WEBVTT
Language: en-US

1
00:00:10.399 --> 00:00:12.319
<v John Lester>Hello and welcome to Buildings of
Tomorrow.

2
00:00:12.760 --> 00:00:15.960
<v John Lester>My name is John Lester, and in today's
episode we'll be talking about fault

3
00:00:15.960 --> 00:00:17.909
<v John Lester>detection versus data analytics.

4
00:00:18.280 --> 00:00:22.239
<v John Lester>I'm joined today by Tyson Suter, the
global business development manager for

5
00:00:22.239 --> 00:00:24.719
<v John Lester>digitalization at Siemens
Smart-Infrastructure.

6
00:00:25.309 --> 00:00:26.360
<v John Lester>Tyson, thank you for joining us.

7
00:00:26.479 --> 00:00:27.059
<v Tyson Suter>Thanks John.

8
00:00:27.559 --> 00:00:30.569
<v John Lester>What's the difference between fault
detection and data analytics?

9
00:00:30.909 --> 00:00:35.069
<v Tyson Suter>Yeah, so fault detection we've seen, you
know, for a very long time now, it, it

10
00:00:35.069 --> 00:00:37.479
<v Tyson Suter>looks at point in time data.

11
00:00:37.759 --> 00:00:41.919
<v Tyson Suter>So, what, what I, what I, what I mean by
this is, If something happens and something

12
00:00:41.919 --> 00:00:43.439
<v Tyson Suter>goes wrong, alarm.

13
00:00:43.799 --> 00:00:45.229
<v Tyson Suter>Tell me exactly at that moment.

14
00:00:45.630 --> 00:00:49.000
<v Tyson Suter>OK, this, this, this happened, this isn't
what we expect.

15
00:00:49.700 --> 00:00:51.709
<v Tyson Suter>Send off a flag saying good or bad.

16
00:00:51.909 --> 00:00:55.979
<v John Lester>So we know what we expect, we check to see
if we see it or not, and if we don't.

17
00:00:56.790 --> 00:00:57.590
<v John Lester>All the alarms go off.

18
00:00:57.669 --> 00:01:02.380
<v Tyson Suter>Yeah, exactly, like we, someone's swiped
their card and the door's supposed to open,

19
00:01:02.750 --> 00:01:03.669
<v Tyson Suter>because they have access.

20
00:01:03.950 --> 00:01:07.660
<v Tyson Suter>If that doesn't happen, that's an alarm,
or maybe they swipe the card, they're not

21
00:01:07.660 --> 00:01:08.730
<v Tyson Suter>supposed to go through that door.

22
00:01:09.080 --> 00:01:13.349
<v Tyson Suter>Uh, it's very simple stuff all the way
down to, uh, you know, expected temperatures

23
00:01:13.349 --> 00:01:19.910
<v Tyson Suter>versus, um, expected movement of people or
very, very much binary on off, yes or no.

24
00:01:20.800 --> 00:01:24.769
<v John Lester>So we preset our expectations, we preset
what we would like to see and a, and a

25
00:01:24.769 --> 00:01:29.330
<v John Lester>sequence of, of events, and if those
events don't correlate specifically with what

26
00:01:29.330 --> 00:01:30.830
<v John Lester>we've defined, we

27
00:01:30.970 --> 00:01:31.529
<v Tyson Suter>have a fault.

28
00:01:31.769 --> 00:01:32.529
<v Tyson Suter>Exactly, and.

29
00:01:33.120 --> 00:01:37.470
<v Tyson Suter>Very valuable as well, but we don't want
to underplay how important it is to, to

30
00:01:37.470 --> 00:01:40.300
<v Tyson Suter>measure expected values and, and see the
results.

31
00:01:40.550 --> 00:01:43.669
<v Tyson Suter>This is the, you know, significant portion
of how we run our buildings.

32
00:01:44.699 --> 00:01:48.839
<v Tyson Suter>So I think analytics and, and, and
bringing the two subjects together is.

33
00:01:49.779 --> 00:01:53.459
<v Tyson Suter>Saying OK fault detection's important,
very valuable, we need to do it, we need to

34
00:01:53.459 --> 00:01:54.800
<v Tyson Suter>do it in a smart way.

35
00:01:55.220 --> 00:02:01.099
<v Tyson Suter>Analytics is, how can I look at large
portions of time or data and say,

36
00:02:02.139 --> 00:02:02.930
<v Tyson Suter>Could this be better?

37
00:02:03.089 --> 00:02:05.000
<v Tyson Suter>Is this performance as expected?

38
00:02:05.370 --> 00:02:08.190
<v Tyson Suter>Is it regressing from what we expect to
see?

39
00:02:08.449 --> 00:02:09.729
<v Tyson Suter>Is it a drift from the normal?

