【摘要】 文中以埋地高密度聚乙烯(PE)燃气管道作为研究对象，首先基于有限元数值分析方法研究了埋地燃气管道在土体非均匀变形中的应力变化，得到管道在不同土体非均匀变形作用下的最大von Mises应力；然后以所获得的数据作为训练样本，采用BP神经网络训练得到了埋地管道在土体非均匀变形作用下的应力预测模型，结果表明预测准确率为94.47%;最后在此基础上绘制出埋地管道最大von Mises应力与土体非均匀变形量之间的应力云图。更多还原

【Abstract】 The buried high-density polyethylene(PE) gas pipeline was used as the research object in this paper.Based on the finite element numerical analysis method, the stress variation of buried gas pipeline in uneven soil deformation was studied.The maximum von Mises stress of the pipeline under different uneven soil deformation was obtained.Then, the obtained data was used as a training sample, a stress prediction model for buried pipeline under uneven soil deformation was trained and obtained by using BP neural network.The result shows that the prediction accuracy of the model is 94.47%.Finally, a stress cloud map between the maximum von Mises stress of the buried pipeline and the uneven soil deformation was depicted on this basis.更多还原