50.309
<v Anton Siering>of course.

111
00:07:50.700 --> 00:07:55.019
<v Anton Siering>Uh, with robotic arms, as you ask it, uh,
we often track things like motor

112
00:07:55.019 --> 00:08:01.899
<v Anton Siering>vibration, joint wear, um, overheating,
um, and things which are similar to, to the

113
00:08:01.899 --> 00:08:04.160
<v Anton Siering>very, um, to the hardware itself.

114
00:08:04.820 --> 00:08:05.640
<v Anton Siering>Um.

115
00:08:07.809 --> 00:08:14.369
<v Anton Siering>When, let me put it like this, we also
monitor more subtle indicators like for

116
00:08:14.369 --> 00:08:21.179
<v Anton Siering>example, Changes in acceleration patterns
or energy consumption that might indicate

117
00:08:21.179 --> 00:08:28.019
<v Anton Siering>some very lean and small bearing where,
um, months actually before actual

118
00:08:28.019 --> 00:08:28.489
<v Anton Siering>failure.

119
00:08:28.779 --> 00:08:33.739
<v Anton Siering>So there are, there is, there is a
company, so to say, of, um, of assets which we

120
00:08:33.739 --> 00:08:35.900
<v Anton Siering>are monitoring within robotic arms.

121
00:08:37.028 --> 00:08:37.669
<v Speaker 2>Understand.

122
00:08:37.698 --> 00:08:40.869
<v Speaker 2>And what about conveyors or paint systems?

123
00:08:41.348 --> 00:08:47.148
<v Anton Siering>Yeah, this is another application, so to
say, or in other assets where we can apply

124
00:08:47.148 --> 00:08:48.299
<v Anton Siering>predictive maintenance.

125
00:08:48.708 --> 00:08:54.189
<v Anton Siering>So conveyor belts might show anomalies in
torque or alignment, right?

126
00:08:54.749 --> 00:08:59.109
<v Anton Siering>But we'll also track belts, tension,
vibrations, and motor current signatures as

127
00:08:59.109 --> 00:08:59.609
<v Anton Siering>well.

128
00:09:00.338 --> 00:09:00.508
<v Anton Siering>Um.

129
00:09:01.330 --> 00:09:08.109
<v Anton Siering>And paint shops, for example, even minor
disturbances in airflow or pump pressure

130
00:09:08.530 --> 00:09:09.909
<v Anton Siering>can affect quality.

131
00:09:10.770 --> 00:09:17.090
<v Anton Siering>We can monitor everything from spray gun
patterns to booth temperature

132
00:09:17.090 --> 00:09:21.190
<v Anton Siering>uniformity, sensor predictive maintenance,
which is the solution.

133
00:09:21.559 --> 00:09:27.039
<v Anton Siering>Um, uh, we can apply sensorpredictive
maintenance for sensor data, as I already

134
00:09:27.039 --> 00:09:33.419
<v Anton Siering>said, from those systems and use AI to
identify those patterns, um, those behaviors.

135
00:09:33.750 --> 00:09:40.750
<v Anton Siering>Um, and then applying, uh, um, um, um,
artificial intelligence, we, we actually can

136
00:09:40.750 --> 00:09:43.479
<v Anton Siering>indicate the early signs of, of the
failure as I already said.

137
00:09:43.559 --> 00:09:47.630
<v Anton Siering>So sometimes, Um, actually weeks in
advance.

138
00:09:47.799 --> 00:09:54.330
<v Anton Siering>Um, what's really powerful is that the
system learns, uh, the unique behavior of

139
00:09:54.330 --> 00:09:57.739
<v Anton Siering>each and every asset in a normal
operation, so to say.

140
00:09:58.090 --> 00:10:03.260
<v Anton Siering>Um, And can basically also consume its
normal

141
00:10:04.799 --> 00:10:06.830
<v Anton Siering>behavior in a specific environment.

142
00:10:07.159 --> 00:10:12.520
<v Anton Siering>A robot in a hot stamping area, for
example, behaves completely differently than the

143
00:10:12.520 --> 00:10:19.400
<v Anton Siering>one in the final assembly, and the AI,
which is applied and deployed within

144
00:10:19.400 --> 00:10:23.719
<v Anton Siering>Sensor predictive maintenance, accounts
for those contextual differences too.

145
00:10:24.969 --> 00:10:29.919
<v Speaker 2>So in the end it's not just about avoiding
breakdowns, it's about protecting quality

146
00:10:29.919 --> 00:10:30.450
<v Speaker 2>too, right?

147
00:10:31.840 --> 00:10:35.739
<v Speaker 2>But many plants already do schedule
preventive maintenance.

148
00:10:36.119 --> 00:10:37.599
<v Speaker 2>Why is that not enough anymore?

149
00:10:37.760 --> 00:10:39.260
<v Speaker 2>Why should they switch to predictive?

150
00:10:40.309 --> 00:10:41.960
<v Anton Siering>Um, that's a very good question.

151
00:10:42.289 --> 00:10:47.429
<v Anton Siering>Um, and that is actually true that
preventive maintenance is widely used across many

152
00:10:47.429 --> 00:10:53.070
<v Anton Siering>manufacturers, automotive manufacturers,
um, but it's based on the fixed intervals,

153
00:10:53.109 --> 00:10:56.070
<v Anton Siering>as already said, not actual asset
condition.

154
00:10:56.340 --> 00:11:02.669
<v Anton Siering>That means you're either maintaining too
early and wasting resources, of course, or

155
00:11:02.669 --> 00:11:06.710
<v Anton Siering>too late and you may risk some failures.

