CN110220593A - A kind of sound abnormality detecting system based on deep learning - Google Patents
A kind of sound abnormality detecting system based on deep learning Download PDFInfo
- Publication number
- CN110220593A CN110220593A CN201910636670.5A CN201910636670A CN110220593A CN 110220593 A CN110220593 A CN 110220593A CN 201910636670 A CN201910636670 A CN 201910636670A CN 110220593 A CN110220593 A CN 110220593A
- Authority
- CN
- China
- Prior art keywords
- sound
- module
- decibel
- unit
- deep learning
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01H—MEASUREMENT OF MECHANICAL VIBRATIONS OR ULTRASONIC, SONIC OR INFRASONIC WAVES
- G01H17/00—Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves, not provided for in the preceding groups
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The invention discloses a kind of sound abnormality detecting systems based on deep learning, including sound acquisition module, the output end of sound acquisition module is connected with sound analysis module, the output end of sound analysis module is connected with sound classification module, sound decibel categorization module, sound classification module, sound decibel categorization module output end be connected with system processing module.The present invention passes through sound acquisition module, collection can be acquired to abnormal sound, then pass through analysis module, sound is analyzed, then sound is handled, then according to sound classification module, sound decibel categorization module is handled, to sound frequency, sound decibel is analyzed and processed classification, to sound frequency, decibel carries out multistratum classification, then pass through system processing module, sound frequency will be in, decibel lights a kind of color alerts lamp in the meeting of first unit, sound frequency will be in, decibel lights two kinds of color alerts lamps in the meeting of second unit.
Description
Technical field
The present invention relates to cacophonia detection technique field more particularly to a kind of cacophonia detections based on deep learning
System.
Background technique
When existing cacophonia is detected, when personnel often hear cacophonia, it can only find that sound occurs not just
Often, can not the degree to cacophonia carry out pair, it should be mentioned that for this purpose, we have proposed a kind of cacophonias based on deep learning
Detection system.
Summary of the invention
The purpose of the present invention is to solve disadvantage existing in the prior art, and propose a kind of based on deep learning
Sound abnormality detecting system.
To achieve the goals above, present invention employs following technical solutions:
A kind of sound abnormality detecting system based on deep learning, including sound acquisition module, the sound acquisition module it is defeated
Outlet is connected with sound analysis module, and the output end of sound analysis module is connected with sound classification module, sound decibel classification mould
Block, the sound classification module, sound decibel categorization module output end be connected with system processing module, the system handles mould
The output end of block is connected with sound alarm module.
Preferably, the sound analysis module includes sound first processing units, the second processing unit, third processing list
Member.
Preferably, the sound classification module includes sound frequency first unit, sound frequency second unit, sound frequency
Third unit.
Preferably, the sound decibel categorization module includes sound decibel first unit, sound decibel second unit, sound
Decibel third unit.
Preferably, the sound alarm module includes the first alarm unit, the second alarm unit, third alarm unit.
Preferably, the input terminal of the sound acquisition module is connected with sound collector.
Preferably, the output end of the sound alarm module is connected with colorful warning lamp, and the first alarm unit is corresponding a kind of
The warning lamp of color, the corresponding two kinds of color alerts lamps of second alarm unit, the corresponding three kinds of colors of the third alarm unit
Warning lamp.
Compared with prior art, the beneficial effects of the present invention are:
The present invention can be acquired collection by sound acquisition module to abnormal sound, then by analysis module, to sound
It is analyzed, then sound is handled, then handled according to sound classification module, sound decibel categorization module, it is right
Sound frequency, sound decibel are analyzed and processed classification, multistratum classification are carried out to sound frequency, decibel, then by system
Manage module, the meeting for be in first unit in sound frequency, decibel lighted into a kind of color alerts lamp, will be in sound frequency,
Decibel lights two kinds of color alerts lamps in the meeting of second unit.
Detailed description of the invention
Fig. 1 is a kind of structural schematic diagram of the sound abnormality detecting system based on deep learning proposed by the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.
Referring to Fig.1, a kind of sound abnormality detecting system based on deep learning, including sound acquisition module, sound collection
The output end of module is connected with sound analysis module, and the output end of sound analysis module is connected with sound classification module, sound point
Shellfish categorization module, sound classification module, sound decibel categorization module output end be connected with system processing module, system handles mould
The output end of block is connected with sound alarm module.
It is worth noting that sound decibel categorization module is detected by sound detection decibel instrument, pass through sound detection
Decibel instrument is connect with controller, and controller detects that sound carries out grade separation to sound decibel instrument, for example 1-10 decibels are one
Class, 10-20 decibels are one kind etc..
