Transformer substation acoustic signal feature extraction method based on dynamic normalization algorithm

Abstract

The invention discloses a transformer substation acoustic signal feature extraction method based on a dynamic normalization algorithm, and belongs to the field of monitoring. The method comprises thesteps that: field acoustic characteristic signals of acoustic signals sent by primary equipment in different operation states are collected, and fault diagnosis is performed according to the acousticsignals collected by the primary equipment in various operation states, and is characterized by: obtaining a feature vector by utilizing a Mel frequency cepstrum coefficient based on discrete cosine transform; adopting a dynamic normalization algorithm to perform fault classification by comparing a reference template vector; and finally, based on the calculation result of the similarity between the test template and the reference template, analyzing actual operation states of primary equipment of various transformer substations, and classifying possible faults. Therefore, the resources occupied is little, the requirement for hardware calculation performances is low, and therefore, the transformer substation acoustic signal feature extraction method is especially suitable for dynamically and quickly matching fault characteristic signals in a transformer substation site, and is suitable for system operation on a single-chip microcomputer system. The method can be widely applied to the field of operation monitoring and state monitoring of unattended substations.

Description

technical field [0001] The invention belongs to the field of monitoring, and in particular relates to a method for extracting fault features of transformers in substations through sound signal processing and performing fault diagnosis and analysis. Background technique [0002] Transformer is one of the most important equipment in the power system. In order to ensure its normal operation and to ensure that the transformer is in normal operation, special regular inspection personnel often inspect each substation. [0003] Due to the way of manual inspection and the relatively large proportion of subjective components, ultrasonic detection methods, infrared signal detection methods, vibration signal detection methods and acoustic signal detection methods have been developed. [0004] The acoustic signal detection method has the characteristics of non-contact, uninterrupted power supply and easy operation, so it has received a certain amount of attention. [0005] In view of t...

AI Technical Summary

Problems solved by technology

[0007] These methods need to provide a large amount of audio data during the training phase, and the model parameters are obtained through repeated calculations. The training process is complex and takes up more resources, so the hardware computing performance is relatively high.

[0008] In addition, the existing acoustic signal detection method usually collects the acoustic signal on the spot of the digital equipment, converts it into an electrical signal and transmits it remotely, and performs the analysis of the acoustic signal processing algorithm and spectrum characteristics in the centralized control center. In terms of resources, it takes up a lot of resources, so it has high requirements for hardware computing performance; and the feature loss or external interference during the remote transmission of acoustic signals is an important factor that affects the accuracy of monitoring results and the comparison of on-site sound collection with standard samples , restricting the accuracy and timeliness of the implementation of the acoustic signal detection method

Images