本研究提出以人工智慧為基礎之船舶安全監控系統，該系統能有智慧地處理三種安全監控項目，包括推進系統之故障診斷、人員之急性腹症診斷與機艙之火災預警。結合共生演化法、模糊聚類法、自適應模糊辨識法、倒傳遞類神經網路與灰色理論建構專業化之監控軟體，以進行船舶安全之診斷與預警。研究首先將船舶系統中各項需要監控之對象分別以模組化的方式加以分類，所開發之監控模組因此可歸為兩大類，第一類為診斷模組，第二類為預警模組，依據受監控對象之不同特性，採用適當的模組進行監控之工作。
　　診斷模組是以共生演化法為基礎之模糊類神經診斷模組，基於共生演化法具有演化速度較快與最佳化設計之優點，提供不同的受監控設備於診斷模組建構時所需之參數組合，藉由模糊聚類、倒傳遞修正及最佳基因搜尋的程序，以獲得最佳化之模糊類神經診斷模組，該模組適用於解讀複雜的診斷資料。預警模組乃將灰色模型與自適應模糊辨識法相結合，當火災發生而系統響應的快慢成為很重要的考量因素時，該模組便可用於對臨界狀態的發展進行預測。將兩項模組合組成具有預測及診斷能力之智慧型船舶安全監控系統，可以完成許多船舶安全監控的工作，監控項目可包括導航設備、船舶結構、引擎轉速與振動、機油狀況等。此外，本研究所提出之智慧型船舶安全監控系統能夠以增加模組的方式隨時加入新的受監控對象，系統便依據受監控對象之資料自動建構診斷機制，不但可以簡化船舶安全監控工程之設計與管理，更可以使本研究所提出之智慧型船舶安全監控系統更具有彈性。
　　以共生演化為基礎之模糊類神經診斷模組與其他傳統方法進行比較，所提出之模糊類神經診斷模組獲得較高的診斷率與較短的系統建構時間。在灰色模糊預警模組方面，利用開放型火災與悶燒型火災之火場資料並與一般商用火災警報器進行比較，灰色模糊預警模組對於溫度及煙濃度能夠進行即時監測與趨勢預測，不但可以提高火災警報之準確性，更可以提早預測火災之發生。
　　本研究所提出之設計可以作為未來開發以人工智慧為基礎之監控系統之核心模型，當應用於船舶航行之監控時，朝向以遠端智慧型網路監控為基礎，將監控系統、受監控對象與資料進行整合，以有效達到安全、經濟、便利與舒適的目標，智慧型船舶安全監控系統之建置也將更形完善。

　　This study presents the hub of an AI-based (artificial intelligence) ship security monitoring system designed to supervise three different maritime monitoring tasks, including propeller-shaft fault detection and diagnosis, human medical diagnosis, and smoke- and temperature-based fire alarm. Particular software for the three tasks is developed using a combination of symbiotic evolution, fuzzy clustering, adaptive fuzzy classification, back-propagation neural networking, and grey theory. Essentially, a modularizing scheme for categorizing various monitored/controlled objectives appearing in the ship system is used in this study. Accordingly, two general-purpose software models, the diagnostic software model and the predictive software model, are proposed. These models implementing monitoring tasks properly are established consistent with the behavior characteristics of the monitored objectives.
　　The diagnostic model is a symbiotic evolution-based fuzzy-neural diagnosis model applicable to the interpretation of complex current data. The predictive model is a grey-fuzzy prediction model, which is available to the crucial situation of early-prediction such as fire alarm for small differences in alarm time. When working together, these models can supervise a wide variety of modern maritime data, including electronic compass, hull motion sensors, engine shaft RPM and vibration sensors, GPS, temperature sensors, engine oil condition, and so on. The AI system has self-designing functions that can easily monitor new objects to be input, upon which the system will automatically develop specified monitoring, diagnosis, and response patterns for the new data. In essence, this methodology simplifies the tasks of system design and management, and increases system flexibility.
　　Compared with several traditional methods by applying the same database, the proposed symbiotic evolution-based fuzzy-neural diagnosis model exhibits higher diagnostic rate and lower model construction time. The grey-fuzzy prediction model tested under the circumstances of open-flame and smoldering fires is compared with the commercial detector operating with the same condition. The experimental results reveal that the proposed model gives superior performance.
