Bearing fault diagnosis method based on symbolic probabilistic finite state machine

Abstract

The invention discloses a bearing fault diagnosis method based on a symbolic probabilistic finite state machine. The method comprises the steps that a one-dimensional time series with concentrated training data is converted to a two-dimensional symbol matrix; a probabilistic finite state machine model is constructed for the two-dimensional symbol matrix; an extracted left feature vector is used as a feature value to represent an original bearing signal; and finally an improved K- nearest neighbor classification (KNN) algorithm is used to learn the left feature vector of a bearing signal of a known failure category. For a bearing signal to be diagnosed, the same feature extraction method is used, and then the improved KNN algorithm is used to realize fault diagnosis. According to the invention, a K-means clustering method is used to improve the traditional K- nearest neighbor classification algorithm, and the computation efficiency and the fault diagnosis effect of the bearing diagnosis algorithm are improved.

Description

technical field [0001] The invention relates to the technical field of bearing fault diagnosis, in particular to a bearing fault diagnosis method based on symbolic dynamics. Background technique [0002] With the rapid development of science and technology and modern industry, machinery and equipment in the machinery, energy, petrochemical, transportation and national defense industries of the national economy are increasingly large, high-speed, integrated and automated, which provides a strong guarantee for the rapid development of my country's economy . However, catastrophic accidents caused by mechanical equipment failures occur frequently. If the abnormal state of the mechanical system can be accurately and timely identified, it will be of great significance to the safe operation of the mechanical system and avoid major and catastrophic accidents. With the demand for high quality, low energy consumption and safe production, a variety of signal processing methods have bee...

AI Technical Summary

Problems solved by technology

However, the KNN algorithm is a lazy learning algorithm based on instance learning. It does not learn an explicit classifier from the training set, which makes it necessary to save all training samples.

With the increase of the training sample library, the storage space required and the time required for classification are greatly increased. This limitation makes the efficiency of the KNN classification algorithm greatly reduced when the sample set is too large.

Images