WEBVTT
Language: en-US

1
00:00:02.559 --> 00:00:05.000
<v Speaker 1>Oh, there's, there's so much value that it
can add.

2
00:00:05.190 --> 00:00:08.560
<v Speaker 1>For example, you can make sure you're
prepared to have a spare parts inventory.

3
00:00:08.750 --> 00:00:13.279
<v Speaker 1>If you know 3 months in advance that a, a
part of your equipment is starting to

4
00:00:13.279 --> 00:00:17.709
<v Speaker 1>degrade, then you can plan to have its
replacement ready to go for when you perform

5
00:00:17.709 --> 00:00:18.459
<v Speaker 1>maintenance.

6
00:00:18.760 --> 00:00:22.440
<v Speaker 1>We have people that have eliminated
planned maintenance on the assets that they're

7
00:00:22.440 --> 00:00:26.879
<v Speaker 1>monitoring with Sensii, so they no longer
send people on a round to put hands on a

8
00:00:26.879 --> 00:00:28.079
<v Speaker 1>machine unnecessarily.

9
00:00:29.200 --> 00:00:34.400
<v Speaker 2>Welcome to the trend detection podcast
powered by Siemens, and now your host, Nel

10
00:00:34.400 --> 00:00:34.919
<v Speaker 2>Sullivan.

11
00:00:36.360 --> 00:00:40.459
<v Speaker 3>Hello, and welcome to the latest episode
of the trend section podcast.

12
00:00:40.840 --> 00:00:44.759
<v Speaker 3>Um, I'm really pleased to be joined by an
old favorite, old in the sense that you've

13
00:00:44.759 --> 00:00:48.799
<v Speaker 3>been on the podcast many times, I should
say, um, Natalie Kergan.

14
00:00:48.909 --> 00:00:49.919
<v Speaker 3>So welcome back, Natalie.

15
00:00:49.959 --> 00:00:51.529
<v Speaker 3>Thank you for coming back and recording.

16
00:00:52.959 --> 00:00:54.229
<v Speaker 3>That's a strange intro, isn't it?

17
00:00:54.279 --> 00:00:56.560
<v Speaker 3>But we'll roll with it, we'll roll with
it.

18
00:00:56.669 --> 00:00:57.180
<v Speaker 3>It's fine.

19
00:00:57.479 --> 00:01:00.520
<v Speaker 3>Now, uh, I mean, today, so we're welcoming
you back, and it was actually you.

20
00:01:00.682 --> 00:01:03.722
<v Speaker 3>Who approached me, which is always nice,
so it's not just me, um, coming up with

21
00:01:03.722 --> 00:01:08.402
<v Speaker 3>these topics, um, as I hear them, but it
was you who came to me, so, um, I guess

22
00:01:08.402 --> 00:01:11.712
<v Speaker 3>before we go into the topic, which, um,
we're talking about when predictor

23
00:01:11.712 --> 00:01:15.163
<v Speaker 3>maintenance is and isn't right for your
plant, which is a very important question

24
00:01:15.163 --> 00:01:15.322
<v Speaker 3>actually.

25
00:01:15.402 --> 00:01:18.042
<v Speaker 3>I'm surprised we haven't covered it, um,
in depth so far.

26
00:01:18.203 --> 00:01:21.553
<v Speaker 3>But I guess before we go into that, Natty,
it'd be great, um, maybe to remind people

27
00:01:21.553 --> 00:01:23.612
<v Speaker 3>of your role at Siemens and with the
Sensa,

28
00:01:24.913 --> 00:01:24.922
<v Speaker 1>um.

29
00:01:25.045 --> 00:01:31.125
<v Speaker 1>So I was actually part of Sensai
pre-Siemens and I worked in delivery, so I was

30
00:01:31.125 --> 00:01:36.945
<v Speaker 1>delivering Sensai directly to customers
and post integration with Siemens, I am now

31
00:01:37.445 --> 00:01:40.276
<v Speaker 1>the head of delivery for all of the
Americas.

32
00:01:40.596 --> 00:01:46.646
<v Speaker 1>So I, I train our regional colleagues to
deliver Sensai and I coordinate efforts and

33
00:01:46.646 --> 00:01:49.265
<v Speaker 1>I consult and I still work with some
customers, so.

34
00:01:49.739 --> 00:01:55.080
<v Speaker 1>I've got a lot of experience at this point
into what makes a good and a bad PDM

35
00:01:55.080 --> 00:01:55.540
<v Speaker 1>project.

36
00:01:56.220 --> 00:01:58.279
<v Speaker 3>Exactly, perfect for this discussion
today.

37
00:01:58.379 --> 00:02:01.500
<v Speaker 3>Um, but I'll, I mean, I'll put the
question back to you, like I said, because you,

38
00:02:01.620 --> 00:02:02.569
<v Speaker 3>you came to me with the topic.

39
00:02:02.610 --> 00:02:05.220
<v Speaker 3>Do you remember why, I'll say do you
remember because it was a little while back,

40
00:02:05.319 --> 00:02:09.770
<v Speaker 3>but do you remember why this topic sort of
came into your mind, um, and it's all

41
00:02:09.770 --> 00:02:11.119
<v Speaker 3>these projects you're involved in, right?

42
00:02:11.300 --> 00:02:12.639
<v Speaker 3>Something sprung from there.

43
00:02:13.160 --> 00:02:17.880
<v Speaker 1>I genuinely, I don't remember exactly why,
but it's something that we encounter all

44
00:02:17.880 --> 00:02:24.279
<v Speaker 1>the time, is that we end up with, with
deployments in plants where it's just not

45
00:02:24.279 --> 00:02:28.339
<v Speaker 1>necessarily the best case scenario for
starting with PDM.

46
00:02:29.050 --> 00:02:33.850
<v Speaker 1>Uh, and then, of course, my role in
delivery and in guiding people to deliver

47
00:02:34.050 --> 00:02:39.369
<v Speaker 1>whatever the customer thinks that they
should get out of the PDM project, we have to

48
00:02:39.369 --> 00:02:42.250
<v Speaker 1>deliver that regardless of whether or not
it actually makes sense.

49
00:02:42.690 --> 00:02:44.910
<v Speaker 1>So that's probably why I came to you.

50
00:02:46.789 --> 00:02:48.669
<v Speaker 3>He came to me to talk it out on the
podcast.

51
00:02:48.789 --> 00:02:50.449
<v Speaker 3>That's, that's fantastic.

52
00:02:51.070 --> 00:02:54.690
<v Speaker 3>But I guess, and I guess it's, it's a lot
of that driven because, you know, I'm in

53
00:02:54.690 --> 00:02:58.869
<v Speaker 3>the marketing side and I've seen sort of
the hype rise in predictive maintenance.

54
00:02:58.949 --> 00:02:59.979
<v Speaker 3>Like everyone's talking about it.

55
00:02:59.990 --> 00:03:01.270
<v Speaker 3>Everyone says they do it.

56
00:03:01.320 --> 00:03:03.389
<v Speaker 3>I guess that's driving a lot of this,
right?

57
00:03:03.509 --> 00:03:08.070
<v Speaker 3>Like we must do predictive maintenance no
matter whether we're ready or not, kind of

58
00:03:08.070 --> 00:03:08.190
<v Speaker 3>thing.

59
00:03:08.369 --> 00:03:09.470
<v Speaker 3>We, we just need to do it.

