A DNN algorithm-based audio signal analysis method for power equipment

A technology of audio signal and power equipment, applied in the field of audio signal analysis of power equipment based on DNN algorithm, can solve problems affecting audio signal feature extraction, strong background noise interference signal, etc., achieve good speed, simple principle, and improve efficiency Effect

Active Publication Date: 2020-12-04
NANJING UNIV OF SCI & TECH
View PDF15 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Professional electrical equipment inspectors will also judge the operating status of the equipment based on the abnormal operating sound on site, but the audio signal collected on site has strong background noise and other interference signals, which affects the feature extraction of the audio signal

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
  • A DNN algorithm-based audio signal analysis method for power equipment
  • A DNN algorithm-based audio signal analysis method for power equipment
  • A DNN algorithm-based audio signal analysis method for power equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] The present invention will be described in detail below with reference to the accompanying drawings and examples.

[0031] The present invention is based on the DNN algorithm audio signal analysis method of power equipment, and its overall working process is as follows figure 1 shown, including the following steps:

[0032] Step 1. The power inspection robot collects the audio signal data during normal and faulty operation of the power equipment through the installed digital pickup, and performs audio signal data preprocessing. The processing method flow is as follows: figure 2 shown;

[0033] Step 1-1, audio signal data pre-emphasis: the audio signal data is processed through a first-order FIR high-pass digital filter, and the filter transfer function is as shown in formula (1):

[0034] H(z)=1-αz -1 , 0.9<α<1.0 (1)

[0035] Pre-emphasis processing helps to enhance the high-frequency components of the audio signal, making the signal spectrum flatter, keeping it in...

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 discloses a DNN algorithm-based analysis method of an audio signal of power equipment. The method comprises the following steps: a power inspection robot collecting audio signal data during normal and fault operation of the power equipment through an installed digital pickup to perform audio signal data preprocessing; extracting feature information from the preprocessed audio signaldata by using MFCC feature parameters; training a deep neural network acoustic model by using an error back propagation method; and the power inspection robot collecting the audio signal data of the on-site power equipment during operation through the digital pickup, inputting the feature information into the deep neural network acoustic model for audio signal data recognition after preprocessingand extraction of feature parameters, and transmitting the recognition result to a substation monitoring host. The DNN algorithm-based analysis method of audio signal of power equipment enriches the fault detection function of the power inspection robot, and can detect the fault of the power equipment in unattended substations in real time, and improves the speed, reliability and accuracy of the power equipment fault monitoring at the same time.

Description

technical field [0001] The invention relates to the field of audio signal analysis of power equipment, in particular to a DNN algorithm-based audio signal analysis method for power equipment. Background technique [0002] With the progress of society, the development of all walks of life is inseparable from the safe operation of the power system, so the position of the power industry in production and life is very important. Power inspection robots can conduct autonomous inspections of power equipment, and analyze and identify the operating status of power equipment through intelligent technology, thereby ensuring the reliable and safe operation of power equipment. Therefore, power inspection robots gradually replace manual inspections, and its market The application prospect is very broad. [0003] The structure of power equipment is complex, and it is easy to fail during operation. Therefore, it is necessary to monitor the fault of power equipment to maintain the safe ope...

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
Patent Type & Authority Patents(China)
IPC IPC(8): G01H17/00
CPCG01H17/00
Inventor 李胜史一露郭健吴益飞袁佳泉施佳伟朱禹璇赵超危海明
Owner NANJING UNIV OF SCI & TECH
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
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap