CN104102782A - Method for controlling temperatures of reactors of pressurized water reactor nuclear power stations by aid of RBF (radial basis function) neural networks - Google Patents
Method for controlling temperatures of reactors of pressurized water reactor nuclear power stations by aid of RBF (radial basis function) neural networks Download PDFInfo
- Publication number
- CN104102782A CN104102782A CN201410344231.4A CN201410344231A CN104102782A CN 104102782 A CN104102782 A CN 104102782A CN 201410344231 A CN201410344231 A CN 201410344231A CN 104102782 A CN104102782 A CN 104102782A
- Authority
- CN
- China
- Prior art keywords
- control
- reactor temperature
- nuclear power
- reactor
- rbf
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Landscapes
- Feedback Control In General (AREA)
Abstract
The invention relates to a method for controlling temperatures of reactors of pressurized water reactor nuclear power stations by the aid of RBF (radial basis function) neural networks. The method is used for controlling the temperatures of the reactors of 900MW pressurized water reactor nuclear station units by the aid of the RBF neural networks, and includes testing characteristics of reactor temperature control systems on pressurized water reactor nuclear power unit simulation test platforms; fitting analytic and transfer functions of the systems according to data acquired from tests, solving the reactor temperature transfer functions and building high-precision mathematical models; designing traditional PID (proportion, integration and differentiation) controllers and controlling the temperatures of the reactors. The method has the advantages that the RBF neural networks are combined with the traditional PID controllers on the basis of the traditional PID controllers, so that the temperatures of the reactors can be compositely controlled, and obvious control effects can be realized as compared with control effects of the traditional PID control and fuzzy PID control; the method has high practical application value in the aspect of reactor temperature control, research and application of advanced intelligent control on nuclear power units can be promoted, and accordingly the control level on the units can be improved.
Description
Technical field
The present invention relates to a kind of, particularly a kind of pressurized-water reactor nuclear power plant reactor temperature RBF neural network control method.
Background technology
Since 21 century, along with the recovery of world economy and more and more serious energy crisis, nuclear energy is favored as the advantage of clean energy resource, has formed three large pillars of world's electric power energy together with thermoelectricity, water power.The heap type of nuclear reactor has multiple, as presurized water reactor, boiling-water reactor, heavy water reactor, fast neutron reactor etc.The unique advantages such as presurized water reactor relies on its compact conformation, technology maturation, capital cost is low, the construction period is short become so far most widely used nuclear reactor in the world.What the present invention studied is exactly the humidity control system of pressurized-water reactor nuclear power plant reactor, and the fundamental purpose of research is that as RBF neural network, PID controller, optimizes the control effect of reactor temperature with this with intelligent controller.It is one of most important control parameter of nuclear power station that the temperature of nuclear reactor is controlled, and core temperature has directly reflected reactivity and the power of reactor core.Temperature controlled quality is directly connected to the safety of nuclear island.Therefore, pressurized-water reactor nuclear power plant reactor humidity control system is studied and designed is very necessary, and has practical significance.
Reactor temperature control system is by regulating the rod position of temperature control rod R rod to carry out the control of realization response stack temperature.Medial temperature regulating system principle of work is moving direction and the speed (movement of R rod trends towards reducing integrated temperature deviation) of R rod controlled by the polarity of integrated temperature deviation e and size, move to always integrated temperature deviation is entered in dead zone range, thereby temperature equaled or be approximately equal to setting valve, reaching that reactor capability is mated with secondary circuit steam turbine power or the object of approximate match.
In recent years, along with the development of nuclear power station, the reactor temperature control system of pressurized-water reactor nuclear power plant has been carried out to a large amount of research both at home and abroad.
2000, Chen Yuzhong, Yang Kaijun, Shen Yongping has carried out the research that nuclear reactor fuzzy is controlled on nuclear reactor experimental simulation system, result of study shows: adopt fuzzy controller to control nuclear reactor system, when load changes, can comparatively fast suppress coolant temperature and change, stable state accuracy is high, can reach good control effect.
