A neural network based operation guidance system for procedure presentation and operation validation in nuclear power plants

Abstract An operation guidance system (OGS) was developed to regulate and supervise operators’ actions during abnormal environments in nuclear power plants (NPPs). The system integrated a primitive computerized procedures system (CPS) and an operation validation system (OVS) imbedded in a virtual simulated operational environment. As the key component of the OGS, OVS provided two important functions for the operators: validated check of operations, and qualitative and quantitative effects analysis of operations. Each of operators’ action was evaluated by the system and possible results were simulated by using artificial neural networks (ANN). Finally, corresponding suggestion or warning was provided to operators. This should reduce human errors during operation in emergency scenarios.

[1]  Lefteri H. Tsoukalas,et al.  Soft computing technologies in nuclear engineering applications , 1999 .

[2]  Poong-Hyun Seong,et al.  An analytic model for situation assessment of nuclear power plant operators based on Bayesian inference , 2006, Reliab. Eng. Syst. Saf..

[3]  Erik Hollnagel,et al.  Integrated computerisation of operating procedures , 2002 .

[4]  J. W. Hines,et al.  Trends in computational intelligence in nuclear engineering , 2005 .

[5]  M. H. Lipner,et al.  Operational benefits of an advanced computerized procedures system , 1994, Proceedings of 1994 IEEE Nuclear Science Symposium - NSS'94.

[6]  Poong Hyun Seong,et al.  An Advanced Computerized Operator Support System for Nuclear Power Plants , 2005 .

[7]  Morten Lind,et al.  Modeling goals and functions of complex industrial plants , 1994, Appl. Artif. Intell..

[8]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[9]  Poong Hyun Seong,et al.  A dynamic neural network aggregation model for transient diagnosis in nuclear power plants , 2007 .

[10]  Erik Hollnagel,et al.  Guidelines for computerized presentation of emergency operating procedures , 1996 .

[11]  Eric B. Bartlett,et al.  Nuclear power plant fault diagnosis using neural networks with error estimation by series association , 1996 .

[12]  Daihwan Min,et al.  Observations on emergency operations using computerized procedure system , 2002, Proceedings of the IEEE 7th Conference on Human Factors and Power Plants.

[13]  Eric B. Bartlett,et al.  Error Prediction for a Nuclear Power Plant Fault-Diagnostic Advisor Using Neural Networks , 1994 .

[14]  Wei Qin,et al.  Development of a testing methodology for computerized procedure system based on junit framework and MFM = Junit 체제와 MFM 기반의 전산화절차서에 대한 테스팅 방법론 개발 , 2004 .

[15]  B. C. Hwang.  Intelligent control for a nuclear power plant using artificial neural networks , 1994, Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94).

[16]  Sheue-Ling Hwang,et al.  Design and evaluation of computerized operating procedures in nuclear power plants , 2003, Ergonomics.

[17]  Mark J. Embrechts,et al.  Hybrid identification of nuclear power plant transients with artificial neural networks , 2004, IEEE Transactions on Industrial Electronics.

[18]  B. S. Sim,et al.  Human factors researches in KAERI for nuclear power plants , 1997, Proceedings of the 1997 IEEE Sixth Conference on Human Factors and Power Plants, 1997. 'Global Perspectives of Human Factors in Power Generation'.

[19]  Yeonsub Jung,et al.  An incremental objective achievement model in computerized procedure execution , 2000, Reliab. Eng. Syst. Saf..

[20]  Martin A. Riedmiller,et al.  A direct adaptive method for faster backpropagation learning: the RPROP algorithm , 1993, IEEE International Conference on Neural Networks.

[21]  Roberto Schirru,et al.  A neural model for transient identification in dynamic processes with “don't know” response , 2003 .

[22]  Jang-Yeol Kim,et al.  Development of the test simulator for advanced instrumentation and control research , 1997, Proceedings of the 1997 IEEE Sixth Conference on Human Factors and Power Plants, 1997. 'Global Perspectives of Human Factors in Power Generation'.

[23]  Jaques Reifman,et al.  Survey of Artificial Intelligence Methods for Detection and Identification of Component Faults in Nuclear Power Plants , 1997 .

[24]  Lee M. Hively,et al.  Emerging Technologies in Instrumentation and Controls , 2003 .

[25]  P. F. Fantoni,et al.  A pattern recognition-artificial neural networks based model for signal validation in nuclear power plants , 1996 .