Prof. Hongzhong Ma 马宏忠教授
Hohai University 河海大学
Speech Title: Research on fault diagnosis technology of transformer acoustic pattern imaging based on acoustic sensor array
Abstract: Power transformer is one of the main equipments of power system, and its safe and stable operation plays an important role in power system. For a long time, the sound emitted by transformers has been regarded as noise, and ignoring the sound contains a large amount of state information, and when transformers fail, their sound signals change. Therefore, this topic studies the diagnostic method of transformer sound pattern imaging based on acoustic sensor array. First of all, based on theoretical derivation, Modeling and simulation， experimental measurement and other methods to study the transformer sound pattern signal generation mechanism and propagation law. Secondly, the transformer fault diagnosis method based on deep learning models such as vector quantification, convolutional neural network and deep forest is studied. Finally, on the basis of deep mining of transformer sound pattern fault characteristics, the method of sound pattern fault location based on TODA and beam formation algorithm is studied. The results show that the transformer sound pattern imaging fault diagnosis method based on the acoustic sensor array has obvious advantages in the transformer fault diagnosis method, and shows a wide range of applications.
Hongzhong Ma, 1962.7, male, doctor, professor, doctoral supervisor, director of The Institute of Fault Diagnosis of Major Electric Power Equipment, Hohai University. Mainly engaged in the condition monitoring, fault diagnosis and health warning research of power main equipment. He is also the professional committee member of Electrical Theory and New Technology of China Society of Electrical Engineering. He has presided over 3 projects of national Natural Science Foundation of China, more than 50 projects of national 863 Science and Technology Project and state Grid science and technology project at various levels. More than 20 science and technology awards at various levels; Published about 300 academic papers; Published 9 academic monographs and textbooks; More than 60 invention patents have been authorized; Supervised 3 post-doctoral students, 21 doctoral students and more than 210 master students.