Application of Online Semi-Supervised Learning Embedded With Chaotic Dynamics in Equipment Health Prognostics
The development of artificial intelligence (AI) methods with high generalization and robustness for industrial equipment prognostics remains a significant challenge. Traditional lifespan prediction models often struggle with complex, dynamic tasks that require real-time performance, primarily due to...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/11037528/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850166122207248384 |
|---|---|
| author | Shuo Wang Jun Li Guangyu Hou Dezhi Yuan |
| author_facet | Shuo Wang Jun Li Guangyu Hou Dezhi Yuan |
| author_sort | Shuo Wang |
| collection | DOAJ |
| description | The development of artificial intelligence (AI) methods with high generalization and robustness for industrial equipment prognostics remains a significant challenge. Traditional lifespan prediction models often struggle with complex, dynamic tasks that require real-time performance, primarily due to limited data availability and the inherent constraints of supervised learning approaches. These models are typically overly reliant on labeled data, which is difficult to obtain in real-world industrial settings, and they suffer from poor dynamic adaptability when dealing with varying operating conditions. To address these limitations, we propose a novel data augmentation method inspired by chaos theory, designed specifically for real-time feature extraction from industrial equipment. In addition, we introduce a semi-supervised learning framework that integrates Kent mapping with model predictive control (MPC), enabling continuous, real-time correction of predictions. This approach is capable of learning from sparse labeled data while maintaining high accuracy in forecasting the remaining useful life (RUL) of critical industrial components, such as lithium-ion batteries, turbine engines, and bearings. By overcoming the traditional model limitations—such as excessive dependence on labeled data and poor adaptability to dynamic environments—our method demonstrates strong predictive capabilities and holds significant promise for real-world industrial applications, offering improved reliability and efficiency in equipment health monitoring and maintenance planning. |
| format | Article |
| id | doaj-art-879f84db2e9d455caec4f6510b42ced5 |
| institution | OA Journals |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-879f84db2e9d455caec4f6510b42ced52025-08-20T02:21:33ZengIEEEIEEE Access2169-35362025-01-011310398210399410.1109/ACCESS.2025.358026711037528Application of Online Semi-Supervised Learning Embedded With Chaotic Dynamics in Equipment Health PrognosticsShuo Wang0https://orcid.org/0009-0008-5280-850XJun Li1https://orcid.org/0009-0008-7474-1326Guangyu Hou2Dezhi Yuan3https://orcid.org/0000-0001-6655-3204School of Electrical and Electronic Engineering, Shanghai Institute of Technology, Shanghai, ChinaSchool of Electrical and Electronic Engineering, Shanghai Institute of Technology, Shanghai, ChinaDepartment of Science Island, University of Science and Technology of China, Hefei, ChinaSchool of Electrical and Electronic Engineering, Shanghai Institute of Technology, Shanghai, ChinaThe development of artificial intelligence (AI) methods with high generalization and robustness for industrial equipment prognostics remains a significant challenge. Traditional lifespan prediction models often struggle with complex, dynamic tasks that require real-time performance, primarily due to limited data availability and the inherent constraints of supervised learning approaches. These models are typically overly reliant on labeled data, which is difficult to obtain in real-world industrial settings, and they suffer from poor dynamic adaptability when dealing with varying operating conditions. To address these limitations, we propose a novel data augmentation method inspired by chaos theory, designed specifically for real-time feature extraction from industrial equipment. In addition, we introduce a semi-supervised learning framework that integrates Kent mapping with model predictive control (MPC), enabling continuous, real-time correction of predictions. This approach is capable of learning from sparse labeled data while maintaining high accuracy in forecasting the remaining useful life (RUL) of critical industrial components, such as lithium-ion batteries, turbine engines, and bearings. By overcoming the traditional model limitations—such as excessive dependence on labeled data and poor adaptability to dynamic environments—our method demonstrates strong predictive capabilities and holds significant promise for real-world industrial applications, offering improved reliability and efficiency in equipment health monitoring and maintenance planning.https://ieeexplore.ieee.org/document/11037528/Health prognosticssemi-supervisedchaotic dynamicsdata augmentationremaining useful life |
| spellingShingle | Shuo Wang Jun Li Guangyu Hou Dezhi Yuan Application of Online Semi-Supervised Learning Embedded With Chaotic Dynamics in Equipment Health Prognostics IEEE Access Health prognostics semi-supervised chaotic dynamics data augmentation remaining useful life |
| title | Application of Online Semi-Supervised Learning Embedded With Chaotic Dynamics in Equipment Health Prognostics |
| title_full | Application of Online Semi-Supervised Learning Embedded With Chaotic Dynamics in Equipment Health Prognostics |
| title_fullStr | Application of Online Semi-Supervised Learning Embedded With Chaotic Dynamics in Equipment Health Prognostics |
| title_full_unstemmed | Application of Online Semi-Supervised Learning Embedded With Chaotic Dynamics in Equipment Health Prognostics |
| title_short | Application of Online Semi-Supervised Learning Embedded With Chaotic Dynamics in Equipment Health Prognostics |
| title_sort | application of online semi supervised learning embedded with chaotic dynamics in equipment health prognostics |
| topic | Health prognostics semi-supervised chaotic dynamics data augmentation remaining useful life |
| url | https://ieeexplore.ieee.org/document/11037528/ |
| work_keys_str_mv | AT shuowang applicationofonlinesemisupervisedlearningembeddedwithchaoticdynamicsinequipmenthealthprognostics AT junli applicationofonlinesemisupervisedlearningembeddedwithchaoticdynamicsinequipmenthealthprognostics AT guangyuhou applicationofonlinesemisupervisedlearningembeddedwithchaoticdynamicsinequipmenthealthprognostics AT dezhiyuan applicationofonlinesemisupervisedlearningembeddedwithchaoticdynamicsinequipmenthealthprognostics |