PSA-ANFIS方法的研究

矿山中的岩土工程灾害预测问题,是采矿工程领域亟需研究解决的重大课题.本文即针对这些问题,采用正交试验设计法和模式搜索算法研究了自适应神经模糊推理系统(ANFIS)的训练参数和模型结构的优化方法,提出和建立了基于模式搜索算法的自适应神经模糊推理方法(PSA-ANFIS).进一步采用一多峰函数进行离散,构建了训练数据对、检测数据对和预测数据对,对PSA-ANFIS的拟合能力和预测能力进行了研究.结果表明,无论是在拟合精度和预测精度上,还是在训练参数的调整、模型结构的建立和训练过程上,PSA-ANFIS均适合于解决矿山岩土工程灾害预测这一高度非线性的映射问题.

Study on the PSA-ANFIS Approach

The problems on predicting geotechnical engineering disasters in mining engineering are the most important research subjects.According to the predicting problems,the paper studied the approach for setting the training parameters and model of ANFIS by using the orthogonal test design method and the pattern search algorithm(PSA),and put forward and established the approach for adaptive neuro-fuzzy inference system based on pattern search algorithm (PSA-ANFIS).Furthermore,the data pairs for training,data pairs for checking and data pairs for prediction were built by using a multi-peaks function,and the training process and the fitting and predicting capability of the PSA-ANFIS was studied.The results show that the PSA-ANFIS is well in parameters adjustment and model establishment,and that is an excellent approach for dealing with the nonliner and complex fitting problem on predicting problems in geotechnical engineering.