01985nas|a2200253 i 450000500170000000800410001703500150005810000300007324500880010326000520019130000220024349000270026550200580029250001350035052008410048565000390132665000290136570000410139470000460143570000520148171000740153381000590160785600650166620260817162834.0121099s1999    th  uzm rtt  00|  a1eng d  a.b117632800 aRattapoohm Parichatprecha10aApplication of artificial neural networks in preliminary design of 2-D steel frames  aBangkok :bAsian Institute of Technology,c1999  a63 leaves :bill.1 aThesis ;vno. ST-99-19  aThesis (M.Eng.) - Asian Institute of Technology, 1999  aA thesis submitted in partial fulfillment of the requirement for the degree of Master of Engineering,  School of Civil Engineering  aThis 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. 0aNeural networks (Computer science) 0aSteel framing (Building)0 aWorsak Kanok-Nukulchai,eChairperson0 aPruettha Nanakorn,eExamination committee1 aWijeyewickrema, Anil C.,eExamination committee2 aAsian Institute of Technology Partial Scholarship,eScholarship donor2 aAsian Institute of Technology.tThesis ;vno. ST-99-19  3Full-Textuhttp://203.159.5.9/ait-thesis/detail.php?q=B12773