Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Transformer sound anomaly detection method based on improved wavelet packet and deep learning

A technology of abnormal sound and deep learning, applied in the computer field, can solve the problems of poor monitoring transformer abnormal sound effect, etc., to reduce maintenance costs, improve efficiency and accuracy, and eliminate noise signals.

Pending Publication Date: 2020-06-09
HANGZHOU ANMAISHENG INTELLIGENT TECH CO LTD
View PDF8 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The technical problem to be solved by the present invention is: the current technical problem of monitoring the abnormal sound effect of the transformer is poor

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Transformer sound anomaly detection method based on improved wavelet packet and deep learning
  • Transformer sound anomaly detection method based on improved wavelet packet and deep learning
  • Transformer sound anomaly detection method based on improved wavelet packet and deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0024] A transformer sound anomaly detection method based on improved wavelet packets and deep learning, taking transformers with voltage levels of 110Kv, 220Kv and 330Kv as examples, such as figure 1 As shown, this embodiment includes the following steps: A) Set the sampling frequency to 16000 Hz, and the sampling time to 1 s, and respectively collect 50 groups of normal and abnormal audio signals of transformers at three different voltage levels.

[0025] B) Perform 4-layer wavelet packet decomposition on each group of collected audio signals to obtain 16 component signals, use the improved sample entropy method to determine the threshold value to determine the threshold λ, and recalculate the wavelet coefficient η of each component, reconstruct the component signal, and obtain The reconstructed audio signal.

[0026] The 4-layer wavelet packet decomposition is performed on each group of collected audio signals to obtain 16 component signals.

[0027] B1: Use the improved s...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention relates to the technical field of computers, in particular to a transformer sound anomaly detection method based on an improved wavelet packet and deep learning. The method comprises thefollowing steps: A) collecting audio signals of N transformers in different running states; B) performing wavelet packet transformation\ on each audio signal, determining a threshold lambda of the sample entropy by adopting an improved sample entropy, recalculating a wavelet coefficient eta of each component, reconstructing component signals, and obtaining reconstructed audio signals; C) performing short-time Fourier transform to generate a feature image; D) classifying the extracted feature images according to the running state of the transformer; and E) establishing a convolutional neural network model, using the classified feature images for training, and using the trained convolutional neural network model for transformer sound anomaly detection. The transformer sound anomaly detection method has the advantages that noise signals in collected transformer signals can be effectively eliminated, abnormal fault characteristics of the transformer are extracted, and engineers are assisted in transformer fault diagnosis.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to a transformer sound anomaly detection method based on improved wavelet packets and deep learning. Background technique [0002] During the operation of the transformer, under the influence of alternating current, a periodically changing alternating magnetic flux will be generated in the iron core, which will further cause the iron core to emit a uniform "humming" sound. The size of the "hum" sound is proportional to the voltage and current installed on the transformer, and the "hum" sound in normal operation is uniform. If the transformer is abnormal, it will produce abnormal sound. By detecting the sound of the transformer, it is possible to diagnose the fault of the transformer. [0003] During the operation of the transformer, the collected audio signal of the transformer contains a lot of noise due to on-site noise and interference from other transformers. Moreover, voic...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06K9/62G06K9/00G01H17/00
CPCG01H17/00G06F2218/08G06F2218/12G06F18/2411G06F18/214G06F18/24Y04S10/50
Inventor 杨皓杰杨雨李倩程胜孙丰诚
Owner HANGZHOU ANMAISHENG INTELLIGENT TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Eureka Blog
Learn More
PatSnap group products