Shuqi Zhang

A hybrid algorithm based on s transform and affinity propagation clustering for separation of two simultaneously artificial partial discharge sources

This paper presents a hybrid algorithm for separation of two simultaneous partial discharge (PD) sources of oil-paper insulation based on S transform (ST) and affinity propagation clustering (APC). Similarities between PD pulses are acquired by comparisons of the corresponding ST-amplitude (STA) matrices, which are input of APC to realize the PD pulses separation and obtain two sub-groups of PD pulses having similar time-frequency characteristics. A classification-based model for separation results validation are developed using a support vector machine with particle swarm optimization (PSO-SVM) classifier and 27 phase-resolved partial discharge (PRPD) statistical features. Artificial defect models are made to simulate two PD sources simultaneously active. Several PD data of different two simultaneous PD sources are acquired in laboratory and adopted for algorithm testing. It is shown that ST computes very fast and is suitable for online PD applications. The separation results of PD data produced in laboratory are verified by the developed validation model, which demonstrate that ST combined with APC can effectively eliminate pulse-shaped noises (PSN) and separate pulses of two simultaneous PD sources. Comparisons with typical separation methods from the state of the art provide better separation performance of the proposed ST combined with APC algorithm for two simultaneous PD sources. The obtained results in this work provide a solid basis for the data mining technique that can be used to facilitate PD diagnosis of transformers.

A new image-oriented feature extraction method for partial discharges

Partial discharge (PD) measurement and recognition is of great importance to assess the health condition of power transformers. However, the variation of defect size, applied voltage as well as insulation aging gives rise to the dispersion and crossover of PD features, which would influence PD recognition reliability of transformers. An image-oriented two-directional modified fuzzy-weighted two-dimensional linear discriminant analysis (TD-MFW-2DLDA) for feature extraction of PD gray images, aiming at solving the above problem, is proposed in this paper. Two classification models including fuzzy C-means (FCM) clustering and support vector machine with genetic algorithm (GA-SVM) are designed for features evaluation and PD pattern recognition. 419 PD samples of four typically artificial defect models are measured in laboratory, in which the multi-factors of defect size, applied voltage and insulation aging are taken into account, and further adopted for algorithms testing. It is shown that TD-MFW-2DLDA achieves optimal successful FCM clustering rate of about 93% and GA-SVM recognition accuracy of about 96%, which are better than that of typical PD features influenced by the multi-factors. Additionally, FCM clustering validity measures provide better compactness within class and separability between classes of TD-MFW-2DLDA which is suitable for on-site PD diagnostic applications.

A new group of image features derived from two-dimensional linear discriminant analysis for partial discharge pattern recognition

Partial discharge (PD) diagnosis is confirmed to be one of the most effective tools for assessing the health condition of power equipment. Classification and recognition of the measured PD data provide the insulation defects information which facilitate the condition diagnosis of electrical apparatus. This paper presents a new group of image features for partial discharge classification, where the gray images are formed to represent different PD defects. The PD gray images are decomposed into various vectors by two-dimensional linear discriminant analysis (2DLDA), where 9 representative parameters are extracted from each image vector. Finally, fuzzy k-nearest neighbor classifier (FkNNC), multi-class support vector machine (MC-SVM) and back-propagation neural network (BPNN) are respectively employed for PD classification. 419 diversified samples of PD data acquired from typically artificial defect models of oil/pressboard insulation, where the defect size, applied voltage and insulation aging are taken into account, are employed for algorithm validation. The recognition results of 419 PD samples show that the defects are well identified by the proposed 2DLDA features with high accuracy. In addition, the significant increments of average recognition accuracies are obtained by different classifiers compared with the phase-resolved partial discharge (PRPD) features in previous works. The obtained results indicate that the proposed 2DLDA features are potentially effective and reliable in recognizing different PD sources and may be considered as an improved PD recognition tool when compared with the intensively used PRPD features.

Insulation design and performance analysis for direct-type lead exit of UHV transformer

A direct-type lead exit for ultra high voltage (UHV) transformer was designed, and the electric field of the lead exit was calculated and analyzed by using finite element method. Then, its insulation structure was optimized. The stress distribution and displacement of the lead exit under vibration condition were investigated. The reliability of the lead exit was verified by electrical test and vibration test.

Oil-paper insulation characteristic and maintenance measures of oil-immersed transformer in cold environment

This paper highlights the operating performance of oil-immersed transformer in extreme cold environment along with the researches on the moisture variations in oil-paper insulation system and its effects on transformer caused by ambient temperature. As one of the main factors that affect the electric strength of oil-paper insulation, the effects of moisture on electric strength for oil and oil immersed paperboard are experimental studied, as well as the researches of moisture transfer rule between oil and paperboard caused by the variation in temperature. The experimental results showed that along with the decreasing of operating temperature, the electric strength of oil-paper insulation reduces first and then increase, with an extreme value occurs at the temperature between −10 °C and −0 °C and so as to the low temperature breakdown characteristics or partial discharge (PD) inception voltage characteristics is generally changing as a U-shaped curve. Moreover, the water solubility in transformer oil decreases and the precipitated water unevenly distributed in transformer oil which lead to the dispensability of insulation strength. After the investigating on the problem may appear while transformer operating in an extreme cold environment, maintenance measures are proposed aim to method of cold start, and avoiding oil spills, oil plug, stop of moving components at low temperature.

Measurement of the electric field strength in transformer oil under impulse voltage

The electric field distribution of the oil-pressboard structure under impulse voltage provides vital reference for the design of transformer insulation. The electric field distribution under impulse voltage is usually held equivalent to that of the capacitive field and calculated by simulation software. An appropriate margin to the calculation results is then selected according to the allowable strength. The design value identified in such a manner, however, falls short of support and verification of actual measurement. The present paper proposes a non-contact real-time measuring method to explore the electric field distribution of the oil-pressboard structure under impulse voltage, using a created measuring apparatus that is composed of optical system, photoelectric converter device, sealed cavity, and impulse voltage generator. Calibrated and verified by a pair of plate electrodes which generated uniform electric field along the propagating direction of the laser beam, the measured values proved to tally well with the actual values of the electric field in terms of both variation trend and numerical value. The minimum sensitivity of the established measuring apparatus was recorded as 3.5 kV/mm and the maximum deviation was 3.6%.

Study on water absorption behaviour of a new type of gas-to-liquid transformer oil

In this report, water absorption behaviors of four kinds of transformer oils composed of Gas-To-Liquid (GTL) and conventional mineral base oils were studied under three different temperature and humidity combinations simulating typical actual storage and transportation conditions of transformer oil. By comparing the test results it is found that the water content of the GTL transformer oil increased to 30mg/kg in a shorter period than the other three conventional mineral oils. Through the diffusion theory analysis, it is concluded that this is mainly because that GTL transformer oil is of relatively lower polarity and it is more difficult to form association structure with water molecules, and therefore water is more rapidly spread in the GTL transformer oil.