CN109979468A - A kind of lightning stroke optical path monitoring system and method - Google Patents
A kind of lightning stroke optical path monitoring system and method Download PDFInfo
- Publication number
- CN109979468A CN109979468A CN201910165412.3A CN201910165412A CN109979468A CN 109979468 A CN109979468 A CN 109979468A CN 201910165412 A CN201910165412 A CN 201910165412A CN 109979468 A CN109979468 A CN 109979468A
- Authority
- CN
- China
- Prior art keywords
- thunder
- lightning
- picture
- audio
- optical path
- 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.)
- Granted
Links
- 230000003287 optical effect Effects 0.000 title claims abstract description 46
- 208000025274 Lightning injury Diseases 0.000 title claims abstract description 42
- 238000012544 monitoring process Methods 0.000 title claims abstract description 36
- 238000000034 method Methods 0.000 title claims abstract description 18
- 238000013135 deep learning Methods 0.000 claims abstract description 20
- 238000001514 detection method Methods 0.000 claims abstract description 18
- 238000004364 calculation method Methods 0.000 claims description 6
- 208000010086 Hypertelorism Diseases 0.000 claims description 5
- 206010020771 Hypertelorism of orbit Diseases 0.000 claims description 5
- 239000000835 fiber Substances 0.000 claims description 5
- 230000003750 conditioning effect Effects 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 6
- XAGFODPZIPBFFR-UHFFFAOYSA-N aluminium Chemical compound [Al] XAGFODPZIPBFFR-UHFFFAOYSA-N 0.000 description 5
- 229910052782 aluminium Inorganic materials 0.000 description 5
- 239000004411 aluminium Substances 0.000 description 5
- 238000004891 communication Methods 0.000 description 5
- 230000005611 electricity Effects 0.000 description 4
- 239000013307 optical fiber Substances 0.000 description 4
- 238000013461 design Methods 0.000 description 3
- 230000005684 electric field Effects 0.000 description 3
- 230000008439 repair process Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 230000006378 damage Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000011835 investigation Methods 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000002265 prevention Effects 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 241000196324 Embryophyta Species 0.000 description 1
- 240000007594 Oryza sativa Species 0.000 description 1
- 235000007164 Oryza sativa Nutrition 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003032 molecular docking Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 235000009566 rice Nutrition 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/10—Alarms for ensuring the safety of persons responsive to calamitous events, e.g. tornados or earthquakes
-
- 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
- G10L17/00—Speaker identification or verification techniques
- G10L17/26—Recognition of special voice characteristics, e.g. for use in lie detectors; Recognition of animal voices
-
- 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)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computational Linguistics (AREA)
- Multimedia (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Acoustics & Sound (AREA)
- Human Computer Interaction (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Molecular Biology (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Environmental & Geological Engineering (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geology (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- General Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Signal Processing (AREA)
- Emergency Alarm Devices (AREA)
Abstract
The invention discloses a kind of lightning stroke optical paths to monitor system and method, belongs to lightning monitoring and analysis technical field;The monitoring system includes photoelectric sensing unit, core cell, image capture device and sound transducer;The photoelectric sensing unit is used to generate trigger signal when thunder and lightning occurs;Under the control of trigger signal, image capture device shoots thunder and lightning picture, and core cell controls the standby acquisition thunder audio-frequency information of the sound transducer;The core cell is used to judge whether the thunder and lightning picture meets Characteristics of Lightning by the algorithm of target detection based on deep learning, when thunder and lightning picture meets Characteristics of Lightning, judge whether the thunder audio-frequency information meets thunder feature by the ambient sound recognizer based on deep learning;When thunder audio-frequency information meets thunder feature, alarm signal is issued;The present invention identifies that double condition judgement improves the accuracy rate of Lightning Warning by thunder and lightning identification and thunder, reduces rate of false alarm, improves the confidence level of monitoring system.
Description
Technical field
The invention belongs to lightning monitorings and analysis technical field, utilize more mesh cameras and sensing more particularly, to a kind of
The lightning stroke optical path monitoring system and method for the comprehensive monitoring lightning stroke shape of device, scale, orientation.
