Fault Diagnosis for Centrifugal Chiller Based on PSO-BP
In this study, a BP (back-propagation network) neural network, optimized by PSO (particle swarm optimization) was applied to the fault diagnosis of a centrifugal chiller. Seven typical faults, including four component-level and three system-level faults, were investigated. Results showed that the pe...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Journal of Refrigeration Magazines Agency Co., Ltd.
2019-01-01
|
| Series: | Zhileng xuebao |
| Subjects: | |
| Online Access: | http://www.zhilengxuebao.com/thesisDetails#10.3969/j.issn.0253-4339.2019.03.115 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849707803047886848 |
|---|---|
| author | Xu Ling Han Hua Cui Xiaoyu Fan Yuqiang Wu Hao |
| author_facet | Xu Ling Han Hua Cui Xiaoyu Fan Yuqiang Wu Hao |
| author_sort | Xu Ling |
| collection | DOAJ |
| description | In this study, a BP (back-propagation network) neural network, optimized by PSO (particle swarm optimization) was applied to the fault diagnosis of a centrifugal chiller. Seven typical faults, including four component-level and three system-level faults, were investigated. Results showed that the performance of fault diagnosis was significantly improved (for both single- and double-hidden BP layers) compared with the model without PSO. The optimization simplified the structure of the neural network from 18 neurons to 10 neurons for a single-hidden-layer network and from 25 neurons to 12 neurons for a double-hidden-layer network. This increased the correct rate of fault diagnosis from 89.42% to 95.30% and from 97.87% to 98.11% for single-hidden-layer network and double-hidden-layer network, respectively. There are also considerable savings in diagnostic time, especially for the double-hidden–layer network, to only 23% of that before optimization. The cases of "false report" and "leaked report" have been reduced, and the false alarm rate is also lower than before. Moreover, the diagnosis performance of the system-level fault, especially the RefLeak (Refrigerant Leakage), and the recognition rate of the normal condition are greatly improved. Through PSO, the BP network is able to jump out of the local minimum and greatly improve the fault diagnosis performance for the centrifugal chiller. |
| format | Article |
| id | doaj-art-7725ff22e90b488b89d6d28b340c3d1d |
| institution | DOAJ |
| issn | 0253-4339 |
| language | zho |
| publishDate | 2019-01-01 |
| publisher | Journal of Refrigeration Magazines Agency Co., Ltd. |
| record_format | Article |
| series | Zhileng xuebao |
| spelling | doaj-art-7725ff22e90b488b89d6d28b340c3d1d2025-08-20T03:15:50ZzhoJournal of Refrigeration Magazines Agency Co., Ltd.Zhileng xuebao0253-43392019-01-014066510324Fault Diagnosis for Centrifugal Chiller Based on PSO-BPXu LingHan HuaCui XiaoyuFan YuqiangWu HaoIn this study, a BP (back-propagation network) neural network, optimized by PSO (particle swarm optimization) was applied to the fault diagnosis of a centrifugal chiller. Seven typical faults, including four component-level and three system-level faults, were investigated. Results showed that the performance of fault diagnosis was significantly improved (for both single- and double-hidden BP layers) compared with the model without PSO. The optimization simplified the structure of the neural network from 18 neurons to 10 neurons for a single-hidden-layer network and from 25 neurons to 12 neurons for a double-hidden-layer network. This increased the correct rate of fault diagnosis from 89.42% to 95.30% and from 97.87% to 98.11% for single-hidden-layer network and double-hidden-layer network, respectively. There are also considerable savings in diagnostic time, especially for the double-hidden–layer network, to only 23% of that before optimization. The cases of "false report" and "leaked report" have been reduced, and the false alarm rate is also lower than before. Moreover, the diagnosis performance of the system-level fault, especially the RefLeak (Refrigerant Leakage), and the recognition rate of the normal condition are greatly improved. Through PSO, the BP network is able to jump out of the local minimum and greatly improve the fault diagnosis performance for the centrifugal chiller.http://www.zhilengxuebao.com/thesisDetails#10.3969/j.issn.0253-4339.2019.03.115chillerfault diagnosisparticle swarm optimization (PSO)back-propagation (BP) networkfalse alarm rate |
| spellingShingle | Xu Ling Han Hua Cui Xiaoyu Fan Yuqiang Wu Hao Fault Diagnosis for Centrifugal Chiller Based on PSO-BP Zhileng xuebao chiller fault diagnosis particle swarm optimization (PSO) back-propagation (BP) network false alarm rate |
| title | Fault Diagnosis for Centrifugal Chiller Based on PSO-BP |
| title_full | Fault Diagnosis for Centrifugal Chiller Based on PSO-BP |
| title_fullStr | Fault Diagnosis for Centrifugal Chiller Based on PSO-BP |
| title_full_unstemmed | Fault Diagnosis for Centrifugal Chiller Based on PSO-BP |
| title_short | Fault Diagnosis for Centrifugal Chiller Based on PSO-BP |
| title_sort | fault diagnosis for centrifugal chiller based on pso bp |
| topic | chiller fault diagnosis particle swarm optimization (PSO) back-propagation (BP) network false alarm rate |
| url | http://www.zhilengxuebao.com/thesisDetails#10.3969/j.issn.0253-4339.2019.03.115 |
| work_keys_str_mv | AT xuling faultdiagnosisforcentrifugalchillerbasedonpsobp AT hanhua faultdiagnosisforcentrifugalchillerbasedonpsobp AT cuixiaoyu faultdiagnosisforcentrifugalchillerbasedonpsobp AT fanyuqiang faultdiagnosisforcentrifugalchillerbasedonpsobp AT wuhao faultdiagnosisforcentrifugalchillerbasedonpsobp |