摘要
蒸汽发生器液位的稳定对核电厂的安全运行有重要影响。蒸汽发生器是一个非线性、时变、非最小相位、小稳定裕度和大时滞的复杂系统。工程中常用的三冲量串级PID控制方法在中、低功率水平下控制效果欠佳。为解决上述问题,提出神经网络PID液位控制系统,根据梯度下降法调整神经网络权重矩阵,对PID控制器参数进行优化。通过Simulink将控制系统部署到SG仿真模型中,在多种功率水平下,采用典型工况进行了数值模拟。仿真结果表明,与经典串级PID控制系统相比,神经网络PID控制系统超调量小、调节时间短,在高、中、低功率水平下控制稳定、抗干扰能力强,具备一定的工程应用价值。
The stability of the steam generator liquid level has a significant impact on the safe operation of nuclear power plants.The commonly used three-impulse cascade PID control method in engineering has poor control performance at medium and low power levels.In order to solve the above problems,this paper proposes a neural network PID level control system.According to the gradient descent,the neural network weight matrix is adjusted to optimize the parameters of the PID controller.The control system is deployed into the SG simulation model through Simulink,and numerical simulations are conducted using typical operating conditions at various power levels.The simulation results show that compared with the classic cascade PID control system,the neural network PID control system has smaller overshoot,shorter adjustment time,stable control and strong anti-interference ability at high,medium,and low power levels,and has certain engineering application value.
作者
陈杰
曹惺笛
Chen Jie;Cao Xingdi(China Nuclear Power Engineering Co.,Ltd.,Beijing 100840,China)
出处
《电子技术应用》
2024年第S2期232-236,共5页
Application of Electronic Technique
关键词
蒸汽发生器
液位控制
神经网络PID
控制系统仿真
steam generator
liquid level control
neural network PID
control system simulation
