CN116311046A - Power equipment acoustic image monitoring method and system based on multi-model fusion - Google Patents
Power equipment acoustic image monitoring method and system based on multi-model fusion Download PDFInfo
- Publication number
- CN116311046A CN116311046A CN202310176299.5A CN202310176299A CN116311046A CN 116311046 A CN116311046 A CN 116311046A CN 202310176299 A CN202310176299 A CN 202310176299A CN 116311046 A CN116311046 A CN 116311046A
- Authority
- CN
- China
- Prior art keywords
- acoustic
- power equipment
- model
- monitoring
- data
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 92
- 230000004927 fusion Effects 0.000 title claims abstract description 37
- 238000000034 method Methods 0.000 title claims abstract description 37
- 230000002159 abnormal effect Effects 0.000 claims abstract description 64
- 238000007781 pre-processing Methods 0.000 claims abstract description 26
- 230000003287 optical effect Effects 0.000 claims abstract description 20
- 238000012937 correction Methods 0.000 claims description 21
- 230000005856 abnormality Effects 0.000 claims description 16
- 238000001228 spectrum Methods 0.000 claims description 13
- 230000003595 spectral effect Effects 0.000 claims description 11
- 238000003384 imaging method Methods 0.000 claims description 3
- 238000012935 Averaging Methods 0.000 claims description 2
- 238000012545 processing Methods 0.000 claims description 2
- 238000002310 reflectometry Methods 0.000 claims 1
- 230000008569 process Effects 0.000 description 6
- 230000009471 action Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000017525 heat dissipation Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/80—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/194—Terrestrial scenes using hyperspectral data, i.e. more or other wavelengths than RGB
-
- 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
- G10L15/00—Speech recognition
- G10L15/08—Speech classification or search
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Remote Sensing (AREA)
- Databases & Information Systems (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Computational Linguistics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The application provides a power equipment acoustic image monitoring method and system based on multi-model fusion, comprising the following steps: the monitoring module monitors whether abnormal fluctuation occurs in the power equipment; acquiring acoustic characteristics obtained by monitoring the power equipment by an acoustic identification module; preprocessing the acoustic characteristics to obtain a preprocessing model; comparing the pretreatment model with an acoustic model of the power equipment in a normal working state to obtain a difference recognition result; recording a difference extreme point in the difference recognition result, and obtaining a model ratio according to the difference extreme point; and determining whether the power equipment fails according to the model ratio. According to the power equipment acoustic image monitoring method and system based on multi-model fusion, acoustic characteristics and abnormal fluctuation of the power equipment monitored by the monitoring module are corresponding to judge whether the abnormal fluctuation occurs, optical data are utilized to perform state analysis on the power equipment, whether the power equipment is abnormal or not is rapidly determined, and the position of the abnormal power equipment is located.
Description
Technical Field
The application relates to an acoustic image monitoring method and system for power equipment based on multi-model fusion.
Background
In the operation process of the power equipment, when a certain equipment is abnormal, the power equipment can influence other equipment on the power grid, so that the operation state of the power grid needs to be monitored in real time, and when the abnormal condition of the equipment is found, the equipment is overhauled in time. Although the current monitoring mode can timely monitor the electric quantity fluctuation of the power grid system, the abnormality of the equipment is fed back through the electric quantity fluctuation, but abnormal equipment cannot be located timely, the equipment on the power grid system needs to be checked one by one for a long time to be located on the corresponding equipment, a great amount of time is consumed, and whether the equipment is caused by abnormality or not cannot be judged aiming at some small abnormal fluctuation, so that the condition that the equipment is not found timely, technical maintenance is not performed, and power grid outage is caused is often caused. How to more efficiently judge whether the power grid equipment is abnormal becomes an urgent problem to be solved.
Disclosure of Invention
The invention aims to provide a power equipment acoustic image monitoring method and system based on multi-model fusion, which have the advantage of high efficiency of finding abnormal power grid equipment.