　　The presented design is useful as a core model for developing more advanced AIs-based monitoring systems. As applied to the monitor maritime, the proposed system provides a good basis for the intelligently remote network-based integration of monitoring system, monitored objects and data. Consequently, the intelligent ship security monitoring system will be essential for optimizing the levels of safety, economy, convenience, and comfort.

[1] 呂建民，類神經網路應用於船舶熱交換系統節能控制與遠端監控之研究，碩士論文，國立海洋大學，民92。
[2] 戴瑞龍，流體機械機件損壞預知技術研究-以船艦用燃氣渦輪主機系統為例，碩士論文，國防大學中正理工學院，民92。
[3] 林文鏘，船舶電力系統穩定度分析，碩士論文，國立海洋大學，民90。
[4] 李仁貴，以混合光纖同軸有線電視網路進行遠距居家照護之應用，博士論文，國立台灣大學，民89。
[5] Gaura, E. I., Rider, R. J., Steel, N. and Naguib, R. N. G., Neural-network compensation methos for capacitive micromachined accelerometers for use in telecare medicine, IEEE Trans. Information technology in biomedicine, vol. 5, no. 3, 2001, pp.248-252.
[6] Rovetta, A., Cuce, A., Solenghi, C. and Bisogni, M., Remote house calls [disease detector], IEEE Robotics & Automation Magazine, vol. 10, 2003, pp.65-71.
[7] Hung, K. and Zhang, Y., Implementation of a WAP-based telemedicine system for patient monitoring, IEEE Transactions on Information Technology in Biomedicine, vol. 7, 2003, pp.101-107.
[8] Virone, G., Noury, N. and Demongeot, J., A system for automatic measurement of circadian activity deviations in telemedicine, IEEE Transactions on Biomedical Engineering, vol. 49, 2002, pp.1463-1469.
[9] 張傳育，整合類神經網路及影像處理技術在鼻咽疾病診斷之應用，博士論文，國立成功大學，民89。
[10] 李建誠，互動式之遠距腹腔醫療診斷系統，博士論文，國立成功大學，民92。
[11] Sheybani, E. O. and Sankar, R., ATMTN: a telemammography network architecture, IEEE Transactions on Biomedical Engineering, vol. 49, 2002, pp.1438-1443.
[12] Ji, W., Naguib, R. N. G., and Ghoneim, M. A., Neural network-based assessment of prognostic markers and outcome prediction in bilharziasis -associated bladder cancer, IEEE Transactions on Information Technology in Biomedicine, vol. 7, 2003, pp.218-224.
[13] Roehle, N. M., Pedreira, C. E. and Teles De Azevedo, H. R., Fuzzy art neural network approach for incipient fault detection and isolation in rotating machines, Proceedings of the IEEE International Conference on Neural Networks, vol. 1, 1995, pp.538–542.
[14] Zhao, L. and Sheng, Z., Combination of discrete cosine transform with neural network in fault diagnosis for rotating machine, Proceedings of the IEEE international conference on industrial technology, 1996, pp.450-454.
[15] McCormick, A. C. and Nandi, A. K., Neural network autoregressive modeling of vibrations for condition monitoring of rotating shafts, International conference on Neural Networks, vol. 4, 1997, pp.2214–2218.
[16] Grimmelius, H.T., Meiler, P.P., Maas, H.L.M.M., Bonnier, B., Grevink, J.S. and Kuilenburg, R.F., Three state-of-the-art methods for condition monitoring, IEEE Trans. on Industrial Electronics, vol. 46, no. 2, 1999, pp.407–416.
[17] Kuo, H.C., Wu, L.J. and Chen, J.H., Neural-fuzzy fault diagnosis in a marine propulsion shaft system, Journal of Materials Proceeding Technology, vol. 122, 2002, pp.12-22.
[18] Li, B., Chow, M. Y., Tipsuwan, Y. and Hung, J. C., Neural- network-based motor rolling bearing fault diagnosis, IEEE Transactions on Industrial Electronics, vol. 47, no. 5, 2000, pp.1060–1069.
