摘要
针对精密角度定位系统存在非线性、时变性,传统PID控制难以获得理想控制效果的问题,提出一种基于模糊神经网络的PID控制方法,将模糊控制、神经网络与PID控制相结合,采用3层前向网络、动态BP算法,利用神经网络的自学习和自适应能力,实时调整网络的权值,改变PID控制器的控制参数,整定出一组适用于控制对象的kp、ki、kd参数,实现精密角度定位PID控制的自适应和智能化。实验结果表明,采用BP神经网络整定的PID控制较传统的PID控制,控制性能有较大的提高,能有效提高定位精度,缩短定位时间。
Due to the non-linearity and time-variation characteristics of precision angular alignment system,traditional PID control can hardly obtain good performance;a precision angular alignment PID control method based on fuzzy neural network is proposed.A control platform combining fuzzy control,neural network and PID control is applied in angular alignment control.A dynamic BP algorithm with three layer forward networks is adopted.With the functions of self-learning and adaptability,the weights of the BP network and the parameters of the PID controller are adjusted in real time to set up a group of kp,ki and kd parameters that are suitable for the control object;therefore the self-adaptation and intelligence of the precision angular alignment PID control can be realized.Experimental result shows that the PID controller based on BP neural network adjusting has better control characteristics than traditional PID controller.The positioning time is shortened and the positioning accuracy is effectively improved.
出处
《仪器仪表学报》
EI
CAS
CSCD
北大核心
2012年第3期549-554,共6页
Chinese Journal of Scientific Instrument
基金
国家863计划(2005AA303610)
江苏省自然科学基金(BK2009406)资助项目