In order to achieve the above object, the present invention provides a method and a system for monitoring an acoustic image of a power device based on multi-model fusion, the method for monitoring an acoustic image of a power device based on multi-model fusion comprising:
s10, a monitoring module monitors whether abnormal fluctuation occurs in the power equipment, and if the abnormal fluctuation is not monitored, the S10 is repeatedly executed; if the abnormal fluctuation is detected, the method goes to S20;
s20, acquiring acoustic characteristics obtained by monitoring the power equipment by an acoustic identification module;
s30, preprocessing the acoustic features to obtain a preprocessing model;
s40, comparing the preprocessing model with an acoustic model which is obtained in advance by the power equipment and is in a normal working state to obtain a difference recognition result of the preprocessing model and the acoustic model;
s50, recording a difference extreme point in the difference recognition result, and obtaining a model ratio according to the difference extreme point;
s60, determining whether the power equipment fails according to the model ratio.
In the scheme, whether the power equipment with abnormal fluctuation is abnormal or not is determined by arranging the acoustic identification module, and the judging efficiency of determining whether the power equipment is abnormal or not when the abnormal fluctuation occurs is improved.
Preferably, the monitoring method further comprises:
s70, an optical identification module monitors the power equipment to obtain spectrum data;
s80, carrying out data correction on the spectrum data to obtain image data;
s90, matching the abnormal fluctuation, the model ratio and the image data in the same time period to obtain a matching result;
and S100, determining the power equipment with faults according to the matching result.
Preferably, the spectral data comprises data obtained by a hyperspectral sensor and an imaging spectral sensor.
In the scheme, the obtained hyperspectral data has the characteristic of multiple wave bands, tens, hundreds and thousands of wave bands can be provided for each pixel, the time period can be more accurately determined, and the subsequent searching time is shortened.
Preferably, performing data correction on the spectrum data in step S80 to obtain image data of a fixed band includes performing correction operation on the spectrum data, where the correction operation corrects the reflectance of the hyperspectral data obtained by the hyperspectral sensor using black-and-white correction.
Preferably, the correction operation further comprises correcting the raw image obtained by the hyperspectral sensor using a multivariate scattering correction.
Preferably, the acoustic recognition module comprises a plurality of monitoring units, different monitoring units monitor acoustic features respectively, a plurality of submodel ratios are obtained by processing according to the different acoustic features, and a model ratio is obtained by averaging the plurality of submodel ratios.
In the scheme, the sub-model ratios obtained by the plurality of monitoring units are averaged to obtain the total model ratio, so that the problem that data deviation is large due to accidental deviation of a single acoustic unit is avoided.
Preferably, the spatial network around the power equipment is divided according to the location of the monitoring unit.
In the scheme, grids near the power equipment are divided, calculated values of all points in the grids are replaced by calculated values of central points of a single grid, and calculated amount is reduced.
Preferably, the acoustic features include voiceprints and acoustic field clouds of the electrical device.
The application also provides a power equipment acoustic image monitoring system based on multi-model fusion, wherein the monitoring system is used for implementing the power equipment acoustic image monitoring method based on multi-model fusion, and the monitoring system comprises the following components:
the monitoring module is used for monitoring whether abnormal fluctuation occurs in the power equipment or not;
the system comprises an acoustic identification module, a control module and a control module, wherein the acoustic identification module comprises a plurality of monitoring units, and the plurality of monitoring units are used for recording acoustic characteristics of the power equipment;
the optical identification module is used for monitoring the power equipment through a hyperspectral sensor;
the fusion comparison module is used for comparing the abnormal fluctuation data monitored by the monitoring module in the same time period with the acoustic characteristics monitored by the acoustic identification module to obtain equipment abnormal data;
the equipment abnormality identification module is used for calculating an abnormal data value based on the abnormal data identified by the fusion comparison module and determining the abnormality type of the power equipment;
and the terminal identification module is used for determining the position of the power equipment with abnormal conditions according to the image data obtained by the optical identification module.
Preferably, the acoustic recognition module comprises an abnormal input part, an abnormal judgment part, a model comparison part and an abnormal data output part; and/or the number of the groups of groups,
the optical identification module comprises a data input part, an image preprocessing part, a wave band preprocessing part and a database recording part.
In summary, compared with the prior art, the method and the system for monitoring the acoustic image of the power equipment based on multi-model fusion have the following beneficial effects:
according to the power equipment acoustic image monitoring method and system based on multi-model fusion, the acoustic characteristics of each power equipment are monitored through the acoustic identification module, the acoustic characteristics are processed and judged, abnormal acoustic characteristics are output, and the acoustic characteristics and the abnormal fluctuation of the power equipment monitored by the monitoring module are subjected to temporal correspondence to judge whether abnormal fluctuation occurs. And when the abnormal fluctuation of the power equipment is identified, performing state analysis on the power equipment by utilizing the optical data monitored by the optical identification module. And determining whether the power equipment has problems or not by combining the data of the monitoring module, the acoustic identification module and the optical identification module, so that the position of the abnormal power equipment can be positioned by the image positioning module in time.
