带偏差单元BP神经网络土体灌浆压力预测
详细信息 本馆镜像全文    |  推荐本文 | | 获取馆网全文
摘要
灌浆压力是土体灌浆加固的重要参数。基于神经网络非线性映射特性,分析土体灌浆压力主要影响因素,建立符合一般工程判断和决策思维的BP网络预测模型,并引入偏差单元对其结构进行改进,实现了快速收敛,较高精度得出灌浆预测压力的具体数值。预测结果与室内灌浆试验压力对比表明,带偏差单元BP神经网络的土体灌浆压力预测结果具有较高准确性和一定的实用意义。
Grouting pressure is an important parameter in soil mass consolidation by grouting.Based on the nonlinear mapping characteristics of neural network,the main factors affecting the grouting pressure are analyzed and the BP network prediction model consistent with general engineering judgment and decisionmaking thoughts is established.In addition,the structure of the model is improved by introduction of bias element;thus fast convergence is realized and the specific value of grouting pressure estimate with high accuracy is obtained.The comparison between predicted result and measured pressure from indoor grouting test shows that the estimate of the grouting pressure by BP neural network with bias element has high accuracy and certain practical significance.
引文
[1]葛家良.化学灌浆技术的发展与展望[J].岩石力学与工程学报.2006,25(2):3384-3392.
    [2]贺俊,杨平,董朝文.基于BP神经网络冻土强度预测模型研究[J].路基工程,2011(3):55-57.
    [3]安宁.基于BP神经网络的黄土湿陷性预测研究[J].路基工程,2009(1):72-73.
    [4]彭小东,陆阳,牟瀚林.压力灌浆在加固公路路基中的应用及问题[J].路基工程,2008(5):97-99.
    [5]王小雄,闫小华,姚永锋,白建军.基于改进BP算法神经网络的路况评价模型研究[J].重庆交通大学学报:自然科学版,2007,26(4):82-85.
    [6]彭放,杨瑞琰,罗文强.数学建模方法[M].北京:科学出版社,2007.
    [7]张传庆,杨庆,栾茂田.非饱和土吸力预测的进化神经网络方法[J].岩土力学,2004,25(1):73-76.
    [8]吕远强,林杜军,罗伟强.基于人工神经网络的区域地质灾害危险性预测评价[J].中国地质灾害与防治学报,2007,18(1):95-98.
    [9]夏金梧,李长安,王旭.基于神经网络理论的三峡水库诱发地震预测研究[J].水文地质工程地质,2007(5):17-20.

版权所有:© 2023 中国地质图书馆 中国地质调查局地学文献中心