本文開發一套系統識別與控制之類神經網路軟體─NeuralLink。NeuralLink包含有8種學習法則：倒傳遞學習法、含慣性項及適應性速率之倒傳遞學習法、牛頓學習法、共軛梯度學習法、快馬特學習法、擬牛頓(BFGS)學習法、擬牛頓(DFP)學習法、和基因演算學習法。本文提出(1)擬牛頓(BFGS)學習法，(2)擬牛頓(DFP)學習法，和(3)基因演算學習法。其中擬牛頓(BFGS)學習法與擬牛頓(DFP)學習法首次整合適應性速率以加速類神經網路學習，而所提出之基因演算學習法更整合了多種複製及交配方法以應用於各式系統，所有學習法則均成功用於系統識別及控制之模擬與實驗上。本文另提出整合擬牛頓(BFGS)學習法與基因演算學習法之兩步驟學習法，以提供較佳初始連接權重及閥值，因此當學習時需要使用不同的初始權值，或需要多次學習，建議使用兩步驟學習法。
　　除了上述之NeuralLink與其學習方法外，本文並提出類神經感測器，以一片壓電感測器透過類神經網路之學習，可估測出系統速度與位移訊號，以大量減少感測器成本。本文應用類神經感測器於智慧結構及建築結構的系統識別與減振控制實驗。在NeuralLink中，不管是類神經網路控制實驗，或是模糊控制的實驗，均可選擇使用類神經感測器代替多個實際的感測器。
　　NeuralLink可以有效應用於(1)系統識別，(2)類神經網路控制器設計，(3)模糊控制器設計，和(4)圖樣辨識等。在系統識別應用中，以類神經感測器估測出系統速度與位移訊號，並將類神經感測器用於智慧結構及建築結構之系統識別實驗中。在圖樣辨識方面，本文將類神經網路應用於車牌辨識中，以發展之列總合法(column-sum algorithm)找出車牌位置，並以類神經網路識別出車牌號碼，此方法在車牌位置尋找的成功率為97.2%，在車牌號碼的辨識率為94.3%。在控制應用方面，NeuralLink可應用於設計類神經網路控制器及模糊控制器，並利用I/O卡將控制器直接實現於工程應用中，這是第一個有如此功能的類神經網路軟體。在智慧結構及建築結構之減振控制實驗裡，以類神經感測器估測速度與位移訊號，整合NeuralLink所設計之類神經網路控制器及模糊控制器分別進行減振實驗，實驗結果可驗證NeuralLink確實可以應用於工程問題。

　　A software NeuralLink is developed as a design synthesis tool for system identification and control. NeuralLink contains eight training algorithms: the backpropagation algorithm, the backpropagation algorithm with momentum term and adaptive learning rate, the Gauss-Newton algorithm, the conjugate gradient algorithm, the Levenberg-Marquardt algorithm, the Quasi-Newton (DFP) algorithm, the Quasi-Newton (BFGS) algorithm and the genetic algorithm. Among these, the Quasi-Newton algorithms developed in this thesis are of second order method in variable step size to accelerate the convergence rate during network training. The genetic algorithm in floating point with improved update rules in mutation and crossover is also presented in this study for integration with neural network. All algorithms in NeuralLink are successfully applied to system identification and control. The Quasi-Newton algorithms are shown to achieve better training efficiency and accuracy. A two-stage training algorithm by combining the advantages of the Quasi-Newton algorithm and genetic algorithm is also developed to provide optimal initial weight and bias so as to accelerate neural network training.
　　NeuralLink is shown effective for applications in: (1) system identification, (2) neural network controller design, (3) fuzzy logic controller design and (4) pattern recognition. In system identification, a novel neural sensor model is developed such that the state variables of displacement and velocity vitally important in feedback control can be generated by the acquisition of only one piezoelectric sensor. Applications of the neural sensor to identification of a smart structure system and a building control system show that NeuralLink is effective and efficient in constructing the associated neural network models. In pattern recognition of car license plate number, a column-sum method is also developed such that NeuralLink can efficiently locate the license plate in an image and successfully identify the plate number. In control applications, NeuralLink provides both neural controller and fuzzy controller design in LAB-VIEW6.1 interfaces. The controllers can then be readily implementated in PC environment for engineering applications. Both simulations and experiments show that NeuralLink is effective to system identification, structure vibration control, and car license plate identification.

