Chemical Process Fault Diagnosis Based on Improved ResNet Fusing CBAM and SPP

This paper proposes a fault diagnosis method based on an improved residual network (ResNet) for complex chemical processes. The can automatically and efficiently extract features from the extensive data generated by operation process. improvement is carried out in three aspects. Firstly, 1D convolution introduced construction of model to reduce number parameters training time, shortcut connections are used alleviate degradation problem traditional deep neural networks. Second, residual-CBAM module proposed combining networks with Convolutional Block Attention Module (CBAM). effectively interference invalid targets improve characterization ability model. Finally, backbone path network, branching after spatial pyramid pooling (SPP) enable different angles feature map further aggregation, which improves robustness Tennessee-Eastman (TE) process as experimental object compare ResNet several other learning models. results show that achieves best results. t-SNE was visualize classification model, effectiveness analyzed verified.