Lightweight intelligent fault diagnosis method based on a multi-stage pruning distillation interleaving network
Authors:
Open Access
- 27 September 2024
- journal article
- research article
- Published by SAGE Publications in Advances in Mechanical Engineering
- Vol. 16 (9)
Abstract
Edge computing, a key technology in the Internet of Things, can help integrate real-time fault diagnosis into industrial applications. Lightweight and compression technologies are essential for deploying high-precision deep learning methods on resource-constrained edge computing systems. However, modeling accuracy is severely compromised by existing methods. To overcome this limitation, a new multi-stage pruning and distillation architecture was proposed in this study to compress a depthwise separable convolutional network for intelligent fault diagnosis of bearings in edge computing systems. The model was implemented on an NVIDIA Jetson Nano and verified using two bearing fault datasets. The results show that the proposed method can significantly reduce the calculation and reasoning time of the model and maintain high accuracy. The proposed method exhibits remarkable effectiveness, requires minimal memory, provides fast inference speeds, and is suitable for use in edge devices with less configuration.Keywords
Funding Information
- National Key Research and Development Program of China (2022YFB3706803)
This publication has 17 references indexed in Scilit:
- Multi-source partial domain adaptation method based on pseudo-balanced target domain for fault diagnosisKnowledge-Based Systems, 2023
- Multi-level federated learning based on cloud-edge-client collaboration and outlier-tolerance for fault diagnosisMeasurement Science and Technology, 2023
- Network lightweight method based on knowledge distillation is applied to RV reducer fault diagnosisMeasurement Science and Technology, 2023
- Adaptive multispace adjustable sparse filtering: A sparse feature learning method for intelligent fault diagnosis of rotating machineryEngineering Applications of Artificial Intelligence, 2023
- A rolling bearing fault diagnosis method using novel lightweight neural networkMeasurement Science and Technology, 2021
- Development of an edge computing-based cyber-physical machine toolRobotics and Computer-Integrated Manufacturing, 2021
- A lightweight neural network with strong robustness for bearing fault diagnosisMeasurement, 2020
- A tool wear monitoring and prediction system based on multiscale deep learning models and fog computingThe International Journal of Advanced Manufacturing Technology, 2020
- Deep Learning With Edge Computing: A ReviewProceedings of the IEEE, 2019
- Pruning algorithms-a surveyIEEE Transactions on Neural Networks, 1993