A fault diagnosis method based on low signal to noise ratio vibration measurement for use in casing cutters

In this paper, a method for fault diagnosis in casing cutters is proposed. A vibration signal acquisition circuit for use in a high-temperature environment was designed, and a casing cutter measurement model was established, including a model of the casing cutter in a trouble-free state and two other common fault states. The vibration characteristics of the model were analyzed. A fault feature enhancement model based on enhancement of the signal to noise ratio and sparse representation, which effectively solves the fault diagnosis problem caused by the limited installation location and the limited performance of the vibration measurement at high temperature, was also designed. The MobileNet-V3-Small convolutional neural network (CNN) model was improved by reducing the basic blocks of the continuous homogeneous structure in the original model, and the Squeeze and Excitation structure expanded to the global level to obtain a lightweight CNN fault recognition model. The effectiveness and efficiency of the proposed method were validated by various experiments.