The present paper presented the training or learning algorithms in telecommunication towers based on\r\nthe artificial neural networks to calculate accurately their natural frequency in different supporting\r\nconditions. Using SAP2000 program, the real frequency is calculated and is defined as a goal function\r\nfor neural network, so that all outputs of the network can be compared to this function and the error can\r\nbe calculated. The inputs including dimensions or specifications of telecommunication towers are made\r\nin MATLAB environment. According to the presented results, the performance of the neural network is\r\noptimum, and the errors are less than 6%, so the network can perform training in different manner.\r\nFurthermore, compare with analysis time of SAP2000 software, the time of frequency calculations in\r\nneural network is very low the precision of 9% is recorded.
Loading....