摘要
PID控制被广泛应用在工业过程控制领域,但是在实际应用中往往具有非线性、时变不确定性,导致PID参数整定难以达到最佳控制要求。本文将神经网络技术应用于PID控制中,利用神经网络具有的非线性函数逼近能力,通过对系统性能的学习来实现具有最佳组合的PID控制,并将研究结果用于单片机温度控制器,效果良好。
PID controllers are used in fields of process industry widely. However, in really application, PID parameters are not satisfied because of non-lined,non-surly characters in real time. NN（neutral network）technique is used in PID control because it can change the parameters on line by itself.In this way, a NN PID of self-tuning could be constructed. The result is used in single clip microcomputer temperature controller. It is proved satisfactory.
出处
《中国仪器仪表》
2006年第5期66-68,共3页
China Instrumentation
关键词
PID控制
BP神经网络
参数整定
温度控制
PID control BP neutral network Parameters self-tuning Temperature control
