1
00:00:05,560 --> 00:00:07,780
At the end of this topic,

2
00:00:07,780 --> 00:00:09,920
you will be able to explain

3
00:00:09,920 --> 00:00:12,290
steel production
processes and its steps,

4
00:00:12,290 --> 00:00:14,240
implementing the digital twin in

5
00:00:14,240 --> 00:00:16,230
the steel making
production process,

6
00:00:16,230 --> 00:00:18,330
describe the IIoT platform

7
00:00:18,330 --> 00:00:21,005
and digital twin
Framework based designs,

8
00:00:21,005 --> 00:00:22,940
explain the real time monitoring

9
00:00:22,940 --> 00:00:25,600
of our process
control parameters.

10
00:00:25,600 --> 00:00:27,980
In our previous discussion,

11
00:00:27,980 --> 00:00:30,640
we explored how digital
twin technology can

12
00:00:30,640 --> 00:00:34,255
optimize production processes
and quality management.

13
00:00:34,255 --> 00:00:36,500
To further enhance
our understanding,

14
00:00:36,500 --> 00:00:38,760
let us now examine
a case study of

15
00:00:38,760 --> 00:00:41,400
the steel making process
in a heavy industry.

16
00:00:41,400 --> 00:00:44,280
Steel making is an important
continuous process

17
00:00:44,280 --> 00:00:46,880
in heavy industries,
which is shown here.

18
00:00:46,880 --> 00:00:49,100
After slabs blooms and

19
00:00:49,100 --> 00:00:51,360
billets are made
from molten steel,

20
00:00:51,360 --> 00:00:54,060
they require forging
and heat treatments.

21
00:00:54,060 --> 00:00:57,540
The basic concepts and
technologies of this scenario can

22
00:00:57,540 --> 00:00:59,420
be applied to
different steel making

23
00:00:59,420 --> 00:01:01,540
or other similar operations.

24
00:01:01,540 --> 00:01:05,820
Next, let us discuss the steps
in steel making processes.

25
00:01:05,820 --> 00:01:07,560
First, let's look at

26
00:01:07,560 --> 00:01:09,780
the primary steel making
production process.

27
00:01:09,780 --> 00:01:12,960
The above figure provides
information about

28
00:01:12,960 --> 00:01:14,120
the various stages in

29
00:01:14,120 --> 00:01:16,880
the primary production
process of steel making,

30
00:01:16,880 --> 00:01:19,210
which is called as
upstream process.

31
00:01:19,210 --> 00:01:22,530
The process of steel
production is complex,

32
00:01:22,530 --> 00:01:26,280
ongoing, and encompasses
a wide range of steps.

33
00:01:26,280 --> 00:01:29,300
Iron ore, coal, limestone,

34
00:01:29,300 --> 00:01:31,220
and recycled steel are used to

35
00:01:31,220 --> 00:01:33,600
produce both common
and specialized steel.

36
00:01:33,600 --> 00:01:35,800
Iron is produced in a coke oven,

37
00:01:35,800 --> 00:01:38,340
blast furnace or a direct
reduction furnace,

38
00:01:38,340 --> 00:01:40,260
while steel is produced in

39
00:01:40,260 --> 00:01:43,980
oxygen furnaces or an
electric arc furnace.

40
00:01:43,980 --> 00:01:46,440
Continuous casting is used to

41
00:01:46,440 --> 00:01:48,720
produce slabs,
blooms, and billets.

42
00:01:48,720 --> 00:01:50,600
Next, let's take a look at the

43
00:01:50,600 --> 00:01:52,700
secondary steel making
production process.

44
00:01:52,700 --> 00:01:54,480
In secondary manufacturing,

45
00:01:54,480 --> 00:01:57,880
raw materials are transformed
into pipes, sheets,

46
00:01:57,880 --> 00:01:59,440
bars, rods,

47
00:01:59,440 --> 00:02:01,320
and other structural
shapes through

48
00:02:01,320 --> 00:02:03,630
heating, forging, or pressing.

