CN202083757U - Sound abnormality detecting system for power equipment - Google Patents
Sound abnormality detecting system for power equipment Download PDFInfo
- Publication number
- CN202083757U CN202083757U CN2011201972816U CN201120197281U CN202083757U CN 202083757 U CN202083757 U CN 202083757U CN 2011201972816 U CN2011201972816 U CN 2011201972816U CN 201120197281 U CN201120197281 U CN 201120197281U CN 202083757 U CN202083757 U CN 202083757U
- Authority
- CN
- China
- Prior art keywords
- module
- audio frequency
- audio
- training
- subsystem
- 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.)
- Expired - Fee Related
Links
- 230000005856 abnormality Effects 0.000 title abstract 4
- 238000001514 detection method Methods 0.000 claims abstract description 40
- 238000012549 training Methods 0.000 claims abstract description 34
- 238000004891 communication Methods 0.000 claims abstract description 23
- 238000007689 inspection Methods 0.000 claims abstract description 13
- 230000007246 mechanism Effects 0.000 claims abstract description 6
- 238000000034 method Methods 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 6
- 230000002457 bidirectional effect Effects 0.000 abstract 1
- 230000006870 function Effects 0.000 description 10
- 230000005540 biological transmission Effects 0.000 description 6
- 230000002159 abnormal effect Effects 0.000 description 4
- 239000000284 extract Substances 0.000 description 4
- 238000013139 quantization Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000005236 sound signal Effects 0.000 description 3
- 230000006835 compression Effects 0.000 description 2
- 238000007906 compression Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 241001269238 Data Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 239000003990 capacitor Substances 0.000 description 1
- 230000001149 cognitive effect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000009713 electroplating Methods 0.000 description 1
- 231100001261 hazardous Toxicity 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 239000012212 insulator Substances 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000010355 oscillation Effects 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Landscapes
- Emergency Alarm Devices (AREA)
Abstract
The utility model discloses a sound abnormality detecting system for power equipment, which is used for sound abnormality detection of equipment of a transformer substation and comprises a tour inspection platform, an audio frequency detecting subsystem and a computer subsystem. The audio frequency detecting subsystem is disposed on the tour inspection platform, the computer subsystem is in wireless communication with the audio frequency detecting subsystem, the tour inspection platform consists of a travel mechanism and a control module controlling the travel mechanism, the audio frequency detecting subsystem comprises an audio frequency acquisition module, a video service module, an audio frequency training and identifying module and a storage module, an output end of the audio frequency acquisition module is connected with an input end of the video service module, an output end of the video service module is connected with a corresponding input end of the audio frequency training and identifying module, the audio frequency training and identifying module is in bidirectional connection with the storage module, and the computer subsystem consists of a host provided with a base station background software system, an audio frequency data display module and an alarm module. The sound abnormality detecting system is flexible in detection, lower in cost and high in reliability.
Description
Technical field
The utility model relates to a kind of cacophonia detection system and method, especially a kind of cacophonia detection system that is used for power equipment.
Background technology
Current, the normal operation of transformer station mainly still relies on artificial scene to patrol and examine and safeguard.There are following two problems in this mode: one, patrol and examine personnel's safety problem, transformer station is a hazardous environment that is full of high pressure and discharge, easily the health of patrolling and examining the staff is damaged; Two, the effect problem of manual inspection when personnel face the work that repeats machinery, is easy to generate tired, slack psychology, effect and quality that reduction is patrolled and examined, and manual inspection also can't satisfy the sudden and promptness of substation equipment fault.Therefore, the effect of manual inspection is unsettled, and reliability also can't improve.
Some transformer stations begin to attempt robotization, intellectualizing system is assisted or replace manual inspection, and the demand of unattended operation transformer station is also more and more.Aspect the substation equipment sound detection, mainly contain the research of substation equipment monitoring and ultrasonic Detection Method.The method that substation equipment is monitored, main audio sensor and the central processing unit that is installed in above the apparatus body that rely on.Its deficiency has following two aspects: one, point of fixity and be close to the mode of body, and make the position of audio sensor fix, there is not dirigibility; Two, each substation equipment all needs to be equipped with independently audio sensor, and the sensor device of too many quantity causes difficult arrangement, and cost is higher.Ultrasonic Detection Method, the defective that have the cost height, can't real-time continuous detects.
The utility model content
The technical problems to be solved in the utility model provides a kind of flexible, lower-cost cacophonia detection system that is used for power equipment that detects; mainly utilize the technology of sound signal processing and pattern-recognition; equipment to transformer station carries out sound detection; differentiate this equipment and whether have unusual or internal fault; thereby keep the normal operation of transformer station, guarantee personal security simultaneously.