60
00:03:09.669 --> 00:03:11.589
<v Speaker 1>So, I think there's a lot of
misconceptions.

61
00:03:11.630 --> 00:03:13.389
<v Speaker 1>I think there's a lot of buzzwords, which
we can't.

62
00:03:13.580 --> 00:03:18.500
<v Speaker 1>Get away from because Sensai is a
predictive maintenance decision support tool,

63
00:03:18.869 --> 00:03:19.259
<v Speaker 1>right?

64
00:03:19.539 --> 00:03:23.500
<v Speaker 1>However, I think some of the, the
confusion comes from all these different places

65
00:03:23.500 --> 00:03:26.380
<v Speaker 1>are saying that they do predictive
maintenance and when I actually go and look at

66
00:03:26.380 --> 00:03:30.220
<v Speaker 1>them, they're, they're actually not all
doing predictive maintenance.

67
00:03:30.300 --> 00:03:35.610
<v Speaker 1>They might just be doing condition
monitoring, which is fine, that's needed too, but

68
00:03:35.610 --> 00:03:36.179
<v Speaker 1>now customers.

69
00:03:36.259 --> 00:03:39.419
<v Speaker 1>Might not have the right idea of what PDM
actually is.

70
00:03:39.619 --> 00:03:43.220
<v Speaker 1>So sometimes they still kind of think it's
this magical solution where they're going

71
00:03:43.220 --> 00:03:47.979
<v Speaker 1>to just give it their data and the system
is going to tell them exactly what is

72
00:03:47.979 --> 00:03:52.080
<v Speaker 1>happening with 100% certainty and what
maintenance actions they need to go perform

73
00:03:52.080 --> 00:03:54.520
<v Speaker 1>and where there's like no input from a
human.

74
00:03:54.660 --> 00:03:56.100
<v Speaker 1>That's just not reality.

75
00:03:56.179 --> 00:03:58.940
<v Speaker 1>There's too many unknowns for a system
like this.

76
00:03:59.020 --> 00:04:02.800
<v Speaker 1>Just be able to take that amount of
control and certainty over the situation.

77
00:04:03.259 --> 00:04:08.419
<v Speaker 1>But I think there's also misconceptions
around labeling tools themselves as

78
00:04:08.419 --> 00:04:12.259
<v Speaker 1>predictive maintenance, because as you've
heard me say before, this is a crusade

79
00:04:12.259 --> 00:04:16.489
<v Speaker 1>that I am on, which is that no tool is
predictive maintenance.

80
00:04:16.579 --> 00:04:21.209
<v Speaker 1>Predictive maintenance is a strategy that
encompasses many tools and many practices.

81
00:04:21.299 --> 00:04:21.679
<v Speaker 1>So.

82
00:04:22.230 --> 00:04:26.829
<v Speaker 1>Senseii is part of that, it's a very
useful part of that, but if you don't embrace

83
00:04:26.829 --> 00:04:31.959
<v Speaker 1>the other parts of predictive maintenance
as a strategy, you aren't going to

84
00:04:31.959 --> 00:04:32.760
<v Speaker 1>succeed.

85
00:04:33.160 --> 00:04:36.720
<v Speaker 3>Yeah, I, and I guess we consider
predictive maintenance isn't a, isn't a tool, it's

86
00:04:36.720 --> 00:04:37.980
<v Speaker 3>more of a, a strategy.

87
00:04:38.559 --> 00:04:42.950
<v Speaker 3>So what I guess are the core conditions
that make predictor maintenance valuable to

88
00:04:42.950 --> 00:04:45.100
<v Speaker 3>a plant, if you think of it through that
lens instead?

89
00:04:45.760 --> 00:04:50.239
<v Speaker 1>Oh, there's, there's so much value that it
can add, uh, you can, for example, you

90
00:04:50.239 --> 00:04:52.820
<v Speaker 1>can make sure you're prepared to have a
spare parts inventory.

91
00:04:53.660 --> 00:04:58.630
<v Speaker 1>Uh, if you know 3 months in advance that a
part of your equipment is starting to

92
00:04:58.630 --> 00:05:03.029
<v Speaker 1>degrade, then you can plan to have its
replacement ready to go for when you perform

93
00:05:03.029 --> 00:05:06.369
<v Speaker 1>maintenance, you know, just before that 3
month period.

94
00:05:06.589 --> 00:05:10.239
<v Speaker 1>We have people that have eliminated
planned maintenance on the assets that they're

95
00:05:10.239 --> 00:05:14.670
<v Speaker 1>monitoring with Sensai, so they no longer
send people on a round to put hands on a

96
00:05:14.670 --> 00:05:15.890
<v Speaker 1>machine unnecessarily.

97
00:05:16.299 --> 00:05:20.529
<v Speaker 1>Uh, no longer do people have to go waste
their time going to some far reaches of the

98
00:05:20.529 --> 00:05:23.720
<v Speaker 1>plans unless they actually have to, as
directed by Sensai.

99
00:05:23.809 --> 00:05:29.029
<v Speaker 1>So having that visibility allows people to
just trust in the system to tell them

100
00:05:29.290 --> 00:05:32.769
<v Speaker 1>when they need to perform the work, and
they, they go and they know what needs to be

101
00:05:32.769 --> 00:05:34.290
<v Speaker 1>done, so they go and do it, but.

102
00:05:34.730 --> 00:05:36.190
<v Speaker 1>I think reducing planned maintenance.

103
00:05:36.570 --> 00:05:38.989
<v Speaker 1>There's also, of course, the safety
aspect.

104
00:05:39.160 --> 00:05:42.359
<v Speaker 1>If, if we are preventing unplanned
downtimes.

105
00:05:42.570 --> 00:05:45.970
<v Speaker 1>I think unplanned downtime, like if
something goes down in the middle of the night,

106
00:05:46.410 --> 00:05:50.570
<v Speaker 1>maybe it's 2 o'clock in the morning, it's
crucial, the whole line gets taken down,

107
00:05:50.609 --> 00:05:51.769
<v Speaker 1>you want to get in and fix.

108
00:05:51.855 --> 00:05:57.114
<v Speaker 1>It as fast as humanly possible, you're a
lot more prone to shortcuts and making

109
00:05:57.114 --> 00:05:59.454
<v Speaker 1>mistakes that could have safety
implications.

110
00:05:59.584 --> 00:06:04.535
<v Speaker 1>So those are just 3 off the top of my
head, but there's so much benefit to just

111
00:06:04.535 --> 00:06:08.484
<v Speaker 1>knowing about the health of your machine
rather than just waiting for something to

112
00:06:08.484 --> 00:06:08.934
<v Speaker 1>happen.

113
00:06:09.399 --> 00:06:12.690
<v Speaker 3>Yeah, I, I don't know if this is a strange
question, but are customers actually

114
00:06:12.690 --> 00:06:13.959
<v Speaker 3>aware of all these different benefits?

115
00:06:14.010 --> 00:06:17.649
<v Speaker 3>I mean, they might be aware of something
like, you know, reducing downtime, for, for

116
00:06:17.649 --> 00:06:21.130
<v Speaker 3>example, but are they aware sort of the
broad benefits rather than just bucketing it

117
00:06:21.130 --> 00:06:25.970
<v Speaker 3>in, oh, it's just another digital thing,
another digital project or initiative we,

118
00:06:26.130 --> 00:06:30.114
<v Speaker 3>we should get off the ground, but we've no
real idea of what They're trying to solve

119
00:06:30.545 --> 00:06:30.765
<v Speaker 3>with it.