Drawings
Fig. 1 is a schematic diagram of the components of the power equipment acoustic image monitoring system based on multi-model fusion.
Fig. 2 is a schematic diagram of the composition of an acoustic recognition module of the power equipment acoustic image monitoring system based on multi-model fusion.
Fig. 3 is a schematic diagram of the components of the acousto-optic recognition module of the power equipment acoustic image monitoring system based on multi-model fusion.
Fig. 4 is a flowchart of a power equipment acoustic image monitoring method based on multi-model fusion according to the present application.
Detailed Description
The technical scheme, constructional features, achieved objects and effects of the embodiments of the present invention will be described in detail below with reference to fig. 1 to fig. 4 in the embodiments of the present invention.
It should be noted that, the drawings are in very simplified form and all use non-precise proportions, which are only used for the purpose of conveniently and clearly assisting in describing the embodiments of the present invention, and are not intended to limit the implementation conditions of the present invention, so that the present invention has no technical significance, and any modification of structure, change of proportion or adjustment of size, without affecting the efficacy and achievement of the present invention, should still fall within the scope covered by the technical content disclosed by the present invention.
It is noted that in the present invention, relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
As shown in fig. 4, the invention provides a power equipment acoustic image monitoring method based on multi-model fusion, which comprises the following steps:
s10, a monitoring module monitors whether abnormal fluctuation occurs in the power equipment, and if the abnormal fluctuation is not monitored, the S10 is repeatedly executed; if abnormal fluctuations are detected, the process proceeds to S20. The monitoring module is used for monitoring the power equipment and performing abnormal operation networking alarm in the power system. In the running process of the power system, the power output by different power equipment can fluctuate, sometimes the power fluctuates due to normal fluctuation caused by power consumption reduction of a user side, sometimes the power fluctuates due to abnormal fluctuation caused by faults of the power equipment, a monitoring module can monitor the power fluctuation of the power equipment, but the reason for the power fluctuation cannot be determined, and other modules are required to assist in judging to determine the reason for the power fluctuation.
S20, acquiring acoustic characteristics obtained by monitoring the power equipment by the acoustic identification module. The acoustic features include voiceprints and acoustic field clouds of the electrical device. The acoustic identification module comprises a plurality of monitoring units, and each monitoring unit is used for monitoring voiceprints and sound field cloud pictures of the power equipment respectively. When the power equipment operates in a normal state, a heat dissipation device or other devices in the power equipment can generate regular sound. When the power equipment fails, sounds different from those in the normal operation state are generated.
S30, preprocessing the acoustic features to obtain a preprocessing model. The pretreatment model is obtained after the pretreatment of the acoustic features, and comprises feature points of the acoustic features of the power equipment, and a comparison result is conveniently obtained through comparison of the feature points so as to determine whether the power equipment is in a normal running state.
S40, comparing the preprocessing model with an acoustic model which is obtained in advance by the power equipment and is in a normal working state to obtain a difference recognition result of the preprocessing model and the acoustic model. The acoustic characteristics of the power equipment in the normal running state are stored in a memory in advance, the acoustic characteristics of the power equipment in the period when the electric quantity fluctuation occurs are monitored by a monitoring module obtained by an acoustic identification module, preprocessing is carried out, and the preprocessing model is compared with the acoustic model of the power equipment in the normal state to obtain a difference identification result of the preprocessing model and the acoustic model. In the application, the acoustic characteristics refer to acoustic data collected by the acoustic identification module when abnormal fluctuation occurs in the power equipment, and the acoustic model refers to acoustic data collected by the acoustic identification module when the power equipment is in normal operation.
S50, recording a difference extreme point in the difference recognition result, and obtaining a model ratio according to the difference extreme point. In this embodiment, the difference extreme point may be obtained by a two-dimensional graph in which the X-axis is a time axis and the Y-axis is a sonic hertz axis. And comparing the difference extreme points of the power equipment in a normal working state with the difference extreme points of the power equipment in the condition of electric quantity fluctuation, and obtaining a model ratio by comparing the difference extreme points with the difference extreme points.
