期刊
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
卷 17, 期 12, 页码 7923-7932出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TII.2021.3056076
关键词
Monitoring; Industrial Internet of Things; Edge computing; Mel frequency cepstral coefficient; Servers; Computer architecture; Computational modeling; Abnormal; fault detection; fog computing; Industrial Internet of Things (IIoT); Industry 4; 0; Internet of Things (IoT); machine learning (ML); malfunction; normal; supervised learning
类别
资金
- Visvesvaraya Ph.D. Scheme for Electronics and IT (Media Lab Asia), the Department of MeitY, Government of India
This article discusses the method of diagnosing machine faults in industrial environments using fog computing architecture, judging the normal and abnormal states of machines through their operating sounds and monitoring.
There is an exponential increase in the use of Industrial Internet of Things (IIoT) devices for controlling and monitoring the machines in an automated manufacturing industry. Different temperature sensors, pressure sensors, audio sensors, and camera devices are used as IIoT devices for pipeline monitoring and machine operation control in the industrial environment. But, monitoring and identifying the machine malfunction in an industrial environment is a challenging task. In this article, we consider machines fault diagnosis based on their operating sound using the fog computing architecture in the industrial environment. The different computing units, such as industrial controller units or micro data center are used as the fog server in the industrial environment to analyze and classify the machine sounds as normal and abnormal. The linear prediction coefficients and Mel-frequency cepstral coefficients are extracted from the machine sound to develop and deploy supervised machine learning (ML) models on the fog server to monitor and identify the malfunctioning machines based on the operating sound. The experimental results show the performance of ML models for the machines sound recorded with different signal-to-noise ratio levels for normal and abnormal operations.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据