针对蔗糖结晶过程控制中存在的模型复杂性和检测困难等问题,建立了蔗糖结晶过程的遗传神经网络模型.该模型用一种改进的实数编码提高了遗传算法的搜索能力,并根据该模型建立了结晶过程的预测控制系统.仿真和实验的结果表明,该方法在确定成糖时间和浓度方面是有效的.“,”In view of the model nonlinearity, the complexity, and the measuring difficulty in the crystallizing process of cane sugar, a genetic neural network model is established. In this model, the coding scheme of real numbers is applied to the genetic algorithm to improve search efficiency. Based on the model, a predictive control system of the crystallizing process is constructed. The results of the simulation and experiment show that the method is effective in calculating the content of sugar crystals and the boiling time of a strike.