WEBVTT
Language: en-US

1
00:00:01.559 --> 00:00:07.840
<v Andrew Rehm>We started doing downtime maintenance,
scheduling the outages, stuff like that, and

2
00:00:07.840 --> 00:00:09.149
<v Andrew Rehm>where we're at now.

3
00:00:10.220 --> 00:00:17.020
<v Andrew Rehm>is really of how do we manage our uptime
with predictive maintenance

4
00:00:17.020 --> 00:00:19.620
<v Andrew Rehm>instead of planned inspection.

5
00:00:20.340 --> 00:00:23.170
<v Speaker 2>Welcome to the trend detection podcast
powered by

6
00:00:23.170 --> 00:00:23.760
<v Speaker 3>Siemens.

7
00:00:23.860 --> 00:00:27.520
<v Speaker 3>Hello and welcome to the latest episode of
the Trend detection podcast.

8
00:00:28.139 --> 00:00:32.650
<v Speaker 3>Uh, I'm really pleased to be joined once
again by one of our fantastic Siemens

9
00:00:32.650 --> 00:00:37.099
<v Speaker 3>customers, so Highland Peellets and Andrew
from Highland Pellets today, and we're

10
00:00:37.099 --> 00:00:38.279
<v Speaker 3>gonna talk about.

11
00:00:38.700 --> 00:00:43.979
<v Speaker 3>What's really a fantastic success case,
we've, we've had a pellet mill success case,

12
00:00:44.020 --> 00:00:48.500
<v Speaker 3>because it's saved over 60 hours of
unplanned downtime thanks to the monitoring of

13
00:00:48.500 --> 00:00:52.580
<v Speaker 3>Sensai and obviously the work of, of the
team at Highland Pellets as well, so we

14
00:00:52.580 --> 00:00:57.090
<v Speaker 3>really want to dig into that, what
happened and how they're using sort of Sensai day

15
00:00:57.090 --> 00:01:00.740
<v Speaker 3>to day as well, but I guess before we get
started, Andrew, it'd be great just to

16
00:01:00.740 --> 00:01:03.919
<v Speaker 3>introduce yourself and a little bit about
Highland pellets as well would be great.

17
00:01:04.220 --> 00:01:04.580
<v Speaker 3>Thank you.

18
00:01:05.010 --> 00:01:05.500
<v Andrew Rehm>Yeah.

19
00:01:05.779 --> 00:01:06.260
<v Andrew Rehm>Thank you.

20
00:01:06.379 --> 00:01:07.680
<v Andrew Rehm>Thank you for having me on here.

21
00:01:07.779 --> 00:01:09.089
<v Andrew Rehm>We're really excited about it.

22
00:01:09.480 --> 00:01:10.529
<v Andrew Rehm>My name's Andrew Ream.

23
00:01:10.779 --> 00:01:14.540
<v Andrew Rehm>Um, I'm the director of reliability and
planning for Highland Pellets.

24
00:01:14.940 --> 00:01:20.419
<v Andrew Rehm>I've been with the company right at 2
years now, and I come from the oil and gas

25
00:01:20.419 --> 00:01:26.860
<v Andrew Rehm>industry, which we started working on
predictive maintenance about 10 years ago, so.

26
00:01:27.300 --> 00:01:33.089
<v Andrew Rehm>We make woody biomass pellets for the
energy market here in Arkansas and ship them

27
00:01:33.089 --> 00:01:35.930
<v Andrew Rehm>overseas for coal replacement actually.

28
00:01:36.220 --> 00:01:39.580
<v Andrew Rehm>So it's quite an interesting ecosystem
that we work in.

29
00:01:39.980 --> 00:01:40.050
<v Andrew Rehm>No,

30
00:01:40.110 --> 00:01:44.330
<v Speaker 3>it does, and I guess it's a little, little
bit off script straight away, but because

31
00:01:44.330 --> 00:01:47.580
<v Speaker 3>you mentioned you're doing predictive
maintenance 10 years ago, just to get your

32
00:01:47.580 --> 00:01:49.919
<v Speaker 3>thoughts on what's changed in that time,
and I guess there's one.

33
00:01:50.300 --> 00:01:54.139
<v Speaker 3>Particular technology that might influence
your answer, but yeah, just to get your

34
00:01:54.139 --> 00:01:55.599
<v Speaker 3>thoughts on that from your experience.

35
00:01:56.339 --> 00:02:02.150
<v Andrew Rehm>Yeah, I, I will say, so the first
predictive maintenance program that I worked on

36
00:02:02.300 --> 00:02:04.139
<v Andrew Rehm>was uh, on an offshore platform.

37
00:02:04.580 --> 00:02:09.580
<v Andrew Rehm>Obviously, having personnel on site on an
offshore platform in the middle of the

38
00:02:09.580 --> 00:02:14.649
<v Andrew Rehm>Gulf, it's very expensive and has its own
hazards associated with it.

39
00:02:14.899 --> 00:02:16.960
<v Andrew Rehm>So part of my group.

40
00:02:17.419 --> 00:02:20.039
<v Andrew Rehm>I was part of a continuous improvement
group there.

41
00:02:20.179 --> 00:02:26.899
<v Andrew Rehm>We started working on a project that used
just the raw data signals from all of

42
00:02:26.899 --> 00:02:33.339
<v Andrew Rehm>the temperature, pressure, everything that
we can read there in telemetry, and set

43
00:02:33.339 --> 00:02:38.970
<v Andrew Rehm>up a more progressive alarming system that
would generate a work order.

44
00:02:39.419 --> 00:02:44.660
<v Andrew Rehm>The biggest advancement From then till
now, obviously, is AI.

45
00:02:44.929 --> 00:02:51.339
<v Andrew Rehm>We did everything manually, so we went to
every control point and wrote in code to

46
00:02:51.339 --> 00:02:58.339
<v Andrew Rehm>say, if this pressure gets above this, and
the vibration is at this

47
00:02:58.339 --> 00:03:00.580
<v Andrew Rehm>level, then we want to know about it.

48
00:03:00.899 --> 00:03:04.940
<v Andrew Rehm>And we did that with every single thing we
could out on the plant.

49
00:03:05.380 --> 00:03:10.949
<v Andrew Rehm>Which meant going through hundreds of work
orders and looking at telemetry data at

50
00:03:10.949 --> 00:03:14.059
<v Andrew Rehm>the point of failure and then backing up
from there.

51
00:03:14.589 --> 00:03:20.619
<v Andrew Rehm>That project took around 10 people, about
a year and a half before we got our first

52
00:03:20.619 --> 00:03:21.259
<v Andrew Rehm>alert.

53
00:03:21.550 --> 00:03:26.929
<v Andrew Rehm>And it did eliminate some maintenance time
out on the, on the platform.

54
00:03:27.550 --> 00:03:33.509
<v Andrew Rehm>I believe they dropped 5 technicians that
had to be on site, but obviously, AI has

55
00:03:33.509 --> 00:03:34.729
<v Andrew Rehm>made that a huge.

56
00:03:35.210 --> 00:03:41.710
<v Andrew Rehm>Difference along with the Sensi technology
where the implementation for this project

57
00:03:41.850 --> 00:03:48.080
<v Andrew Rehm>took around 3 months and it was pretty
much myself and another technician that

58
00:03:48.080 --> 00:03:53.880
<v Andrew Rehm>worked on it and we got results pretty
much right away and a lot more results than

59
00:03:53.880 --> 00:03:58.169
<v Andrew Rehm>we did by manually going through there
because it picks up on things that you could

60
00:03:58.169 --> 00:04:00.990
<v Andrew Rehm>never imagine when you're looking through.