Abe, S., 1998, “Dynamic Cluster Generation for a Fuzzy Classifier with Ellipsoidal Regions,” IEEE Trans. on Systems, Man and Cybernetics-Part B, vol. 28, no. 6, pp. 869-876.

Agarwala, R., Ozcelik, S. and Faruqi, M., 2000, “Active Vibration Control of a Multi-Degree-of-Freedom Structure by the Use of Direct Model Reference Adaptive Control,” Proc. of the American Control Conf., vol. 5, pp. 3580–3584.

Amini, F., Chen, H. M., Qi, G. Z. and Yang, J. C. S., 1997, “Generalized Neural Network Based Model for Structural Dynamic Identification, Analytical and Experimental Studies,” Proc. Intelligent Information Systems, pp. 138-142.

Baba, N., 1989, “A New Approach for Finding the Global Minimum of Error Function of Neural Networks,” Neural Networks, vol. 2, pp. 367-373.

Billing, S. A. and Zheng, G. L., 1995, “Radial Basis Function Network Configuration Using Genetic Algorithms,” Neural Networks, vol. 8, no. 6, pp. 877-890.

Botha, E. C., Barnard, E. and Barnard, C. J., 1996, “Feature-Base Classification of Aerospace Radar Targets Using Neural Networks,” Neural Networks, vol. 9, no. 1, pp. 129-142.

Cho, S. B., 1997, “Neural–Network Classifiers for Recognizing Totally Unconstrained Handwritten Numerals,” IEEE Trans. Neural Networks, vol. 8, no. 1, pp. 43-53.

Comelli, P., Ferragina, P., Granieri, M. N. and Stabile, F., 1995, “Optical Recognition of Motor Vehicle License Plates,” IEEE Trans. on Vehicular Technology, vol. 44, no. 4, pp. 790-799.

Emiris, D. M. and Koulouriotis, D. E., 2001, “Automated Optic Recognition of Alphanumeric Content in Car License Plates in a Semi-Structured Environment,” Proc. of IEEE International Conf. on Image Processing, vol. 3, pp. 50 -53.

Farag, W. A., Quintana, V. H. and Germano, L. T., 1998, “A Genetic-Based Neuro-Fuzzy Approach for Modeling and Control of Dynamical System,” IEEE Trans. Neural Networks, vol. 9, no. 5, pp. 756-767.

Forrai, A., Hashimoto, S., Funato, H. and Kamiyama, K., 2001, “Structural Control Technology: System Identification and Control of Flexible Structures,” J. of Computing & Control Engineering, pp. 257-262.

Funahashi, K. I., 1989, “On the Approximate Relization of Continuous Mappings by Neural Networks,” Neural Networks, vol. 2, pp. 183-192.

Garibotto, G., Castello, P., Ninno, E. D., Pedrazzi, P. and Zan, G., 2001, “Speed-Vision: Speed Measurement by License Plate Reading and Tracking,” Proc. IEEE Intelligent Transportation Systems, pp. 585–590.

Hagan, M. T. and Menhaj, M. B., 1994, “Training Feedforward Networks with the Marquardt Algorithm,” IEEE Trans. Neural Networks, vol. 5, no. 6, pp. 989-993.

Han, M., Han, G., Jiang, X. and Lian, Z., 2001, “Study of Dynamic Response of Dams with Neural Network,” IEEE International Conf. on Systems, Man, and Cybernetics, vol. 1, pp. 134–139.

Hecht-Nielsen, R., 1987, “Kolmogorov’s Mapping Neural Network Existence Theorem,” Proc. IEEE ICNN, IEEE Press, New York, vol. 3, pp. 11-13.

Hecht-Nielsen, R., 1989, “Theory of the Backpropagation Neural Network,” IJCNN, vol. 1, pp. 593-605.

Hontani, H. and Koga, T., 2001, “Character Extraction Method without Prior Knowledge on Size and Position Information,” Proc. of the IEEE International Vehicle Electronics Conf., pp. 67 –72.

Hung, S. L. and Adeli, H., 1994, “A Parallel Genetic/Neural Network Learning Algorithm for MIMD Shared Memory Machines,” IEEE Trans. Neural Networks, vol. 5, no. 6, pp. 900-909.

Jacobs, R. A., 1988, “Increased Rates of Convergence Through Learning Rate Adaptation,” Neural Networks, vol. 1, pp. 295-307.