49
00:02:03,630 --> 00:02:06,005
These shapes may
undergo heat treatment,

50
00:02:06,005 --> 00:02:08,050
surface coating, and finishing

51
00:02:08,050 --> 00:02:10,270
before being shipped
as finished products.

52
00:02:10,270 --> 00:02:13,870
The figure shows each basic
production process may have

53
00:02:13,870 --> 00:02:16,290
multiple sub-processes
supported by

54
00:02:16,290 --> 00:02:18,430
production lines with
complex machinery.

55
00:02:18,430 --> 00:02:20,750
They also highlight
the interaction

56
00:02:20,750 --> 00:02:22,450
between upstream and downstream

57
00:02:22,450 --> 00:02:23,750
parts of the supply chain.

58
00:02:23,750 --> 00:02:25,290
The upstream processes have

59
00:02:25,290 --> 00:02:26,990
an impact on the
downstream ones.

60
00:02:26,990 --> 00:02:29,610
The production of high end
special steel requires

61
00:02:29,610 --> 00:02:31,350
additional procedures and makes

62
00:02:31,350 --> 00:02:33,950
quality monitoring and
tracking very difficult.

63
00:02:33,950 --> 00:02:37,410
Special steel is manufactured
in small batches and is

64
00:02:37,410 --> 00:02:41,410
used in equipment requiring
high reliability and safety.

65
00:02:41,410 --> 00:02:43,950
Hence, stricter quality
standards are applied.

66
00:02:43,950 --> 00:02:45,950
Traceability of product quality

67
00:02:45,950 --> 00:02:48,510
throughout the production
process is very essential.

68
00:02:48,510 --> 00:02:52,245
We have a few examples
here. Managing the process.

69
00:02:52,245 --> 00:02:55,230
Speed of continuous
casting and temperature of

70
00:02:55,230 --> 00:02:59,090
molten steel are the
detecting parameters,

71
00:02:59,090 --> 00:03:02,590
inclusion that float on
top of molten steel.

72
00:03:02,590 --> 00:03:05,850
Visibility parameters,
temperature is taken

73
00:03:05,850 --> 00:03:07,930
into account during
the rolling process

74
00:03:07,930 --> 00:03:09,330
from beginning to the end.

75
00:03:09,330 --> 00:03:11,250
Moving on to the
implementation of

76
00:03:11,250 --> 00:03:14,210
a digital twin in the steel
making production process.

77
00:03:14,210 --> 00:03:17,190
Controlling and monitoring
industrial operations

78
00:03:17,190 --> 00:03:19,040
is made possible
with the help of

79
00:03:19,040 --> 00:03:20,120
Internet of Things and

80
00:03:20,120 --> 00:03:21,860
digital twin technologies

81
00:03:21,860 --> 00:03:24,325
including programmable
logical Controls,

82
00:03:24,325 --> 00:03:26,740
TLCs, and supervisory control

83
00:03:26,740 --> 00:03:28,685
and data acquisition, SCADA.

84
00:03:28,685 --> 00:03:30,160
SCADA is a type of

85
00:03:30,160 --> 00:03:32,360
monitoring software
used for controlling

86
00:03:32,360 --> 00:03:35,280
PLC hardware and recording data

87
00:03:35,280 --> 00:03:37,515
even from remote locations.

88
00:03:37,515 --> 00:03:41,440
The ISA-95 standard
uses a layered model of

89
00:03:41,440 --> 00:03:43,180
manufacturing technology and

90
00:03:43,180 --> 00:03:45,760
a business process
with four levels.

91
00:03:45,760 --> 00:03:49,140
In recent decades, the steel
industry has invested in

92
00:03:49,140 --> 00:03:54,000
IT applications that align
with the ISA-95 levels 0-4.

93
00:03:54,000 --> 00:03:56,560
These systems manage various
aspects of production,

94
00:03:56,560 --> 00:03:58,280
such as production processes,

95
00:03:58,280 --> 00:04:00,520
quality managed system, QMS,

96
00:04:00,520 --> 00:04:03,235
control management system,
production planning,

97
00:04:03,235 --> 00:04:07,825
execution, MES, and equipment
management system, EMS.

