Wound-rotor induction generator short-circuit fault classification using a new neural network based on digital data

Capocchi, Laurent; Toma, Samuel; Capolino, Gérard‐André; Fnaiech, Farhat; Yazidi, A.

doi:10.1109/demped.2011.6063691

Cited by 14 publications

(6 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The combination of PNN and SFAM don't require structure initialization, however, the back propagation neural network needs to be compiled many times to confirm a structure which can be not optimal. In the literature there are some empirical recommendations to define the structure of the back propagation neural network, however, no mathematical justification was given (Capocchi et al, 2011).…”

Section: Comparison With Some Previous Workmentioning

confidence: 99%

Linear feature selection and classification using PNN and SFAM neural networks for a nearly online diagnosis of bearing naturally progressing degradations

Ali

Saïdi

Mouelhi

et al. 2015

Engineering Applications of Artificial Intelligence

View full text Add to dashboard Cite

In this work, an effort is made to characterize seven bearing states depending on the energy entropy of Intrinsic Mode Functions (IMFs) resulted from the Empirical Modes Decomposition (EMD). Three run-to-failure bearing vibration signals representing different defects either degraded or different failing components (roller, inner race and outer race) with healthy state lead to seven bearing states under study. Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA) are used for feature reduction. Then, six classification scenarios are processed via a Probabilistic Neural Network (PNN) and a Simplified Fuzzy Adaptive resonance theory Map (SFAM) neural network. In other words, the three extracted feature data bases (EMD, PCA and LDA features) are processed firstly with SFAM and secondly with a combination of PNN-SFAM. The computation of classification accuracy and scattering criterion for each scenario shows that the EMD-LDA-PNN-SFAM combination is the suitable strategy for online bearing fault diagnosis. The proposed methodology reveals better generalization capability compared to previous works and it's validated by an online bearing fault diagnosis. The proposed strategy can be applied for the decision making of several assets.

show abstract

Section: Comparison With Some Previous Workmentioning

confidence: 99%

Linear feature selection and classification using PNN and SFAM neural networks for a nearly online diagnosis of bearing naturally progressing degradations

Ali

Saïdi

Mouelhi

et al. 2015

Engineering Applications of Artificial Intelligence

View full text Add to dashboard Cite

show abstract

“…• Based on trial and error tests to find the best configuration for the WRIG fault classification [36], both learning and momentum factors (named N and M) have been chosen respectively at 0.1 and 0.9. • The number of neurons inside the input layer is related to the input data, which gives 2000 neurons for the network without digital compression and 96 neurons when digital compression is applied.…”

Section: Neural Network Simulationmentioning

confidence: 99%

“…After validating the digital pre-processing mode [36], it is very interesting to see the impact of changing the number of digits used to code the analog data extracted from the test bench. All the results presented above have been based on 16-bit analog-to-digital (AD) converter and use an accuracy level of the four digits after the decimal point.…”

Section: Neural Network Simulationmentioning

confidence: 99%

Wound-Rotor Induction Generator Inter-Turn Short-Circuits Diagnosis Using a New Digital Neural Network

Toma

Capocchi

Capolino

2013

IEEE Trans. Ind. Electron.

View full text Add to dashboard Cite

“…Currently, the interest in detecting any failure in rotary machines is remarkable, especially in induction motors [13][14][15][16]. In this type of machines, the detection of broken bars [17][18][19], the detection of rotor asymmetries [20], the detection of rotor fault [21] and inter-turn faults [22], are very active research topics.…”

Section: Introductionmentioning

confidence: 99%

Field-winding fault detection in synchronous machines with static excitation through frequency response analysis

Blánquez

Platero

Rebollo

et al. 2015

International Journal of Electrical Power & Energy Systems

View full text Add to dashboard Cite

a b s t r a c tFrequency Response Analysis is a well-known technique for the diagnosis of power transformers. Currently, this technique is under research for its application in rotary electrical machines. This paper presents significant results on the application of Frequency Response Analysis to fault detection in field winding of synchronous machines with static excitation. First, the influence of the rotor position on the frequency response is evaluated. Secondly, some relevant test results are shown regarding ground fault and inter-turn fault detection in field windings at standstill condition. The influence of the fault resistance value is also taken into account. This paper also studies the applicability of Frequency Response Analysis in fault detection in field windings while rotating. This represents an important feature because some defects only appear with the machine rated speed. Several laboratory test results show the applicability of this fault detection technique in field windings at full speed with no excitation current.

show abstract

Wound-rotor induction generator short-circuit fault classification using a new neural network based on digital data

Cited by 14 publications

References 18 publications

Linear feature selection and classification using PNN and SFAM neural networks for a nearly online diagnosis of bearing naturally progressing degradations

Linear feature selection and classification using PNN and SFAM neural networks for a nearly online diagnosis of bearing naturally progressing degradations

Wound-Rotor Induction Generator Inter-Turn Short-Circuits Diagnosis Using a New Digital Neural Network

Field-winding fault detection in synchronous machines with static excitation through frequency response analysis

Contact Info

Product

Resources

About