[19] da Silva Vicente, S. A., Fujimoto, R. Y. and Padovese, L. R., Rolling bearing fault diagnostic system using fuzzy logic, The 10th IEEE International Conference on Fuzzy Systems, vol. 3, 2001, pp.816-819.
[20] Kyusung, K., Parlos, A. G. and Mohan Bharadwaj, R., Sensorless fault diagnosis of induction motors, IEEE Transactions on Industrial Electronics, vol. 50, no. 5, 2003, pp.1038–1051.
[21] Chabat, F., Hansell, D. M. and Yang, G., Computerized decision support in medical imaging, IEEE engineering in medicine and biology, September/October, 2000, pp.89-96.
[22] Johnson, L., Computer based medical diagnosis, IEE colloquium on Computer based diagnosis, London, UK, 1988, pp.1/1-1/46.
[23] Frohlich, M. W., Miller, P. L. and Morrow, J. S., PATHMASTER: Modeling differential diagnosis as “Dynamic Competition” between systematic analysis and disease-directed deduction, Computers and biomedical research, vol. 23, 1990, pp.499-513.
[24] Hojjatoleslami, A., Sardo, L. and Kittler, J., An RBF based classifier for the detection of microcalcifications in mammograms with outlier rejection capability, International conference on Neural Networks, Houston, USA, 1997, pp.1379-1384.
[25] Peng, C., Xiao, S., Nie, Z., Wang, Z. and Wang, F., Applying Bayes’ theorem in medical expert systems, IEEE Engineering in Medicine and Biology, May/June, 1996, pp.76-79.
[26] Xiao, S., Peng, C., Wang, Z., Wang, F. and Nie, Z., Using the algebraic sum method in medical expert system, IEEE Engineering in Medicine and Biology, May/June, 1996, pp.80-82.
[27] Adlassnig, K. P., Fuzzy set theory in medical diagnosis, IEEE Trans. Syst., Man, Cybern., vol. 16, no. 2, 1986, pp.260-265.
[28] Hudson, D. L. and Cohen, M. E., Fuzzy logic in medical expert systems, IEEE Engineering in Medicine and Biology Magazine, Nov.-Dec., 1994, pp.693-698.
[29] Garibaldi, J. M. and Ifeachor, E. C., Application of simulated annealing fuzzy model tuning to umbilical cord acid-base interpretation, IEEE Transactions on Fuzzy Systems, vol. 7, no. 1, 1999, pp.72-84.
[30] Walter, D. and Mohan, C. K., ClaDia: A fuzzy classifier system for disease diagnosis, Proc. Congress Evolutionary Computation, CA, 2000, pp.1429-1435.
[31] Zahan, S., A fuzzy approach to computer-assisted myocardial ischemia diagnosis, Artif. Intell. Med., vol. 21, 2001, pp.271-275.
[32] Filho, D. V., dos Santos, M. A., Ludermir, T. B. and Silva, M. J., A fuzzy approach to support a musculoskeletal disorders diagnosis, Proceedings VII Brazilian Symposium on Neural Networks, 2002, pp.154.
[33] Seker, H., Odetayo, M. O., Petrovic, D. and Naguib, R. N. G., A fuzzy logic based-method for prognostic decision making in breast and prostate cancers, IEEE Transactions on Information Technology in Biomedicine, vol. 7, no. 2, 2003, pp.114–122.
[34] Kordylewski, H., Graupe, D. and Liu, K., A novel large-memory neural network as an aid in medical diagnosis applications, IEEE Transactions on Information Technology in Biomedicine, vol. 5, no. 3, 2001, pp.202–209.
[35] Zhou, Z. and Jiang, Y., Medical diagnosis with C4.5 rule preceded by artificial neural network ensemble, IEEE Transactions on Information Technology in Biomedicine, vol. 7, no. 1, 2003, pp.37–42.
[36] Ozyilmaz, L. and Yildirim, T., Artificial neural networks for diagnosis of hepatitis disease, Proceedings of the International Joint Conference on Neural Networks, 2003, pp.586–589.
[37] Wang, X., Xiao, J. and Bao, M., A ship fire alarm system based on fuzzy neural network, Proceeding of the 3rd world congress on intelligent control and automation, Hefei, China, June 28-july 2, 2000.
