WEBVTT
Language: en-US

1
00:00:05.590 --> 00:00:10.310
<v Liz McGinn>Welcome to the trend detection podcast,
powered by Siemens, and now your host, Liz

2
00:00:10.310 --> 00:00:10.710
<v Liz McGinn>McGinn.

3
00:00:16.438 --> 00:00:17.679
<v Liz McGinn>Hi everyone, I'm Liz McGinn.

4
00:00:17.759 --> 00:00:24.679
<v Liz McGinn>I am here um to talk about simplifying
your data um and kind of, uh, that

5
00:00:24.679 --> 00:00:25.399
<v Liz McGinn>was a bad intro.

6
00:00:25.438 --> 00:00:26.138
<v Liz McGinn>I am sorry.

7
00:00:31.000 --> 00:00:32.400
<v Liz McGinn>Hi everyone, I'm Liz McGinn.

8
00:00:32.680 --> 00:00:38.119
<v Liz McGinn>Today we're gonna talk about um how
Siemens simplifies the implementation and use of

9
00:00:38.119 --> 00:00:38.979
<v Liz McGinn>drive data.

10
00:00:39.560 --> 00:00:41.919
<v Liz McGinn>And I'm joined here by Dominic, our
expert.

11
00:00:42.080 --> 00:00:43.369
<v Liz McGinn>Dominic, do you want to introduce
yourself?

12
00:00:44.479 --> 00:00:45.759
<v Dominic>Hi, this is Dominic.

13
00:00:46.000 --> 00:00:48.500
<v Dominic>Thank you for having me here and talk
about this topic.

14
00:00:48.930 --> 00:00:55.479
<v Dominic>Um, I am, uh, at Siemens for 14 years now
and I'm coming from the

15
00:00:55.479 --> 00:00:58.720
<v Dominic>drives department, so you already saw it
in the title.

16
00:00:58.840 --> 00:01:05.360
<v Dominic>Um, I started my career as a, um, system
test engineer for drive systems.

17
00:01:05.440 --> 00:01:06.339
<v Dominic>I went over.

18
00:01:06.800 --> 00:01:11.879
<v Dominic>To field service and, and, and
commissioning engineer as well.

19
00:01:11.959 --> 00:01:15.580
<v Dominic>And then I started to get into
digitalization.

20
00:01:15.809 --> 00:01:21.720
<v Dominic>So I'm working as a project manager for
R&amp;D projects in

21
00:01:21.720 --> 00:01:24.209
<v Dominic>digitalization regarding drive technology.

22
00:01:24.559 --> 00:01:30.400
<v Dominic>And now, meanwhile, I'm a product manager
for an industrial edge app, um, also

23
00:01:30.400 --> 00:01:35.470
<v Dominic>addressing digitalization for drive
technology, especially in regards of predictive

24
00:01:35.470 --> 00:01:36.040
<v Dominic>maintenance.

25
00:01:37.190 --> 00:01:37.639
<v Liz McGinn>Awesome.

26
00:01:37.839 --> 00:01:41.080
<v Liz McGinn>Before we get too far into it, I'm from
the marketing world and I've heard the word

27
00:01:41.080 --> 00:01:45.319
<v Liz McGinn>drives in a couple of different contexts,
usually, like, you know, a one, you know,

28
00:01:45.389 --> 00:01:46.019
<v Liz McGinn>your one drive.

29
00:01:46.080 --> 00:01:48.940
<v Liz McGinn>Can you explain exactly what you mean when
you're saying drives?

30
00:01:50.139 --> 00:01:54.940
<v Dominic>Yes, so in industries whenever something
is in motion, normally it comes from a

31
00:01:54.940 --> 00:01:55.709
<v Dominic>drive system.

32
00:01:55.860 --> 00:02:01.400
<v Dominic>So, um, the easiest thing is you have a
motor, an electrical motor,

33
00:02:01.980 --> 00:02:06.139
<v Dominic>and in many cases you need that motor to
run in a certain speed.

34
00:02:06.220 --> 00:02:09.559
<v Dominic>So then you attach to it a frequency
converter.

35
00:02:10.330 --> 00:02:13.529
<v Dominic>So that you can run the motion like you
want to have it.

36
00:02:13.770 --> 00:02:19.889
<v Dominic>So mainly spoken drive technology is
frequency converters and electrical motors in

37
00:02:19.889 --> 00:02:20.550
<v Dominic>our case.

38
00:02:21.169 --> 00:02:26.029
<v Liz McGinn>OK, so it's both the motor and the thing
that makes the motor go, or the, you know.

39
00:02:27.100 --> 00:02:27.339
<v Liz McGinn>Yeah, it tells you what

40
00:02:28.619 --> 00:02:29.710
<v Dominic>you could call it like that, yeah,

41
00:02:30.259 --> 00:02:32.520
<v Liz McGinn>OK, at least that's what makes sense in my
brain.

42
00:02:32.619 --> 00:02:38.899
<v Liz McGinn>So, um, why is usability such a critical
focus for Siemens drive solutions?

43
00:02:40.589 --> 00:02:46.960
<v Dominic>Yeah, so when you look at the uh topic
usability, I have a great example in mind,

44
00:02:47.119 --> 00:02:52.919
<v Dominic>um, an awesome example for usability, and
that would be, for example, chat GPT.

45
00:02:53.559 --> 00:03:00.259
<v Dominic>So it's, it's a quite, uh, I would say
difficult technology, but it is packed in a

46
00:03:00.259 --> 00:03:02.080
<v Dominic>way that everybody can use it.

47
00:03:02.119 --> 00:03:07.479
<v Dominic>It is absolutely easy to use because you
do the most natural thing in the world.

48
00:03:07.559 --> 00:03:14.050
<v Dominic>You talk to the Um, uh, to your, uh,
chatbot or whatever you

49
00:03:14.789 --> 00:03:15.270
<v Dominic>are using.

50
00:03:15.389 --> 00:03:16.770
<v Dominic>So it's, it's pretty easy.

51
00:03:17.509 --> 00:03:23.509
<v Dominic>And when it comes to drive technology, um,
of course, there are not that many

52
00:03:23.509 --> 00:03:26.929
<v Dominic>experts in this, um, field of technology.

