Windowed feature Hilbert imaging-based power equipment diagnosis method and system

Abstract

The invention discloses a windowed feature Hilbert imaging-based power equipment diagnosis method and system, and belongs to the field of electrical equipment fault diagnosis, and the method comprisesthe steps: obtaining a monitoring data original data set comprising electrical equipment fault features; introducing windowing feature calculation considering logarithm constraints to process the data to obtain a feature sequence; further performing processing by using a Hilbert imaging method to obtain a Hilbert image data set, and applying the Hilbert image data set to training and verificationof a convolutional neural network; and finally, after windowing feature calculation and Hilbert imaging processing are performed on newly acquired test sample data, directly inputting the newly acquired test sample data into the trained network for fault diagnosis and positioning. According to the method and system, windowing feature calculation and Hilbert imaging are used for processing the power equipment monitoring data, fault features are fully extracted, the diagnosis accuracy is effectively improved, the convolutional neural network is used for diagnosis, and the diagnosis intelligenceis improved.

Description

technical field [0001] The invention belongs to the field of fault diagnosis of electric equipment, and more specifically relates to a method and system for diagnosing electric equipment based on windowing feature Hilbert imaging. Background technique [0002] Fault diagnosis of power transmission and transformation equipment is an important guarantee for the safe and economical operation of power systems. With the gradual advancement of smart grid construction, power equipment will continue to develop in the direction of intelligence and high integration. However, the current power equipment fault diagnosis methods are weak in extracting power equipment fault features, so the diagnosis effect is not ideal, and cannot meet the construction needs of smart grids, and most studies only consider the fault type diagnosis of power equipment, and its fault location method is very difficult. Get less consideration. At present, in the actual diagnosis of power equipment, the experi...

Images