156
00:11:07.150 --> 00:11:12.469
<v Anton Siering>I have seen cases where manufacturers, uh,
were replacing perfectly good components

157
00:11:12.469 --> 00:11:18.710
<v Anton Siering>and just, just because the calendar said
so, that's very expensive and wasteful, of

158
00:11:18.710 --> 00:11:19.169
<v Anton Siering>course.

159
00:11:20.229 --> 00:11:22.830
<v Speaker 2>But sometimes the opposite happens too,
right?

160
00:11:24.460 --> 00:11:25.929
<v Anton Siering>Yeah, sure.

161
00:11:26.340 --> 00:11:29.039
<v Anton Siering>Sometimes we have some opposite cases too,
exactly.

162
00:11:29.330 --> 00:11:34.530
<v Anton Siering>Um, I have also seen equipment fail two
weeks before scheduled maintenance, um,

163
00:11:34.739 --> 00:11:39.659
<v Anton Siering>because, um, because the usage patterns,
so the behavior within the plant, within

164
00:11:39.659 --> 00:11:40.940
<v Anton Siering>the line had changed.

165
00:11:41.140 --> 00:11:43.940
<v Anton Siering>Predictive maintenance is data-driven and
very dynamic.

166
00:11:44.039 --> 00:11:48.940
<v Anton Siering>It adjusts in, in, in real time, so that
the asset is.

167
00:11:49.510 --> 00:11:55.929
<v Anton Siering>Um, is actually, so, um, we're able to
say, um,

168
00:11:56.309 --> 00:12:02.429
<v Anton Siering>consume the, the real environment, the
actual, um, uh, conditions, so to say, of the

169
00:12:02.429 --> 00:12:02.909
<v Anton Siering>asset.

170
00:12:03.309 --> 00:12:08.190
<v Anton Siering>Um, the weir, um, the usage, the load
condition, and so forth and so forth.

171
00:12:08.590 --> 00:12:13.429
<v Anton Siering>So, for instance, if a production line
runs over time to meet demand, um, the

172
00:12:13.429 --> 00:12:16.510
<v Anton Siering>maintenance needs, uh, change accordingly.

173
00:12:16.890 --> 00:12:21.570
<v Anton Siering>You know, um, and the system recognized
this, um, the system, by the system, I mean,

174
00:12:21.710 --> 00:12:27.049
<v Anton Siering>um, sense of predictive maintenance, um,
is able to recognize this and adjust its

175
00:12:27.049 --> 00:12:28.330
<v Anton Siering>prediction, basically, right?

176
00:12:28.409 --> 00:12:29.619
<v Anton Siering>So it's very dynamic.

177
00:12:29.929 --> 00:12:32.989
<v Anton Siering>And that's the key, um, I guess, in
automotive, um.

178
00:12:33.750 --> 00:12:39.710
<v Anton Siering>An industry where each and every downtime
is very, very costly.

179
00:12:40.460 --> 00:12:46.710
<v Anton Siering>It disrupts everything from production to
delivery schedules and can even impact

180
00:12:46.710 --> 00:12:48.929
<v Anton Siering>customer vehicle deliveries itself.

181
00:12:50.750 --> 00:12:55.090
<v Speaker 2>Right, and I think those disruptions
ripple through entire plants as we know, right?

182
00:12:55.590 --> 00:12:59.010
<v Speaker 2>So, maybe let's talk about real world
impact now.

183
00:12:59.270 --> 00:13:05.349
<v Speaker 2>Can you share with us a real-world example
of some automotive company that already

184
00:13:05.349 --> 00:13:08.570
<v Speaker 2>uses Siemens predictive maintenance here
sinceI in this case?

185
00:13:09.390 --> 00:13:11.109
<v Anton Siering>Sure, that's, that's a very good question.

186
00:13:11.440 --> 00:13:17.799
<v Anton Siering>Um, so just from the top of my head, one
example that stands out is a customer using

187
00:13:17.799 --> 00:13:24.799
<v Anton Siering>Sensai who was able to save $45 million in
labor in

188
00:13:24.799 --> 00:13:27.200
<v Anton Siering>unplanned downtime, um.

189
00:13:28.590 --> 00:13:32.919
<v Anton Siering>Uh, and this, uh, on at a very, very
single site.

190
00:13:33.039 --> 00:13:36.840
<v Anton Siering>So you have to imagine that that's really
a number, right?

191
00:13:36.960 --> 00:13:43.809
<v Anton Siering>So only one site since 2019 when the
sensori was first deployed there, um,

192
00:13:44.239 --> 00:13:49.919
<v Anton Siering>they already been able to save so much
money in labor, but also in, in, in unplanned

193
00:13:49.919 --> 00:13:50.479
<v Anton Siering>downtime.

194
00:13:51.820 --> 00:13:56.900
<v Speaker 2>Wow, yes, $45 million sounds, is a massive
number for sure.

195
00:13:57.520 --> 00:13:58.000
<v Anton Siering>That's true.

196
00:13:58.080 --> 00:13:58.440
<v Anton Siering>That's true.

197
00:13:58.520 --> 00:14:05.479
<v Anton Siering>That's, that's really is, um, but what's
even more exciting is how quickly

198
00:14:05.479 --> 00:14:08.260
<v Anton Siering>they were able to, to make those returns.

199
00:14:09.020 --> 00:14:15.840
<v Anton Siering>Um, uh, so the return on investment was
reached in less than 3 months after the

200
00:14:15.840 --> 00:14:17.150
<v Anton Siering>scaling phase, of course.