61
00:04:01.330 --> 00:04:05.089
<v Andrew Rehm>Work order history, you can imagine, for
years, so.

62
00:04:05.490 --> 00:04:06.490
<v Speaker 3>No, fantastic.

63
00:04:06.649 --> 00:04:10.929
<v Speaker 3>Yeah, and, and of course we're gonna dive
into, let's say, sen sizes impact at

64
00:04:11.149 --> 00:04:15.490
<v Speaker 3>Island Pets, but maybe just to open it up
to the audience a little bit, so, maybe

65
00:04:15.490 --> 00:04:20.250
<v Speaker 3>you could start by explaining the role
equipment reliability plays in your

66
00:04:20.250 --> 00:04:24.410
<v Speaker 3>particular environment, so in the pellet
mill and helping it operate most

67
00:04:24.410 --> 00:04:25.119
<v Speaker 3>effectively.

68
00:04:25.690 --> 00:04:29.630
<v Andrew Rehm>Yeah, it's, it's, it's a unique industry
because.

69
00:04:30.119 --> 00:04:35.880
<v Andrew Rehm>We have really dry fiber all throughout
and conveyance is our biggest issue, right?

70
00:04:36.079 --> 00:04:40.799
<v Andrew Rehm>Getting it from point A to point B,
breaking it down, resizing all the way

71
00:04:40.799 --> 00:04:41.420
<v Andrew Rehm>throughout.

72
00:04:41.760 --> 00:04:46.040
<v Andrew Rehm>And it's very dependent upon each point in
the process.

73
00:04:46.119 --> 00:04:49.140
<v Andrew Rehm>So we don't have a lot of redundancy built
into the system.

74
00:04:49.519 --> 00:04:50.920
<v Andrew Rehm>It's huge volumes.

75
00:04:51.079 --> 00:04:55.179
<v Andrew Rehm>We're, we're on track to do 600,000 tons
this year.

76
00:04:55.880 --> 00:05:02.660
<v Andrew Rehm>So, Reliability was one thing when I first
started with the company that we focused

77
00:05:02.660 --> 00:05:03.369
<v Andrew Rehm>on a lot.

78
00:05:03.579 --> 00:05:09.130
<v Andrew Rehm>We started doing downtime maintenance,
scheduling outages, stuff like that.

79
00:05:09.549 --> 00:05:16.230
<v Andrew Rehm>And where we're at now is really of how do
we manage our

80
00:05:16.230 --> 00:05:22.369
<v Andrew Rehm>uptime with predictive maintenance instead
of planned inspection maintenance.

81
00:05:22.700 --> 00:05:24.959
<v Andrew Rehm>So that's really where our focus is right
now.

82
00:05:25.390 --> 00:05:31.269
<v Andrew Rehm>An hour of downtime for us is around
$67,000 that we lose.

83
00:05:31.510 --> 00:05:34.609
<v Andrew Rehm>So, it's, it's huge difference.

84
00:05:34.750 --> 00:05:41.269
<v Andrew Rehm>So one outage is roughly $2 million that
we lose in, in production, but we gain that

85
00:05:41.269 --> 00:05:42.940
<v Andrew Rehm>back obviously in up time.

86
00:05:43.190 --> 00:05:47.630
<v Andrew Rehm>But it's something that, that's that last
10% that's really hard to get.

87
00:05:48.070 --> 00:05:49.750
<v Andrew Rehm>We started out at 60%.

88
00:05:50.209 --> 00:05:54.640
<v Andrew Rehm>Up time, when I started, we're at 89 right
now.

89
00:05:54.859 --> 00:06:01.290
<v Andrew Rehm>And it's really using this new sensors
that we just added on, hopefully, to get to

90
00:06:01.290 --> 00:06:04.809
<v Andrew Rehm>that 95% of time at the plant.

91
00:06:05.190 --> 00:06:08.429
<v Speaker 3>Yeah, I mean, it's amazing, yeah, you
actually took the, the question right out of

92
00:06:08.429 --> 00:06:09.630
<v Speaker 3>my mouth, cos I was gonna ask.

93
00:06:09.910 --> 00:06:11.829
<v Speaker 3>No, no, no, no, no need to apologize at
all.

94
00:06:11.950 --> 00:06:16.109
<v Speaker 3>It's just what I was thinking about the
impact of production stoppages and, and

95
00:06:16.109 --> 00:06:20.179
<v Speaker 3>that, and you've illustrated that
perfectly, that we're talking about 60 hours of

96
00:06:20.179 --> 00:06:24.589
<v Speaker 3>downtime, so I think people can do the
maths on this particular success case, right?

97
00:06:24.989 --> 00:06:25.149
<v Speaker 3>Yeah,

98
00:06:25.230 --> 00:06:30.109
<v Andrew Rehm>it's that particular case, we have 20
presses, so.

99
00:06:30.649 --> 00:06:35.850
<v Andrew Rehm>We dry the fiber, obviously chip it up
from round logs and break it down, run it

100
00:06:35.850 --> 00:06:40.049
<v Andrew Rehm>through a dryer, and then run it through
another hammer mill and into these pellet

101
00:06:40.049 --> 00:06:40.750
<v Andrew Rehm>presses.

102
00:06:41.170 --> 00:06:44.630
<v Andrew Rehm>We have 20 of them, so it's 60 hours on
that unit.

103
00:06:44.720 --> 00:06:47.269
<v Andrew Rehm>It wasn't plant-wide in that particular
case.

104
00:06:47.920 --> 00:06:51.760
<v Andrew Rehm>But we have had a couple of those events
as well that we've been able to detect.

105
00:06:52.170 --> 00:06:56.880
<v Andrew Rehm>But the main thing on that is just these
parts are, are hard to get sometimes on an

106
00:06:56.880 --> 00:06:58.549
<v Andrew Rehm>emergency basis.

107
00:06:59.059 --> 00:07:04.179
<v Andrew Rehm>So we would have lost it for probably
longer than that if we didn't have the parts

108
00:07:04.179 --> 00:07:05.760
<v Andrew Rehm>available to do the replacement.

109
00:07:06.320 --> 00:07:07.579
<v Andrew Rehm>Yeah, it's good fun.

110
00:07:07.980 --> 00:07:13.209
<v Speaker 3>No, no, exactly, no, definitely, and I
guess, just, just stepping back again,

111
00:07:13.220 --> 00:07:16.820
<v Speaker 3>because you, you've illustrated perfectly
that the significant savings have been

112
00:07:16.820 --> 00:07:20.459
<v Speaker 3>made by spotting these issues early, but
it all makes me think, what were you doing

113
00:07:20.459 --> 00:07:22.459
<v Speaker 3>before you had Sensa deployed?

114
00:07:22.720 --> 00:07:24.260
<v Speaker 3>How were maintenance decisions made?

115
00:07:24.299 --> 00:07:27.760
<v Speaker 3>You mentioned, obviously some planned
maintenance practices, but.

116
00:07:27.970 --> 00:07:31.690
<v Speaker 3>Yeah, clearly that was in, and you
mentioned about obviously trying to figure a.

117
00:07:31.980 --> 00:07:35.420
<v Speaker 3>You're, you're already making effective
decisions, but it's about those gains you

118
00:07:35.420 --> 00:07:37.660
<v Speaker 3>can make on top of that, I think you were
saying earlier.

119
00:07:37.859 --> 00:07:40.420
<v Speaker 3>So, yeah, so, yeah, what were you doing
before Sensai?

120
00:07:40.459 --> 00:07:41.369
<v Speaker 3>I guess simply.

