模糊—神经网络控制算法及其在离心力—振动复合环境试验系统中的应用

针对离心－振动复合环境试验系统所存在的耦合性、非线性和不确定性提出了一种模糊－神经网络控制算法，利用被控对象输入输出信息离线、在线相结合学习系统的动态特性，对时变、非线性系统进行跟踪控制，并研究了该算法在系统中的实现方法。实现表明了控制系统具有良好的跟踪能力。该算法也适用于快速变化这类系统的实时控制。

Fuzzy-Neural Network Control Algorithm and the Application in Centrifugal Force and Vibration Combined Environment Testing System

A new adaptive control method based on fuzzy neural network, with respect of the complex nonlinearities and coupling in the centrifugal force and vibration combined environment testing system, is presented and a controller based fuzzy neural reasoning is designed in this paper. A controller is composed of the fuzzy controller and FNI network. The control rules is produced by fuzzy controller. FNI network is trained off line by steepest gradient drop algorithm, the samples for training FNI regulated on line by using the measured input/output data with the neural network learning method derived from steepest gradient drop algorithm. The output of network is mapped the input of vibrator by compressor. The effectiveness of the tracking control system is verified by experiment results.