Background technique
Lightning Disaster is a kind of irresistible natural calamity, frequently results in casualties, it is also possible to lead to power supply and distribution system
The damage of system, communication equipment, civil electric appliance causes forest fire, and the burnings such as storage, oil plant, oil field are even exploded, and causes weight
Huge economic loss and bad social influence.National over the years Lightning Disaster statistics indicate that, compared to other industry, electric power industry is more held
It is subject to thunder calamity, and consequence is also even more serious.It then becomes necessary to accomplish to the precognition in advance of Lightning Disaster, early warning, prevention, it is right
It is likely to occur or has occurred and that the region of thunder and lightning is identified, tracked and forecasting and warning, effectively prevention and reduce thunder and lightning and threaten.
Harm for pre- thunder-lightning to power industry establishes thunder and lightning detection early warning system;Lightning monitoring early warning at present
System is mostly basic equipment with atmospheric electric field detector, prejudges Thunderstorm Weather by analysis electric field strength variation tendency, advantage is
Monitoring range is wide, can issue Lightning Warning signal before lightning stroke occurs;But it has the disadvantage in that first is that this only pass through judgement
Whether electric field strength is more than that threshold value is arranged the high situation of empty alarm rate often occur come the method for carrying out early warning, and early warning accuracy rate needs
It improves;Second is that the precise optical image data of lightning strike spot can not be provided, reason analysis after being unfavorable for support accident, or investigation and
Repair lightning Protection Design weak spot.
Summary of the invention
For at least one defect or Improvement requirement of the prior art, the present invention provides a kind of monitorings of lightning stroke optical path
System and method, its object is to solve existing for existing detection early warning system, early warning accuracy rate is low, can not accurately obtain thunder
Hit the problem of optical image data a little is for lightning strike accident subsequent analysis.
To achieve the above object, according to one aspect of the present invention, a kind of lightning stroke optical path monitoring system, packet are provided
Include photoelectric sensing unit, core cell, image capture device and sound transducer;
The photoelectric sensing unit is used to generate trigger signal when thunder and lightning occurs;Under the control of the trigger signal,
Described image acquires equipment and shoots thunder and lightning picture, and the core cell controls the sound transducer and acquires thunder audio-frequency information;
The core cell is used to judge whether the thunder and lightning picture accords with by the algorithm of target detection based on deep learning
It closes Characteristics of Lightning and institute is judged by the ambient sound recognizer based on deep learning when thunder and lightning picture meets Characteristics of Lightning
State whether thunder audio-frequency information meets thunder feature;When thunder audio-frequency information meets thunder feature, alarm signal is issued.
Preferably, above-mentioned lightning stroke optical path monitors system, and core cell is also used to meet thunder in thunder audio-frequency information
Thunder and lightning distance and bearing is calculated when acoustic signature, by thunder and lightning time of origin, the information flag of thunder and lightning distance and bearing on thunder and lightning picture
And the thunder and lightning picture after label is sent to external server.
Preferably, above-mentioned lightning stroke optical path monitors system, and core cell includes support plate, and is arranged in the support plate
On core board, time service module and external memory;
The core board identifies for realizing the detection and identification of thunder and lightning picture, thunder information, when thunder and lightning picture meets thunder
Electrical feature and when thunder audio-frequency information meets thunder feature, issues alarm signal, and by thunder and lightning time of origin, thunder and lightning distance and side
Position information flag is on thunder and lightning picture;
The support plate is equipped with power module and multiple expansion interfaces;The power module is used for externally input exchange
Operating voltage needed for electricity is respectively converted into each hardware of internal system realizes system-oriented power supply output;The expansion interface
It is mainly used for realizing that the data-interface between core board and image capture device, external server extends;
The external memory is used to be locally stored the thunder and lightning picture and core of thunder audio-frequency information, image capture device acquisition
Thunder and lightning picture after core label;
The time service module passes through for obtaining the initial time of origin of thunder and lightning and the initial time of origin of thunder, core board in real time
Thunder calculates thunder and lightning distance with thunder and lightning time of origin difference.