[38] Chen, S., Yi, J. and Zhao, Y., Self-learning fuzzy neural network and its application to fire auto-detecting in fire protection system, Proceeding of the 3rd world congress on intelligent control and automation, Hefei, China, June 28-july 2, 2000.
[39] Ray, K. S. and Dinda, T. K., Pattern classification using fuzzy relational calculus, IEEE Transactions on Systems, Man and Cybernetics, Part B, vol. 33, 2003, pp.1-16.
[40] Purkait, P., Chatterjee, A., Chakravorti, S. and Bhattacharya, K., Translationally adaptive fuzzy classifier for transformer impulse fault identification, IEE Proceedings-Generation, Transmission and Distribution, vol. 150, 2003, pp.33-40.
[41] Setnes, M. and Roubos, H., GA-FUZZY modeling and classification: Complexity and performance, IEEE Trans. Fuzzy system, vol. 8, no. 5, 2000, pp.509-522.
[42] Li, Z., Khananian, A., Fraser, R. H. and Cihlar, J., Automatic detection of fire smoke using artificial neural networks and threshold approaches applied to AVHRR imagery, IEEE Trans. Geoscience and remote sensing, vol. 39, no. 9. 2001, pp.1859-1870.
[43] Neubauer, A., Genetic algorithms in automatic fire detection technology, Second international conference on genetic algorithms in engineering systems: Innovations and applications, Galesia, Sept. 2-4, 1997.
[44] Deng, J., Control problems of grey system, Syst. Contr. Lett., vol. 5, 1982, pp.288-294.
[45] Chen, J. L. and Chen, P. Y., An efficient grey search algorithm for the estimation of motion vectors, IEEE Trans. Syst. Man, Cybern., vol. 31, no. 2, 2001, pp.242-248.
[46] Kuo, H. C. and Wu, L. J., Prediction of deformation to thin ship panels for different heat sources, Journal of ship production, vol. 17, no.2, 2001, pp.52-61.
[47] Yuan, B., Guo, J., Tang, G. and Wang, L., Using grey theory to predict the gas-in-oil concentrations in oil-filled transformer, Proceedings of the 6th international conference on properties and applications of dielectric materials, Xian, China, June 21-26, 2000.
[48] Brameier, M. and Banzhaf, W., A comparison of linear genetic programming and neural networks in medical data mining, IEEE Transactions on Evolutionary Computation, vol. 5, no. 1, 2001, pp.17–26.
[49] Paul, S. and Kumar, S., Subsethood-product fuzzy neural inference system, IEEE Transactions on Neural Networks, vol. 13, no. 3, 2002, pp.578–599.
[50] Lee, C., Chung, P. and Tsai, H., Identifying multiple abdominal organs from CT image series using a multimodule contextual neural network and spatial fuzzy rules, IEEE Transactions on Information Technology in Biomedicine, vol. 7, no. 3, 2003, pp.208–217.
[51] Meesad, P. and Yen, G. G., Combined numerical and linguistic knowledge representation and its application to medical diagnosis. IEEE Transactions on Systems, Man, and Cybernetics-Part A, vol. 33, no. 2, 2003, pp.206-222.
[52] Huang, Y., Evolving neural nets for fault diagnosis of power transformers, IEEE Trans. Power Delivery, vol. 18, 2003, pp.843-848.
[53] Goldberg, D. E., Genetic Algorithms in Search Optimization and Machine Learning, Reading, MA: Addison-Wesley, 1989.
[54] Alpaydin, G., Dundar, G. and Balkir, S., Evolutin-based design of neural fuzzy networks using self-adapting genetic parameters, IEEE Trans. Fuzzy Systems, vol. 10, 2002, pp.211-221,.
[55] Wang, W. Y. and Li, Y. H., Evolutionary learning of BMF fuzzy-neural networks using a reduced-form genetic algorithm, IEEE Transactions on Systems, Man and Cybernetics, Part B, vol. 33, 2003,pp.966-976.
[56] Zhou, Y. and Lai, L., Optimal design for fuzzy controllers by genetic algorithms, IEEE Trans. Industry Application, vol. 36, 2000, pp. 93-97.
