A Diagnosis Framework for High-reliability Equipment with Small Sample Based on Transfer Learning
Conventional methods for fault diagnosis typically require a substantial amount of training data. However, for equipment with high reliability, it is arduous to form a large-scale well-annotated dataset due to the expense of data acquisition and costly annotation. Besides, the generated data have a...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-01-01
|
| Series: | Complexity |
| Online Access: | http://dx.doi.org/10.1155/2022/4598725 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849691173702074368 |
|---|---|
| author | Jinxin Pan Bo Jing Xiaoxuan Jiao Shenglong Wang Qingyi Zhang |
| author_facet | Jinxin Pan Bo Jing Xiaoxuan Jiao Shenglong Wang Qingyi Zhang |
| author_sort | Jinxin Pan |
| collection | DOAJ |
| description | Conventional methods for fault diagnosis typically require a substantial amount of training data. However, for equipment with high reliability, it is arduous to form a large-scale well-annotated dataset due to the expense of data acquisition and costly annotation. Besides, the generated data have a large number of redundant features which degraded the performance of models. To overcome this, we proposed a feature transfer scenario that transfers knowledge from similar fields to enhance the accuracy of fault diagnosis with small sample. To reduces the redundant information, data were filtered according to manifold consistency. Then, features were extracted based on CNN and feature transfer was conducted. For adequate fitness, the joint adaptation of conditional distribution and marginal distribution was used between the two domains. Minimum structural risk and MMD of adaptation were two indicators weighted for training the model. To test the efficiency of the model, we built an airborne fuel pump testbed, and contributed a new dataset that contained 15 categories of fault data, which serves as the small sample dataset in this research. Then the proposed model was applied in our experimental data. As a result, the fault diagnosis rate increases by 28.6% through our proposed model, which is more precise than other classical methods. The results of feature visualization further demonstrate that the features are more distinguished through the proposed method. All code and data are accessible on my GitHub. |
| format | Article |
| id | doaj-art-e344b21457a449648c60da45e1cc9b0d |
| institution | DOAJ |
| issn | 1099-0526 |
| language | English |
| publishDate | 2022-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Complexity |
| spelling | doaj-art-e344b21457a449648c60da45e1cc9b0d2025-08-20T03:21:07ZengWileyComplexity1099-05262022-01-01202210.1155/2022/4598725A Diagnosis Framework for High-reliability Equipment with Small Sample Based on Transfer LearningJinxin Pan0Bo Jing1Xiaoxuan Jiao2Shenglong Wang3Qingyi Zhang4Air Force Engineering UniversityAir Force Engineering UniversityAir Force Engineering UniversityAir Force Engineering UniversityAir Force Engineering UniversityConventional methods for fault diagnosis typically require a substantial amount of training data. However, for equipment with high reliability, it is arduous to form a large-scale well-annotated dataset due to the expense of data acquisition and costly annotation. Besides, the generated data have a large number of redundant features which degraded the performance of models. To overcome this, we proposed a feature transfer scenario that transfers knowledge from similar fields to enhance the accuracy of fault diagnosis with small sample. To reduces the redundant information, data were filtered according to manifold consistency. Then, features were extracted based on CNN and feature transfer was conducted. For adequate fitness, the joint adaptation of conditional distribution and marginal distribution was used between the two domains. Minimum structural risk and MMD of adaptation were two indicators weighted for training the model. To test the efficiency of the model, we built an airborne fuel pump testbed, and contributed a new dataset that contained 15 categories of fault data, which serves as the small sample dataset in this research. Then the proposed model was applied in our experimental data. As a result, the fault diagnosis rate increases by 28.6% through our proposed model, which is more precise than other classical methods. The results of feature visualization further demonstrate that the features are more distinguished through the proposed method. All code and data are accessible on my GitHub.http://dx.doi.org/10.1155/2022/4598725 |
| spellingShingle | Jinxin Pan Bo Jing Xiaoxuan Jiao Shenglong Wang Qingyi Zhang A Diagnosis Framework for High-reliability Equipment with Small Sample Based on Transfer Learning Complexity |
| title | A Diagnosis Framework for High-reliability Equipment with Small Sample Based on Transfer Learning |
| title_full | A Diagnosis Framework for High-reliability Equipment with Small Sample Based on Transfer Learning |
| title_fullStr | A Diagnosis Framework for High-reliability Equipment with Small Sample Based on Transfer Learning |
| title_full_unstemmed | A Diagnosis Framework for High-reliability Equipment with Small Sample Based on Transfer Learning |
| title_short | A Diagnosis Framework for High-reliability Equipment with Small Sample Based on Transfer Learning |
| title_sort | diagnosis framework for high reliability equipment with small sample based on transfer learning |
| url | http://dx.doi.org/10.1155/2022/4598725 |
| work_keys_str_mv | AT jinxinpan adiagnosisframeworkforhighreliabilityequipmentwithsmallsamplebasedontransferlearning AT bojing adiagnosisframeworkforhighreliabilityequipmentwithsmallsamplebasedontransferlearning AT xiaoxuanjiao adiagnosisframeworkforhighreliabilityequipmentwithsmallsamplebasedontransferlearning AT shenglongwang adiagnosisframeworkforhighreliabilityequipmentwithsmallsamplebasedontransferlearning AT qingyizhang adiagnosisframeworkforhighreliabilityequipmentwithsmallsamplebasedontransferlearning AT jinxinpan diagnosisframeworkforhighreliabilityequipmentwithsmallsamplebasedontransferlearning AT bojing diagnosisframeworkforhighreliabilityequipmentwithsmallsamplebasedontransferlearning AT xiaoxuanjiao diagnosisframeworkforhighreliabilityequipmentwithsmallsamplebasedontransferlearning AT shenglongwang diagnosisframeworkforhighreliabilityequipmentwithsmallsamplebasedontransferlearning AT qingyizhang diagnosisframeworkforhighreliabilityequipmentwithsmallsamplebasedontransferlearning |