120
00:06:30.855 --> 00:06:31.214
<v Speaker 3>I don't know.

121
00:06:31.334 --> 00:06:34.614
<v Speaker 1>I don't know if they're aware of that from
the onset, but it's definitely a big part

122
00:06:34.614 --> 00:06:39.274
<v Speaker 1>of our conversations as soon as, pretty
much as soon as I start working with them,

123
00:06:39.454 --> 00:06:43.334
<v Speaker 1>uh, so as soon as it gets sold, you know,
we start these conversations not just

124
00:06:43.334 --> 00:06:46.654
<v Speaker 1>around what data do we need and how do we
get your data, but it's around what value

125
00:06:46.654 --> 00:06:49.114
<v Speaker 1>are you going to get from this because
everybody's different.

126
00:06:49.660 --> 00:06:54.260
<v Speaker 1>And some of those, some of those value
indicators are really hard to quantify.

127
00:06:54.380 --> 00:06:56.029
<v Speaker 1>How do you quantify safety?

128
00:06:56.299 --> 00:06:59.679
<v Speaker 1>I don't know, but it, it's something that
should be taken into account.

129
00:07:00.420 --> 00:07:00.739
<v Speaker 3>Exactly.

130
00:07:00.820 --> 00:07:05.299
<v Speaker 3>And I guess you mentioned there as well,
you know, like data as well, but, you know,

131
00:07:05.420 --> 00:07:08.619
<v Speaker 3>it encompasses so many different things of
predictive maintenance projects, and you,

132
00:07:08.700 --> 00:07:11.915
<v Speaker 3>you know, whether it's technically,
whether it's You know, the organization, whether

133
00:07:11.915 --> 00:07:13.316
<v Speaker 3>it's a cultural thing.

134
00:07:13.485 --> 00:07:17.765
<v Speaker 3>So, with those three key areas in mind, so
what's, you know, what are the warning

135
00:07:17.765 --> 00:07:21.235
<v Speaker 3>signs that something's not quite in
alignment for a predictive maintenance project?

136
00:07:21.756 --> 00:07:26.955
<v Speaker 1>Well, it, it always comes down to the
organizational structure, I would say, of

137
00:07:26.955 --> 00:07:28.756
<v Speaker 1>whoever's implementing Sensei.

138
00:07:28.835 --> 00:07:32.971
<v Speaker 1>So, I can give you some examples of Times
when it's been very difficult, and it, it

139
00:07:32.971 --> 00:07:34.712
<v Speaker 1>usually comes down to lack of support.

140
00:07:35.212 --> 00:07:39.731
<v Speaker 1>I have a customer I'm working with right
now, who is a really good example because

141
00:07:39.731 --> 00:07:44.731
<v Speaker 1>quite literally the CEO is in the calls
during the case reviews with me all the way

142
00:07:44.731 --> 00:07:46.111
<v Speaker 1>down to the maintainer level.

143
00:07:46.731 --> 00:07:50.052
<v Speaker 1>Tell me about another company that has
that level of support from the top and the

144
00:07:50.052 --> 00:07:51.432
<v Speaker 1>bottom all at once.

145
00:07:51.869 --> 00:07:54.970
<v Speaker 1>So anything that needs to get done, they
get it done.

146
00:07:55.329 --> 00:08:00.529
<v Speaker 1>So, um, I think what, what can happen is
people get this tool, they feed their data

147
00:08:00.529 --> 00:08:03.420
<v Speaker 1>in, and they don't realize that you have
to do something.

148
00:08:03.609 --> 00:08:06.609
<v Speaker 1>When Sensi tells you something, you have
to make the decision.

149
00:08:06.649 --> 00:08:08.329
<v Speaker 1>It cannot make it for you.

150
00:08:08.769 --> 00:08:13.369
<v Speaker 1>So you need somebody who understands how
to look at data, and you need somebody that

151
00:08:13.369 --> 00:08:18.450
<v Speaker 1>understands and, and has a workflow in
place to actually do something about it.

152
00:08:18.529 --> 00:08:20.630
<v Speaker 1>So let's say we do spot something.

153
00:08:21.570 --> 00:08:25.929
<v Speaker 1>Um, and, and, you know, part of the, the
aspects of predictive maintenance is we are

154
00:08:25.929 --> 00:08:26.410
<v Speaker 1>predicting.

155
00:08:26.529 --> 00:08:30.850
<v Speaker 1>So it could be something that's 6 months
down the line, it's gonna be a problem for

156
00:08:30.850 --> 00:08:30.959
<v Speaker 1>you.

157
00:08:31.010 --> 00:08:32.250
<v Speaker 1>What are you going to do about it right
now?

158
00:08:32.369 --> 00:08:34.830
<v Speaker 1>OK, so since that tells you what is your
workflow.

159
00:08:34.960 --> 00:08:38.289
<v Speaker 1>If you don't have a workflow, OK, let's
make sure we have a spare part inventory,

160
00:08:38.400 --> 00:08:41.630
<v Speaker 1>let's check our plant maintenance
schedule, let's plan for a scheduled downtime.

161
00:08:42.119 --> 00:08:45.280
<v Speaker 1>You know, during this event to make sure
that we can address this way before it's an

162
00:08:45.280 --> 00:08:46.229
<v Speaker 1>actual problem.

163
00:08:46.770 --> 00:08:51.250
<v Speaker 1>Let's change operations to, you know, slow
it down or something to baby the machine

164
00:08:51.250 --> 00:08:53.250
<v Speaker 1>to make sure it can last to a different
plan maintenance.

165
00:08:53.330 --> 00:08:57.929
<v Speaker 1>So you need somebody like a maintenance
planner involved that can, can help make

166
00:08:57.929 --> 00:08:58.690
<v Speaker 1>these decisions.

167
00:08:58.770 --> 00:09:01.890
<v Speaker 1>So there's a whole workflow involved that
needs to be in place.

168
00:09:01.929 --> 00:09:04.669
<v Speaker 1>And at this point I've been rambling and I
don't remember the original question.

169
00:09:05.090 --> 00:09:05.890
<v Speaker 3>No, that's OK.

170
00:09:06.049 --> 00:09:09.330
<v Speaker 3>Rambling's fine on a podcast in the right
place, Natalie, don't worry.

171
00:09:09.599 --> 00:09:12.799
<v Speaker 3>Um, but what I was going to lead that to,
I mean, that's an incredible example of

172
00:09:12.799 --> 00:09:13.200
<v Speaker 3>the CEO.

173
00:09:13.239 --> 00:09:14.580
<v Speaker 3>I've never heard of that.

174
00:09:15.080 --> 00:09:15.440
<v Speaker 3>It's great.

175
00:09:15.479 --> 00:09:18.520
<v Speaker 3>I mean, what, what sort of role do they
play on the call, because I mean, some

176
00:09:18.520 --> 00:09:22.940
<v Speaker 3>people might imagine the CEO's overbearing
and like, you know, like wants to, you

177
00:09:22.940 --> 00:09:26.119
<v Speaker 3>know, with other people on the call might
feel like all the CEO's here, but what

178
00:09:26.119 --> 00:09:28.190
<v Speaker 3>you're saying is that's, that's not the
case at all, right?

179
00:09:28.239 --> 00:09:30.440
<v Speaker 3>They're just genuinely interested in
what's going on,

180
00:09:31.080 --> 00:09:34.020
<v Speaker 1>I could absolutely see what the example
you just gave.

