基于DRNN的三电机变频调速系统参数PID控制研究

PID Control of Three-motor Variable Frequency Speed-regulating System Based on DRNN Network

三电机变频调速系统是一个多输入多输出、非线性、耦合的系统。针对电流跟踪型感应电机系统,以解析式的方式建立其数学模型。采用基于对角递归DRNN神经网络的自整定PID控制器,结合自适应神经元解耦补偿器的解耦控制技术,设计三电机变频调速系统神经网络控制器。基于S7-300 PLC控制平台进行实际的试验,结果表明,该方法能够根据外界环境信息变化获得最佳PID调节参数,较好的实现了速度和张力的解耦控制,系统具有良好的动静态性能和抗干扰能力。提出的方法满足了许多工业控制场合的需要,具有良好应用前景。

Three-motor variable frequency speed-regulation system is a multi-input multi-output（MIMO）,nonlinear,and high coupling complex control system.Focusing on the system of induction motors powered by current-tract SPWM transducers,the mathematic model of the system of three motors is established.Combining decoupling technology of adaptive neuron decoupling compensator,self-turning PID controller based on DRNN neural network is adopted to design the neural network controller of three-motor synchronous system.The experiment results show that the control system can get some optimal parameters of the PID controllers according to different running state of system,and realize the better decoupling control of speed and tension with better performances of dynamic and static status.Thus,the method presented in the paper meets the requirements of many industrial control environments,with good application prospects.