121
00:07:42.019 --> 00:07:46.700
<v Andrew Rehm>Yeah, so, and, and, and we're changing
that schedule this year, but basically we

122
00:07:46.700 --> 00:07:51.700
<v Andrew Rehm>would bring the plant down and visually
inspect every piece of equipment 3 times a

123
00:07:51.700 --> 00:07:52.200
<v Andrew Rehm>year.

124
00:07:52.660 --> 00:07:59.019
<v Andrew Rehm>That took around 3 days each time we had
to go down to do that, to start up and

125
00:07:59.019 --> 00:07:59.959
<v Andrew Rehm>everything as well.

126
00:08:00.350 --> 00:08:07.209
<v Andrew Rehm>But yeah, our, our maintenance inspections
were our only early detector

127
00:08:07.390 --> 00:08:08.480
<v Andrew Rehm>of failures.

128
00:08:08.630 --> 00:08:13.350
<v Andrew Rehm>And we have around, oh, I wish I had that
number in front of me.

129
00:08:13.540 --> 00:08:16.220
<v Andrew Rehm>I, I think it was 8% return.

130
00:08:16.429 --> 00:08:22.609
<v Andrew Rehm>So while they were out doing inspections,
8% of the time, they found something that

131
00:08:22.910 --> 00:08:26.209
<v Andrew Rehm>needed to be repaired, which is not huge.

132
00:08:26.709 --> 00:08:33.190
<v Andrew Rehm>So really, it's Trying to get that up to a
percentage where it makes more sense to

133
00:08:33.190 --> 00:08:34.400
<v Andrew Rehm>bring the equipment down.

134
00:08:34.590 --> 00:08:39.750
<v Andrew Rehm>So we adjusted our time slots, how we did
inspections, all of the things that you

135
00:08:39.750 --> 00:08:41.369
<v Andrew Rehm>try to do to drive that up.

136
00:08:42.030 --> 00:08:49.030
<v Andrew Rehm>We got up to around 20% of accuracy, which
is still, that means 80% of the

137
00:08:49.030 --> 00:08:54.289
<v Andrew Rehm>equipment that we brought down did not
need to be brought down, but it's without

138
00:08:54.419 --> 00:08:56.510
<v Andrew Rehm>having the instrumentation in the live.

139
00:08:57.200 --> 00:09:02.869
<v Andrew Rehm>Feedback from it, you just, that's the
only option you have to prevent a

140
00:09:02.989 --> 00:09:06.599
<v Andrew Rehm>catastrophic failure that causes more
downtime.

141
00:09:07.049 --> 00:09:13.950
<v Andrew Rehm>So like I said, that's really my focus now
is how do we utilize this data and

142
00:09:14.250 --> 00:09:21.130
<v Andrew Rehm>start pulling away from some of those
planned outages and start reducing the

143
00:09:21.130 --> 00:09:23.080
<v Andrew Rehm>number of equipment that we look at during
them.

144
00:09:23.289 --> 00:09:29.020
<v Andrew Rehm>So, This year, I plan on bringing the
whole plant down 3 times, but 1 day apiece.

145
00:09:29.409 --> 00:09:34.619
<v Andrew Rehm>So that in itself is, is quite a large
change for the type of equipment that we're

146
00:09:34.619 --> 00:09:34.940
<v Andrew Rehm>looking at.

147
00:09:35.059 --> 00:09:39.739
<v Andrew Rehm>Some things obviously, you just have to
look inside and do structural inspections

148
00:09:39.739 --> 00:09:40.840
<v Andrew Rehm>and stuff like that.

149
00:09:41.179 --> 00:09:44.849
<v Andrew Rehm>But everything that we can, we're putting
sensors on and we're, we're loading those

150
00:09:44.849 --> 00:09:50.609
<v Andrew Rehm>into Sensi and using that to really
dictate when we need to bring that equipment

151
00:09:50.609 --> 00:09:51.020
<v Andrew Rehm>down.

152
00:09:51.400 --> 00:09:52.469
<v Speaker 3>Yeah, that makes it.

153
00:09:52.760 --> 00:09:57.539
<v Speaker 3>And, and I was wondering as well, because
you mentioned certain equipment requires

154
00:09:57.539 --> 00:09:59.280
<v Speaker 3>monitoring, maybe versus others.

155
00:09:59.330 --> 00:10:03.559
<v Speaker 3>So, it leads me to wonder, during the
initial deployment of Sens I, like, how did

156
00:10:03.559 --> 00:10:06.630
<v Speaker 3>you decide which areas of production to
focus on first?

157
00:10:06.840 --> 00:10:11.320
<v Speaker 3>Of course, it was in collaboration with
the Siemens team as well, but just to, just

158
00:10:11.320 --> 00:10:13.549
<v Speaker 3>to understand that decision process as
well.

159
00:10:14.000 --> 00:10:17.989
<v Andrew Rehm>Yeah, so, what we looked at first was our
highest criticality.

160
00:10:18.080 --> 00:10:20.960
<v Andrew Rehm>We do an annual criticality assessment on
each asset.

161
00:10:21.419 --> 00:10:27.630
<v Andrew Rehm>And we looked at what impacts it has
safety, financial, and production.

162
00:10:27.979 --> 00:10:31.349
<v Andrew Rehm>And then also the frequency of failures.

163
00:10:31.570 --> 00:10:37.580
<v Andrew Rehm>So we take those into consideration and
basically rank every piece of equipment by

164
00:10:37.580 --> 00:10:38.409
<v Andrew Rehm>criticality.

165
00:10:38.580 --> 00:10:43.159
<v Andrew Rehm>We took the highest criticality equipment,
and then I went through it with our

166
00:10:43.739 --> 00:10:49.549
<v Andrew Rehm>maintenance manager that's on site and
looked at What sensors do we currently have,

167
00:10:49.830 --> 00:10:55.030
<v Andrew Rehm>and what sensors could we put in place
where we actually felt that we can detect a

168
00:10:55.030 --> 00:10:56.390
<v Andrew Rehm>failure on there.

169
00:10:56.469 --> 00:11:01.109
<v Andrew Rehm>So bearings were our first major
implementation.

170
00:11:01.190 --> 00:11:08.070
<v Andrew Rehm>A lot of high speed fans, low speed
bearings on our feeder screws, stuff

171
00:11:08.070 --> 00:11:08.729
<v Andrew Rehm>like that.

172
00:11:09.109 --> 00:11:15.760
<v Andrew Rehm>And then we went into Bass plate vibration
on our hammer mills,

173
00:11:15.880 --> 00:11:22.719
<v Andrew Rehm>so high speed hammer mills, green and dry,
and that, that was our

174
00:11:22.719 --> 00:11:23.780
<v Andrew Rehm>first round.

175
00:11:24.070 --> 00:11:30.239
<v Andrew Rehm>And then we looked at the decline in
failure rates after that, and decided to go

176
00:11:30.239 --> 00:11:33.109
<v Andrew Rehm>with the next group, which was the pellet
presses themselves.

177
00:11:33.599 --> 00:11:37.510
<v Andrew Rehm>We had some instrumentation on there, but
everything was set up basically as an

178
00:11:37.510 --> 00:11:38.440
<v Andrew Rehm>alarm basis.

179
00:11:39.070 --> 00:11:45.710
<v Andrew Rehm>So trying to get more of the early
identification of a failure before it

180
00:11:45.710 --> 00:11:46.309
<v Andrew Rehm>fails.

