Power transformer is one of the most critical equipment in the power system, its operational status is directly related to the security and stability of the power system, Once the transformer fault occurs, it not only cause widespread power outages and bring huge economic losses to the country, but may cause a fire or even explode, so early detection of potential failure, and raising the level of the operation and maintenance of power transformers has important significance in the project.In this paper, the traditional transformer oil dissolved gas analysis is uesd to build a transformer on-line monitoring and fault diagnosis system with the combination of sensor technology, communications technology and computer technology, the transformer fault on-line monitoring can be achieved by the data obtained from various states of the transformer. Once the transformer fails,the judgement is timely made to identify the fault type and then we could make a treatment program by the on-line monitoring system.In this paper, the BP neural network algorithm is applied to establish the database in the transformer fault on-line monitoring, a transformer on-line monitoring and fault diagnosis system is developed on the basis of the functional requirements of the whole system. Power transformer fault monitoring and diagnosis is achieved by the system which is used to effectively monitor the operating status of the transformer. |