S60, determining whether the power equipment fails according to the model ratio. And the acoustic characteristics monitored by the acoustic identification module are used for verification to determine whether the electric quantity fluctuation of the power equipment is normal fluctuation or abnormal in the running state, so that the judging time is shortened, and the judging efficiency is improved.
In this embodiment, the monitoring method further includes:
s70, acquiring spectral data obtained by monitoring the power equipment by the optical identification module. The spectral data includes data obtained from hyperspectral sensors and imaging spectral sensors. The hyperspectral data obtained by the hyperspectral sensor has the characteristic of multiple wave bands, tens, hundreds and thousands of wave bands can be provided for each pixel, the time period required to be searched can be more accurately determined, and the search time is shortened. In this example, the spectral data is an HSI (Hue; saturation; luminance) spectrum.
S80, carrying out data correction on the optical data to obtain image data of a fixed wave band. In this embodiment, performing data correction on the spectral data to obtain image data of a fixed band includes performing correction operation on the spectral data, the correction operation correcting reflectance of the hyperspectral data obtained by the hyperspectral sensor using black-and-white correction. The correction operation further includes correcting the raw image obtained by the hyperspectral sensor using a multivariate scattering correction.
And S90, matching the abnormal fluctuation, the model ratio and the image data in the same time period to obtain a matching result. And searching the acoustic characteristics and the spectrum data in the corresponding time period according to the occurrence time of the abnormal fluctuation.
And S100, determining the power equipment with faults according to the matching result. After abnormal fluctuation of the power equipment is determined with the aid of the acoustic identification module, matching the acoustic characteristics and the spectrum data in the period of the abnormal fluctuation of the power equipment to determine the fault type of the fault equipment. The optical identification module determines the fault type of the power equipment and the specific position of the power equipment with the fault according to the spectrum data of the power equipment, transmits the data to an maintainer, and the maintainer can directly overhaul the corresponding power equipment without searching the equipment with the fault like the prior art, thereby improving the overhaul efficiency.
The acoustic identification module comprises a plurality of monitoring units, and different monitoring units are respectively positioned at different positions. And the different monitoring units monitor and obtain acoustic features respectively, process the acoustic features according to the different acoustic features to obtain a plurality of submodel ratios, and calculate the average value of the submodel ratios to obtain a model ratio. In this embodiment, the spatial network around the power device is divided according to the location where the listening unit is located. Through grid division, the calculated value of single-point controllable response power in the grid replaces the calculated value of all points in the grid, and the calculated amount is reduced.
As shown in fig. 1, the present invention further provides a power equipment acoustic image monitoring system based on multi-model fusion, where the monitoring system is configured to implement the power equipment acoustic image monitoring method based on multi-model fusion, and the monitoring system includes:
the monitoring module is used for monitoring whether abnormal fluctuation occurs in the power equipment. The monitoring module is used for the electric quantity output by the power equipment.
And the acoustic identification module comprises a plurality of monitoring units, and the plurality of monitoring units are used for recording the acoustic characteristics of the power equipment. The power equipment can make sound when working, but the sound that makes when normal work and power equipment take place equipment trouble is different, and the acoustic model of power equipment when normal work is recorded to the acoustic identification module at first under test environment, and the acoustic identification module is used for monitoring the sound that power equipment made in the course of working to compare with the acoustic model of advance storage, in order to judge whether the state of power equipment is normal.
The optical identification module is used for monitoring the power equipment through the hyperspectral sensor. The optical identification module acquires light waves of different wave bands emitted by the power equipment in the working state to judge the working state of the power equipment, and determines the position of the power equipment in an abnormal state according to the optical information.
The fusion comparison module is used for comparing the abnormal fluctuation data monitored by the monitoring module in the same time period with the acoustic characteristics monitored by the acoustic identification module to obtain equipment abnormal data. If the abnormal fluctuation data of the monitoring module and the acoustic characteristics obtained by the monitoring module obtained by the fusion comparison module are not in the same time period, the acoustic characteristics and the corresponding time points are stored for subsequent query comparison.
