基于RBF神经网络预测方法的碱渣土工程特性分析
|
摘要
为了缓解纯碱行业生产快速发展与碱渣贮放的矛盾,国内碱厂主要采用贮渣池加高作为解决手段.对待建碱渣坝土样的工程特性进行预测分析,能够为坝体的后续加固加高提供科学依据.碱渣土具有复杂的物理力学性质,应用优化识别预测方法能够更好地揭示数据中各指标间的非线性关系,因此采用RBF神经网络的数据拟合能力,建立碱渣土工程特性的预测模型.通过工程算例的应用效果表明,RBF神经网络具有可调参数少、网络性能稳定和预测精度高等优点,分析了输入样本数目和宽度向量对RBF神经网络预测性能的影响,可为碱渣土工程特性的初步预测分析提供有效的决策依据.
In order to relieve a contradiction between the rapid development of soda industry and sludge storage,heightening residue storage tank was applied as a mean of resolution in many soda companies.If we analyze the engineering characteristics of slag soil,the analysis results can provide the scientific basis for raising dam.Because slag soil has the complex physico-mechanical properties,the optimal identification forecasting method should better reveal nonlinear relationship of data.In this paper a forecasting model is established with RBF neural network;it has an excellent data fitting ability.Through case studies show that RBF neural network has advantages of few adjustable parameters,network stability and good accuracy.In this paper,the effects of number of input samples and width vector on the prediction ability of RBF neural network are analyzed.Therefore,based on RBF neural network about optimal prediction for engineering characteristics of slag soil is feasible.
In order to relieve a contradiction between the rapid development of soda industry and sludge storage,heightening residue storage tank was applied as a mean of resolution in many soda companies.If we analyze the engineering characteristics of slag soil,the analysis results can provide the scientific basis for raising dam.Because slag soil has the complex physico-mechanical properties,the optimal identification forecasting method should better reveal nonlinear relationship of data.In this paper a forecasting model is established with RBF neural network;it has an excellent data fitting ability.Through case studies show that RBF neural network has advantages of few adjustable parameters,network stability and good accuracy.In this paper,the effects of number of input samples and width vector on the prediction ability of RBF neural network are analyzed.Therefore,based on RBF neural network about optimal prediction for engineering characteristics of slag soil is feasible.
引文
[1]王芳,徐竹青,严丽雪,等.碱渣土工试验方法及其工程土特性研究[J].岩土工程学报,2007,29(8):1211-1214.
[2]王迎春,王洁,杜安利,等.基于BP神经网络的动能杆毁伤指标预测模型[J].系统工程与电子技术,2013,35(9):1898-1902.
[3]卢万银.基于BP网络多指标多因素最优工艺参数分析[J].吉首大学学报:自然科学版,2012,33(5):34-38.
[4]尚福华,杨慧,张吉峰,等.基于QPSO的BP神经网络油田节能指标预测[J].计算机系统应用,2013,22(6):95-97.
[5]刘显德,杨婷婷,严胡勇,等.基于Elman神经网络和遗传算法的油田指标预测[J].计算机与现代化,2013,210(2):150-152.
[6]李四海,魏邦龙,李爱英.基于小波神经网络的空气污染指数预报[J].长春大学学报,2013,23(2):146-148.
[7]朱大奇,史慧.人工神经网络原理及应用[M].北京:科学出版社,2006.
[2]王迎春,王洁,杜安利,等.基于BP神经网络的动能杆毁伤指标预测模型[J].系统工程与电子技术,2013,35(9):1898-1902.
[3]卢万银.基于BP网络多指标多因素最优工艺参数分析[J].吉首大学学报:自然科学版,2012,33(5):34-38.
[4]尚福华,杨慧,张吉峰,等.基于QPSO的BP神经网络油田节能指标预测[J].计算机系统应用,2013,22(6):95-97.
[5]刘显德,杨婷婷,严胡勇,等.基于Elman神经网络和遗传算法的油田指标预测[J].计算机与现代化,2013,210(2):150-152.
[6]李四海,魏邦龙,李爱英.基于小波神经网络的空气污染指数预报[J].长春大学学报,2013,23(2):146-148.
[7]朱大奇,史慧.人工神经网络原理及应用[M].北京:科学出版社,2006.