Gaussian mixture hidden Markov model and regression analysis remaining life prediction method

Abstract

The invention discloses a Gaussian mixture hidden Markov model and regression analysis remaining life prediction method. The Gaussian mixture hidden Markov model and regression analysis remaining life prediction method comprises the specific steps of 1 performing characteristic vector extraction through wavelet packet algorithm decomposition, 2 establishing Gaussian mixture hidden Markov model libraries of different fault modes; 3 establishing part failure time modes of different fault modes; 4 performing part fault mode recognition and failure state assessment; 5 utilizing regression analysis to predict remaining life. The Gaussian mixture hidden Markov model and regression analysis remaining life prediction method integrates data drive and probability statistics fully utilizes respective advantages that the hidden Markov models predict the remaining life and have randomness and real-timeliness; the par failure process is divided into multiple stages, the probability statistics and the regression analysis are adopted to correct current usage time, and the remaining life prediction accuracy is improved. The Gaussian mixture hidden Markov model and regression analysis remaining life prediction method has the advantages of being high in prediction accuracy, operation speed and real-timeliness, low in cost and the like.

Description

technical field [0001] The invention belongs to the field of fault diagnosis and life prediction, in particular to a remaining life prediction method based on Gaussian mixture hidden Markov model and regression analysis. Background technique [0002] In the demand for the competitiveness of electromechanical products, in addition to continuously improving the practicability, reliability, and safety of products, it is also required to continuously reduce product maintenance and maintenance costs. At present, most electromechanical products adopt after-event maintenance and regular maintenance. Although these two maintenance methods are operable, because they do not take into account the actual operation and aging status of the equipment, the effect of these maintenance methods is actually not ideal, resulting in insufficient maintenance or maintenance. excessive phenomenon. [0003] Condition-Based Maintenance (CBM) is a viable solution that helps reduce the cost of traditio...

AI Technical Summary

Problems solved by technology

[0010] There are also problems such as high cost, long forecast period, and poor real-time performance in the crossover method produced by combining two or three of the above methods.

Images