Preferably, above-mentioned lightning stroke optical path monitors system, and photoelectric sensing unit includes the photoelectric sensing being sequentially connected
Device, amplifier, filter and voltage comparator;
When thunder and lightning occurs, the photoelectric sensor is influenced to generate step signal by flash of light;The step signal successively passes through
Trigger signal is generated after amplifier, filter and voltage comparator conditioning.
Preferably, above-mentioned lightning stroke optical path monitors system, further includes temperature sensor, the temperature sensor and core
Board communications connection, for acquiring temperature information when thunder and lightning occurs;Core board is according to the temperature information and thunder and thunder and lightning
Time difference calculates thunder and lightning distance;Specific formula for calculation are as follows:
Wherein, S indicates thunder and lightning distance, and unit is rice;A indicates the velocity of sound, and unit is meter per second,T indicates temperature
The thermodynamic temperature of sensor acquisition is spent, unit is Kelvin;T indicates thunder and thunder and lightning time difference, and unit is the second.
Preferably, above-mentioned lightning stroke optical path monitors system, and image capture device includes the industry of multiple and different directions
Camera, the sum of field angle of all industrial cameras is more than or equal to 360 °, to realize 360 ° of panoramic shootings;Core board is according to industrial phase
The thunder and lightning picture and corresponding camera direction of machine acquisition calculate thunder and lightning orientation, calculation formula are as follows:
Wherein, A indicates thunder and lightning orientation, is identified with azimuth, and unit is degree;O indicates the practical direction of industrial camera, with side
Parallactic angle indicates that unit is degree;F indicates that the field angle of industrial camera lens, unit are degree;X indicates the thunder of industrial camera acquisition
The width of electrograph piece, unit are pixel;X indicates the abscissa value of shared regional center point position of the thunder and lightning on picture, unit
For pixel.
Preferably, above-mentioned lightning stroke optical path monitors system, further includes fiber optical transceiver, core board is received by the optical fiber
It sends out device and the thunder and lightning picture after label is sent to external server.
Preferably, above-mentioned lightning stroke optical path monitors system, further includes camera support and cabinet;
The camera support includes support rod and the camera fixed part for being mounted on the supporting bar top;Industrial camera is equal
On the even prism for being mounted on the camera fixed part, to ensure that four industrial cameras being capable of 360 ° of monitoring peripheral regions;It is described
Cabinet is hung on support rod, and core cell is mounted on cabinet inside, and photoelectric sensor and microphone are mounted on crate part.
Other side according to the invention additionally provides a kind of lightning stroke optical path monitoring method, comprising the following steps:
S1: the trigger signal generated when thunder and lightning occurs by flash of light triggering is obtained;It is acquired under the control of the trigger signal
Thunder and lightning picture and thunder audio-frequency information;
S2: judge whether the thunder and lightning picture meets Characteristics of Lightning by the algorithm of target detection based on deep learning;When
When thunder and lightning picture meets Characteristics of Lightning, the thunder audio-frequency information is judged by the ambient sound recognizer based on deep learning
Whether thunder feature is met;
S3: when thunder audio-frequency information meets thunder feature, issuing alarm signal, calculate thunder and lightning distance and thunder and lightning orientation,
And by thunder and lightning time of origin, thunder and lightning distance and bearing label on thunder and lightning picture;And the thunder and lightning picture after label is sent to outer
Portion's server.
Preferably, above-mentioned lightning stroke optical path monitoring method, in step S2, when thunder and lightning picture does not meet Characteristics of Lightning
When, then determine false triggering and deletes thunder and lightning picture;
In step S3, when thunder audio-frequency information does not meet thunder feature, then thunder and lightning hypertelorism is determined, and by thunder and lightning figure
Piece and thunder audio-frequency information store.
