交通荷载下煤矸石路基填料累积变形PSO-BP神经网络预测模型  

PSO-BP neural network prediction model for cumulative deformation of coal gangue subgrade filler under traffic loading

作　　者：张宗堂[1] 肖天祥 高文华 杨洋 衣利伟 ZHANG Zongtang;XIAO Tianxiang;GAO Wenhua;YANG Yang;YI Liwei(Hunan Provincial Key Laboratory of Geotechnical Engineering for Stability Control and Health Monitoring,Hunan University of Science and Technology,Xiangtan 411201,China;Hunan Construction Engineering Group Co.Ltd.,Changsha 410004,China;Hunan Software Vocational and Technical University,Xiangtan 411201,China;Gansu Jingyuan Coal Engineering Survey and Design Co.,Ltd.,Baiyin 730913,China;China Construction Fifth Engineering Division Co.,Ltd.,Changsha 410004,China)

机构地区：[1]湖南科技大学岩土工程稳定控制与健康监测湖南省重点实验室,湖南湘潭411201 [2]湖南建工集团有限公司,湖南长沙410004 [3]湖南软件职业技术大学,湖南湘潭411201 [4]甘肃省靖远煤业工程勘察设计有限公司,甘肃白银730913 [5]中国建筑第五工程局有限公司,湖南长沙410004

出　　处：《水利水电科技进展》2024年第2期87-91,共5页Advances in Science and Technology of Water Resources

基　　金：国家自然科学基金项目(52208341);湖南省自然科学基金项目(2023JJ40293);湖南省科技人才托举工程项目—“小荷”科技人才专项(2023TJ-X74);湖南省教育厅科学研究优秀青年项目(23B0492)。

摘　　要：基于煤矸石路基填料大型动三轴试验结果,采用灰色关联分析法分析累积变形影响因子,确定了围压、压实度、级配参数、循环荷载振动次数4个特征参数。引入PSO算法对BP神经网络的权重、阈值进行全局寻优并赋值,提出了一种煤矸石路基填料累积变形PSO-BP神经网络预测模型。与传统BP神经网络模型对比结果验证了该预测模型的可行性和优越性,并通过不同学习程度下模型的预测效果分析了模型的泛化能力,证明了模型的预测潜力。Based on the results of large-scale dynamic triaxial tests on coal gangue subgrade fillers,the grey correlation analysis method was used to analyze the influencing factors of cumulative deformation,and four characteristic parameters were determined,including confining pressure,compactness,gradation,and cyclic loading number.The particle swarm optimization(PSO)algorithm was used to globally optimize and assign the weights and thresholds of the back propagation(BP)neural network,and a PSO-BP neural network prediction model for cumulative deformation of coal gangue subgrade fillers was established.By comparing the traditional BP neural network with the established prediction model,the feasibility and superiority of the established prediction model were verified.The generalization ability of the model was further analyzed by comparing the prediction effects of the model under different learning levels,which proved the prediction potential of the model.

关 键 词：煤矸石路基 累积变形预测 灰色关联分析 粒子群算法 BP神经网络 

分 类 号：TU411[建筑科学—岩土工程]