پيشنهاد يك شبكه عصبي موجك فازي نوع-2 و الگوريتم تركيبي جهت تشخيص عيب سيستم سه تانك

چكيده انگليسي :

Proposing a type 2 fuzzy wavelet neural network and a hybrid algorithm for fault diagnosis of the three tanks system Vahid Safari Dehnavi v safari@ec iut ac ir September 15 2019 Department of Electrical and Computer Engineering Isfahan University of Technology Isfahan 84156 83111 Iran Degree M Sc Language Farsi Supervisors Assoc Prof Maryam Zekri mzekri@cc iut ac ir Abstract Fault occurrence in systems causes loss of life and financial damage therefore diagnosing a fault occurrence inthe shortest time decreases this damage The persistence of the fault existence for a long time in the system causes damage so it is essential to supervise the system to diagnose faults in the shortest time Intelligent networks can diagnose the faultfaster and more accurate than humans so different kinds of intelligent networks can be used to diagnose the fault Oneof the common networks for the fault diagnosis is the neural network which has appropriate adaptation however it is notappropriate because of constrains on the results interpretation The fuzzy logic is one of the other methods which is usedfor diagnosing the fault and has appropriate interpretation however it does not have appropriate adaptation unlike neuralnetworks So the combination of the neural network and the fuzzy logic can resolve the constrains The type 1 neuro fuzzymakes by the combination of fuzzy logic and neural network The analysis functions in the conclusion part are used inthe type 1 neuro fuzzy In this study in the conclusion the wavelet functions which show the conception of the type 1fuzzy wavelet neural network have been used to improve the network efficiency and decrease the numbers of rules in thetype 1 neuro fuzzy Also available data for the fault diagnosis is with noise that decrease the accuracy of the fault diagnosisnetworks The fuzzy function is not appropriate in the noisy situations and does not have acceptable accuracy So thetype 2 fuzzy was used in this research The use of the type 2 fuzzy decreases the noise effect and uncertainty in the faultdiagnosis networks According to the mentioned information in this study the structure of a type 2 fuzzy wavelet neuralnetwork has been proposed with an appropriate combination algorithm In this algorithm three algorithms were used thek means cluster algorithm to initialize nonlinear parameters the least square algorithm to initialize the linear parameters and the recursive least square method with the adaptive forgetting parameter to update linear parameters Also to updatethe nonlinear algorithms back propagation with the adaptive momentum parameter was used to accelerate convergenceand the learning amount that guarantee convergence In this study convergence and stability of the proposed combinationalgorithm were proved and to show the ability of the network and algorithm examples of the classification approximationof the functions and the time series prediction were considered Therefore the fault diagnosis of the three tanks system wasconsidered that in this system the type 2 fuzzy wavelet neural network was used to diagnose the system fault In this study the diagnosis of the leakage fault of the tanks the partial obstruction of the communication channel between tanks wereconsidered Then the advantages of the proposed method in relation to other former methods were shown Key Words Fault diagnosis Three tank system Type 2 fuzzy wavelet neural network

صفري دهنوي، وحيد

پيشنهاد يك شبكه عصبي موجك فازي نوع-2 و الگوريتم تركيبي جهت تشخيص عيب سيستم سه تانك

تشخيص عيب , سيستم سه تانك , شبكه عصبي موجك فازي نوع-2