[57] Ku, K. W. C., Mak, M. W. and Siu, W., A study of the Lamarckian evolution of recurrent neural networks, IEEE Trans. Evolutionary Computation, vol. 4, 2000, pp.31-42.
[58] Wang, Y., Yang, S., Ni, G., Ho, S. L. and Liu, Z.J., An Emigration Genetic Algorithm and Its Application to Multiobjective Optimal Designs of Electromagnetic Devices, IEEE Transactions on Magnetics, vol. 40, 2004, pp.1240-1243.
[59] Juang, C. F., Lin, J. Y. and Lin, C. T., Genetic reinforcement learning through symbiotic evolution for fuzzy controller design, IEEE Trans. Syst., Man, Cybern., vol. 30, 2000, pp.290–302.
[60] Moriarty, D. E. and Miikkulainen, R., Efficient reinforcement learning through symbiotic evolution, Mach. Learn., vol. 22, 1996, pp.11–32.
[61] Haykin, S., Neural Network, Prentice-Hall, Englewood Cliffs, NJ, 1999.
[62] Jinwook, G., Gunhee, H., Hagbae, K. and Chulhee, L., Multigradient: a new neural network learning algorithm for pattern classification, IEEE Trans. on Geosci. Remote Sensing, vol. 39, no. 5, 2001, pp.986-993.
[63] Rumelhart, D.E., Hinton, G.E. and Williams, R.J., Learning Internal Representations by Error Propagation, MIT Press, Cambridge, Ma, 1986.
[64] Linkens, D. A. and Chen, M., Input selection and partition validation for fuzzy modeling using nerral networks, Fuzzy Sets Syst., vol. 107, 1999, pp.299-308,.
[65] Chen, M. and Linkens, D. A., A systematic neuro-fuzzy modeling framework with application to material property prediction, IEEE Trans. on Syst., Man, Cybern. B., vol. 31, 2001, pp. 781-790.
[66] Li, M. and Tam, H., Hybrid evolutionary search method based on clusters, IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 23, 2001, pp.786-799.
[67] Fogel, D. B., An introduction to simulated evolutionary optimization, IEEE Trans. Neural Network, vol. 5, 1994, pp.3-14.
[68] Grefenstette, J. J., Genetic algorithms for changing environment, The Netherlands in Parallel Problem Solving from Nature, Amsterdam, North Holland, 1992, pp.145–154.
[69] Nozaki, K., Ishibuchi, H. and Tanaka, H., Adaptive fuzzy rule-based classification systems, IEEE Trans. Fuzzy Systems, vol. 4, no. 3, 1996, pp.238-250.
[70] Ishibuchi, H. and Nakashima, T., Improving the performance of fuzzy classifier systems for pattern classification problems with continuous attributes, IEEE Trans. Industrial Electronics, vol. 46, no. 6, 1999, pp.1057-1038.
[71] Gunn, A. A., The acute abdomen: the role of computer-assisted diagnosis, Bailliere’s clinical Gastroenterology, vol. 5, No. 3, 1991.
[72] Wellwood, J. M. and Spiegelhaiter, D. J., Computer and the diagnosis of acute abdominal pain, British journal of hospital medicine, vol. 41, 1989.
[73] 郭振邦，急性腹症的電腦諮詢系統--使用模糊模式，碩士論文，國立成功大學，民82。
[74] UL 268, Standard for smoke detectors for fire protective signaling systems, 2nd edn., Underwriters Laboratories, Northbrook, IL, 1981, June 9.
[75] Kuo, H. C. and Chang, H. K., A real-time shipboard fire-detection system based on grey-fuzzy algorithms, Fire Safety Journal, vol. 38, 2003, pp.341-363.
[76] Sugeno, M. and Yasukawa, T., A fuzzy-logic-based approach to qualitative modeling, IEEE Trans. Fuzzy Syst., vol. 1, no. 1, 1993, pp.7-31.
[77] Rojas, I., Pomares, H., Ortega, J. and Prieto, A., Self-organized fuzzy system generation from training examples, IEEE Trans. Fuzzy Syst., vol. 8, no. 1, 2000, pp.23-36.