2003, Hussein Arab-Alibeik, Saeed Setayeshi uses based on LQG/LTR(Linear-Quadratic-Gauss or loop transmission and recovers) control presurized water reactor temperature control system is improved.
2009, Ji Huayan, leaf Jian Hua were inquired into the emulation technology of nuclear power generating sets average reactor temperature control system, had set forth the instrument that utilizes graphical modeling and the method for the medial temperature control system of nuclear power replicating machine being carried out to graphical modeling.
In June, 2011, to Model Predictive Control, the application in nuclear power station core temperature is controlled is studied Yu's Yun.By the research to Model Predictive Control Theory, for core temperature, control a difficult problem, design the model prediction constrained optimization control strategy based on state space, and carried out simulation study at different operating points.
In October, 2011, in generation and, Dai Xiang, Cao Xinrong analyze under high burnup presurized water reactor temperature coefficient, by changing initial enrichment, batch of material number, length of the cycle, designs a high burnup reactor core.With CASMO-4/SIMULATE-3, set up core model, and calculating is greater than the temperature coefficient under 60GWD/T burn-up level at average discharge burn-up.Result of study shows, in high burnup situation, no matter whether there is burnable poison, the neutron spectrum of sclerosis increases moderator temperature coefficient absolute value, and increase along with the increase of circulation burnup, especially the end of term in longevity absolute value exceeds general presurized water reactor limit value, and fuel temperature coefficient variation is not remarkable.
In May, 2013, Zhou Haixiang, Lin Ye, Wang Yunwei are by research, the mechanism that pressurized water type reactor temperature effect is produced to negative reactivity feedback is set forth, and based on Point reactor nutron kinetics model, under the simulated environment of Matlab/Simulink, set up the transient condition reactor core response realistic model with temperature feedback link.According to set up realistic model, consider the transient condition of reactor lifting power, the negative feedback impact of different reactor temperatures coefficient has been carried out to simulation analysis.The result of simulation analysis shows, when reactor need to change its output power, reactor core is introduced after the disturbance of step microresponse, due to the negative temperature coefficient effect of nuclear fuel and moderator, make reactor itself possess intrinsic stability, the variation of reactor core neutron population tends towards stability.According to simulation result, the temperature effect that reactor negative temperature coefficient produces has favorable influence to reactive control under nuclear power plant's transient condition.
In June, 2013, Gong Dichen be take PWR nuclear power plant as object, and the important control system of presurized water reactor is studied.Setting up on the basis of controlling realistic model, from the angle of real-time control, traditional control theory and Intelligent Control Theory are combined and control optimization, from the probabilistic angle of things development and change, the theory of utilizing random network and stochastic process to nuclear power plant open stack operation process, burst accident contingency procedure is carried out quantitative test and algorithm optimization, and utilize existing computer software and hardware condition, nuclear power plant's controlling run information management system platform has been proposed to detailed design scheme and ins and outs analysis.
In production process of nuclear power plant, reactor temperature adopts conventional PI to control conventionally.Nuclear reactor, due to its special safety issue and the remarkable nonlinear characteristic self having, adopts the routine control as PI to be difficult to accomplish not only to improve the rapidity of power variation but also can hold concurrently and overshoot, generally can only make between the two compromise.Improve the performance of reactor control system, need to introduce advanced control strategy.With fuzzy control strategy, setting up of fuzzy rule will rely on experience, is difficult to accomplish accurate control.The present invention attempts using RBF neural network, and training pid parameter, controls reactor temperature, has obtained reasonable control effect.
Summary of the invention
The present invention be directed in present production process of nuclear power plant, reactor temperature is controlled strict requirement, now control cannot adaptive system parameter wide variation problem, a kind of pressurized-water reactor nuclear power plant reactor temperature RBF neural network control method has been proposed, when reactor steady working condition is moved, parameter is among a small circle under situation of change, it is relatively good that conventional PI or PID control effect, but cannot adaptive system parameter wide variation, the present invention combines RBF neural network and traditional PID control, realize compound control, the effect of controlling is better than to be controlled with traditional PID and fuzzy control.
