Intelligent fault diagnosis of mechanical equipment under varying working condition via iterative matching network augmented with selective Signal reuse strategy

Abstract

Change of working condition leads to discrepancy in domain distribution of equipment vibration signals. This discrepancy poses an obstacle to application of deep learning method in fault diagnosis of wind turbine. When lacking domain adaptation ability, diagnostic accuracy of deep learning method applied to unseen condition will decrease significantly. To solve this problem, an iterative matching network augmented with selective sample reuse strategy is proposed. By generating pseudo labels for unlabeled signals from unseen condition and reusing these signals to iteratively update parameters, embedding space of matching network reduce discrepancy in domain distribution between different working conditions. This makes the model more adaptable to unseen condition. Specially designed filter is proposed for selecting pseudo-labeled signals to increase proportion of correctly labeled signals in iteration. By combing these two points, proposed algorithm can be updated iteratively based on selected pseudo-labeled signals and achieve higher accuracy when analyzing signals of unseen working conditions. Multiscale feature extractor is used to extract features at different scales and form embedding space. Effectiveness of the proposed algorithm is verified by four datasets. Experiments show that this algorithm not only has good performance under varying load and speed conditions but also surpasses other domain adaptation methods.