53
00:03:27.309 --> 00:03:33.039
<v Dominic>And, uh, it is very important that you
bring, um, the knowledge and bring all the

54
00:03:33.039 --> 00:03:38.389
<v Dominic>benefits that, um, knowledge about this
technology can have to the people, to the

55
00:03:38.389 --> 00:03:43.389
<v Dominic>people that normally do other things like
a maintenance manager who's caring about

56
00:03:43.389 --> 00:03:46.169
<v Dominic>the, um, uptime of a machine.

57
00:03:46.839 --> 00:03:48.889
<v Dominic>Um, he doesn't want to be a drive expert.

58
00:03:49.009 --> 00:03:53.250
<v Dominic>He wants to be an expert in maintenance,
and he don't want to get too deep into it.

59
00:03:53.330 --> 00:03:55.600
<v Dominic>He wants to have a system that he can use
easily.

60
00:03:56.210 --> 00:04:02.850
<v Dominic>So in this regard, our target group are
just the normal people in a, in a

61
00:04:02.850 --> 00:04:04.899
<v Dominic>factory that want to keep it up and
running.

62
00:04:05.410 --> 00:04:07.710
<v Dominic>And furthermore, there is another aspect.

63
00:04:08.929 --> 00:04:14.199
<v Dominic>Also, when you look at the demographic
changes, so experts and well-experienced

64
00:04:14.199 --> 00:04:20.540
<v Dominic>persons um are getting less and less
because our, um, people get older and older

65
00:04:20.540 --> 00:04:26.279
<v Dominic>and in these, these cases also, it is very
important that you have easy to use

66
00:04:26.279 --> 00:04:32.190
<v Dominic>solutions for all the younger people, all
the unexperienced people also to um have

67
00:04:32.190 --> 00:04:36.589
<v Dominic>the um benefits of this, all these, all
this knowledge.

68
00:04:37.010 --> 00:04:39.029
<v Dominic>And put in a technical solution.

69
00:04:40.160 --> 00:04:45.519
<v Liz McGinn>That makes a lot of sense from the, you
know, demographic changes to sometimes like

70
00:04:45.519 --> 00:04:49.119
<v Liz McGinn>old technology can just prove extra
difficult and you have to jump through many

71
00:04:49.119 --> 00:04:50.040
<v Liz McGinn>hoops to make it work.

72
00:04:50.119 --> 00:04:53.640
<v Liz McGinn>I remember like old video games where you
had to like blow on the cartridges to get

73
00:04:53.640 --> 00:04:57.679
<v Liz McGinn>the dust out before it even started and I
can't even imagine people trying to use

74
00:04:57.679 --> 00:04:58.239
<v Liz McGinn>that these days.

75
00:04:58.320 --> 00:05:04.070
<v Liz McGinn>So I can definitely see updating it to
make it easier to use, not only from the new

76
00:05:04.070 --> 00:05:09.200
<v Liz McGinn>people perspective, but also it's annoying
to have to keep, you know, Wiggle it just

77
00:05:09.200 --> 00:05:12.100
<v Liz McGinn>a certain way to make it work or however
you have to do it.

78
00:05:13.779 --> 00:05:14.190
<v Liz McGinn>Awesome.

79
00:05:14.269 --> 00:05:16.839
<v Liz McGinn>So what makes Siemens so usable?

80
00:05:16.910 --> 00:05:21.790
<v Liz McGinn>Like how, how are we, are we chatbotting
in that chat GBT function, or is it

81
00:05:21.790 --> 00:05:23.489
<v Liz McGinn>something, um, more simple?

82
00:05:24.690 --> 00:05:25.049
<v Dominic>Yeah, sure.

83
00:05:25.160 --> 00:05:31.209
<v Dominic>Uh, also chatbots are, um, often used in,
in our solutions, um, especially when you

84
00:05:31.209 --> 00:05:36.209
<v Dominic>look at the, um, Sensei predictive
maintenance solution, a chatbot is navigating and

85
00:05:36.209 --> 00:05:37.709
<v Dominic>helping you in any cases.

86
00:05:38.089 --> 00:05:43.329
<v Dominic>Um, but not only chatbots are important,
also the usability of the software itself.

87
00:05:43.410 --> 00:05:48.109
<v Dominic>So when you're using an analytic software,
um, not everything is done by a chat

88
00:05:48.109 --> 00:05:48.760
<v Dominic>chatbot.

89
00:05:48.890 --> 00:05:51.630
<v Dominic>Also, um, the, the commissioning and so
on.

90
00:05:52.850 --> 00:05:58.089
<v Dominic>has to be done by someone and the more
easy it is, the better it is.

91
00:05:58.649 --> 00:06:03.529
<v Dominic>And as I already told you, we have quite
some experience in drive technology, so we

92
00:06:03.529 --> 00:06:09.690
<v Dominic>have decades of experience and we want to
use this experience and provide it to a

93
00:06:09.690 --> 00:06:16.089
<v Dominic>customer and whoever, whoever is using our
solutions in the easiest way.

94
00:06:16.209 --> 00:06:21.149
<v Dominic>So the first point is we know our devices,
so we know how to preconfigure.

95
00:06:22.269 --> 00:06:29.269
<v Dominic>solutions, we know how to avoid complex
setups and also we know what kind

96
00:06:29.269 --> 00:06:34.859
<v Dominic>of data is within our drives, our
equipment, and

97
00:06:36.059 --> 00:06:42.600
<v Dominic>Wherever we can use this data even to
avoid additional sensors, so to make it

98
00:06:43.029 --> 00:06:44.910
<v Dominic>as easy to implement as it gets.

99
00:06:46.950 --> 00:06:51.640
<v Liz McGinn>Is the Siemens solution, do you need an
like a Siemens expert to implement these

100
00:06:51.640 --> 00:06:54.619
<v Liz McGinn>drives, or can um customers use them on
their own?

101
00:06:56.200 --> 00:06:58.559
<v Dominic>So our goal is that everybody can use it.