201
00:14:17.599 --> 00:14:23.200
<v Anton Siering>So initially they started with just the
most critical assets as the most customers

202
00:14:23.200 --> 00:14:23.760
<v Anton Siering>should do.

203
00:14:24.099 --> 00:14:29.390
<v Anton Siering>Um, basically the bottleneck equipment
that would cause, um, the most destruction,

204
00:14:29.890 --> 00:14:32.330
<v Anton Siering>um, in case this will fail, of course.

205
00:14:32.619 --> 00:14:38.140
<v Anton Siering>Within weeks, the system identified, um,
developing faults in a key press, um, in

206
00:14:38.140 --> 00:14:44.770
<v Anton Siering>the press line, uh, that would have
resulted basically if it would happen, uh,

207
00:14:45.059 --> 00:14:49.539
<v Anton Siering>there was a result in a catastrophic
failure during the peak production time, right?

208
00:14:49.619 --> 00:14:52.179
<v Anton Siering>So it's really a disaster, um.

209
00:14:52.960 --> 00:14:59.739
<v Anton Siering>And by addressing it during a planned
maintenance window, they avoided what

210
00:14:59.919 --> 00:15:02.710
<v Anton Siering>would have been a multi-day shutdown.

211
00:15:03.119 --> 00:15:04.559
<v Anton Siering>So that's, that's great, right?

212
00:15:04.719 --> 00:15:06.099
<v Anton Siering>So the confidence.

213
00:15:07.390 --> 00:15:12.840
<v Anton Siering>Basically, this gave them to lead rapid
expansion, uh, just a simple example, right,

214
00:15:13.380 --> 00:15:17.989
<v Anton Siering>uh, across basically other assets and
other lines.

215
00:15:18.450 --> 00:15:23.380
<v Anton Siering>And now they're using predictive
maintenance insights, not just for the, for the

216
00:15:23.380 --> 00:15:27.419
<v Anton Siering>maintenance, but also for the production
planning and spare parts, um, inventory

217
00:15:27.419 --> 00:15:28.119
<v Anton Siering>optimization.

218
00:15:28.539 --> 00:15:32.479
<v Anton Siering>So there are also some other use cases
possible using.

219
00:15:33.700 --> 00:15:35.799
<v Speaker 2>Yeah, yeah, for sure, that's a powerful
result.

220
00:15:36.500 --> 00:15:42.059
<v Speaker 2>But when we talk about automotive
industry, um, we know that it does not work in

221
00:15:42.059 --> 00:15:42.859
<v Speaker 2>isolation.

222
00:15:43.049 --> 00:15:48.900
<v Speaker 2>It also relies heavily on suppliers and
OEMs often work with tier one and tier 2

223
00:15:48.900 --> 00:15:49.700
<v Speaker 2>suppliers, yeah.

224
00:15:50.179 --> 00:15:55.280
<v Speaker 2>So, Can predictive maintenance be extended
to supply networks as well?

225
00:15:56.859 --> 00:16:02.799
<v Anton Siering>Yeah, well, actually it's not the use
case, so absolutely, yes, we're seeing more

226
00:16:02.799 --> 00:16:07.640
<v Anton Siering>manufacturers, more automotive
manufacturers encouraging or even requiring their

227
00:16:07.640 --> 00:16:13.270
<v Anton Siering>suppliers to adopt predictive
capabilities, predictive maintenance, in general,

228
00:16:13.320 --> 00:16:14.500
<v Anton Siering>predictive capabilities.

229
00:16:14.849 --> 00:16:18.929
<v Anton Siering>Um, with sensor predictive maintenance,
the solution can be applied across plants,

230
00:16:18.969 --> 00:16:21.799
<v Anton Siering>so it's horizontally scalable, right?

231
00:16:22.130 --> 00:16:27.309
<v Anton Siering>Where it is the OAM's facility or tier,
uh, tier one supplier.

232
00:16:28.380 --> 00:16:32.320
<v Speaker 2>Yeah, so in the end we can say that
predictive maintenance isn't just an OEM

233
00:16:32.320 --> 00:16:36.130
<v Speaker 2>advantage, but it can actually strengthen
the whole supply chain, yeah,

234
00:16:36.700 --> 00:16:37.979
<v Anton Siering>for sure, for sure, totally.

235
00:16:38.059 --> 00:16:44.780
<v Anton Siering>This kind of shared visibility helps
basically to make supply chain more

236
00:16:44.780 --> 00:16:49.619
<v Anton Siering>stable and also reduce last minute quality
issues or delays.

237
00:16:49.700 --> 00:16:55.299
<v Anton Siering>For example, we have OMs who are sharing
predictive maintenance best practices with

238
00:16:55.299 --> 00:17:01.200
<v Anton Siering>their key suppliers and um Even providing
access to, uh, to the same platform.

239
00:17:01.780 --> 00:17:08.709
<v Anton Siering>Um, and this, of course, creates, um, the
common language around assets, around, um,

240
00:17:08.770 --> 00:17:11.180
<v Anton Siering>assets, health and reliability.

241
00:17:11.459 --> 00:17:15.339
<v Anton Siering>When a supplier can predict and prevent
failures in their stamping press or

242
00:17:15.339 --> 00:17:21.250
<v Anton Siering>injection molding machines, um, it
directly benefits the OAM's production stability,

243
00:17:21.339 --> 00:17:21.530
<v Anton Siering>right?

244
00:17:21.619 --> 00:17:23.680
<v Anton Siering>So everything is basically connected.

