论文部分内容阅读
针对目前对高压电缆的温度测量方法大都是只能测量当前的温度,滞后控制,不能进行提前辨识的问题,对传统电缆测温方法进行研究,提出用神经网络控制器对高压电缆温度进行测量的方法.在3种常规控制器的基础上设计了3种基于神经网络的控制器:神经自校正控制器、神经PID(proportion integration differentiation)控制器和神经自适应控制器,不仅对它们进行神经网络训练,而且用MATLAB软件进行仿真.通过仿真结果最终选用神经PID控制器,并将其应用于实际高压电缆测温系统当中,经在新疆供电系统检验,效果良好.
According to the current methods of measuring the temperature of high voltage cables, most of them can only measure the current temperature and hysteresis control, and can not be identified in advance. The traditional method of temperature measurement is studied, and the temperature of high voltage cable is measured by neural network controller Three kinds of controllers based on neural network are designed based on three kinds of conventional controllers: neural self-tuning controller, neural network PID (proportional integration differentiation) controller and neural adaptive controller, not only their neural network Train, and use MATLAB software to simulate.Finally, the neural PID controller is selected by the simulation results and applied to the actual high-voltage cable temperature measurement system, which is tested by Xinjiang Power Supply System and works well.