For solving the problems of the technologies described above, the technical solution adopted in the utility model is:
A kind of cacophonia detection system that is used for power equipment, described system comprise the audio detection subsystem and with the computer subsystem of described audio detection subsystem wireless telecommunications;
Described audio detection subsystem comprises audio collection module, Video service module, audio frequency training and identification module, memory module and first communication module; The input end of the output termination Video service module of described audio collection module, the output ending connecting audio training of described Video service module and the respective input of identification module, the corresponding output end of described audio frequency training and identification module connects the input end of first communication module, and described memory module is connected with identification module is two-way with the audio frequency training;
Described computer subsystem comprises main frame, voice data display module, alarm module and second communication module that base station daemon software system is housed; The respective input of the output termination main frame of described second communication module; The corresponding output end of described main frame connects the input end of voice data display module and alarm module respectively.
Preferably, described system also comprises and patrols and examines platform, describedly patrols and examines the control module that platform comprises travel mechanism and the described travel mechanism of control; Described audio detection subsystem is arranged on described patrolling and examining on the platform.
Described audio frequency training is made up of ARM9 microprocessor and DSP microprocessor with identification module, and described ARM9 microprocessor adopts the S3C2440 chip, and described DSP microprocessor adopts the TMS320X2812 chip.
Describedly patrol and examine platform to adopt model be the electric inspection process robot of LER-3000.
The subsystem of audio detection described in the utility model is primarily aimed at abnormal occurrence or the internal fault that substation equipment is contingent, can differentiate from sound, provides testing result.Can embody the substation equipment fault of fault by sound, mainly contain several: the device interior discharge, insulator arc-over, electric and magnetic oscillation sound is unusual, and fan, Oil pump electrical machinery rotate unusual, capacitor cacophonia etc.The workflow of audio detection subsystem is as follows substantially: crusing robot is patrolled and examined according to pre-determined route or task samsara in transformer station, can repeatedly patrol and examine in one day, and cover most of geographic range of transformer station.Audio collection module in the audio detection subsystem can be gathered the sound of crusing robot place of arrival substation equipment operation in real time.The audio frequency training is responsible for this sound is discerned with identification module, whether has unusual or fault thereby judge this equipment.If finding has fault, then the audio detection subsystem sends warning message to base station daemon software system, the operator on duty of notice transformer station.Thereby the operator on duty can take solution fast, eliminates fault or hidden danger, guarantees the safe operation of transformer station.
The beneficial effect that adopts technique scheme to produce is: 1) assist or replace the mode of manual inspection by patrolling and examining platform, can effectively eliminate personnel's work danger, the protection personal safety; 2) audio detection subsystem can effectively detect the abnormal sound of substation equipment, improves the reliability and stability of patrolling and examining, and safeguards the normal operation of transformer station; 3) patrol and examine all devices in the platform samsara measuring station, flexible, freely control, and only need assemble an acoustic pickup, the quantity that has reduced other scheme sound intermediate frequency sensors with dispose difficulty, with low cost, device is simple and easy and reliability is high; 4) audio detection subsystem and computer subsystem real-time Communication for Power, computer subsystem can receive, analyze, show various voice datas in real time, in time abnormal results is reported to the police, the operation hidden danger or the fault of the quick abatement apparatus of assistance personnel can effectively guarantee to patrol and examine quality.
Description of drawings
Fig. 1 is the theory diagram of the utility model embodiment;
Fig. 2 is the process flow diagram of the utility model embodiment detection method;
Fig. 3 is the software flow pattern of training of the utility model audio frequency and identification module.
Embodiment
Referring to Fig. 1, present embodiment comprise the audio detection subsystem and with the computer subsystem of described audio detection subsystem wireless telecommunications;
Described audio detection subsystem comprises audio collection module, Video service module, audio frequency training and identification module, memory module and first communication module; The input end of the output termination Video service module of described audio collection module, the output ending connecting audio training of described Video service module and the respective input of identification module, the corresponding output end of described audio frequency training and identification module connects the input end of first communication module, and described memory module is connected with identification module is two-way with the audio frequency training;
Described computer subsystem comprises main frame, voice data display module, alarm module and second communication module that base station daemon software system is housed; The corresponding output end of described main frame connects the input end of voice data display module and alarm module respectively; The respective input of the output termination main frame of described second communication module.