Technical scheme of the present invention is: a kind of pressurized-water reactor nuclear power plant reactor temperature RBF neural network control method, on compressed water reactor nuclear power unit simulation test platform, carries out the characteristic test of reactor temperature control system; According to the data of experiment gained, system is analyzed to the matching with transport function, try to achieve the transport function of reactor temperature, set up high-precision mathematical model; Design traditional PID controller, reactor temperature is controlled; On the basis of traditional PID controller, RBF neural network and traditional PID control are combined, realize compound control.
Described RBF neural network is combined and is realized compound control with traditional PID control, is the intelligent optimization under traditional PI D-algorithm, adjusts online the more pid parameter of high-quality, and concrete steps are as follows:
1) determine the structure of RBF network, learning rate, inertial coefficient, weighting coefficient are carried out to the setting of initial value;
2) sampling obtains input rin (k) and the output yout (k) of reactor temperature system, asks for error e rror (k)=rink (k)-yout (k);
3) calculate each layer of neuronic input of RBF neural network, output, the 3rd layer of output layer is output as three parameter kp, ki, the kd of PID controller;
4) kp, ki, tri-parameters of kd are brought PID controller into, calculate the output u (k) of PID controller, for controlling in real time and calculating, reactor temperature is controlled, produce the output y (k+1) of next step reactor temperature system, calculate error e rror (k+1)=rink (k+1)-yout (k+1) now;
5) adjust RBF weight coefficient, hidden node center vector sound stage width parameter;
6) return to step 2, until error meets accuracy requirement.
Beneficial effect of the present invention is: pressurized-water reactor nuclear power plant reactor temperature RBF neural network control method of the present invention, for 900 MW presurized water reactor units, study, reactor temperature is controlled and had very high actual application value, can promote advanced intelligent to be controlled at research and the application on nuclear power generating sets, thereby improve the level of control of unit.
Accompanying drawing explanation
Fig. 1 is the comparison diagram between experimental data curve of the present invention and matching transfer curve;
Fig. 2 is the step response curve comparison diagram that three groups of pid parameters of the present invention are controlled;
Fig. 3 is the structural drawing of RBF neural network of the present invention;
Fig. 4 is the process flow diagram that RBF neural network Composite PID of the present invention is controlled;
Fig. 5 is the response curve comparison diagram that fuzzy controller and PID controller are controlled;
Fig. 6 is the control effect contrast figure of RBF neural network Composite PID controller of the present invention and PID controller.
Embodiment
For 900 MW pressurized-water reactor nuclear power plant units, reactor temperature RBF neural network control method has been proposed, first, on compressed water reactor nuclear power unit simulation test platform, carry out the characteristic test of reactor temperature control system; According to the data of experiment gained, system is analyzed to the matching with transport function, try to achieve the transport function of reactor temperature, set up high-precision mathematical model; Design traditional PID controller, reactor temperature is controlled; On the basis of traditional PID controller, RBF neural network and traditional PID control combine, and realize compound control, and the effect of control and traditional PID control effect and compare, and compare with the control effect of fuzzy.Concrete steps are as follows:
1, first on the typical second generation three loop 900MW compressed water reactor nuclear power unit simulation test platforms, carry out the characteristic test of reactor temperature control system, obtain under the various disturbances of control rod the response curve of reactor temperature.At reactor temperature control rod R rod, added under-5% step signal the response curve of reactor temperature system.The data of our Simulation Experimental Platform, with in nuclear power station actual operating data error 1%, can think that the data of experiment gained are exactly the actual operating data of nuclear power station.
2,, according to the data of experiment gained, system is analyzed to the matching with transport function.Use the technology of System Discrimination reactor temperature to be carried out to the matching of transport function, set up high-precision mathematical model.The result of matching requires maximum error within 0.1%.Fitting result as shown in Figure 1.
