岸桥金属材料与焊接结构寿命预测

Life Prediction of Metal Material and Welded Structure of Quayside Container Crane

基于不同损伤理论,利用人工智能技术来预测岸桥金属结构疲劳寿命的智能算法已经成为岸桥领域新的热点。为提高寿命预测精度,分别利用神经网络算法和支持向量机算法进行仿真实验,估算在两级载荷下的疲劳寿命。根据前人给出的实验数据,分别运用基于遗传算法优化的神经网络和基于粒子群优化的支持向量机算法对正火35#钢和调质45#钢进行疲劳仿真,描述应力与累积损伤之间的非线性关系,以及应力加载顺序对疲劳寿命的影响;并对海洋平台中最为常见的焊接管接头结构进行疲劳参数的预测,以验证经过优化的智能算法的实用性。同时与优化过的BP神经网络和支持向量机预测结果进行比较,表明优化方法对于提高智能算法的预测精度有较大作用。

Based on the different damage theory,the intelligent algorithm,which can predict the fatigue life of crane metal structure via artificial intelligence technology has become a new hot point in the crane field.In practice,some intelligent algorithms are often used to solve some complex nonlinear problems.Therefore,the neural network algorithm and the support vector machine algorithm are used to simulate the experiment,and the fatigue life under the two stage load is estimated,respectively.According to the experimental data given by predecessors,the fatigue simulation of normalizing No.35 steel and the quenched and tempered No.45 steel is carried out by using the neural network and genetic algorithm and the support vector machine algorithm based on the particle swarm optimization,respectively.Besides,the nonlinear relationship between the stress and cumulative damage and the influence of stress loading sequence on the fatigue life are described.The fatigue parameters of the most common welded pipe joints in offshore platforms are predicted to verify the practicability of the optimized intelligent algorithm.At the same time,the results are compared with the optimized BP neural network and support vector machine to verify.The optimization method has the great effect on the improvement of the prediction precision of the intelligent algorithm.