基于遗传规划算法的不同应力比下不同厚度7050铝合金疲劳裂纹扩展寿命预测

Prediction of Fatigue Crack Growth Life of 7050 Aluminum Alloy with Different Thicknesses under Various Load Ratios by Genetic Programming

针对不同厚度7050铝合金试样进行了不同应力比条件下的一系列疲劳裂纹扩展试验,并运用遗传规划算法对疲劳裂纹扩展寿命进行预测。遗传规划算法是模拟自然界中生物的进化策略,通过交换、突变等遗传操作,搜索目标的最优解。建立7050铝合金疲劳裂纹扩展速率的遗传规划模型,并利用试验数据对模型进行测试,后与其他典型疲劳裂纹扩展模型进行比较。研究结果表明:GP模型预测的7050铝合金疲劳裂纹扩展寿命结果与试验值基本吻合,相对误差小于1.5%,且GP模型预测结果的准确性高于Paris模型和Walker模型。

In order to predict the fatigue crack growth life by genetic programming,fatigue test of 7050 aluminum alloy specimens with different thicknesses under various load ratios were carried out.Genetic programming simulates natural evolution by gene operations like crossover and mutation to get an optimal solution.The model of the fatigue crack growth of 7050 aluminum alloy was established by genetic programming and tested with the experimental data,also compared with other typical models.The results show that the model established by genetic programming matches with the experimental data,that relative error is less than 1.5%,with a higher accuracy than Paris model and Walker model.