245
00:17:24.078 --> 00:17:30.798
<v Anton Siering>Um, we're also seeing innovative models
where OEMs and suppliers share their cost

246
00:17:30.798 --> 00:17:33.918
<v Anton Siering>savings from reduced downtime, creating.

247
00:17:34.239 --> 00:17:38.698
<v Speaker 2>That's becoming critical, especially with
today's global supply chain challenges.

248
00:17:39.038 --> 00:17:44.399
<v Speaker 2>But as we also know, automotive companies
are often short of skilled labor.

249
00:17:44.558 --> 00:17:50.598
<v Speaker 2>Yeah, what happens if a manufacturer,
let's say, doesn't have in-house data experts

250
00:17:50.598 --> 00:17:51.479
<v Speaker 2>to manage all this?

251
00:17:52.430 --> 00:17:59.250
<v Anton Siering>Yeah, and that's exactly the right spot
for Siemens to come in, um, uh,

252
00:17:59.270 --> 00:18:01.189
<v Anton Siering>with another, say, solution.

253
00:18:01.979 --> 00:18:07.069
<v Anton Siering>It's a Siemens data enhanced service
contracts, and those contracts can make a real

254
00:18:07.069 --> 00:18:08.030
<v Anton Siering>difference, right?

255
00:18:08.189 --> 00:18:14.479
<v Anton Siering>So we go beyond delivering technology and
we're combining ongoing monitoring um

256
00:18:15.109 --> 00:18:20.430
<v Anton Siering>with expert-driven data interpretation, so
to say.

257
00:18:20.770 --> 00:18:27.510
<v Anton Siering>Um, and those, this combination technology
and expertise onsite, basically,

258
00:18:28.050 --> 00:18:34.209
<v Anton Siering>um, is there to ensure that our customers
can act based on, uh, on, on data without

259
00:18:34.209 --> 00:18:38.000
<v Anton Siering>needing an in-house analytics, um, teams
or experts.

260
00:18:39.140 --> 00:18:44.219
<v Speaker 2>So basically you're saying that Plant
doesn't need to hire any of its own data

261
00:18:44.219 --> 00:18:44.790
<v Speaker 2>science team.

262
00:18:44.939 --> 00:18:49.160
<v Speaker 2>Siemens can essentially provide the
support.

263
00:18:49.930 --> 00:18:51.599
<v Anton Siering>Yes, that's exactly correct.

264
00:18:51.729 --> 00:18:53.790
<v Anton Siering>That's, that's absolutely correct.

265
00:18:54.449 --> 00:18:59.130
<v Anton Siering>Take the case of one of multiple CNC
machines in a manufacturing plant, right?

266
00:18:59.290 --> 00:19:06.170
<v Anton Siering>So through the service, through those
contracts, and by leverage, leveraging the

267
00:19:06.170 --> 00:19:11.969
<v Anton Siering>data which might be extracted from the
machines, Siemens experts remotely, they

268
00:19:11.969 --> 00:19:16.209
<v Anton Siering>don't need to be on site remotely monitor
the various machines' production data and

269
00:19:16.209 --> 00:19:17.130
<v Anton Siering>health statuses.

270
00:19:17.800 --> 00:19:24.400
<v Anton Siering>And if the efficiency, for example, of a
CNC machine drops, just for

271
00:19:24.400 --> 00:19:31.359
<v Anton Siering>example, say due to local operator faults
or gradual performance decline, the system

272
00:19:31.359 --> 00:19:38.300
<v Anton Siering>detects this immediately, and it
automatically raises the service ticket

273
00:19:38.520 --> 00:19:40.439
<v Anton Siering>by a shuffle monitoring services.

274
00:19:40.630 --> 00:19:41.729
<v Anton Siering>It's another solution.

275
00:19:42.180 --> 00:19:48.780
<v Anton Siering>And Siemens expert steps in to analyze the
root case and to help the customer to

276
00:19:48.780 --> 00:19:50.060
<v Anton Siering>solve this case.

277
00:19:51.680 --> 00:19:55.109
<v Speaker 2>OK, so they basically guiding this fix,
right?

278
00:19:56.170 --> 00:19:57.050
<v Anton Siering>Yeah, yeah, exactly.

279
00:19:57.209 --> 00:20:02.109
<v Anton Siering>So, so instead of requiring, uh, the
plant, uh, maintenance managers to, um,

280
00:20:02.280 --> 00:20:07.489
<v Anton Siering>interpret the complex data, you know, our
experts identify the, the, uh, identifies

281
00:20:07.489 --> 00:20:10.050
<v Anton Siering>the cycle time issue and recommend the
fix.

282
00:20:10.329 --> 00:20:11.469
<v Anton Siering>So very easy.

283
00:20:11.770 --> 00:20:16.689
<v Anton Siering>Um, and this can be done remotely or via
on-site support.

284
00:20:16.770 --> 00:20:22.069
<v Anton Siering>It's up to the customer to decide which,
which type of that, uh, is preferable.

285
00:20:22.500 --> 00:20:29.500
<v Anton Siering>Uh, we have had cases where, um, we helped
customers solve problems they didn't even

286
00:20:29.500 --> 00:20:30.739
<v Anton Siering>know they had, right?

287
00:20:30.939 --> 00:20:35.020
<v Anton Siering>Because we are deeply into the data and
trying to analyze the data each and every

288
00:20:35.020 --> 00:20:37.290
<v Anton Siering>time, um, the data is coming.

