Conception of complex probabilistic neural network system for classification of partial discharge patterns using multifarious inputs

Karthikeyan, B.; Gopal, S.; Vimala, M.

doi:10.1016/j.eswa.2005.06.014

Cited by 38 publications

(14 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The pattern layer is the radial basis function layer. Probability density function ( ) k f X adopts the method Parzen found out assessing probability density function from data samples, as in [9]. Only there are enough data samples, it will obtain a smooth and continuous approximate function distribution of original probability density, expression is shown as…”

Section: Braking Behavioral Neural Network Modelmentioning

confidence: 99%

Early Forecast and Recognition of the Driver Emergency Braking Behavior

Xiao

Liu

2009

2009 International Conference on Computational Intelligence and Security

View full text Add to dashboard Cite

The driver emergency braking behavior to be distinguished and predicted exactly was difficult. In order to gain the testing data of driver emergency braking action, 7 professional drivers were selected and 3 scenes of driver braking behavior were designed and simulated by means of road test. And the testing data were captured by the data acquisition system with sensors. Utilizing relative fuzzy membership degrees, the testing data were normalized for the probability neural network (PNN). Under different number of training sample data selected from test data, neural network construction model based on the PNN was built and simulated. Results show that when the number of testing sample data is 260 the hit rate is 95.3 %. And more, the results indicate the validity of fuzzy normalization and PNN with adequate road testing data, consequently, are an effective method for recognition and prediction of the driver emergency braking behavior.

show abstract

Section: Braking Behavioral Neural Network Modelmentioning

confidence: 99%

Early Forecast and Recognition of the Driver Emergency Braking Behavior

Xiao

Liu

2009

2009 International Conference on Computational Intelligence and Security

View full text Add to dashboard Cite

show abstract

“…In this paper, multi-layer neural network is used for identification on MATLAB platform with high-speed mathematical operating capability for numerous data (Candela, Mirelli, & Schifani, 2000;Haykin, 1999;Karthikeyan, Gopal, & Venkatesh, 2006;Karthikeyan, Gopal, & Vimala, 2005;Salama & Bartnikas, 2002). The neural network architecture used here consists of three layers (input, hidden and output layers), while the learning rule is based on the proposed PSO-BP algorithm and the neuron of input and output layer are decided by the users as shown in Fig.…”

Section: Setup Of Artificial Neural Networkmentioning

confidence: 99%

Artificial recognition system for defective types of transformers by acoustic emission

Kuo¹

2009

Expert Systems with Applications

View full text Add to dashboard Cite

“…In order to perform PD classification, it is necessary to choose which discriminatory features to be extracted and which feature extraction method to be used [17]. The purpose of feature extraction is to extract meaningful input feature from the unprocessed PD data to represent the PD pattern associated with a specific defect [18]. These extracted features are used as input of the classifier during the training process.…”

Section: Introductionmentioning

confidence: 99%

Classification of Partial Discharge Measured under Different Levels of Noise Contamination

2017

View full text Add to dashboard Cite

Cable joint insulation breakdown may cause a huge loss to power companies. Therefore, it is vital to diagnose the insulation quality to detect early signs of insulation failure. It is well known that there is a correlation between Partial discharge (PD) and the insulation quality. Although many works have been done on PD pattern recognition, it is usually performed in a noise free environment. Also, works on PD pattern recognition in actual cable joint are less likely to be found in literature. Therefore, in this work, classifications of actual cable joint defect types from partial discharge data contaminated by noise were performed. Five cross-linked polyethylene (XLPE) cable joints with artificially created defects were prepared based on the defects commonly encountered on site. Three different types of input feature were extracted from the PD pattern under artificially created noisy environment. These include statistical features, fractal features and principal component analysis (PCA) features. These input features were used to train the classifiers to classify each PD defect types. Classifications were performed using three different artificial intelligence classifiers, which include Artificial Neural Networks (ANN), Adaptive Neuro-Fuzzy Inference System (ANFIS) and Support Vector Machine (SVM). It was found that the classification accuracy decreases with higher noise level but PCA features used in SVM and ANN showed the strongest tolerance against noise contamination.

show abstract

Conception of complex probabilistic neural network system for classification of partial discharge patterns using multifarious inputs

Cited by 38 publications

References 18 publications

Early Forecast and Recognition of the Driver Emergency Braking Behavior

Early Forecast and Recognition of the Driver Emergency Braking Behavior

Artificial recognition system for defective types of transformers by acoustic emission

Classification of Partial Discharge Measured under Different Levels of Noise Contamination

Contact Info

Product

Resources

About