181
00:11:46.710 --> 00:11:51.070
<v Andrew Rehm>Historically, it just shut the equipment
down, so it didn't damage anything else,

182
00:11:51.150 --> 00:11:52.590
<v Andrew Rehm>and we would go fix it then.

183
00:11:53.070 --> 00:11:58.340
<v Andrew Rehm>One good example of that that we found
during the first round, and it was within a

184
00:11:58.340 --> 00:12:04.989
<v Andrew Rehm>couple of weeks of starting the project,
was a large bearing on our RTO

185
00:12:04.989 --> 00:12:08.460
<v Andrew Rehm>fan that would have caused the whole plant
to go down.

186
00:12:08.900 --> 00:12:11.510
<v Andrew Rehm>And it's very expensive bearing, as you
can imagine.

187
00:12:11.750 --> 00:12:14.979
<v Andrew Rehm>It's a, I think it's a sixty-inch fan.

188
00:12:15.469 --> 00:12:20.830
<v Andrew Rehm>It's quite large, and it moves the air
through the dryers to allow for the drying to

189
00:12:20.830 --> 00:12:21.750
<v Andrew Rehm>occur, obviously.

190
00:12:22.190 --> 00:12:28.929
<v Andrew Rehm>But that picked up a, we had put sensors
on it and picked up a small vibration

191
00:12:29.789 --> 00:12:32.450
<v Andrew Rehm>that changed from the inboard to the
outboard.

192
00:12:32.549 --> 00:12:37.270
<v Andrew Rehm>So typically, your inboard bearing is
gonna have a little bit more vibration.

193
00:12:37.840 --> 00:12:40.890
<v Andrew Rehm>Then you're outboard just because it's the
driven bearing.

194
00:12:41.400 --> 00:12:47.960
<v Andrew Rehm>And when that vibration switched from the
outboard being the highest to the inboard

195
00:12:47.960 --> 00:12:52.520
<v Andrew Rehm>being the highest, we got an alarm from
that, from SensIi, and we sent a technician

196
00:12:52.520 --> 00:12:52.979
<v Andrew Rehm>out there.

197
00:12:53.559 --> 00:12:59.000
<v Andrew Rehm>And it was one of those things that they
had done maintenance on the oiler system

198
00:12:59.000 --> 00:13:04.119
<v Andrew Rehm>for that bearing and trash had gotten in
there and just stopped it up.

199
00:13:04.239 --> 00:13:06.679
<v Andrew Rehm>So it just wasn't lubricating the bearing.

200
00:13:07.150 --> 00:13:12.630
<v Andrew Rehm>So we were able to fix that, but after
looking at it, we determined that that

201
00:13:12.630 --> 00:13:18.229
<v Andrew Rehm>bearing would have failed within the next
like 48 hours if we hadn't have found that

202
00:13:18.229 --> 00:13:19.109
<v Andrew Rehm>greasing issue.

203
00:13:19.229 --> 00:13:21.979
<v Andrew Rehm>So it's, that was a huge win right off the
bat.

204
00:13:22.109 --> 00:13:25.630
<v Andrew Rehm>And then we've had several more like that
throughout the plant.

205
00:13:26.169 --> 00:13:30.010
<v Andrew Rehm>One thing, uh, sorry, I keep just rambling
into the next, but no,

206
00:13:30.130 --> 00:13:31.210
<v Speaker 3>no, it's good,

207
00:13:31.549 --> 00:13:32.049
<v Andrew Rehm>it's good.

208
00:13:32.530 --> 00:13:38.969
<v Andrew Rehm>One thing that we found early on was that
it wasn't just maintenance

209
00:13:38.969 --> 00:13:41.190
<v Andrew Rehm>issues that we found.

210
00:13:41.609 --> 00:13:48.119
<v Andrew Rehm>We have feeder screws that feed from a
hopper into our hammer mills, and then they

211
00:13:48.119 --> 00:13:49.299
<v Andrew Rehm>feed out from there.

212
00:13:49.719 --> 00:13:51.859
<v Andrew Rehm>And we kept getting alerts.

213
00:13:52.460 --> 00:13:58.229
<v Andrew Rehm>For RPM on those feeder screws, and they
are adjusted by the driven equipment.

214
00:13:58.380 --> 00:14:04.900
<v Andrew Rehm>So if the mill itself isn't getting enough
feed, then it speeds

215
00:14:04.900 --> 00:14:08.640
<v Andrew Rehm>up the screws and then slows them down,
vice versa, right?

216
00:14:09.020 --> 00:14:11.859
<v Andrew Rehm>And what we found was a mismatch.

217
00:14:12.020 --> 00:14:17.419
<v Andrew Rehm>So the mill was calling for more feed, the
screws were speeding up.

218
00:14:18.059 --> 00:14:19.140
<v Andrew Rehm>But they weren't stopping.

219
00:14:19.179 --> 00:14:23.429
<v Andrew Rehm>They were maxing out, and the mill was
still calling for more feed.

220
00:14:23.859 --> 00:14:28.219
<v Andrew Rehm>And at first we didn't know exactly what
was going on, so it took us a, I think we

221
00:14:28.219 --> 00:14:32.719
<v Andrew Rehm>went out and looked at it 3 times,
thinking that it was a screw issue.

222
00:14:33.190 --> 00:14:36.280
<v Andrew Rehm>So we took the bin apart, looked at the
screw, nothing was there.

223
00:14:36.659 --> 00:14:41.739
<v Andrew Rehm>And what we ended up figuring out out of
that was, it was actually the screens on

224
00:14:41.739 --> 00:14:43.400
<v Andrew Rehm>the bottom of the hammer mill.

225
00:14:43.750 --> 00:14:48.429
<v Andrew Rehm>We had a hole in, a piece of concrete that
went through there and blown a hole out

226
00:14:48.429 --> 00:14:49.429
<v Andrew Rehm>of that screen.

227
00:14:49.830 --> 00:14:55.409
<v Andrew Rehm>And it was, I, I guess it's maintenance
fixed it, but it was really something that

228
00:14:55.630 --> 00:15:00.859
<v Andrew Rehm>should have been picked up by our PSD, our
particle size coming out of that hammer

229
00:15:00.859 --> 00:15:01.330
<v Andrew Rehm>mill.

230
00:15:01.719 --> 00:15:06.109
<v Andrew Rehm>So we set an alarm for that and we've
actually been able to find about 12 of those.

231
00:15:06.400 --> 00:15:12.330
<v Andrew Rehm>So, We find them before our quality does,
just by monitoring that alarm and setting

232
00:15:12.330 --> 00:15:17.969
<v Andrew Rehm>up that condition to say, hey, if this is
still calling for feed and it's at max RP

233
00:15:17.969 --> 00:15:22.119
<v Andrew Rehm>create a notification in our system for us
to go out and look at it.

234
00:15:22.530 --> 00:15:27.750
<v Andrew Rehm>So that was one interesting thing that
just happened that we didn't expect as well.

235
00:15:28.130 --> 00:15:34.960
<v Andrew Rehm>And we've taken that now into our pellet
presses where we're Our next

236
00:15:34.960 --> 00:15:38.830
<v Andrew Rehm>phase of this will be adding sensors to
the rolls itself.

237
00:15:39.169 --> 00:15:44.049
<v Andrew Rehm>So you have two rolls in there and a die
that presses the wood through where we're

238
00:15:44.049 --> 00:15:46.450
<v Andrew Rehm>looking at roll adjustments.

239
00:15:46.650 --> 00:15:52.989
<v Andrew Rehm>We've done some small scale testing on
that, and you can pick up the vibration of

240
00:15:52.989 --> 00:15:55.830
<v Andrew Rehm>that roll losing contact with the die.

