发动机试验台测控系统模糊神经网络控制方法的研究  

A Research on Fuzzy Neural Network Control for the Measuring System of Engine Test Bed

作　　者：石晶[1] 段敏[1] 陈勇[1] 张涛[1] 鲁晓丽[1] 

机构地区：[1]辽宁工学院汽车与交通工程学院,锦州121001

出　　处：《汽车工程》2006年第1期48-50,84,共4页Automotive Engineering

基　　金：辽宁省教育厅基金项目(29101299)资助。

摘　　要：结合模糊控制、神经网络、遗传算法的优点,提出发动机试验台测控系统模糊神经网络控制方法。利用遗传算法的全局优化策略,避免陷入局部最小点的缺陷。在建立发动机-测功机传动系统动力学模型、发动机有效转矩模型、测功机励磁电流模型的基础上,进行了动态仿真模拟,较好地解决了试验台控制的稳定性及测量的实时准确性问题。Combining the advantages of fuzzy control, neural network and genetic algorithm, a network control method is proposed for the measuring system of engine test bed. Utilizing the global fuzzy neural optimization strategy of genetic algorithm, the defect of the least part point is avoided. The dynamics model for the drive system between engine and dynamometer, the effective engine torque model, and the model for excitation current of dynamometer are set up, and the dynamic simulation is performed. The results indicate that the control scheme has high stability and accuracy in the control of test-bed.

关 键 词：发动机试验台 控制系统.模糊神经网络.仿真 

分 类 号：U467.522[机械工程—车辆工程] TP242[交通运输工程—载运工具运用工程]