對於國內面臨電力資源有限且開發困難的情況下，掌握並維持最佳之電廠熱效率，以增進電廠運轉效能，是近年來在電力自由化的潮流趨勢下，先進國家積極努力的目標。本研究提出以適應性類神經模糊推論系統建立電廠汽機環路模式，蒐集電廠過去三個運轉週期的歷史運轉數據，以線性迴歸模式篩選異常運轉數據，經由數據的前處理程序，增加數據的可分析性。再以汽機環路重要的運轉參數，建立智慧型汽機環路模式，其預測機組之輸出功率比傳統建模方法精確，也省去傳統建模繁雜過程及建模所需時間。經由沸水式及壓水式核能電廠實際運轉數據的驗證，已證明本研究所提方法的有效性與實用性。此外，也將執行汽機性能試驗之數據，輸入至以適應性類神經模糊推論系統為基礎的汽機環路模式，以分析汽輪發電機之輸出功率，計算結果再次驗證了汽機環路模式的正確性與有效性。因此本研究所提的方法，可以有效地做為監測電廠發電量之工具，供電廠工程師實際用來執行機組在正常運轉狀況下，汽輪發電機應有的輸出功率，以掌握電廠運轉性能之變化，提昇電廠的營運績效。

Due to facing the limited power resources and the difficulty to develop new electricity utilities, to maintain the power plant optimal thermal efficiency for improving plant operation performance is the goal for advanced countries under the trend of electricity utility deregulation in recent years. In this research, an adaptive neuro-fuzzy inference system (ANFIS) was adopted to develop the turbine cycle model to predict the turbine-generator output. Operating data above the 95% load level from the plant's past three fuel cycles were collected and validated to serve as a baseline performance data set. The plant operating data was verified using a linear regression model with a corresponding 95% confidence interval. The key variables that strongly affect the turbine-generator output are selected as the input variables of the ANFIS model, which is then used to predict the turbine-generator output above the 95% load level under normal operating conditions. A comparison of measured data with estimated results shows that the ANFIS based turbine cycle model is reliable and effective. The results also show that this turbine cycle model can be used to accurately predict turbine-generator output. In addition, by comparing turbine-generator output from the ANFIS based turbine cycle model with that from a commercial simulation tool, the effectiveness and accuracy of ANFIS based turbine cycle model is validated. The proposed ANFIS based turbine cycle model can be used to predict the turbine-generator output for NPPs in practice. The achievement of this study also provides an alternative approach to evaluate the thermal performance for nuclear power plants.

[1]Electric Power Research Institute (EPRI), “Megawatt Improvement Casebook and Guideline,” EPRI TR-101867, Project No. 2407-05, Final Report, 1992.
[2]Electric Power Research Institute (EPRI), “Main Turbine Performance Upgrade Guideline,” EPRI TR-106230, Project No. 3186-46, Final Report, 1997.
[3]PEPSE® User Input Description, Scientech Inc., 2001.
[4]G. L. Minner, W. C. Kettenacker, D. R. Fleming, and G. C. Rice, “PEPSE® User Input Description,” Scientech Inc., Idaho Falls, Idaho, 2001.
[5]Scientech Inc., 2002, PEPSE®: Engineering Model Description, USA.
[6]G. Heo, S. H. Chang, and S. S. Choi, “Development of a Need-Oriented Steam Turbine Cycle Simulation Toolbox,” IEEE Transactions on Energy Conversion, Vol. 20, No. 4, pp. 859-869, 2005.
[7]S. Kim and K. Choi, “PERUPS (PERformance UPgrade System) for On-Line Performance Analysis of a Nuclear Power Plant Turbine Cycle,” Nuclear Engineering and Technology, Vol. 37, No. 2, pp. 167-176, 2005.
[8]C. J. Chang, Y. K. Chan, C. H. Tsai, and D. W. Lee, “Development of a Thermal Efficiency Monitoring System for Kuosheng Nuclear Power Plant,” 6th International Conference on Nuclear Thermal-Hydraulics, Operations and Safety, Nara, Japan, 2004.
[9]Y. Nakao, E. Koda, and T. Takahashi, “Development of General-Purpose Software to Analyze the Statistic Thermal Characteristic of Nuclear Power Plant,” Journal of Power and Energy Systems, Vol. 3, No. 1, pp. 2-11, 2009.
[10]E. D. Ubeyli, “Automatic Detection of Electroencephalographic Changes Using Adaptive Neuro-Fuzzy Inference System Employing Lyapunov Exponents,” Expert Systems with Applications, Vol. 36, pp. 9031-9038, 2009.