The equipment abnormality recognition module is used for determining the abnormality type of the abnormal power equipment, and based on the abnormal data recognized by the fusion comparison module, the equipment abnormality recognition module calculates an abnormal data value to determine the abnormality type of the power equipment.
And the terminal identification module is used for merging the time period of the power equipment failure determined by the comparison module and identifying the image data in the time period. And the terminal identification module determines the position of the power equipment with abnormal conditions according to the image data obtained by the optical identification module.
As shown in fig. 2, the acoustic recognition module includes an abnormality input section, an abnormality determination section, a model comparison section, and an abnormality data output section. The abnormal input part is used for preprocessing and modeling the sound field cloud image of the voiceprint data set and comparing the sound field cloud image with an acoustic model obtained in the power equipment testing stage. The model comparison part is used for model comparison and differentiation recognition, records differentiated extreme point data, and compares the extreme point data with the extreme point data to obtain a single model ratio. The abnormality data output unit outputs whether or not an abnormality has occurred in the power equipment and the type of the abnormality has occurred.
As shown in fig. 3, the optical recognition module includes a data input section, an image preprocessing section, a band preprocessing section, and a database recording section. The data input unit is used for inputting data obtained by the hyperspectral sensor. The image preprocessing part is used for sorting the image data to obtain a plurality of spectrum band data graphs. The band preprocessing part carries out data correction on the spectrum band data graph to obtain an image with a fixed band. The database recording part is used for recording the image wave band data in the corresponding time period of each device.
While the present invention has been described in detail through the foregoing description of the preferred embodiment, it should be understood that the foregoing description is not to be considered as limiting the invention. Many modifications and substitutions of the present invention will become apparent to those of ordinary skill in the art upon reading the foregoing. Accordingly, the scope of the invention should be limited only by the attached claims.
Claims (10)
1. The utility model provides a power equipment acoustic image monitoring method based on multi-model fusion, which is characterized in that the monitoring method comprises the following steps:
s10, a monitoring module monitors whether abnormal fluctuation occurs in the power equipment, and if the abnormal fluctuation is not monitored, the S10 is repeatedly executed; if the abnormal fluctuation is detected, the method goes to S20;
s20, acquiring acoustic characteristics obtained by monitoring the power equipment by an acoustic identification module;
s30, preprocessing the acoustic features to obtain a preprocessing model;
s40, comparing the preprocessing model with an acoustic model which is obtained in advance by the power equipment and is in a normal working state to obtain a difference recognition result of the preprocessing model and the acoustic model;
s50, recording a difference extreme point in the difference recognition result, and obtaining a model ratio according to the difference extreme point;
s60, determining whether the power equipment fails according to the model ratio.
2. The multi-model fusion-based power equipment acoustic image monitoring method of claim 1, wherein the monitoring method further comprises:
s70, acquiring spectral data obtained by monitoring the power equipment by an optical identification module;
s80, carrying out data correction on the spectrum data to obtain image data;
s90, matching the abnormal fluctuation, the model ratio and the image data in the same time period to obtain a matching result;
and S100, determining the power equipment with faults according to the matching result.
3. The multi-model fusion-based power device acoustic image monitoring method of claim 2, wherein the spectral data comprises data obtained by a hyperspectral sensor and an imaging spectral sensor.
4. The method for monitoring acoustic images of power equipment based on multi-model fusion according to claim 3, wherein performing data correction on the spectrum data to obtain image data of a fixed band in step S80 comprises performing correction operation on the spectrum data, wherein the correction operation corrects reflectivity of hyperspectral data obtained by the hyperspectral sensor by using black-and-white correction.
5. The method of power plant acoustic image monitoring based on multi-model fusion of claim 4, wherein the correcting operation further comprises correcting the raw image obtained by the hyperspectral sensor using a multivariate scattering correction.
6. The method for monitoring the acoustic image of the power equipment based on the multi-model fusion according to claim 1, wherein the acoustic recognition module comprises a plurality of monitoring units, the different monitoring units monitor respectively to obtain acoustic features, a plurality of submodel ratios are obtained by processing according to the different acoustic features, and a model ratio is obtained by averaging the submodel ratios.
7. The method for acoustic image monitoring of a power device based on multi-model fusion according to claim 6, wherein the spatial network around the power device is partitioned according to the location of the listening unit.
8. The multi-model fusion-based power device acoustic image monitoring method of claim 1, wherein the acoustic features comprise voiceprints and acoustic field clouds of the power device.