289
00:20:37.660 --> 00:20:44.119
<v Anton Siering>Um, so I said, we're identifying the
certain shift patterns, uh, which, uh, um,

290
00:20:44.329 --> 00:20:51.079
<v Anton Siering>causing Uh, for example, accelerated wear,
um, on specific, um, um, uh, on specific

291
00:20:51.079 --> 00:20:51.719
<v Anton Siering>equipment.

292
00:20:51.839 --> 00:20:57.880
<v Anton Siering>Um, and, uh, this real-time support is,
um, included, of course, in the service

293
00:20:57.880 --> 00:20:58.839
<v Anton Siering>contract, right?

294
00:20:59.109 --> 00:21:03.920
<v Anton Siering>Um, uh, making it basically even, even
easier, right?

295
00:21:04.119 --> 00:21:08.910
<v Anton Siering>Making it, um, plug and play model for the
customers with limited internal

296
00:21:08.910 --> 00:21:09.420
<v Anton Siering>resources.

297
00:21:09.709 --> 00:21:14.550
<v Anton Siering>It's particularly valuable actually for
mid-sized suppliers who want

298
00:21:14.550 --> 00:21:21.270
<v Anton Siering>enterprise-level capabilities without
building large data science

299
00:21:21.270 --> 00:21:22.729
<v Anton Siering>teams on their site.

300
00:21:24.180 --> 00:21:26.150
<v Speaker 2>Yeah, that's for sure a huge value add.

301
00:21:26.579 --> 00:21:30.489
<v Speaker 2>And yeah, as I can see, AI is clearly at
the heart of it.

302
00:21:31.060 --> 00:21:34.969
<v Speaker 2>So speaking about AI, what role does it
actually play here?

303
00:21:35.300 --> 00:21:39.819
<v Speaker 2>Can the system, let's say, learn across
multiple production lines, lines or

304
00:21:39.819 --> 00:21:40.479
<v Speaker 2>factories?

305
00:21:41.359 --> 00:21:43.199
<v Anton Siering>Yes, absolutely, absolutely.

306
00:21:43.560 --> 00:21:45.959
<v Anton Siering>Um, that's one of the biggest benefits
actually.

307
00:21:46.729 --> 00:21:52.599
<v Anton Siering>Sensor AI learns the normal behavior of
the assets and then detects deviations.

308
00:21:53.449 --> 00:21:57.689
<v Speaker 2>Yes, OK, so then it's just, it's not just
a monitoring solution, it actually learns

309
00:21:57.689 --> 00:21:58.430
<v Speaker 2>the context.

310
00:21:59.250 --> 00:22:00.150
<v Anton Siering>Absolutely.

311
00:22:01.810 --> 00:22:04.369
<v Anton Siering>It goes actually even deeper than that.

312
00:22:05.199 --> 00:22:07.969
<v Anton Siering>The AI is able to understand the context.

313
00:22:08.160 --> 00:22:14.369
<v Anton Siering>It knows that a robot working 3 shifts
behaves differently than the one working on

314
00:22:14.369 --> 00:22:21.130
<v Anton Siering>the 2, so the contextualization of the
environment is already inbuilt in the

315
00:22:21.130 --> 00:22:21.449
<v Anton Siering>solution.

316
00:22:21.989 --> 00:22:28.430
<v Anton Siering>Another example is basically summer heat
affects equipment differently than

317
00:22:28.430 --> 00:22:29.810
<v Anton Siering>the winter cold.

318
00:22:31.109 --> 00:22:31.479
<v Anton Siering>You know,

319
00:22:32.689 --> 00:22:36.719
<v Speaker 2>yeah, and can it apply then this learning
beyond a single machine?

320
00:22:37.270 --> 00:22:38.369
<v Anton Siering>Yes, absolutely.

321
00:22:39.209 --> 00:22:41.359
<v Anton Siering>Um, it also supports fleet learning.

322
00:22:41.510 --> 00:22:47.670
<v Anton Siering>So if one robot welder in factory A fails,
the model helps identify

323
00:22:47.670 --> 00:22:53.810
<v Anton Siering>risks basically across similar assets in
factory B and also C.

324
00:22:54.199 --> 00:22:54.810
<v Anton Siering>What does it mean?

325
00:22:54.869 --> 00:23:01.680
<v Anton Siering>That means, um, that the operator itself
is able to make

326
00:23:01.680 --> 00:23:07.160
<v Anton Siering>smarter decisions at scale, not just on
asset by asset, so to say, not only on one

327
00:23:07.160 --> 00:23:09.349
<v Anton Siering>asset, but really across all the fleet.

328
00:23:09.969 --> 00:23:15.630
<v Anton Siering>We have seen this prevent cascading
failure across multiple plants, for instance,

329
00:23:15.859 --> 00:23:22.719
<v Anton Siering>um, When bearing failure, for example, was
detected in

330
00:23:22.719 --> 00:23:28.300
<v Anton Siering>one of the plant's conveyor system, the AI
flagged similar risks

331
00:23:29.229 --> 00:23:36.089
<v Anton Siering>signatures, so to say, patterns in two
other facilities, and this does allow.

332
00:23:38.140 --> 00:23:43.339
<v Anton Siering>Basically, preemptively replaced during
scheduled downtime.

333
00:23:44.869 --> 00:23:47.900
<v Speaker 2>And then the system also keeps improving
over time.

334
00:23:49.319 --> 00:23:50.540
<v Anton Siering>That's also correct.

335
00:23:51.270 --> 00:23:56.119
<v Anton Siering>Each and every failure, um, every
successful prediction, every false alarm teaches

336
00:23:56.119 --> 00:23:59.140
<v Anton Siering>the eye to be more um.