98
00:04:07,825 --> 00:04:10,580
These investments have led
to improved productivity,

99
00:04:10,580 --> 00:04:13,965
quality, and cost efficiency
in the steel industry.

100
00:04:13,965 --> 00:04:17,560
Level 0, this defines
the physical process.

101
00:04:17,560 --> 00:04:19,820
Level 1 defines the sensing

102
00:04:19,820 --> 00:04:21,940
and manipulating
physical process.

103
00:04:21,940 --> 00:04:25,680
Level 2 monitors and
controls physical process.

104
00:04:25,680 --> 00:04:29,860
Level 3 defines workflow
tasks to produce end goods.

105
00:04:29,860 --> 00:04:31,880
Level 4 defines business

106
00:04:31,880 --> 00:04:34,695
related manufacturing
management activities.

107
00:04:34,695 --> 00:04:36,795
In the past few decades,

108
00:04:36,795 --> 00:04:38,550
many heavy industries such as

109
00:04:38,550 --> 00:04:39,870
the steel making industry

110
00:04:39,870 --> 00:04:41,880
has been focusing on automation.

111
00:04:41,880 --> 00:04:44,940
As a result, ISA 95 Levels 1 and

112
00:04:44,940 --> 00:04:48,045
2 are primarily used for
equipment automation.

113
00:04:48,045 --> 00:04:52,680
Interconnected PLCs at
ISA 95 Levels 1 and

114
00:04:52,680 --> 00:04:55,380
2 make data collection
very difficult.

115
00:04:55,380 --> 00:04:59,445
PLCs connected to SCADA systems
are typically separate.

116
00:04:59,445 --> 00:05:01,770
Human machine interfaces are

117
00:05:01,770 --> 00:05:04,410
used to view data and alarms.

118
00:05:04,410 --> 00:05:06,930
SCADA data and alarms cannot

119
00:05:06,930 --> 00:05:09,060
be easily connected
with other systems.

120
00:05:09,060 --> 00:05:10,965
Analyzing them takes more time

121
00:05:10,965 --> 00:05:13,005
due to their technical content.

122
00:05:13,005 --> 00:05:15,555
Automation and IT applications

123
00:05:15,555 --> 00:05:18,150
are used to manage steel
making operations.

124
00:05:18,150 --> 00:05:20,685
Connectivity and
integration issues

125
00:05:20,685 --> 00:05:22,740
restrict further
efficiency gains.

126
00:05:22,740 --> 00:05:24,870
These hurdles are caused by

127
00:05:24,870 --> 00:05:26,925
technical difficulties
between production,

128
00:05:26,925 --> 00:05:29,310
operation management
application systems

129
00:05:29,310 --> 00:05:31,440
and automation control systems.

130
00:05:31,440 --> 00:05:33,180
The PLCs and SCADAs.

131
00:05:33,180 --> 00:05:35,340
ID application and
automation systems

132
00:05:35,340 --> 00:05:37,125
encounter barriers such as

133
00:05:37,125 --> 00:05:39,330
improper connections
between PLCs

134
00:05:39,330 --> 00:05:42,090
and SCADAs with
application systems.

135
00:05:42,090 --> 00:05:45,450
This hinders communication
between many applications and

136
00:05:45,450 --> 00:05:47,325
the production environment where

137
00:05:47,325 --> 00:05:50,580
equipment is running and
products are being processed.

138
00:05:50,580 --> 00:05:54,000
Automation system data is
incompletely collected and

139
00:05:54,000 --> 00:05:56,520
used limiting
production transparency

140
00:05:56,520 --> 00:05:58,515
and data driven management.

141
00:05:58,515 --> 00:06:00,900
The application systems such

142
00:06:00,900 --> 00:06:03,150
as process, quality, equipment,

143
00:06:03,150 --> 00:06:06,285
energy production
planning and execution

144
00:06:06,285 --> 00:06:08,760
impede manufacturing
processes and

145
00:06:08,760 --> 00:06:10,200
lines such as those

146
00:06:10,200 --> 00:06:12,375
described in the steel
making processes.

