Recent advance of deep learning has seen remarkable progress in compound fault diagnosis modeling for industrial robots. Nevertheless, the data scarcity of compound fault samples jeopardizes the modeling performance of deep learning algorithms. Meta-learning has become an effective tool in few-shot fault diagnosis modeling. However, due to the training instability of meta-learning, it is challenging to deploy advanced networks such as transformers as the base learner due to the extremely large model size. Therefore, this study proposes a lightweight convolutional transformers (LCT) network enhanced meta-learning (Meta-LCT) method to achieve accurate compound fault diagnosis with limited compound fault samples. Specifically, the LCT is first designed by taking the advantage of linear spatial reduction (LSR) attention and spatial pooling mechanism to achieve high computational efficiency. LCT is adopted as the base learner in the Meta-stochastic gradient descent (SGD) algorithm, and then, the meta-training is performed based on the single fault data. Subsequently, the limited compound fault samples are used in the meta testing stage to obtain a compound fault diagnosis model. An experimental study based on the real-world compound fault dataset of industrial robots is presented. The experimental results indicate that the proposed Meta-LCT can achieve the compound fault diagnosis accuracy of 81.1% when only 40 data samples in each compound fault category are available.
|Number of pages||12|
|Journal||IEEE Transactions on Instrumentation and Measurement|
|Early online date||29 May 2023|
|Publication status||Published - 29 May 2023|
Bibliographical noteCopyright © 2023 IEEE. Personal use is permitted, Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
This work was supported in part by the Key Program of NSFC-Guangdong Joint Funds under Grant U2001201 and Grant U1801263, in part by the Industrial Core and Key Technology Plan of Zhuhai City under Grant ZH22044702190034HJL, in part by the Natural Science Foundation of Guangdong Province under Grant 2020B1515120010, and in part by the Guangdong Provincial Key Laboratory of Cyber-Physical System under Grant 2020B1212060069.
- Compound fault diagnosis
- Deep learning
- Fault diagnosis
- Feature extraction
- Industrial robot
- Industrial robots
- Meta learning
- Task analysis
- Transformers networks