337
00:23:59.839 --> 00:24:05.040
<v Anton Siering>Yeah, how should I say, to be more
accurate and more nuanced in its, um, in its

338
00:24:05.040 --> 00:24:05.560
<v Anton Siering>prediction.

339
00:24:05.750 --> 00:24:06.260
<v Anton Siering>Yes.

340
00:24:06.760 --> 00:24:08.939
<v Speaker 2>Wow, yeah, that, that sounds really
powerful.

341
00:24:09.609 --> 00:24:15.599
<v Speaker 2>And now, this discussion actually leads
into something we are hearing more about

342
00:24:15.599 --> 00:24:18.479
<v Speaker 2>with every day, uh, which is
sustainability.

343
00:24:18.900 --> 00:24:23.270
<v Speaker 2>Automotive companies are under pressure to
hit sustainability goals, as we know.

344
00:24:23.430 --> 00:24:29.069
<v Speaker 2>So can predictive maintenance help them
reduce waste or extend equipment lifetime,

345
00:24:29.150 --> 00:24:29.770
<v Speaker 2>for example?

346
00:24:30.869 --> 00:24:33.209
<v Anton Siering>Um, so, absolutely.

347
00:24:33.510 --> 00:24:35.270
<v Anton Siering>Um, yes, um, definitely.

348
00:24:35.510 --> 00:24:41.229
<v Anton Siering>So by replacing parts only when needed,
uh, you reduce waste and also extend the

349
00:24:41.229 --> 00:24:46.489
<v Anton Siering>usable life of the assets, um, uh, of the
assets too, yes.

350
00:24:47.489 --> 00:24:47.890
<v Speaker 2>Very cool.

351
00:24:48.020 --> 00:24:53.130
<v Speaker 2>So basically predictive maintenance
directly cuts down on any unnecessary

352
00:24:53.130 --> 00:24:54.030
<v Speaker 2>replacements, right?

353
00:24:54.449 --> 00:24:56.130
<v Anton Siering>Yes, exactly, exactly.

354
00:24:57.010 --> 00:25:03.650
<v Anton Siering>It also lowers the energy use, the quality
scrap, and also the consumption of the

355
00:25:03.650 --> 00:25:04.410
<v Anton Siering>spare parts.

356
00:25:04.770 --> 00:25:10.489
<v Anton Siering>We have seen customers, to be honest,
which were able to reduce their spare parts

357
00:25:10.489 --> 00:25:14.130
<v Anton Siering>inventory by 30%, which is quite a number,
right?

358
00:25:14.520 --> 00:25:21.260
<v Anton Siering>while actually improving their
availability because they know exactly what they need

359
00:25:21.479 --> 00:25:23.119
<v Anton Siering>and when they do need that.

360
00:25:24.109 --> 00:25:24.119
<v Speaker 2>Mhm.

361
00:25:24.949 --> 00:25:26.949
<v Speaker 2>And what about energy efficiency?

362
00:25:27.069 --> 00:25:28.500
<v Speaker 2>Does it play a role too?

363
00:25:28.829 --> 00:25:30.030
<v Anton Siering>Yes, absolutely.

364
00:25:30.390 --> 00:25:35.260
<v Anton Siering>Energy efficiency is another big win of
predictive maintenance and sani, especially.

365
00:25:35.550 --> 00:25:42.189
<v Anton Siering>Equipment which is running in degraded
conditions often consumes

366
00:25:42.189 --> 00:25:48.660
<v Anton Siering>more energy, something around 15 to 20%
more energy by maintaining.

367
00:25:49.000 --> 00:25:53.319
<v Anton Siering>And the optimal performance and the
optimal conditions of the assets, you are

368
00:25:53.319 --> 00:25:57.500
<v Anton Siering>directly reducing the carbon footprint and
so the energy consumption too.

369
00:25:58.630 --> 00:25:59.079
<v Speaker 2>Mhm.

370
00:25:59.280 --> 00:26:05.380
<v Speaker 2>And I think that it also ties into broader
sustainability strategies, correct?

371
00:26:05.939 --> 00:26:07.150
<v Anton Siering>Absolutely, exactly.

372
00:26:07.319 --> 00:26:12.229
<v Anton Siering>So, um, Just think of the following
combination.

373
00:26:12.410 --> 00:26:19.140
<v Anton Siering>If you combine Sensai with our circular
service offerings, for example,

374
00:26:19.810 --> 00:26:25.500
<v Anton Siering>like buyback options for return parts,
predictive maintenance becomes a key,

375
00:26:25.930 --> 00:26:28.430
<v Anton Siering>basically a key enabler of more.

376
00:26:28.819 --> 00:26:31.170
<v Anton Siering>more sustainable production.

377
00:26:31.530 --> 00:26:38.329
<v Anton Siering>Some of our automotive customers are now
including predictive maintenance metrics

378
00:26:38.329 --> 00:26:43.930
<v Anton Siering>in their sustainability reports showing
stakeholders how smart maintenance,

379
00:26:44.209 --> 00:26:48.170
<v Anton Siering>predictive maintenance, smart maintenance
contributes basically to their

380
00:26:48.170 --> 00:26:53.609
<v Anton Siering>environmental goals and and also
sustainable strategies, so.

381
00:26:53.890 --> 00:26:59.089
<v Anton Siering>It's not just about being green, it's
really about being lean and green

382
00:26:59.089 --> 00:27:00.270
<v Anton Siering>simultaneously.

383
00:27:01.829 --> 00:27:05.329
<v Speaker 2>So in the end, it's good for up time and
for the planet.