241
00:15:56.369 --> 00:16:01.330
<v Andrew Rehm>And that's our next phase is right now we
have people that go out there and shut

242
00:16:01.330 --> 00:16:06.409
<v Andrew Rehm>down the presses, open them up, look at
them every day, and we're trying to use this

243
00:16:06.409 --> 00:16:12.049
<v Andrew Rehm>instrumentation to, to do away with that
inspection and just use the vibration

244
00:16:12.049 --> 00:16:12.960
<v Andrew Rehm>sensors on it.

245
00:16:13.369 --> 00:16:14.960
<v Andrew Rehm>So sorry, I went on a bit of a tangent.

246
00:16:15.460 --> 00:16:20.539
<v Speaker 3>No, no, no, no, no, if you, I always say,
if you're talking more than me, that's

247
00:16:20.539 --> 00:16:21.919
<v Speaker 3>always, that's always a good sign.

248
00:16:22.460 --> 00:16:27.059
<v Speaker 3>So, no, it's pretty, but I think what,
what's really interesting though, and, and to

249
00:16:27.059 --> 00:16:32.059
<v Speaker 3>me, just hearing you talk, Andrew, is how,
cos a lot of the time, the adoption of

250
00:16:32.059 --> 00:16:36.340
<v Speaker 3>tools like Senites, how maintenance teams
trust the, the.

251
00:16:36.669 --> 00:16:40.200
<v Speaker 3>The insights it's providing, right, and
actually taking action on it, but it seems

252
00:16:40.200 --> 00:16:45.520
<v Speaker 3>like on your side, that, that seemed to
happen quite quickly in terms of trusting

253
00:16:45.520 --> 00:16:48.679
<v Speaker 3>the system, right, and what it's, what
it's advising.

254
00:16:49.119 --> 00:16:51.070
<v Speaker 3>So, interested to get your thoughts on
that.

255
00:16:51.109 --> 00:16:51.419
<v Speaker 3>Yeah,

256
00:16:51.840 --> 00:16:56.719
<v Andrew Rehm>yeah, obviously we had some pushback at,
at the beginning, is it gonna take my job

257
00:16:56.719 --> 00:17:00.960
<v Andrew Rehm>away or is it gonna, gonna be accurate,
are we just gonna be chasing our tails, all

258
00:17:00.960 --> 00:17:02.200
<v Andrew Rehm>of those kind of comments.

259
00:17:02.640 --> 00:17:05.989
<v Andrew Rehm>And, and understandably so until it's
proven.

260
00:17:06.280 --> 00:17:13.239
<v Andrew Rehm>But once we had a couple of major finds
throughout this, the guys became a

261
00:17:13.239 --> 00:17:14.689
<v Andrew Rehm>lot more trusting in it.

262
00:17:14.959 --> 00:17:20.209
<v Andrew Rehm>And I honestly, I, I became better at
reading the information from SensI.

263
00:17:20.989 --> 00:17:25.560
<v Andrew Rehm>So knowing what was a false alarm before
we sent somebody out there helped quite a

264
00:17:25.560 --> 00:17:26.420
<v Andrew Rehm>bit as well.

265
00:17:26.920 --> 00:17:31.780
<v Andrew Rehm>And then now we have our on-site planners
are going through that data.

266
00:17:32.250 --> 00:17:39.170
<v Andrew Rehm>And we just did an integration with our
CMMS system where since I will

267
00:17:39.170 --> 00:17:44.640
<v Andrew Rehm>create a case and it creates a work
request in our CMMS so the planners can look at

268
00:17:44.640 --> 00:17:50.670
<v Andrew Rehm>it directly in there and issue it out from
the CMMS system into a work order.

269
00:17:51.060 --> 00:17:52.719
<v Andrew Rehm>So it gets them more involved in it.

270
00:17:53.089 --> 00:17:59.849
<v Andrew Rehm>I think we're right now we're at 63.5%
accuracy on

271
00:17:59.849 --> 00:18:00.420
<v Andrew Rehm>cases.

272
00:18:00.959 --> 00:18:02.800
<v Andrew Rehm>We were a little higher than that.

273
00:18:02.920 --> 00:18:08.670
<v Andrew Rehm>We were running around 80%, and then we
added an additional 100 assets.

274
00:18:08.880 --> 00:18:11.800
<v Andrew Rehm>So we're back in that training period for
them right now.

275
00:18:12.709 --> 00:18:19.339
<v Andrew Rehm>But overall we're at that 63% accuracy,
which is fair to do on this scale.

276
00:18:19.479 --> 00:18:24.800
<v Andrew Rehm>We have a right at 200 assets that we're
measuring right now are monitoring out of

277
00:18:24.800 --> 00:18:26.109
<v Andrew Rehm>our 700 total.

278
00:18:26.319 --> 00:18:26.640
<v Andrew Rehm>So,

279
00:18:27.040 --> 00:18:30.400
<v Speaker 3>and yeah, I guess another, another,
another point that, that picked up.

280
00:18:30.500 --> 00:18:34.959
<v Speaker 3>Up On is how between all the various
teams, reliability, operations, maintenance,

281
00:18:35.239 --> 00:18:39.319
<v Speaker 3>there seems to be a lot really close
collaboration, but there, there must have been

282
00:18:39.319 --> 00:18:43.400
<v Speaker 3>before, of course, but this, how has it
changed the way you, you all work together?

283
00:18:43.790 --> 00:18:47.479
<v Speaker 3>Because it's not, as we always say, it's
not just a technology deployment, it's a, a

284
00:18:47.479 --> 00:18:50.579
<v Speaker 3>change within the organization as well,

285
00:18:50.959 --> 00:18:51.300
<v Andrew Rehm>right?

286
00:18:51.520 --> 00:18:52.810
<v Andrew Rehm>Yeah, for sure.

287
00:18:53.280 --> 00:19:00.000
<v Andrew Rehm>We've, we've been able to use the data
collected to Encourage and give access to

288
00:19:00.000 --> 00:19:06.520
<v Andrew Rehm>everyone that wants it or that needs it in
the, in the plant to really understand

289
00:19:06.979 --> 00:19:12.739
<v Andrew Rehm>that we need to be more of a data-driven
mindset on maintenance, it's especially and

290
00:19:12.739 --> 00:19:13.880
<v Andrew Rehm>on operations.

291
00:19:14.380 --> 00:19:19.099
<v Andrew Rehm>We had, we still have a lot of really good
employees that have been there for a long

292
00:19:19.099 --> 00:19:22.219
<v Andrew Rehm>time, so they know they have the knowledge
inside of them.

293
00:19:22.339 --> 00:19:27.270
<v Andrew Rehm>So we encourage them to be part of this
implementation and really help.

294
00:19:27.689 --> 00:19:29.500
<v Andrew Rehm>Identify issues.

295
00:19:29.910 --> 00:19:36.130
<v Andrew Rehm>So if we got an alert from SEI, we
encourage those well-respected

296
00:19:36.390 --> 00:19:42.810
<v Andrew Rehm>long-term employees to go out and do the
analysis in the field

297
00:19:43.030 --> 00:19:46.750
<v Andrew Rehm>and correlate it to those measurements
that we got back from SensI.

298
00:19:47.829 --> 00:19:53.170
<v Andrew Rehm>And that really brought on a lot more
buy-in from those technicians.

299
00:19:53.660 --> 00:19:58.130
<v Andrew Rehm>Because they feel like they're not just
being replaced by AI, it's a tool for them

300
00:19:58.660 --> 00:20:00.729
<v Andrew Rehm>to be better at their job as well.

