【摘要】 针对五步开关控制算法易超调以及控制参数取值具有近似性和不确定性等不足，提出了一种参数自整定和参数寻优的控制算法，并在最关键的脉冲调制控制环节运用了改进的BP神经网络算法和粒子群（PSO）算法来寻找最优阀门控制参数。搭建智能阀门定位器实验平台，采用传统五步开关控制算法和本控制算法分别对阀门进行控制试验。结果表明，本控制算法相较于传统五步开关控制算法的适用性大大增强，避免了超调，缩短了响应时间，阀门控制精度达到0.03%，阀门开度稳定时间缩短至1 s以内。更多还原

【Abstract】 In view of the shortcomings,such as susceptibility of the five-step switch control algorithm to overshooting,and the approximateness and uncertainty of the values of control parameters,a control algorithm of parameter self-tuning and parameter optimization was proposed,and the improved BP neural network algorithm and particle swarm optimization(PSO) algorithm were used in the most critical pulse modulation control link to find the optimal valve control parameters. The experimental platform of intelligent valve positioner was built,and the valve control experiments were carried out using the traditional five-step switch control algorithm and this control algorithm,respectively. The experimental results show that compared with the traditional fivestep switch control algorithm,the applicability of this control algorithm is greatly enhanced,which avoids overshooting,shortens the response time,achieves 0.03% valve control accuracy,and shortens the valve opening stabilization time to less than 1 second.更多还原