Frame Optimization using Neural Network

The development of Neural-network (NN) technology stemmed from the desire to create an artificial system that could perform “intelligent” tasks similar to those performed by the human brain. In this paper the performance of NN to the structural optimization concept of frame structure is presented. The optimum set of frame designs is obtained using Finite Element (FE) software where stress and displacement constraints has been chosen as the optimum criteria. The optimized data then used to train the NN through Back Propagation Neural-network technique (BPNN) to identify the capability of this strategy to predict the exact data. Three case studies were performed with different complexity of structural configuration. Result indicates the Neural-network capable of predicting the exact solution with proper training but this ability depends on the complexity of the frame structural optimization itself