圧縮センシングを用いた回転機械の故障診断

抄録

Vibration and sound are widely used in the diagnosis of rotating machinery failures. While this method has the advantage of simplicity and high accuracy, it has the disadvantage of requiring high measurement frequency. Therefore, we have developed a method for vibration-based fault diagnosis with a measurement frequency that is a few hundredths of the frequency required by the sampling theorem, by performing signal reconstruction using compressed sensing. In this paper, we report the results of the evaluation of the parameter setting method based on the measurement results of propeller drive sound in the laboratory. We also report the results of applying the method to the vibration of a rotating machine in a real environment and evaluating its noise resistance performance.