CN112542033A - Fire-fighting audible and visual alarm fault detection method based on sound recognition - Google Patents
Fire-fighting audible and visual alarm fault detection method based on sound recognition Download PDFInfo
- Publication number
- CN112542033A CN112542033A CN202011239847.7A CN202011239847A CN112542033A CN 112542033 A CN112542033 A CN 112542033A CN 202011239847 A CN202011239847 A CN 202011239847A CN 112542033 A CN112542033 A CN 112542033A
- Authority
- CN
- China
- Prior art keywords
- sound
- amplitude
- visual alarm
- audible
- frequency
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 30
- 230000000007 visual effect Effects 0.000 title claims abstract description 27
- 238000010606 normalization Methods 0.000 claims description 6
- 230000002159 abnormal effect Effects 0.000 claims description 3
- 230000005856 abnormality Effects 0.000 claims description 3
- 238000000034 method Methods 0.000 abstract description 5
- 230000006378 damage Effects 0.000 abstract description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B29/00—Checking or monitoring of signalling or alarm systems; Prevention or correction of operating errors, e.g. preventing unauthorised operation
- G08B29/02—Monitoring continuously signalling or alarm systems
- G08B29/04—Monitoring of the detection circuits
- G08B29/043—Monitoring of the detection circuits of fire detection circuits
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Security & Cryptography (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The invention discloses a fire-fighting audible and visual alarm fault detection method based on sound recognition. Therefore, manual detection is replaced, and the harm of the detection process to the human body is reduced while the detection efficiency is improved.
Description
Technical Field
The invention relates to the technical field of fire safety, in particular to an audible and visual alarm in fire-fighting electronic equipment.
Background
Fire safety is an important component of national public safety, and the development level of the fire industry becomes an important sign of the developed degree of national economy and society. In recent years, with the development of the fire-fighting industry, the demand of fire-fighting electronic equipment is gradually increased, wherein the demand of an audible and visual alarm in the fire-fighting electronic equipment is remarkably increased as common fire-fighting equipment.
However, in actual production, the fault detection of the audible and visual alarm still adopts a manual detection method, and whether the audible and visual alarm has a fault is judged by manually listening to the alarm sound state. The detection method has the problems of low detection efficiency and high misjudgment rate, and can cause certain damage to the hearing of detection personnel for a long time.
Disclosure of Invention
The invention aims to provide a fire-fighting audible and visual alarm fault detection method based on sound recognition.
The technical problem to be solved by the invention is realized by adopting the following technical scheme:
a fire-fighting audible and visual alarm fault detection method based on voice recognition comprises the steps of firstly quantizing collected alarming voice of an audible and visual alarm, then carrying out feature selection, feature normalization and coding on quantized voice data, and finally carrying out voice coding recognition, and extracting information needing to be verified from the coded voice data so as to obtain a voice detection result.
The further technology of the invention is as follows:
preferably, the feature selection: firstly, quantifying and visualizing the alarm sound of the audible and visual alarm in the form of audio amplitude-frequency curves, selecting the frequency a and the amplitude b of the peak value in each amplitude-frequency curve, taking the amplitude mean value c and the minimum value d of signals in the range of (1000Hz and 9000Hz) as characteristics, taking the information of the first 6 peak values as characteristics of each amplitude-frequency curve, and filling zero when the number of the peak values is insufficient. The feature vector formed by the above feature values can be formulated as follows:
wherein t represents a feature vector, a represents a frequency corresponding to the sound when the sound is at the peak, b represents an amplitude corresponding to the sound when the sound is at the peak, c represents an amplitude average value, and d represents an amplitude minimum value.
