Yazar "Demirtas, M" seçeneğine göre listele

Listeleniyor 1 - 2 / 2
  • [ X ]
    Öğe
    Optimal tuning of PI speed controller coefficients for electric drives using neural network and genetic algorithms
    (Springer, 2005) Ustun, SV; Demirtas, M
    This paper presents a method of tuning Proportional Integral (PI) controller coefficients in the off-line control of a nonlinear system. In this method, the first step is the identification of the system via Artificial Neural Networks (ANNs), using maximum overshoot and settling time obtained from the application circuit for different K-p-K-i pairs. With this in mind, multi-layer ANN, which uses back-propagation of the error algorithm, was used as the learning algorithm. In the second step, the purpose is to find the optimum controller coefficients using the ANN model as the objective function via Genetic Algorithms (GAs). A Digital Signal Processor (DSP-TMS320C50) was used to carry out control applications. The C++ language was used for ANN and GA, and and the Assembly language was used for the DSP. It is determined that maximum overshoot and settling time are very small if the system is controlled by control parameters obtained from the optimization process that uses GA.
  • [ X ]
    Öğe
    Position control of induction motor a new-bounded fuzzy sliding mode controller
    (Emerald Group Publishing Limited, 2005) Senol, I; Demirtas, M; Rustemov, S; Gumus, B
    Purpose - The aims of the paper are to improve the dynamic response of an induction motor based position servo system and to remove the chattering problem in the sliding mode control theory by using fuzzy logic principles. The obtained results are also compared with conventional sliding mode controller to show its performance. Design/methodology/approach - The main method used for the research is to form a thin boundary layer neighboring the switching surface by using fuzzy logic. The sliding mode control law is inherently discontinuous naturally. Therefore, there are some difficulties such as so many switches occurring between the control bounds, which cannot be carried out by real controllers. Therefore, fuzzy logic is used in the thin boundary layer to determine the control signal current. Thus, the chattering is eliminated. Findings - The results show that the designed controller has superior performance. But, there are also some difficulties. It is difficult to obtain fuzzy rules. The rules can be obtained by using genetic algorithms without expert's knowledge. However, sliding surface slope C can be optimized to increase system's dynamic performance. Originality/value - A new boundary layer consisting of the fuzzy rules in the sliding mode control is formed.