Present embodiment also comprises patrols and examines platform, and the described platform of patrolling and examining adopts electric inspection process robot (hereinafter to be referred as robot), and its model is LER-3000, is the carrier of audio detection subsystem, is responsible for loading the audio detection subsystem and carries out patrol task.The corresponding output end of described robot connects the start end of audio detection module, when robot when route moves to the equipment point of setting according to the rules, its corresponding output end can trigger the start end of audio detection module, and described audio detection module begins the sound of collecting device operation.
The audio collection module adopts tone arm, and described acoustic pickup can be realized the high-fidelity recording operation of open air, long distance environment.Described acoustic pickup is installed in the front portion of crusing robot, the substation equipment sound collection of robot place of arrival is got up, it adopts firm, durable metal shell attractive in appearance, electroplating surface is handled, has waterproof and dampproof, high-fidelity, low noise characteristics are for follow-up Audio Signal Processing provides reliable voice data.
The Video service module directly links to each other with described tone arm, is used to receive the voice data of acoustic pickup, finishes the function of digital signal compression and transmission.Compressed format adopts a rule pcm audio form, and transmission mode adopts the ICP/IP protocol transmission standard.
Audio frequency training and identification module are assemblied in robot interior, are made up of ARM9 microprocessor and DSP microprocessor; Described ARM9 microprocessor adopts the S3C2440 chip, is used for the voice data that the receiver, video service module is sent, and realizes data communication function; Described DSP microprocessor adopts the TMS320X2812 chip, finishes the function of training and identification voice data.Described audio frequency training comprises training program and recognizer with identification.Described training program is promptly by the VQ(vector quantization) algorithm trains normal substation equipment operation sound, obtains the normal sound feature database, and this feature database is stored in memory module; Training work only need be carried out once, just can use this feature database to carry out the work of all audio identification.Described recognizer, it is the subband feature that the DSP microprocessor extracts the voice data of current collection earlier, compare in the audio frequency characteristics storehouse of then subband feature being advanced and leaving in the memory module in advance, if comparison result shows is FALSE, the cacophonia that then shows current transformer station equipment operation, simultaneously, comparison result is transferred to ARM9 and is sent to base station daemon software system.
The VQ(vector quantization) algorithm is a kind of important method for classifying modes.In audio recognition systems, vector quantization can be used to each voice data to be identified is carried out modeling.Promptly in the training stage, with the LBG algorithm audio frequency characteristics there is not tutor's pattern clustering, form each code book; At cognitive phase, seek the average minimum quantization distortion distance between tested speech and each code book, promptly export apart from reckling as recognition result.Whether finally can differentiate voice data unusual.
Described memory module is the FLASH memory device that is connected on the ARM9 microprocessor.Described memory module is used to store the audio frequency characteristics storehouse of training formation and the result after the audio identification, and operating system nucleus and file system etc.
Described computer subsystem is arranged on transformer station's master-control room, but and being arranged on the audio detection subsystem of patrolling and examining on the platform by mutual communication between first communication module and second communication module, described first communication module and second communication module meet the 802.11n agreement; Computer subsystem in time receives the abnormal results of audio detection and reports to the police by alarm module; Simultaneously, can carry out the displaying of voice data to staff on duty or related personnel, as Wave data, subband feature data, this task is born by the voice data display module.
Adopt technique scheme to carry out the method that the power equipment cacophonia detects, carry out according to following step, referring to Fig. 2 ~ Fig. 3:
(1) starts the electric inspection process robot;
(2) described electric inspection process robot moves to power equipment according to fixed route and patrols and examines a little, triggers the start end of described audio collection module, and described audio collection module is gathered the voice data of power equipment;
(3) adopt the Video service module to receive the voice data of audio collection module, carry out digital signal compression and transmission;
(4) adopting audio frequency to train with identification module carries out the voice data of receiver, video service module transmission and carries out the training or the identification of voice data;
At first judge the audio frequency characteristics data that whether have this equipment in the audio frequency characteristics storehouse, when having the audio frequency characteristics of this equipment, then do not need to carry out training program, directly enter recognizer, otherwise enter training program.
When the needs training, enter training program, normal substation equipment operation sound is trained, get the normal audio feature database, be stored in the described memory module;
When not needing to train, enter recognizer, the DSP microprocessor extracts the subband feature of the voice data of current collection earlier, is compared in described subband feature and the audio frequency characteristics storehouse that is stored in the described memory module then;
(5) training of described audio frequency and identification module transfer to main frame with the real-time communication of comparison result by described first communication module and second communication module, when comparison result is unusual, alarm module sounds the alarm, voice data shows audio frequency Wave data and subband feature, otherwise, the only Wave data of output audio and subband feature;
(6) judge whether patrol and examine route all patrols and examines and finish,, finish, otherwise enter step (2) when all patrolling and examining when finishing.