Preferably, the feature normalization: firstly, calculating the maximum amplitude value B of all peak values in the feature vector, dividing the amplitude B and the amplitude mean value c of all peak values by B, and then dividing the frequency a of all peak values in the feature vector by 9000Hz to enable the orders of magnitude of all elements in the feature vector to be similar. The normalized feature vector t' can be formulated as shown:
where t' represents the normalized feature vector, a0＝9000。
Preferably, the voice encoding: by analyzing the sound frequency, the sound frequency can be divided into n parts, and each part is correspondingly encoded to be 0 or 1 so as to form a piece of encoded data consisting of the sound frequency. Then, a self-made check code is added into the segment of code to form new coded data, wherein the check code is mainly used for positioning and judging whether the sound is abnormal or not and whether the abnormality occurs in a certain loop.
Preferably, the voice code recognition: through standard alarm sound analysis and coding of the audible and visual alarm of the company, a standard sound coding data can be formed. And comparing and analyzing the voice coded data to be detected with the standard coded voice data to obtain a fault detection result.
The invention has the beneficial effects that:
the method comprises the steps of firstly quantizing the collected alarm sound of the audible and visual alarm, then carrying out feature selection, feature normalization and coding on the quantized sound data, and finally extracting information to be checked from the coded sound data to further obtain a sound detection result. Therefore, manual detection is replaced, and the harm of the detection process to the human body is reduced while the detection efficiency is improved.
Description of the drawings:
FIG. 1 is a schematic view of the detection process of the present invention;
FIG. 2 is a schematic diagram of the detection structure of the present invention.
Detailed Description
The present invention will be further described with reference to specific embodiments for the purpose of facilitating an understanding of technical means, characteristics of creation, objectives and functions realized by the present invention, but the following embodiments are only preferred embodiments of the present invention, and are not intended to be exhaustive. Based on the embodiments in the implementation, other embodiments obtained by those skilled in the art without any creative efforts belong to the protection scope of the present invention.
As shown in figures 1 and 2 of the drawings,
the embodiment is a method for automatically detecting the failure of a fire-fighting audible and visual alarm,
as shown in fig. 2, the sound collection device and the audible and visual alarm are arranged in a relatively closed space, the sound collection device and the audible and visual alarm are controlled by a PC, and collected sound information is processed by detection software on the PC.
Firstly, the sound collecting device and the audible and visual alarm are arranged in a relatively closed space to reduce the external noise interference as much as possible.
Then, fault detection is identified for the collected sound of the audible and visual alarm, and the steps are as shown in fig. 1:
1) selecting characteristics: firstly, quantifying and visualizing the alarm sound of the audible and visual alarm in the form of audio amplitude-frequency curves, selecting the frequency a and the amplitude b of the peak value in each amplitude-frequency curve, taking the amplitude mean value c and the minimum value d of signals in the range of (1000Hz and 9000Hz) as characteristics, taking the information of the first 6 peak values as characteristics of each amplitude-frequency curve, and filling zero when the number of the peak values is insufficient. The feature vector formed by the above feature values can be formulated as follows:
wherein t represents a feature vector, a represents a frequency corresponding to the sound when the sound is at the peak, b represents an amplitude corresponding to the sound when the sound is at the peak, c represents an amplitude average value, and d represents an amplitude minimum value.
2) Characteristic normalization: firstly, calculating the maximum amplitude value B of all peak values in the feature vector, dividing the amplitude B and the amplitude mean value c of all peak values by B, and then dividing the frequency a of all peak values in the feature vector by 9000Hz to enable the orders of magnitude of all elements in the feature vector to be similar. The normalized feature vector t' can be formulated as shown:
where t' represents the normalized feature vector, a0＝9000。
3) Sound coding
By analyzing the sound frequency, the sound frequency can be divided into n parts, and each part is correspondingly encoded to be 0 or 1 so as to form a piece of encoded data consisting of the sound frequency. For example, if the sound amplitude is 1-15db, the corresponding frequency range code is 00, the corresponding frequency range code is 01, the corresponding frequency range code is 10, the corresponding frequency range code is 11, the corresponding frequency range code is 100, the corresponding frequency range code is 101, and the corresponding frequency range code is 100, the corresponding frequency range code is 101, the corresponding frequency range code is 70-85db, and so on, the sound code of 000111100101 can be formed. Then, a self-made check code is added into the segment of code to form new coded data, wherein the check code is mainly used for positioning and judging whether the sound is abnormal or not and whether the abnormality occurs in a certain loop.
