設備會隨時間的消逝以及長期的運轉下，使得性能受損而提高設備故障率。由於退化是不可避免，因此多數設備並無法穩定維持在最佳狀態下運轉，故必須透過維護管理，使得設備能持續保持其應有的功能，進而延長其使用年限。設備維護在經費與資源有限下，必須建立一套有效益的維護策略，在能達到最低要求性能與預算內，透過策略達到提升設備性能與降低成本之目標。
對於設備性能隨時間的變化，常常不容易明確被表達。在性能退化時，不同時期之性能退化也不一，且不同維修方式於同一設備下，所得的結果也有所變動。因此，設備維護策略必須考量維修間隔時間與維修方式對設備性能造成的變化。過去研究當中，已有採用馬可夫鏈理論來建立性能轉換機率矩陣以模擬性能變化並求解最佳維護策略；但由於建築設備大多缺乏維護資料，因此不易預測其設備性能退化過程之轉換機率，以及轉換機率的分析費時且亦受資料數量與品質的影響，故造成模式建構費時而求解效率不良。
在此，本研究對象以建築機電設備為例，利用模糊集合理論，提供一套符合建築機電設備需求的維護策略最佳化模式；考量維修間隔時間與維修方式對設備性能的影響，並在有限成本的限制下，透過模糊集合運算，來求得設備性能變化，建立維護策略效益的評估，並採用基因演算法求解出最佳策略。
從研究結果得知，透過本研究使得設備維護管理者，可藉由所提供之應用程式，可以方便達到設備維護管理的需求；瞭解採用何種維修方式並於何時執行維修動作；將此置入維護計畫中，管理者可依此針對設備性能偏低時予以控管，使整體效率提升。

Building’s facilities start to deteriorate after they are put in operation. In addition, building’s facilities must be operated at certain level to provide adequate service. Because of deterioration, building’s facilities could not perform well as planned if they are not properly maintained. Since deterioration is inevitable and maintenance requires certain amount of money, it is necessary for the facility manager to develop a maintenance strategy that can keep facilities functional without going over the budget. However, the status of the building’s facilities usually varies with time and is hard to predict. Moreover, different building’s facilities have different deterioration rates that would change over time according to the time interval and the maintenance method applied. Therefore, developing a maintenance strategy is not an easy task.
In the past research, Markov-Chain theory has been applied to describe the status of the building's facilities. However, because of lack of historical data, determining the transition probability matrix of each facility could be difficult. Therefore, it is needed to develop a maintenance model not only can effectively estimate the status of the facility but also minimize the cost of maintaining facilities.
This research presents a model that develops the optimal maintenance strategy for building facilities by minimizing the net present value of the money spent over the planning horizon. At first the status prediction model of the building facility is developed according to the theory of Fuzzy Sets. This status prediction model is presented in the form of a Fuzzy Sets, in which the current status and the status of each facility after being maintained can be determined. Then, an optimization model that incorporates genetic algorithms and the status prediction model is developed.
Results show that the proposed optimal maintenance strategy along with the computer implementation can provide an easy-to-use interface and satisfactory results for building managers to develop the optimal maintenance strategy which determines how long each facility being maintained by what method.

1. Bateman, J. (1995). “Preventive maintenance: Stand alone manufacturing compared with cellular manufacturing.” Industrial Management 37 (1), 19-21.
2. Canfield, R. V. (1986). “Cost Optimization of Periodic Preventive Maintenance.” IEEE Transactions on Reliability, Vol.R-35, No.1.
3. Catherine Azzaro, Pascal Floquet, Pibouleau Luc and Domenech S. (1994). “A FUZZY SIMULATION MODEL FOR PRODUCTION CONTROL IN A SEMICONDUCTOR WAFER MANUFACTURING.” IEEE.
4. Chaudhuri, Dipak and Suresh, P. V. (1995), “An algorithm for maintenance and replacement policy using fuzzy set theory.” Reliability Engineering and System Safety, 50 79-86.
5. Chen, C. T., Chen, Y. W., and Tuan, J. (2003). “On a Dynamic Preventive Maintenance Policy for a System under Inspection.”Reliability Engineering and System Safety, 80, 41-47.
6. Dahal, K.P., and Aldridge, C.J., and McDonald, J.R. (1998). “Generator maintenance scheduling using a genetic algorithm with a fuzzy evaluation function.” Fuzzy Sets and Systems, 102 21-29.