Jagannathan, S., 2001, “Control of a Class of Nonlinear Discrete-Time Systems Using Multilayer Neural Netwprks,” IEEE Trans. Neural Networks, vol. 12, no. 5, pp. 1113-1120.

Jeng, C. A., Yang, S. M. and Lin, J. N., 1997, “Multi-Mode Control of Structures by Using Neural Networks with Marquardt Algorithms,” Journal of Intelligent Material Systems and Structures, vol. 8, no. 12, pp. 1035-1043.

Jin, Y. C. and Jay, A. F., 2001, “Adaptive Observer Backstepping Control Using Neural Networks,” IEEE Trans. Neural Networks, vol. 12, no. 5, pp. 1103-1112.

Karakasoglu, A., Suharsanan, S. I. and Sudareshan, M. K., 1993, “Identification and Decentralized Adaptive Control Using Dynamical Neural Networks with Application to Robotic Manipulators,” IEEE Trans. Neural Networks, vol. 4, no. 6, pp. 919-930.

Kim, J. H., Jabbari, F. and Yang, J. N., 2000, “Actuator Saturation and Control Design for Buildings Under Seismic Excitation,” Proc. of the American Control Conf., vol. 1, PP. 29–33.

Kim, K. K., Kim, K. I., Kim, J. B. and Kim, H. J., 2000, “Learning-Based Approach for License Plate Recognition,” Proc. of the 2000 IEEE Signal Processing Society Workshop on Neural Networks for Signal Processing X, vol. 2, pp. 614-623.

Kim, D. S. and Chien, S. I., 2001, “Automatic Car License Plate Extraction Using Modified Generalized Symmetry Transform and Image Warping,” Proc. ISIE 2001. IEEE International Symposium on Industrial Electronics, vol. 3, pp. 2022-2027.

Ku, C. C. and Lee, K. Y., 1995, “Diagonal Recurrent Neural Networks for Dynamic Systems Control,” IEEE Trans. Neural Networks, vol. 6, no. 1, pp. 144-155.

Lee E. R., Kim P. K. and Kim H. J., 1994, “Automatic Recognition of a Car License Plate Using Color Image Processing,” Proc. of IEEE International Conf. on Image Processing, vol. 2, pp. 301–305.

Lee, J., Ha, D. and Kim, Y. D., 2001, “A Study on the Hardware Implementation for Car License Plate Area Extraction,” IEEE International Conf. on Systems, Man, and Cybernetics, vol. 4, pp. 2281-2284.

Lee, T. S., Chen, Y. H. and Chuang, C. H., 1997, “Robust Control of Building Structures,” Proc. of the American Control Conf., vol. 5, PP. 3421–3425.

Levin, A. U. and Narendra, K. S., 1996, “Control of Nonlinear Dynamical Systems Using Neural Networks-Part Ⅱ: Observability, Identification, and Control,” IEEE Trans. Neural Networks, vol. 7, no. 1, pp. 30-41.

Lo, S. C., Chan, H. P., Lin, J. S., Li, H., Freedom, M. T. and Mun, S. K., 1995, “Artificial Convolution Neural Network for Medical Image Pattern Recognition,” Neural Networks, vol. 8, no. 7-8, pp. 1201-1214.

Magoulas, G. D., Vrahatis, M. N. and Androulakis, G. S., 1997, “Effective Backpropagation Training with Variable Stepsize,” Neural Networks, vol. 10, no. 1, pp. 69-82.

Makris, N., 1997, “Vibration Control of Structures During Urban Earthquakes,” Proc. of the American Control Conf., vol. 6, pp. 3957-3961.

Maniezzo, V., 1994, “Genetic Evolution of the Topolgy and Weight Distribution of Neural Networks,” IEEE Trans. Neural Networks, vol. 5, no. 1, pp. 39-53.

Miachalewicz, Z., 1996, Genetic Alogorithms + Data Structure = Evolution Programs, New York: Springer-Verlag.

Minai, A. A. and Williams, R. D., 1990, “Acceleration of Back-propagation Through Learning Rate and Momentum Adaptation,” Proc. of IJCNN, vol. 1, pp. 676-679.

Naito, T., Tsukada, T., Yamada, K., Kozuka, K. and Yamamoto, S., 2000, “Robust License-Plate Recognition Method for Passing Vehicles under Outside Environment,” IEEE Trans. on Industrial Electronics, vol. 49, no. 6, pp. 2309-2319.

