Intelligent fault diagnosis of rolling mills based on gram angular difference field and dual-attention residual network

Abstract Monitoring the health of rolling mills has always been a concern for the steel industry. However, existing methods make it difficult to obtain fault features under the conditions of unbalanced data and serious disturbances during rolling. Therefore, we propose a fault diagnosis of the rolling mill based on the Gramian angular difference field (GADF) and the dual-attention residual network. Firstly, original one-dimensional vibration signals are converted into two-dimensional GADF images as the input of the network. Secondly, the dual attention mechanism of channel and space is introduced into the residual network to focus on the channel and spatial information of the input image for the re-integration of the extracted features. Finally, the model is trained to complete the recognition of faults. To validate the superiority of the proposed method, datasets with different data distributions were designed on the rolling mill test bench. Experimental comparisons have proven the superiority of GADF and the dual-attention mechanism. Moreover, when compared with other methods on several imbalanced datasets, the proposed method achieves an average accuracy that is at least 1.8% higher than that of other methods.