102
00:06:58.799 --> 00:07:05.239
<v Dominic>So when you want to analyze the drive
data, um, it should be as easy as possible and

103
00:07:05.239 --> 00:07:09.179
<v Dominic>of course, um, usable for anybody, for
everybody.

104
00:07:09.799 --> 00:07:15.970
<v Dominic>So, um, Yeah, you would have to have a
cut, so I forgot your question a little bit.

105
00:07:16.820 --> 00:07:17.179
<v Liz McGinn>You're good.

106
00:07:17.260 --> 00:07:21.339
<v Liz McGinn>I was just um kind of implement like uh
focusing kind of on this like usable outside

107
00:07:21.339 --> 00:07:27.200
<v Liz McGinn>the box, like, do you need a Siemens
expert to um implement these, these drives?

108
00:07:28.799 --> 00:07:31.980
<v Dominic>Um No, you don't need an expert.

109
00:07:32.649 --> 00:07:36.299
<v Dominic>The solutions are designed that they are
easy to use.

110
00:07:36.420 --> 00:07:43.380
<v Dominic>For example, we made for the commissioning
of the solutions a video, and this

111
00:07:43.380 --> 00:07:45.440
<v Dominic>video takes 15 minutes.

112
00:07:45.779 --> 00:07:49.640
<v Dominic>So then the complete solution is set up
and running.

113
00:07:50.100 --> 00:07:54.700
<v Dominic>Of course, in your first try, you will
need some more time because you will have to

114
00:07:54.700 --> 00:07:56.540
<v Dominic>search for some buttons or something like
that.

115
00:07:56.980 --> 00:08:01.940
<v Dominic>But when you have looked at this video and
you take it as a guide, I'm pretty sure

116
00:08:01.940 --> 00:08:06.459
<v Dominic>you can, um, do the commissioning on your
own within a very short time.

117
00:08:08.040 --> 00:08:11.230
<v Liz McGinn>That's awesome that there's a video in the
background because I know a lot of people

118
00:08:11.230 --> 00:08:12.079
<v Liz McGinn>use videos to do things.

119
00:08:12.119 --> 00:08:16.320
<v Liz McGinn>I know my dad, um, he fixes cars and he
has to look up every time where to find my

120
00:08:16.320 --> 00:08:17.920
<v Liz McGinn>oil filter or whatever on my car.

121
00:08:18.019 --> 00:08:20.980
<v Liz McGinn>So, um, it's great that there's a video
that you can just follow along.

122
00:08:22.230 --> 00:08:27.679
<v Dominic>Yeah, I think that's that's the new way we
have to think things and to also enable

123
00:08:27.679 --> 00:08:28.980
<v Dominic>trainings for anybody.

124
00:08:29.480 --> 00:08:34.520
<v Dominic>Everybody is using YouTube for when he
wants to fix something, when he wants to get

125
00:08:34.520 --> 00:08:40.159
<v Dominic>knowledge about something, and of course
also in industries we should use this

126
00:08:40.159 --> 00:08:47.039
<v Dominic>medium because it can bring very much
information into

127
00:08:47.039 --> 00:08:48.679
<v Dominic>a very attractive.

128
00:08:49.229 --> 00:08:55.710
<v Dominic>A way of showing it and in a very compact
way of showing things and you, yeah, just

129
00:08:55.710 --> 00:09:00.030
<v Dominic>bring it on much faster than if you would
only read a manual.

130
00:09:00.549 --> 00:09:03.510
<v Liz McGinn>Yeah, and there's a visual aspect of it
that makes it easier, so you can say the

131
00:09:03.510 --> 00:09:10.429
<v Liz McGinn>button here versus trying to figure out a
manual of the images and be like this

132
00:09:10.429 --> 00:09:12.030
<v Liz McGinn>isn't even, I can't even tell.

133
00:09:12.109 --> 00:09:13.799
<v Liz McGinn>It's like building furniture from IKEA.

134
00:09:13.830 --> 00:09:15.289
<v Liz McGinn>I'm like I have no idea what's going on.

135
00:09:18.020 --> 00:09:23.489
<v Liz McGinn>Yeah Awesome, I know you mentioned, um, a
lot of the experience of Siemens and

136
00:09:23.489 --> 00:09:24.489
<v Liz McGinn>knowing the drives.

137
00:09:24.690 --> 00:09:26.650
<v Liz McGinn>How, how long have we actually been doing
that?

138
00:09:26.719 --> 00:09:27.309
<v Liz McGinn>Do you know?

139
00:09:29.960 --> 00:09:35.460
<v Dominic>Um, So it started with analog drives, I
think in the 80s.

140
00:09:35.510 --> 00:09:39.169
<v Dominic>I'm, I'm not really sure, so I would have
to look up on my own.

141
00:09:39.909 --> 00:09:46.169
<v Dominic>Um my, my first boss I had at Siemens, who
was one of the first guys

142
00:09:47.229 --> 00:09:52.830
<v Dominic>actually dealing with this analog drives,
having to play around with resistors and

143
00:09:52.830 --> 00:09:57.789
<v Dominic>so on to bring speed controls in, in, in
an optimized way.

144
00:09:58.229 --> 00:09:59.890
<v Dominic>So I'm, I'm pretty sure.

145
00:10:01.640 --> 00:10:02.940
<v Dominic>40, 50 years.

146
00:10:03.400 --> 00:10:07.200
<v Liz McGinn>Yeah, so basically the idea is we've been
doing it pretty much as long as there's

147
00:10:07.200 --> 00:10:08.780
<v Liz McGinn>been some type of drives.

148
00:10:09.869 --> 00:10:12.630
<v Liz McGinn>In existence kind of does that sound about

149
00:10:12.630 --> 00:10:13.049
<v Dominic>right?

150
00:10:13.150 --> 00:10:16.289
<v Dominic>Much longer because we have, we have
different generations, of course.

151
00:10:16.830 --> 00:10:23.059
<v Dominic>So starting with the, with the analog
drives and then we, we went into the

152
00:10:23.059 --> 00:10:28.070
<v Dominic>generation of digital drives and and um
starting with SIMmadune Simo Vat

153
00:10:30.309 --> 00:10:36.059
<v Dominic>going over to master drive, micromaster,
and then the newest generation, the

154
00:10:36.059 --> 00:10:38.849
<v Dominic>cinemics and also in the cinemics we are
already.

