Artificial Neural Networks In Calculation Of Transmission Towers Natural Frequency

In this paper, trainig or learning algorithms in transmission towers based on the artificial neural networks are presented to calculate accurately their natural frequency in diffrent supporting conditions. Artificial neural networks are developed from neurophysiology by morphologically and computationally mimiking human brains. One of the most important training and learnig algorithm is back propagation algorithm which is a systematic method for training multi layer artificial network. It is based on gradient descant which means that it moves downward on the error declination and regulates the weights for the minimum error. In this research, using SAP۲۰۰۰ program, the real frequency is calculated and is defined as a goal function for neural network, so that all outputs of the network can be compared to this function and the error can be calculated. After that, a set of inputs including dimensions or specifications of transmission towers are made in MATLAB environment. After the determination of algorithm and quantification of the network, the phases of training and testing of the results are carried out and the output of the network is created. According to resuls,It is concluded that the performance of the neural network is optimum, and the errors are less than ۶%, so the network can perform training in different manner. Furthermore, compare with analysis time of SAP۲۰۰۰ software, the time of frequency calculations in neural network is very low and it’s precision is acceptable(less than ۹%).

کلیدواژه ها:

frequency ، artificial intelligence ، transmission towers ، excitement functions ، training functions ، learning functions.