7. Deb, Kalyanmoy and David E. Goldberg. (1991). “mGA in C: A Messy Genetic Algorithm in C.” Illinois Genetic Algorithm Laboratory, Illinois.
8. Duffuaa S.O., and Ben-Daya, M., and Al-Sultan, K.S. and Andijani, A.A. (2001). “A generic conceptual simulation model for maintenance systems.” Journal of Quality in Maintenance Engineering, Vol. 7 No. 3.
9. Duffuaa, S. O., Raouf, A., and Campbell, J. D. (1999). Planning and Control of Maintenance System: Modeling and Analysis, John Wiley & Sons, New York.
10. Ferreira, A., Antunes, A., and Picado-Santos, L. (2002). “Probabilistic segment-linked pavement management optimization model.” Journal of Transportation Engineering, ASCE128 (6) 568-577.
11. Fwa, T. F., Chen, W. T., and Hoque, K. Z. (1994). “Multiobjective optimization for pavement maintenance programming.” Journal of Transportation Engineering, ASCE126 (5) 367-374.
12. Gen, M. and Cheng, R. (1997), Genetic algorithms and engineering design, A Wiley-Interscience Publication, New York.
13. Giegling, S., Tim, H., and William A. Verdini, Dr. John Konopka (1997) “Implementation of Overall Equipment Effectiveness (OEE) System at a Semiconductor Manufacturer.” IEEE/CPMT Int’l Electronics Manufacturing Technology Symposium.
14. Golabi, K. and Shepard, R. (1997). “Pontis : a system for maintenance optimization and improvement of US Bridge Networks.” Interfaces, 27 71-88.
15. Heverlee, Belgium, and Vereecke Ann (2006). “Evaluating the effectiveness of maintenance strategies.”Journal of Quality in Maintenance Engineering, Vol. 12 No. 1.
16. Kuranoa, M., Yasudab, M., and Nakagamib, J. and Yoshidac, Y. (2006). “A fuzzy approach to Markov decision processes with uncertain transition probabilities.” Fuzzy Sets and Systems, 157 2674-2682.
17. Laura Swanson (2001). “Linking maintenance strategies to performance.” Int. J. Production Economics, 70 237-244.
18. Lie, C. H. and Chun, Y. H. (1986). “An Algorithm for Preventive Maintenance Policy.”IEEE Transactions on Reliability, Vol.R-35, No.1.
19. Liu, C., Hammad, A., and Itoh, Y. (1997). “Maintenance strategy optimization of bridge decks using genetic algorithm.” Journal of Transportation Engineering, ASCE123 (2) 91-100.
20. Liu, James N.K. and Sin, K.Y. (1996). “Fuzzy Knowledge System for Machine Maintenance.” Australian New Zealand Conf. on Intelligent Information Systems.
21. Mechefske, Chris K., and Wang, Zheng (2003). “Using fuzzy linguistic to select optimum maintenance and condition monitoring strategies.”Mechanical systems and signal processing 17(2), 305-316.
22. Miyamoto, A., Kawamura, K., and Makamura, H. (2000). “Bridge management system and maintenance optimization for existing bridges.” Computer-Aided Civil and Infrastructure Engineering, 15 45-55.
23. Morcousa, G., and Lounis, Z. (2005). “Maintenance optimization of infrastructure networks using genetic algorithms.” Automation in Construction, 14, 129-142.
24. Ntuen, C. A. and park, E. U. (1999). “Simulation of crew size requirement in a maintained reliability system.” Computers and Industrial Engineering, Vol. 37, pp.219-22.
25. Park, D.H., Jung, G.M., Yum, J.K. (2000). “Cost Minimization for Periodic Maintenance Policy of a System Subject to Slow Degradation.” Reliability Engineering and System Safety, 68, pp.105-112.
26. Pham, H. and Wang, H. (1996). “Optimal Maintenance Policies for Several Imperfect Maintenance Models.” International Journal of System Science.
27. Pinjala, S.K. and Pintelon, L. (2004). “Bridging the gap between manufacturing and maintenance.” Operations Management as a Change Agent, Vol. II, Insead Business School, Fontainebleau, pp. 587-96.