155
00:10:39.280 --> 00:10:41.450
<v Dominic>Uh, not in the first generation anymore.

156
00:10:41.570 --> 00:10:47.010
<v Dominic>So, of course, this is also an evolving
topic, but being at Siemens, um, you have

157
00:10:47.010 --> 00:10:52.729
<v Dominic>always these, these, uh, guys working with
the old equipment and guys with the new

158
00:10:52.729 --> 00:10:57.789
<v Dominic>equipment, and we bring them together to,
um, exchange the, the knowledge there.

159
00:10:57.929 --> 00:11:03.409
<v Dominic>And of course, this brings us the decades
of knowledge that we can put into our

160
00:11:03.409 --> 00:11:03.809
<v Dominic>solutions.

161
00:11:04.609 --> 00:11:11.289
<v Dominic>Like I said, my boss, my former boss was
uh in the 80s, a drive engineer, so he

162
00:11:11.289 --> 00:11:15.270
<v Dominic>could also give some, some experience and
some knowledge to me.

163
00:11:16.349 --> 00:11:20.669
<v Liz McGinn>It's good to know that we're not, um, kind
of, I mean, obviously the goal is to make

164
00:11:20.669 --> 00:11:25.229
<v Liz McGinn>older equipment obsolete, but we still
have experts that can help on those older

165
00:11:25.229 --> 00:11:26.770
<v Liz McGinn>equipments that are still running.

166
00:11:27.270 --> 00:11:27.570
<v Dominic>Yeah.

167
00:11:28.820 --> 00:11:29.090
<v Dominic>Exactly.

168
00:11:29.609 --> 00:11:34.010
<v Dominic>You need also these experts, for example,
when you want to run retrofits afterwards

169
00:11:34.570 --> 00:11:39.690
<v Dominic>because someone has to know how the old
machine was working and how you can switch

170
00:11:39.690 --> 00:11:41.010
<v Dominic>it to a new type of machine.

171
00:11:41.919 --> 00:11:42.849
<v Liz McGinn>That's a really good point.

172
00:11:42.919 --> 00:11:44.020
<v Liz McGinn>I didn't even think of that.

173
00:11:46.059 --> 00:11:50.289
<v Liz McGinn>Can you provide a, a kind of a real world
example of how, how we're using this

174
00:11:50.289 --> 00:11:50.500
<v Liz McGinn>technology?

175
00:11:52.960 --> 00:11:58.570
<v Dominic>Um, yes, so we had recently a very

176
00:12:01.349 --> 00:12:04.179
<v Dominic>Uh, yeah, I will start once again.

177
00:12:04.469 --> 00:12:04.960
<v Liz McGinn>You're good.

178
00:12:05.609 --> 00:12:06.000
<v Liz McGinn>Yeah,

179
00:12:06.900 --> 00:12:13.780
<v Dominic>Um, we recently had a very happy customer
that came to us and said he is

180
00:12:13.780 --> 00:12:19.940
<v Dominic>using our solution and has now made the
jump into predictive maintenance.

181
00:12:19.979 --> 00:12:23.599
<v Dominic>It's a company in located in Austria.

182
00:12:24.200 --> 00:12:30.679
<v Dominic>Um, and this is the biggest spice
manufacturer of Austria, and they are

183
00:12:30.679 --> 00:12:36.229
<v Dominic>using our solutions to have a look at
their conveyor belts.

184
00:12:36.239 --> 00:12:41.080
<v Dominic>They had the problem in the past that
these conveyor belts got dirty from time to

185
00:12:41.080 --> 00:12:48.039
<v Dominic>time, and they had to stop production,
tidy it up, make it clean

186
00:12:48.039 --> 00:12:48.359
<v Dominic>again.

187
00:12:48.849 --> 00:12:51.239
<v Dominic>And then proceed with production.

188
00:12:51.380 --> 00:12:57.909
<v Dominic>Now, nowadays they can observe the
gratitude or the grade of um

189
00:12:58.570 --> 00:13:02.390
<v Dominic>Of the dirt in the conveyor belts.

190
00:13:03.020 --> 00:13:07.859
<v Dominic>And so that they, that they can react
before this conveyor belt gets too dirty.

191
00:13:08.059 --> 00:13:14.880
<v Dominic>So that's predictive maintenance in the
clearest way how you can see it.

192
00:13:14.979 --> 00:13:18.859
<v Dominic>So prevent a problem before it occurs.

193
00:13:19.739 --> 00:13:23.700
<v Liz McGinn>Yeah, is that using Sensi predictive
maintenance or another Siemens

194
00:13:23.700 --> 00:13:24.039
<v Dominic>technology?

195
00:13:24.489 --> 00:13:29.369
<v Dominic>Um, no, actually they are using predictive
service analyzer, so that's the product

196
00:13:29.369 --> 00:13:33.309
<v Dominic>where I'm responsible for as a product
manager.

197
00:13:33.909 --> 00:13:34.169
<v Liz McGinn>OK.

198
00:13:34.239 --> 00:13:39.440
<v Liz McGinn>And can you explain a little bit into what
is PSA or predictive Service analyzer?

199
00:13:39.609 --> 00:13:39.770
<v Liz McGinn>Yeah,

200
00:13:39.929 --> 00:13:45.390
<v Dominic>predictive Service Analyzer is an app for
the industrial edge ecosystem, so it is an

201
00:13:45.390 --> 00:13:49.260
<v Dominic>app that is running on premise directly in
your factory.

202
00:13:50.119 --> 00:13:56.859
<v Dominic>And, um, yeah, it consists of these
benefits that I, uh, already told, um,

203
00:13:57.150 --> 00:14:02.200
<v Dominic>at the beginning of our conversation, um,
that it is a very easy to use solution,

204
00:14:02.440 --> 00:14:09.440
<v Dominic>um, very easy to, to, um, commission, and
it is especially designed for drive

205
00:14:09.440 --> 00:14:09.760
<v Dominic>systems.

