MS_CMAC neural network learning model in structural engineering

The present American Institute of Steel Construction specifications use the alignment charts and approximate formulas conveniently to determine some c oefficients in design, such as moment gradient coefficient C-b for beams of I-shaped section and effective length factor K of columns. In these method s, the coefficients are unconservative when the boundary conditions are dif ferent from the development of specifications. The governing equations, num erical approaches, on the K and C-b coefficients provide more accurate resu lts. The approaches, however, are not readily available for structural engi neers to use in design. Applying neural network computing toward structural engineering problems has received increasing interest, with particular emp hasis placed on supervised neural networks. The cerebellar model articulati on controller (CMAC), one of the supervised neural network learning models, is mostly used in the domain of control. In this work, we use a newly deve loped Macro Structure CMAC (MS(-)CMAC) neural network learning model to aid steel structure design. The topology of the novel learning model is constr ucted by a number of time inversion CMACs as a tree structure. The learning performance of the MS(-)CMAC is first compared with a stand-alone time inv ersion CMAC using one structural engineering example. That comparison indic ates not only superior prediction-but also fast learning propriety for the MS-CMAC neural network learning model. In addition, the MS-CMAC neural netw ork learning model is applied to two steel design problems. It is shown tha t the MS-CMAC not only can learn structural design problems within a reason able central processing unit time but also can estimate more accurate coeff icients than that estimated through alignment charts and approximate formul as in American Institute of Steel Construction specifications.