Scalable fault models for diagnosis in a synchronous generator using feature mapping and transformation techniques
Condition based maintenance (CBM) needs data acquired during healthy and faulty conditions to develop intelligent system for fault diagnosis. However, fault injection is not allowed/possible in a highly expensive components of complex/critical systems to collect fault condition data. Therefore, prot...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
The Prognostics and Health Management Society
2018-06-01
|
| Series: | International Journal of Prognostics and Health Management |
| Subjects: | |
| Online Access: | https://papers.phmsociety.org/index.php/ijphm/article/view/2737 |
| _version_ | 1818455481756155904 |
|---|---|
| author | R. Gopinath C. Santhosh Kumar R. I. Ramachandran |
| author_facet | R. Gopinath C. Santhosh Kumar R. I. Ramachandran |
| author_sort | R. Gopinath |
| collection | DOAJ |
| description | Condition based maintenance (CBM) needs data acquired during healthy and faulty conditions to develop intelligent system for fault diagnosis. However, fault injection is not allowed/possible in a highly expensive components of complex/critical systems to collect fault condition data. Therefore, proto-type/small working models are used to conduct experiments for abnormal/fault conditions, to obtain and scale the intelligence of the system for effective health monitoring of complex system. This methodology is referred as scalable fault models. For proof of concept, in this work, we considered two different capacity synchronous generators with rating of 3 kVA and 5 kVA to emulate the behavior of prototype/small working model and complex system respectively, for scalable fault models. We explored feature mapping and transformation techniques to achieve effective scalability.
From the preliminary experiments, it is observed that the baseline system performance deteriorated due to the changes in the system (capacity) and its characteristics with load changes.
We therefore, expressed the input features in terms of load and system independent manner, to make the features less dependent on load and system variations. We explored locality constrained linear coding (LLC) to express the features load/system independently. It is observed that experimenting LLC with the backend support vector machine (SVM) classifier gave the best fault classification performance for linear kernel, suggesting that the faults are linearly separable in the new feature space.
Since the LLC mapped feature space is linearly separable, we then explored linear feature transformation technique, nuisance attribute projection (NAP) on the LLC mapped feature space to further minimize the load/system specific variations. We observed that LLC-NAP improved the overall accuracy and sensitivity of the classifier significantly. We also noted that the performance of NAP was limited in the original feature space since the feature space (NAP without LLC) is nonlinear with load/system variations. |
| first_indexed | 2024-12-14T22:11:28Z |
| format | Article |
| id | doaj.art-e60e875cabb743f4a86641a43c2e838a |
| institution | Directory Open Access Journal |
| issn | 2153-2648 2153-2648 |
| language | English |
| last_indexed | 2024-12-14T22:11:28Z |
| publishDate | 2018-06-01 |
| publisher | The Prognostics and Health Management Society |
| record_format | Article |
| series | International Journal of Prognostics and Health Management |
| spelling | doaj.art-e60e875cabb743f4a86641a43c2e838a2022-12-21T22:45:45ZengThe Prognostics and Health Management SocietyInternational Journal of Prognostics and Health Management2153-26482153-26482018-06-0192doi:10.36001/ijphm.2018.v9i2.2737Scalable fault models for diagnosis in a synchronous generator using feature mapping and transformation techniquesR. Gopinath0C. Santhosh Kumar1R. I. Ramachandran2Machine Intelligence Research Lab., Department of Electronics and Communication Engineering, Amrita School of Engineering, Coimbatore, Amrita Vishwa Vidyapeetham, Amrita University, India-641112Machine Intelligence Research Lab., Department of Electronics and Communication Engineering, Amrita School of Engineering, Coimbatore, Amrita Vishwa Vidyapeetham, Amrita University, India-641112Machine Intelligence Research Lab., Department of Electronics and Communication Engineering, Amrita School of Engineering, Coimbatore, Amrita Vishwa Vidyapeetham, Amrita University, India-641112Condition based maintenance (CBM) needs data acquired during healthy and faulty conditions to develop intelligent system for fault diagnosis. However, fault injection is not allowed/possible in a highly expensive components of complex/critical systems to collect fault condition data. Therefore, proto-type/small working models are used to conduct experiments for abnormal/fault conditions, to obtain and scale the intelligence of the system for effective health monitoring of complex system. This methodology is referred as scalable fault models. For proof of concept, in this work, we considered two different capacity synchronous generators with rating of 3 kVA and 5 kVA to emulate the behavior of prototype/small working model and complex system respectively, for scalable fault models. We explored feature mapping and transformation techniques to achieve effective scalability. From the preliminary experiments, it is observed that the baseline system performance deteriorated due to the changes in the system (capacity) and its characteristics with load changes. We therefore, expressed the input features in terms of load and system independent manner, to make the features less dependent on load and system variations. We explored locality constrained linear coding (LLC) to express the features load/system independently. It is observed that experimenting LLC with the backend support vector machine (SVM) classifier gave the best fault classification performance for linear kernel, suggesting that the faults are linearly separable in the new feature space. Since the LLC mapped feature space is linearly separable, we then explored linear feature transformation technique, nuisance attribute projection (NAP) on the LLC mapped feature space to further minimize the load/system specific variations. We observed that LLC-NAP improved the overall accuracy and sensitivity of the classifier significantly. We also noted that the performance of NAP was limited in the original feature space since the feature space (NAP without LLC) is nonlinear with load/system variations.https://papers.phmsociety.org/index.php/ijphm/article/view/2737condition based maintenance (cbm)synchronous generatorsupport vector machinedata driven approacheslocality constrained linear coding (llc)nuisance attribute projection (nap)frequency domain features |
| spellingShingle | R. Gopinath C. Santhosh Kumar R. I. Ramachandran Scalable fault models for diagnosis in a synchronous generator using feature mapping and transformation techniques International Journal of Prognostics and Health Management condition based maintenance (cbm) synchronous generator support vector machine data driven approaches locality constrained linear coding (llc) nuisance attribute projection (nap) frequency domain features |
| title | Scalable fault models for diagnosis in a synchronous generator using feature mapping and transformation techniques |
| title_full | Scalable fault models for diagnosis in a synchronous generator using feature mapping and transformation techniques |
| title_fullStr | Scalable fault models for diagnosis in a synchronous generator using feature mapping and transformation techniques |
| title_full_unstemmed | Scalable fault models for diagnosis in a synchronous generator using feature mapping and transformation techniques |
| title_short | Scalable fault models for diagnosis in a synchronous generator using feature mapping and transformation techniques |
| title_sort | scalable fault models for diagnosis in a synchronous generator using feature mapping and transformation techniques |
| topic | condition based maintenance (cbm) synchronous generator support vector machine data driven approaches locality constrained linear coding (llc) nuisance attribute projection (nap) frequency domain features |
| url | https://papers.phmsociety.org/index.php/ijphm/article/view/2737 |
| work_keys_str_mv | AT rgopinath scalablefaultmodelsfordiagnosisinasynchronousgeneratorusingfeaturemappingandtransformationtechniques AT csanthoshkumar scalablefaultmodelsfordiagnosisinasynchronousgeneratorusingfeaturemappingandtransformationtechniques AT riramachandran scalablefaultmodelsfordiagnosisinasynchronousgeneratorusingfeaturemappingandtransformationtechniques |