[11]G. Yildirim and M. Ozger, “Neuro-Fuzzy Approach in Estimating Hazen-Williams Friction Coefficient for Small-Diameter Polyethylene pipes,” Advances in Engineering Software, Vol. 40, pp. 593-599, 2009.
[12]A. Hasiloglu, M. Yilmaz, O. Comakli, and I. Ekmekci, “Adaptive Neuro-Fuzzy Modeling of Transient Heat Transfer in Circular Duct Air Flow,” International Journal of Thermal Sciences, Vol. 43, pp. 1075-1090, 2004.
[13]M. A. Awadallah, M. M. Morcos, S. Gopalakrishnan, and T. W. Nehl, “A Neuro-Fuzzy Approach to Automatic Diagnosis and Location of Stator Inter-Turn Faults in CSI-fed PM Brushless DC Motors,” IEEE Transactions on Energy Conversion, Vol. 20, No. 2, pp. 253-259, 2005.
[14]S. V. Ustun and M. Demirtas, “Modeling and control of V/f controlled induction motor,” Energy Conversion and Management, Vol. 50, pp. 786-791, 2009.
[15]A. Mellit and S. A. Kalogirou, “ANFIS-Based Modelling for Photovoltaic Power Supply System: A Case Study,” Renewable Energy, Vol. 36, pp. 250-258, 2011.
[16]A. C. F. Guimaraes and C. M. F. Lapa, “Fuzzy Inference System for Evaluating and Improving Nuclear Power Plant Operating Performance,” Annals of Nuclear Energy, Vol. 31, No. 31, pp. 311-322, 2004.
[17]K. Kim and E. B. Bartlett, “Nuclear Power Plant Fault Diagnosis Using Neural Networks with Error Estimation by Series Association,” IEEE Transactions on Nuclear Science, Vol. 43, No. 4, pp. 2373-2388, August 1996.
[18]S. R. Munasinghe, M. S. Kim, and J. J. Lee, “Adaptive Neurofuzzy Controller to Regulate UTSG Water Level in Nuclear Power Plants,” IEEE Transactions on Nuclear Science, Vol. 52, No. 1, pp. 421-429, February, 2005.
[19]C. M. Bartolini, F. Caresana, G. Comodi, L. Pelagalli, M. Renzi, and S. Vagni, “Application of Artificial Neural Networks to Micro Gas Turbines,” Energy Conversion and Management, Vol. 52, pp. 781-788, 2011.
[20]S. Jassar, Z. Liao, and L. Zhao, “Adaptive Neuro-Fuzzy Based Inferential Sensor Model for Estimating the Average Air Temperature in Space Heating Systems,” Building and Environment, Vol. 44, pp. 1609-1616, 2009.
[21]ASME PTC 6-Performance Test Code on Steam Turbines (2004).
[22]http://www.taipower.com.tw，台灣電力公司網站資料，民國100年。
[23]楊昭義、歐陽敏盛，核能發電工程學，水牛圖書出版事業有限公司，台北，民國九十八年。
[24]台灣電力公司第三核能發電廠資料，民國100年。
[25]F. F. Tsai, “Kuosheng NPP Unit 1 LP Turbine Rotors Retrofit,” AESIEAP 18th Conference of the Electric Power Supply Industry, Taipei, Taiwan, Oct. 24-28, 2010.
[26]荊軍安、苑穎瑞、張欽章、高良書、陳新儒、范湧、張梓喬、黃啟誠、張學植、黃平輝、朱偉朋和施勝利，「核三廠小幅度功率提昇運轉」，台電工程月刊，第754期，3月號，第16-34頁，民國一百年。
[27]J. S. R. Jang, “ANFIS: Adaptive Network Based Fuzzy Inference System,” IEEE Transactions on Systems, Man, and Cybernetics, Vol. 23, No. 3, pp. 665-685, 1993.
[28]J. S. R. Jang, C. T. Sun, and E. Mizutani, Neuro-Fuzzy and Soft Computing: A Computational Approach to Learning and Machine Intelligence, Prentice-Hall, New Jersey, 1997.
[29]T. Takagi and M. Sugeno, “Fuzzy identification of systems and its applications to modeling and control,” IEEE Transactions on Systems, Man, and Cybernetics, Vol. 15, pp. 116-132, 1985.
[30]T. Dalstein, T. Friedrich, B. Kulicke, and D. Sobajic, “Multi Neural Network Based to Fault Area Estimation for High Speed Protective Relays,” IEEE Transactions on Power Delivery, Vol. 11, No. 2, pp. 740-747, April 1996.
[31]N. Amjady and F. Keynia, “A New Neural Network Approach to Short Term Load Forecasting of Electrical Power Systems,” Energies, pp. 488-503, 2011.
