Incipient fault diagnosis of limit switch based on a ARMA model

Abstract

The limit switch is one of the key components in many pieces of electromechanical equipment. Although the limit switch is cheap and its structure is simple usually, it plays a key role in ensuring good operation condition of electromechanical equipment. Any failure of a limit switch may lead to the complete shutdown of equipment. In this paper, an incipient fault diagnosis method is developed, based on which one can replace the limit switch before its functional failure. In this method, the voltage of the limit switch is monitored and sampled. Then, the feature extraction of the voltage data sequence based on the Auto-Regressive and Moving Average (ARMA) model is performed, and the k-Nearest Neighbor (k-NN) method is used for the feature classification of the voltage data. Finally, the experiment of the incipient fault diagnosis is described and the result is given. The study in this paper may be beneficial for avoiding breakdown of electromechanical equipment due to the functional failure of limit switches.