4) Speech coding recognition
Through standard alarm sound analysis and coding of the audible and visual alarm of the company, a standard sound coding data can be formed. And comparing and analyzing the voice coded data to be detected with the standard coded voice data to obtain a fault detection result.
The foregoing shows and describes the general principles, essential features, and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, and the preferred embodiments of the present invention are described in the above embodiments and the description, and are not intended to limit the present invention. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (5)
1. A fire-fighting audible and visual alarm fault detection method based on voice recognition is characterized in that firstly, collected alarming sounds of an audible and visual alarm are quantized, then, feature selection, feature normalization and coding are carried out on quantized sound data, finally, voice coding recognition is carried out, and information needing to be verified is extracted from the coded sound data so as to obtain a voice detection result.
2. The fire-fighting audible and visual alarm fault detection method based on the voice recognition as claimed in claim 1, wherein the feature selection comprises: firstly, quantifying and visualizing the alarm sound of the audible and visual alarm in the form of audio amplitude-frequency curves, selecting the frequency a and the amplitude b of peak values in each amplitude-frequency curve, taking the amplitude mean value c and the minimum value d of signals in the range of (1000Hz and 9000Hz) as characteristics, taking the information of the first 6 peak values as characteristics for each amplitude-frequency curve, and filling zero when the number of the peak values is insufficient, wherein a characteristic vector formed by the characteristic values can be formulated as follows:
wherein t represents a feature vector, a represents a frequency corresponding to the sound when the sound is at the peak, b represents an amplitude corresponding to the sound when the sound is at the peak, c represents an amplitude average value, and d represents an amplitude minimum value.
3. The fire-fighting audible and visual alarm fault detection method based on the voice recognition as claimed in claim 1, wherein the characteristic normalization: firstly, calculating the maximum amplitude value B of all peak values in the feature vector, dividing the amplitude B and the amplitude mean value c of all peak values by B, then dividing the frequency a of all peak values in the feature vector by 9000Hz to enable the magnitude orders of all elements in the feature vector to be similar, and formulating the normalized feature vector t' as shown in the specification:
where t' represents the normalized feature vector, a0＝9000。
4. A fire alarm sound and light fault detection method based on voice recognition as claimed in claim 1, wherein the voice coding: by analyzing the sound frequency, the sound frequency can be divided into n parts, each part is correspondingly coded into 0 or 1 to form a section of coded data consisting of the sound frequency, and then, self-made check coding is added into the section of coded data to form new coded data, wherein the check coding is mainly used for positioning and judging whether the sound is abnormal or not and whether the abnormality occurs in a certain loop.
5. A fire-fighting audible and visual alarm fault detection method based on voice recognition as claimed in claim 1, characterized in that said voice coding recognition: a standard sound encoding data can be formed by analyzing and encoding the standard alarm sound of the audible and visual alarm, and the fault detection result can be obtained by comparing and analyzing the sound encoding data to be detected and the standard encoding sound data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011239847.7A CN112542033A (en) | 2020-11-09 | 2020-11-09 | Fire-fighting audible and visual alarm fault detection method based on sound recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011239847.7A CN112542033A (en) | 2020-11-09 | 2020-11-09 | Fire-fighting audible and visual alarm fault detection method based on sound recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112542033A true CN112542033A (en) | 2021-03-23 |
Family
ID=75014430