40
00:02:10.130 --> 00:02:15.229
<v Tyson Suter>Can we predict what should happen and can
then we say, oh, we could do better here.

41
00:02:15.649 --> 00:02:19.710
<v John Lester>So not looking at one specific point in
time, but actually looking at the history.

42
00:02:20.160 --> 00:02:24.369
<v John Lester>And understanding how often something
happens or what's regular interval is causing

43
00:02:24.369 --> 00:02:26.559
<v John Lester>this, which might lead you to more
information.

44
00:02:26.929 --> 00:02:31.509
<v Tyson Suter>Exactly, so you know, predicting er
something that's really valuable is pressure

45
00:02:31.509 --> 00:02:35.860
<v Tyson Suter>leakage, saying oh OK that's, we expect a
certain performance in these conditions,

46
00:02:36.539 --> 00:02:41.929
<v Tyson Suter>with a bit of data and a bit of analysis
on past performance, we can know what to

47
00:02:41.929 --> 00:02:43.649
<v Tyson Suter>expect to see in certain conditions.

48
00:02:44.160 --> 00:02:49.210
<v Tyson Suter>If it's certain temperature outside and a
certain uh uh heat volume within a

49
00:02:49.210 --> 00:02:52.190
<v Tyson Suter>building, we can we can say OK, we expect
it to perform this way.

50
00:02:52.729 --> 00:02:56.690
<v Tyson Suter>With a huge amount of data we can say
great, we know what to expect, it's not doing

51
00:02:56.690 --> 00:02:58.410
<v Tyson Suter>that anymore, that's an issue.

52
00:02:58.570 --> 00:03:02.389
<v Tyson Suter>Let's go there before it's 50% uh failed.

53
00:03:02.649 --> 00:03:07.250
<v Tyson Suter>Let's go at 99% when it starts losing that
kind of very valuable refrigerant.

54
00:03:07.899 --> 00:03:13.580
<v John Lester>Yeah, right, so, so having a better idea
of understanding what happens leading up to

55
00:03:13.580 --> 00:03:17.259
<v John Lester>a fault occurring, so that you might be
able to catch or prevent that fault

56
00:03:17.259 --> 00:03:17.539
<v John Lester>completely.

57
00:03:17.940 --> 00:03:22.419
<v Tyson Suter>Exactly, and when you bring the two things
together, it kind of really enables to

58
00:03:22.419 --> 00:03:26.500
<v Tyson Suter>run a building efficiently, but we've
talked about this in the past, but if you can.

59
00:03:27.520 --> 00:03:32.100
<v Tyson Suter>Combine those two really valuable methods,
and then prioritize what's important.

60
00:03:32.990 --> 00:03:36.029
<v Tyson Suter>That's where the true value comes from,
making sure that you hold people accountable

61
00:03:36.029 --> 00:03:39.440
<v Tyson Suter>and and close issues off so we can get
value in our buildings.

62
00:03:39.979 --> 00:03:44.139
<v Tyson Suter>Analytics is really nice to have but if
your building isn't running effectively at

63
00:03:44.139 --> 00:03:47.529
<v Tyson Suter>all, Well you need to stick with fault
detection, make sure you can get it to a like

64
00:03:47.529 --> 00:03:49.369
<v Tyson Suter>a baseline, and then look for the
improvement.

65
00:03:49.729 --> 00:03:49.850
<v Tyson Suter>Right,

66
00:03:49.929 --> 00:03:53.169
<v John Lester>so you need to get to a level, you don't
have so many faults that it's impossible to

67
00:03:53.169 --> 00:03:56.729
<v John Lester>see, like we would say you, you can't see
the, the trees for the forest or the

68
00:03:56.729 --> 00:04:00.850
<v John Lester>forest for the trees, uh, so you have to
have an operating building, you know,

69
00:04:01.089 --> 00:04:06.149
<v John Lester>within a certain reasonable response so
that you can then start to apply a, a more

70
00:04:06.529 --> 00:04:07.149
<v John Lester>considered approach.

71
00:04:07.250 --> 00:04:11.369
<v Tyson Suter>Yeah, and if we don't have any data prior
to connecting, that's going to be the

72
00:04:11.369 --> 00:04:12.029
<v Tyson Suter>worst day.

73
00:04:12.330 --> 00:04:17.149
<v Tyson Suter>So we do need to create, Uh, a data set to
be able to analyze like what is good.

74
00:04:17.609 --> 00:04:21.200
<v Tyson Suter>You know, we have other buildings and
other equipment but there's many variables in

75
00:04:21.200 --> 00:04:25.320
<v Tyson Suter>every building, so the most valuable data
we can have is from, from your site.

76
00:04:25.730 --> 00:04:28.029
<v Tyson Suter>So we connect up and say this is day one.