Design the comparison and analysis that a program realizes error size between the experimental record data data corresponding with matching transport function, the curve of error log matching as shown in table 1 and the error analysis of actual curve, maximum Error Absolute Value is 0.00091 0.09%, and the precision of matching is very high.
Table 1
3, design traditional PID controller, and parameter is adjusted repeatedly, realization response stack temperature is controlled.In research process, 3 groups of pid parameters have been designed.Fig. 2 is the step response curve comparison diagram that three groups of pid parameters are controlled.First group of K=0.3, Ti=0.03, in the control parameter combinations of Td=100, reactor temperature has overshoot, and system response time is very fast; Second group of K=0.6, Ti=0.02, in the control parameter combinations of Td=70, reactor temperature had not both had overshoot, and response speed is also very fast, the 3rd K=1, Ti=0.008, in the control parameter combinations of Td=100, system non-overshoot, but response speed is slower.Choose second group and control parameter combinations as the pid control parameter of reactor.At this moment PID controller parameter is: K=0.3; Ti=0.03; Td=100, the adjustment time t under this controller control
s=270s, non-overshoot.Such controller meets the requirement of the technological process of production.
4, RBF neural network Composite PID control algolithm is the intelligent optimization under traditional PI D-algorithm, adjusts online the more pid parameter of high-quality, and controlled device is carried out to more effective control.Fig. 3 is the structural drawing of RBF neural network.
If Fig. 4 is the process flow diagram that RBF neural network Composite PID is controlled, this controller control algolithm can be summarized as:
1) determine the structure of RBF network, learning rate, inertial coefficient, weighting coefficient are carried out to the setting of initial value;
2) sampling obtains input rin (k) and the output yout (k) of reactor temperature system, asks for error e rror (k)=rink (k)-yout (k);
3) calculate each layer of neuronic input of RBF neural network, output, the 3rd layer of output layer is output as three parameter kp, ki, the kd of PID controller;
4) kp, ki, tri-parameters of kd are brought PID controller into, calculate the output u (k) of PID controller, for controlling in real time and calculating, reactor temperature is controlled, produce the output y (k+1) of next step reactor temperature system, calculate error e rror (k+1)=rink (k+1)-yout (k+1) now;
5) adjust RBF weight coefficient, hidden node center vector sound stage width parameter;
6) return to step 2, until error meets accuracy requirement.
Fig. 5 is the response curve comparison diagram that fuzzy controller and PID controller are controlled, now the adjustment time t of fuzzy controller
s=140s.
Fig. 6 is the control effect contrast figure of RBF neural network Composite PID controller and PID controller, and the adjustment time is
=75s.Visible, the adjustment time was compared with the adjustment time of conventional PID controllers, fuzzy controller, shortened dramatically.Therefore, reactor temperature RBF ANN (Artificial Neural Network) Control, scheme is practical.
Claims (2)
1. a pressurized-water reactor nuclear power plant reactor temperature RBF neural network control method, is characterized in that, on compressed water reactor nuclear power unit simulation test platform, carries out the characteristic test of reactor temperature control system; According to the data of experiment gained, system is analyzed to the matching with transport function, try to achieve the transport function of reactor temperature, set up high-precision mathematical model; Design traditional PID controller, reactor temperature is controlled; On the basis of traditional PID controller, RBF neural network and traditional PID control are combined, realize compound control.
