A Lifetime Prediction Method Fused with Field Data and Two-Stage Accelerated Degradation Data

Abstract

The invention discloses a life prediction method that combines field data and two-stage accelerated degradation data. According to the accelerated degradation data of motor insulation material test samples under different thermal stresses, the position of the change point in the degradation process is determined by using SIC and the minimum criterion of the sum of squares of residual errors ;Construct a motor insulation performance degradation model based on a two-stage stochastic process under the action of thermal stress, obtain the relationship between model parameters and change point distribution parameters and temperature according to the Arrhenius equation, and extrapolate the probability density of the change point position of the product under normal temperature degradation process function and model parameters; use the on-site degradation data of the motor insulation material to be tested, use the CUSUM control chart to identify the change point, and combine the probability density function of the change point to determine the probability of the change point; use the accelerated degradation data as the prior information of the model parameters , and then based on the Bayesian method, the posterior estimates of the model parameters are obtained according to the field degradation data, and the cumulative distribution function of the product life in the sense of first arrival time is obtained, so as to realize the real-time life prediction of the motor insulation.

Description

technical field [0001] The invention relates to the technical field of equipment life prediction, in particular to a life prediction method that combines on-site data and two-stage accelerated degradation data. Background technique [0002] In order to cope with energy shortage and air pollution, my country attaches great importance to the development of new energy power generation and electric vehicles. As an important equipment for new energy power generation, wind turbines operate under complex and harsh environmental conditions for a long time. Generator insulation damage is one of the important reasons for wind turbine failures. Due to the operating characteristics of electric vehicle drive motors such as frequent starting, variable speed, and changing road conditions, the failure of the drive motor is mainly caused by damage to the motor windings, and one of the important reasons for winding damage is insulation damage. Therefore, it is of great significance to predic...

AI Technical Summary

Problems solved by technology

[0006] In view of this, the present invention provides a life prediction method that combines field data and two-stage accelerated degradation data, which solves the problem of the lack of historical failure data, difficulty in collection, and the multi-stage degradation process that does not consider the change point in the modeling of accelerated degradation data. The problem of inaccuracy in reliability assessment

Images