In general, through the invention it is contemplated above technical scheme is compared with the prior art, can obtain down and show
Beneficial effect:
(1) lightning stroke optical path provided by the invention monitors system and method, acquires thunder and lightning figure when thunder and lightning occurs respectively
Piece and thunder audio-frequency information, first determine whether thunder and lightning picture meets Characteristics of Lightning;Thunder sound is further judged when these segmentation symbols match
When frequency information meets thunder feature;Only meet Characteristics of Lightning simultaneously and thunder feature just issues alarm signal;Pass through dual item
Part determines to improve the accuracy rate of Lightning Warning, reduces rate of false alarm, improve the confidence level of monitoring system;In addition, calculating thunder and lightning
Distance and bearing and by these information flags on thunder and lightning picture, the thunder and lightning picture after label makes for lightning strike accident subsequent analysis
With;
(2) lightning stroke optical path provided by the invention monitors system and method, can set for the emphasis in number kilometer range
It applies and carries out comprehensive monitoring, issue alarm when lightning strike accident occurs, and the image data captured can also be after support accident
The analysis of causes, and investigate and repair lightning Protection Design weak spot.
Detailed description of the invention
Fig. 1 is the logic diagram of lightning stroke optical path monitoring system provided in an embodiment of the present invention;
Fig. 2 is the composed structure schematic diagram of lightning stroke optical path monitoring system provided in an embodiment of the present invention;
Fig. 3 is the surface structure schematic diagram of lightning stroke optical path monitoring system provided in an embodiment of the present invention;Wherein, 1- phase
Machine support;2- support rod;3- camera fixed part;4- cast aluminium waterproof cabinet;
Fig. 4 is the flow chart of lightning stroke optical path monitoring method provided in an embodiment of the present invention;
Fig. 5 is the monitoring method flow chart provided in an embodiment of the present invention based on lightning stroke optical path monitoring system.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to the accompanying drawings and embodiments, right
The present invention is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and
It is not used in the restriction present invention.As long as in addition, technical characteristic involved in the various embodiments of the present invention described below
Not constituting a conflict with each other can be combined with each other.
Fig. 1 is the logic diagram of lightning stroke optical path monitoring system provided in an embodiment of the present invention;Fig. 2 is implementation of the present invention
The composed structure schematic diagram for the lightning stroke optical path monitoring system that example provides;Fig. 3 is lightning stroke optics provided in an embodiment of the present invention
The surface structure schematic diagram of trace monitor system;As shown in Figures 1 to 3, a kind of lightning stroke optical path prison provided by the present embodiment
Examining system, including core cell, photoelectric sensing unit, several industrial cameras, sound pick-up and cast aluminium waterproof cabinet;
The quantity of industrial camera is determined by the field angle of camera, it is only necessary to which the sum of the field angle for meeting all industrial cameras is greater than
Equal to 360 °, to realize 360 ° of panoramic shootings;4 industrial cameras are used in the present embodiment, the camera lens of the industrial camera is
2.8mm focal length, 100 ° of field angle, communication interface is USB2.0, and industrial camera is connected by usb hub with core cell;
Industrial camera is mounted on camera support, and the structure of the camera support is as shown in figure 3, including support rod and being mounted on support rod
The camera fixed part on top;Four industrial cameras are uniformly mounted on the prism of camera fixed part, to ensure four industrial phases
Machine being capable of 360 ° of monitoring peripheral regions;Camera fixed part includes four support bases, offers peace on the prism of each support base
Hole is filled, for docking an industrial camera;The quantity of support base on the camera fixed part with industrial camera quantity variation and
Variation;Core cell is placed on inside cast aluminium waterproof cabinet, and photoelectric sensing unit, sound pick-up and temperature sensor are mounted on cabinet
Outside, cast aluminium waterproof cabinet hang on support rod, it is ensured that demolition and maintenance are also convenient for while stability.
Photoelectric sensing unit is used to generate trigger signal when thunder and lightning occurs;Under the control of trigger signal, four industry
Camera shoots thunder and lightning picture to the sky of different angle simultaneously, and core cell starts microphone pick thunder audio-frequency information;The biography
Sound device is sound transducer module, for converting electric signal for thunder for core cell identification, to realize that thunder is monitored
Function;
Core cell filters out the picture for capturing thunder and lightning image from the picture that four industrial cameras are shot first, then
Judge whether thunder and lightning picture meets Characteristics of Lightning by the algorithm of target detection based on deep learning, when thunder and lightning picture meets thunder and lightning
When feature, judge whether thunder audio-frequency information meets thunder feature by the ambient sound recognizer based on deep learning;When
When thunder audio-frequency information meets thunder feature, issue alarm signal, and calculate thunder and lightning distance and bearing, by thunder and lightning time of origin,
The information flag of thunder and lightning distance and bearing is on thunder and lightning picture.Wherein, about the algorithm of target detection based on deep learning, this implementation
The a large amount of true thunder and lightning pictures of example acquisition first simultaneously demarcate the thunder and lightning position on each Zhang Lei electricity picture, generate training
Collection, is then trained neural network model by the training set, obtains the target detection model detected for thunder and lightning;About
Ambient sound recognizer based on deep learning, a large amount of true thunder audio data of the present embodiment acquisition, by the thunder sound
Frequency arrives the thunder detection model for thunder and lightning identification according to being trained in input deepness belief network.