301
00:20:01.430 --> 00:20:03.310
<v Andrew Rehm>And then the benefits of it, right?

302
00:20:03.469 --> 00:20:07.829
<v Andrew Rehm>So any downtime avoidance is, is better
for the company.

303
00:20:07.900 --> 00:20:11.949
<v Andrew Rehm>It's better for the employee, and you
started a bonus program to help with that as

304
00:20:11.949 --> 00:20:12.410
<v Andrew Rehm>well.

305
00:20:12.829 --> 00:20:17.290
<v Andrew Rehm>So they're just as invested as, as I am in
making sure that this works.

306
00:20:17.750 --> 00:20:21.869
<v Speaker 3>And you mentioned that they beyond, we've
talked about avoiding downtime and of

307
00:20:21.869 --> 00:20:26.910
<v Speaker 3>course, this success case that brought us
together is a significant downtime saving,

308
00:20:26.989 --> 00:20:32.949
<v Speaker 3>but in terms of what other, what big
difference Sensai has made in terms of

309
00:20:32.949 --> 00:20:36.469
<v Speaker 3>planning, how, how you allocate resources,
and I think you've touched upon some of

310
00:20:36.469 --> 00:20:41.989
<v Speaker 3>it already, Andrew, in terms of when to go
and investigate something versus not and

311
00:20:41.989 --> 00:20:42.550
<v Speaker 3>these kind of things.

312
00:20:42.630 --> 00:20:44.569
<v Speaker 3>But yeah, so beyond downtime, is there.

313
00:20:45.069 --> 00:20:49.030
<v Speaker 3>Other real standout benefits of utilizing
Sensai.

314
00:20:49.550 --> 00:20:56.209
<v Andrew Rehm>Yeah, so our, which obviously downtime,
but breaking work, as you're aware,

315
00:20:56.349 --> 00:21:00.079
<v Andrew Rehm>obviously is just supremely inefficient.

316
00:21:00.189 --> 00:21:06.829
<v Andrew Rehm>It's, we had a huge amount of break-in
work when we first started with this, and

317
00:21:06.829 --> 00:21:13.790
<v Andrew Rehm>what it's allowed us to do overall on the,
on the 200 assets that we Monitor is,

318
00:21:13.800 --> 00:21:20.760
<v Andrew Rehm>it typically gives us about 2.5 to 3 weeks
to plan, get materials in, and,

319
00:21:20.880 --> 00:21:24.380
<v Andrew Rehm>and move that into planned predictive
work.

320
00:21:24.839 --> 00:21:30.800
<v Andrew Rehm>And I'm looking at some numbers here, and
obviously, this is just on a couple of

321
00:21:30.800 --> 00:21:37.239
<v Andrew Rehm>pieces of equipment, but our break-in rate
was, for one year was around

322
00:21:37.239 --> 00:21:40.520
<v Andrew Rehm>$135,000 on one piece of equipment.

323
00:21:41.060 --> 00:21:43.420
<v Andrew Rehm>And we still have those failures.

324
00:21:43.459 --> 00:21:50.380
<v Andrew Rehm>Obviously, that doesn't eliminate a, a
failure, but what it did was moved all

325
00:21:50.380 --> 00:21:56.520
<v Andrew Rehm>of those failures, but I think 32,000 of
break-in is all we had

326
00:21:56.859 --> 00:21:58.849
<v Andrew Rehm>after we implemented the system.

327
00:21:59.260 --> 00:22:02.949
<v Andrew Rehm>So it just gives us that efficiency on the
repair side.

328
00:22:03.329 --> 00:22:08.140
<v Andrew Rehm>And a knowledge going into the problem
where it's not just the equipment shut down.

329
00:22:08.530 --> 00:22:11.400
<v Andrew Rehm>Let's go spend an hour figuring out what
it is.

330
00:22:11.969 --> 00:22:16.930
<v Andrew Rehm>When we get an alert early on, we know
what the issue is.

331
00:22:17.410 --> 00:22:22.770
<v Andrew Rehm>Typically, it'll identify the very bearing
that's going out, and it really just

332
00:22:22.770 --> 00:22:24.589
<v Andrew Rehm>makes my planner's job easier.

333
00:22:24.770 --> 00:22:28.930
<v Andrew Rehm>They can get all everything together
before they send the first technician out to go

334
00:22:28.930 --> 00:22:29.810
<v Andrew Rehm>work on that equipment.

335
00:22:30.239 --> 00:22:33.109
<v Andrew Rehm>So everybody's a little happy with it.

336
00:22:33.520 --> 00:22:35.520
<v Speaker 3>No, well, that's, that's what, that's what
we'd like to hear.

337
00:22:35.640 --> 00:22:39.719
<v Speaker 3>I was, I was also gonna comment on the,
the fact, that was an interesting point you

338
00:22:39.719 --> 00:22:44.479
<v Speaker 3>made about investigating something and,
and fixing it and stuff, but what happens to

339
00:22:44.479 --> 00:22:45.439
<v Speaker 3>the knowledge afterwards?

340
00:22:45.479 --> 00:22:48.569
<v Speaker 3>When you, you fix something, you want to
retain that knowledge for next time, right?

341
00:22:48.640 --> 00:22:50.239
<v Speaker 3>When there's similar cases and things like
that.

342
00:22:50.310 --> 00:22:52.589
<v Speaker 3>Has it, has it helped from that
perspective as well?

343
00:22:52.800 --> 00:22:56.479
<v Speaker 3>Yeah, capturing the knowledge of that
particular case and closing it, and then you

344
00:22:56.479 --> 00:22:59.680
<v Speaker 3>can use that again for future similar
cases to obviously speed up.

345
00:23:00.280 --> 00:23:00.979
<v Speaker 3>Maintaining

346
00:23:01.469 --> 00:23:01.560
<v Andrew Rehm>in the future.

347
00:23:02.079 --> 00:23:06.160
<v Andrew Rehm>Absolutely, yeah, one of the things that I
really liked, and it was, I can't

348
00:23:06.160 --> 00:23:09.280
<v Andrew Rehm>remember when it rolled out a couple of
months ago, it may have been longer than

349
00:23:09.280 --> 00:23:09.680
<v Andrew Rehm>that.

350
00:23:10.119 --> 00:23:15.760
<v Andrew Rehm>And since I, obviously it, it takes the
feedback from the work orders, which that,

351
00:23:15.920 --> 00:23:20.040
<v Andrew Rehm>that's been a, a struggle to get guys to
fill in the information back in the work

352
00:23:20.040 --> 00:23:21.859
<v Andrew Rehm>orders, but we're getting there,
obviously.

353
00:23:22.040 --> 00:23:23.140
<v Andrew Rehm>I think that's pretty common.

354
00:23:24.239 --> 00:23:30.750
<v Andrew Rehm>But it gives you a percentage on the case
of what it historically has been,

355
00:23:31.150 --> 00:23:36.439
<v Andrew Rehm>and that we found is quite accurate if we
get good feedback in the system from

356
00:23:36.439 --> 00:23:36.810
<v Andrew Rehm>there.

357
00:23:37.280 --> 00:23:41.020
<v Andrew Rehm>And it's one of the features I really like
when we get those cases.

358
00:23:41.079 --> 00:23:47.030
<v Andrew Rehm>Again, it's not just this bearings making
this vibration, it's, hey, last time we

359
00:23:47.030 --> 00:23:48.290
<v Andrew Rehm>had the same issue.

360
00:23:48.839 --> 00:23:53.459
<v Andrew Rehm>Here's what happened, and here's the parts
that we used because it's linked into our

361
00:23:54.079 --> 00:23:55.270
<v Andrew Rehm>CMMS system.