2. pressurized-water reactor nuclear power plant reactor temperature RBF neural network control method according to claim 1, it is characterized in that, described RBF neural network is combined with traditional PID control and is realized compound control, it is the intelligent optimization under traditional PI D-algorithm, adjust online the more pid parameter of high-quality, concrete steps are as follows:
1) determine the structure of RBF network, learning rate, inertial coefficient, weighting coefficient are carried out to the setting of initial value;
2) sampling obtains input rin (k) and the output yout (k) of reactor temperature system, asks for error e rror (k)=rink (k)-yout (k);
3) calculate each layer of neuronic input of RBF neural network, output, the 3rd layer of output layer is output as three parameter kp, ki, the kd of PID controller;
4) kp, ki, tri-parameters of kd are brought PID controller into, calculate the output u (k) of PID controller, for controlling in real time and calculating, reactor temperature is controlled, produce the output y (k+1) of next step reactor temperature system, calculate error e rror (k+1)=rink (k+1)-yout (k+1) now;
5) adjust RBF weight coefficient, hidden node center vector sound stage width parameter;
6) return to step 2, until error meets accuracy requirement.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410344231.4A CN104102782B (en) | 2014-07-18 | 2014-07-18 | Method for controlling temperatures of reactors of pressurized water reactor nuclear power stations by aid of RBF (radial basis function) neural networks |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410344231.4A CN104102782B (en) | 2014-07-18 | 2014-07-18 | Method for controlling temperatures of reactors of pressurized water reactor nuclear power stations by aid of RBF (radial basis function) neural networks |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104102782A true CN104102782A (en) | 2014-10-15 |
| CN104102782B CN104102782B (en) | 2017-05-24 |
Family
ID=51670933
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410344231.4A Active CN104102782B (en) | 2014-07-18 | 2014-07-18 | Method for controlling temperatures of reactors of pressurized water reactor nuclear power stations by aid of RBF (radial basis function) neural networks |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104102782B (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106682735A (en) * | 2017-01-06 | 2017-05-17 | 杭州创族科技有限公司 | BP neural network algorithm based on PID adjustment |
| CN108427271A (en) * | 2018-05-21 | 2018-08-21 | 上海电力学院 | Pressurized-water reactor nuclear power plant primary Ioops coolant temperature control method |
| CN109461510A (en) * | 2018-10-23 | 2019-03-12 | 国网福建省电力有限公司 | The operating dead zone setting method of nuclear power unit primary frequency modulation control R stick |
| CN110032822A (en) * | 2019-04-22 | 2019-07-19 | 广西防城港核电有限公司 | Weary pond loses temperature and the analysis method of temperature rise rate calculating after the cooling of part |
| CN111456840A (en) * | 2020-05-18 | 2020-07-28 | 江苏隆信德科技有限公司 | Intelligent control method for cooling water flow of internal combustion engine based on RBF neural network |
| CN112307670A (en) * | 2020-09-29 | 2021-02-02 | 中国原子能科学研究院 | Design method of pressurized water reactor core parameter prediction model based on bagging integrated neural network |
| CN112886039A (en) * | 2021-01-11 | 2021-06-01 | 清华大学深圳国际研究生院 | Pressurized water reactor core automatic control method based on reinforcement learning |
| CN113076684A (en) * | 2021-02-23 | 2021-07-06 | 中国核动力研究设计院 | Intelligent calculation method for transient parameters in rod adjusting process of nuclear reactor core |
| CN113465778A (en) * | 2021-06-21 | 2021-10-01 | 中国原子能科学研究院 | Temperature acquisition method |
| CN113885310A (en) * | 2020-07-01 | 2022-01-04 | 东北大学 | Intelligent control system for vacuum dry pump test |
| CN113963826A (en) * | 2021-10-14 | 2022-01-21 | 西安交通大学 | Reactor abnormal condition diagnosis and control system |
| CN114462336A (en) * | 2022-04-11 | 2022-05-10 | 四川大学 | Method for calculating average temperature of coolant of main pipeline of nuclear reactor |
