Turn to Turn Fault Diagnosis for Induction Machines Based on Wavelet Transformation and BP Neural Network

2011-09-10
Najafi, Atabak
Iskender, Iris
Farhadi, Pavam
Najafi, Babak
Based upon Wavelet Transformation analysis and BP neural network, a method for the fault diagnosis of stator winding is proposed in this paper. Firstly wavelet transformation was used to decompose vibration time signal of stator to extract the characteristic values - wavelet transformation energy, and features were input in to the BP NN. After training the BP NN could be used to identify the stator winding fault (Turn to Turn fault) patterns. Three typical turn to turn faults as 10 turn, 20 turn and 35 turn were studied. The result showed that the method of BP NN with wavelet transformation could not only detect the exiting of the fault in stator winding, but also effectively identify the fault patterns.

Suggestions

Multielectrode venous catheter mapping as a high quality constraint for electrocardiographic inverse solution
Serinağaoğlu Doğrusöz, Yeşim; YILMAZ, BÜLENT; Brooks, DH (Elsevier BV, 2002-01-01)
A persistent challenge in solving inverse problems in electrocardiography is the application of suitable constraints to the calculation of cardiac sources. Whether one formulates the inverse problem in terms of epicardial potentials or activation wavefronts, the problem is physically ill-posed and hence results in numerically unstable computations. Suitable physiological constraints applied with appropriate weighting can recover useful inverse solutions. However, it is often difficult to determine the best ...
2D simulation studies and initial experimental results for hall effect imaging /
Gözü, Mehmet Soner; Gençer, Nevzat Güneri; Department of Electrical and Electronics Engineering (2014)
In this thesis, 2D simulation studies of Hall Effect Imaging (HEI) technique using linear phased array transducer are performed and initial experimental results are obtained. The goal of HEI is to image the conductivity distribution in biological bodies. For this purpose, HEI uses the interaction of ultrasound with a static magnetic field to generate velocity current density distribution inside the body. Due to the velocity current density, a resultant voltage is sensed by electrodes attached on the surface...
Bond strength of lap-spliced bars
Canbay, Erdem (2005-07-01)
Calculation methods to evaluate the strength of tension lap splices are based primarily on nonlinear regression analysis of test results. While the results from these analyses are extremely useful, applicability of their results beyond the domain of the data is often, questioned. The objective of this research was to develop an expression for the calculation of bond strength based on a physical model of tension cracking of concrete in the lap-spliced region. Two different types of failure modes are consider...
Efficient finite difference calculation of partial derivative seismic wavefield using reciprocity and convolution
Sheen, Dong-hoon; Tuncay, Kağan; Baag, Chang-eob; Ortoleva, Peter J. (null; 2004-01-01)
Seismic waveform inversion is commonly studied by the least-squares method which transforms the inverse problem to an iterative minization problem of residuals between the synthetic model response and observed data. One can solve this problem using the gradient method, the Gauss-Newton method or the full Newton method. The performance of the inverse method depends on the algorithm for calculating the partial derivative seismic wavefield due to perturbations in the subsurface. In this work, 2-D elastic stagg...
Efficient finite difference calculation of partial derivative seismic wavefield using reciprocity and convolution
Sheen, Dong-Hoon; Tuncay, Kağan; Baag, Chang-Eob; Ortoleva, Peter J. (2004-01-01)
Seismic waveform inversion is commonly studied by the least‐squares method which transforms the inverse problem to an iterative minization problem of residuals between the synthetic model response and observed data. One can solve this problem using the gradient method, the Gauss‐Newton method or the full Newton method. The performance of the inverse method depends on the algorithm for calculating the partial derivative seismic wavefield due to perturbations in the subsurface. In this work, 2‐D elastic stagg...
Citation Formats
A. Najafi, I. Iskender, P. Farhadi, and B. Najafi, “Turn to Turn Fault Diagnosis for Induction Machines Based on Wavelet Transformation and BP Neural Network,” 2011, p. 294, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/67436.