Radial-Basis-Function-Based Neural Network for Harmonic Detection

Chang, G.W.; Chen, Cheng-I; Teng, Yu-Feng

doi:10.1109/tie.2009.2034681

Cited by 169 publications

(79 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…An RBF approach has been proposed for the harmonic amplitudes detection of a signal in Ref. [22]. The RBF is able to approximate the mapping between the sample signal and the amplitude and the phase angle of each harmonic component.…”

Section: Neural Network Methods For Harmonic Identificationmentioning

confidence: 99%

Current Harmonic Estimation in Power Transmission Lines Using Multi-layer Perceptron Learning Strategies

Wira¹,

Nguyen²

2017

JEE

View full text Add to dashboard Cite

This main contribution of this work is to propose a new approach based on a structure of MLPs (multi-layer perceptrons) for identifying current harmonics in low power distribution systems. In this approach, MLPs are proposed and trained with signal sets that are generated from real harmonic waveforms. After training, each trained MLP is able to identify the two coefficients of each harmonic term of the input signal. The effectiveness of the new approach is evaluated by two experiments and is also compared to another recent MLP method. Experimental results show that the proposed MLPs approach enables to identify effectively the amplitudes of harmonic terms from the signals under noisy condition. The new approach can be applied in harmonic compensation strategies with an active power filter to ensure power quality issues in electrical power systems.

show abstract

Section: Neural Network Methods For Harmonic Identificationmentioning

confidence: 99%

Current Harmonic Estimation in Power Transmission Lines Using Multi-layer Perceptron Learning Strategies

Wira¹,

Nguyen²

2017

JEE

View full text Add to dashboard Cite

show abstract

“…However, ADALINE network is limited to only one output neuron. The convergence of ADALINE slows as the number of harmonics included increases and it is also subjected to fall in local minima [28,29,30].…”

Section: State Of Artmentioning

confidence: 99%

A Brief Review on Advances of Harmonic State Estimation Techniques in Power Systems

Arumugam¹

2011

IJIEE

View full text Add to dashboard Cite

Abstract-As the demand for power increases, the need for harmonic state estimation (HSE) has been increasing as well. Harmonics, injected by the non-linear equipments along the distribution networks, causes several power quality issues. Therefore, HSE plays an important role in harmonics monitoring and control. Various HSE techniques and algorithms have been developed since 1989, which would be reviewed and discussed in this paper. The author outlines the role of artificial intelligence (AI) in the field and the process overview of neural network and also a hybrid algorithm which combines particle swarm optimization (PSO) and gradient descent (GD) to train the weights of neural network (NN).

show abstract

“…Some other intelligent harmonics extraction algorithms, such as fuzzy control [12], adaptive [13], [14], neural network [15]- [18] and phase-lock-loop (PLL) [19]- [21] based algorithms, also provide nice performances. However, their complexity is still a barrier for practical applications.…”

Section: Introductionmentioning

confidence: 99%

A Single-phase Harmonics Extraction Algorithm Based on the Principle of Trigonometric Orthogonal Functions

Hao¹,

Zhuo²,

Wang³

et al. 2017

Journal of Power Electronics

View full text Add to dashboard Cite

For a single-phase active power filter (APF), designing a more efficient algorithm to guarantee accurate and fast harmonics extraction with a lower computing cost is still a meaningful topic. The common idea still employs a IRPT-based Park transform, which was originally designed for 3-phase applications. Therefore, an additional virtual signal generation (VSG) link is necessary when it is used in the single-phase condition. This method, with virtual signal generation and transform, is obviously not the most efficient one. Regarding this problem, this paper proposes a novel harmonics extraction algorithm to further improve efficiency. The new algorithm is based on the principle of trigonometric orthogonal functions (TOF), and its mathematical principle and physical meaning are introduced in detail. Its implementation and superiority in terms of computation efficiency are analyzed by comparing it with conventional methods. Finally, its effectiveness is well validated through detailed simulations and laboratory experiments.

show abstract

Radial-Basis-Function-Based Neural Network for Harmonic Detection

Cited by 169 publications

References 21 publications

Current Harmonic Estimation in Power Transmission Lines Using Multi-layer Perceptron Learning Strategies

Current Harmonic Estimation in Power Transmission Lines Using Multi-layer Perceptron Learning Strategies

A Brief Review on Advances of Harmonic State Estimation Techniques in Power Systems

A Single-phase Harmonics Extraction Algorithm Based on the Principle of Trigonometric Orthogonal Functions

Contact Info

Product

Resources

About