Lightning stroke optical path provided by the embodiment monitors system, acquires thunder and lightning by industrial camera and sound pick-up respectively
When thunder and lightning picture and thunder audio-frequency information;Core cell first determines whether thunder and lightning picture meets Characteristics of Lightning;When these segmentation symbols match
When further judging that thunder audio-frequency information meets thunder feature;After only meeting Characteristics of Lightning and thunder feature simultaneously, core
Unit just issues alarm signal;The accuracy rate that Lightning Warning is improved by double condition judgement, reduces rate of false alarm, improves prison
The confidence level of examining system;In addition, calculating thunder and lightning distance and bearing and the thunder by these information flags on thunder and lightning picture, after label
Electrograph piece is for the use of lightning strike accident subsequent analysis.
As shown in Fig. 2, photoelectric sensing unit includes photoelectric sensor, amplifier, filter and voltage comparator, it is used for
Thunder and lightning generates trigger signal when occurring;When thunder and lightning occurs, photoelectric sensor is influenced to generate step signal, step letter by flash of light
Number by amplifier, filter and voltage comparator conditioning after obtain trigger signal;Voltage comparator respectively with four industrial phases
The external trigger interface of machine, digital I/O mouthfuls of core cell are connected, and the trigger signal of generation is sent to industrial camera and core simultaneously
Heart unit;After receiving trigger signal, four shoot thunder and lightning towards sky of the different industrial cameras to different angle simultaneously
Thunder and lightning picture is simultaneously sent to core cell by picture.
Core cell includes core board, time service module, external memory and support plate;
Core board identifies that the core board in the present embodiment is adopted for realizing the detection and identification of thunder and lightning picture, thunder information
Jetson TX2 is reached with tall and handsome;
Support plate is equipped with power module and multiple expansion interfaces;Power module for turning externally input alternating current respectively
Operating voltage needed for being changed to each hardware of internal system realizes system-oriented power supply output;Expansion interface is mainly used for realizing
Data-interface extension between core board and industrial camera, external server, interface type include but is not limited to that network interface, USB connect
Mouthful etc.;
Time service module is used for real-time acquisition time, and core board determines the initial time of origin of thunder and lightning and thunder by time service module
Initial time of origin, to calculate thunder and lightning distance according to thunder and thunder and lightning time difference.
External memory is used to be locally stored thunder audio-frequency information, the thunder and lightning picture of industrial camera acquisition and core board label
Thunder and lightning picture afterwards;The external memory uses SSD solid state hard disk.
After core board receives trigger signal, start sound pick-up, while starting core board timer internal, sound pick-up recording
Stop after 15 seconds;The thunder and lightning picture that shooting is obtained is by judging whether picture accords with based on the algorithm of target detection of deep learning
Characteristics of Lightning is closed, if meeting feature, starts time service module and obtains the initial time of origin of thunder and lightning, and 15 seconds just now are recorded
By judging whether recording meets thunder feature based on the ambient sound recognizer of deep learning, if meeting feature,
The initial time of origin of thunder is obtained by time service module, then calculates thunder and lightning distance and thunder and lightning orientation;If thunder and lightning picture is not met
Characteristics of Lightning, then it is assumed that false triggering simultaneously deletes picture;If picture meets Characteristics of Lightning, but recording does not meet thunder feature, then recognizes
For thunder and lightning hypertelorism, picture and recording are only stored in external memory;Only meet thunder and lightning and thunder feature simultaneously, it just can be
External server is sent on thunder and lightning picture after the information such as nominal time, orientation, distance, and by data in outer memory backup.
