An EPS-kNN Fault Propagation Analysis Method for Industrial Processes Based on the Fusion of Knowledge and Data

To reduce the false connections resulting from numerous redundant paths in the fault propagation analysis for industrial processes, an equal probability symbolized k-nearest neighbors (EPS-kNN) fault propagation analysis method based on the fusion of fault data and process knowledge is proposed. Sub...

Full description

Saved in:
Bibliographic Details
Main Authors: Wang Lixin, Qian Xiaoyi, Feng Yanliang, Dai Ziheng, Kang Changsheng, Guan Shuai, Zhao Yi
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10955191/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849311876258725888
author Wang Lixin
Qian Xiaoyi
Feng Yanliang
Dai Ziheng
Kang Changsheng
Guan Shuai
Zhao Yi
author_facet Wang Lixin
Qian Xiaoyi
Feng Yanliang
Dai Ziheng
Kang Changsheng
Guan Shuai
Zhao Yi
author_sort Wang Lixin
collection DOAJ
description To reduce the false connections resulting from numerous redundant paths in the fault propagation analysis for industrial processes, an equal probability symbolized k-nearest neighbors (EPS-kNN) fault propagation analysis method based on the fusion of fault data and process knowledge is proposed. Subblock interaction monitoring is introduced to identify potential fault areas and eliminate redundant variables. The complex network model is incorporated into the EPS-kNN-based fault propagation path identification to improve accuracy and interpretability. Different types of faults in the Tennessee Eastman process and Ammonia synthesis process are applied to verify the effectiveness, and the result shows that the proposed method can identify the fault propagation path more effectively and reduce the occurrence of false connections compared with the traditional methods.
format Article
id doaj-art-4ad2a761bcde44fbb04681cc6e3efec6
institution Kabale University
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-4ad2a761bcde44fbb04681cc6e3efec62025-08-20T03:53:17ZengIEEEIEEE Access2169-35362025-01-0113783357834710.1109/ACCESS.2025.355863110955191An EPS-kNN Fault Propagation Analysis Method for Industrial Processes Based on the Fusion of Knowledge and DataWang Lixin0https://orcid.org/0009-0009-9281-0249Qian Xiaoyi1https://orcid.org/0000-0002-3926-6813Feng Yanliang2Dai Ziheng3https://orcid.org/0009-0002-5596-5734Kang Changsheng4https://orcid.org/0009-0006-3994-7834Guan Shuai5Zhao Yi6Liaoning Key Laboratory of Power Grid Energy Conservation and Control, Shenyang Institute of Engineering, Shenyang, ChinaLiaoning Key Laboratory of Power Grid Energy Conservation and Control, Shenyang Institute of Engineering, Shenyang, ChinaState Grid Liaoning Electric Power Company Ltd., Yingkou Power Supply Company, Yingkou, ChinaLiaoning Key Laboratory of Power Grid Energy Conservation and Control, Shenyang Institute of Engineering, Shenyang, ChinaLiaoning Key Laboratory of Power Grid Energy Conservation and Control, Shenyang Institute of Engineering, Shenyang, ChinaLiaoning Key Laboratory of Power Grid Energy Conservation and Control, Shenyang Institute of Engineering, Shenyang, ChinaLiaoning Key Laboratory of Power Grid Energy Conservation and Control, Shenyang Institute of Engineering, Shenyang, ChinaTo reduce the false connections resulting from numerous redundant paths in the fault propagation analysis for industrial processes, an equal probability symbolized k-nearest neighbors (EPS-kNN) fault propagation analysis method based on the fusion of fault data and process knowledge is proposed. Subblock interaction monitoring is introduced to identify potential fault areas and eliminate redundant variables. The complex network model is incorporated into the EPS-kNN-based fault propagation path identification to improve accuracy and interpretability. Different types of faults in the Tennessee Eastman process and Ammonia synthesis process are applied to verify the effectiveness, and the result shows that the proposed method can identify the fault propagation path more effectively and reduce the occurrence of false connections compared with the traditional methods.https://ieeexplore.ieee.org/document/10955191/Complex network modelfault propagation pathk-nearest neighborssubblock interaction monitoring
spellingShingle Wang Lixin
Qian Xiaoyi
Feng Yanliang
Dai Ziheng
Kang Changsheng
Guan Shuai
Zhao Yi
An EPS-kNN Fault Propagation Analysis Method for Industrial Processes Based on the Fusion of Knowledge and Data
IEEE Access
Complex network model
fault propagation path
k-nearest neighbors
subblock interaction monitoring
title An EPS-kNN Fault Propagation Analysis Method for Industrial Processes Based on the Fusion of Knowledge and Data
title_full An EPS-kNN Fault Propagation Analysis Method for Industrial Processes Based on the Fusion of Knowledge and Data
title_fullStr An EPS-kNN Fault Propagation Analysis Method for Industrial Processes Based on the Fusion of Knowledge and Data
title_full_unstemmed An EPS-kNN Fault Propagation Analysis Method for Industrial Processes Based on the Fusion of Knowledge and Data
title_short An EPS-kNN Fault Propagation Analysis Method for Industrial Processes Based on the Fusion of Knowledge and Data
title_sort eps knn fault propagation analysis method for industrial processes based on the fusion of knowledge and data
topic Complex network model
fault propagation path
k-nearest neighbors
subblock interaction monitoring
url https://ieeexplore.ieee.org/document/10955191/
work_keys_str_mv AT wanglixin anepsknnfaultpropagationanalysismethodforindustrialprocessesbasedonthefusionofknowledgeanddata
AT qianxiaoyi anepsknnfaultpropagationanalysismethodforindustrialprocessesbasedonthefusionofknowledgeanddata
AT fengyanliang anepsknnfaultpropagationanalysismethodforindustrialprocessesbasedonthefusionofknowledgeanddata
AT daiziheng anepsknnfaultpropagationanalysismethodforindustrialprocessesbasedonthefusionofknowledgeanddata
AT kangchangsheng anepsknnfaultpropagationanalysismethodforindustrialprocessesbasedonthefusionofknowledgeanddata
AT guanshuai anepsknnfaultpropagationanalysismethodforindustrialprocessesbasedonthefusionofknowledgeanddata
AT zhaoyi anepsknnfaultpropagationanalysismethodforindustrialprocessesbasedonthefusionofknowledgeanddata
AT wanglixin epsknnfaultpropagationanalysismethodforindustrialprocessesbasedonthefusionofknowledgeanddata
AT qianxiaoyi epsknnfaultpropagationanalysismethodforindustrialprocessesbasedonthefusionofknowledgeanddata
AT fengyanliang epsknnfaultpropagationanalysismethodforindustrialprocessesbasedonthefusionofknowledgeanddata
AT daiziheng epsknnfaultpropagationanalysismethodforindustrialprocessesbasedonthefusionofknowledgeanddata
AT kangchangsheng epsknnfaultpropagationanalysismethodforindustrialprocessesbasedonthefusionofknowledgeanddata
AT guanshuai epsknnfaultpropagationanalysismethodforindustrialprocessesbasedonthefusionofknowledgeanddata
AT zhaoyi epsknnfaultpropagationanalysismethodforindustrialprocessesbasedonthefusionofknowledgeanddata