Design of Fault Diagnosis and Fault Prediction System for Stacker Traveling Mechanism Based on Digital Twin

This paper addresses the typical fault diagnosis and prediction problems of stacker cranes in the intelligent manufacturing process. Firstly, a digital twin of the target object is constructed, achieving the modeling of physical space modules, digital space modules, twin database modules, application system modules, and connection modules. Through data mapping, the geometric model of the walking wheel mechanism’s digital twin is made to correspond to the physical entity of the walking wheel mechanism. Data collected from the physical entity is used to drive the digital twin model in real time, enabling the identification and prediction results of bearing faults to be reflected in the digital twin. Then, for the typical fault diagnosis and prediction process of the walking mechanism, a wavelet transform method is provided to convert vibration signals into time-frequency image features. The time-frequency feature map is used as the input of the 2D-CNN network to ultimately achieve fault diagnosis. At the same time, the convolutional layer, pooling layer, fully connected layer, and classification layer of the recognition model are optimized. Finally, a simulation experiment is set up. In the experiment, the bearing fault datasets from Case Western Reserve University and Xi’an Jiaotong University are used as the training and testing datasets. Through comparative experiments, the method proposed in this paper can improve the recognition accuracy and efficiency in bearing fault diagnosis and prediction.