A novel dynamic machine learning-based explainable fusion monitoring: application to industrial and chemical processes
The complexity and fusion dynamism of the modern industrial and chemical sectors have been increasing with the rapid progress of IR 4.0–5.0. The transformative characteristics of Industry 4.0–5.0 have not been fully explored in terms of the fundamental importance of explainability. Traditional monit...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IOP Publishing
2025-01-01
|
| Series: | Machine Learning: Science and Technology |
| Subjects: | |
| Online Access: | https://doi.org/10.1088/2632-2153/ada088 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841543413573353472 |
|---|---|
| author | Husnain Ali Rizwan Safdar Yuanqiang Zhou Yuan Yao Le Yao Zheng Zhang Weilong Ding Furong Gao |
| author_facet | Husnain Ali Rizwan Safdar Yuanqiang Zhou Yuan Yao Le Yao Zheng Zhang Weilong Ding Furong Gao |
| author_sort | Husnain Ali |
| collection | DOAJ |
| description | The complexity and fusion dynamism of the modern industrial and chemical sectors have been increasing with the rapid progress of IR 4.0–5.0. The transformative characteristics of Industry 4.0–5.0 have not been fully explored in terms of the fundamental importance of explainability. Traditional monitoring techniques for automatic anomaly detection, identifying the potential variables, and root cause analysis for fault information are not intelligent enough to tackle the intricate problems of real-time practices in the industrial and chemical sectors. This study presents a novel dynamic machine learning based explainable fusion approach to address the issues of process monitoring in industrial and chemical process systems. The methodology aims to detect faults, identify their key causes and feature variables, and analyze the root path of fault propagation with the time and magnitude of one cause variable to another impact. This study proposed using a time domain multivariate granger-entropy-aided dynamic independent component analysis (DICA)—distributed canonical correlation analysis approach, incorporating the dynamics time wrapping supported time delay-signed directed graph. The proposed methodology utilized the application to industrial and chemical processes and verified using the continuous stirred tank reactor and Tennessee Eastman process as practical application benchmarks. The framework’s validations and efficiency are evaluated using established techniques such as classic computed ICA and DICA as standard model scenarios. The outcomes and results showed that the newly developed strategy is preferable to previous approaches regarding explainability and robust detection and identification of the actual root causes with high FDRs and low FARs. |
| format | Article |
| id | doaj-art-96e03d63d7eb4d6987d7ea9822a66721 |
| institution | Kabale University |
| issn | 2632-2153 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IOP Publishing |
| record_format | Article |
| series | Machine Learning: Science and Technology |
| spelling | doaj-art-96e03d63d7eb4d6987d7ea9822a667212025-01-13T12:20:28ZengIOP PublishingMachine Learning: Science and Technology2632-21532025-01-016101500510.1088/2632-2153/ada088A novel dynamic machine learning-based explainable fusion monitoring: application to industrial and chemical processesHusnain Ali0https://orcid.org/0000-0002-4877-1045Rizwan Safdar1https://orcid.org/0000-0002-9889-4289Yuanqiang Zhou2https://orcid.org/0000-0002-0269-4726Yuan Yao3https://orcid.org/0000-0002-0025-6175Le Yao4Zheng Zhang5Weilong Ding6Furong Gao7https://orcid.org/0000-0002-5900-1353Department of Chemical and Biological Engineering, Hong Kong University of Science and Technology , Hong Kong Special Administrative Region of China, People’s Republic of ChinaHenan Province International Collaboration Lab of Forest Resources Utilization, School of Forestry, Henan Agricultural University , Zhengzhou 450002, People’s Republic of ChinaCollege of Electronic and Information Engineering, Tongji University , Shanghai 201804, People’s Republic of ChinaDepartment of Chemical Engineering, National Tsing Hua University , Hsinchu 30013, TaiwanSchool of Mathematics, Hangzhou Normal University , Hangzhou, People’s Republic of ChinaDepartment of Chemical and Biological Engineering, Hong Kong University of Science and Technology , Hong Kong Special Administrative Region of China, People’s Republic of ChinaDepartment of Chemical and Biological Engineering, Hong Kong University of Science and Technology , Hong Kong Special Administrative Region of China, People’s Republic of ChinaDepartment of Chemical and Biological Engineering, Hong Kong University of Science and Technology , Hong Kong Special Administrative Region of China, People’s Republic of China; Guangzhou HKUST, Fok Ying Tung Research Institute , Guangzhou 511458, People’s Republic of ChinaThe complexity and fusion dynamism of the modern industrial and chemical sectors have been increasing with the rapid