Narendra, K. S. and Parthasarathy, K., 1990, “Identification and Control of Dynamical Systems Using Neural Networks,” IEEE Trans. Neural Networks, vol. 1, no. 1, pp. 4-27.

Nguyen, D. and Widrow, B., 1990, “Improving the Learning Speed of 2-Layer Neural Networks by Choosing Initial Values of the Adaptive Weights,” Proc. of IJCNN, San Diego, California, vol. 3, pp. 22-26.

Nguyen, T., Jabbari, F. and Miguei, S. D., 1998, “Application of Active Control to Buildings Under Seismic Excitation: Actuator Saturation,” Proc. of the 1998 IEEE International Conf. on Control Appl., vol. 2, pp. 1051-1055.

Nijhuis, J. A. G.., Ter Brugge, M. H., Helmholt, K. A., Pluim, J. P. W., Spaanenburg, L., Venema, R. S. and Westenberg, M. A., 1995, “Car License Plate Recognition with Neural Networks and Fuzzy Logic,” Proc. of IEEE International Conf. on Neural Networks, vol. 5, pp. 2232–2236.

Nishimura, H. and Kojima, A., 1999, “Seismic isolation control for a building-like structure,” IEEE Control Systems Magazine, pp. 38-44.

Nishitani, A., Nitta, Y. and Yamada, N., 1996, “Variable Gain-Based Structural Control Considering the Limit of AMD Movement,” Proc. of the 35th IEEE Conf. on Decision and Control, vol. 1, pp. 185–190.

Parker, D. B., 1985, “Learning Logic,” Technical Report TR-47, Center for Computational Research in Economics and Management Science, Massachusetts Institute of Technology, Cambridge, MA.

Park, S. H., Kim, K. I., Jung, K. and Kim, H. J., 1999, “Locating Car License Plates Using Neural Networks,” Electronics Letters, vol. 35, no. 17, pp.1475-1477.

Phansalkar, V. V. and Sastry, P. S., 1994, “Analysis of the Back-propagation Algorithm with Momentum,” IEEE Trans. Neural Networks, vol. 5, no. 3, pp. 505-509.

Popescu, T. D., 2001, “Robust change detection method with application in vibration structures monitoring,” Proc. of 8th IEEE International Conf. on Emerging Technologies and Factory Automation, vol. 1, pp. 95-102.

Ramallo, J. C., Johnson, E. A., Spencer, B. F. Jr. and Sain, M. K., 1999, “Semi-Active Building Base Isolation,” Proc. of the American Control Conf., vol. 1, pp. 515-519.

Raus, M. and Kreft, L., 1996, “Reading Car License Plates by the Use of Artificial Neural Networks,” Proc. of the 38th Midwest Symposium on Circuits and Systems, vol. 1, pp. 538-541.

Roger, S. K., Colombi, J. M., Martin, C. E., Gainey, J. C., Fielding, K. H., Burns, T. J., Ruck, D. W., Kabrisky, M. and Oxley, M., 1995, “Neural Network for Automatic Target Recognition,” Neural Networks, vol. 8, no. 7-8, pp. 1153-1184.

Rumelhart, D. E., Hinton, G. E. and Williams, P. J., 1986, “Learning Internal Representation by Error Propagation,” in Parallel Distributed Processing, D. E. Rumelhart and J. L. McClelland, Eds. Cambridge, MA: MIT Press.

Schittenkopf, C., Deco, G. and Brauer, W., 1997, “Two strategies to avoid over- fitting in Feed forward Networks,” Neural Networks, vol. 10, no. 3, pp. 505-516.

Seto, K., 1996, “A Structural Control Method of the Vibration of Flexible Buildings in Response to Large Earthquakes and Strong Winds,” Proc. of the 35th IEEE Conf. on Decision and Control, vol. 1, pp. 658–663.

Seto, F. and Matsumoto, Y., 1999, “Active Vibration Control of Multiple Buildings Connected with Active Control Bridges in Response to Large Earthquakes,” Proc. of the American Control Conf., vol. 2, PP. 1007–1011.

Sirithinaphong, T. and Chamnongthai, K., 1999, “The Recognition of Car Llicense Plate for Automatic Parking System,” Proc. of the Fifth International Symposium on Signal Processing and Its Applications, vol. 1, pp. 455 –457.