206
00:14:09.880 --> 00:14:16.500
<v Dominic>So that's also, um, One difference
compared to sensei

207
00:14:16.500 --> 00:14:17.599
<v Dominic>predictive maintenance.

208
00:14:18.289 --> 00:14:23.609
<v Dominic>Um, in Sensei, you have the holistic
overview about your whole um factory and you

209
00:14:23.609 --> 00:14:26.590
<v Dominic>can attach a lot of different
applications.

210
00:14:26.969 --> 00:14:31.489
<v Dominic>In our case, we're really looking very
deep into drive systems.

211
00:14:31.609 --> 00:14:37.130
<v Dominic>So that's our field of expertise where we
have developed the solution and to give

212
00:14:37.130 --> 00:14:40.260
<v Dominic>you the deepest insight in your drive
system.

213
00:14:40.369 --> 00:14:45.080
<v Dominic>Of course, based on our knowledge that we
have gained the last decades.

214
00:14:46.090 --> 00:14:51.049
<v Liz McGinn>Oh, that's interesting that there's an
expertise versus an overarching thing.

215
00:14:51.090 --> 00:14:55.210
<v Liz McGinn>I know Sensai is overarching, but it's
interesting to learn the different solutions

216
00:14:55.210 --> 00:14:57.929
<v Liz McGinn>that are a little bit more specialized as
humans.

217
00:14:58.489 --> 00:15:03.289
<v Dominic>Exactly, and they come together perfectly,
so they fit together perfectly because

218
00:15:03.289 --> 00:15:06.619
<v Dominic>when you want to have the holistic
overview, Sensai is the perfect fit.

219
00:15:06.979 --> 00:15:11.929
<v Dominic>And when you want to go very into detail
into a certain drive because this drive is

220
00:15:11.929 --> 00:15:18.489
<v Dominic>crucial for for your production or Um, a
downtime means very high costs.

221
00:15:18.929 --> 00:15:24.989
<v Dominic>Then you can have the specialized solution
on top and um

222
00:15:25.570 --> 00:15:28.039
<v Dominic>have a deeper look inside it.

223
00:15:29.630 --> 00:15:33.599
<v Dominic>Even extending the functionality of Sensi
in this regards.

224
00:15:34.270 --> 00:15:35.250
<v Liz McGinn>Yeah, that's awesome to know.

225
00:15:35.299 --> 00:15:39.130
<v Liz McGinn>It's just another way of getting
information for, for maintenance teams to make sure

226
00:15:39.130 --> 00:15:42.590
<v Liz McGinn>that everything's running smoothly because
the last thing we want is anything to be

227
00:15:42.590 --> 00:15:43.130
<v Liz McGinn>shut down.

228
00:15:44.130 --> 00:15:44.469
<v Liz McGinn>Yeah.

229
00:15:46.219 --> 00:15:46.500
<v Liz McGinn>Awesome.

230
00:15:46.549 --> 00:15:48.190
<v Liz McGinn>So how does usability kind of go into
that?

231
00:15:48.229 --> 00:15:49.599
<v Liz McGinn>You mentioned that it's easy to use.

232
00:15:49.710 --> 00:15:55.510
<v Liz McGinn>Is it, I know like Sensei prides itself on
not needing data analytic like analytics

233
00:15:55.510 --> 00:15:59.539
<v Liz McGinn>or, you know, obviously it's data
analytics, but you don't need to be a data analyst

234
00:15:59.539 --> 00:16:00.229
<v Liz McGinn>to use it.

235
00:16:00.429 --> 00:16:03.909
<v Liz McGinn>Is that the same with a predictive service
analyzer or um

236
00:16:03.909 --> 00:16:04.820
<v Dominic>exactly, exactly.

237
00:16:04.909 --> 00:16:07.130
<v Dominic>So that's the same goal we had there.

238
00:16:07.619 --> 00:16:11.830
<v Dominic>Um, we wanted to that everybody can use
it.

239
00:16:11.950 --> 00:16:13.469
<v Dominic>You don't have to be a drive expert.

240
00:16:13.549 --> 00:16:20.349
<v Dominic>You don't have to be an analytics or AI
expert because we have set so

241
00:16:20.349 --> 00:16:26.270
<v Dominic>much preconfiguration, easy setup that you
don't need that knowledge.

242
00:16:26.390 --> 00:16:28.669
<v Dominic>We put all that knowledge already inside
it.

243
00:16:29.659 --> 00:16:32.559
<v Liz McGinn>Is uh, PSA using AI?

244
00:16:33.919 --> 00:16:40.400
<v Dominic>Yeah, it's, it's to 95% using AI and to 5%
real-time

245
00:16:40.400 --> 00:16:41.369
<v Dominic>simulation.

246
00:16:41.960 --> 00:16:44.320
<v Liz McGinn>OK, I didn't realize that it was using AI
as well.

247
00:16:44.400 --> 00:16:46.500
<v Liz McGinn>Can you explain like what are they using
AI for?

248
00:16:48.799 --> 00:16:50.580
<v Dominic>mainly for anomaly detection.

249
00:16:50.859 --> 00:16:57.460
<v Dominic>So we are looking especially at all parts
of the drivetrain beginning from the grid

250
00:16:57.460 --> 00:16:59.700
<v Dominic>where the frequency converter is attached
to.

251
00:16:59.780 --> 00:17:06.500
<v Dominic>So we have also observation, observation
AI that is looking at the grid grid

252
00:17:06.500 --> 00:17:07.239
<v Dominic>quality.

253
00:17:07.819 --> 00:17:11.920
<v Dominic>We have AI looking at the status of the
drive itself.

254
00:17:12.020 --> 00:17:13.560
<v Dominic>So for the frequency converter.

255
00:17:14.390 --> 00:17:21.189
<v Dominic>We have also artificial intelligence to
look at the motor, especially, and also one

256
00:17:21.189 --> 00:17:27.130
<v Dominic>very powerful functionality which is also
bringing the benefit to the spice

257
00:17:27.130 --> 00:17:32.609
<v Dominic>manufacturer is an artificial intelligence
to observe the whole application.

