IEPE accelerometer fault diagnosis for maintenance management system information integration in a heavy industry

Chao Chung Peng, Lin Ga Tsan

研究成果: Article

摘要

With the increasing demand for reliable production facilities, the design of a health condition monitoring system with the implementation of automatic diagnosis as well as software solutions is one of the main issues for a smart factory. Among many industrial applications, accelerometer is one of the most frequently used sensors for facility vibration monitoring. Thus, the health condition of the sensor itself is a critical factor for a correct diagnosis. Failure to monitor the sensor's health condition would potentially cause a false alarm, which may lead to a wrong decision making made by field operators. In this research, a preprocessing method of synthetic data and a Gaussian mixture model (GMM) classifier were developed to classify the health conditions of the online integrated electronic piezoelectric (IEPE) accelerometers. The proposed method was integrated into a product line and the test results achieved >99% of accuracy in determining five different health conditions of the accelerometers. With the aid of the proposed method, the time of human inspection can be significantly reduced and the field safety can also be improved. Moreover, false alarms caused by sensor failure can be prevented. This leads to increase in reliability of the facility monitoring system. 3 features to represent > 99% 3 features to represent > 99%

原文English
文章編號100120
期刊Journal of Industrial Information Integration
17
DOIs
出版狀態Published - 2020 三月

指紋

Accelerometers
Failure analysis
Information systems
Health
Sensors
Industry
Monitoring
Condition monitoring
Industrial applications
Industrial plants
Classifiers
Inspection
Decision making
Integrated
Fault diagnosis
Maintenance management
Information integration
Management system
Sensor
Monitoring system

All Science Journal Classification (ASJC) codes

  • Industrial and Manufacturing Engineering
  • Information Systems and Management

引用此文

@article{e86e843d18854195af2fa1552dd21af6,
title = "IEPE accelerometer fault diagnosis for maintenance management system information integration in a heavy industry",
abstract = "With the increasing demand for reliable production facilities, the design of a health condition monitoring system with the implementation of automatic diagnosis as well as software solutions is one of the main issues for a smart factory. Among many industrial applications, accelerometer is one of the most frequently used sensors for facility vibration monitoring. Thus, the health condition of the sensor itself is a critical factor for a correct diagnosis. Failure to monitor the sensor's health condition would potentially cause a false alarm, which may lead to a wrong decision making made by field operators. In this research, a preprocessing method of synthetic data and a Gaussian mixture model (GMM) classifier were developed to classify the health conditions of the online integrated electronic piezoelectric (IEPE) accelerometers. The proposed method was integrated into a product line and the test results achieved >99{\%} of accuracy in determining five different health conditions of the accelerometers. With the aid of the proposed method, the time of human inspection can be significantly reduced and the field safety can also be improved. Moreover, false alarms caused by sensor failure can be prevented. This leads to increase in reliability of the facility monitoring system. 3 features to represent > 99{\%} 3 features to represent > 99{\%}",
author = "Peng, {Chao Chung} and Tsan, {Lin Ga}",
year = "2020",
month = "3",
doi = "10.1016/j.jii.2019.100120",
language = "English",
volume = "17",
journal = "Journal of Industrial Information Integration",
issn = "2452-414X",
publisher = "Elsevier BV",

}

TY - JOUR

T1 - IEPE accelerometer fault diagnosis for maintenance management system information integration in a heavy industry

AU - Peng, Chao Chung

AU - Tsan, Lin Ga

PY - 2020/3

Y1 - 2020/3

N2 - With the increasing demand for reliable production facilities, the design of a health condition monitoring system with the implementation of automatic diagnosis as well as software solutions is one of the main issues for a smart factory. Among many industrial applications, accelerometer is one of the most frequently used sensors for facility vibration monitoring. Thus, the health condition of the sensor itself is a critical factor for a correct diagnosis. Failure to monitor the sensor's health condition would potentially cause a false alarm, which may lead to a wrong decision making made by field operators. In this research, a preprocessing method of synthetic data and a Gaussian mixture model (GMM) classifier were developed to classify the health conditions of the online integrated electronic piezoelectric (IEPE) accelerometers. The proposed method was integrated into a product line and the test results achieved >99% of accuracy in determining five different health conditions of the accelerometers. With the aid of the proposed method, the time of human inspection can be significantly reduced and the field safety can also be improved. Moreover, false alarms caused by sensor failure can be prevented. This leads to increase in reliability of the facility monitoring system. 3 features to represent > 99% 3 features to represent > 99%

AB - With the increasing demand for reliable production facilities, the design of a health condition monitoring system with the implementation of automatic diagnosis as well as software solutions is one of the main issues for a smart factory. Among many industrial applications, accelerometer is one of the most frequently used sensors for facility vibration monitoring. Thus, the health condition of the sensor itself is a critical factor for a correct diagnosis. Failure to monitor the sensor's health condition would potentially cause a false alarm, which may lead to a wrong decision making made by field operators. In this research, a preprocessing method of synthetic data and a Gaussian mixture model (GMM) classifier were developed to classify the health conditions of the online integrated electronic piezoelectric (IEPE) accelerometers. The proposed method was integrated into a product line and the test results achieved >99% of accuracy in determining five different health conditions of the accelerometers. With the aid of the proposed method, the time of human inspection can be significantly reduced and the field safety can also be improved. Moreover, false alarms caused by sensor failure can be prevented. This leads to increase in reliability of the facility monitoring system. 3 features to represent > 99% 3 features to represent > 99%

UR - http://www.scopus.com/inward/record.url?scp=85076516613&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85076516613&partnerID=8YFLogxK

U2 - 10.1016/j.jii.2019.100120

DO - 10.1016/j.jii.2019.100120

M3 - Article

AN - SCOPUS:85076516613

VL - 17

JO - Journal of Industrial Information Integration

JF - Journal of Industrial Information Integration

SN - 2452-414X

M1 - 100120

ER -