Sound analysis module includes sound first processing units, the second processing unit, third processing unit, sound classification mould
Block includes sound frequency first unit, sound frequency second unit, sound frequency third unit, and sound decibel categorization module includes
Sound decibel first unit, sound decibel second unit, sound decibel third unit, sound alarm module include that the first warning is single
Member, the second alarm unit, third alarm unit, the input terminal of sound acquisition module are connected with sound collector, and sound warns mould
The output end of block is connected with colorful warning lamp, and the first alarm unit corresponds to a kind of warning lamp of color, and the second alarm unit is corresponding
Two kinds of color alerts lamps, the corresponding three kinds of color alerts lamps of third alarm unit.
It is worth noting that sound classification module is to carry out sound detection collection by sound frequency detector, pass through sound
Voice frequency detector is connect with controller, and the sound that controller is collected into sound frequency detector is classified according to frequency,
For example 100-120 fundamental frequency is one kind etc..
By sound acquisition module, collection can be acquired to abnormal sound, then by analysis module, to sound into
Row analysis, then handles sound, is then handled according to sound classification module, sound decibel categorization module, to sound
Voice frequency, sound decibel are analyzed and processed classification, carry out multistratum classification to sound frequency, decibel, then handle by system
The meeting for being in first unit in sound frequency, decibel is lighted a kind of color alerts lamp by module, will be in sound frequency, be divided
The meeting that shellfish is in second unit lights two kinds of color alerts lamps.
It is worth noting that sound analysis module is will to belong to same category of sound by sound analyzer and be divided
Analysis is sorted out, and the influence of other sound is reduced.
Meanwhile controller collects the sound and normal sound of classification by sound classification module, sound decibel categorization module
Processing is compared, detection prompting is carried out to cacophonia in terms of the frequency of sound, decibel two.
The foregoing is only a preferred embodiment of the present invention, but scope of protection of the present invention is not limited thereto,
Anyone skilled in the art in the technical scope disclosed by the present invention, according to the technique and scheme of the present invention and its
Inventive concept is subject to equivalent substitution or change, should be covered by the protection scope of the present invention.
Claims (7)
1. a kind of sound abnormality detecting system based on deep learning, including sound acquisition module, which is characterized in that the sound
The output end of acquisition module is connected with sound analysis module, and the output end of sound analysis module is connected with sound classification module, sound
Cent shellfish categorization module, the sound classification module, sound decibel categorization module output end be connected with system processing module, institute
The output end for stating system processing module is connected with sound alarm module.
2. a kind of sound abnormality detecting system based on deep learning according to claim 1, which is characterized in that the sound
Sound analysis module includes sound first processing units, the second processing unit, third processing unit.
3. a kind of sound abnormality detecting system based on deep learning according to claim 1, which is characterized in that the sound
Cent generic module includes sound frequency first unit, sound frequency second unit, sound frequency third unit.
4. a kind of sound abnormality detecting system based on deep learning according to claim 1, which is characterized in that the sound
Cent shellfish categorization module includes sound decibel first unit, sound decibel second unit, sound decibel third unit.
5. a kind of sound abnormality detecting system based on deep learning according to claim 1, which is characterized in that the sound
Sound alarm module includes the first alarm unit, the second alarm unit, third alarm unit.
6. a kind of sound abnormality detecting system based on deep learning according to claim 1, which is characterized in that the sound
The input terminal of sound acquisition module is connected with sound collector.
7. a kind of sound abnormality detecting system based on deep learning according to claim 1, which is characterized in that the sound
The output end of sound alarm module is connected with colorful warning lamp, and the first alarm unit corresponds to a kind of warning lamp of color, and described second
Alarm unit corresponds to two kinds of color alerts lamps, the corresponding three kinds of color alerts lamps of the third alarm unit.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910636670.5A CN110220593A (en) | 2019-07-15 | 2019-07-15 | A kind of sound abnormality detecting system based on deep learning |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910636670.5A CN110220593A (en) | 2019-07-15 | 2019-07-15 | A kind of sound abnormality detecting system based on deep learning |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110220593A true CN110220593A (en) | 2019-09-10 |
Family
ID=67813388
