The efficiency of the low-cost renewable energy source i.e. solar is very poor due to inadequate extraction of maximum power. By employing the proper maximum power point tracking algorithm, the efficiency can be increased. An innovative adaptive backstepping neural network controller is proposed in this paper to extract the maximum power from the solar panels by tracking the desired photovoltaic array voltage in real-time. The maximum power is extracted indirectly by tuning the PV voltage to the desired PV voltage where the maximum power is attained at the desired PV voltage point. The desired photovoltaic array voltage is obtained from the linear regression method. The change in photovoltaic current caused by varying irradiance and temperature is approximated using the Chebyshev polynomials. The quicker steady-state and transient responses are accomplished and the computational burden of the photovoltaic system control law is reduced because of the orthogonal property of Chebyshev polynomials. The asymptotically stable system is obtained by tuning the weights of the neurons in accordance with the Lyapunov stability analysis. Also, Lyapunov control function of the backstepping control design procedure finds a control law by an innovative cubic equation interpretation, instead of resolving the first derivative of the control law, that diminishes the ripples in the duty cycle to make its appropriateness in real-time. A prototype is developed to validate the robustness of this controller in maximum power extraction at a faster time and the results confirm that adaptive backstepping neural network controller surpasses the performances of conventional backstepping controller and constant voltage PID controller.
Summary
An indirect approach is employed to track the desired output voltage of the boost converter by controlling the inductor current in the proposed adaptive backstepping Chebyshev neural network controller, because of the non‐minimum phase nature of the converter. The computational complexity of the neural network is avoided by the use of Chebyshev polynomials as the basis function. The online weight update of the Chebyshev neural network is designed for the closed‐loop system based on the Lyapunov stability analysis to obtain an asymptotically stable system. In the proposed work, the required duty cycle is obtained by a novel method of solving the quadratic equation of the control function instead of the first derivative of the duty cycle to get the desired output voltage from the Lyapunov control function. Detailed analyses of simulations are carried out for a wide range of variations in the set point and load, and the results are compared with that of backstepping and PID controllers. The proposed controller exhibits superior performance than other controllers for the uncertainties caused by disturbances. To ensure its suitability in real time, a prototype is designed for the proposed controller, and the obtained results are compared with that of backstepping and PID controllers. Investigation of experimental results confirms the adaptability of the proposed control scheme as it exhibits accurate and fast response irrespective of disturbances acting upon it.
A low‐cost battery‐less solar‐powered PMDC motor using an adaptive backstepping Chebyshev neural network controller to track the desired speed for any change in irradiance and load torque is proposed in this paper. The neural network is used for approximating the variable load torque because of its approximation property. The computational burden of the control law is reduced because of the orthogonal property of Chebyshev polynomials. The asymptotically stable system is obtained by tuning the weights of neurons in accordance with the Lyapunov stability analysis. From the Lyapunov control function of backstepping control design procedure, the control law is obtained by an innovative way of elucidating the cubic equation, in place of resolving the derivative of the control law in the control function. This approach eliminates the constraints caused by the non‐strict feedback system for the backstepping control approach and also this reduces ripples in the duty cycle which makes its appropriateness in real‐time. To ensure its robustness in tracking the desired speed at a faster time and minimum overshoot, simulations are done for an extensive range of variations in irradiance and load torque, and the obtained results are assessed by comparing it with the PID controller and conventional backstepping controller. Because of the use of neural network the robustness of the proposed controller is ensured with enhanced transient and steady state responses. A prototype is developed in the laboratory and the obtained results are assessed by comparing it with the backstepping controller and PID controller.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.