A Decision-Making Method for Machinery Abnormalities Based on Neural Network Prediction and Bayesian Hypothesis Testing
For anomaly identification of predicted data in machinery condition monitoring, traditional threshold methods have problems during residual testing. It is difficult to make decisions when the residuals are close to the threshold and fluctuate. This paper proposes a Bayesian dynamic thresholding meth...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-07-01
|
Series: | Electronics |
Subjects: | |
Online Access: | https://www.mdpi.com/2079-9292/10/14/1610 |
_version_ | 1797527282833686528 |
---|---|
author | Gaojun Liu Shan Yang Gaixia Wang Fenglei Li Dongdong You |
author_facet | Gaojun Liu Shan Yang Gaixia Wang Fenglei Li Dongdong You |
author_sort | Gaojun Liu |
collection | DOAJ |
description | For anomaly identification of predicted data in machinery condition monitoring, traditional threshold methods have problems during residual testing. It is difficult to make decisions when the residuals are close to the threshold and fluctuate. This paper proposes a Bayesian dynamic thresholding method that combines Bayesian inference with neural network signal prediction. The method makes full use of historical prior data to build an anomaly identification and warning model applicable under single variable or multidimensional variables. A long short-term memory signal prediction model is established, and then a Bayesian hypothesis testing-based anomaly identification strategy is presented to quantify the probability of anomaly occurrence and issue early warnings for anomalies beyond a certain probability. The model was applied to open data sets of a pumping station and actual operating data of a nuclear power turbine. The results indicate that the model successfully predicts the failure probability and failure time. The effectiveness of the proposed method is verified. |
first_indexed | 2024-03-10T09:40:46Z |
format | Article |
id | doaj.art-05d627c633144c28affcd04f1acdcd87 |
institution | Directory Open Access Journal |
issn | 2079-9292 |
language | English |
last_indexed | 2024-03-10T09:40:46Z |
publishDate | 2021-07-01 |
publisher | MDPI AG |
record_format | Article |
series | Electronics |
spelling | doaj.art-05d627c633144c28affcd04f1acdcd872023-11-22T03:37:12ZengMDPI AGElectronics2079-92922021-07-011014161010.3390/electronics10141610A Decision-Making Method for Machinery Abnormalities Based on Neural Network Prediction and Bayesian Hypothesis TestingGaojun Liu0Shan Yang1Gaixia Wang2Fenglei Li3Dongdong You4State Key Laboratory of Nuclear Power Safety Monitoring Technology and Equipment, China Nuclear Power Engineering Company Ltd., Shenzhen 518172, ChinaSchool of Mechanical and Automotive Engineering, South China University of Technology, Guangzhou 510640, ChinaState Key Laboratory of Nuclear Power Safety Monitoring Technology and Equipment, China Nuclear Power Engineering Company Ltd., Shenzhen 518172, ChinaSchool of Mechanical and Automotive Engineering, South China University of Technology, Guangzhou 510640, ChinaSchool of Mechanical and Automotive Engineering, South China University of Technology, Guangzhou 510640, ChinaFor anomaly identification of predicted data in machinery condition monitoring, traditional threshold methods have problems during residual testing. It is difficult to make decisions when the residuals are close to the threshold and fluctuate. This paper proposes a Bayesian dynamic thresholding method that combines Bayesian inference with neural network signal prediction. The method makes full use of historical prior data to build an anomaly identification and warning model applicable under single variable or multidimensional variables. A long short-term memory signal prediction model is established, and then a Bayesian hypothesis testing-based anomaly identification strategy is presented to quantify the probability of anomaly occurrence and issue early warnings for anomalies beyond a certain probability. The model was applied to open data sets of a pumping station and actual operating data of a nuclear power turbine. The results indicate that the model successfully predicts the failure probability and failure time. The effectiveness of the proposed method is verified.https://www.mdpi.com/2079-9292/10/14/1610Bayesian hypothesis testingabnormality identificationlong short-term memorynuclear power turbine |
spellingShingle | Gaojun Liu Shan Yang Gaixia Wang Fenglei Li Dongdong You A Decision-Making Method for Machinery Abnormalities Based on Neural Network Prediction and Bayesian Hypothesis Testing Electronics Bayesian hypothesis testing abnormality identification long short-term memory nuclear power turbine |
title | A Decision-Making Method for Machinery Abnormalities Based on Neural Network Prediction and Bayesian Hypothesis Testing |
title_full | A Decision-Making Method for Machinery Abnormalities Based on Neural Network Prediction and Bayesian Hypothesis Testing |
title_fullStr | A Decision-Making Method for Machinery Abnormalities Based on Neural Network Prediction and Bayesian Hypothesis Testing |
title_full_unstemmed | A Decision-Making Method for Machinery Abnormalities Based on Neural Network Prediction and Bayesian Hypothesis Testing |
title_short | A Decision-Making Method for Machinery Abnormalities Based on Neural Network Prediction and Bayesian Hypothesis Testing |
title_sort | decision making method for machinery abnormalities based on neural network prediction and bayesian hypothesis testing |
topic | Bayesian hypothesis testing abnormality identification long short-term memory nuclear power turbine |
url | https://www.mdpi.com/2079-9292/10/14/1610 |
work_keys_str_mv | AT gaojunliu adecisionmakingmethodformachineryabnormalitiesbasedonneuralnetworkpredictionandbayesianhypothesistesting AT shanyang adecisionmakingmethodformachineryabnormalitiesbasedonneuralnetworkpredictionandbayesianhypothesistesting AT gaixiawang adecisionmakingmethodformachineryabnormalitiesbasedonneuralnetworkpredictionandbayesianhypothesistesting AT fengleili adecisionmakingmethodformachineryabnormalitiesbasedonneuralnetworkpredictionandbayesianhypothesistesting AT dongdongyou adecisionmakingmethodformachineryabnormalitiesbasedonneuralnetworkpredictionandbayesianhypothesistesting AT gaojunliu decisionmakingmethodformachineryabnormalitiesbasedonneuralnetworkpredictionandbayesianhypothesistesting AT shanyang decisionmakingmethodformachineryabnormalitiesbasedonneuralnetworkpredictionandbayesianhypothesistesting AT gaixiawang decisionmakingmethodformachineryabnormalitiesbasedonneuralnetworkpredictionandbayesianhypothesistesting AT fengleili decisionmakingmethodformachineryabnormalitiesbasedonneuralnetworkpredictionandbayesianhypothesistesting AT dongdongyou decisionmakingmethodformachineryabnormalitiesbasedonneuralnetworkpredictionandbayesianhypothesistesting |