Bearing fault prediction method and device based on equal division

Abstract

The invention discloses a bearing fault prediction method and device based on equal division. The bearing fault prediction method comprises the following steps that one-dimensional or multi-dimensional vibration signals of a bearing are detected, and accordingly, sample signals are obtained according to the one-dimensional or multi-dimensional vibration signals; the sample signals are equally divided so as to obtain equally-divided time sequence segments; and the equally-divided time sequence segments are input into a fault prediction model according to the collecting time, and the predictionresult of each time sequence segment is obtained; and according to an attention mechanism, the weight is distributed to the finally-output contribution sizes for the hidden state of the model at eachtime, so that the fault prediction result of the bearing is generated after the contribution sizes are subjected to weighted summation. According to the bearing fault prediction method based on equaldivision, complicated feature engineering is omitted, an end-to-end fault diagnosis system is achieved, the bearing fault prediction method is further suitable for multi-channel sensing scenarios, theprediction accuracy and time efficiency of the prediction model are effectively improved, applicability is high, and the bearing fault prediction method is simple and easy to implement.

Description

technical field [0001] The invention relates to the technical field of fault prediction, in particular to a bearing fault prediction method and device based on equal division. Background technique [0002] In order to accurately perceive the performance degradation of equipment and avoid catastrophic failures, data-driven health perception and predictive maintenance have been widely used in industrial manufacturing. As a key component of rotating machinery, bearings are very important whether their working conditions are normal or not. Therefore, it is even more necessary to accurately identify faults and implement repairs in the most effective way. With the rapid development of smart sensing, signal processing, and artificial intelligence technologies, data-driven methods have gradually become mainstream solutions for industrial equipment health monitoring, and are widely used in the fields of failure prediction and remaining service life estimation. In addition, compared...

AI Technical Summary

Problems solved by technology

But it has two disadvantages that cannot be ignored: 1. It requires expensive human labor and high-quality expertise for feature engineering; 2. The number of deployed sensors is increasing day by day, and traditional methods cannot cope with the rapid growth of industrial big data

[0004] However, since sensors usually have extremely high sampling frequency, and the deployment conditions in specific scenarios are not exactly the same, this means that the complexity of feature engineering will inevitably rise

At the same time, the length of the entire sequence increases continuously with the prolongation of the sampling time, which is not good for efficient learning of long sequences

Images