论文部分内容阅读
为了解决起重机吊重系统吊重摆角速度不易直接测量的问题,利用神经网络能对任意函数逼近的原理,采用RBF神经网络针对吊重摆角子系统,以吊重摆角为可测输入量,在基本状态观测器的基础上设计了神经网络状态观测器,通过合理设计神经网络参数,实现对吊重摆角速度现场软测量.与基本观测器的观测结果进行了对比仿真,结果表明:神经网络观测器的观测时间不到1 s;当系统存在建模误差和参数摄动时,神经网络观测器能较好地适应小车驱动力输入形式;在达到观测时间之前,基本观测器存在明显的高频振荡现象,且振荡的幅值随外界干扰幅值的增大而增大,神经网络观测器具有较平稳的观测过程.
In order to solve the problem that it is not easy to directly measure the hoisting speed of the hoisting system of a crane, the RBF neural network is used to approximate the hoisting subsystem based on the principle that a neural network can approximate any function, and the hoisting angle is taken as the measurable input. Based on the basic state observer, the neural network state observer is designed, and the soft sensor measurement of the swaying angle is achieved through the reasonable design of the neural network parameters.Compared with the observational results of the basic observer, the results show that the neural network observational The observer time is less than 1 s; when the system has modeling error and parameter perturbation, the neural network observer can better adapt to the input form of car driving force; before observing time, the basic observer has obvious high frequency Oscillation phenomenon, and the amplitude of oscillation increases with the increase of the amplitude of the external disturbance. The neural network observer has a relatively smooth observation process.