progress of IR 4.0–5.0. The transformative characteristics of Industry 4.0–5.0 have not been fully explored in terms of the fundamental importance of explainability. Traditional monitoring techniques for automatic anomaly detection, identifying the potential variables, and root cause analysis for fault information are not intelligent enough to tackle the intricate problems of real-time practices in the industrial and chemical sectors. This study presents a novel dynamic machine learning based explainable fusion approach to address the issues of process monitoring in industrial and chemical process systems. The methodology aims to detect faults, identify their key causes and feature variables, and analyze the root path of fault propagation with the time and magnitude of one cause variable to another impact. This study proposed using a time domain multivariate granger-entropy-aided dynamic independent component analysis (DICA)—distributed canonical correlation analysis approach, incorporating the dynamics time wrapping supported time delay-signed directed graph. The proposed methodology utilized the application to industrial and chemical processes and verified using the continuous stirred tank reactor and Tennessee Eastman process as practical application benchmarks. The framework’s validations and efficiency are evaluated using established techniques such as classic computed ICA and DICA as standard model scenarios. The outcomes and results showed that the newly developed strategy is preferable to previous approaches regarding explainability and robust detection and identification of the actual root causes with high FDRs and low FARs.https://doi.org/10.1088/2632-2153/ada088industry 4.0process monitoringmachine learningexplainableactual root propagationCSTR |
| spellingShingle | Husnain Ali Rizwan Safdar Yuanqiang Zhou Yuan Yao Le Yao Zheng Zhang Weilong Ding Furong Gao A novel dynamic machine learning-based explainable fusion monitoring: application to industrial and chemical processes Machine Learning: Science and Technology industry 4.0 process monitoring machine learning explainable actual root propagation CSTR |
| title | A novel dynamic machine learning-based explainable fusion monitoring: application to industrial and chemical processes |
| title_full | A novel dynamic machine learning-based explainable fusion monitoring: application to industrial and chemical processes |
| title_fullStr | A novel dynamic machine learning-based explainable fusion monitoring: application to industrial and chemical processes |
| title_full_unstemmed | A novel dynamic machine learning-based explainable fusion monitoring: application to industrial and chemical processes |
| title_short | A novel dynamic machine learning-based explainable fusion monitoring: application to industrial and chemical processes |
| title_sort | novel dynamic machine learning based explainable fusion monitoring application to industrial and chemical processes |
| topic | industry 4.0 process monitoring machine learning explainable actual root propagation CSTR |
| url | https://doi.org/10.1088/2632-2153/ada088 |
| work_keys_str_mv | AT husnainali anoveldynamicmachinelearningbasedexplainablefusionmonitoringapplicationtoindustrialandchemicalprocesses AT rizwansafdar anoveldynamicmachinelearningbasedexplainablefusionmonitoringapplicationtoindustrialandchemicalprocesses AT yuanqiangzhou anoveldynamicmachinelearningbasedexplainablefusionmonitoringapplicationtoindustrialandchemicalprocesses AT yuanyao anoveldynamicmachinelearningbasedexplainablefusionmonitoringapplicationtoindustrialandchemicalprocesses AT leyao anoveldynamicmachinelearningbasedexplainablefusionmonitoringapplicationtoindustrialandchemicalprocesses AT zhengzhang anoveldynamicmachinelearningbasedexplainablefusionmonitoringapplicationtoindustrialandchemicalprocesses AT weilongding anoveldynamicmachinelearningbasedexplainablefusionmonitoringapplicationtoindustrialandchemicalprocesses AT furonggao anoveldynamicmachinelearningbasedexplainablefusionmonitoringapplicationtoindustrialandchemicalprocesses AT husnainali noveldynamicmachinelearningbasedexplainablefusionmonitoringapplicationtoindustrialandchemicalprocesses AT rizwansafdar noveldynamicmachinelearningbasedexplainablefusionmonitoringapplicationtoindustrialandchemicalprocesses AT yuanqiangzhou noveldynamicmachinelearningbasedexplainablefusionmonitoringapplicationtoindustrialandchemicalprocesses AT yuanyao noveldynamicmachinelearningbasedexplainablefusionmonitoringapplicationtoindustrialandchemicalprocesses AT leyao noveldynamicmachinelearningbasedexplainablefusionmonitoringapplicationtoindustrialandchemicalprocesses AT zhengzhang noveldynamicmachinelearningbasedexplainablefusionmonitoringapplicationtoindustrialandchemicalprocesses AT weilongding noveldynamicmachinelearningbasedexplainablefusionmonitoringapplicationtoindustrialandchemicalprocesses AT furonggao noveldynamicmachinelearningbasedexplainablefusionmonitoringapplicationtoindustrialandchemicalprocesses |