147
00:06:12,375 --> 00:06:14,610
Let's discuss the
other challenges on

148
00:06:14,610 --> 00:06:16,170
implementing a digital twin

149
00:06:16,170 --> 00:06:18,390
in a steel production process.

150
00:06:18,390 --> 00:06:20,910
Industrial domain experts have

151
00:06:20,910 --> 00:06:22,620
thorough knowledge
of steel making

152
00:06:22,620 --> 00:06:25,290
production processes
and are capable of

153
00:06:25,290 --> 00:06:26,880
transforming customer needs and

154
00:06:26,880 --> 00:06:29,355
demands into business
requirements.

155
00:06:29,355 --> 00:06:32,160
Industrial software
application analysts

156
00:06:32,160 --> 00:06:33,825
translate business requirements

157
00:06:33,825 --> 00:06:35,775
into software requirements and

158
00:06:35,775 --> 00:06:38,175
assist in building
software solutions.

159
00:06:38,175 --> 00:06:40,350
Industrial data
analytic engineers

160
00:06:40,350 --> 00:06:42,450
with data modeling skills

161
00:06:42,450 --> 00:06:44,505
can link data
analytic requirements

162
00:06:44,505 --> 00:06:46,920
into input data and
modeling demands,

163
00:06:46,920 --> 00:06:50,220
industrial control or
automation engineers gather

164
00:06:50,220 --> 00:06:51,990
project deployment structure and

165
00:06:51,990 --> 00:06:54,135
equipment configuration
information,

166
00:06:54,135 --> 00:06:57,375
evaluate connection and
data gathering needs,

167
00:06:57,375 --> 00:07:00,105
and design IoT
software solutions.

168
00:07:00,105 --> 00:07:01,920
Furthermore, we will discuss

169
00:07:01,920 --> 00:07:03,900
the steel production
process using

170
00:07:03,900 --> 00:07:08,100
an IoT platform and digital
twin framework based design.

171
00:07:08,100 --> 00:07:09,870
The displayed image is

172
00:07:09,870 --> 00:07:11,400
the functional architecture of

173
00:07:11,400 --> 00:07:13,965
UI Things Wise iDOS platform.

174
00:07:13,965 --> 00:07:16,020
Online analytics depend on

175
00:07:16,020 --> 00:07:19,950
collected data to improve
online and batch quality.

176
00:07:19,950 --> 00:07:22,110
Connectivity to equipment and

177
00:07:22,110 --> 00:07:26,085
sensors to collect data through
the Internet of Things.

178
00:07:26,085 --> 00:07:29,490
The digital twin architecture
has three layers,

179
00:07:29,490 --> 00:07:32,700
a bottom layer, a middle
layer, and a top layer.

180
00:07:32,700 --> 00:07:34,920
Complete digital
representation or

181
00:07:34,920 --> 00:07:37,245
digital twins of the
production environment,

182
00:07:37,245 --> 00:07:39,000
including equipment twins,

183
00:07:39,000 --> 00:07:42,945
product twins for tracking
status and process data.

184
00:07:42,945 --> 00:07:44,760
The dynamic relationship between

185
00:07:44,760 --> 00:07:47,670
product introduction,
PIPs and equipment.

186
00:07:47,670 --> 00:07:50,850
The actual process data
can be collected and

187
00:07:50,850 --> 00:07:53,940
associated with the PIPs
analytical capabilities

188
00:07:53,940 --> 00:07:56,940
that can be embedded within
the digital twins to analyze

189
00:07:56,940 --> 00:08:00,060
data associations
development ops setting in

190
00:08:00,060 --> 00:08:02,010
which the applications
that provide

191
00:08:02,010 --> 00:08:03,990
the necessary business logic and

192
00:08:03,990 --> 00:08:06,990
user interfaces may be
built and operated.

