A Novel Deep Model with Meta-learning for Rolling Bearing Few-shot Fault Diagnosis

Abstract

Machine learning, especially deep learning, has been highly successful in data-intensive applications, however, the performance of these models will drop significantly when the amount of the training data amount does not meet the requirement. This leads to the so-called Few-Shot Learning (FSL) problem, which requires the model rapidly generalize to new tasks that containing only a few labeled samples. In this paper, we proposed a new deep model, called deep convolutional meta-learning networks (DCMLN), to address the low performance of generalization under limited data for bearing fault diagnosis. The essential of our approach is to learn a base model from the multiple learning tasks using a support dataset and finetune the learnt parameters using few-shot tasks before it can adapt to the new learning task based on limited training data. The proposed method was compared to several few-shot learning methods, including methods with and without pre-training the embedding mapping, and methods with finetuning the classifier or the whole model by utilizing the few-shot data from the target domain. The comparisons are carried out on one-shot and ten-shot tasks using the CWRU bearing dataset and a cylindrical roller bearing dataset. The experimental result illustrates that our method has good performance on the bearing fault diagnosis across various few-shot conditions. In addition, we found that the pre-training process does not always improve the prediction accuracy.

Few-Shot Learning Approaches for Fault Diagnosis Using Vibration Data: A Comprehensive Review

“…A matching network and prototypical network were applied, respectively, in the proposed model to match the metric features to the support features using a public dataset. A similar approach was applied in [29] employing a matching network to match the metric features to the support features using experimental datasets.…”

A novel signal resolution enhance method based on CBAM-ResNet for bearing intelligent fault diagnosis

“…With a large number of inspected equipments, high sampling frequency, and prolonged working times, a substantial volume of diagnostic data is being generated. This presents new opportunities for the research and application of intelligent fault diagnosis in machinery, propelling the field of rotating machinery fault diagnosis into the era of 'big data' [6,7]. Han et al [8] proposed a Hybrid Distance Guided Adversarial Network, which utilizes Wasserstein distance and multicore maximum mean difference (MMD) to measure domain distance in various metric spaces and enhance the extracting invariant features in the domain.…”

Lightweight RepVGG-Based Cross-Modality Data Prediction Method for Solid Rocket Motors

“…Peng et al [32] proposed a residual mixed-domain attention CNN method to solve the mechanical fault diagnosis problem. Liang et al [33] proposed a deep convolutional element-learning network to solve the problem of the low generalization performance of bearing fault diagnosis using limited data. Li et al [34] proposed a mechanical fault diagnosis method based on federated transfer learning to solve the problem of difficulty in collecting data.…”