Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A noise anomaly detection method of air conditioner indoor unit based on time-frequency domain deep learning algorithm

A deep learning, air-conditioning internal unit technology, applied in computer parts, computing, speech analysis, etc., can solve the problem of difficulty in summarizing abnormal signals through manual analysis, improve analysis accuracy and reliability, increase feature quantity, increase The effect of reliability

Active Publication Date: 2022-06-03
SHANDONG UNIV
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the performance of abnormal signals is diverse, and it is difficult to manually analyze all abnormal signals and summarize their characteristics. Therefore, the traditional method of first extracting features from samples and then using classifiers for classification is difficult to achieve.

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 noise anomaly detection method of air conditioner indoor unit based on time-frequency domain deep learning algorithm
  • A noise anomaly detection method of air conditioner indoor unit based on time-frequency domain deep learning algorithm
  • A noise anomaly detection method of air conditioner indoor unit based on time-frequency domain deep learning algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

Embodiment 2

[0072] The number of training iterations of the first LSTM neural network is 100 times, the learning rate is 0.01, the training optimizer is Adam, and the training

[0074] The number of training iterations is 100, the learning rate is 0.01, and the training optimizer is Adam, when the number of training iterations is reached

[0079] The time domain diagram of the original sound signal is shown in FIG. 1 , and the frequency domain diagram of the original sound signal obtained by conversion is shown in FIG. 2 .

[0085] Threshold detection and fluctuation detection are used to detect obvious anomalies, such as very high amplitude signals.

[0095] The weighted fusion of the detection results has the following advantages: 1. Improve the detection rate of abnormal air conditioners. Air conditioner malfunction

[0096] 2. Reduce the abnormal false positive rate. When the detection system reports abnormality, the air conditioner needs to be repaired. If the detection system

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 a method for detecting abnormal noise of an air conditioner indoor unit based on a deep learning algorithm in the time-frequency domain. Fluctuation detection; the effective time-domain sound signal is input into the trained global information detection model for detection, and the global detection result is obtained; the effective time-domain sound signal is input into the trained local information detection model for detection, and the local detection result is obtained; the obtained The detection results are weighted and fused to obtain the final detection result. The method automatically performs effective sound extraction and abnormal detection, has fast detection speed and high detection accuracy, reduces labor costs, and reduces the damage to the health of detection workers caused by noise.

Description

An abnormal detection method for air conditioner indoor unit noise based on time-frequency domain deep learning algorithm technical field The present invention relates to a kind of abnormal detection method of air conditioner internal noise based on time-frequency domain deep learning algorithm, belongs to acoustic The technical field of sound signal processing and air conditioning quality detection. Background technique In the field of air conditioner manufacturing, before the air conditioner leaves the factory for sale, it is necessary to check the sound of the manufactured air conditioner during operation. to determine whether there is some fault in the air conditioner to be tested. In the field of traditional air conditioner manufacturing, this testing process requires special The staff does it, but there are certain problems with this method. First of all, this work has certain requirements to the staff, and the sound tester needs to pass through a special trai...

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): G10L25/51G10L25/30G06N3/04G06K9/00G06K9/62
Inventor 袁东风康天宇张明强
Owner SHANDONG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com