1. College of Automation,Shenyang Aerospace University,Shenyang 110136,China
2. Science and Technology on Thermal Energy and Power Laboratory No. 719,Research Institute of China Shipbuilding Industry Corporation,Wuhan 430205,China
Considering the complex factors of nuclear power steam generator system,such as unknown communication faults and variable working conditions,a model prediction/data-driven switching control method for steam generator water level was proposed. First,a deep deterministic policy gradient (DDPG) controller was designed,which includes state parameter selection,action parameter design,reward function design,was done condition design and network design,etc. The DDPG controller operates normally when there were no communication faults in the steam generator control system. On this basis,a model predictive control (MPC) predictive compensation controller was designed to resist communication failures. The system was switched to the MPC controller to compensate for the lost data when communication failures occurred. The simulation results show that the MPC/DDPG switching controller of the steam generator water level can obtain a good control performance under the typical external inputs. They also show good stability and security under unknown failures.
DemerdashN A, El-HameedM A, EisawyE A,et al.Optimal feed-water level control for steam generator in nuclear power plant based on meta-heuristic optimization[J].Journal of Radiation Research and Applied Sciences,2020,13(1):468-484.
[4]
戴旭.基于模糊自整定PID内模的蒸汽发生器水位控制[D].沈阳:沈阳工业大学,2015.
[5]
AblayG.A robust estimator-based optimal algebraic approach to steam generator feedwater control system[J].Turkish Journal of Electrical Engineering and Computer Sciences,2016,24(1):206-218.
[6]
WangJ, ZhouJ, LuanX,et al.Discrete gain-scheduled PD control to nuclear steam generator water level[C].2016 35th Chinese Control Conference (CCC).Chengdu:IEEE,2016:2992-2997.
[7]
AnsarifarG R.Control of the nuclear steam generators using adaptive dynamic sliding mode method based on the nonlinear model[J].Annals of Nuclear Energy,2016,88(10):280-300.
[8]
SalehiA, SafarzadehO, KazemiM H.Fractional order PID control of steam generator water level for nuclear steam supply systems[J].Nuclear Engineering and Design,2019,342(12):45-59.
[9]
本刊采编部.“震网”病毒袭击伊朗核设施[J].信息安全与通信保密,2016,14(9):24.
[10]
陆念慈.船用蒸汽发生器动态性能及水位控制研究[D].哈尔滨:哈尔滨工程大学,2018.
[11]
SuttonR S, BartoA G, WilliamsR J.Reinforcement learning is direct adaptive optimal control[J].IEEE Control Systems Magazine,1992,12(2):19-22.
[12]
SilverD, SchrittwieserJ, SimonyanK,et al.Mastering the game of go without human knowledge[J].Nature,2017,550(76):354-359.
[13]
王晓争.基于改进DDPG算法的永磁吸附式机器人的控制研究[D].大庆:东北石油大学,2022.
[14]
ChenG.Autonomous and cooperative control of UAV cluster with multi-agent reinforcement learning[J].The Aeronautical Journal,2022,126(1300):932-951.
AlamdariS H, KarrasG C, MarantosP,et al.A robust predictive control approach for underwater robotic vehicles[J].IEEE Transactions on Control Systems Technology,2020,28(6):2352-2363.
[19]
LiD, SchutterB D.Distributed Model⁃free adaptive predictive control for urban traffic networks [J].IEEE Transactions on Control Systems Technology,2022,30(1):180-192.
[20]
ChenJ, YangF, HanQ.Model⁃free predictive H∞ control for grid⁃connected solar power generation systems[J].IEEE Transactions on Control Systems Technology,2014,22(5):2039-2047.
[21]
HanH, LiuZ, LiuH,et al.Knowledge-data-driven model predictive control for a class of nonlinear systems[J].IEEE Transactions on Systems,Man,and Cybernetics:Systems,2019,51(7):4492-4504.
[22]
WanJ, WuS, NuerlanA,et al.Dynamic modeling of AP1000 steam generator for control system design and simulation[J].Annals of Nuclear Energy,2017,109(5):648-657.