论文部分内容阅读
服役零件疲劳寿命的预测与评估是装备高质量运行的前提。为准确预测服役零件的剩余寿命,基于磁记忆检测方法探索影响零件剩余寿命的参数,建立剩余寿命预测的新方法。以汽车车桥桥壳为对象,通过ABAQUS对服役零件进行疲劳寿命模拟分析,识别零件的疲劳危险区域;借助金属磁记忆检测技术和断裂力学理论,提取零件疲劳危险区中表征疲劳损伤程度的裂纹长度、应力强度因子、磁记忆信号法向分量梯度最大值、应力集中度等作为参数;引入支持向量机(SVM)理论,建立零件的剩余寿命预测模型。结果表明:SVM模型具有较高的预测精度,预测值与疲劳试验实测剩余寿命值相比误差不超过10%;预测精度同时受到零件损伤程度、训练样本数量、载荷大小和输入特征参数等的影响;建立的方法能够有效应用于低载荷高周疲劳下的桥壳等服役零件的剩余寿命预测。
Prediction and evaluation of fatigue life of service parts is the premise of high quality operation of equipment. In order to accurately predict the remaining service life of service parts, the method of magnetic memory testing is used to explore the parameters that affect the remaining service life of spare parts, and a new method of remaining life prediction is established. The fatigue life of the service parts was simulated and analyzed by ABAQUS to identify the fatigue danger area of the parts. The magnetic fatigue testing method and fracture mechanics theory were used to extract the cracks Length, stress intensity factor, maximum value of normal component gradient of magnetic memory signal, stress concentration and so on as parameters. The support vector machine (SVM) theory is introduced to establish the residual life prediction model. The results show that the SVM model has higher prediction accuracy, and the prediction error is less than 10% compared with the residual life measured by the fatigue test. The prediction accuracy is also affected by the degree of part damage, the number of training samples, the load size and the input characteristic parameters The established method can be effectively applied to predict the remaining life of service parts such as axle housing under low load and high cycle fatigue.