谷氨酸发酵工艺参数的模式识别优化设计  

The Optimization of Technological Condition of Glutamate Fermentation by Pattern Recognition Method

作　　者：徐驰[1] 陈超菊 王焕章 孙剑萍 

机构地区：[1]中国科学院上海冶金研究所,上海200050 [2]广东肇庆星湖味精集团公司,广东526060

出　　处：《生物工程学报》1994年第2期124-129,共6页Chinese Journal of Biotechnology

摘　　要：应用模式识别调优法,对谷氨酸发酵的各项可控工艺参数(如pH值,温度,风量等)进行优化设计。以多维空间图象处理技术揭示模式空间的可视优化区,结合Monte Carlo模拟法从低维映照平面逆照到高维原始空间,设计了若干组优化工艺条件,经生产试验后补充新的生产记录,再行设计新的数学模型。对比试验表明:按模式识别优化设计的工艺条件操作,糖酸转化率提高2.90％,罐产量提高1.45％,产酸率提高2.65％。优化设计方案已投入实际生产应用。该方法对降低原料单耗、产品成本具有很大潜力。The technological condition of the fermention process of glutamate (such as pH value, temperature, ventilation rate et al. ) were optimized by computerized pattern recognition method. The optimization region, which is visual, were found based on the mapping from multi-dimensional pattern space into plane, then it is transformed by reciprocal direction into the original data space using Monte Carlo simulation, so the deric-tion of optimization and best combination of all factors can be determined. A new mathematical model is being proposed based on experimental evidence taken from actual production. Using the optimization method the conversion yield of carbonhydrate into glutamate increases 2.90% , the production capacity increases 1. 45%, and the glutamate output increases 2. 65%. The method has great potentialities for the decrement of the expense of raw materials and that of production cost. ,

关 键 词：谷氨酸 发酵 优化设计 模式识别 

分 类 号：TQ922.1[轻工技术与工程—发酵工程]