181
00:09:34.419 --> 00:09:38.460
<v Speaker 1>Being a risk because usually, you know,
these, the people maybe in a steering

182
00:09:38.460 --> 00:09:42.250
<v Speaker 1>committee aren't so technically minded and
they don't understand quite so well, but

183
00:09:42.250 --> 00:09:45.739
<v Speaker 1>I would say the CEO might be the person
that understands the best.

184
00:09:45.820 --> 00:09:48.500
<v Speaker 1>I think he was the main driver for getting
Sensai.

185
00:09:48.570 --> 00:09:51.640
<v Speaker 1>He's the one that was the main person
excited about it.

186
00:09:52.059 --> 00:09:55.900
<v Speaker 1>So there were other people in the call
asking questions about things that were

187
00:09:55.900 --> 00:09:58.960
<v Speaker 1>actually out of scope for this project,
for this deployment.

188
00:09:59.270 --> 00:10:03.830
<v Speaker 1>And he would step in and say, yeah, that's
not on our, our path right now, uh, when

189
00:10:03.830 --> 00:10:06.020
<v Speaker 1>we scale, you know, we'll we'll talk about
that.

190
00:10:06.349 --> 00:10:11.340
<v Speaker 1>But he's an engineer, so he understands
what he's looking at, and he's, he's

191
00:10:11.340 --> 00:10:13.150
<v Speaker 1>helping, you know, I would, I would raise
something.

192
00:10:13.229 --> 00:10:16.030
<v Speaker 1>I said, OK, this, this case is indicating
something.

193
00:10:16.150 --> 00:10:17.409
<v Speaker 1>Your machine is in trouble.

194
00:10:17.549 --> 00:10:18.859
<v Speaker 1>What are you going to do about it?

195
00:10:19.229 --> 00:10:23.229
<v Speaker 1>And for a moment, his team was silent and
he stepped in and said, Come on guys, what

196
00:10:23.229 --> 00:10:24.460
<v Speaker 1>are we going to do about it?

197
00:10:24.739 --> 00:10:26.849
<v Speaker 1>And I'm like, this is, this is great.

198
00:10:27.599 --> 00:10:27.609
<v Speaker 3>Wow.

199
00:10:28.690 --> 00:10:31.400
<v Speaker 3>Yeah, I mean, because we're always saying,
and we're always saying on this podcast,

200
00:10:31.510 --> 00:10:35.599
<v Speaker 3>right, that, you know, you need multiple
levels of stakeholders involved, but, you

201
00:10:35.599 --> 00:10:37.859
<v Speaker 3>know, to have that sort of involvement
from the CEO is just.

202
00:10:38.690 --> 00:10:40.390
<v Speaker 3>Just something else, right, driving it.

203
00:10:40.609 --> 00:10:47.010
<v Speaker 3>Um, but I mean, and who, I mean, if we're
talking about, you know, because we're

204
00:10:47.010 --> 00:10:50.690
<v Speaker 3>talking today about what isn't, uh, you
know, whether PDM's right or isn't right for

205
00:10:50.690 --> 00:10:50.960
<v Speaker 3>a plant.

206
00:10:51.010 --> 00:10:54.989
<v Speaker 3>So who's involved in that decision on a,
we just want a plant because we know it can

207
00:10:54.989 --> 00:10:56.330
<v Speaker 3>roll out much further than that.

208
00:10:56.450 --> 00:11:00.489
<v Speaker 3>But if we just talk about a plant itself,
who, who'd be involved in those case

209
00:11:00.489 --> 00:11:03.450
<v Speaker 3>reviews or some of the earlier discussions
about it?

210
00:11:03.809 --> 00:11:07.969
<v Speaker 1>So the, the critical thing when we get
involved with the customer is we need what we

211
00:11:07.969 --> 00:11:08.840
<v Speaker 1>call a champion.

212
00:11:09.239 --> 00:11:11.849
<v Speaker 1>This champion needs to really want Sensai.

213
00:11:12.090 --> 00:11:13.409
<v Speaker 1>They need to be interested in it.

214
00:11:13.450 --> 00:11:17.929
<v Speaker 1>They need to be able to see the benefit
that Sensai will bring to them in terms of

215
00:11:17.929 --> 00:11:20.289
<v Speaker 1>efficiency and savings.

216
00:11:20.729 --> 00:11:21.840
<v Speaker 1>So they need to care about it.

217
00:11:22.099 --> 00:11:23.530
<v Speaker 1>They also need to be technically minded.

218
00:11:23.599 --> 00:11:25.289
<v Speaker 1>They need to understand their machines.

219
00:11:25.690 --> 00:11:29.929
<v Speaker 1>They need to be able to read the data in
the charts because again, some level of

220
00:11:29.929 --> 00:11:30.109
<v Speaker 1>competition.

221
00:11:30.989 --> 00:11:34.640
<v Speaker 1>Competency is needed in our in in data
analysis.

222
00:11:34.760 --> 00:11:38.640
<v Speaker 1>You don't have to be an expert data
scientist, but you need to be able to look at a

223
00:11:38.640 --> 00:11:43.619
<v Speaker 1>time series and understand what the data
shown might be indicating for your machine.

224
00:11:44.039 --> 00:11:48.400
<v Speaker 1>So a champion has to kind of encompass all
of those, and they need to be also

225
00:11:48.400 --> 00:11:53.919
<v Speaker 1>proactive and have channels of
communication open to, like I said, follow up after

226
00:11:53.919 --> 00:11:54.380
<v Speaker 1>the case.

227
00:11:54.840 --> 00:11:56.679
<v Speaker 1>How, how is Sensa embedded in your work?

228
00:11:56.750 --> 00:11:58.830
<v Speaker 1>Workflow, your predictive maintenance
strategy.

229
00:11:59.109 --> 00:12:03.909
<v Speaker 1>So they need to be able to go talk to
operations and have some amount of uh control

230
00:12:03.909 --> 00:12:07.900
<v Speaker 1>there to be able to maybe change how the
machine is operated or they need to talk to

231
00:12:07.900 --> 00:12:12.309
<v Speaker 1>the maintenance planner, um, so they need
to have some amount of authority.

232
00:12:12.630 --> 00:12:14.250
<v Speaker 1>So I would say that champion is critical.

233
00:12:14.309 --> 00:12:19.750
<v Speaker 1>If we don't have a champion, we have a
really hard time because we need one person

234
00:12:19.750 --> 00:12:23.030
<v Speaker 1>who is taking charge and saying, I'm
owning this.

235
00:12:23.299 --> 00:12:27.780
<v Speaker 1>Eventually we get end users in who are
just regular users, but we need that initial

236
00:12:27.780 --> 00:12:30.320
<v Speaker 1>admin, that champion from the, from the
beginning.

237
00:12:30.739 --> 00:12:34.020
<v Speaker 3>And, and again, yeah, we talked about
champions a lot, but I think it's interesting

238
00:12:34.020 --> 00:12:37.500
<v Speaker 3>because you brought up the situation with
the CEO joining the call.

239
00:12:37.609 --> 00:12:42.760
<v Speaker 3>So is the champion usually someone in a
certain type of role, or, or can it vary?

240
00:12:42.859 --> 00:12:45.960
<v Speaker 3>Like with the CEO maybe becomes the
champion in a rare case.

