A new neural network and an ANFIS network based hysteresis modeling approach based on Preisach model
Publish place: 1st National Conference on Development of Civil Engineering, Architecure,Electricity and Mechanical in Iran
Publish Year: 1393
نوع سند: مقاله کنفرانسی
زبان: English
View: 1,137
This Paper With 12 Page And PDF Format Ready To Download
- Certificate
- من نویسنده این مقاله هستم
این Paper در بخشهای موضوعی زیر دسته بندی شده است:
استخراج به نرم افزارهای پژوهشی:
شناسه ملی سند علمی:
DCEAEM01_206
تاریخ نمایه سازی: 18 دی 1393
Abstract:
One of the main issues in modeling the behavior of electric machineries is the process of modeling the magnetic material used in such machineries. Almost all ferromagnetic materials display a set of behaviors which are known under the term of magnetic hysteresis. Models which are proposed for the hysteresis phenomenon based onthe physical behavior of ferromagnetic materials, such as Preisach, is so complicated which require large computerstorage and also consume a lot of time for calculation. Therefore, artificial neural networks and combination of fuzzy logic with neural networks could be considered as suitable alternatives since along with featuring a high accuracy, they are fast and require less computer storage. Using multi-layer feed-forward neural networks and anAdaptive Neuro Fuzzy Inference System (ANFIS) network in the following paper, a model for magnetic hysteresis is proposed which could model all internal loops along with the main hysteresis loop. Results to the simulation suggest a good agreement between the aforementioned model and accurate model of Preisach
Keywords:
Hysteresis identification , preisach model , neural network , perception , radial basis function (RBF) , fuzzy logic , ANFIS , Adaptive Neuro Fuzzy Interference
Authors
Behroz Safarinejadian
Shiraz University of Technology
Alireza roosta
Shiraz University of Technology
Alireza Soltanimehr
Shiraz University of Technology