Model construction for quality of beer and brewing process using FNN
Model construction for quality of beer and brewing process using FNN
复制标题
DOI：
10.1252/kakoronbunshu.25.695
复制
发表时间：
1999-09-01
影响因子：
0.4
通讯作者：
Kobayashi, T
中科院分区：
文献类型：
--
作者：
Noguchi, H;Hanai, T;Kobayashi, T
利用模糊神经网络建立了啤酒感官评价模型和啤酒酿造过程模型。将遗传算法和SWEEP算子相结合的优化模型选择方法与传统的参数递增法进行了比较。结果表明，该方法简化了模型结构，提高了模糊规则的可靠性，加快了计算速度（约为传统方法的10倍），可获得高精度的模型。感官评价模型的正确回答率为92%。选取重要变量作为输入变量，建模得到的模糊规则与过程操作员获取的知识数据库吻合较好，证明了所建立的模糊神经网络模型是适当的。
Models for sensory evaluation of beer and the beer brewing process were constructed using a fuzzy neural network (FNN). A new method for optimal model selection using a genetic algorithm and a SWEEP operator method was compared with a conventional method using the parameter increasing method. As the result, the new method was useful for the optimal model selection by simplifying the model structure, improving the reliability of fuzzy rules, and accelerating the calculation speed (about 10 times as fast as conventional method) for constructing the model with high accuracy. The percentage of correct answers of the sensory evaluation model is 92%. The important variables are selected as the input variables, and the obtained fuzzy rules in modeling coincide well with knowledge data bases acquired by process operators, and it is proven that the obtained FNN models are adequate.