Rattapoohm Parichatprecha creator Worsak Kanok-Nukulchai Chairperson Pruettha Nanakorn Examination committee Wijeyewickrema, Anil C. Examination committee Asian Institute of Technology Partial Scholarship Scholarship donor text series technical report th Bangkok Asian Institute of Technology 1999 continuing eng 63 leaves : ill. This study deals with the application of artificial neural networks in the preliminary design of 2-D steel frames. The preliminary design model is very importance in the synthesis of a finally acceptable solution in design problems. The preliminary process is extremely difficult to computerize because it requires engineering experiences and human intuition. Development of a network for preliminary design process has been reported. The simple characteristics of structural members (Moment, Shear force, Axial force, Length of each member, and type of member) were selected as the input data to the neural network to generate the sufficient areas of each member. Various considerations and the steps in the development of the neural network for preliminary design are illustrated with an example of optimal design of 2-D steel frames. A thesis submitted in partial fulfillment of the requirement for the degree of Master of Engineering, School of Civil Engineering Thesis (M.Eng.) - Asian Institute of Technology, 1999 Neural networks (Computer science) Steel framing (Building) Asian Institute of Technology. http://203.159.5.9/ait-thesis/detail.php?q=B12773 http://203.159.5.9/ait-thesis/detail.php?q=B12773 121099 20260817162834.0