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

Air conditioner indoor unit abnormal sound detection method based on sound classification model

A technology of air conditioner internal unit and classification model, applied in speech analysis, instruments, etc., can solve problems such as one-way analysis, and achieve the effect of improving accuracy, improving manufacturer's reputation, and improving user experience

Pending Publication Date: 2021-12-07
SHANDONG UNIV
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although LSTM can analyze longer time series, it can only analyze data in one direction

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
  • Air conditioner indoor unit abnormal sound detection method based on sound classification model
  • Air conditioner indoor unit abnormal sound detection method based on sound classification model
  • Air conditioner indoor unit abnormal sound detection method based on sound classification model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0084] A method for detecting abnormal sounds of air-conditioning indoor units based on a sound classification model, such as Figure 6 As shown, the detection method includes:

[0085] (1) Collect and record the operating sound signal of the air conditioner internal unit through the soundproof room;

[0086] (2) intercepting the abnormal part in the sound signal that step (1) obtains, slicing the intercepted abnormal part, and marking each segment according to the abnormal type;

[0087] (3) Intercept the normal part in the sound signal that step (1) obtains, slice the normal part intercepted, and mark each segment as normal sound;

[0088] (4) Fast Fourier Transform (FFT) is performed on all segments in step (2) and step (3), and the energy spectrum is obtained by square, and the Mel spectrum is obtained by Mel filtering, and the Mel spectrum feature is extracted based on the Mel spectrum ;

[0089] (5) Perform logarithmic compression on the amplitude of the Mel spectrum,...

Embodiment 2

[0098] According to a method for detecting abnormal sound of an air conditioner indoor unit based on a sound classification model described in Embodiment 1, the difference is that:

[0099] In step (1) and step (8), when collecting and recording the running sound signal of the air conditioner internal unit, the sampling rate is 48000 Hz, and the monophonic 32-bit storage format is adopted. According to the setting, the air conditioner has to go through two stages of low wind speed mode and high wind speed mode, and the duration of the two stages is fixed. Since the sound of the air conditioner in the high wind speed mode has higher loudness and frequency, the abnormal sound is covered up, so only the sound data of the low wind speed mode is used for quality inspection. It is difficult to distinguish the air-conditioning sound signals collected in steps (1) and (8) in the time domain, such as figure 1 shown. Therefore, the present invention uses the method described in step (...

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 an air conditioner indoor unit abnormal sound detection method based on a sound classification model. The air conditioner indoor unit abnormal sound detection method comprises three parts of data preprocessing, Mel joint feature extraction and network classification. The method comprises the specific steps of collecting and slicing sound data of a to-be-detected air conditioner; extracting a Mel spectrum feature and a Mel cepstrum coefficient of each fragment, and forming a Mel joint feature by using the Mel spectrum feature and the Mel cepstrum coefficient; inputting the Mel joint features into a trained classification network for classification, wherein each segment corresponds to a classification result; and visualizing the result sequence, and meanwhile, giving an overall judgment result of the air conditioner quality. According to the method, the abnormal sound of the air conditioner can be quickly and accurately detected, and automation and intelligence of a quality inspection link are realized, so that the production efficiency is improved, and the production cost is reduced.

Description

technical field [0001] The invention relates to a method for detecting abnormal sound of an air conditioner internal unit based on a sound classification model, and belongs to the fields of sound signal processing, artificial intelligence application and air conditioner quality detection. Background technique [0002] In the field of manufacturing, product quality control is an essential link. Pre-diagnosing the faults of the air conditioner before leaving the factory will help reduce the product defect rate and improve the reputation of the manufacturer. In the era of big data, it is necessary to rely on artificial intelligence technology for quality inspection. Common methods include appearance inspection and sound analysis. Appearance inspection relies on mature computer vision technology to find omissions in the assembly process, thereby helping to improve the production process. But the appearance inspection is floating on the surface and cannot go deep into the insid...

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): G10L25/18G10L25/24G10L25/30G10L25/51
CPCG10L25/18G10L25/24G10L25/30G10L25/51
Inventor 袁东风高东
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