Wherein, core board is on the basis of the practical direction of industrial camera in captured picture including thunder and lightning image, with thunder
Electricity relative position shared in picture is that judgment basis calculates thunder and lightning orientation A, calculation formula are as follows:
Wherein, A indicates thunder and lightning orientation, is identified with azimuth, and unit is degree;O indicates the practical direction of industrial camera, with side
Parallactic angle indicates that unit is degree;F indicates that the field angle of industrial camera lens, unit are degree;X indicates the thunder of industrial camera acquisition
The width of electrograph piece, unit are pixel;X indicates the abscissa value of shared regional center point position of the thunder and lightning on picture, unit
For pixel.
One as the present embodiment preferably further includes temperature sensor in the monitoring system, the temperature sensor and core
Core communication connection, for acquiring temperature information when thunder and lightning occurs;When core board is according to temperature information and thunder and thunder and lightning
Between difference calculate thunder and lightning distance S;In air, velocity of sound formula can simplify are as follows:Wherein, a indicates the velocity of sound, single
Position is meter per second;T indicates the thermodynamic temperature of temperature sensor acquisition, and unit is Kelvin;
Therefore, the calculation formula of thunder and lightning distance S are as follows:
In formula, t indicates the difference of thunder and lightning initial time of origin and the initial time of origin of thunder;In the not high field of required precision
It closes, velocity of sound empirical value a=340 meter per second also can be used directly to calculate thunder and lightning distance, i.e. thunder and lightning distance S=t × 340, at this time then
No setting is required temperature sensor.
One as the present embodiment is preferred, further includes that the optical fiber being arranged in cast aluminium waterproof cabinet is received in the monitoring system
Device is sent out, core cell is communicated to connect by fiber optical transceiver and external server, will be marked with thunder and lightning time of origin, thunder and lightning side
The thunder and lightning picture of position and range information is sent to external server;Fiber optical transceiver converts the Ethernet interface on core cell
At optical fiber interface, make to pass through optical-fibre communications between monitoring system and external server.
The present embodiment additionally provides a kind of lightning stroke optical path monitoring method, as shown in Figure 4, comprising the following steps:
S101: the trigger signal generated when thunder and lightning occurs by flash of light triggering is obtained;Thunder is acquired under the control of trigger signal
Electrograph piece and thunder audio-frequency information;
S102: judge whether the thunder and lightning picture meets Characteristics of Lightning by the algorithm of target detection based on deep learning;
When thunder and lightning picture meets Characteristics of Lightning, judge that the thunder audio is believed by the ambient sound recognizer based on deep learning
Whether breath meets thunder feature;
When thunder and lightning picture does not meet Characteristics of Lightning, then determines false triggering and delete thunder and lightning picture;
S103: when thunder audio-frequency information meets thunder feature, alarm signal is issued, calculates thunder and lightning distance and thunder and lightning side
Position, and by thunder and lightning time of origin, thunder and lightning distance and bearing label on thunder and lightning picture;And the thunder and lightning picture after label is sent to
External server;
When thunder audio-frequency information does not meet thunder feature, then thunder and lightning hypertelorism is determined, and by thunder and lightning picture and thunder
Audio-frequency information stores.
