Failure prediction method facing to numerically-controlled machine tool

Abstract

The invention relates to the fault diagnosis and forecast filed, in particular to a failure prediction method facing to a numerically-controlled machine tool. The failure prediction method comprises the following steps of adopting a hierarchical-type hierarchical structure model to divide the numerically-controlled machine tool to be a plurality of core subsystems and analyze typical gradual failures; reducing a data set of sensor parameters to obtain a data set of failure foreboding parameters and relative relevance degree between the parameters and the failures; using a failure occurrence point to serve as a limit, diving each failure foreboding parameter historical data set according to time series, and corresponding to failure foreboding state series; adopting wavelet analysis technology to extract failure foreboding feature vectors of the data in different time intervals, conducting counter propagation neural network training, and obtaining a failure foreboding judgment model of each parameter; and adopting a dynamic confidence coefficient matching algorithm to monitor an accumulated confidence coefficient of each failure foreboding parameter on line, fusing state dynamic matching results of each failure foreboding parameter, and forecasting probability and time of failure occurrence. The failure prediction method has the advantages of high forecast accuracy, small forecast time difference, low false alarm rate, strong robustness, wide application prospect and the like.

Description

technical field [0001] The invention relates to the field of fault diagnosis and prediction of numerical control machine tools, in particular to a fault prediction method for numerical control machine tools. Background technique [0002] As a typical mechatronic product, CNC machine tools are very different from traditional manufacturing systems in terms of complexity, behavior and working environment. CNC machine tools have a high degree of automation, are expensive, and have a complex structure. The possibility of failure is high, and it is difficult to obtain fault knowledge, fault location, and troubleshooting. With the development of integrated circuit technology, the mechanical faults of CNC machine tools account for 75% of the total faults, and most of them are gradual faults. There are signs of failure before this type of failure occurs and gradually changes with time and the environment. It is mainly manifested in failures caused by the gradual decline in system pe...

AI Technical Summary

Problems solved by technology

The conventional BP neural network adopts single-step prediction and multi-step prediction based on time series, and predicts the time series value at the next moment with the help of any N continuous time series values. The prediction time step is inversely proportional to the prediction accuracy. Components, difficult to accurately model in a short period of time, not suitable for medium and long-term forecasting

Prediction technology based on multi-sensor information fusion has advantages in improving prediction efficiency and accuracy, but uncertainty information processing and theoretical modeling technology still need further research

Images