xPC环境下CMACNN在淀粉生产线液位控制中的应用  

Application of CMAC Controller in Starch Production-line Liquid-level Based on xPC Environment

作　　者：沈刚[1] 何景峰[1] 丛大成[1] 白晓东[1] 唐晖[2] 韩俊伟[1] 

机构地区：[1]哈尔滨工业大学机电工程学院,哈尔滨150001 [2]长春职业技术学院工程技术分院,长春130033

出　　处：《农业机械学报》2009年第2期142-145,95,共5页Transactions of the Chinese Society for Agricultural Machinery

基　　金：哈尔滨工业大学与北大荒九三薯业股份有限公司合作项目(070716-028HB100130)

摘　　要：在分析CMAC神经网络的基础上,提出了利用自适应CMAC神经网络来调节淀粉生产线中乳液的液位。通过对淀粉生产线中某一液位回路进行数学建模,然后对常规PID和自适应CMAC神经网络两种控制器进行了设计与仿真。仿真结果表明,自适应CMAC神经网络在控制效果上明显优于常规PID,并且具有很高的鲁棒性。在Matlab实时开发环境xPC Target下建立了液位实时控制系统,采用快速原型控制方式,具有系统组建方便、成本低、开发周期短等特点,该系统可实现精确的过程控制。Self-adaptive CMAC NN was used to adjust the liquid-level of the starch production-line after analyzing and comparing the principle of tradition PID and self-adaptive CMAC NN and a mathematical model about one of liquid-level loop of starch production-line was built, then, a controller was designed and simulated. The simulation results showed that self-adaptive CMAC NN is better than tradition PID on the respect of control effect and its robustness is higher than tradition PID. Real-time level process control system was devised on the basis of xPC Target software environment of Matlab. The rapid prototyping control system could be done easily and the investment is cheap. The period of development could be shortened. This system could realize the accuracy process control.

关 键 词：淀粉生产线 自适应 CMAC神经网络 液位控制 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置] TS234[自动化与计算机技术—控制科学与工程]