241
00:12:46.429 --> 00:12:49.440
<v Speaker 1>I would say CEOs are generally not our
champions.

242
00:12:50.119 --> 00:12:54.960
<v Speaker 1>They might be our, our leading sponsor,
which I think, I think is this case.

243
00:12:55.080 --> 00:12:57.789
<v Speaker 1>He's just more technically minded than
most probably.

244
00:12:58.039 --> 00:13:02.179
<v Speaker 1>Um, I would say a champion, my ideal
champion is a reliability engineer.

245
00:13:02.679 --> 00:13:05.599
<v Speaker 1>Uh, sometimes people don't have those,
actually, the, the customer I'm talking about

246
00:13:05.599 --> 00:13:09.919
<v Speaker 1>right now doesn't have a reliability
engineer, but they found somebody who, if they

247
00:13:09.919 --> 00:13:12.419
<v Speaker 1>decided to have that role, I think it
would be this person.

248
00:13:13.359 --> 00:13:16.000
<v Speaker 3>And that just proves it's, it's a per
organization thing, right?

249
00:13:16.239 --> 00:13:19.479
<v Speaker 3>You know, it could be the CEO, it could be
reliability engineer, it could be.

250
00:13:19.715 --> 00:13:23.234
<v Speaker 3>Someone in maintenance, but the idea is
you need someone who's proactive, who's

251
00:13:23.234 --> 00:13:25.875
<v Speaker 3>going to not just, you know, see the
information, but actually connect with the

252
00:13:25.875 --> 00:13:29.114
<v Speaker 3>relevant people so people take action on
the information that's actually been

253
00:13:29.114 --> 00:13:29.455
<v Speaker 3>provided.

254
00:13:29.594 --> 00:13:33.515
<v Speaker 1>And to make, just to make the decisions,
make, make decisions on what needs to

255
00:13:33.515 --> 00:13:40.195
<v Speaker 1>happen, we actually have, it almost looks
like a, a job posting for like the

256
00:13:40.195 --> 00:13:44.635
<v Speaker 1>required characteristics of a person to be
in the role of a champion and an end

257
00:13:44.635 --> 00:13:44.955
<v Speaker 1>user.

258
00:13:45.065 --> 00:13:48.594
<v Speaker 1>So we actually have those in our help
center to help organizations find the right

259
00:13:48.594 --> 00:13:49.094
<v Speaker 1>people.

260
00:13:49.679 --> 00:13:52.640
<v Speaker 1>Within themselves to to fill those roles.

261
00:13:53.140 --> 00:13:53.840
<v Speaker 3>I think that's interesting as well.

262
00:13:53.950 --> 00:13:56.880
<v Speaker 3>So they might not even, even if they see
it on paper, these are the roles, they

263
00:13:56.880 --> 00:14:00.549
<v Speaker 3>might not even understand themselves
within the organization who's who's right.

264
00:14:00.820 --> 00:14:05.299
<v Speaker 3>Again, it's clearly it's not just a, you
know, cookie cutter approach to every

265
00:14:05.299 --> 00:14:05.340
<v Speaker 3>organization,

266
00:14:05.510 --> 00:14:05.840
<v Speaker 1>right?

267
00:14:06.200 --> 00:14:06.369
<v Speaker 1>Right.

268
00:14:06.479 --> 00:14:09.239
<v Speaker 1>Well, sometimes they come to me and they
say, OK, who is our champion?

269
00:14:09.309 --> 00:14:11.469
<v Speaker 1>And I said, I can't answer that for you.

270
00:14:11.760 --> 00:14:16.070
<v Speaker 1>But here's, here's kind of what this
person needs to have the characteristics of,

271
00:14:16.239 --> 00:14:18.020
<v Speaker 1>um, so we can start there.

272
00:14:19.650 --> 00:14:24.780
<v Speaker 3>In terms of examples where another way to
look at it, I guess, is when everything

273
00:14:24.780 --> 00:14:25.590
<v Speaker 3>looks right on paper.

274
00:14:25.700 --> 00:14:29.119
<v Speaker 3>So, you know, right organization, you've
got a champion, then it just doesn't work

275
00:14:29.530 --> 00:14:30.919
<v Speaker 3>for whatever reason.

276
00:14:31.099 --> 00:14:35.140
<v Speaker 3>I mean, do you have any examples in that
area where, you know, everything could look

277
00:14:35.140 --> 00:14:38.559
<v Speaker 3>set up for real greatness, but it just
doesn't quite work out that way?

278
00:14:39.039 --> 00:14:40.080
<v Speaker 1>Hm, that's a good question.

279
00:14:40.659 --> 00:14:42.580
<v Speaker 1>I think, I think it's.

280
00:14:42.640 --> 00:14:46.679
<v Speaker 1>So I've said this already before in this
call even, but it's so important to have

281
00:14:46.679 --> 00:14:51.700
<v Speaker 1>support from the bottom and the top,
because if you have, let's say you have a great

282
00:14:51.700 --> 00:14:56.270
<v Speaker 1>champion, and they're doing their thing,
and then they learn everything, the ins and

283
00:14:56.270 --> 00:15:02.239
<v Speaker 1>outs of Sensai, and then they leave their
job or they move, and then no one else

284
00:15:02.239 --> 00:15:03.619
<v Speaker 1>cares enough to take it up.

285
00:15:03.960 --> 00:15:04.669
<v Speaker 1>What do you do?

286
00:15:05.080 --> 00:15:05.580
<v Speaker 1>So.

287
00:15:06.289 --> 00:15:11.840
<v Speaker 1>I think that's where the support from a
sponsor is so important because you can rely

288
00:15:11.840 --> 00:15:17.039
<v Speaker 1>on your champion a lot, but you need
support in case something changes

289
00:15:17.039 --> 00:15:17.630
<v Speaker 1>organizationally.

290
00:15:18.049 --> 00:15:21.849
<v Speaker 1>And I would, I would also say, so from
the, the people point of view, that's always

291
00:15:21.849 --> 00:15:26.030
<v Speaker 1>the struggle, but From the assets and the
data point of view, of course, that could

292
00:15:26.030 --> 00:15:28.900
<v Speaker 1>be our other area where, where things
don't quite work out.

293
00:15:28.989 --> 00:15:31.969
<v Speaker 1>Maybe the right assets were not chosen in
the beginning.

294
00:15:32.219 --> 00:15:37.690
<v Speaker 1>Uh, maybe the assets chosen are super
complicated, so complicated that maybe the

295
00:15:37.690 --> 00:15:41.830
<v Speaker 1>champion can't make sense of what Sensai
is trying to tell them about the.

296
00:15:41.960 --> 00:15:47.780
<v Speaker 1>Changes in their data, maybe they don't
have the right data or low data quality or,

297
00:15:47.789 --> 00:15:49.039
<v Speaker 1>you know, anything to do with data.

298
00:15:49.119 --> 00:15:53.919
<v Speaker 1>You need to, since I will give you what
you put into it, so if you put in terrible

299
00:15:53.919 --> 00:15:57.599
<v Speaker 1>quality data or not enough of it, it's,
it's not going to be able to tell you

300
00:15:57.599 --> 00:15:58.479
<v Speaker 1>magical results.

301
00:15:58.659 --> 00:16:00.700
<v Speaker 1>So, of course, that's always a factor.

302
00:16:01.700 --> 00:16:05.030
<v Speaker 3>Yeah, let's go more technical side in, in
terms of data and connectivity.

