Purpose -The paper aims to propose an adaptive and robust on-line trained neuro-fuzzy current controller based on indirect field oriented control (IFOC) for the current control of multilevel inverter fed induction motor (IM). Design/methodology/approach -Torque current of IM is controlled with Sugeno type neuro-fuzzy controller (NFC) which has the ability of self tuning against parameter variations and load disturbance. Input variables of the neuro-fuzzy current controller are chosen error and integral of error in order to eliminate steady state error. The consequent parameters of neuro-fuzzy current controller are trained on-line through backpropagation learning algorithm. Findings -The validity of proposed current control algorithm is shown with experimental results carried out under different speed commands, parameter variations and load disturbances. The experimental results show that control performance of NFC in the current control of IMs is satisfactory because of its adaptive and robust structure. Originality/value -This paper presents the design of an on-line trained neuro-fuzzy current control to improve the current control performance. The performance of the current controller largely depends on using converter systems. In this study, a multilevel inverter is used to obtain less harmonic distortion and near sinusoidal form of output voltage and current waveforms of the converter.

No abstract

Abstract:Monitoring Power Quality Events (PQE) is a crucial task for sustainable and resilient smart grid. This paper proposes a fast and accurate algorithm for monitoring PQEs from a pattern recognition perspective. The proposed method consists of two stages: feature extraction (FE) and decision-making. In the first phase, this paper focuses on utilizing a histogram based method that can detect the majority of PQE classes while combining it with a Discrete Wavelet Transform (DWT) based technique that uses a multi-resolution analysis to boost its performance. In the decision stage, Extreme Learning Machine (ELM) classifies the PQE dataset, resulting in high detection performance. A real-world like PQE database is used for a thorough test performance analysis. Results of the study show that the proposed intelligent pattern recognition system makes the classification task accurately. For validation and comparison purposes, a classic neural network based classifier is applied.

No abstract

No abstract