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011239847.7A Pending CN112542033A (en) | 2020-11-09 | 2020-11-09 | Fire-fighting audible and visual alarm fault detection method based on sound recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112542033A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115019475A (en) * | 2022-05-31 | 2022-09-06 | 中山亿联智能科技有限公司 | Tsunami early warning monitoring alarm system based on set top box platform |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006157789A (en) * | 2004-12-01 | 2006-06-15 | Kddi Corp | Sound failure detection device |
| CN103926525A (en) * | 2014-04-30 | 2014-07-16 | 广州视源电子科技股份有限公司 | System and method for acquiring quality information of mainboard of electronic product through sound |
| CN104077900A (en) * | 2013-03-29 | 2014-10-01 | 北京谊安医疗系统股份有限公司 | Medical instrument alarm apparatus starting detection device and starting detection method |
| CN106198062A (en) * | 2016-07-27 | 2016-12-07 | 哈尔滨市科佳通用机电有限公司 | The vehicle-mounted acoustic testing system of track vehicle fault and detection method |
-
2020
- 2020-11-09 CN CN202011239847.7A patent/CN112542033A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006157789A (en) * | 2004-12-01 | 2006-06-15 | Kddi Corp | Sound failure detection device |
| CN104077900A (en) * | 2013-03-29 | 2014-10-01 | 北京谊安医疗系统股份有限公司 | Medical instrument alarm apparatus starting detection device and starting detection method |
| CN103926525A (en) * | 2014-04-30 | 2014-07-16 | 广州视源电子科技股份有限公司 | System and method for acquiring quality information of mainboard of electronic product through sound |
| CN106198062A (en) * | 2016-07-27 | 2016-12-07 | 哈尔滨市科佳通用机电有限公司 | The vehicle-mounted acoustic testing system of track vehicle fault and detection method |
Non-Patent Citations (2)
| Title |
|---|
| 侯增起: "基于声音特征的变电设备故障分类与定位方法研究", 《中国优秀博硕士学位论文全文数据库（硕士） 工程科技II辑》 * |
| 朱健民: "基于ARM Cortex-M4和快速傅里叶变换的蜂鸣器自动测试方案", 《机电信息》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115019475A (en) * | 2022-05-31 | 2022-09-06 | 中山亿联智能科技有限公司 | Tsunami early warning monitoring alarm system based on set top box platform |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101494049B (en) | Method for extracting audio characteristic parameter of audio monitoring system | |
| CN109616140B (en) | Abnormal sound analysis system | |
| Seo et al. | Audio fingerprinting based on normalized spectral subband moments | |
| CN110364141B (en) | Elevator typical abnormal sound alarm method based on depth single classifier | |
| CN109545242A (en) | A kind of audio data processing method, system, device and readable storage medium storing program for executing | |
| JP2012048689A (en) | Abnormality detection apparatus | |
| JP2004310117A (en) | Method for embedding and detecting watermark by quantization of characteristic value of signal | |
| CN105489217A (en) | Method and system of monitoring the aged through sound by means of internet of things | |
| CN115359807B (en) | Noise online monitoring system for urban noise pollution | |
| CN112542033A (en) | Fire-fighting audible and visual alarm fault detection method based on sound recognition | |
| CN104851424A (en) | Voice recognition caring and nursing method and system | |
| CN105304091A (en) | Voice tamper recovery method based on DCT | |
| JP2012058944A (en) | Abnormality detection device | |
| CN109557583A (en) | A kind of seismic attribute extracting method and system | |
| CN101350198B (en) | Method for compressing watermark using voice based on bone conduction | |
| US20230366729A1 (en) | Trained autoencoder, trained autoencoder generation method, non-stationary vibration detection method, non-stationary vibration detection device, and computer program | |
| CN116746887B (en) | Audio-based sleep stage method, system, terminal and storage medium | |
| CN112666430A (en) | Intelligent transformer voiceprint fault detection method and system | |
| CN118250083A (en) | Log processing method and device for network security detection | |
| CN110579657A (en) | Transformer fault detection system based on vibration signal analysis and detection method thereof | |
| CN115293205A (en) | Anomaly detection method, self-encoder model training method and electronic equipment | |
| CN112443319A (en) | Well kick monitoring method | |
| Wan et al. | Pipeline monitoring using acoustic principal component analysis recognition with the Mel scale | |
| CN115440254A (en) | Noise data identification method and equipment | |
| CN112989101A (en) | Reminding method, device, equipment and storage medium suitable for hearing-impaired patients |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210323 |