The effect that the combination of input, the number of membership function of input, training times and training sample affect the learning ability and generalization ability of NFS was researched respectively. The relation between the learning ability and generalization ability was studied. 分别研究了输入变量组合、隶属函数个数、训练次数、训练样本个数等对神经模糊系统的学习能力、泛化能力的影响以及神经模糊系统的学习能力和泛化能力之间的关系。
This algorithm is realized by means of obtaining membership function, constructing and training fuzzy neural network, then pruning network and extracting rules. 通过计算隶属函数、构造及训练模糊神经网络、网络裁减、规则提取等步骤实现该算法；
In addition we discuss the influence upon training efficiency and performance of this network generated by overlapping state of membership functions of fuzzy subsets. We bring forward modifying parameters of membership functions during samples learning and training. The problem on selecting and optimizing parameters was resolved effectively. 本文探讨了模糊子集隶属函数的重叠状态对网络训练效率及性能的影响，提出在网络训练中通过样本学习和训练修正隶属函数的参数，有效地解决了隶属函数参数选取和优化的问题。
Basically, it is a competitive soft learning vector quantization embedded with reinforcement learning, and the reinforcement signal is so constructed as to depend on the membership function of the supervised signal of the corresponding training vector. 该算法是在模糊竞争学习矢量量化的基础上引入增强学习，并用输入训练模式的监督信号与类别模式之间的隶属度控制增强信号。
Considering long time delay and strong coupling existed in the process of continuous carbonation decomposition, an intelligent resolution ratio control system is developed. In this system, the membership functions and fuzzy reference rules are optimized by genetic algorithm through training the stable error as objective function. 针对连续碳酸化分解过程具有大滞后、强耦合的特点，建立了分解率模糊智能控制系统，将稳态误差作为目标函数，用遗传算法优化隶属函数参数和模糊推理规则。
