基于免疫遗传算法的动态递归模糊神经网络在发酵过程中的应用

针对软测量建模数据中过失误差及动态递归模糊神经网络的结构复杂，大量参数难以确定的情况，提出基于免疫遗传算法动态递归模糊神经网络软测量方法。利用样本间马氏距离进行样本相似程度分析，去除样本中错误数据以提高计算速度。此外应用减法聚类确定模糊规则数,以简化网络结构，同时应用免疫遗传算法优化模型参数以提高模型的精度和泛化能力。该方法应用于赖氨酸发酵过程菌体浓度的软测量，仿真结果表明，该方法具有较高的预测精度,满足现场测量要求。

Application of Dynamic Recursive Fuzzy Neural Network Based on Immune Genetic Algorithm to Fermentation Process

In order to solve the problem of the existence of gross errors in data samples for soft sensing modeling and the dynamic recursion fuzzy neural network's structure is complex, the massive parameters determined with difficulty, An soft sensor based on immune genetic algorithm and dynamic recursive fuzzy neural network is proposed.Similarities between samples were analyzed by way of computing Mahalanobis distance ,most of the original sample points were removed to increase the computing speed.moreover. In addition, application of subtractive clustering to determine the number of fuzzy rules in order to simplify the network structure, an immune genetic algorithm was introduced to optimise the model parameters At the same time to enhance the its precision and generalization ability. The model applies in biomass concentration soft in the lysine fermentation process,the simulation example shows that the model has high prediction precision and good generalization ability, and it satisfies the need of spot measurement.