362
00:23:55.599 --> 00:24:01.199
<v Andrew Rehm>I can pull up that work order and, and
say, look, this is the last time you went and

363
00:24:01.199 --> 00:24:01.630
<v Andrew Rehm>fixed it.

364
00:24:01.680 --> 00:24:04.060
<v Andrew Rehm>Here are the parts you needed, here's how
long it took.

365
00:24:04.520 --> 00:24:10.680
<v Andrew Rehm>So, yeah, the, the feedback loop back in
the sense I and it understanding that and

366
00:24:10.680 --> 00:24:15.420
<v Andrew Rehm>being able to feed it into the next case
that happens on that equipment has been a

367
00:24:15.599 --> 00:24:17.119
<v Andrew Rehm>game changer for us for sure.

368
00:24:17.479 --> 00:24:18.260
<v Speaker 3>Oh, fantastic.

369
00:24:18.520 --> 00:24:19.869
<v Speaker 3>Yeah, they're really good.

370
00:24:20.359 --> 00:24:25.000
<v Speaker 3>So, we're coming, coming towards the end
of our chat now, but what I wanted to, to

371
00:24:25.000 --> 00:24:29.680
<v Speaker 3>ask, so one thing I didn't mention before
we recorded is actually, we got recently

372
00:24:29.680 --> 00:24:35.650
<v Speaker 3>introduced to, the mini quickfire round,
and nothing too strenuous, it's, yeah, free

373
00:24:35.650 --> 00:24:36.920
<v Speaker 3>question off top of your head.

374
00:24:36.959 --> 00:24:40.319
<v Speaker 3>But before, before we do that, just, just
to reflect a little bit on the deployment

375
00:24:40.319 --> 00:24:43.280
<v Speaker 3>so far, it's fantastic to hear about all
the success you've.

376
00:24:43.599 --> 00:24:47.760
<v Speaker 3>You've mentioned today, substantial
success, and not just in terms of the, some of

377
00:24:47.760 --> 00:24:51.319
<v Speaker 3>the numbers and the savings, but also just
the adoption of the, the team, I think

378
00:24:51.319 --> 00:24:54.339
<v Speaker 3>is, for me, personally, quite, quite
inspiring as well.

379
00:24:55.040 --> 00:24:59.160
<v Speaker 3>But if you were to do the deployment from
scratch again, and it's very easy to look

380
00:24:59.160 --> 00:25:02.510
<v Speaker 3>back in hindsight, of course, but if you
were to do it again, would you do anything

381
00:25:02.510 --> 00:25:05.640
<v Speaker 3>differently, and, or what things would you
do differently, because I'm sure there

382
00:25:05.640 --> 00:25:07.079
<v Speaker 3>are maybe a few things.

383
00:25:07.160 --> 00:25:07.660
<v Speaker 3>Yeah,

384
00:25:08.160 --> 00:25:11.099
<v Andrew Rehm>yeah, and it's an interesting question
because I'm.

385
00:25:11.609 --> 00:25:14.609
<v Andrew Rehm>Working on an implementation at our other
plant as well.

386
00:25:14.890 --> 00:25:16.780
<v Andrew Rehm>So we are gonna get to do it again.

387
00:25:17.150 --> 00:25:17.459
<v Andrew Rehm>Oh, there we go.

388
00:25:18.250 --> 00:25:24.569
<v Andrew Rehm>So one, now that we, we have a better
grasp on what equipment gives us the best

389
00:25:24.569 --> 00:25:28.839
<v Andrew Rehm>feedback, we're working through a more
accurate list for our other plant.

390
00:25:29.290 --> 00:25:34.189
<v Andrew Rehm>We, we loaded a bunch of assets during the
first side that we're just not.

391
00:25:34.550 --> 00:25:39.030
<v Andrew Rehm>They're not well suited for the program,
real slow conveyance, stuff like that.

392
00:25:39.329 --> 00:25:42.489
<v Andrew Rehm>So we have a better return idea on that.

393
00:25:42.839 --> 00:25:49.540
<v Andrew Rehm>And then the other thing that I would do
is bring in the people that are going to be

394
00:25:49.540 --> 00:25:53.160
<v Andrew Rehm>long-term users of it earlier in the
process.

395
00:25:53.670 --> 00:25:57.890
<v Andrew Rehm>And what I'm doing for this other plant
now is bringing in.

396
00:25:58.329 --> 00:26:03.680
<v Andrew Rehm>The maintenance team now to help do the
analysis behind the failures of the

397
00:26:03.680 --> 00:26:07.699
<v Andrew Rehm>equipment, even before we put the sensors
out there.

398
00:26:08.170 --> 00:26:12.290
<v Andrew Rehm>Just so everyone's aware of kind of our
failure rate of that equipment.

399
00:26:12.650 --> 00:26:18.890
<v Andrew Rehm>And I think it'll help give us a better
buy-in right off the bat when they start to

400
00:26:18.890 --> 00:26:22.280
<v Andrew Rehm>see that, that rate decline over time.

401
00:26:22.650 --> 00:26:26.969
<v Andrew Rehm>So that, those are the two biggest things
that we learned from the first

402
00:26:26.969 --> 00:26:27.969
<v Andrew Rehm>implementation.

403
00:26:28.339 --> 00:26:31.660
<v Speaker 3>And, yeah, that's fantastic, you're
looking at scale even further.

404
00:26:31.739 --> 00:26:36.459
<v Speaker 3>Is there, and yeah, of course, you wanna
replicate a lot of the success you've had

405
00:26:36.459 --> 00:26:39.520
<v Speaker 3>already, but it's a, is it, what would you
like to take further?

406
00:26:39.579 --> 00:26:43.430
<v Speaker 3>Or what other areas would you like to
explore with Sensai?

407
00:26:43.619 --> 00:26:43.900
<v Andrew Rehm>Yeah.

408
00:26:44.260 --> 00:26:48.339
<v Andrew Rehm>So, yeah, like I said, we've got a couple
of phases from the maintenance side we're

409
00:26:48.339 --> 00:26:54.020
<v Andrew Rehm>looking at, obviously, downtime avoidance,
and we're removing some of our downtime

410
00:26:54.020 --> 00:26:57.260
<v Andrew Rehm>PMs and spreading those out over longer
periods.

411
00:26:57.729 --> 00:27:04.050
<v Andrew Rehm>But the next thing that we're really
looking into is more of the operational side of

412
00:27:04.050 --> 00:27:09.430
<v Andrew Rehm>our system and utilizing it for, like I
said, role adjustments.

413
00:27:09.770 --> 00:27:15.489
<v Andrew Rehm>It's not necessarily things that are going
to cause a failure, but would reduce

414
00:27:15.489 --> 00:27:18.829
<v Andrew Rehm>production out of each individual piece of
equipment.

415
00:27:19.209 --> 00:27:24.589
<v Andrew Rehm>So we're looking at hammer changes being
driven by data from SensI

416
00:27:25.930 --> 00:27:30.060
<v Andrew Rehm>because We've noticed that we can pick
that up through the system.

417
00:27:30.680 --> 00:27:37.560
<v Andrew Rehm>And so we've got a uh INE team that is
working on getting some of the more detailed

418
00:27:37.560 --> 00:27:43.459
<v Andrew Rehm>programming stuff complete now so that we
can get better readings to feed into

419
00:27:43.459 --> 00:27:43.810
<v Andrew Rehm>Sensei for that.