28. Pujadas, W. and Chen, F. Frank (1996). “A reliability centered maintenance strategy for a discrete part manufacturing facility.” Computers ind. Engng. Vol. 31, No.1/2, pp.241-244.
29. Robert A. Davis, Robert J. Vokurka (2005). “The effect of facility size on manufacturing structure and performance.” Industrial management & Data systems, Vol.105, No.8.
30. Sarah A. Mosley, Tim Teyner, and Reha M. Uzsoy (1998). “Maintenance Scheduling and Staffing Policies in a Wafer Fabrication Facility.” IEEE transactions on semiconductor manufacturing, Vol.11, No.2.
31. Swanson Laura (2001). “Linking maintenance strategies to performance.” Int. J. Production Economics 70 237–244.
32. Thompson Peter (1994), “The Maintenance Factor in Facilities Management.” MCB University Press, Facilities, Vol. 12 No. 6, 1994, pp. 13-16.
33. Tsai, Y. T., Wang, K. S., and Teng, H. Y. (2001). “Optimal Preventive Maintenance for Mechanical Components Using Genetic Algorithms.” Reliability Engineering and System Safety, 74, pp.89-97.
34. Waeyenbergh, Geert, and Pintelon, Liliane. (2004). “Maintenance concept development: A case study.” Int. J. Production Economics 89 395–405.
35. Wang Cheng-Hua and Hwang Sheue-Ling (2004). “A stochastic maintenance management model with recovery factor.” Journal of Quality in Maintenance Engineering, Vol. 10, No. 2., pp.154-164.
36. Weil, N., “Make the most of maintenance.” Manufacturing Engineering 120 (5) (1998) 118-126.
37. 陳永甡，設備保養管理，科學圖書大庫，民國77年。
38. 莊嘉文，建築機電設備概論：電氣設備、空氣調節設備、給排水設備、輸送設備、消防設備，詹氏書局，台北，民國75年。
39. 鄭達才，設備維護管理-現在與未來，中國生產力中心，台北，民國89年。
40. 呂振華，工廠叢書-生產設備管理，麥可國際出版公司，民國95年。
41. 劉明國，建築物用途別之分類研究及建築物之使用管理，中華民國建築學會，台北，民國76年。
42. 楊燦煌，設備管理，書泉出版社，民國78年。
43. 尤建國，應用基因演算法及馬可夫鏈於建築機電設備維護策略最佳化之研究，國立成功大學土木工程研究所碩士論文，民國95年。
44. 宋欣財，專案排程趕工決策模式，國立成功大學土木工程研究所碩士論文，民國92年。
45. 陳惠娟，結合QFD及模糊基因演算法於工程設計之應用，國立成功大學土木工程研究所碩士論文，民國93年。
46. 劉賓陽，作業研究，三民書局，台北，民國89年。
47. 姚景星、劉睦雄，作業研究（應用篇），東華書局，民國83年。
48. 薄喬萍，作業研究決策分析，復文書局，民國78年。
49. 王文俊，認識Fuzzy，全華科技圖書股份有限公司，民國95年。
50. 楊英魁、孫宗瀛、鄭魁香、林建德、蔣旭堂，模糊控制理論與技術，全華科技圖書股份有限公司，民國91年。
51. 楊松林，工程模糊論方法及其應用，國防工業出版社，民國85年。
52. 陳明佑，利用模糊目標規劃法求解田口式多品質特性最佳化問題，國立成功大學工業管理研究所碩士論文，民國91年。
53. 林易俊，應用模糊類神經網路於積體電路之微影製程機台故障診斷分析，國立成功大學工業資訊管理學系碩士論文，民國93年。
54. 王仲宇、陳明正，台灣地區橋梁延壽技術回顧與探討，民國94年。
55. 許旭昌、江中晉、蔡沛原，多重應力下、韋伯分布下及可修復之預測系統的不完善轉換系統可靠度，國立交通大學機械工程系碩士班，民國95年。
56. 劉仁彬、唐應輝，修理設備可更換且修理有延遲的兩不同型部件並聯可修系統，高校應用數學學報A輯，民國95年。
57. 周鼎金，建築設備，民國85年。
58. 紀冠安，考慮成本與考靠度之不完全預防維護類型，朝陽科技大學工業工程與管理研究所碩士論文，民國90年。
59. 安信誠二（1991），フアジイ工學，昭晃堂，東京。