To sum up, when robot movement arrives the substation equipment next door, robot can start the audio collection module, record the operation sound of substation equipment with the sampling rate of 8k by acoustic pickup, behind the sound recording, import the Video service module into, the Video service module is encoded to this sound and is compressed, and forms the sound signal that A leads the PCM form.This digital signal can enter audio frequency training and identification module.
Audio frequency training and identification module have two branches, i.e. training function and recognition function.Before robot carried out patrol task for the first time, training function was enabled by robot.The function of training is the sound that the receiver, video service module transmits, and extracts the feature of this sound, produces the audio frequency characteristics storehouse, and this feature database and the sound that sends are together deposited in memory module.The function of training only need be carried out once, just can produce the audio frequency characteristics storehouse, for recognition function is got ready.After the function of identification is the sound of receiver, video service module transmission, extract the feature of sound to be detected, and take out the good sound characteristic storehouse of precondition from memory module, and the feature of sound characteristic storehouse and sound to be identified is compared, thereby draw comparison result.If comparison result is FALSE, it is unusual to illustrate that sound to be detected exists, audio frequency training and identification module and computer subsystem wireless telecommunications, and then alarm module can start warning, simultaneously, the voice data display module can show some data and the feature of this sound.
Claims (4)
1. cacophonia detection system that is used for power equipment, it is characterized in that described system comprise the audio detection subsystem and with the computer subsystem of described audio detection subsystem wireless telecommunications;
Described audio detection subsystem comprises audio collection module, Video service module, audio frequency training and identification module, memory module and first communication module; The input end of the output termination Video service module of described audio collection module, the output ending connecting audio training of described Video service module and the respective input of identification module, the corresponding output end of described audio frequency training and identification module connects the input end of first communication module, and described memory module is connected with identification module is two-way with the audio frequency training;
Described computer subsystem comprises main frame, voice data display module, alarm module and second communication module that base station daemon software system is housed; The respective input of the output termination main frame of described second communication module; The corresponding output end of described main frame connects the input end of voice data display module and alarm module respectively.
2. the cacophonia detection system that is used for power equipment according to claim 1 is characterized in that also comprising and patrols and examines platform, and the described platform of patrolling and examining comprises travel mechanism and the control module of controlling described travel mechanism; Described audio detection subsystem is arranged on described patrolling and examining on the platform.
3. the cacophonia detection system that is used for power equipment according to claim 2, it is characterized in that described audio frequency is trained and identification module is made up of ARM9 microprocessor and DSP microprocessor, described ARM9 microprocessor adopts the S3C2440 chip, and described DSP microprocessor adopts the TMS320X2812 chip.
4. the cacophonia detection system that is used for power equipment according to claim 3 is characterized in that describedly patrolling and examining platform to adopt model being the electric inspection process robot of LER-3000.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011201972816U CN202083757U (en) | 2011-06-13 | 2011-06-13 | Sound abnormality detecting system for power equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011201972816U CN202083757U (en) | 2011-06-13 | 2011-06-13 | Sound abnormality detecting system for power equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN202083757U true CN202083757U (en) | 2011-12-21 |
Family
ID=45344382
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2011201972816U Expired - Fee Related CN202083757U (en) | 2011-06-13 | 2011-06-13 | Sound abnormality detecting system for power equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN202083757U (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102322943A (en) * | 2011-06-13 | 2012-01-18 | 河北省电力公司超高压输变电分公司 | Detection system and method for sound abnormality of power equipment |
| CN110595609A (en) * | 2019-09-29 | 2019-12-20 | 国网河南省电力公司南召县供电公司 | Diagnosis device for rapidly judging fault of power transformation equipment through sound abnormity |
| CN111158337A (en) * | 2019-12-16 | 2020-05-15 | 上海集成电路研发中心有限公司 | Device and method for diagnosing running state of integrated circuit equipment |