77
00:04:28.799 --> 00:04:32.160
<v Tyson Suter>We're not gonna be able to predict
expected performance for this piece of equipment,

78
00:04:32.279 --> 00:04:34.380
<v Tyson Suter>but you know, a few months in we're gonna
be able to do that.

79
00:04:35.109 --> 00:04:38.829
<v John Lester>You mentioned before as well
responsibilities, so you, you have people operating a

80
00:04:38.829 --> 00:04:42.350
<v John Lester>building, there's always a human element,
not only to bring their expertise, but

81
00:04:42.350 --> 00:04:47.149
<v John Lester>also on a day to day basis, they have to
continue to continually operate and and

82
00:04:47.149 --> 00:04:52.720
<v John Lester>monitor, and when we see faults, Happen,
you know, in, in a certain point in time,

83
00:04:52.989 --> 00:04:56.959
<v John Lester>often it's the responsibility of one of
these people to acknowledge or something

84
00:04:56.959 --> 00:04:57.399
<v John Lester>like this.

85
00:04:57.690 --> 00:05:02.690
<v John Lester>Does data analytics give us the power to
expand our view beyond acknowledging a

86
00:05:02.690 --> 00:05:03.350
<v John Lester>single fault?

87
00:05:03.640 --> 00:05:03.799
<v John Lester>Yeah,

88
00:05:04.000 --> 00:05:08.279
<v Tyson Suter>so there's also the root cause analysis
where you can get rid of duplicate alarms,

89
00:05:08.399 --> 00:05:13.640
<v Tyson Suter>but, Also just smarter ways to look at the
alarm data and say like we don't need to.

90
00:05:14.230 --> 00:05:18.029
<v Tyson Suter>Acknowledge everything, cos that doesn't
solve any problems, but what we can do is

91
00:05:18.029 --> 00:05:22.149
<v Tyson Suter>say, well, we know this is significantly
causing us large issues, these are our

92
00:05:22.149 --> 00:05:26.149
<v Tyson Suter>critical alarms, solve them straight away,
but here's the big cost items, it's

93
00:05:26.149 --> 00:05:31.769
<v Tyson Suter>either gonna be a big risk in, um, tenant
comfort or maybe it's gonna be a risk in

94
00:05:31.769 --> 00:05:32.299
<v Tyson Suter>energy or

95
00:05:32.299 --> 00:05:33.910
<v John Lester>performance, asset damage or something
else.

96
00:05:34.109 --> 00:05:38.239
<v Tyson Suter>Exactly, we can say great, let's just
prioritize these first and, This stuff down

97
00:05:38.239 --> 00:05:41.839
<v Tyson Suter>here, not that important, cos there's a
lot of alarms that, you know, yeah, it's not

98
00:05:41.839 --> 00:05:45.899
<v Tyson Suter>working perfectly, but in reality, let's
let's worry about that later, let's focus

99
00:05:45.899 --> 00:05:47.269
<v Tyson Suter>on the big, big ticket items.

100
00:05:48.119 --> 00:05:49.660
<v Tyson Suter>And that's what you can do with a smart
system.

101
00:05:49.720 --> 00:05:53.829
<v Tyson Suter>You can bring all these things together,
put it in the hands of experts and say,

102
00:05:53.839 --> 00:05:58.489
<v Tyson Suter>great, this is important to us, here's the
potential savings, here's what we need to

103
00:05:58.489 --> 00:06:01.089
<v Tyson Suter>do to fix it, let's get the right people
there to do it.

104
00:06:01.399 --> 00:06:01.630
<v Tyson Suter>Great,

105
00:06:01.839 --> 00:06:02.420
<v John Lester>thank you very much.

106
00:06:02.450 --> 00:06:02.880
<v John Lester>Thank you.

107
00:06:03.579 --> 00:06:07.459
<v John Lester>And thank you for not just listening to
this episode, but to all the episodes

108
00:06:07.459 --> 00:06:08.380
<v John Lester>throughout 2020.

109
00:06:08.420 --> 00:06:12.260
<v John Lester>It's been a crazy year, but we've very
much enjoyed from this perspective bringing

110
00:06:12.260 --> 00:06:16.940
<v John Lester>you so many exciting topics and so much
knowledge from our exciting experts.

111
00:06:17.269 --> 00:06:22.640
<v John Lester>This is the last episode we're releasing
in 2020, so we'll see you early in 2021

112
00:06:22.640 --> 00:06:27.529
<v John Lester>with a lot more new episodes with new
topics, new experts, and a lot more

113
00:06:27.529 --> 00:06:30.019
<v John Lester>conversations around this exciting
industry that we work in.

114
00:06:30.140 --> 00:06:32.739
<v John Lester>Be safe and secure, and we'll see you
again soon.