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910636670.5A Pending CN110220593A (en) | 2019-07-15 | 2019-07-15 | A kind of sound abnormality detecting system based on deep learning |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110220593A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115985331A (en) * | 2023-02-27 | 2023-04-18 | 百鸟数据科技(北京)有限责任公司 | Audio automatic analysis method for field observation |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE19749372A1 (en) * | 1997-11-07 | 1999-05-12 | Volkswagen Ag | Electronic recognition system for acoustic signals |
KR20020013042A (en) * | 2000-08-10 | 2002-02-20 | 이수갑 | Portable noise warning device |
CN102122491A (en) * | 2011-03-24 | 2011-07-13 | 深圳市中庆微科技开发有限公司 | LED (light-emitting diode) display control system for on-line detection of application environment noise |
CN102752454A (en) * | 2012-06-30 | 2012-10-24 | 成都西可科技有限公司 | Mobile phone warning method based on voice recognition |
CN102980652A (en) * | 2012-11-14 | 2013-03-20 | 广东电网公司电力科学研究院 | Single noise exposure protective device |
CN207304760U (en) * | 2017-08-24 | 2018-05-01 | 北京融通智慧科技有限公司 | The noise airborne dust monitoring terminal system of wisdom building site control platform |
CN109029692A (en) * | 2018-07-12 | 2018-12-18 | 军事科学院军事医学研究院环境医学与作业医学研究所 | Wearable patient-specific susceptibility assesses early warning system |
CN109616140A (en) * | 2018-12-12 | 2019-04-12 | 浩云科技股份有限公司 | A kind of abnormal sound analysis system |
CN109784410A (en) * | 2019-01-18 | 2019-05-21 | 西安邮电大学 | A kind of feature extraction and classification method of ships radiated noise signal |
-
2019
- 2019-07-15 CN CN201910636670.5A patent/CN110220593A/en active Pending
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE19749372A1 (en) * | 1997-11-07 | 1999-05-12 | Volkswagen Ag | Electronic recognition system for acoustic signals |
KR20020013042A (en) * | 2000-08-10 | 2002-02-20 | 이수갑 | Portable noise warning device |
CN102122491A (en) * | 2011-03-24 | 2011-07-13 | 深圳市中庆微科技开发有限公司 | LED (light-emitting diode) display control system for on-line detection of application environment noise |
CN102752454A (en) * | 2012-06-30 | 2012-10-24 | 成都西可科技有限公司 | Mobile phone warning method based on voice recognition |
CN102980652A (en) * | 2012-11-14 | 2013-03-20 | 广东电网公司电力科学研究院 | Single noise exposure protective device |
CN207304760U (en) * | 2017-08-24 | 2018-05-01 | 北京融通智慧科技有限公司 | The noise airborne dust monitoring terminal system of wisdom building site control platform |
CN109029692A (en) * | 2018-07-12 | 2018-12-18 | 军事科学院军事医学研究院环境医学与作业医学研究所 | Wearable patient-specific susceptibility assesses early warning system |
CN109616140A (en) * | 2018-12-12 | 2019-04-12 | 浩云科技股份有限公司 | A kind of abnormal sound analysis system |
CN109784410A (en) * | 2019-01-18 | 2019-05-21 | 西安邮电大学 | A kind of feature extraction and classification method of ships radiated noise signal |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115985331A (en) * | 2023-02-27 | 2023-04-18 | 百鸟数据科技(北京)有限责任公司 | Audio automatic analysis method for field observation |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107522053A (en) | A kind of elevator platform detecting system and method based on audio analysis | |
CN102491140A (en) | Characteristic-signal-based elevator safety checking device and elevator safety checking method | |
CN206197169U (en) | Electric field intensity early warning safety helmet induction system and nearly electric warning safety helmet | |
CN109633394A (en) | A kind of arc detector | |
CN105842739A (en) | Passing-through type specific metal detecting door | |
CN106574863A (en) | Power equipment sound diagnosis system | |
CN110220593A (en) | A kind of sound abnormality detecting system based on deep learning | |
CN117630319A (en) | Big data-based water quality monitoring and early warning method and system | |
WO2015199434A1 (en) | Device and method for determining integrity of separation membrane module using acoustic sensors | |
CN208834459U (en) | A kind of free-standing photoelectric smoke detecting alarm based on NB-IoT module | |
CN106019089A (en) | Method for carrying out partial discharging determination based on related relationship feature of alternate signals | |
CN109410522A (en) | A kind of hearing-impaired people's traffic trip suggestion device | |
CN102879475A (en) | Identification system for fatigue damage state of 16 manganese steel bearing member based on PCA and TDF | |
CN110057587A (en) | A kind of nuclear power pump bearing intelligent failure diagnosis method and system | |
CN109856495A (en) | A kind of portable cable inspection earthing state assisted detection system and method | |
CN204480432U (en) | Intelligent radio alarm control unit | |
CN204964727U (en) | Power detection equipment | |
CN107014483A (en) | A kind of plant equipment self-checking system monitored based on sound | |
CN113240649A (en) | Building component detection method and system based on image analysis | |
CN110990452A (en) | Big data segmentation contrast fault screening system | |
WO2019066641A2 (en) | A system and method for recognising license plate | |
CN110307899A (en) | Sound anomaly detection system based on deep learning | |
CN112304834B (en) | Biological aerosol early warning system | |
CN113766407B (en) | Audio phase detection system based on singlechip | |
CN203324261U (en) | Hospital wastewater detection alarming device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190910 |
|
RJ01 | Rejection of invention patent application after publication |