| CN112014774A (en) * | 2020-03-26 | 2020-12-01 | 中国铁建电气化局集团第二工程有限公司 | Transformer fault inspection system and method based on sound processing |
| CN113484639A (en) * | 2021-07-02 | 2021-10-08 | 国网山东省电力公司潍坊供电公司 | Substation main equipment health diagnosis device based on' sound + |
-
2011
- 2011-06-13 CN CN2011201972816U patent/CN202083757U/en not_active Expired - Fee Related
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102322943A (en) * | 2011-06-13 | 2012-01-18 | 河北省电力公司超高压输变电分公司 | Detection system and method for sound abnormality of power equipment |
| CN102322943B (en) * | 2011-06-13 | 2013-01-16 | 国家电网公司 | Detection system and method for sound abnormality of power equipment |
| CN110595609A (en) * | 2019-09-29 | 2019-12-20 | 国网河南省电力公司南召县供电公司 | Diagnosis device for rapidly judging fault of power transformation equipment through sound abnormity |
| CN111158337A (en) * | 2019-12-16 | 2020-05-15 | 上海集成电路研发中心有限公司 | Device and method for diagnosing running state of integrated circuit equipment |
| CN112014774A (en) * | 2020-03-26 | 2020-12-01 | 中国铁建电气化局集团第二工程有限公司 | Transformer fault inspection system and method based on sound processing |
| CN113484639A (en) * | 2021-07-02 | 2021-10-08 | 国网山东省电力公司潍坊供电公司 | Substation main equipment health diagnosis device based on' sound + |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102322943B (en) | Detection system and method for sound abnormality of power equipment | |
| CN202083757U (en) | Sound abnormality detecting system for power equipment | |
| CN101150788B (en) | Self modulation radio broadcast terminal system and its monitoring processor | |
| CN212207527U (en) | Transformer on-line monitoring device based on multi-source information fusion | |
| CN110208022A (en) | Power equipment multiple features audio-frequency fingerprint fault diagnosis method and system based on machine learning | |
| CN106066254B (en) | The detection in real time of factory's failure based on Internet of Things and positioning system and method | |
| CN109695475A (en) | A kind of coal mine roadway exception monitoring device and method based on sound | |
| CN106003040A (en) | Transformer substation inspection robot system with obstacle avoidance function | |
| CN102023604A (en) | Intelligent online monitoring system capable of preventing external damage on transmission line | |
| CN106408852A (en) | Robot alarm system based on mobile Internet | |
| CN113595251B (en) | Automatic monitoring and early warning system and method for substation power equipment | |
| CN110525456A (en) | A kind of train safe driving monitoring system and method | |
| CN202837484U (en) | Ultrasonic partial discharge detection system with intelligent substation inspection robot | |
| CN106057195A (en) | Unmanned aerial vehicle detection system based on embedded audio recognition | |
| CN105897483B (en) | Airplane fault real time monitoring and positioning system and method based on Internet of Things | |
| CN208924280U (en) | A kind of Community Watch management system | |
| CN203466977U (en) | Coal mine staff life security management system based on RFID and ZigBee wireless sensor network | |
| CN203039803U (en) | Power transmission line remote monitoring system | |
| CN213799697U (en) | Railway electricity maintenance operation monitoring and management system | |
| CN109300279A (en) | A kind of shop security monitoring method | |
| CN202854284U (en) | Transformer substation intelligent inspection robot based on ultrasonic detection technology | |
| CN108408521A (en) | A kind of big data analysis system and method based on elevator passenger daily behavior | |
| CN110379103A (en) | The method for preventing bridge security monitoring device stolen | |
| CN110201606B (en) | System, method and device for monitoring top hammer of cubic press | |
| CN103593929A (en) | Anti-theft tower monitoring system and method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| ASS | Succession or assignment of patent right |
Owner name: THE MAINTENANCE BRANCH OF HEBEI ELECTRIC POWER COR Free format text: FORMER OWNER: SHANDONG LUNENG INTELLIGENT TECHNOLOGY CO., LTD. Effective date: 20121210 Owner name: STATE GRID CORPORATION OF CHINA Free format text: FORMER OWNER: HEBEI POWER COMPANY ULTRA-HV TRANSMISSION + DISTRIBUTION COMPANY Effective date: 20121210 |
|
| C41 | Transfer of patent application or patent right or utility model | ||
| COR | Change of bibliographic data |
Free format text: CORRECT: ADDRESS; FROM: 050070 SHIJIAZHUANG, HEBEI PROVINCE TO: 100761 DONGCHENG, BEIJING |
|
| TR01 | Transfer of patent right |
Effective date of registration: 20121210 Address after: 100761 West Chang'an Avenue, Beijing, No. 86 Patentee after: State Grid Corporation of China Patentee after: Maintenance Branch, Hebei Electric Power Co.,Ltd. Patentee after: Shandong Luneng Intelligent Technology Co., Ltd. Address before: 050070 Hebei city of Shijiazhuang province Zhong Sheng Lu No. 66 Hebei EHV branch Patentee before: Hebei Power Company Ultra-HV Transmission & Distribution Company Patentee before: Shandong Luneng Intelligent Technology Co., Ltd. |
|
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20111221 Termination date: 20180613 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |