An improved adaptive RBF neuro‐sliding mode control strategy: Application to a static synchronous series compensator controlled system

Abstract

Summary An improved adaptive neuro‐sliding mode control scheme that incorporated a completely adaptive radial basis function (RBF) neural network into a sliding‐mode controller to approximate the control of a static synchronous series compensator device is presented in this paper. The proposed nonlinear controller does not require the full state of the nonlinear system nor the full knowledge of the bounds of uncertainty, disturbance, and approximation error. It makes use of a reduced number of hidden units, and the weights, centers, and widths are all updated through an on‐line learning mechanism. The effectiveness of the proposed control scheme has been verified on a three‐machine, nine‐bus Institute of Electrical and Electronics Engineers (IEEE) power system with a static synchronous series compensator in MATLAB/Simulink software. The stability of the system and adaptive control laws have been proven using the Lyapunov stability theorem. Simulation results show that the robustness of the proposed controller can satisfactorily alleviate the chattering effects as well as the internal and external perturbations considered.

Challenges and opportunities of FACTS devices interacting with electric vehicles in distribution networks: A technological review

“…This study provides a new mho relay algorithm (MRA) that uses a phasor measurement unit (PMU) to increase distance relay performance in terms of a FACTS device [223]. This study presents an enhanced responsive neuro-sliding mode control technique that incorporates a fully adaptable radial basis function (RBF) NN into a sliding-mode controller to approximate control of an SSSC device [224]. We suggested a new fractional-order resilient attenuation control system for SSSC coupled with an infinite power transmission network in the current research [225].…”

Design of a novel neuro‐adaptive excitation control system for power systems

“…The advantage of neural networks is that, with a suitable number of neural network functions, any (sufficiently smooth) continuous/discontinuous non-linear function can be modelled in a compact set [45]. Intelligent computing techniques are increasingly attracting attention due to the rapid evolution of power systems [35][36][37]. These methodologies have been developed to improve and deal with uncertainties and non-linearities [25][26][27].…”

Rotor Transverse Slots’ Influence on Negative Sequence Loss and Heat Distribution Prediction of Large Generators Based on Improved Radial Basis Function Process Neural Network

“…Liu and Fei presented an adaptive fractional sliding mode control scheme based on dual RBF neural networks (NNs) to enhance the performance of a three-phase shunt active power filter [23]. With continuous improvement and development, the RBF network has been widely used in various applications of the power system [24][25][26][27][28][29][30]. However, the RBF network has certain problems-the network structure, particularly the number of hidden layer nodes, is difficult to determine and the training process easily falls into the local minima that affects its practical application [31][32][33][34][35][36][37].…”