258
00:17:32.739 --> 00:17:39.500
<v Dominic>So to find out if there are anomalies in
the behavior of the machine that could

259
00:17:39.500 --> 00:17:43.579
<v Dominic>lead to a standstill or to a failure and
to find it.

260
00:17:43.930 --> 00:17:47.810
<v Dominic>In a very early stage to have the chance
to react to it.

261
00:17:48.969 --> 00:17:53.300
<v Liz McGinn>OK, and what would, I guess, for an
example, what would that kind of anomaly look

262
00:17:53.300 --> 00:17:56.780
<v Liz McGinn>like in in the spice, um, like conveyor
belts?

263
00:17:56.859 --> 00:18:00.560
<v Liz McGinn>Would that be like a spice jar tipping
over or something, or is it something?

264
00:18:01.209 --> 00:18:01.949
<v Liz McGinn>Something else.

265
00:18:02.750 --> 00:18:08.959
<v Dominic>Um, so the AI is working in a way that it
learns the normal behavior of the machine.

266
00:18:09.119 --> 00:18:14.020
<v Dominic>So you're just in a in a first stage
you're just recording data from this machine

267
00:18:14.520 --> 00:18:17.989
<v Dominic>where the machine was running fine, where
everything was good, where you don't see

268
00:18:17.989 --> 00:18:23.060
<v Dominic>any problems, and when you say, OK, when
it stays in this status or in this.

269
00:18:23.729 --> 00:18:28.660
<v Dominic>Um, in these boundaries, then everything
is fine.

270
00:18:28.780 --> 00:18:33.040
<v Dominic>Then my day as a production manager or a
maintenance manager would be just perfect.

271
00:18:33.910 --> 00:18:39.219
<v Dominic>And you take this data, give it to the AI,
and the AI is learning what is the normal

272
00:18:39.219 --> 00:18:40.079
<v Dominic>behavior of the machine.

273
00:18:40.189 --> 00:18:45.949
<v Dominic>So every working point, every recipe,
every single scenario that this machine is

274
00:18:45.949 --> 00:18:48.810
<v Dominic>seeing is then learned by the artificial
intelligence.

275
00:18:49.390 --> 00:18:56.150
<v Dominic>And in future, the AI gives you then the
hint if there are deviations to the normal

276
00:18:56.150 --> 00:18:56.750
<v Dominic>behavior.

277
00:18:57.310 --> 00:19:03.750
<v Dominic>So in the spice manufacturing, For
example, when the conveyor belt gets clogged or

278
00:19:03.750 --> 00:19:09.989
<v Dominic>something like that, um, you could see it
in different values of the drive, for

279
00:19:09.989 --> 00:19:15.989
<v Dominic>example, the torque that drive is needing
or the speed points that it is driving.

280
00:19:16.109 --> 00:19:21.910
<v Dominic>So with these data points you can then see
if there is something animal in the

281
00:19:21.910 --> 00:19:22.369
<v Dominic>system.

282
00:19:23.310 --> 00:19:25.109
<v Dominic>And then the story goes further.

283
00:19:25.270 --> 00:19:30.130
<v Dominic>So when you know, OK, there is an anomaly
in my system, I have to find out what,

284
00:19:30.219 --> 00:19:32.229
<v Dominic>what is causing that.

285
00:19:32.930 --> 00:19:35.780
<v Dominic>Um, you have something what we call an
explainer.

286
00:19:36.010 --> 00:19:41.469
<v Dominic>It gives you an indicator which value is
causing this anomaly.

287
00:19:41.930 --> 00:19:45.770
<v Dominic>So is it an animal torque or an animal
speed value?

288
00:19:46.479 --> 00:19:50.739
<v Dominic>And with this knowledge you can go and
find out what the machine.

289
00:19:53.729 --> 00:19:58.300
<v Dominic>What caused this behavior in the machine
and the great thing is afterwards when you

290
00:19:58.300 --> 00:20:03.020
<v Dominic>have gained this knowledge, what was the
problem, you can also give this knowledge

291
00:20:03.020 --> 00:20:08.739
<v Dominic>to the artificial intelligence once again
and the next time the same scenario

292
00:20:08.739 --> 00:20:11.640
<v Dominic>appears, the artificial intelligence will
give you a hint.

293
00:20:11.939 --> 00:20:15.699
<v Dominic>Hey, please have in mind in the past I've
seen something like that.

294
00:20:16.099 --> 00:20:18.219
<v Dominic>Please check this as a first measure.

295
00:20:18.949 --> 00:20:21.859
<v Dominic>And also you can put some some more
knowledge into it.

296
00:20:21.949 --> 00:20:24.930
<v Dominic>So for example, how you got rid of this
situation.

297
00:20:25.589 --> 00:20:31.910
<v Dominic>So maybe you have to go there just by
wiping with a with a cloth and have it clean

298
00:20:31.910 --> 00:20:32.109
<v Dominic>again.

299
00:20:32.819 --> 00:20:35.989
<v Dominic>Or sometimes it's even a little bit more
complicated.

300
00:20:36.069 --> 00:20:40.810
<v Dominic>Then you can also put in a step by step
manual how to get rid of this situation.

301
00:20:41.150 --> 00:20:45.410
<v Dominic>And here we come again to this topic of
knowledge sharing.

302
00:20:45.760 --> 00:20:51.989
<v Dominic>So when you have some very experienced
persons in your maintenance team and some

303
00:20:51.989 --> 00:20:56.880
<v Dominic>newbies, also these very experienced
persons can give their knowledge over this

304
00:20:56.880 --> 00:21:02.199
<v Dominic>database to the new bees that they are
also capable of doing the job.

305
00:21:03.619 --> 00:21:06.910
<v Liz McGinn>Yeah, that's awesome that you have, uh,
kind of that built-in knowledge and then

306
00:21:06.910 --> 00:21:09.270
<v Liz McGinn>being able to share that for future,
future issues.

307
00:21:09.310 --> 00:21:11.630
<v Liz McGinn>I know that's really important, um.

308
00:21:12.270 --> 00:21:16.290
<v Liz McGinn>And obviously avoids a lot more shutdowns
and stuff if you have an idea.