9. A power plant acoustic image monitoring system based on multi-model fusion, wherein the monitoring system is configured to perform the power plant acoustic image monitoring method based on multi-model fusion as set forth in any one of claims 1-8, the monitoring system comprising:
the monitoring module is used for monitoring whether abnormal fluctuation occurs in the power equipment or not;
the system comprises an acoustic identification module, a control module and a control module, wherein the acoustic identification module comprises a plurality of monitoring units, and the plurality of monitoring units are used for recording acoustic characteristics of the power equipment;
the optical identification module is used for monitoring the power equipment through a hyperspectral sensor;
the fusion comparison module is used for comparing the abnormal fluctuation data monitored by the monitoring module in the same time period with the acoustic characteristics monitored by the acoustic identification module to obtain equipment abnormal data;
the equipment abnormality identification module is used for calculating an abnormal data value based on the abnormal data identified by the fusion comparison module and determining the abnormality type of the power equipment;
and the terminal identification module is used for determining the position of the power equipment with abnormal conditions according to the image data obtained by the optical identification module.
10. The multi-model fusion-based power equipment acoustic image monitoring system according to claim 9, wherein the acoustic recognition module comprises an anomaly input portion, an anomaly determination portion, a model comparison portion, and an anomaly data output portion; and/or the number of the groups of groups,
the optical identification module comprises a data input part, an image preprocessing part, a wave band preprocessing part and a database recording part.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310176299.5A CN116311046A (en) | 2023-02-28 | 2023-02-28 | Power equipment acoustic image monitoring method and system based on multi-model fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310176299.5A CN116311046A (en) | 2023-02-28 | 2023-02-28 | Power equipment acoustic image monitoring method and system based on multi-model fusion |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116311046A true CN116311046A (en) | 2023-06-23 |
Family
ID=86837204
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310176299.5A Pending CN116311046A (en) | 2023-02-28 | 2023-02-28 | Power equipment acoustic image monitoring method and system based on multi-model fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116311046A (en) |
-
2023
- 2023-02-28 CN CN202310176299.5A patent/CN116311046A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111555716B (en) | Method, device, equipment and storage medium for determining working state of photovoltaic array | |
| JP2023508759A (en) | Method and Apparatus, Device and Storage Medium for Determining Operational State of Photovoltaic Array | |
| CN116880412B (en) | Visual production management platform based on cloud | |
| CN115174639B (en) | Industrial equipment management method and system based on Internet of things | |
| CN114169692A (en) | Equipment hidden danger processing system and method, electronic equipment and medium | |
| WO2015191906A1 (en) | Automatic recipe stability monitoring and reporting | |
| CN114255784A (en) | Substation equipment fault diagnosis method based on voiceprint recognition and related device | |
| CN115580972A (en) | Automatic control system and control method for intelligent stage light show | |
| CN117689270B (en) | Method, system and storage medium for improving quality management of power equipment production process | |
| CN116311046A (en) | Power equipment acoustic image monitoring method and system based on multi-model fusion | |
| CN117331790A (en) | Machine room fault detection method and device for data center | |
| CN116388685A (en) | Solar cell panel operation control system | |
| CN111539642B (en) | Object-oriented power plant data acquisition and processing system and method thereof | |
| CN113294295A (en) | System and method for detecting turbine performance and operational anomalies | |
| CN113806495B (en) | Outlier machine detection method and device | |
| CN116304763B (en) | Power data pre-analysis method, system, equipment and medium | |
| CN116453437B (en) | Display screen module testing method, device, equipment and storage medium | |
| CN117639281B (en) | On-load monitoring protection method and system for radio frequency power supply | |
| CN117408671A (en) | Ship equipment quality inspection operation and maintenance system | |
| CN118312910A (en) | Abnormal data screening method and system for water damage data | |
| CN117314394A (en) | Analytic hierarchy process-based wind turbine maintenance decision method, system, device and medium | |
| CN117019668A (en) | Packing carton quality detection system | |
| CN117412183A (en) | Visual imaging system, visual imaging method, electronic equipment and storage medium | |
| CN118157325A (en) | Real-time monitoring method and system for new energy power | |
| CN117148793A (en) | Real-time production line quality monitoring method, storage medium and computer equipment |
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 |