Adaptive model-agnostic meta-learning network for cross-machine fault diagnosis with limited samples

Abstract

Deep learning-based methods have been extensively studied in rotating machinery defect diagnosis. However, training an accurate and robust diagnostic model is still a challenge under severe domain bias and limited samples. For this reason, a new adaptive model-agnostic meta-learning (AMAML) is proposed for cross-machine fault diagnosis with limited samples. First, a novel adaptive feature encode network is built, incorporating lightweight spatial-bilateral channel attention. This enables the network to extract critical fault information in multiple dimensions adaptively within limited samples, which improves the learning efficiency of generalized diagnostic knowledge. Then, an adaptive loss computation (ALC) method is devised, which inventively realizes the interaction between loss computation and model performance. The underfitting and overfitting dilemmas under few-shot conditions are tackled by ALC. Finally, an adaptive meta-optimization strategy is proposed for dynamically adapting the update strategy of the base learner, so that the model is always optimized in the direction of strong generalizability while obtaining high performance. Six cross-machine diagnosis tasks are conducted to verify the effectiveness of AMAML. The average diagnostic accuracy of the AMAML under the 5-shot setting reached 97.42%. Experiments confirm that AMAML is superior to other prevailing methods and is potentially promising for engineering applications.