Fault Diagnosis of Rotating Machinery Bearings Based on Improved DCNN and WOA-DELM

A bearing is a critical component in the transmission of rotating machinery. However, due to prolonged exposure heavy loads and high-speed environments, rolling bearings are highly susceptible faults, Hence, it crucial enhance fault diagnosis ensure safe reliable operation In order achieve this, machinery method based on deep convolutional neural network (DCNN) Whale Optimization Algorithm (WOA) optimized Deep Extreme Learning Machine (DELM) proposed this paper. DCNN combination Efficient Channel Attention Net (ECA-Net) Bi-directional Long Short-Term Memory (BiLSTM). method, firstly, classification constructed. The ECA-Net BiLSTM brought into extract features. Next, WOA used optimize weight initial input layer DELM build WOA-DELM classifier model. Finally, features extracted by Improved (IDCNN) sent model for diagnosis. diagnostic capability IDCNN-WOA-DELM was evaluated through multiple-condition experiments using CWRU-bearing dataset with various settings, comparative tests against other methods were conducted as well. results indicate that demonstrates good performance.