Development of a New Controller to Optimize Operation of a 500 Watt, Half-Bridge DC-DC Converter

سال انتشار: 1390
نوع سند: مقاله کنفرانسی
زبان: انگلیسی
مشاهده: 1,245

فایل این مقاله در 6 صفحه با فرمت PDF قابل دریافت می باشد

استخراج به نرم افزارهای پژوهشی:

لینک ثابت به این مقاله:

شناسه ملی سند علمی:

PEDSTC03_035

تاریخ نمایه سازی: 25 شهریور 1392

چکیده مقاله:

This paper presents the simulation, design methodology and implementation of a Half Bridge DC-DC Converter using an optimized multi-layer feed-forwardArtificial Neural Network (ANN). The ANN controller provides an appropriate control signal to keep the output voltage of the converter stable. It was trained, using backpropagationalgorithm according to an ideal MATLAB SIMULINK model of the converter. The Ideal model is run 'off-line' to generate a record of 'perfect' control signals in response to input and output perturbations. The recorded data then are used as an 'off-line' training set fora Neural Network controller. A network pruning algorithm also is used to reduce the size of controller and an online training process performed to fine-tune thecontroller parameters. Experimental results show that the ANN controller can guarantee an acceptable load and lineregulation and provide improved performances. The proposed controller can be readily expanded to other topologies of DC converters.

نویسندگان

Mohammad Islamic Azad University Fasa branch

Islamic Azad University, Fasa branch

Mohammad Amin Heidari

Islamic Azad University, Fasa branch

Zahra Malekjamshidi

Islamic Azad University, Marvdasht