傳統上群樁基礎均採用試誤法的程序來設計，雖能符合規範中強度與位移上的要求，卻無法保證造價的經濟性。本研究的目的便是利用遺傳演算法則來進行預鑄混凝土群樁基礎的低價化設計。
本文的目標函數是群樁基礎之總造價，包含土方開挖費用、樁帽費用和基樁費用等三部分；其設計主要包括樁徑、樁數、樁長、基樁間距和樁帽的尺寸，且均視為離散變數來處理。而預鑄混凝土基樁的尺寸，則由國內廠商已生產之尺寸所建立的資料庫來選取。
群樁基礎之強度與位移束制條件是參考國內建築物基礎構造設計規範來建立，包括基樁間距、穿孔剪力、撓曲剪力、樁頭位移、基樁承載力、樁帽的尺寸等。
遺傳演算法則的效率將透過數個設計例來說明，而影響群樁基礎造價的主要設計參數，亦將透過數值演算結果來探討，以供工程設計之參考。

Conventional design of pile groups is based on the trial-and-error procedures. Although the design results can satisfy strength and displacement requirements that stipulated in code provisions, it is not a minimum cost design. The purpose of this study is to apply the genetic algorithm (GA) for searching the minimum cost design of precast concrete pile groups.
The objective function of the problem is the total cost of the foundation, including the costs of soil excavation, cap and piles. The design variables are pile diameter, pile nummers, pile length, pile spacing , and dimensions of cap, which are all considered as discrete design variables. The size of precast concrete piles is selected from the available sections in the engineering market.
The strength and displacement constraints for the minimum cost design of pile groups are formulated according to the foundation design code provisions of Taiwan. Size constrains, such as the spacing of piles, punching shear, bending shears, and dimensions of the pile cap are also considered in the formulation.
The application of GA to the minimum cost design of pile groups is shown by a number of design examples. The efficiency of GA and sensitivity analyses of design variables on the cost of pile groups are also discussed.

參 考 文 獻
(1) Cheng, F.Y. and Juang, D.S., “Recursive Optimization for Seismic Steel Frames,” J. of Structural Engineering, ASCE, Vol.115, No.2, 1989.
(2) Chow, Y.K. and Thevendran, V, “Optimization of Pile Groups,” Comput. Geotech. 4, pp.43-58, 1987.
(3) Hobak, A.S., and Truman, K.Z., “Least Weight Design of Steel Pile Foundations,” Engng. Struct., 15(5), pp.379-385, 1993.
(4) Thanedar, P.B. and Vanderplaats, G.N., “Survey of Discrete Variable Optimization For Structural Design,” J. of Structural Engineering, ASCE, Vol 121, No.2, pp.301-306, 1995.
(5) Sandgren, E., “Nonlinear Integer and Discrete Programming in Mechanical Design Optimization,” ASME, J. of Mech. Des., 112(2), pp.223-229, 1990.
(6) Tseng, C.H., Wang, L.W., and Ling, S.F., “A Numerical Study of the Branch and Bound Method in Structural Optimization,” Tech. Rep., Department of Mechanical Engineering, National Chiao Tung University, Hsinchu, Taiwan, 1992.
(7) Olsen, G., and Vanderplaats, G.N., “A Method for Nonlinear Optimization with Discrete Variables,” AIAA J., Vol 27(11), pp.1584-1589, 1989.
(8) Zhu, D.M., “An Improved Templeman’s Algorithm for Optimum Design of Trusses with Discrete Member Sizes,” Engng. Optim., pp.303-312, 1986.
(9) 莊德興、吳朗益，「群樁基礎之離散最佳化設計」，第25屆力學研討會，台中市，2001.
(10) Holland, J.H., “Adaptation in Natural and Artificial Systems, ” Ann Arbor,The University of Michigan Press, 1975.
(11) Goldberg, D.E., Genetic Algorithms in Search, Optimization and Machine Learning, Addisson-Wesley, MA, 1989.
(12) Hayalioglu, M.S., “Optimum Design of Geometrically Non-linear Elastic-Plastic Steel Frames via Genetic Algorithm,” Comput. Struct., Vol. 77, pp.527-538, 2000.
(13) Leite, J.P.B, and Topping, B.H.V, “Improved Genetic Operators for Structural Engineering Optimization,” In Developments in Neural Networks and Evolutionary Computing for Civil and Structural Engineering. Edited by Topping B.H.V, Edinburgh, Civil-Comp Press, pp143-169, 1995.
(14) Rajeev, S., and Krishnamoorthy, C.S., “Discrete Optimization of Structures Using Genetic Algorithms”, J. Struct. Engrg., ASCE, Vol 118, pp1233-1250, 1992
(15) Yotota, T., Gen, M., and Li, Y.X., “Genetic Algorithm for Nonlinear Mixed Integer Programming Problems and Its Applications,” Int’l J. of Comp. and Indust. Eng., 30(4), 1994.
(16) Jeffrey A.J., and Christopher R.H., “On the Use of Non-Stationary Penalty Functions to Solve Nonlinear Constrained Optimization Programs with GA’s,” Department of Industrial Engineering North Carolina University,NC 27695-7906,1985
(17) Coello, C.A., and Christriansen, A.D., “Multiobjective Optimization of Truss using Genetic Algorithms,” Computers and Structures, Vol. 77, pp647-660, 2000.
(18) Adeli, H., and Cheng, N.T., “Augmented Lagrangian Genetic Algorithm for Structural Optimization,” J.Archit.Engrg.,Vol. 7 ,No. 1 ,January, pp.104-118,1994
(19) 大地工程學會，「建築物基礎構造設計規範」，民國90年12月。
(20) Wu, S.j., and Chow, P.T., ”The Applications of Genetic Algorithms to Discrete Optimization Problems,” Journal of the Chinese Society of Mechanical Engineers, Vol.16, No.6, pp.587-598,1995
(21) Gen, M., and Cheng, R., “A Survey of Penalty Techniques in Genetic Algorithms”, Proceedings of the IEEE Conference on Evolutionary Computation, pp.804-809, 1996.
(22) 中國土木水利工程學會，「混凝土工程設計規範與解說-土木401-86」，1998
(23) Chang, Y.L., Discussion on “Lateral Pile-Loading Tests” by L.B. Feagin,Trans, ASCE ,Vol.102, pp.272~278, 1937.
(24) 日本道路協會，「道路橋示方書‧同解說」，1996。
(25) Meyerhof, G.G., “Bearing Capacity and Settlement of Pile Foundation”, J. of Geotech. Eng. Div., ASCE, Vol.102, No. GT3, pp. 195-227, 1976.
(26) 台灣營建研究院，「營建物價」，2001
(27) 振農水泥製品公司，「預力基樁產品規格」，2001
(28) 吳明賢，「應用遺傳演算法於群樁基礎低價化設計」，碩士論文，國立中央大學土木系，2001