303
00:16:05.090 --> 00:16:08.809
<v Speaker 3>So that, I guess there must be like a
minimum amount that that's required to get

304
00:16:09.070 --> 00:16:09.789
<v Speaker 3>something up and running.

305
00:16:09.909 --> 00:16:14.229
<v Speaker 3>I'm gonna presume a little bit that it's
underestimated what's actually required,

306
00:16:14.429 --> 00:16:17.030
<v Speaker 3>maybe, or maybe you could answer that
rather than me presuming.

307
00:16:18.950 --> 00:16:23.890
<v Speaker 1>It's, I would say that everybody's least
favorite answer is it depends.

308
00:16:24.479 --> 00:16:30.640
<v Speaker 1>I think as long as expectations are
manageable or reasonable, so for example, let's

309
00:16:30.640 --> 00:16:32.390
<v Speaker 1>take something really simple, a motor.

310
00:16:32.799 --> 00:16:36.719
<v Speaker 1>Let's say all you have is motor current,
and that's the only thing you can get out

311
00:16:36.719 --> 00:16:36.960
<v Speaker 1>of it.

312
00:16:37.039 --> 00:16:38.539
<v Speaker 1>We can start with that.

313
00:16:39.000 --> 00:16:44.010
<v Speaker 1>We can, but are we going to detect bearing
problems if all we have is motor current?

314
00:16:44.200 --> 00:16:49.830
<v Speaker 1>No, we can, we can detect electrical
problems, maybe not all of them, but it's a

315
00:16:49.830 --> 00:16:50.900
<v Speaker 1>place to start.

316
00:16:51.119 --> 00:16:55.320
<v Speaker 1>But what we find is, you know, we onboard
some data like that, and we might have a

317
00:16:55.320 --> 00:16:58.400
<v Speaker 1>customer that says, well, the, the motor
went down, why didn't you detect it?

318
00:16:58.469 --> 00:16:59.909
<v Speaker 1>And we say, well, why did it go down?

319
00:17:00.030 --> 00:17:03.890
<v Speaker 1>And they say, oh, because of This thing
that happened downstream or, you know, this

320
00:17:03.890 --> 00:17:08.650
<v Speaker 1>bearing was crushed or something, and it's
like, how could we possibly detect that?

321
00:17:08.729 --> 00:17:10.770
<v Speaker 1>I'm looking at the data with my eyes.

322
00:17:10.849 --> 00:17:14.329
<v Speaker 1>I see nothing to indicate any sort of
degradation.

323
00:17:14.650 --> 00:17:18.609
<v Speaker 1>So if you want to detect that, we need
more data, but that's like an expectation

324
00:17:18.609 --> 00:17:23.469
<v Speaker 1>that has to be managed from the first
conversation with a customer.

325
00:17:24.430 --> 00:17:27.229
<v Speaker 3>And it, and it links back to what you were
saying earlier, Natalie, about, you know,

326
00:17:27.469 --> 00:17:31.689
<v Speaker 3>predicting maintenance being some magic
box you, you could apply and it'll just spot

327
00:17:32.030 --> 00:17:35.550
<v Speaker 3>anything and everything, even like you
said in that, in that those examples, even

328
00:17:35.550 --> 00:17:38.400
<v Speaker 3>without the right data to actually spot
that, right?

329
00:17:38.829 --> 00:17:42.949
<v Speaker 3>So you can only do so much, right, with
the data and everything else that's that's

330
00:17:42.949 --> 00:17:43.540
<v Speaker 3>put into it.

331
00:17:43.709 --> 00:17:47.670
<v Speaker 1>Right, so one of my, one of the things I
like to say is sensei predictive

332
00:17:47.670 --> 00:17:50.930
<v Speaker 1>maintenance cannot predict unpredictable
events.

333
00:17:52.420 --> 00:17:56.579
<v Speaker 1>Which sounds so obvious when I put it that
way, but sometimes something might happen

334
00:17:56.579 --> 00:18:00.660
<v Speaker 1>instantaneously, and since I doesn't
detect it, because it was an instantaneous

335
00:18:00.660 --> 00:18:02.459
<v Speaker 1>failure, there was no degradation.

336
00:18:02.500 --> 00:18:06.699
<v Speaker 1>It just maybe something, maybe a meteorite
fell out of the sky and landed on your

337
00:18:06.699 --> 00:18:07.140
<v Speaker 1>motor.

338
00:18:07.189 --> 00:18:08.819
<v Speaker 1>Like, how could we predict that?

339
00:18:10.390 --> 00:18:12.800
<v Speaker 3>And, and actually maybe we could explore
that a little bit more in terms of these

340
00:18:12.800 --> 00:18:15.760
<v Speaker 3>misconceptions because I, I mean, again,
we talked about it a little bit earlier,

341
00:18:15.839 --> 00:18:19.760
<v Speaker 3>but I've sort of misconceptions about
predicting maintenance are there, you know,

342
00:18:19.839 --> 00:18:21.780
<v Speaker 3>which you, you, you hear in conversations.

343
00:18:22.630 --> 00:18:26.989
<v Speaker 1>I think one of the ones, especially now
that we have copilot, copilot is so helpful

344
00:18:26.989 --> 00:18:32.270
<v Speaker 1>in giving its best guess as to what's
happening on the machine, why the case was

345
00:18:32.270 --> 00:18:38.390
<v Speaker 1>raised, but some of the misconceptions are
that co-pilot just knows everything from

346
00:18:38.390 --> 00:18:39.030
<v Speaker 1>the beginning.

347
00:18:39.550 --> 00:18:39.989
<v Speaker 1>Doesn't.

348
00:18:40.050 --> 00:18:41.689
<v Speaker 1>It starts with some good information.

349
00:18:41.750 --> 00:18:47.939
<v Speaker 1>It has like a, a base baseline database of
knowledge, but If you don't tell it

350
00:18:47.939 --> 00:18:54.380
<v Speaker 1>stuff, if, if the data changes on a
machine suddenly, and you don't tell it, oh

351
00:18:54.380 --> 00:18:56.170
<v Speaker 1>yeah, I went out and replaced it.

352
00:18:56.300 --> 00:19:00.219
<v Speaker 1>I replaced this whole component, and you
don't tell Sunai that, how could it

353
00:19:00.219 --> 00:19:01.560
<v Speaker 1>possibly know?

354
00:19:01.819 --> 00:19:07.900
<v Speaker 1>So it's going to tell you it's best guess
based on what it knows, but You have to

355
00:19:07.900 --> 00:19:09.300
<v Speaker 1>give it more context.

356
00:19:09.540 --> 00:19:13.910
<v Speaker 1>So anytime, anytime you interfere with the
machine, if the, you know, if something

357
00:19:13.910 --> 00:19:16.719
<v Speaker 1>changes, you have to go tell it that so it
can learn.

358
00:19:17.199 --> 00:19:22.000
<v Speaker 3>How's the, now the introduction of
generative AI and co-pilot technology, has that

359
00:19:22.219 --> 00:19:25.859
<v Speaker 3>made that whole, it's magic thing, you
know, even more so.

360
00:19:25.979 --> 00:19:29.920
<v Speaker 3>A bit of expectations raised even higher,
if that's even possible.

361
00:19:30.219 --> 00:19:30.729
<v Speaker 1>I think so.

362
00:19:30.780 --> 00:19:34.959
<v Speaker 1>I still, I do think Gen AI is kind of
magic, so I'm gonna need somebody who knows.

