肇始事件的辨識，對核電廠嚴重事故的排除非常重要。為提升事故辨識系統的效能，本研究提出一個由感測器種類區塊投影法(sensor type-wise block projection, stBP)及可縮減循序向前選擇法(deflatable sequential forward selection, dSFS)所組成的二階段訊號特徵萃取演算法，來擷取多重感測器所量測數據裡對事件辨識有助益的資訊。藉由stBP，我們可在不破壞電廠多通道訊號間關聯性的情況下，將某一特定種類感測器的訊號特徵值萃取出。接著再利用感測器偵選法則，挑選出合適的感測器組合，用以縮減用來進行辨識工作所需的特徵值數量。由於在搜尋最佳感測器組合的問題上，使用全面搜尋法(exhaustive search)並不是一個合適的策略，故仍需要一適宜的替代方法來解決組合最佳化搜尋的問題。本研究所提出的可縮減循序向前選擇法，建構在循序向前選擇法的基礎上，可針對預先選擇出的感應器組合，做進一步的迭代調整更新，以獲致更佳的感測器組合。為了驗證此二階段訊號特徵萃取演算法的效能，我們採用了台灣馬鞍山核能電廠模擬分析軟體(PCTRAN-PWR)來進行多種肇始事件，例如：冷卻水流失事件(loss of coolant accident, LOCA)、蒸汽產生器管路破裂事件(steam generator tube rupture, SGTR)等12類肇始事件的模擬。由最後的實驗結果顯示，此二階段訊號特徵萃取演算法(stBP + dSFS)較現存的方法在肇始事件的辨識上有更佳的功效，透過留一交叉驗證法(leave-one-out cross validation)的驗證試驗，最後事件成功辨識率可達95.36%。

Initiating event identification is essential in managing nuclear power plant (NPP) severe accidents. To facilitate the identification, a two-stage feature extraction scheme that incorporates the proposed sensor type-wise block projection (stBP) and deflatable sequential forward selection (dSFS) is utilized to elicit the discriminant information in the data from various NPP sensors. Based on the idea of stBP, the primal features can be extracted without breaking the intrinsic spatial structure among the multi-channel data of specific sensor types. The extracted features are then subject to further dimensionality reduction by selecting the sensors that are most relevant to the events under consideration. Exhaustive search is not feasible in this selection, and a combinatorial optimization technique is required to find suitable solutions. Unlike the original sequential forward selection, dSFS includes a sensor deflation scheme allowing sensors in the preselected set to be recursively refined. Results from detailed experiments with data generated from a simulator of Taiwan Maanshan NPP illustrate the efficacy of the proposed scheme, achieved a recognition rate of 95.36 % that is higher than those obtained using the features from the existing methods.

摘要 i
Abstract ii
致謝 iii
Contents iv
Figure Captions v
Table Captions vi
List of Symbols vii
List of Acronyms ix
Chapter 1 Introduction 1
Chapter 2 Feature Extraction Methods 4
2.1 Time integration 4
2.2 Discrete wavelet transform 4
2.3 Sensor type-wise block projection (stBP) feature extraction 5
2.3.1 Multiple sensors of the same type 5
2.3.2 Sensor type with a single sensor 7
Chapter 3 Sensor Selection Methods 9
3.1 Genetic Algorithm (GA) 9
3.2 Deflatable Sequential Forward Selection (dSFS) 10
Chapter 4 Experiments and Discussions 13
4.1 Data Generation 13
4.2 Parameter Setting 19
4.3 Results and Discussions 19
Chapter 5 Conclusions and Future Works 24
Reference 25

