模糊神经网络的混合学习算法及其软测量建模

提出了一阶TSK模糊神经网络的混合学习算法，算法由三部分组成：基于模糊聚类的网络初始化；基于梯度下降的规则前件的学习算法；基于部分最小二乘的规则后件的学习算法。该混合算法可以根据训练样本的分布自动确定模糊神经网络的初始值，当输入变量个数多时不会出现模糊规则数爆炸现象，训练速度快，模型精度高。将混合学习算法应用到PTA工业过程中4-CBA含量的软测量建模中，取得了令人满意的效果。

Fuzzy Neural Network Based on Hybrid Learning Algorithm and Its Application to Soft Sensor

A new hybrid learning algorithm was proposed to train the fuzzy neural network based on TSK fuzzy model. Firstly, fuzzy c-means algorithm was applied to initialize the parameters of the fuzzy neural network. Secondly, the parameters of the premise part of the fuzzy rule were learned by the gradient descent algorithm. Finally, the parameters of consequent part were learned by the partial least squares algorithm. The proposed hybrid method could automatically give appropriate initial parameters of the fuzzy neural network and prevent the fuzzy rule number from increasing for high-dimensional systems. The results of simulation and industrial application show that the hybrid learning algorithm has properties of fast convergence and high accuracy. The proposed method has been applied to build a soft-sensor for measuring the 4-CBA concentration in the industrial PTA(Purified Terephthalic Acid)oxidation process and the result demonstrates that the proposed method is suitable to practical application.