384
00:27:07.550 --> 00:27:10.349
<v Speaker 2>So now let's bring it back to outcomes.

385
00:27:10.609 --> 00:27:15.530
<v Speaker 2>Uh, what kind of improvements would you
say can an automotive manufacturer expect?

386
00:27:15.589 --> 00:27:17.069
<v Speaker 2>But let's talk in real numbers, yeah?

387
00:27:17.589 --> 00:27:18.390
<v Anton Siering>Yeah, sure, sure.

388
00:27:18.709 --> 00:27:25.010
<v Anton Siering>So on average, on average, we see
customers reduce unplanned downtime by around 50%,

389
00:27:25.469 --> 00:27:26.349
<v Anton Siering>quite a number, right?

390
00:27:26.709 --> 00:27:28.969
<v Anton Siering>Just a half of the downtime.

391
00:27:29.380 --> 00:27:36.260
<v Anton Siering>Um, we're able to reach and cut
maintenance costs by 30%,

392
00:27:36.630 --> 00:27:36.969
<v Anton Siering>right?

393
00:27:37.099 --> 00:27:39.839
<v Anton Siering>It's another good number, good indicator.

394
00:27:40.500 --> 00:27:47.400
<v Anton Siering>Um, but as we talked about spare parts,
sustainability, we are able to increase

395
00:27:47.400 --> 00:27:53.290
<v Anton Siering>asset lifetime by sometimes even more than
20%.

396
00:27:53.739 --> 00:27:55.219
<v Anton Siering>So those are the real numbers.

397
00:27:55.819 --> 00:27:58.920
<v Speaker 2>Wow, yeah, those are impressive averages
actually.

398
00:27:59.609 --> 00:28:03.689
<v Speaker 2>But can you maybe share concrete examples
from real plants?

399
00:28:03.900 --> 00:28:05.280
<v Anton Siering>Oh yeah, yeah, sure, sure, sure.

400
00:28:05.859 --> 00:28:12.219
<v Anton Siering>So for example, one Bo shop reduced their
robot-related downtime from 120 hours per

401
00:28:12.219 --> 00:28:14.719
<v Anton Siering>hour to just 45 hours.

402
00:28:15.060 --> 00:28:21.380
<v Anton Siering>A paint shop customer improved their first
time, um, uh, first time through quality

403
00:28:21.380 --> 00:28:22.300
<v Anton Siering>by 8%.

404
00:28:22.500 --> 00:28:27.380
<v Anton Siering>That's really a number just by preventing
equipment degradation that was causing

405
00:28:27.380 --> 00:28:29.219
<v Anton Siering>those effects and quality issues.

406
00:28:29.530 --> 00:28:35.119
<v Anton Siering>Another manufacturer extended the life of
their press tools by 35%, right?

407
00:28:35.209 --> 00:28:37.930
<v Anton Siering>Xenia, so that's, that's really a number.

408
00:28:39.420 --> 00:28:44.219
<v Speaker 2>Yeah, it sounds like in the end it's not
just about cost savings, but it's also

409
00:28:44.219 --> 00:28:46.640
<v Speaker 2>about creating some kind of
predictability.

410
00:28:47.760 --> 00:28:49.479
<v Anton Siering>Exactly, yes, absolutely.

411
00:28:49.560 --> 00:28:54.560
<v Anton Siering>It's about creating predictability in our,
um, in your operation, the customer's

412
00:28:54.560 --> 00:28:59.439
<v Anton Siering>operations, so you can plan ahead, reduce
risks, and deliver on time, right?

413
00:28:59.560 --> 00:29:03.000
<v Anton Siering>So that's kind of like the big win, so to
say.

414
00:29:03.109 --> 00:29:05.469
<v Anton Siering>Predictability has cascading benefits.

415
00:29:05.880 --> 00:29:08.469
<v Anton Siering>It's a, it's a better production on the
one hand side.

416
00:29:08.479 --> 00:29:09.989
<v Anton Siering>It's a better production planning.

417
00:29:10.079 --> 00:29:14.380
<v Anton Siering>It's more accurate delivery promises to
the customer.

418
00:29:14.900 --> 00:29:21.640
<v Anton Siering>Um, uh, you can also reduce the overtime
costs and, of course, improve worker,

419
00:29:21.739 --> 00:29:28.479
<v Anton Siering>um, the, the safety for the workers itself
because you're not dealing with, um, uh,

420
00:29:28.579 --> 00:29:30.439
<v Anton Siering>with emergency repairs anymore.

421
00:29:31.060 --> 00:29:33.180
<v Anton Siering>Um, and of course, the financial impact.

422
00:29:33.260 --> 00:29:38.979
<v Anton Siering>The financial impact typically shows up in
multiple areas of the P&amp;L, not just in,

423
00:29:39.060 --> 00:29:41.979
<v Anton Siering>in the maintenance budget as we, as we
talked about.

424
00:29:43.040 --> 00:29:49.359
<v Speaker 2>Yeah, well, those are either compelling
numbers, but now if someone is listening and

425
00:29:49.359 --> 00:29:52.709
<v Speaker 2>thinking, where do I even start, what
would you say?

426
00:29:52.839 --> 00:29:58.359
<v Speaker 2>What is a realistic first step, and how
long will it actually take until they can

427
00:29:58.359 --> 00:29:59.660
<v Speaker 2>see the first results?

428
00:30:00.439 --> 00:30:05.989
<v Anton Siering>Yeah, so talking about the roadmap, so to
say, um, for predictive maintenance, I

429
00:30:05.989 --> 00:30:09.640
<v Anton Siering>would always, always say start with a
pilot on fuel.

