10354

9553

كارشناسي ارشد

كنترل

اصفهان: دانشگاه صنعتي اصفهان، دانشكده برق و كامپيوتر

1394

سيزده، 79ص.: مصور، جدول، نمودار

مريم ذكري

فرهاد بهنام فر

1394/05/19

جواد عسگري، فريد شيخ الاسلام

1396/10/03

كتابنامه

برق و كامپيوتر

مهندسي برق و كامپيوتر

ID9553

به فارسي و انگليسي

80 Structural identification using fuzzy modified wavelet neural network Asefeh mardany a mardany@ec iut ac ir Date of Submission May 12 2015 Department of Electrical and Computer Engineering Isfahan University of Technology Degree M Sc Language FarsiSupervisor Maryam zekri mzekri@cc iut ac irAbstract Structural identification is one of the most important issues in structural engineering The goal of structural system identification research is to develop a mathematical modelfor a structural system based on a set of inputs and corresponding output measurements When structures are damaged during a strong ground motion changes occur to theirdynamic characteristics Structural system identification used to determination of structuralproperties such as stiffness natural periods and frequencies and assess damage severity andlocation There are two fundamentally different approaches for the solution of the systemidentification problem parametric method and nonparametric method The dynamic time delay fuzzy wavelet neural network has been applied successfully to structuralidentification In this study a fuzzy modified wavelet neural network with internalfeedback is designed and suggested for using in structural identification The internalfeedback is applied by implementation of feedback in second layer it adds memory to thenetwork and can help improving a dynamic behavior of system and cause to achieve betteraccuracy even with simple network In existing training algorithm such as Levenberg Marquardt the network s parameters are modified based on the human s experiences Inthis study a hybrid learning algorithm modified Levenberg Marquardt least squaresalgorithm is developed for estimating the parameters of the fuzzy WNN model and toimprove the performance of the algorithm a fuzzy inference system is used for adjustingthe training parameter The initialization of parameters of the network is also an importantfactor in training process The initialization of the adjustable parameters of the network hassignificant impact on the convergence Hence in this study a clustering algorithm is usedfor initialization of the translation parameters of the wavelets For initialization of the biasparameters the least square method was used Other parameters initialized randomly Theproposed network was used for identification of five story steel frame that simulated inabaqus with the excitation of luma prieta earthquake and three other earthquakes Theacceleration of these earthquakes obtained from the data based that is available in www peer berkeley edu Keywords Wavelet recurrent wavelet neural network fuzzy logic

مريم ذكري

فرهاد بهنام فر

جواد عسگري، فريد شيخ الاسلام