论文部分内容阅读
在边坡最危险滑动面的搜索过程中,为避免目标函数建立时因公式化简带来的误差及传统优化算法易陷入局部极小值的问题,提出了基于BP-遗传算法的排土场稳定性分析方法。以瑞典条分法为基础,通过BP神经网络建立潜在滑动面的圆心、半径与其安全系数间的非线性关系式,利用遗传算法,搜索边坡的最危险滑动面,并计算其相应的安全系数。弓长岭排土场实例分析结果表明:与传统稳定性分析方法相比,BP-遗传算法的稳定性分析结果更加精确、可靠,具有较好的应用前景。
In the process of searching for the most dangerous slip surface of slope, in order to avoid the error caused by the formula simplification when the objective function is established and the traditional optimization algorithm easy to fall into the local minimum, the paper puts forward the stability of the dump based on BP-genetic algorithm Sexual analysis method. Based on the Swedish slice method, the nonlinear relationship between the center and radius of the potential slip surface and its safety factor is established by BP neural network. The genetic algorithm is used to search the most dangerous slip surface of the slope and calculate the corresponding safety factor . The results of the example of Gongchangling dump indicate that compared with the traditional stability analysis method, the stability analysis result of BP-GA is more accurate and reliable and has a good application prospect.