193
00:08:06,990 --> 00:08:10,050
First let's look at
the bottom layer.

194
00:08:10,050 --> 00:08:12,540
The Internet of
Things allows for

195
00:08:12,540 --> 00:08:14,685
the interconnection of devices,

196
00:08:14,685 --> 00:08:16,515
the collection of information,

197
00:08:16,515 --> 00:08:18,315
and the management of systems.

198
00:08:18,315 --> 00:08:21,705
The following benefits
are provided by IoT.

199
00:08:21,705 --> 00:08:23,430
The connection of equipment,

200
00:08:23,430 --> 00:08:26,835
collection of information,
preparation of data,

201
00:08:26,835 --> 00:08:29,880
input or output device
information storage,

202
00:08:29,880 --> 00:08:33,600
service for remotely
managing gateways in IoT.

203
00:08:33,600 --> 00:08:37,050
A digital twin framework
is a set of tools used to

204
00:08:37,050 --> 00:08:40,545
create a digital representation
of a production setting,

205
00:08:40,545 --> 00:08:44,130
store and manage information
on production equipment,

206
00:08:44,130 --> 00:08:47,880
and combine analytical models
related to that machinery.

207
00:08:47,880 --> 00:08:51,105
Designing a user interface
for a digital twin,

208
00:08:51,105 --> 00:08:55,185
data mapping for digital twins
to the Internet of Things.

209
00:08:55,185 --> 00:08:58,110
Analytical modeling
using a Digital Twin,

210
00:08:58,110 --> 00:09:01,390
open API for digital twins.

211
00:09:01,550 --> 00:09:04,170
Moving on to the top layer,

212
00:09:04,170 --> 00:09:07,635
a development and operations
framework for creating,

213
00:09:07,635 --> 00:09:10,210
deploying, and managing
applications in

214
00:09:10,210 --> 00:09:13,650
both codeless and code based
graphic user interfaces.

215
00:09:13,650 --> 00:09:15,910
A device for displaying data.

216
00:09:15,910 --> 00:09:18,110
A streamlined
method for creating

217
00:09:18,110 --> 00:09:21,830
graphical user interface
software development kit

218
00:09:21,830 --> 00:09:24,780
that supports programming
in multiple languages.

219
00:09:24,780 --> 00:09:27,010
Microservice architecture.

220
00:09:27,010 --> 00:09:29,765
The platform's IoT
framework layer,

221
00:09:29,765 --> 00:09:33,680
which includes IIoT application
integration gateways,

222
00:09:33,680 --> 00:09:37,430
enables equipment connectivity
and data collection.

223
00:09:37,430 --> 00:09:40,850
It also allows for integration
with other systems,

224
00:09:40,850 --> 00:09:42,695
such as visual configuration,

225
00:09:42,695 --> 00:09:45,740
process specification
management systems and

226
00:09:45,740 --> 00:09:49,070
production management system
without any coding required.

227
00:09:49,070 --> 00:09:50,900
A digital twin layer is

228
00:09:50,900 --> 00:09:53,555
built by digital twin
designer application.

229
00:09:53,555 --> 00:09:56,540
The digital twin layer
sends the micro services to

230
00:09:56,540 --> 00:09:58,340
the application framework layer

231
00:09:58,340 --> 00:10:00,875
which enables the following
business functions;

232
00:10:00,875 --> 00:10:02,510
a real time monitoring of

233
00:10:02,510 --> 00:10:05,210
quality and process
quality, anomaly,

234
00:10:05,210 --> 00:10:07,505
and a process
exception handling,

235
00:10:07,505 --> 00:10:09,320
lean quality management,

236
00:10:09,320 --> 00:10:12,305
quality and process
optimization analysis,

237
00:10:12,305 --> 00:10:15,050
traceability of product quality.

238
00:10:15,050 --> 00:10:19,265
All relevant data is fed into
a digital twin platform.

