基于已有数据和粒子滤波的Paris参数估计和剩余寿命预测

Estimation of Parameters in Paris Model and Prediction of Residual Life Based on Existing Data and Particle Filter

论文对Paris模型及其材料参数C和m以及粒子滤波的基本原理进行了介绍,基于粒子滤波算法,对30Cr2Ni4MoV钢和2024-T42铝合金这两种材料的疲劳裂纹扩展试验数据进行了计算分析。计算过程中,C和m由初始分布逐渐向真实值靠拢,降低了材料参数的不确定性,同时还得到了C和m的线性相关方程。预测得到了剩余寿命的中值和置信区间,预测结果和试验结果非常接近,验证了粒子滤波应用于疲劳裂纹扩展率参数估计和寿命预报的可行性和有效性。该方法可以用于疲劳裂缝扩展数据的处理和在役结构的剩余寿命预测。

In this paper,the Paris model and material parameters C and mare introduced,and basic principles of the particle filter are briefly described.Based on the particle filter algorithm,experimental data of fatigue crack propagation of aluminum alloy 2024-T42 and steel 30Cr2Ni4MoV were processed.In the calculation process,C and m are gradually close to real values from their initial distribution,so as to reduce the uncertainty of material parameters.Then a linear correlation equation is obtained for C and m.Prediction of the median value and the confidence interval of remaining life is very close to the test results,which verifies the feasibility and effectiveness of the proposed method.This procedure can be used to process data of fatigue crack propagation and predict residual life of structures in service.