【摘要】 将人工神经网络与遗传算法相结合， 提出了一种用于位移反分析的进化神经网络方法。这种方法基于正交试验获得的样本进行学习， 用遗传算法搜索最优的神经网络结构， 并用最佳推广预测学习算法训练此网络， 以此训练好的网络描述岩体（土）的力学参数与岩体位移之间的非线性关系， 再应用遗传算法从全局空间上搜索， 进行岩体力学参数的最优辩识。作为例子， 文中给出了弹性问题的反分析， 结果是令人满意的。更多还原

【Abstract】 An evolutionary neural network method for displacement back analysis is proposed by combining the neural network and genetic algorithm. The samples produced in orthogonal experiment are used to train the neural network whose architecture is determined in global optimum by genetic algorithm. Thus, the neural network with optimal architecture trained by optimal prediction algorithm is used to describe the relationship between the rock mechanical parameters and displacements produced due to excavation. Then genetic algorithm is adopted again to search the optimal rock mechanical parameters in their global ranges. As an example, a back analysis for elastic problem is introduced. The results are satisfactory.更多还原