正確的預測專案工程所需的時間，對於業主與營造商而言是相當重要的決策資訊。對業主是在於提供往後的規劃設計上的資訊，而對營造商則是提供其投標前之決策資訊。
目前的研究對於專案工期預測大多著重在細部設計階段後的預測。然而在該階段預測工期，必須先將專案解析成可分解的工程作業，再尋找作業關係與其所需資源後，才可進行工期預測，在此一階段的預測相當費工費時。因此本研究將提前在初步設計階段完成後進行工期預測。
本研究利用以快速模糊類神經網路模式搜尋引擎（Fast Fuzzy Neural Inference Model Search Engine, FFNIMSE）為核心，建立一專案工期預測模式。首先藉由分析影響專案工期之因素，將影響因素以模糊數值的方式表現，並且利用類神經網路訓練模糊化後之影響因素，再以快速混雜基因演算法尋找最佳的模糊類神經網路架構。期望能將搜尋之最佳模糊類神經網路架構，實際應用於專案初期之工期預測。最後，本研究根據所建立之模式，開發一專案工期預測模式（Project Duration Forecast Model, PDFM）。
經由案例之訓練與測試本研究開發的專案工期預測模式結果顯示出本研究所建立之預測模式其平均誤差不大於±15%，對於在專案初步規劃階段的預測已是不錯的精度，對於提供業主與營造商的決策資訊也已足夠。因此藉由本研究提出之模式與PDFM應用系統，確可以將影響專案工期之因素納入考量，並且提供精確度達一定水準之工期預測。

Estimate the project duration with precision is essential to the owner and the contractor. A precise estimation on project duration can provide good decision information for the owner to go on the project, so is for the contractor to bid on the project.
Previous research on estimating project duration mostly is conducted after the detailed design phase. However, to estiamte project duraiton after detailed design phase, the project engineers have to break down the project into separable activities, and then define the relationships of these activities and their resource consumptions. It takes a lot of labor efforts and time to predict the project duration at this phase. In this study the project duration forecast model is performed before the detailed design phase.
This thesis aims at utilizing the Fast Fuzzy Neural Inference Model Search Engine (FFNIMSE) to estimate the project duration. First of all, this study searches all possible factors that influence project duration, and then transfers these factors into fuzzy numbers to train the developed neural networks. Finally, FFNIMSE seeks out the best fuzzy neural network typology by using fast messy genetic algorithms, and applies the best typology to predict the project duration. According to the above mentioned process, this study develops a graphical user interface program called PDFM (Project Duration Forecast Model) for owner and contractor.
From the results reported by PDFM, the average prediction error is less than 15%. The error rate is accurate enough for a project at planning and conceptual design phase and also for owners and contractors to make decision.

英文部份
1. Akintoye, Akintola (2000). “Analysis of factors influencing project cost estimating practice.” Construction Management and Economics, 18, 77-89.
2. Altug, S., H. J., and Chow, M. Y. (1999). “A “mutual update” training algorithms for fuzzy adaptive logic control/decision network (FALCON).” IEEE Transactions on Neural Networks, 10(1), 196-199.
3. Chan, Daniel W. M. and Kumaraswamy, Mohan M. (1995). “A study of the factors affection construction durations in Hong Kong.” Construction Management and Economics, 13, 319-333.
4. Deb, Kalyanmoy, and Goldberg, David E. (1991). mGA in C: A Messy Genetic Algorithm in C. Illinois Genetic Algorithms Laboratory, University of Illinois At Urbana-Champaign, Urbana, Illinois.
5. Gen, M. and Cheng, R. (1997). Genetic algorithms and engineering design., A Wiley-Interscience Publication, New York.
6. Goldberg, D. E. (1989). “Messy genetic algorithms: Motivation, analysis, and first results.” Complex Systems, 3(5), 493-530.
7. Goldberg, D. E., Deb, K. and Clark, J. H. (1992). “Genetic algorithms, noise, and the sizing of populations.” Complex Systems, 6, 333-362.
8. Goldberg, D. E., Deb, K. and Kargupa, H. and Harik, G. (1993). “Rapid, Accurate Optimization Using Fast Messy Genetic Algorithms.” IlliGAL Report No. 93004, Illinois Genetic Algorithms Laboratory, University of Illinois At Urbana-Champaign, Urbana, Illinois.