309
00:21:16.900 --> 00:21:18.750
<v Liz McGinn>And I know you kind of talked about costs
there.

310
00:21:18.989 --> 00:21:24.660
<v Liz McGinn>How does um having this kind of
implemented in a usability kind of format help the

311
00:21:24.660 --> 00:21:27.089
<v Liz McGinn>ROI of uh manufacturers?

312
00:21:28.630 --> 00:21:35.319
<v Dominic>So, often AI driven solutions have the
problem that they have

313
00:21:35.319 --> 00:21:42.239
<v Dominic>a quite long, um, commissioning phase, a
quite intense and costly phase where

314
00:21:42.239 --> 00:21:46.800
<v Dominic>you have to implement everything, we have
to set up everything, um, where you have

315
00:21:46.800 --> 00:21:53.040
<v Dominic>to train your models and to retrain the
models and, uh, go on and on until the

316
00:21:53.040 --> 00:21:54.040
<v Dominic>solution is up and running.

317
00:21:54.160 --> 00:21:56.420
<v Dominic>So this causes a lot of time.

318
00:21:56.689 --> 00:22:00.410
<v Dominic>A lot of efforts and of course costs in
these ways.

319
00:22:01.369 --> 00:22:06.329
<v Dominic>And when you have a solution that is easy
to implement and is set up in 15 minutes

320
00:22:06.329 --> 00:22:12.760
<v Dominic>by some experienced people, um, and even
by some unexperienced people in 1 hour, um,

321
00:22:13.010 --> 00:22:18.849
<v Dominic>this is of course a very big factor when
it comes to an ROI at the end.

322
00:22:19.369 --> 00:22:26.329
<v Dominic>So I had a customer, um, that said, OK, if
we even can find 2 failures a

323
00:22:26.329 --> 00:22:29.589
<v Dominic>year, this solution has already paid off.

324
00:22:30.910 --> 00:22:37.189
<v Dominic>When you see it in comparison with what um
unexpected downtimes cause, um, as, as

325
00:22:37.189 --> 00:22:44.069
<v Dominic>cost, and when you then see a very um easy
to implement and, and, uh, cost

326
00:22:44.069 --> 00:22:50.819
<v Dominic>attractive solution, uh compared to it,
then often, uh, the decision is quite easy

327
00:22:50.819 --> 00:22:52.750
<v Dominic>to uh implement it.

328
00:22:53.829 --> 00:22:58.239
<v Liz McGinn>Yeah, how long does it take to train the
AI model with these solutions?

329
00:22:58.280 --> 00:23:02.719
<v Liz McGinn>I know in like uh getting it installed is
easy, but how long does the actual process

330
00:23:02.719 --> 00:23:04.040
<v Liz McGinn>take for it to learn your equipment?

331
00:23:05.150 --> 00:23:07.439
<v Dominic>This is depending on how complex your data
is.

332
00:23:07.560 --> 00:23:13.239
<v Dominic>So when you have a machine that is
producing product A one day, the next product the

333
00:23:13.239 --> 00:23:19.400
<v Dominic>next day, and the third product the 3rd
day, then maybe you need 6 days or 9 days so

334
00:23:19.400 --> 00:23:25.599
<v Dominic>that you have every product some data
points so that the artificial intelligence can

335
00:23:25.599 --> 00:23:26.160
<v Dominic>learn from it.

336
00:23:26.989 --> 00:23:33.959
<v Dominic>Of course, if it is an, an easier uh
application that only knows, um, let's say

337
00:23:33.959 --> 00:23:40.880
<v Dominic>daytime and nighttime uh production, um,
then the period of time that you need for

338
00:23:40.880 --> 00:23:42.209
<v Dominic>training is, is shorter.

339
00:23:42.719 --> 00:23:49.719
<v Dominic>But in fact, um, what you have to do at
the end is uh exactly the same, it needs

340
00:23:49.719 --> 00:23:53.030
<v Dominic>the same time, it is exactly the same
work, um.

341
00:23:53.660 --> 00:23:57.739
<v Dominic>In this time where the training data is
recorded, you have to do nothing.

342
00:23:57.859 --> 00:24:03.979
<v Dominic>You just have a listener there, so the AI
is just listening what data is coming in

343
00:24:03.979 --> 00:24:04.260
<v Dominic>there.

344
00:24:05.089 --> 00:24:10.520
<v Dominic>After the listening time, the recording
time is over, you have to go there as a

345
00:24:10.520 --> 00:24:16.290
<v Dominic>user, set the time intervals where your
production was running fine and where

346
00:24:16.290 --> 00:24:17.189
<v Dominic>everything was smooth.

347
00:24:17.869 --> 00:24:20.719
<v Dominic>And afterwards push start training button.

348
00:24:21.140 --> 00:24:22.109
<v Dominic>That's all you have to do.

349
00:24:22.189 --> 00:24:25.349
<v Dominic>You don't have to sit next to it for 2
weeks.

350
00:24:25.430 --> 00:24:31.390
<v Dominic>You just install it, leave it there for 2
weeks, come back, give some time intervals

351
00:24:31.390 --> 00:24:34.589
<v Dominic>where production was, was fine, and push
start training.

352
00:24:34.829 --> 00:24:36.550
<v Dominic>That was everything you have to do.

353
00:24:37.489 --> 00:24:40.180
<v Liz McGinn>Oh, that sounds super simple, and it's
nice that you don't have to sit there and

354
00:24:40.180 --> 00:24:42.439
<v Liz McGinn>kind of babysit a new piece of equipment.

355
00:24:42.859 --> 00:24:43.219
<v Liz McGinn>Yeah.

356
00:24:44.569 --> 00:24:45.040
<v Liz McGinn>That's awesome.

357
00:24:45.089 --> 00:24:46.689
<v Liz McGinn>So how is it getting this data?

358
00:24:46.729 --> 00:24:49.069
<v Liz McGinn>I know it's obviously focused on the
drives.

359
00:24:49.329 --> 00:24:51.209
<v Liz McGinn>Is it, is the drive sending it directly?

360
00:24:51.290 --> 00:24:53.630
<v Liz McGinn>Are we using additional sensors?

