Energy Efficiency Optimization of Industrial Internet of Things and Predictive Maintenance of Equipment

Yilin Ouyang

doi:10.47297/taposatWSP2633-456921.20250609

PDF
Export
Share
Collection
Album

Energy Efficiency Optimization of Industrial Internet of Things and Predictive Maintenance of Equipment

Volume 6, Issue 9

Views: 0 Downloads: 2

Energy Efficiency Optimization of Industrial Internet of Things and Predictive Maintenance of Equipment
Energy Efficiency Optimization of Industrial Internet of Things and Predictive Maintenance of Equipment
School of Mechanical and Electrical Engineering and Automation, Shanghai University, Shanghai, 200444, China
Vol. 6, Issue 9, Pages: 102-106(2025)
Published：30 September 2025
DOI：10.47297/taposatWSP2633-456921.20250609
Accepted：

Scan QR Code

Ouyang Yilin.Energy Efficiency Optimization of Industrial Internet of Things and Predictive Maintenance of Equipment[J].Theory and Practice of Science and Technology,2025,06(09):102-106.
DOI：

Ouyang Yilin.Energy Efficiency Optimization of Industrial Internet of Things and Predictive Maintenance of Equipment[J].Theory and Practice of Science and Technology,2025,06(09):102-106. DOI： 10.47297/taposatWSP2633-456921.20250609.

摘要

Abstract

This study aims to explore the key paths for energy efficiency optimization and predictive maintenance of equipment in the industrial Internet of Things (IoT) environment. In response to the challenges such as low utilization of on-site industrial data and the difficulty in balancing the real-time performance and economic efficiency of algorithms

modern industries mainly adopt solutions including association rule algorithms and neural network algorithms

and construct a collaborative architecture of "edge real-time perception + cloud global optimization". Meanwhile

to verify this method

the author designed a simulation scheme: taking the data from an engine factory as the object

the Apriori algorithm was used to mine the association rules of parameters such as temperature

humidity

and power

and a BP neural network dynamic prediction model was constructed. The parameters were optimized through gradient descent

and the effectiveness of the model in reducing unplanned downtime and energy consumption was ultimately evaluated

providing empirical evidence for industrial applications.

关键词

Keywords

references

H. Wang, J. Wang, Y. Zhao, Q. Liu, M. Liu and W. Shen. Few-shot Learning for Fault Diagnosis with a Dual Graph Neural Network. IEEE Transactions on Industrial Informatics, 2022.

Ma Shuaiyin, Ding Wei, Liu Yang, Ren Shan, Yang Haidong. Digital twin and big data-driven sustainable smart manufacturing based on information management systems for energy-intensive industries [J]. Applied Energy,2020.

Aragones R.; Oliver J.; Marlette R.; Oliver Parela M. Ferrer Model and Implementation of a New Thermoelectric Battery free IIoT Architecture for Predictive Industrial Maintenance,2024.

Casado-Vara, Roberto.C Distributed Contnuous-Time Fault Estmaton Control for Multple Devices in IoT Networks[J].Ieeexplore, 2019.

Springer Association Rule Mining: Recent Advances,2021.

A. Ceglar and J. F. Prddick. Associaton Mining[J]. ACM Computng Surveys, 2006.

Han.JandKamber.M.Data Mining: Concepts and Techniques[J]. Morgan Kaufmann,2006.

Wu Bin, Yu Chunmei, Li Qiang Process Industry Fault Diagnosis Science Press.

Shao Hanshu Research on Equipment Abnormal Monitoring and Fault Diagnosis Method Based on Equipment Management Industrial Internet of Things 2095-1302 (2025) 16-0087-04.

Li Ruozhu, Wang Jiaxin Industrial Internet of Things and Electronic Equipment Remote Detecton[J]. 1672-6413 (2025) 04-0216-03.

Xiao Lei and ZhangJie, Intelligent operaton and health management[M]. tsinghua university press, 2023.

Alert me when the article has been cited

Submit

No data

Related Author

No data

Related Institution

No data

⁰