430
00:30:10.170 --> 00:30:16.130
<v Anton Siering>On the very few critical assets, typically
something around 5 to 10.

431
00:30:17.079 --> 00:30:22.589
<v Anton Siering>5 to 10 pieces of equipment that are
either the bottleneck or having high failure

432
00:30:22.589 --> 00:30:22.609
<v Anton Siering>costs.

433
00:30:24.000 --> 00:30:29.819
<v Anton Siering>So those should be the indicators for how
to find out those critical assets.

434
00:30:30.239 --> 00:30:36.280
<v Anton Siering>Um, it's very fast to deploy, um, and the
results typically come in, uh, in weeks,

435
00:30:36.400 --> 00:30:37.479
<v Anton Siering>not, not months.

436
00:30:38.079 --> 00:30:43.790
<v Anton Siering>So, in fact, we often detect the first
actionable insights within 2, maybe 3 weeks,

437
00:30:43.800 --> 00:30:45.699
<v Anton Siering>um, of deployment from there.

438
00:30:46.060 --> 00:30:52.260
<v Anton Siering>You can expand, you can scale up, right,
across more equipment, across perhaps even

439
00:30:52.579 --> 00:30:53.609
<v Anton Siering>multiple plants.

440
00:30:54.099 --> 00:30:59.859
<v Anton Siering>So, um, the key is really to choose the
right asset for your pilot.

441
00:31:00.170 --> 00:31:05.310
<v Anton Siering>Uh, we help customers actually to
identify, um, equipment with good data

442
00:31:05.310 --> 00:31:10.670
<v Anton Siering>availability, um, And also with very high
business impact.

443
00:31:10.760 --> 00:31:16.239
<v Anton Siering>So we're partnering from the very
beginning, uh, with the customer, um, together to

444
00:31:16.239 --> 00:31:22.609
<v Anton Siering>find out and also to guide the customer
throughout the, the whole, um, Uh,

445
00:31:22.750 --> 00:31:24.469
<v Anton Siering>predictive maintenance journey, so to say.

446
00:31:24.540 --> 00:31:27.520
<v Anton Siering>With Siemens, we support the full life
cycle, as I said, right?

447
00:31:27.670 --> 00:31:34.420
<v Anton Siering>So from really initial assessment and
onboarding to analytics, training, and

448
00:31:34.420 --> 00:31:39.000
<v Anton Siering>continuous improvement, the whole, um, end
to end process is covered.

449
00:31:39.349 --> 00:31:40.040
<v Anton Siering>Um.

450
00:31:40.589 --> 00:31:46.040
<v Anton Siering>We have developed a proven roadmap that
takes customers from the pilot to plan-wide

451
00:31:46.040 --> 00:31:52.770
<v Anton Siering>deployment in 6 to 12 months or so, so
completely from 0 to 0, so to say,

452
00:31:54.199 --> 00:31:57.760
<v Anton Siering>and the beauty is that the pilot phase is
self-funding, right?

453
00:31:57.880 --> 00:32:04.160
<v Anton Siering>So the savings from preventing just 1 or 2
failures typically covers the

454
00:32:04.160 --> 00:32:06.400
<v Anton Siering>initial investment for the pilot phase.

455
00:32:06.930 --> 00:32:12.650
<v Anton Siering>And this does make it real easy to build
the business case for expansion.

456
00:32:13.859 --> 00:32:15.969
<v Speaker 2>OK, that sounds really interesting.

457
00:32:16.219 --> 00:32:19.339
<v Speaker 2>And I think this all has been incredibly
insightful.

458
00:32:19.459 --> 00:32:24.280
<v Speaker 2>So thank you very much, Anton, for sharing
your experience and also showing how

459
00:32:24.640 --> 00:32:28.599
<v Speaker 2>predictive maintenance is actually
reshaping the automotive industry.

460
00:32:30.380 --> 00:32:31.060
<v Anton Siering>Thank you very much.

461
00:32:31.219 --> 00:32:36.619
<v Anton Siering>It's been, it's been my pleasure um to, to
be there and having this, this, uh, this

462
00:32:36.619 --> 00:32:37.319
<v Anton Siering>talk with you.

463
00:32:37.660 --> 00:32:43.089
<v Anton Siering>It is an exciting time actually to be in
this field in the automotive industry, um,

464
00:32:43.099 --> 00:32:49.660
<v Anton Siering>and I'm also very, very thrilled to help
our customers unload such great benefits.

465
00:32:49.900 --> 00:32:50.979
<v Anton Siering>Thank you very much, Senia.

466
00:32:51.680 --> 00:32:55.390
<v Speaker 2>And to our listeners, if you'd like to
learn more about starting your own digital

467
00:32:55.390 --> 00:32:59.959
<v Speaker 2>journey or see how predictive maintenance
can help you reduce downtime, cut costs,

468
00:33:00.010 --> 00:33:04.560
<v Speaker 2>and boost performance, visit the Siemens
website for resources and for real-world

469
00:33:04.560 --> 00:33:05.199
<v Speaker 2>examples.

470
00:33:05.760 --> 00:33:08.050
<v Speaker 2>Thanks for tuning in and we'll see you
next time.

471
00:33:10.660 --> 00:33:15.619
<v Speaker 1>Please like and subscribe on all major
podcast channels and find out more about

472
00:33:15.619 --> 00:33:19.140
<v Speaker 1>Sensei predictive maintenance at
Siemens.com.