9. Hayashi, I., Umano, M., Maeda, T., Bastian, A., and Jain, L. C. (1998). “Acquisition of Fuzzy Knowledge by NN and GA – A survey of the Fusion and Union Methods Proposed in Japan,” Second International Conference on Knowledge-Based Intelligent Electronic Systems, IEEE, Adelaide, Australia.
10. Hegazy, Tarek, Member, ASCE, and Ayed, Amr (1998). “Neural Network Model for Parametric Cost Estimation of Highway Projects.” Journal of Construction Engineering and Management, ASCE, 124, 210-218.
11. Hideyuki Ishigami, Toshio Fukuda, Takanori Shibata, and Fumihito Arai (1995). “Structure optimization of fuzzy neural network by genetic algorithm.” Fuzzy Sets and Systems, 71, 257-264.
12. Holland, J. H. (1975). Adaptation in natural and artificial systems. University of Michigan Press, Ann Arbor, Mich.
13. Juang, Chia-Feng (2004). “Temporal problems solved by dynamic fuzzy network based on genetic algorithm with variable-length chromosomes.” Fuzzy Sets and Systems, 142, 199-219.
14. Kargupta, Hillol (1996). SERACH, Polynomial Complexity, And The Fast Messy Genetic Algorithm. Illinois Genetic Algorithms Laboratory, University of Illinois At Urbana-Champaign, Urbana, Illinois.
15. Kaming, Peter F., Olomolaiye, Paul O., Holt, Gary D., and Harris, Frank C. (1997). “Factors influencing construction time and cost overruns on high-rise projects in Indonesia.” Construction Management and Economics, 15, 83-94.
16. Khosrowshahi, F. and Kaka, A. P. (1996). “Estimation of Project Total Cost and Duration for Housing Projects in the U.K.” Building and Environment, vol. 31, no. 4, pp. 373-383.
17. Knjazew, Dimitri (2002). OmeGA: a competent genetic algorithm for solving permutation and scheduling problems. Kluwer Academic Publishers, Boston.
18. Ko, C. H. (2002). Evolutionary Fuzzy Neural Inference Model (EFNIM) for Decision-Making in Construction Management. MS Thesis, National Taiwan University of Science and Technology, Taipei, Tawan.
19. Koehn, Philipp (1994). “Combining Genetic Alogrithms and Neural Networks: The Encoding Problem.” MS thesis, The University of Tennessee, Knoxville.
20. Kumaraswamy, Mohan M. and Chan, Daniel W. M. (1995). “Determinants of construciton duration.” Construction Management and Economics, 13, 209-217.
21. Lin, F. J., Fung R. F., and Lin, H. H. (1999). “A supervisory fuzzy neural network controller for slider-crank mechanism.” Proceedings of the 1999 IEEE International Conference on control application, IEEE, Piscataway, New Jersey, 2, 1710-1715.
22. Michaelwicz, Z. (1996). Genetic Algorithms + Data Structures = Evolution Programs. 3rd edition. Springer, New York.
23. Nkado, Raymond N. (1995). “Construction time-influencing factors: the contractor’s perspective.” Construction Management and Economics, 13, 81-89.
24. Skitmore, R. Martin and Ng, S. Thomas (2003). “Forecast models for actual construction time and cost.” Building and Environment, vol. 38, pp. 1075-1083.
25. Warszawski, A. (2003). “Parametric analysis of the financing cost in a building project.” Construction Management and Economics, 21, 447-459.
26. Zadeh, L. A. (1965). “Fuzzy sets.” Information Control, 8, 338-353.
中文部分
27. 林嘉軍，應用快速混亂基因演算法於營建作業流程模擬，碩士論文，朝陽科技大學營建工程系，台中，民國92年。
28. 張德周，契約與規範，文笙書局，民國91年。
29. 葉怡成，類神經網路模式應用與實作，儒林圖書有限公司，台北，民國88年。
30. 謝文魁，建築工程基礎開挖檔土施工策略專家系統之研究，碩士論文，中華工學院土木工程學系營建組，新竹，民國86年。
31. 謝文山，演化式建築工程成本概算模式之研究，碩士論文，國立台灣科技大學營建工程系，台北，民國91年。
32. 蘇木春、張孝得，機器學習：類神經網路、模糊系統以及基因演算法則，全華科技圖書股份有限公司，台北，民國88年。