[1] C. CNSC, "Fukushima task force report," ed: INFO-0824, Ottawa, Canada, 2011.
[2] K.-C. Kwon and J.-H. Kim, "Accident identification in nuclear power plants using hidden Markov models," Engineering Applications of Artificial Intelligence, vol. 12, pp. 491-501, 1999.
[3] M. G. Na, S. H. Shin, S. M. Lee, D. W. Jung, S. P. Kim, J. H. Jeong, et al., "Prediction of major transient scenarios for severe accidents of nuclear power plants," IEEE transactions on nuclear science, vol. 51, pp. 313-321, 2004.
[4] Y.-G. No, J.-H. Kim, M.-G. Na, D.-H. Lim, and K.-I. Ahn, "Monitoring severe accidents using AI techniques," Nuclear Engineering and Technology, vol. 44, pp. 393-404, 2012.
[5] K. Moshkbar-Bakhshayesh and M. B. Ghofrani, "Transient identification in nuclear power plants: A review," Progress in Nuclear Energy, vol. 67, pp. 23-32, 2013.
[6] J. Ma and J. Jiang, "Applications of fault detection and diagnosis methods in nuclear power plants: A review," Progress in nuclear energy, vol. 53, pp. 255-266, 2011.
[7] T.-Y. Hsiao, C. Lin, and Y. Yuann, "Identification of initiating events for pressurized water reactor accidents," Annals of Nuclear Energy, vol. 37, pp. 1502-1512, 2010.
[8] J. Galbally and D. Galbally, "A pattern recognition approach based on DTW for automatic transient identification in nuclear power plants," Annals of Nuclear Energy, vol. 81, pp. 287-300, 2015.
[9] E. Zio and P. Baraldi, "Identification of nuclear transients via optimized fuzzy clustering," Annals of Nuclear Energy, vol. 32, pp. 1068-1080, 2005.
[10] C. Gottlieb, V. Arzhanov, W. Gudowski, and N. Garis, "Feasibility study on transient identification in nuclear power plants using support vector machines," Nuclear technology, vol. 155, pp. 67-77, 2006.
[11] T. Santosh, G. Vinod, R. Saraf, A. Ghosh, and H. Kushwaha, "Application of artificial neural networks to nuclear power plant transient diagnosis," Reliability Engineering & System Safety, vol. 92, pp. 1468-1472, 2007.
[12] M. J. Embrechts and S. Benedek, "Hybrid identification of nuclear power plant transients with artificial neural networks," IEEE Transactions on Industrial Electronics, vol. 51, pp. 686-693, 2004.
[13] M. Marseguerra and A. Zoia, "The AutoAssociative Neural Network in signal analysis: II. Application to on-line monitoring of a simulated BWR component," Annals of Nuclear Energy, vol. 32, pp. 1207-1223, 2005.
[14] K. Mo, S. J. Lee, and P. H. Seong, "A dynamic neural network aggregation model for transient diagnosis in nuclear power plants," Progress in Nuclear Energy, vol. 49, pp. 262-272, 2007.
[15] D. Roverso, "Soft computing tools for transient classification," Information Sciences, vol. 127, pp. 137-156, 2000.
[16] D. Roverso, "Plant diagnostics by transient classification: The aladdin approach," International Journal of Intelligent Systems, vol. 17, pp. 767-790, 2002.
[17] D. Roverso, "Fault diagnosis with the aladdin transient classifier," in AeroSense 2003, pp. 162-172, 2003.
[18] D. Roverso, "Dynamic empirical modelling techniques for equipment and process diagnostics in nuclear power plants," Int. J. Nucl. Knowl. Manag, vol. 2, pp. 239-248, 2005.
[19] K.-C. Kwon, "HMM-based transient identification in dynamic process," Trans Control Automat Syst Eng, vol. 2, pp. 40-46, 2000.
[20] E. Zio, P. Baraldi, and D. Roverso, "An extended classifiability index for feature selection in nuclear transients," Annals of Nuclear Energy, vol. 32, pp. 1632-1649, 2005.
[21] M. G. Na, W. S. Park, and D. H. Lim, "Detection and diagnostics of loss of coolant accidents using support vector machines," IEEE Transactions on Nuclear Science, vol. 55, pp. 628-636, 2008.
[22] J. A. C. C. Medeiros and R. Schirru, "Identification of nuclear power plant transients using the Particle Swarm Optimization algorithm," Annals of Nuclear Energy, vol. 35, pp. 576-582, 2008.
[23] A. dos Santos Nicolau, R. Schirru, and A. A. de Moura Meneses, "Quantum evolutionary algorithm applied to transient identification of a nuclear power plant," Progress in Nuclear Energy, vol. 53, pp. 86-91, 2011.
[24] C. Lin and H.-J. Chang, "Identification of pressurized water reactor transient using template matching," Annals of Nuclear Energy, vol. 38, pp. 1662-1666, 2011.
[25] S. Benedek and M. Embrechts, "Rapid identification of nuclear power plant malfunctions with artificial neural networks via Fourier transformed signals," Proc. ANNNIE, vol. 96, 1996.
[26] E. K. Chong and S. H. Zak, An introduction to optimization vol. 76: John Wiley & Sons, 2013.
[27] A. W. Whitney, "A direct method of nonparametric measurement selection," IEEE Transactions on Computers, vol. 100, pp. 1100-1103, 1971.
[28] I. A. Gheyas and L. S. Smith, "Feature subset selection in large dimensionality domains," Pattern recognition, vol. 43, pp. 5-13, 2010.
[29] C. S. Burrus, R. A. Gopinath, and H. Guo, Introduction to wavelets and wavelet transforms: a primer. Englewood Cliffs, NJ, USA: Prentice-Hall, 1998.
[30] D. L. Hall and J. Llinas, "An introduction to multisensor data fusion," Proceedings of the IEEE, vol. 85, pp. 6-23, 1997.
[31] J. Yang, D. Zhang, A. F. Frangi, and J.-y. Yang, "Two-dimensional PCA: a new approach to appearance-based face representation and recognition," IEEE transactions on pattern analysis and machine intelligence, vol. 26, pp. 131-137, 2004.
[32] T. Korenius, J. Laurikkala, and M. Juhola, "On principal component analysis, cosine and Euclidean measures in information retrieval," Information Sciences, vol. 177, pp. 4893-4905, 2007.
[33] J. C. Melo, G. Cavalcanti, and K. Guimaraes, "PCA feature extraction for protein structure prediction," in Neural Networks, 2003. Proceedings of the International Joint Conference on, 2003, pp. 2952-2957.
[34] P. Baraldi, N. Pedroni, and E. Zio, "Application of a niched Pareto genetic algorithm for selecting features for nuclear transients classification," International Journal of Intelligent Systems, vol. 24, pp. 118-151, 2009.
[35] U. N. R. Commission, "Assessment of the TRACE Code Using Transient Data from Maanshan PWR Nuclear Power Plant," Report NUREG/IA-0241, Washington, DC2010.
[36] Y.-H. Cheng, C. Shih, S.-C. Chiang, and T.-L. Weng, "Introducing PCTRAN as an evaluation tool for nuclear power plant emergency responses," Annals of Nuclear Energy, vol. 40, pp. 122-129, 2012.
[37] R. O. Duda, P. E. Hart, and D. G. Stork, Pattern classification: John Wiley & Sons, 2012.
[38] M. Mohri, A. Rostamizadeh, and A. Talwalkar, Foundations of machine learning: MIT press, 2012.