改进的模糊神经网络应用于投标报价

针对模糊神经网络规则膨胀导致的网络训练速度慢和泛化能力弱的缺陷,提出了一种改进的基于T-S模型的模糊神经网络的结构和算法。网络结构包括前件和后件网络二部分,本文在后件网络中增加了一个隐含层以提高计算能力,在前件网络中运用了有效模糊规则选取的方法以提高收敛速度。最后将提出的网络结构应用于建筑工程的投标报价中,仿真结果证明:该网络能达到更高的误差精度、更快的训练速度和更好的泛化能力。

An Improved Fuzzy Neural Network and Its Application in Bidding

Because of the expanding of the fuzzy rules caused by the increasing of the input numbers,the training speed is slower and generalization ability of the fuzzy neural network is weaker.This paper proposes an improved fuzzy nerual network(IFNN) based on T-S model to overcome these problems.The structure of IFNN contains two sub networks:premise network and consequent network.One hidden layer is added in consequent network to improve its approximate ability and generalization ability.And in premise network the fuzzy rules are chosen efficiently to speed up the train speed.At last the proposed network is used to the construction bidding system.The results of the simulation indicate that it can obtain higher error precision,training speed and generalization ability.