363
00:19:35.165 --> 00:19:40.204
<v Speaker 1>More about it than I do to tell me it's
not, but just in the world, it seems like,

364
00:19:40.244 --> 00:19:42.224
<v Speaker 1>oh my God, this thing is incredible.

365
00:19:42.685 --> 00:19:46.604
<v Speaker 1>But yeah, so we'll see still some
misconceptions, not so much about predictive

366
00:19:46.604 --> 00:19:51.484
<v Speaker 1>maintenance, but about Sensei in
particular, is that the Sensai workflow is that a

367
00:19:51.484 --> 00:19:54.645
<v Speaker 1>case is raised, that's your notification
that something has changed.

368
00:19:54.685 --> 00:19:58.515
<v Speaker 1>It's going to give you its best guess into
what is going on in the condition of the

369
00:19:58.515 --> 00:20:02.244
<v Speaker 1>machine based on information you've told
it previously or closed other cases that

370
00:20:02.244 --> 00:20:03.025
<v Speaker 1>were similar.

371
00:20:03.609 --> 00:20:08.770
<v Speaker 1>But you, you have to come back and tell it
what you've found.

372
00:20:09.010 --> 00:20:13.689
<v Speaker 1>So, if, if a case is raised and you don't
like it, and you close the case and you

373
00:20:13.689 --> 00:20:18.010
<v Speaker 1>take no follow-up action, so you close the
case and you say, I'm grumpy.

374
00:20:18.089 --> 00:20:20.290
<v Speaker 1>I don't like this case, don't open it
again.

375
00:20:20.780 --> 00:20:24.890
<v Speaker 1>You have not told anyone what about the
case you don't like.

376
00:20:25.140 --> 00:20:30.180
<v Speaker 1>And just telling sense I, I don't like
this case, there are like uh uh more than a

377
00:20:30.180 --> 00:20:34.119
<v Speaker 1>dozen different parameters that could be
the reason you don't like the case.

378
00:20:34.420 --> 00:20:38.020
<v Speaker 1>Is it because this was moving up, it was
it not moving up fast enough?

379
00:20:38.140 --> 00:20:41.180
<v Speaker 1>Was, you know, was the baseline shift not
big enough?

380
00:20:41.260 --> 00:20:43.500
<v Speaker 1>Was it going down and you only care if
it's going up?

381
00:20:43.819 --> 00:20:45.380
<v Speaker 1>How can the system know, right?

382
00:20:45.760 --> 00:20:50.640
<v Speaker 1>So you have to come back and tell somebody
what you didn't like, and when I say

383
00:20:50.640 --> 00:20:52.739
<v Speaker 1>somebody, I mean a real human being.

384
00:20:53.160 --> 00:20:56.989
<v Speaker 1>You can raise a ticket and sun sign and
say, hey, I got a, I got a case on a

385
00:20:56.989 --> 00:20:57.959
<v Speaker 1>decrease in temperature.

386
00:20:58.040 --> 00:20:59.800
<v Speaker 1>I only care when temperature is going up.

387
00:20:59.920 --> 00:21:01.479
<v Speaker 1>Can you, can you tune the algorithms?

388
00:21:01.560 --> 00:21:04.040
<v Speaker 1>We can say, sure, and we can go do that.

389
00:21:04.119 --> 00:21:09.150
<v Speaker 1>But the, the app isn't going to do that on
its own because there's way too much.

390
00:21:09.400 --> 00:21:11.219
<v Speaker 1>You need a human involved in that.

391
00:21:11.410 --> 00:21:14.400
<v Speaker 1>Uh, there's just too many different
parameters that it could possibly be.

392
00:21:14.560 --> 00:21:18.949
<v Speaker 1>So, I'd say that's a big misconception,
specifically with Sensai is that you close a

393
00:21:18.949 --> 00:21:21.880
<v Speaker 1>case and you say you're grumpy about it,
and then you get the same case opening a

394
00:21:21.880 --> 00:21:22.439
<v Speaker 1>week later.

395
00:21:22.599 --> 00:21:25.780
<v Speaker 1>It's because you didn't do anything about
it, you have to take that follow-up action

396
00:21:26.079 --> 00:21:27.219
<v Speaker 1>to get the result you want.

397
00:21:27.719 --> 00:21:31.319
<v Speaker 3>It's funny, I have a sort of relate
related story, not, not so I'm being grumpy with

398
00:21:31.319 --> 00:21:34.880
<v Speaker 3>the case, but actually, when I
interviewed, um, one of our colleagues, Jordan on the

399
00:21:34.880 --> 00:21:39.109
<v Speaker 3>podcast, he, he was talking about how a
customer was reluctant to let us know that

400
00:21:39.109 --> 00:21:39.939
<v Speaker 3>Sensai had done.

401
00:21:40.800 --> 00:21:43.270
<v Speaker 3>Had, had opened a case that wasn't
relevant or whatever.

402
00:21:43.800 --> 00:21:45.469
<v Speaker 3>And it's a similar, you know, it's a
similar result.

403
00:21:45.520 --> 00:21:49.599
<v Speaker 3>If you don't tell us or let anyone know,
then it will keep appearing, right?

404
00:21:49.760 --> 00:21:52.160
<v Speaker 3>And that was the sort of the point he was
saying to them, we want to know this

405
00:21:52.160 --> 00:21:52.359
<v Speaker 3>stuff.

406
00:21:52.719 --> 00:21:53.739
<v Speaker 3>We need to know this stuff.

407
00:21:54.000 --> 00:21:56.880
<v Speaker 3>So it's good for you, it's good for us,
it's good, you know, for your deployment of

408
00:21:56.880 --> 00:21:57.660
<v Speaker 3>sensei, right?

409
00:21:58.150 --> 00:22:02.680
<v Speaker 3>Um, I guess as we sort of come to a close,
I I wanted to think about, because we

410
00:22:02.680 --> 00:22:06.760
<v Speaker 3>talked a lot about why predicts
maintenance might be right for an organization or a

411
00:22:06.760 --> 00:22:08.880
<v Speaker 3>plant, sorry, or, or, or not right.

412
00:22:09.359 --> 00:22:12.890
<v Speaker 3>But if a plant decides, and they, they
know in their mind, right, we're not ready

413
00:22:12.890 --> 00:22:17.449
<v Speaker 3>for predicting maintenance right now, but
maybe they want to be in the near future

414
00:22:17.449 --> 00:22:18.329
<v Speaker 3>or medium term.

415
00:22:18.530 --> 00:22:22.329
<v Speaker 3>So what, what steps they need to take to
sort of get to that stage, and we're

416
00:22:22.329 --> 00:22:24.239
<v Speaker 3>talking very generally here, of course.

417
00:22:24.650 --> 00:22:25.790
<v Speaker 1>That's a really great question.

418
00:22:25.890 --> 00:22:29.609
<v Speaker 1>I would say the first question that they
have to be able to answer is why do they

419
00:22:29.609 --> 00:22:31.670
<v Speaker 1>think predictive maintenance will help
them?

420
00:22:32.540 --> 00:22:33.989
<v Speaker 1>What do they want to get out of it?

421
00:22:35.359 --> 00:22:41.319
<v Speaker 1>Uh, we start with a lot of people that
have no idea of what sort of savings they

422
00:22:41.319 --> 00:22:43.000
<v Speaker 1>want to, to try and achieve.

