Adaptive neuro‐fuzzy inference systems (ANFIS) controller design on single‐phase full‐bridge inverter with a cascade fractional‐order PID voltage controller

Abstract

Adaptive neuro-fuzzy inference system (ANFIS) technique is a significant alternative of research which is structured with a combination of two soft-computing strategies of fuzzy logic and artificial neural network. The design of ANFIS controller for a single-phase fullbridge inverter with pulse width modulation is demonstrated here in the presence of different disturbances. Moreover, an LC filter is designed to decrease the disturbing harmonics which the stability of the filter can be noted as an important issue. Based on the fuzzy C-mean clustering method used for decreasing fuzzy rules, the computational burden has been improved resulting in faster dynamic performance. This method considers the system as a black-box structure which omits the need for an exact model of system and can be an appropriate technique for ill-defined systems. Additionally, to deal with the variations of supply DC voltage, a fractional-order proportional-integral-derivative controller is designed which is tuned by particle swarm optimiser algorithm and can generate a sinusoidal reference for the system input. This double-loop control technique is known as cascade control strategy. It can be seen that ANFIS scheme provides appropriate results with less computational burden and simple structure with optimised responses in challenging conditions. The capability of the proposed method is validated for different operating conditions through simulation and experimental results.This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

Self‐tuning regulator adaptive controller design for DC‐DC boost converter with a novel robust improved identification method

“…Firstly, more accuracy can be reached using a larger limitation for parametric estimation; also, a constant regulation considering the latest variations can be achieved. Equation (13) illustrates this algorithm, so-called the "forgetting factor algorithm" [29].…”

“…Discrete control techniques can perform well based on the switching properties of the Boost converter. The following methods are some of the most popular controllers: Sliding-mode (SM) control [7,8], Model Predictive Control(MPC) [9][10][11], Fuzzybased strategies [12,13], dead beat control [14,15], and Internal Model Control (IMC) [16,17]. The main advantages of Fuzzy and MPC are its robustness in load uncertainty and minimum distortion of the output signal; yet, it suffers from the high computational burden and slow dynamics.…”

Fractional order modelling and robust multi-model intelligent controllers’ synthesis for ACP1000 nuclear power plant

“…In this research work, a Takagi and Sugeno's rule based ANFIS controller is adopted as reference controller known as ANFIS Type-3 controller [16]. ANFIS Type-3 controller is adaptive controller optimized by Fuzzy Clustering Mean (FCM) algorithm that finds the optimal clustering of data.…”

“…Some literature has been reviewed in which Adaptive Neuro-Fuzzy Inference System (ANFIS) has been adopted as controller in [15]. A research has been explored in which ANFIS controller has been used for single phase full bridge inverter in [16]. An investigation has been made in [17] for the optimization of ANFIS controller using ant colony algorithm.…”

Generalised model predictive controller design for A DC–DC non‐inverting buck–boost converter optimised with a novel identification technique

“…Meanwhile, a popularity is growing for the control techniques containing more well-behaved structures, which has led to the digital controllers in switching circuits. Because of the switching properties of buck-boost converters and the non-minimum structure presented by boost typologies, methods such as sliding-mode [10], dead beat [11], and internal model controllers [12,13] are proposed which using an adaptive mechanism. The primary pros of dead beat, internal model, and sliding-mode structures is providing output voltage without overshoot and ringing.…”