Improved BP Neural Network for Transformer Fault Diagnosis

The back propagation (BP)-based artificial neural nets (ANN) can identify complicated relationships among dissolved gas contents in transformer oil and corresponding fault types, using the highly nonlinear mapping nature of the neural nets. An efficient BP-ALM (BP with Adaptive Learning Rate and Momentum coefficient) algorithm is proposed to reduce the training time and avoid being trapped into local minima, where the learning rate and the momentum coefficient are altered at iterations. We developed a system of transformer fault diagnosis based on Dissolved Gases Analysis (DGA) with a BP-ALM algorithm. Training patterns were selected from the results of a Refined Three-Ratio method (RTR). Test results show that the system has a better ability of quick learning and global convergence than other methods and a superior performance in fault diagnosis compared to convectional BP-based neural networks and RTR.

NEW METHOD OF EXTRACTING WEAK FAILURE INFORMATION IN GEARBOX BY COMPLEX WAVELET DENOISING

Because the extract of the weak failure information is always the difficulty and focus of fault detection. Aiming for specific statistical properties of complex wavelet coefficients of gearbox vibration signals, a new signal-denoising method which uses local adaptive algorithm based on dual-tree complex wavelet transform （DT-CWT） is introduced to extract weak failure information in gear, especially to extract impulse components. By taking into account the non-Gaussian probability distribution and the statistical dependencies among wavelet coefficients of some signals, and by taking the advantage of near shift-invariance of DT-CWT, the higher signal-to-noise ratio （SNR） than common wavelet denoising methods can be obtained. Experiments of extracting periodic impulses in gearbox vibration signals indicate that the method can extract incipient fault feature and hidden information from heavy noise, and it has an excellent effect on identifying weak feature signals in gearbox vibration signals.

PARAMETERS OPTIMIZATION OF CONTINUOUS WAVELET TRANSFORM AND ITS APPLICATION IN ACOUSTIC EMISSION SIGNAL ANALYSIS OF ROLLING BEARING

Morlet wavelet is suitable to extract the impulse components of mechanical fault signals. And thus its continuous wavelet transform （CWT） has been successfully used in the field of fault diagnosis. The principle of scale selection in CWT is discussed. Based on genetic algorithm, an optimization strategy for the waveform parameters of the mother wavelet is proposed with wavelet entropy as the optimization target. Based on the optimized waveform parameters, the wavelet scalogram is used to analyze the simulated acoustic emission （AE） signal and real AE signal of rolling bearing. The results indicate that the proposed method is useful and efficient to improve the quality of CWT.

Tracing overlapping biological signals in mid-infrared using colonic tissues as a model system

AIMTo understand the interference of carbohydrates absorbance in nucleic acids signals during diagnosis of malignancy using Fourier transform infrared (FTIR) spectroscopy.METHODSWe used formalin fixed paraffin embedded colonic tissues to obtain infrared (IR) spectra in the mid IR region using a bruker II IR microscope with a facility for varying the measurement area by varying the aperture available. Following this procedure we could measure different regions of the crypt circles containing different biochemicals. Crypts from 18 patients were measured. Circular crypts with a maximum diameter of 120 μm and a lumen of about 30 μm were selected for uniformity. The spectral data was analyzed using conventional and advanced computational methods.RESULTSAmong the various components that are observed to contribute to the diagnostic capabilities of FTIR, the carbohydrates and nucleic acids are prominent. However there are intrinsic difficulties in the diagnostic capabilities due to the overlap of major absorbance bands of nucleic acids, carbohydrates and phospholipids in the mid-IR region. The result demonstrates colonic tissues as a biological system suitable for studying interference of carbohydrates and nucleic acids under ex vivo conditions. Among the diagnostic parameters that are affected by the absorbance from nucleic acids is the RNA/DNA ratio, dependent on absorbance at 1121 cm-1 and 1020 cm-1 that is used to classify the normal and cancerous tissues especially during FTIR based diagnosis of colonic malignancies. The signals of the nucleic acids and the ratio (RNA/DNA) are likely increased due to disappearance of interfering components like carbohydrates and phosphates along with an increase in amount of RNA.CONCLUSIONThe present work, proposes one mechanism for the observed changes in the nucleic acid absorbance in mid-IR during disease progression (carcinogenesis).