| CN116821588A (en) * | 2023-07-06 | 2023-09-29 | 四川大学 | Reactor working condition judging and predicting method based on DSMF fusion algorithm |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101763035A (en) * | 2009-11-13 | 2010-06-30 | 上海电力学院 | Method for controlling radial basis function (RBF) neural network tuned proportion integration differentiation (PID) and fuzzy immunization |
| CN101968629A (en) * | 2010-10-19 | 2011-02-09 | 天津理工大学 | PID (Proportional Integral Derivative) control method for elastic integral BP neural network based on RBF (Radial Basis Function) identification |
| US20130054500A1 (en) * | 2011-08-22 | 2013-02-28 | King Fahd University Of Petroleum And Minerals | Robust controller for nonlinear mimo systems |
-
2014
- 2014-07-18 CN CN201410344231.4A patent/CN104102782B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101763035A (en) * | 2009-11-13 | 2010-06-30 | 上海电力学院 | Method for controlling radial basis function (RBF) neural network tuned proportion integration differentiation (PID) and fuzzy immunization |
| CN101968629A (en) * | 2010-10-19 | 2011-02-09 | 天津理工大学 | PID (Proportional Integral Derivative) control method for elastic integral BP neural network based on RBF (Radial Basis Function) identification |
| US20130054500A1 (en) * | 2011-08-22 | 2013-02-28 | King Fahd University Of Petroleum And Minerals | Robust controller for nonlinear mimo systems |
Non-Patent Citations (2)
| Title |
|---|
| 刘悦婷: "基于RBF 神经网络的PID 控制在锅炉温度系统中的应用研究", 《宝鸡文理学院学报（自然科学版）》 * |
| 张国铎: "基于智能控制理论的压水堆稳压器控制系统的研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106682735B (en) * | 2017-01-06 | 2019-01-18 | 杭州创族科技有限公司 | The BP neural network algorithm adjusted based on PID |
| CN106682735A (en) * | 2017-01-06 | 2017-05-17 | 杭州创族科技有限公司 | BP neural network algorithm based on PID adjustment |
| CN108427271A (en) * | 2018-05-21 | 2018-08-21 | 上海电力学院 | Pressurized-water reactor nuclear power plant primary Ioops coolant temperature control method |
| CN109461510A (en) * | 2018-10-23 | 2019-03-12 | 国网福建省电力有限公司 | The operating dead zone setting method of nuclear power unit primary frequency modulation control R stick |
| CN110032822A (en) * | 2019-04-22 | 2019-07-19 | 广西防城港核电有限公司 | Weary pond loses temperature and the analysis method of temperature rise rate calculating after the cooling of part |
| CN110032822B (en) * | 2019-04-22 | 2023-09-01 | 广西防城港核电有限公司 | Analysis method for calculating temperature and temperature rise rate of spent pool after partial cooling loss |
| CN111456840A (en) * | 2020-05-18 | 2020-07-28 | 江苏隆信德科技有限公司 | Intelligent control method for cooling water flow of internal combustion engine based on RBF neural network |
| CN111456840B (en) * | 2020-05-18 | 2022-01-14 | 江苏隆信德科技有限公司 | Intelligent control method for cooling water flow of internal combustion engine based on RBF neural network |
| CN113885310A (en) * | 2020-07-01 | 2022-01-04 | 东北大学 | Intelligent control system for vacuum dry pump test |
| CN113885310B (en) * | 2020-07-01 | 2023-03-28 | 东北大学 | Intelligent control system for vacuum dry pump test |
| CN112307670A (en) * | 2020-09-29 | 2021-02-02 | 中国原子能科学研究院 | Design method of pressurized water reactor core parameter prediction model based on bagging integrated neural network |
| CN112886039B (en) * | 2021-01-11 | 2021-11-23 | 清华大学深圳国际研究生院 | Pressurized water reactor core automatic control method based on reinforcement learning |
| CN112886039A (en) * | 2021-01-11 | 2021-06-01 | 清华大学深圳国际研究生院 | Pressurized water reactor core automatic control method based on reinforcement learning |
| CN113076684B (en) * | 2021-02-23 | 2022-09-20 | 中国核动力研究设计院 | Intelligent calculation method for transient parameters in rod adjusting process of nuclear reactor core |
| CN113076684A (en) * | 2021-02-23 | 2021-07-06 | 中国核动力研究设计院 | Intelligent calculation method for transient parameters in rod adjusting process of nuclear reactor core |
| CN113465778A (en) * | 2021-06-21 | 2021-10-01 | 中国原子能科学研究院 | Temperature acquisition method |
