Sun Laijun

Fault Diagnosis Method of HV Circuit Breaker Based on Wavelets Neural Network

Fault diagnosis of HV circuit break has been investigated extensively as an important device in the field of power system. In view of the shortcoming of the traditional neural network, such as the slow convergence rate and the lo- cal minimum easy to form, fault diagnosis method of HV circuit breaker is proposed to remedy the defects of traditional neural network based on wavelets neural. This method adopts wavelets function rather than the hidden nodes of traditional neural network, which is propitious to conducive to achieve a rapid convergence of online learning. This work firstly dis- cussed the principles of fault diagnosis method in detail, and then compared diagnosis effect using wavelets function with that of the traditional neural network. The results show that the training speed and classification effect of wavelets neural network are superior obviously to those of traditional neural network. Wavelets neural network based on vibration signals is more suitable in application to the fault diagnosis of HV circuit breakers.

A New Fault Diagnosis Method for High Voltage Circuit Breakers Based on Wavelet Packet and Radical Basis Function Neural Network

A new method that researching fault diagnosis of high-voltage (HV) circuit breaker (CB) is proposed. The method combines Wavelet Packet (WP) with Radical Basis Function (RBF) Neural Network (NN). Firstly, by applying the theory of WP decomposition and reconstruction, the mechanical vibration signal of CB was decomposed into different frequency bands, and the coefficients are reconstructed in the corresponding node. After that, the feature vector was ex- tracted by equal-energy segment entropy from reconstructed signals. Finally, fault diagnosis has been realized through the classification of feature parameters combined with RBF neural network. The experiment outputs show that the method can be applied in diagnosis.

Self-tuning weighted measurement fusion Kalman filter with cooperating identification for multisensor system with correlated noises

For the multisensor system with correlated noises and unknown noise statistics, the measurement function can be dealt with in a unified way to form a new tracking system by least square method. The result of the measurements can make some groups of steady random sequence, and the variances Ru and covariance Ry of these measurements can be yielded by the matrix equations of the correlation function, and then the estimates of TQ^T can be obtained. Then the self-tuning weighted measurement fusion Kalman filter is obtained. A simulation example for a tracking system with 3 sensors shows its fast convergence and exactness.

A method of classified HV circuit breaker fault signal based on EEMD and BP neural network

During the process of high voltage circuit breaker run, the change of the vibration signal reflects the mechanical state of the circuit breaker, an efficient method of extracting vibration signal features is directly related to the accuracy and practicability of fault diagnosis. In the paper, a status feature extraction based on overall empirical mode decomposition (ensemble empirical mode decomposition EEMD) and correlation dimension has been presented. Firstly, the original non-stationary vibration signals are broken down to a plurality of stationary intrinsic mode function (IMF); Secondly, using GP algorithm to calculate the correlated dimensions of first four IMF as a high voltage circuit breaker vibration signals feature vectors. Finally, constructing BP (back propagation) neural network to classify the feature vectors. Through testing different fault vibration signals of circuit breaker, it showed that the method can accurately diagnose all kinds of circuit breaker fault state and provide a new thinking way about fault diagnosis.

Quality analysis of wheat based on BP neural network and Near Infrared Reflectance Spectroscopy

With its quick, simple, nicety and nondestructive characteristic, NIRS (Near Infrared Reflectance Spectroscopy) is a new method for quality analysis of wheat. In this paper, a new method to model-building for wheat quality analysis with NIRS is presented. Opposite near infrared parameters shield the testing accuracy from outer disturb and random factors. Local minimization is escaped, and a high convergence velocity is reached by modified BP algorithm. The experimental results indicate that a high-accuracy testing results can be get in spite of large disturb from temperature and moisture.

Determination of zeleny subsidence value of wheat based on Near Infrared Transmittance Spectroscopy

The subsidence value is an synthesis target to evaluate the wheat quality. NIRS (Near Infrared Transmittance Spectroscopy) is a new method for quality analysis of wheat with its quick, simple, accurate and nondestructive characteristic. In this paper, spectral data were dealt with moving window average method and second differential and SNV analysis firstly, on the basis of which, the partial least squares model was established. The experiment results indicated that the R and MSE were 0.9809 and 0.1130 respectively. In contrast with the calibration model built with the original data, the predicted results can basically complete the grain reserves and the food processing profession division and the breeding preliminary generation.

Determination of wet gluten in wheat based on wavelet de-noising and PLS

NIRS (Near Infrared Transmittance Spectroscopy) is a new analytic technique in analytical chemistry which is developing very quickly in recent years. It has quick, simple, and nondestructive characteristic. This study is based on the analysis of wheat by near infrared spectroscopy to predict the wet gluten in wheat. Using the wavelet transform to de-noise the spectrum firstly, on the basis of which, the partial least squares model of wheat wet gluten is established. The experimental results indicate that the R, MSE and Er are 0.9711, 1.155 and 3.371% respectively, which certificate that this model could predict the wet gluten in wheat accurately.