Sirithinaphong, T. and Chamnongthai, K., 1998, “Extraction of Car License Plate Using Motor Vehicle Regulation and Character Pattern Recognition,” IEEE Asia-Pacific Conf. on Circuits and Systems, pp. 559-562.

Sridhar, S. and Hassan, K. K., 2000, “Output Feedback Control of Nonlinear Systems Using RBF Neural Networks,” IEEE Trans. Neural Networks, vol. 11, no. 1, pp. 69-79.

Stager, F. and Agarwal, M., 1997, “Three Methods to Speed Up the Training of Feedforward and Feedback Perceptrons,” Neural Networks, vol. 10, no. 8, pp. 1435-1443.

Sun, Y. N., Horng, M. H., Lin, X. Z. and Wang, J. Y., 1996, “Ultrasonic Image Analysis for Liver Diagnosis,” IEEE Engineering in Medicine and Biology Magazine, vol. 15, no. 6, pp. 93 – 101.

Suzuki, Y., 1998, “Acceleration Feedforward Control for Active Magnetic Bearing Systems Excited by Ground Motion,” Proc. Control Theory Appl., vol. 145, no. 2, pp. 113–118.

Tani, A. and Kawamura, H., 1993, “Fuzzy Optimal Seismic Control Systems of Buildings-In Case of Active Equivalent Variable Mass System,” Proc. of Second International Symposium on Uncertainty Modeling and Analysis, pp. 611-618.

Werbos, P. J., 1974, “Beyond Regression: New Tools for Prediction and Analysis in the Behavioral Sciences,” Ph. D. Thesis, Harvard Univ., Cambridge, MA.

Yamamoto, K., Yamamoto, T., Ohmori, H. and Sano, A., 1997, “Adaptive Feedforward Control Algorithms for Active Vibration Control of Tall Structures,” Proc. of the 1997 IEEE International Conf. on Control Appl., pp. 736 – 742.

Yan, D., Hongqing, M., Jilin, L and Langang, L., 2001, “A High Performance Llicense Plate Recognition System Based on the Web Technique,” Proc. IEEE Intelligent Transportation Systems, pp. 325-329.

Yang, S. M. and Lee, G. S., 1997, “Vibration Control of Smart Structure by Using Neural Networks,” Trans ASME. J. of Dynamic Systems, Measurment, and control, vol. 119, no. 1, pp. 34-39.

Yang, S. M. and Tung, Y. J., 2001, “A Neuro-Fuzzy System Design Methodology for Modeling and Control,” 4th Pacific International Conference on Aerospace Science and Technology, Kaohsing, Taiwan.

Yang, S. M., Tung, Y. J. and Huang, W. L., 2002, “A Neuro-Fuzzy System and Its Applications to Modeling and Control,” CSSV Conf. Taiwan, pp. 35-42.

Yang, S. M. and Huang, W. L., 2002, “System Identification and Control by Using Feedforward Network with Two-Stage Training Algorithm,” CSSV Conf. Taiwan, pp. 274-280.

Yi, F., Dyke, S. J., Caicedo, J. M. and Carlson, J. D., 1999, “Seismic Response Control Using Smart Dampers,” Proc. of the American Control Conf., vol. 2, pp. 1022–1026.

Yu, W. and Li, X., 2001, “ Some New Results on System Identification with Dynamic Neural Networks,” IEEE Trans. Neural Networks, vol. 12, no. 2, pp. 412-417.

Yu, X. H., Chen, G. A. and Cheng, S. X., 1995, “Dynamic Learning Rate Optimization of the Backpropagation Algorithm,” IEEE Trans. Neural Networks, vol. 6, no. 3, pp. 669-677.

Yu, X. H. and Chen, G. A., 1997, “Efficient Backpropagation Learning Using Optimal Learning Rate and Momentum,” Neural Networks, vol. 10, no. 3, pp. 517-527.

Zhu, C. and Paul, F. W., 1995, “A Fourier Series Neural Network and Its Application to System Identification,” J. of Dynamic Systems, Measurement, and Control, vol. 117, pp. 253-261.

Zunino, R. and Rovetta, S., 2000, “Vector Quantization for License-Plate Location and Iimage Coding,” IEEE Trans. on Industrial Electronics, vol. 47, no. 1, pp. 159-167.