423
00:22:43.079 --> 00:22:44.430
<v Speaker 1>They don't know their KPIs.

424
00:22:44.680 --> 00:22:49.270
<v Speaker 1>So, it's interesting to me to invest in
something without knowing really why,

425
00:22:49.680 --> 00:22:51.959
<v Speaker 1>because there's so much buzz around it,
you want to get involved in it, but you

426
00:22:51.959 --> 00:22:53.689
<v Speaker 1>don't actually know how it can help you.

427
00:22:54.119 --> 00:22:57.680
<v Speaker 1>So to get started and try to understand
that, you can review your maintenance logs,

428
00:22:57.750 --> 00:23:02.640
<v Speaker 1>you can figure out which assets are
continuously causing you problems and how much

429
00:23:02.640 --> 00:23:04.140
<v Speaker 1>those problems are costing.

430
00:23:04.520 --> 00:23:08.609
<v Speaker 1>In whatever KPIs, maybe it's in downtime,
maybe it's in product loss, maybe it's an

431
00:23:08.609 --> 00:23:09.189
<v Speaker 1>environmental.

432
00:23:10.410 --> 00:23:11.920
<v Speaker 1>I don't know, of Greaeses or something.

433
00:23:13.030 --> 00:23:15.550
<v Speaker 1>Um, labor, any of that sort of stuff.

434
00:23:15.829 --> 00:23:19.869
<v Speaker 1>Maybe you want to be able to better manage
your spare parts inventory, uh, maybe you

435
00:23:19.869 --> 00:23:21.709
<v Speaker 1>want to reduce plan maintenance, so.

436
00:23:22.270 --> 00:23:26.550
<v Speaker 1>Get an idea of what your starting values
are for all of those things, because if you

437
00:23:26.550 --> 00:23:32.099
<v Speaker 1>don't know where you're starting, it's
really hard to track value with Sensii or

438
00:23:32.099 --> 00:23:33.449
<v Speaker 1>with any PDM solution.

439
00:23:34.069 --> 00:23:38.300
<v Speaker 1>So I would say start there and figure out,
starting with the maintenance logs, which

440
00:23:38.300 --> 00:23:43.469
<v Speaker 1>assets are causing problems, um, and then
go into seeing, OK, what data do we have

441
00:23:43.469 --> 00:23:44.589
<v Speaker 1>available on those assets?

442
00:23:44.630 --> 00:23:48.369
<v Speaker 1>Do we, will we need additional sensing,
and that's probably a good place to start.

443
00:23:49.050 --> 00:23:49.849
<v Speaker 3>Yeah, exactly.

444
00:23:50.010 --> 00:23:54.530
<v Speaker 3>So then you at least have the big picture
before then choosing, you know, when and

445
00:23:54.530 --> 00:23:57.229
<v Speaker 3>how to approach predictive maintenance at
the right time.

446
00:23:57.569 --> 00:24:01.770
<v Speaker 1>And then I would say finding that
champion, finding someone who, if you have a

447
00:24:01.770 --> 00:24:06.209
<v Speaker 1>reliability engineer, that would be a
great person, um, but if not, finding that

448
00:24:06.209 --> 00:24:12.050
<v Speaker 1>person who is interested and has some
level of competency with, with data and the

449
00:24:12.050 --> 00:24:12.670
<v Speaker 1>machines

450
00:24:13.089 --> 00:24:14.959
<v Speaker 3>or your CEO as it, as its

451
00:24:14.959 --> 00:24:16.150
<v Speaker 1>CEO apparently

452
00:24:16.650 --> 00:24:18.359
<v Speaker 3>you can get them on board even better,
but.

453
00:24:19.260 --> 00:24:20.099
<v Speaker 3>No, that's fantastic.

454
00:24:20.219 --> 00:24:24.739
<v Speaker 3>So, at, at the beginning of, um, oh well,
before we sort of start recording, I'll

455
00:24:24.739 --> 00:24:28.780
<v Speaker 3>let you know very last minute that we've
introduced a lightning round to, um, to our

456
00:24:28.780 --> 00:24:29.699
<v Speaker 3>recent podcast episode.

457
00:24:29.780 --> 00:24:31.130
<v Speaker 3>So, you're no exception, Natalie.

458
00:24:31.180 --> 00:24:33.290
<v Speaker 3>So, it's, it's really about the first
thing that comes into your head,

459
00:24:33.420 --> 00:24:33.900
<v Speaker 1>right?

460
00:24:34.739 --> 00:24:36.660
<v Speaker 3>So, if you're ready, so we have 3
questions.

461
00:24:36.780 --> 00:24:40.439
<v Speaker 3>So, the 1st, 1st 1 is, one thing that
customers always underestimate.

462
00:24:41.439 --> 00:24:45.060
<v Speaker 1>How, how difficult it is to get started.

463
00:24:46.170 --> 00:24:47.000
<v Speaker 1>To get data in.

464
00:24:47.859 --> 00:24:48.420
<v Speaker 3>Fantastic.

465
00:24:48.619 --> 00:24:51.579
<v Speaker 1>Even if we provide the whole solution,
it's, it's still, it takes

466
00:24:51.579 --> 00:24:52.060
<v Speaker 3>time.

467
00:24:52.500 --> 00:24:53.119
<v Speaker 3>Absolutely.

468
00:24:53.469 --> 00:24:58.300
<v Speaker 3>Um, and one step you should never skip in
the process in deploying predictive

469
00:24:58.300 --> 00:24:58.859
<v Speaker 3>maintenance.

470
00:24:59.260 --> 00:25:00.760
<v Speaker 1>Determine your KPIs.

471
00:25:01.500 --> 00:25:04.239
<v Speaker 3>And finally, one myth you wish would
disappear.

472
00:25:05.380 --> 00:25:07.380
<v Speaker 1>That sunset and magic black box.

473
00:25:08.400 --> 00:25:08.410
<v Speaker 1>Oh,

474
00:25:08.959 --> 00:25:10.540
<v Speaker 3>fantastic, fantastic.

475
00:25:11.020 --> 00:25:11.439
<v Speaker 3>Awesome.

476
00:25:11.579 --> 00:25:13.060
<v Speaker 3>No, thank you, really, really good.

477
00:25:13.180 --> 00:25:17.189
<v Speaker 3>Um, so yeah, no, that brings us to the
end, we've covered a lot of topics, probably

478
00:25:17.189 --> 00:25:21.040
<v Speaker 3>other topics we could have covered, but of
course we could always, um, record again

479
00:25:21.099 --> 00:25:24.489
<v Speaker 3>at some point, but it's lovely to have you
back on the podcast, Nasty, thanks for

480
00:25:24.489 --> 00:25:25.339
<v Speaker 3>taking part.

481
00:25:25.699 --> 00:25:26.599
<v Speaker 1>Thanks so much for having me.

482
00:25:27.359 --> 00:25:31.239
<v Speaker 3>Yeah, and thank you everyone out there for
listening, wherever you are, and we'll

483
00:25:31.239 --> 00:25:32.140
<v Speaker 3>see you on the next episode.

484
00:25:32.560 --> 00:25:33.520
<v Speaker 3>Thank you very much.

485
00:25:34.630 --> 00:25:39.589
<v Speaker 2>Please like and subscribe on all major
podcast channels and find out more about

486
00:25:39.589 --> 00:25:42.969
<v Speaker 2>Sensei predictive maintenance at
Siemens.com.
