LSTM and Edge Computing for Big Data Feature Recognition of Industrial Electrical Equipment

Chin-Feng Lai, Wei Che Chien, Laurence T. Yang, Weizhong Qiang

Research output: Contribution to journalArticle

Abstract

With the rapid development of Industrial Internet of Things, the category and quantity of industrial equipment will increase gradually. For centralized monitoring and management of numerous and multivariate equipment in the intelligent manufacturing process, the equipment categories shall be identified first. However, manual labeling of electrical equipment needs high costs. For the purpose of recognizing industrial equipment accurately in manufacturing systems, this study adopts the long short-term memory to analyze big data features and build a nonintrusive load monitoring system. Edge computing is used to implement parallel computing to improve the efficiency of equipment identification. Considering the practical popularity, the fairly priced low-frequency Smart Meter is used to collect the appliance data. According to the proposed optimal adjustment strategy of parameter model, the average random recognition rate can achieve 88% and the average recognition rate of the continuous data of a single electrical equipment can achieve 83.6%.

Original languageEnglish
Article number8611107
Pages (from-to)2469-2477
Number of pages9
JournalIEEE Transactions on Industrial Informatics
Volume15
Issue number4
DOIs
Publication statusPublished - 2019 Apr 1

Fingerprint

Frequency meters
Smart meters
Monitoring
Parallel processing systems
Big data
Labeling
Costs
Internet of things
Long short-term memory

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Information Systems
  • Computer Science Applications
  • Electrical and Electronic Engineering

Cite this

Lai, Chin-Feng ; Chien, Wei Che ; Yang, Laurence T. ; Qiang, Weizhong. / LSTM and Edge Computing for Big Data Feature Recognition of Industrial Electrical Equipment. In: IEEE Transactions on Industrial Informatics. 2019 ; Vol. 15, No. 4. pp. 2469-2477.
@article{3a19be97fbc04be0b36522c13790a30c,
title = "LSTM and Edge Computing for Big Data Feature Recognition of Industrial Electrical Equipment",
abstract = "With the rapid development of Industrial Internet of Things, the category and quantity of industrial equipment will increase gradually. For centralized monitoring and management of numerous and multivariate equipment in the intelligent manufacturing process, the equipment categories shall be identified first. However, manual labeling of electrical equipment needs high costs. For the purpose of recognizing industrial equipment accurately in manufacturing systems, this study adopts the long short-term memory to analyze big data features and build a nonintrusive load monitoring system. Edge computing is used to implement parallel computing to improve the efficiency of equipment identification. Considering the practical popularity, the fairly priced low-frequency Smart Meter is used to collect the appliance data. According to the proposed optimal adjustment strategy of parameter model, the average random recognition rate can achieve 88{\%} and the average recognition rate of the continuous data of a single electrical equipment can achieve 83.6{\%}.",
author = "Chin-Feng Lai and Chien, {Wei Che} and Yang, {Laurence T.} and Weizhong Qiang",
year = "2019",
month = "4",
day = "1",
doi = "10.1109/TII.2019.2892818",
language = "English",
volume = "15",
pages = "2469--2477",
journal = "IEEE Transactions on Industrial Informatics",
issn = "1551-3203",
publisher = "IEEE Computer Society",
number = "4",

}

LSTM and Edge Computing for Big Data Feature Recognition of Industrial Electrical Equipment. / Lai, Chin-Feng; Chien, Wei Che; Yang, Laurence T.; Qiang, Weizhong.

In: IEEE Transactions on Industrial Informatics, Vol. 15, No. 4, 8611107, 01.04.2019, p. 2469-2477.

Research output: Contribution to journalArticle

TY - JOUR

T1 - LSTM and Edge Computing for Big Data Feature Recognition of Industrial Electrical Equipment

AU - Lai, Chin-Feng

AU - Chien, Wei Che

AU - Yang, Laurence T.

AU - Qiang, Weizhong

PY - 2019/4/1

Y1 - 2019/4/1

N2 - With the rapid development of Industrial Internet of Things, the category and quantity of industrial equipment will increase gradually. For centralized monitoring and management of numerous and multivariate equipment in the intelligent manufacturing process, the equipment categories shall be identified first. However, manual labeling of electrical equipment needs high costs. For the purpose of recognizing industrial equipment accurately in manufacturing systems, this study adopts the long short-term memory to analyze big data features and build a nonintrusive load monitoring system. Edge computing is used to implement parallel computing to improve the efficiency of equipment identification. Considering the practical popularity, the fairly priced low-frequency Smart Meter is used to collect the appliance data. According to the proposed optimal adjustment strategy of parameter model, the average random recognition rate can achieve 88% and the average recognition rate of the continuous data of a single electrical equipment can achieve 83.6%.

AB - With the rapid development of Industrial Internet of Things, the category and quantity of industrial equipment will increase gradually. For centralized monitoring and management of numerous and multivariate equipment in the intelligent manufacturing process, the equipment categories shall be identified first. However, manual labeling of electrical equipment needs high costs. For the purpose of recognizing industrial equipment accurately in manufacturing systems, this study adopts the long short-term memory to analyze big data features and build a nonintrusive load monitoring system. Edge computing is used to implement parallel computing to improve the efficiency of equipment identification. Considering the practical popularity, the fairly priced low-frequency Smart Meter is used to collect the appliance data. According to the proposed optimal adjustment strategy of parameter model, the average random recognition rate can achieve 88% and the average recognition rate of the continuous data of a single electrical equipment can achieve 83.6%.

UR - http://www.scopus.com/inward/record.url?scp=85064128984&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85064128984&partnerID=8YFLogxK

U2 - 10.1109/TII.2019.2892818

DO - 10.1109/TII.2019.2892818

M3 - Article

VL - 15

SP - 2469

EP - 2477

JO - IEEE Transactions on Industrial Informatics

JF - IEEE Transactions on Industrial Informatics

SN - 1551-3203

IS - 4

M1 - 8611107

ER -