A neural-network-based adaptive state-observer for pressurized water reactors

Pressurized water reactor (PWR) is now the most widely utilized nuclear reactor, and its safe, stable and efficient operation is meaningful to the current rebirth of nuclear fission energy industry. Power-level control is a crucial technique which can deeply affect the operation stability and efficiency of PWRs. Comparing with the classical power-level control, the advanced power-level control may strengthen both the closed-loop stability and control performance by feeding back internal state-variables. However, not all of the internal state variables of a PWR can be measured directly. To implement advanced power-level control laws, it is necessary to develop a state-observer to reconstruct the unmeasurable state-variables. Since a PWR is naturally a complex nonlinear system with its parameters varying with the powerlevel, fuel burnup, Xenon isotope production, control rod worth and etc, it is meaningful to design a nonlinear observer for the PWR with adaptability to system uncertainties. Due to this and the strong learning capability of the multilayer artificial neural network (MNN), an MNN-based nonlinear adaptive observer is given for PWRs. Based on Lyapunov stability theory, it is proved theoretically that this newly-built observer can provide bounded and convergent state-observation. This observer is then applied to the state-observation of a special PWR, i.e. the nuclear heating reactor (NHR), and numerical simulation results not only verify its feasibility but also show the relationship between the performance and parameter values of this newly-built observer.

[1]  Zhe Dong.  Nonlinear Adaptive Power-Level Control for Modular High Temperature Gas-Cooled Reactors , 2013, IEEE Transactions on Nuclear Science.

[2]  Andrés Etchepareborda,et al.  Research reactor power controller design using an output feedback nonlinear receding horizon control method , 2007 .

[3]  Wang Dazhong.  The design characteristics and construction experiences of the 5 MWt Nuclear Heating Reactor , 1993 .

[4]  Wang Dazhong,et al.  Chinese nuclear heating test reactor and demonstration plant , 1992 .

[5]  Yuri B. Shtessel,et al.  Sliding mode control of the space nuclear reactor system , 1998 .

[6]  Heidar Ali Talebi,et al.  A stable neural network-based observer with application to flexible-joint manipulators , 2006, IEEE Transactions on Neural Networks.

[7]  Zhe Dong,et al.  Power-Level Control of Nuclear Reactors Based on Feedback Dissipation and Backstepping , 2010, IEEE Transactions on Nuclear Science.

[8]  Hossein Arabalibeik,et al.  Improved temperature control of a PWR nuclear reactor using an LQG/LTR based controller , 2003 .

[9]  Dong Zhe.  Nonlinear adaptive power-level control for the modular high temperature gas-cooled reactors , 2013, Proceedings of the 32nd Chinese Control Conference.

[10]  Ken-ichi Funahashi,et al.  On the approximate realization of continuous mappings by neural networks , 1989, Neural Networks.

[11]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1989, Math. Control. Signals Syst..

[12]  Kwang Y. Lee,et al.  State Feedback Assisted Classical Control: An Incremental Approach to Control Modernization of Existing and Future Nuclear Reactors and Power Plants , 1990 .

[13]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[14]  Zhe Dong,et al.  Dynamic model for control system design and simulation of a low temperature nuclear reactor , 2009 .

[15]  Kwang Y. Lee,et al.  LQG/LTR robust control of nuclear reactors with improved temperature performance , 1992 .

[16]  J.H. Perez-Cruz,et al.  Estimation of the Precursor Power and Internal Reactivity in a Nuclear Reactor by a Neural Observer , 2007, 2007 4th International Conference on Electrical and Electronics Engineering.

[17]  Zhe Dong,et al.  Dissipation-Based High Gain Filter for Monitoring Nuclear Reactors , 2010, IEEE Transactions on Nuclear Science.