420
00:27:45.189 --> 00:27:49.709
<v Andrew Rehm>But yeah, I, I think that's gonna be huge
for our operations team as well, to be

421
00:27:49.709 --> 00:27:50.790
<v Andrew Rehm>able to utilize it.

422
00:27:51.069 --> 00:27:51.189
<v Andrew Rehm>Oh,

423
00:27:51.310 --> 00:27:51.750
<v Speaker 3>fantastic.

424
00:27:51.949 --> 00:27:56.550
<v Speaker 3>Well, I wish you every success with the,
the scaling, and hope, hopefully, yeah, the

425
00:27:56.550 --> 00:27:58.229
<v Speaker 3>trajectory just continues to accelerate.

426
00:27:58.349 --> 00:28:00.469
<v Speaker 3>So, you've, like I said, you've achieved
so much so far.

427
00:28:00.540 --> 00:28:02.010
<v Speaker 3>It's really fantastic.

428
00:28:14.949 --> 00:28:19.949
<v Speaker 3>So, so, yeah, so, like I said, we're gonna
end with 3 very sort of simple questions.

429
00:28:20.930 --> 00:28:25.739
<v Speaker 3>The idea generally is to very short and
sharp answers, but we're flexible, so it's

430
00:28:25.739 --> 00:28:26.089
<v Speaker 3>fine.

431
00:28:26.430 --> 00:28:27.430
<v Speaker 3>But yeah, so 3 questions.

432
00:28:27.579 --> 00:28:32.020
<v Speaker 3>So, the first one, so, what is, what is
the biggest benefit Sensi delivered for

433
00:28:32.020 --> 00:28:35.989
<v Speaker 3>Highland pellets in one word or phrase, if
you can narrow it down?

434
00:28:36.430 --> 00:28:36.469
<v Speaker 3>It,

435
00:28:36.989 --> 00:28:41.310
<v Andrew Rehm>it's really just moving towards predictive
maintenance instead of shutdown

436
00:28:41.310 --> 00:28:41.890
<v Andrew Rehm>maintenance.

437
00:28:42.339 --> 00:28:43.819
<v Speaker 3>Excellent, that's good.

438
00:28:44.060 --> 00:28:50.099
<v Speaker 3>And what is one piece of advice you'd give
to another, say, manufacturer or starting

439
00:28:50.099 --> 00:28:54.609
<v Speaker 3>its predicting maintenance journey for
another organization, let's say.

440
00:28:54.900 --> 00:28:55.310
<v Speaker 3>I,

441
00:28:55.959 --> 00:29:01.900
<v Andrew Rehm>it would just adopt it as soon as you can,
as soon as it makes sense for your

442
00:29:01.900 --> 00:29:02.670
<v Andrew Rehm>business.

443
00:29:03.099 --> 00:29:03.800
<v Andrew Rehm>It's scary.

444
00:29:04.489 --> 00:29:10.130
<v Andrew Rehm>To spend a lot of money on something that
is different from the historical way that

445
00:29:10.130 --> 00:29:15.560
<v Andrew Rehm>we've done maintenance, but it's certainly
a result-driven investment that we've

446
00:29:15.560 --> 00:29:16.869
<v Andrew Rehm>really seen the results from.

447
00:29:17.489 --> 00:29:17.810
<v Speaker 3>Exactly.

448
00:29:17.930 --> 00:29:18.930
<v Speaker 3>Trust the process.

449
00:29:19.089 --> 00:29:19.839
<v Speaker 3>Trust the process.

450
00:29:20.130 --> 00:29:20.329
<v Speaker 3>Yeah.

451
00:29:20.930 --> 00:29:25.050
<v Speaker 3>And, yeah, and finally as well, so more on
sort of the Highland pellets perspective.

452
00:29:25.130 --> 00:29:30.030
<v Speaker 3>So, so for Highland pellets, the future of
maintenance, let's finish that sentence.

453
00:29:30.130 --> 00:29:33.520
<v Speaker 3>So, what's the future of maintenance from
a Highland pellets perspective?

454
00:29:33.770 --> 00:29:38.650
<v Andrew Rehm>The, the future of maintenance at Highland
pellets is going to be a lot more

455
00:29:38.650 --> 00:29:44.810
<v Andrew Rehm>structured around the planned repairs, and
uh right now, a large portion of our

456
00:29:44.810 --> 00:29:47.089
<v Andrew Rehm>technicians' time is inspections.

457
00:29:47.589 --> 00:29:54.109
<v Andrew Rehm>And I really want to utilize their time
better and allow the equipment to run to its

458
00:29:54.109 --> 00:29:54.709
<v Andrew Rehm>optimal.

459
00:29:54.910 --> 00:30:00.150
<v Andrew Rehm>So, the future of Highland pellets is
predictive maintenance across our entire

460
00:30:00.150 --> 00:30:00.540
<v Andrew Rehm>plant.

461
00:30:00.790 --> 00:30:02.130
<v Andrew Rehm>It's really where we're driving.

462
00:30:02.469 --> 00:30:03.199
<v Speaker 3>Fantastic.

463
00:30:03.479 --> 00:30:04.229
<v Speaker 3>Fantastic.

464
00:30:04.719 --> 00:30:08.900
<v Speaker 3>Yeah, and what, what a great way to win
with such a forward thinking and vision as

465
00:30:08.900 --> 00:30:09.150
<v Speaker 3>well.

466
00:30:09.270 --> 00:30:13.829
<v Speaker 3>So, first of all, thank you, Andrew, for
taking the time for explaining sort of your

467
00:30:13.829 --> 00:30:15.130
<v Speaker 3>great success so far.

468
00:30:15.310 --> 00:30:16.089
<v Speaker 3>I'm sure.

469
00:30:16.459 --> 00:30:21.150
<v Speaker 3>Yeah, I'm sure everyone who's listened
will have taken something away to bring into

470
00:30:21.150 --> 00:30:22.560
<v Speaker 3>their own predictive maintenance journey.

471
00:30:22.640 --> 00:30:24.099
<v Speaker 3>So yeah, thank you for joining me today.

472
00:30:24.680 --> 00:30:25.400
<v Andrew Rehm>Yeah, absolutely.

473
00:30:25.479 --> 00:30:28.180
<v Andrew Rehm>It's really nice to talk to y'all, and

474
00:30:28.489 --> 00:30:28.780
<v Speaker 3>yeah.

475
00:30:29.199 --> 00:30:33.959
<v Speaker 3>Well, maybe we'll catch up again in 6
months to 2 years' time and see where you are

476
00:30:33.959 --> 00:30:36.630
<v Speaker 3>then, and how far you've scaled since
then.

477
00:30:37.449 --> 00:30:38.219
<v Andrew Rehm>That'll be great, man.

478
00:30:38.630 --> 00:30:39.079
<v Speaker 3>Fantastic.

479
00:30:39.199 --> 00:30:42.140
<v Speaker 3>But yeah, no, thank you for joining,
Andrew, and thank you everyone.

480
00:30:42.599 --> 00:30:46.619
<v Speaker 3>Out there for listening wherever you are,
and we'll see you on the next episode.

481
00:30:47.040 --> 00:30:48.140
<v Speaker 3>Thank you very much.

482
00:30:48.650 --> 00:30:48.719
<v Andrew Rehm>Right.

483
00:30:49.280 --> 00:30:49.959
<v Andrew Rehm>Thank you, sir.

484
00:30:56.089 --> 00:30:59.569
<v Speaker 2>Please like and subscribe on all major
podcast channels.

485
00:30:59.650 --> 00:31:04.569
<v Speaker 2>And to find out more about Sensi
predictive maintenance, go to Siemens.com.