| CN113465778B (en) * | 2021-06-21 | 2022-04-08 | 中国原子能科学研究院 | Temperature acquisition method |
| CN113963826A (en) * | 2021-10-14 | 2022-01-21 | 西安交通大学 | Reactor abnormal condition diagnosis and control system |
| CN113963826B (en) * | 2021-10-14 | 2024-01-12 | 西安交通大学 | Abnormal working condition diagnosis and control system for reactor |
| CN114462336A (en) * | 2022-04-11 | 2022-05-10 | 四川大学 | Method for calculating average temperature of coolant of main pipeline of nuclear reactor |
| CN116821588A (en) * | 2023-07-06 | 2023-09-29 | 四川大学 | Reactor working condition judging and predicting method based on DSMF fusion algorithm |
| CN116821588B (en) * | 2023-07-06 | 2024-05-03 | 四川大学 | Reactor working condition judging and predicting method based on DSMF fusion algorithm |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104102782B (en) | 2017-05-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104102782B (en) | Method for controlling temperatures of reactors of pressurized water reactor nuclear power stations by aid of RBF (radial basis function) neural networks | |
| Wu et al. | On transitioning from PID to ADRC in thermal power plants | |
| Guo et al. | Modeling and dynamic response control for primary frequency regulation of hydro-turbine governing system with surge tank | |
| CN113076684B (en) | Intelligent calculation method for transient parameters in rod adjusting process of nuclear reactor core | |
| CN107065556A (en) | A kind of automatic search method of reactor core unit Variable power optimization of operation strategy scheme | |
| Wang et al. | Dynamic simulation and study of Mechanical Shim (MSHIM) core control strategy for AP1000 reactor | |
| Hasan et al. | Real time simulation of automatic generation control for interconnected power system | |
| Zhang et al. | Research on pressurizer water level control of pressurized water reactor nuclear power station | |
| CN115146545A (en) | Intelligent analysis method and system for critical steady state parameters of nuclear reactor core | |
| Ma et al. | Disturbance observer-based Takagi-Sugeno fuzzy control of a delay fractional-order hydraulic turbine governing system with elastic water hammer via frequency distributed model | |
| Hui et al. | Adaptive second-order nonsingular terminal sliding mode power-level control for nuclear power plants | |
| Hui et al. | Load following control of a PWR with load-dependent parameters and perturbations via fixed-time fractional-order sliding mode and disturbance observer techniques | |
| CN106528978A (en) | Dynamic simulation method and system of speed regulating systems of advanced pressurized water reactor nuclear power unit | |
| Wang et al. | A feasibility study of load-follow operation without boron adjustment for CPR1000 | |
| CN104570769A (en) | Actual measurement modeling method of power system electromechanical transient model of nuclear power unit speed regulating system | |
| Lu et al. | Evaluation of an FPGA-based fuzzy logic control of feed-water for ABWR under automatic power regulating | |
| Cai et al. | A machine learning-based model predictive control method for pumped storage systems | |
| Cao et al. | Data-driven-based methodology to improve performance of reactor power regulation system in small pressurized water reactor | |
| Shayeghi et al. | An online Q-learning based multi-agent LFC for a multi-area multi-source power system including distributed energy resources | |
| CN113328474B (en) | New energy AGC substation test system, method, equipment and medium | |
| CN111262280A (en) | Modeling and analyzing method for primary frequency modulation of pressurized water reactor nuclear power unit | |
| Wang et al. | Application of an improved mechanical shim control strategy for AP1000 reactor | |
| Zhang et al. | Modeling and simulation study of hydraulic turbine governor based on SIMULINK | |
| CN111637435B (en) | Nuclear power system steam generator water level control method based on SARSA | |
| Kuang et al. | A review of control strategies for automatic generation control in power systems with renewable energy |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |