基于MEA-BP神经网络预测冻土应力-应变关系  

Prediction of Stress-strain Behavior of Frozen Soil Based on MEA-BP Neural Network

作　　者：王金元 彭远锋 芮瑞[1] WANG Jin-yuan;PENG Yuan-feng;RUI Rui(School of Civil Engineering and Architecture,Wuhan University of Technology,Wuhan 430o70,China)

机构地区：[1]武汉理工大学土木工程学院,武汉430070

出　　处：《武汉理工大学学报》2024年第3期86-92,115,共8页Journal of Wuhan University of Technology

基　　金：国家自然科学面上基金(42272315)。

摘　　要：为了实现冻土的应力-应变关系的准确预测,研究采用遗传算法(GA)、思维进化算法(MEA)和麻雀优化算法(SSA)对反向传播(BP)神经网络的初始权重和阈值进行优化。以温控三轴试验中冻土的温度、围压和轴向应变3个主要参数为输入,以其轴向应变所对应的偏应力为输出,建立了基于3种优化算法优化的BP神经网络预测模型。结果表明,MEA对于BP神经网络模型的优化性能最佳;MEA-BP均方根误差最小,预测值和实际值的拟合度(R^(2))接近于1,能够有效地对冻土的应力-应变关系进行预测。In order to achieve accurate prediction of the stress-strain relationship of frozen soil,researchers have utilized genetic algorithm(GA),mind evolutionary algorithm(MEA),and sparrow search algorithm(SSA)to optimize the initial weights and thresholds of the backpropagation(BP)neural network.Taking the temperature,confining pressure,and axial strain as the main input parameters in the temperature-controlled triaxial test,and the corresponding deviator stress of the axial strain as the output,a BP neural network prediction model optimized by these three algorithms was established.The research results indicate that MEA achieves the best optimization performance for the BP neural network model.MEA-BP has the smallest root mean square error and a high degree of fit(R^(2))close to 1 between predicted values and actual values,effectively predicting the stress-strain relationship of frozen soil.

关 键 词：冻土 应力-应变关系 遗传算法 思维进化算法 麻雀优化算法 BP神经网络 

分 类 号：TU43[建筑科学—岩土工程]