Transformer fault diagnosis method and system based on integrated deep belief network

Abstract

The invention discloses a transformer fault diagnosis method and system based on an integrated deep belief network. The method belongs to the field of electronic circuit engineering and computer vision, and comprises the following steps: acquiring a plurality of groups of vibration signals of various types of transformers under different fault types, extracting the characteristics of each vibration signal, and forming training data by the extracted characteristics; training a plurality of deep belief networks with different learning rates through the training data, and obtaining the fault diagnosis accuracy of each deep belief network; and reserving the target deep belief networks corresponding to the fault diagnosis accuracy meeting the requirements, and establishing an integrated deep belief network by each target deep belief network so as to perform fault diagnosis on the transformer through the integrated deep belief network. The problem that a single deep belief network is imperfect when used for transformer fault diagnosis can be solved, and the fault diagnosis accuracy can be effectively improved.

Description

technical field [0001] The invention belongs to the fields of electronic circuit engineering and computer vision, and more specifically relates to a transformer fault diagnosis method and system based on an integrated deep belief network. Background technique [0002] In a substation, a transformer is one of the most important electrical equipment, and its operating status is directly related to the safety and reliability of the power generation and power supply system. In the long-term operation of transformers, various faults will inevitably occur, so it is very necessary to diagnose transformer faults. At present, for transformer fault diagnosis, the vibration signal of the transformer is measured first, then the extracted vibration signal is processed by computer algorithm, and finally the fault identification method is used to distinguish the fault occurred. At present, there are methods for fault diagnosis of transformers through deep belief networks. However, in thi...

AI Technical Summary

Problems solved by technology

[0003] In view of the above defects or improvement needs of the prior art, the present invention proposes a transformer fault diagnosis method and system based on an integrated deep belief network, thereby solving the technical problem that a single deep belief network cannot effectively diagnose various types of transformer faults

Images