239
00:10:19,265 --> 00:10:22,730
Lean manufacturing and six
Sigma concepts are recorded

240
00:10:22,730 --> 00:10:24,800
for optimizing
production processes

241
00:10:24,800 --> 00:10:26,585
and quality management.

242
00:10:26,585 --> 00:10:28,520
First, let's look at

243
00:10:28,520 --> 00:10:30,875
the optimization of
production processes.

244
00:10:30,875 --> 00:10:32,840
Optimizing the
production process with

245
00:10:32,840 --> 00:10:34,610
the help of a digital twin is

246
00:10:34,610 --> 00:10:36,965
nothing but using a
process management tool

247
00:10:36,965 --> 00:10:38,735
to collect, regulate,

248
00:10:38,735 --> 00:10:40,670
and verify data obtained from

249
00:10:40,670 --> 00:10:43,970
equipment and
machinery, operations,

250
00:10:43,970 --> 00:10:47,360
method, product and
equipment specifications,

251
00:10:47,360 --> 00:10:50,780
standards, production
planning and quality design.

252
00:10:50,780 --> 00:10:52,175
This figure shows

253
00:10:52,175 --> 00:10:55,250
a special alloy making
equipment and processes.

254
00:10:55,250 --> 00:10:57,260
Here the billets and

255
00:10:57,260 --> 00:10:59,585
other semi finished
products are following

256
00:10:59,585 --> 00:11:02,030
an optimized production
path to complete

257
00:11:02,030 --> 00:11:05,225
all other operations involved
in steel making process.

258
00:11:05,225 --> 00:11:07,685
The digital twin frame design

259
00:11:07,685 --> 00:11:10,250
suggests the optimized
production path by

260
00:11:10,250 --> 00:11:12,380
considering all
critical data and

261
00:11:12,380 --> 00:11:15,200
constraints in each level
of steel making process.

262
00:11:15,200 --> 00:11:18,125
Multiple product
manufacturing is frequent.

263
00:11:18,125 --> 00:11:20,375
Dynamic production
scheduling for

264
00:11:20,375 --> 00:11:21,950
each product in production

265
00:11:21,950 --> 00:11:24,755
maximizes the overall
equipment effectiveness

266
00:11:24,755 --> 00:11:26,435
and production capacity.

267
00:11:26,435 --> 00:11:28,355
Each PiP can follow

268
00:11:28,355 --> 00:11:29,750
a unique path in

269
00:11:29,750 --> 00:11:32,585
the equipment matrix over
its production lifespan.

270
00:11:32,585 --> 00:11:36,270
Now we will be discussing
about the quality management.

271
00:11:36,270 --> 00:11:39,040
The key aspects of steel
product quality are

272
00:11:39,040 --> 00:11:41,680
structure performance,
surface quality,

273
00:11:41,680 --> 00:11:44,365
and geometric
dimensions which depend

274
00:11:44,365 --> 00:11:47,460
on material composition
and processing methods.

275
00:11:47,460 --> 00:11:49,100
To meet the needs of a client.

276
00:11:49,100 --> 00:11:50,600
In quality of a product,

277
00:11:50,600 --> 00:11:52,310
we should gather data on

278
00:11:52,310 --> 00:11:54,995
quality attributes and
process control design.

279
00:11:54,995 --> 00:11:57,695
The recorded data from
digital twin exhibits,

280
00:11:57,695 --> 00:11:59,195
the real time measurements.

281
00:11:59,195 --> 00:12:02,420
The real time measurement
of a process and monitoring

282
00:12:02,420 --> 00:12:04,850
the actual process
are very useful

283
00:12:04,850 --> 00:12:07,775
for quality measure and
to satisfy the clients.

284
00:12:07,775 --> 00:12:10,925
It is also useful for
finding deviations.

285
00:12:10,925 --> 00:12:12,620
Weak process control gives

286
00:12:12,620 --> 00:12:15,695
bad impacts on quality of
high-end special steel.

287
00:12:15,695 --> 00:12:18,755
Now let's examine the
real time monitoring

288
00:12:18,755 --> 00:12:20,450
of a process control parameter,

289
00:12:20,450 --> 00:12:23,360
which is obtained from a
digital twin analysis.

