A Multisensor Data Fusion Method for Ball Screw Fault Diagnosis Based on Convolutional Neural Network With Selected Channels

Abstract

In the real industrial application, the problem of ball screw health condition monitoring and fault diagnosis is still confronted many challenges. In some cases, the rotating machinery has long rotor, it need to arrange multiple sensors at different positions of the system and different faults are located at different positions of the system. The primary difficult issue involved in the task is to recognize the multiple faults at different positions of ball screw with high accuracy and feasibility. In order to overcome the problem, a novel method for ball screw fault diagnosis is proposed. The proposed method combines weighted data of the multiple sensors at different positions with convolutional neural network and it considers the sensitive index of different faults at different sensors for weight assignment. The proposed method mainly contains three steps. Firstly, a new data segmentation algorithm is proposed to obtain the uniform data of the vibration signals. Secondly, a sensitive sensor data selection criterion based on ball screw failure mechanism is developed to obtain the sensor importance factor. Finally, the weighted data is classified by the convolutional neural network. The effectiveness of the proposed method is verified by the experiment on the ball screw test-bed.