361
00:24:54.560 --> 00:24:56.750
<v Liz McGinn>Um, to kind of gather that, or?

362
00:24:58.339 --> 00:25:03.400
<v Dominic>So wherever possible we want to avoid
additional sensors because it makes it more

363
00:25:03.400 --> 00:25:09.000
<v Dominic>complicated, it makes it more expensive,
and when you have a look at, for example

364
00:25:09.000 --> 00:25:10.280
<v Dominic>our dynamics drives.

365
00:25:11.680 --> 00:25:18.359
<v Dominic>There is a list, a parameters list, so
kind of all the values that the frequency

366
00:25:18.359 --> 00:25:24.560
<v Dominic>converter knows and records and
calculates, and these are hundreds,

367
00:25:24.959 --> 00:25:29.760
<v Dominic>hundreds of parameters giving you
information about what the drive is doing, what

368
00:25:29.760 --> 00:25:32.900
<v Dominic>the grid is doing, what the machine is
doing, what the motor is doing.

369
00:25:33.420 --> 00:25:40.130
<v Dominic>And the best thing you can do is to dig
out this treasure because

370
00:25:40.140 --> 00:25:46.979
<v Dominic>there are already a lot of measured data,
calculated data that you can use for, for

371
00:25:46.979 --> 00:25:49.380
<v Dominic>example, the sake of predictive
maintenance.

372
00:25:50.209 --> 00:25:51.979
<v Liz McGinn>Well, that's good to know that you don't
have to add a bunch of stuff.

373
00:25:52.020 --> 00:25:55.300
<v Liz McGinn>You already have kind of the data points
within the drives you're already

374
00:25:55.300 --> 00:25:55.910
<v Liz McGinn>collecting.

375
00:25:56.420 --> 00:25:56.780
<v Liz McGinn>Yeah.

376
00:25:57.920 --> 00:26:02.449
<v Liz McGinn>Awesome, so I know we talked a lot about
the spice industry, um, based on the one

377
00:26:02.449 --> 00:26:06.430
<v Liz McGinn>customer uh example you gave, what other
industries can really benefit from

378
00:26:06.640 --> 00:26:07.930
<v Liz McGinn>implementing these solutions?

379
00:26:09.650 --> 00:26:16.410
<v Dominic>So that's a tough question indeed because
my very simple answer would be all of the

380
00:26:16.410 --> 00:26:17.089
<v Dominic>industries.

381
00:26:17.609 --> 00:26:23.410
<v Dominic>So no matter in which industry you are, so
we have a lot of different customers

382
00:26:23.410 --> 00:26:29.569
<v Dominic>coming from different branches, for
example, cement industry, food and

383
00:26:29.569 --> 00:26:30.430
<v Dominic>beverage.

384
00:26:31.310 --> 00:26:37.630
<v Dominic>steel industry are completely different
from each other, but what makes what they

385
00:26:37.630 --> 00:26:40.599
<v Dominic>have in common is that they all use drive
systems.

386
00:26:41.069 --> 00:26:46.969
<v Dominic>They all have the need to have something
rotating or something being transported,

387
00:26:47.339 --> 00:26:54.270
<v Dominic>and mainly you could say everywhere where
you have a drive system that is crucial

388
00:26:54.270 --> 00:26:55.969
<v Dominic>for your production.

389
00:26:56.319 --> 00:27:02.420
<v Dominic>And is very expensive if you have a
breakdown or a downtime,

390
00:27:03.000 --> 00:27:05.510
<v Dominic>then our solutions come into play.

391
00:27:05.709 --> 00:27:10.060
<v Liz McGinn>What are some key takeaways for
manufacturers considering Siemens solutions?

392
00:27:12.140 --> 00:27:17.420
<v Dominic>So I would say when you invest in Siemens
you're not just buying a product, you're

393
00:27:17.420 --> 00:27:24.380
<v Dominic>really gaining access to the decades of
expertise that we have in our technology

394
00:27:24.380 --> 00:27:31.380
<v Dominic>and that give us the opportunity to make
digitalization easy, impactful, and also

395
00:27:31.380 --> 00:27:32.020
<v Dominic>scalable.

396
00:27:34.109 --> 00:27:34.560
<v Liz McGinn>That's awesome.

397
00:27:34.599 --> 00:27:36.069
<v Liz McGinn>It's not just a one-off.

398
00:27:36.119 --> 00:27:40.359
<v Liz McGinn>You have, you have a whole company, I
guess, behind you and people to support, which

399
00:27:40.359 --> 00:27:42.400
<v Liz McGinn>is nice, especially when implementing new
technology.

400
00:27:42.439 --> 00:27:47.800
<v Liz McGinn>I know it can be a challenge to, to get
those implemented and running and then also

401
00:27:47.800 --> 00:27:48.339
<v Liz McGinn>used.

402
00:27:49.310 --> 00:27:50.050
<v Dominic>Absolutely.

403
00:27:51.369 --> 00:27:53.219
<v Liz McGinn>Awesome, so we're kind of ending up here.

404
00:27:53.380 --> 00:27:57.479
<v Liz McGinn>Do you have any additional things that
people should know before we we sign off?

405
00:27:58.420 --> 00:28:00.630
<v Dominic>Mhm, I don't think so.

406
00:28:01.189 --> 00:28:01.920
<v Liz McGinn>Awesome.

407
00:28:02.380 --> 00:28:02.579
<v Liz McGinn>Perfect.

408
00:28:02.739 --> 00:28:04.579
<v Liz McGinn>Well, thank you so much for joining us
today.

409
00:28:04.660 --> 00:28:09.400
<v Liz McGinn>I appreciated, uh, all of your answers and
explaining it in a way that makes sense,

410
00:28:09.900 --> 00:28:13.060
<v Liz McGinn>um, at least to me, hopefully for everyone
else too.

411
00:28:14.260 --> 00:28:15.099
<v Dominic>Thank you.

412
00:28:15.750 --> 00:28:20.170
<v Liz McGinn>Please like and subscribe on all major
podcast channels and find out more about

413
00:28:20.609 --> 00:28:22.630
<v Liz McGinn>Sensi Predictive maintenance at
Siemens.com.
