摘要
为了解决通过室内试验评价渣土改良效果存在耗时长、成本高,无法满足目前隧道掘进中的预测需求等问题,基于深度学习,引入遗传算法GA(genetic algorithm)对传统BP(back propagation)神经网络重新设计和优化,创建GA-BP模型;选择均方根误差GMSE、平均绝对误差MAE和决定系数R2作为评价模型预测效果的研究指标;利用机器学习中支持向量机算法与随机森林算法的预测结果与GA-BP模型的预测结果进行对比。试验结果表明:1)基于深度学习的传统BP模型和本文创建的GA-BP模型的各项评价指标皆高于机器学习算法;2)相较于传统BP网络的预测结果,GA-BP模型对内摩擦角、渗透系数和坍落度预测的最高相对误差分别降低了7.18%、5.02%、1.17%,且GA-BP模型的RMSE、MAE和R2值都优于传统BP模型和机器学习算法的预测结果。由此可得,基于深度学习的神经网络比机器学习算法更能提取到数据之间的关联性,且经过遗传算法优化后得到的GA-BP模型提高了传统BP模型的预测准确度。
The existing indoor tests on soil conditioning effect have many disadvantages such as long time and high cost,as well as cannot meet prediction needs in tunnel excavation.In this paper,based on deep learning,genetic algorithm(GA)is introduced to redesign and optimize the traditional back propagation(BP)neural network to create a GA-BP model.The root mean square error(RMSE),the mean absolute error(MAE),and the determinable coefficients R 2 are selected as the research indicators to evaluate the prediction effect of the model.Finally,the prediction results of the support vector machine algorithm and the random forest algorithm in machine learning are compared with those of the GA-BP model.The experimental results show the following:(1)Both the traditional BP model based on deep learning and the GA-BP model created have higher evaluation indexes than the machine learning algorithm.(2)Compared with the prediction results of the traditional BP network,the highest relative errors of the GA-BP model for the prediction of internal friction angle,permeability coefficient,and slump are reduced by 7.18%,5.02%,and 1.17%respectively.(3)The RMSE,MAE,and R 2 values of the GA-BP model are better than the prediction results of the traditional BP model and the machine learning algorithm.It can be concluded that deep learning-based neural networks are better at extracting correlations between data than machine learning algorithms,and the GA-BP model obtained after optimization by genetic algorithms improves the prediction accuracy of traditional BP models.
作者
刘汭琳
满轲
刘晓丽
宋志飞
周然
LIU Ruilin;MAN Ke;LIU Xiaoli;SONG Zhifei;ZHOU Ran(College of Engineering,North China University of Technology,Beijing 100043,China;State Key Laboratory of Hydroscience and Hydraulic Engineering,Tsinghua University,Beijing 100084,China;YSD Rail Transit Construction Co.,Ltd.,Guangzhou 510610,Guangdong,China)
出处
《隧道建设(中英文)》
CSCD
北大核心
2023年第S01期222-232,共11页
Tunnel Construction
基金
国家重点研发项目(2018YFC1504801,2018YFC1504902)
国家自然科学基金项目(51522903,51774184)
清华大学水沙科学与水利水电工程国家重点实验室资助(2019-KY-03)
北方工业大学毓杰项目(216051360020XN199/006)
北方工业大学城市地下空间智能建造关键技术(110051360022XN108-19)。
关键词
富水砂层
渣土改良
遗传算法
BP神经网络
效果预测
water-rich sandy stratum
soil conditioning
genetic algorithm
back propagation neural network
effect prediction