摘要
工程地质类比法作为一种经验迁移法,在应用过程中,人的主观意识起很大作用,故将人工神经网络与遗传算法相结合,智能化地建立不同工程之间非线性映射关系,将工程地质类比法程序化,降低了人为因素造成的差异性和不确定性,并通过边坡工程实例验证了该方法的可行性.
Engineering geological analogy method is often considered as an experience method, which provides physical-mechanics parameters of rock and soil in the project design and construction. However, it is found that the different engineers obtain different results in the process of its application. A programmed design of engineering geological analogy method is introduced based on a combined arithmetic between BP neural network and Genetic Algorithm,which can automatically establish a high-nonlinear mapping relation between different projects and reduce the diversity as well as the uncertainty. The feasibility of this new method is proved by slope engineering case study.
出处
《华北水利水电学院学报》
2007年第2期62-64,共3页
North China Institute of Water Conservancy and Hydroelectric Power
基金
国家自然科学基金项目(40602034)
河南省创新人才基金项目(200108)
关键词
工程地质类比法
BP神经网络
遗传算法
engineering geological analogy
BP neural network
genetic algorithm