[32]C. A. Protopapas, K. P. Psaltiras, and A. V. Machias, “An Expert System for Substation Fault Diagnosis and Alarm Processing,” IEEE Transactions on Power Delivery, Vol. 6, No. 2, pp. 648-655, April 1991.
[33]Z. A. Vale and A. M. Moura, “An Expert System with Temporal Reasoning for Alarm Processing in Power System Control Center,” IEEE Transactions on Power Systems, Vol. 8, No. 3, pp. 1307-1314, August 1993.
[34]H. J. Lee, B. S. Ahn, and Y. M. Park, “A Fault Diagnosis Expert System for Distribution Substations,” IEEE Transactions on Power Systems, Vol. 15, No. 1, pp. 92-974, January 2000.
[35]W. H. Chen, C. W. Liu, and Men-Shen Tsai, “On-Line Fault Diagnosis of Distribution Substations Using Hybrid Cause-Effect Network and Fuzzy Rule-Based Method,” IEEE Transaction on Power Delivery, Vol. 15, No. 2, pp. 710-717, April 2000.
[36]D. E. Rumelhart, G. E. Hinton, and R. J. Williams, “Learning Representations by Back-Propagation Errors,” Nature, Vol. 323, pp. 533-536, 1986.
[37]D. Marquardt, “An Algorithm for Least Square Estimation of Non-Linear Parameters,” Journal of the Society for Industrial and Applied Mathematics, pp. 431-441, 1963.
[38]A. M. C. Chan and A. K. Ahluwalia, “Feedwater Flow Measurement in U.S. Nuclear Power Generation Station,” Electric Power Research Institute (EPRI) Task Report 101388, 1992.
[39]C. J. Chang, L. Kao, T. Wang, C. P. Lin, L. C. Hong, and S. R. Chen, “Measurement Uncertainty Recapture Power Uprates in Taiwan,” 8th International Conference on Nuclear Thermal-Hydraulics, Operations and Safety, Shanghai, China, 2010.
[40]Taiwan Power Company, Final Safety Analysis Report, Kuosheng Nuclear Power Station Units 1 & 2, Amendment No. 18, 2010.
[41]C. J. Chang, T. Wang, and C. P. Lin, “Measurement Uncertainty Recapture (MUR) Power Uprates Operation at Kuosheng Nuclear Power Station”, International Congress on Advences in Nuclear Power Plants, Tokyo, Japan, 2009.
[42]ASME PTC 6A-Test Code for Steam Turbines-Appendix A to PTC 6, 2001.
[43]ASME PTC 6S-Procedures for Routine Performance Test of Steam Turbines, 1998.
[44]ASME PTC 6.1-Interim Test Code for an Alternative Procedure for Testing Steam Turbines, 1984.
[45]ASME PTC 6 Report-Guidance for Evaluation of Measurement Uncertainty in Performance Tests of Steam Turbines, 1985.
[46]Bornstein, B., and Cotton, K. C., “A Simplified ASME Acceptance Test Procedure for Steam Turbines,” Journal of Engineering for Power, Vol. 104, pp. 224-230, 1982.
[47]M. Smachlo and G. Keselowsky, “Plant Design and Planning for the Alternate ASME Turbine Acceptance Test,” ASME Paper No.：84-JPGC-PTC-3, 1984.
[48]J. Davids, N. R. Deming and G. J. Silvestri, “Effectiveness vs. Efficiency as a Measure of Low Pressure Steam Turbine Performance,” ASME Paper No.：84-JPGC-PTC-4, 1984.
[49]K. C. Cotton and H. S. Shafer, “Demonstration of an Alternative ASME Steam Turbine Generator Acceptance Test,” EPRI CS-4410, Final Report, 1986.
[50]J. L. Klucar, “Preparations for an ASME PTC 6 Alternative Test for Limerick Units 1 & 2 Turbine Replacement,” EPRI Nuclear Plant Performance Improvement Seminar, San Antonio, Texas, Aug. 11-12 , 1997.
[51]R. D Brown, F. Y. Simma, and R. J. Chetwynd, “Efficiency Improvement Features of Recent ABB-ALSTOM HP-LP Turbine Retrofit at Southern California Edisons San Onofre Nuclear Generating Station,” Proceedings 2000 International Joint Power Generation Conference, Miami, Florida, July 23~26, 2000.
[52]STD0015007 Revision C, “Performance Test Procedure for Maanshan HP Turbine Module Retrofit,” ALSTOM Power, 2011.
[53]STX0010545 Revision B, “Maanshan Test Equipment Installation Procedure,” ALSTOM Power, 2011.