Modular Neural Network Architecture for Precise Condition Monitoring

Marzi, Hosein

doi:10.1109/tim.2007.909411

Cited by 13 publications

(6 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…3. MNN process has been widely used in applications to discriminate the direction of faults for transmission line protection [18], for pattern recognition [19], recognition of partial discharge sources [20], condition monitoring of industrial machines [21]. Advantage of modular structure is that individual model responds to a given input faster than a complex monolithic system.…”

Section: Modular Neural Networkmentioning

confidence: 99%

Classification of voltage sag, swell and harmonics using S-transform based modular neural network

Venkatesh

Sarma

Sydulu

2010

Proceedings of 14th International Conference on Harmonics and Quality of Power - ICHQP 2010

View full text Add to dashboard Cite

This paper presents classification and characterization of typical voltage disturbances-sag, swell, interruption and harmonics employing S-transform analysis combined with modular neural network. S-transform is used to extract various features of disturbance signal as it has excellent time-frequency resolution characteristics and ability to detect disturbance correctly even in the presence of noise. Classification is performed using modular neural network with features extracted from S-transform. Modular neural network is designed by modifying the structure of traditional multilayer network into modules for each disturbance to provide less training period and better classification. Disturbances are characterized by magnitude and phase information using S-transform analysis. Simulation and experimental results show that S-transform combined with Modular neural network can effectively detect, classify and characterize the disturbances.

show abstract

Section: Modular Neural Networkmentioning

confidence: 99%

Classification of voltage sag, swell and harmonics using S-transform based modular neural network

Venkatesh

Sarma

Sydulu

2010

Proceedings of 14th International Conference on Harmonics and Quality of Power - ICHQP 2010

View full text Add to dashboard Cite

show abstract

“…ANNs usually learn from examples -Supervised Learning (Khoshgoftaar et al, 2010). In contrast to FSs, ANNs have learning and generalization capacities, thus they exhibit robust performance in the presence of disturbances (Marzi, 2006(Marzi, , 2008a.…”

Section: Introductionmentioning

confidence: 99%

Training ANFIS Using the Enhanced Bees Algorithm and Least Squares Estimation

Marzi

Darwish

Helfawi

2016

Intelligent Automation & Soft Computing

View full text Add to dashboard Cite

This paper presents the result of research in developing a novel training model for Adaptive NeuroFuzzy Inference Systems (ANFIS). ANFIS integrates the learning ability of Artificial Neural Networks with the Takagi-Sugeno Fuzzy Inference System to approximate nonlinear functions. Therefore, it is considered as a Universal Estimator. The original algorithm used in ANFIS training process has a hybrid model that uses Steepest Decent Derivative; therefore, it inherits low convergence rate and local minima during training. In this study, a training algorithm is proposed that combines Bees Algorithm (BA) and Least Square Estimation (LSE) (BA-LSE). The local and global exploration of BA as integrates with the best-fit solution of the LSE improves current shortcomings of ANFIS training process. The proposed training algorithm is examined under three different scenarios of function approximation, time series prediction, and classification experiments in order to verify the promising improvements in the training process of ANFIS. The experimental results validate high generalization capabilities of the BA-LSE training algorithm in comparison to the original hybrid training model of ANFIS. The new training model also enhances local minima avoidance and has high convergence rate.

show abstract

“…M. Magalhaes et al, 2008) approach designed by modifying the structure of multilayer neural network. MNN process has been widely used to discriminate direction of faults for transmission line protection (Lahiri et al, 2005), for pattern recognition (Melin et al, 2005), recognition of partial discharge sources (Hong et al, 1996), condition monitoring of industrial machines (Marzi, 2008). Combined wavelet transform and MNN classifier is used for automatic classification of voltage disturbances such as sag, swell, interruption and harmonics.…”

Section: Introductionmentioning

confidence: 99%

Wavelet feature-based modular neural network for detection and classification of power quality disturbances

Venkatesh¹,

Sarma

Sydulu

2013

IJPELEC

View full text Add to dashboard Cite

Disturbances such as voltage sag, swell, interruption and harmonics are very typical in a power system. Power quality monitoring should be capable of identifying these disturbances to initiate mitigation action and protect sensitive loads. This paper presents wavelet-neural network-based detection and classification of power quality disturbances. Wavelet transform has the ability to analyse signals simultaneously in both time and frequency domains and is used to extract features of the disturbances by decomposing the signal using multi resolution analysis. These features, used to detect and localise the disturbances and are not easily separable, will reduce the performance of multilayer neural network. Improvement in the classification accuracy is suggested by employing modular neural network obtained by dividing a complex task into easier subtasks. The algorithm proposed is tested for classification of various power quality disturbances and it is found that a modular neural network has a higher classification accuracy over traditional multilayer neural network.

show abstract

Modular Neural Network Architecture for Precise Condition Monitoring

Cited by 13 publications

References 20 publications

Classification of voltage sag, swell and harmonics using S-transform based modular neural network

Classification of voltage sag, swell and harmonics using S-transform based modular neural network

Training ANFIS Using the Enhanced Bees Algorithm and Least Squares Estimation

Wavelet feature-based modular neural network for detection and classification of power quality disturbances

Contact Info

Product

Resources

About