290
00:12:23,360 --> 00:12:26,210
This figure demonstrates
the real time monitoring of

291
00:12:26,210 --> 00:12:29,570
a process control parameters
with statistics and alarms.

292
00:12:29,570 --> 00:12:31,250
The main approaches of

293
00:12:31,250 --> 00:12:33,965
lean management are
eliminating waste,

294
00:12:33,965 --> 00:12:36,530
standardizing processes
and procedures,

295
00:12:36,530 --> 00:12:38,525
implementing
standard operations,

296
00:12:38,525 --> 00:12:40,085
and continuous improvement.

297
00:12:40,085 --> 00:12:42,050
By implementing a digital twin,

298
00:12:42,050 --> 00:12:44,120
the following solutions
are achieved in

299
00:12:44,120 --> 00:12:46,475
manufacturing processes
and quality management.

300
00:12:46,475 --> 00:12:49,025
A standardized operation.

301
00:12:49,025 --> 00:12:52,325
To standardize the workflow
and procedures that deliver

302
00:12:52,325 --> 00:12:53,570
quality products within

303
00:12:53,570 --> 00:12:55,910
established limits
and uncertainties,

304
00:12:55,910 --> 00:12:58,625
we use software to
maintain the standards.

305
00:12:58,625 --> 00:13:01,565
Reduce waste, address
quality issues

306
00:13:01,565 --> 00:13:04,355
by reducing product
faults and reworks.

307
00:13:04,355 --> 00:13:07,280
Use data driven production
control to maintain

308
00:13:07,280 --> 00:13:11,195
process consistency and eliminate
unnecessary variations.

309
00:13:11,195 --> 00:13:15,050
Detect process failures and
quality irregularities in

310
00:13:15,050 --> 00:13:16,610
real time to prevent

311
00:13:16,610 --> 00:13:19,490
downstream waste.
Continuous improvement.

312
00:13:19,490 --> 00:13:22,370
Regularly analyze quality
performance using

313
00:13:22,370 --> 00:13:24,200
standard statistical process

314
00:13:24,200 --> 00:13:26,390
control methodologies based on

315
00:13:26,390 --> 00:13:28,175
real time data so that

316
00:13:28,175 --> 00:13:29,930
quality performance issues can

317
00:13:29,930 --> 00:13:31,430
be identified and redeemed.

318
00:13:31,430 --> 00:13:34,025
Conclusion of digital
twin implementation.

319
00:13:34,025 --> 00:13:37,670
The combination of
IoT, digital twin,

320
00:13:37,670 --> 00:13:39,230
and industrial analytics can

321
00:13:39,230 --> 00:13:41,420
facilitate the digitalization of

322
00:13:41,420 --> 00:13:43,730
industrial operations
management including

323
00:13:43,730 --> 00:13:46,640
manufacturing processes and
product quality control.

324
00:13:46,640 --> 00:13:49,385
Both equipment and
product digital twins

325
00:13:49,385 --> 00:13:50,900
are effective methods and

326
00:13:50,900 --> 00:13:52,595
technologies for monitoring

327
00:13:52,595 --> 00:13:54,170
product quality and

328
00:13:54,170 --> 00:13:56,555
building quality
traceability records.

329
00:13:56,555 --> 00:13:59,690
Digital twins can reflect
manufacturing value flows.

330
00:13:59,690 --> 00:14:01,460
An IIoT platform with

331
00:14:01,460 --> 00:14:03,470
a digital twin
structure simplifies

332
00:14:03,470 --> 00:14:04,940
the deployment of safe,

333
00:14:04,940 --> 00:14:07,985
scalable, reliable
industrial operation

334
00:14:07,985 --> 00:14:09,710
and a quality management system.

335
00:14:09,710 --> 00:14:12,215
By this, we have come to
the end of this topic.

336
00:14:12,215 --> 00:14:15,630
Let us meet in another
interesting session. Thank you.