Abstract: Neural networks are simply known as the biological nervous system. An Artificial Network (ANN) is an information processing system that is inspired by the way biological Nervous System, such as the brain, process information. The key element of ANN is the novel structure of the information processing system. It is composed of a large number of highly interconnected processing elements (neurons) working in unison to solve specific problems. ANNs, like people learn by example. They can be trained with a known example of a problem. Once trained, the network can be put to use in solving unknown and untrained problems. An ANN is configured for a specific application , such as pattern recognition or data classification, through a learning process. Learning in biological system involves adjustment to the synaptic connection that exist between the neurons. This examines the efficiency of neural networks. Taking into consideration type of ANNs such as Generalized Regression (GR) neural network. Radial Basis Function (RBF) neural networks, Linear Layer (LL) neural network efficiency of ANNs is checked in the design of trusses. The neural networking tool available in MATLAB is used. To train ANNs, various input and output data are provided using an analysis and design package STAAD PRO. The ANNs are trained with some values and are tested for both interpolation and extrapolation Then percentage error is calculated in all three ANN. Based on percentage error, the efficiency of each ANNs is compared in the design of trusses. The study is made by increasing the number of training, by increasing the number of input and output variables, by training in the matrix form, etc. From these results the suitability of each ANN is studied and conclusions are drawn.

Keywords: Neural networks, Truss, General Regression Neural Network, Generalized Regression

PDF | DOI: 10.17148/IJARCCE.2022.11730

Open chat
Chat with IJARCCE