Fault Diagnosis and Prediction of Continuous Industrial Processes Based on Hidden Markov Model-Bayesian Network Hybrid Model
Hidden Markov models (HMMs) have been recently used for fault detection and prediction in continuous industrial processes; however, the expected maximum (EM) algorithm in the HMM has local optimality problems and cannot accurately find the fault root cause variables in complex industrial processes w...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-01-01
|
| Series: | International Journal of Chemical Engineering |
| Online Access: | http://dx.doi.org/10.1155/2022/3511073 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832552706563112960 |
|---|---|
| author | Jiarula Yasenjiang Chenxing Xu Shengpeng Zhang Xin Zhang |
| author_facet | Jiarula Yasenjiang Chenxing Xu Shengpeng Zhang Xin Zhang |
| author_sort | Jiarula Yasenjiang |
| collection | DOAJ |
| description | Hidden Markov models (HMMs) have been recently used for fault detection and prediction in continuous industrial processes; however, the expected maximum (EM) algorithm in the HMM has local optimality problems and cannot accurately find the fault root cause variables in complex industrial processes with high-dimensional data and strong variable coupling. To alleviate this problem, a hidden Markov model-Bayesian network (HMM-BN) hybrid model is proposed to alleviate the local optimum problem in the EM algorithm and diagnose the fault root cause variable. Firstly, the model introduces expert empirical knowledge for constructing BN to accurately diagnose the fault root cause variable. Then, the EM algorithm is improved by sequential and parallel learning to alleviate the initial sensitivity and local optimum problems. Finally, the log-likelihood estimates (LL) calculated by the improved hidden Markov model provide empirical evidence for the BN and give fault detection, prediction, and root cause variable detection results based on information about the similar increasing and decreasing patterns of LL for the training data and the online data. Combining the Tennessee Eastman (TE) process and the continuously stirred tank reactor (CSTR) process, the feasibility and effectiveness of the model are verified. The results show that the model can not only find the fault in time but also find the cause of the fault accurately. |
| format | Article |
| id | doaj-art-4fc90dc18ff6420cbaf9602dae0b6635 |
| institution | Kabale University |
| issn | 1687-8078 |
| language | English |
| publishDate | 2022-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | International Journal of Chemical Engineering |
| spelling | doaj-art-4fc90dc18ff6420cbaf9602dae0b66352025-02-03T05:57:56ZengWileyInternational Journal of Chemical Engineering1687-80782022-01-01202210.1155/2022/3511073Fault Diagnosis and Prediction of Continuous Industrial Processes Based on Hidden Markov Model-Bayesian Network Hybrid ModelJiarula Yasenjiang0Chenxing Xu1Shengpeng Zhang2Xin Zhang3Department of Industrial EngineeringDepartment of Industrial EngineeringChina National Petroleum Corporation Western Drilling and Engineering Research InstituteChina National Petroleum Corporation Western Drilling and Engineering Research InstituteHidden Markov models (HMMs) have been recently used for fault detection and prediction in continuous industrial processes; however, the expected maximum (EM) algorithm in the HMM has local optimality problems and cannot accurately find the fault root cause variables in complex industrial processes with high-dimensional data and strong variable coupling. To alleviate this problem, a hidden Markov model-Bayesian network (HMM-BN) hybrid model is proposed to alleviate the local optimum problem in the EM algorithm and diagnose the fault root cause variable. Firstly, the model introduces expert empirical knowledge for constructing BN to accurately diagnose the fault root cause variable. Then, the EM algorithm is improved by sequential and parallel learning to alleviate the initial sensitivity and local optimum problems. Finally, the log-likelihood estimates (LL) calculated by the improved hidden Markov model provide empirical evidence for the BN and give fault detection, prediction, and root cause variable detection results based on information about the similar increasing and decreasing patterns of LL for the training data and the online data. Combining the Tennessee Eastman (TE) process and the continuously stirred tank reactor (CSTR) process, the feasibility and effectiveness of the model are verified. The results show that the model can not only find the fault in time but also find the cause of the fault accurately.http://dx.doi.org/10.1155/2022/3511073 |
| spellingShingle | Jiarula Yasenjiang Chenxing Xu Shengpeng Zhang Xin Zhang Fault Diagnosis and Prediction of Continuous Industrial Processes Based on Hidden Markov Model-Bayesian Network Hybrid Model International Journal of Chemical Engineering |
| title | Fault Diagnosis and Prediction of Continuous Industrial Processes Based on Hidden Markov Model-Bayesian Network Hybrid Model |
| title_full | Fault Diagnosis and Prediction of Continuous Industrial Processes Based on Hidden Markov Model-Bayesian Network Hybrid Model |
| title_fullStr | Fault Diagnosis and Prediction of Continuous Industrial Processes Based on Hidden Markov Model-Bayesian Network Hybrid Model |
| title_full_unstemmed | Fault Diagnosis and Prediction of Continuous Industrial Processes Based on Hidden Markov Model-Bayesian Network Hybrid Model |
| title_short | Fault Diagnosis and Prediction of Continuous Industrial Processes Based on Hidden Markov Model-Bayesian Network Hybrid Model |
| title_sort | fault diagnosis and prediction of continuous industrial processes based on hidden markov model bayesian network hybrid model |
| url | http://dx.doi.org/10.1155/2022/3511073 |
| work_keys_str_mv | AT jiarulayasenjiang faultdiagnosisandpredictionofcontinuousindustrialprocessesbasedonhiddenmarkovmodelbayesiannetworkhybridmodel AT chenxingxu faultdiagnosisandpredictionofcontinuousindustrialprocessesbasedonhiddenmarkovmodelbayesiannetworkhybridmodel AT shengpengzhang faultdiagnosisandpredictionofcontinuousindustrialprocessesbasedonhiddenmarkovmodelbayesiannetworkhybridmodel AT xinzhang faultdiagnosisandpredictionofcontinuousindustrialprocessesbasedonhiddenmarkovmodelbayesiannetworkhybridmodel |