Fig. 5 is the monitoring method flow chart provided in this embodiment based on above-mentioned lightning stroke optical path monitoring system, such as Fig. 5
Shown, which includes:
S201: event occurs for photoelectric sensing unit real-time monitoring thunder and lightning, and when thunder and lightning occurs, photoelectric sensor is by flash of light shadow
It rings and generates trigger signal and the trigger signal is sent to core cell and industrial camera;Control of the industrial camera in trigger signal
Lower shooting thunder and lightning picture;
S202: core cell circulation waits trigger signal, after receiving trigger signal, starts sound pick-up, while starting core
Core timer internal is set with the record length to sound pick-up;The thunder and lightning figure that industrial camera is shot is received simultaneously
Piece, into algorithm of target detection queue;
S203: by judging whether picture meets Characteristics of Lightning based on the algorithm of target detection of deep learning, if not being inconsistent
It closes, is then determined as false triggering, stop recording and delete recording file and thunder and lightning picture;If thunder and lightning picture meets Characteristics of Lightning,
Judge whether to need to stop in advance recording;If so, stopping recording and deleting recording file;When thunder and lightning intensively occurs, twice
Or the time interval that multiple thunder and lightning occurs is too small, occurs for last thunder and lightning earlier than the thunder generation moment moment, then deletes first thunder
The corresponding thunder recording file of electricity, and the thunder information common as thunder and lightning twice using the recording file of last thunder and lightning triggering;If
It is no, then judge whether record length reaches the time of setting;When reaching the record length of setting, team is identified into ambient sound
Column;Otherwise continue to record;
S204: judge whether thunder audio-frequency information meets thunder spy by the ambient sound recognizer based on deep learning
Sign;If it is not, then determining thunder and lightning hypertelorism, thunder and lightning picture and recording are stored in external memory;If so, entering in next step;
S205: thunder and lightning azimuth-range is calculated, and the information such as thunder and lightning time of origin, thunder and lightning azimuth-range are demarcated in thunder
Electrograph on piece;
S206: calibrated thunder and lightning picture is sent to external server, and is backed up in external memory.
Early warning system is detected compared to existing thunder and lightning, lightning stroke optical path provided by the invention monitors system and method,
It identifies that double condition judgement improves the accuracy rate of Lightning Warning by thunder and lightning identification and thunder, reduces rate of false alarm, improve prison
The confidence level of examining system;Comprehensive monitoring can be carried out for the emphasis facility in number kilometer range, be sent out when lightning strike accident occurs
The image data alarmed, and captured out can also reason analysis after support accident, investigation and repair lightning Protection Design weak spot.
As it will be easily appreciated by one skilled in the art that the foregoing is merely illustrative of the preferred embodiments of the present invention, not to
The limitation present invention, any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should all include
Within protection scope of the present invention.
Claims (10)
1. a kind of lightning stroke optical path monitors system, which is characterized in that including photoelectric sensing unit, core cell, Image Acquisition
Equipment and sound transducer;
The photoelectric sensing unit is used to generate trigger signal when thunder and lightning occurs;It is described under the control of the trigger signal
Image capture device shoots thunder and lightning picture, and the core cell starts the sound transducer and acquires thunder audio-frequency information;
The core cell is used to judge whether the thunder and lightning picture meets thunder by the algorithm of target detection based on deep learning
Electrical feature judges the thunder by the ambient sound recognizer based on deep learning when thunder and lightning picture meets Characteristics of Lightning
Whether acoustic audio information meets thunder feature;When thunder audio-frequency information meets thunder feature, alarm signal is issued.
2. lightning stroke optical path monitors system as described in claim 1, which is characterized in that the core cell is also used in thunder
Acoustic audio information calculates thunder and lightning distance and bearing when meeting thunder feature, by thunder and lightning time of origin, thunder and lightning distance and bearing information
Label is sent to external server on thunder and lightning picture and by the thunder and lightning picture after label.
3. lightning stroke optical path monitors system as claimed in claim 2, which is characterized in that the core cell includes support plate,
And core board, time service module and external memory on the support plate are set;
The core board identifies for realizing the detection and identification of thunder and lightning picture, thunder information, when thunder and lightning picture meets thunder and lightning spy
Sign and thunder audio-frequency information is when meeting thunder feature, issues alarm signal, and thunder and lightning time of origin, thunder and lightning distance and bearing are believed
Breath label is on thunder and lightning picture;
The support plate is equipped with power module and multiple expansion interfaces;The power module is used for externally input alternating current point
Operating voltage needed for not being converted to each hardware of internal system realizes system-oriented power supply output;The expansion interface is main
For realizing the data-interface extension between core board and image capture device, external server;
The external memory is used to be locally stored the thunder and lightning picture and core board of thunder audio-frequency information, image capture device acquisition
Thunder and lightning picture after label;
The time service module passes through thunder for obtaining the initial time of origin of thunder and lightning and the initial time of origin of thunder, core board in real time
Thunder and lightning distance is calculated with thunder and lightning time of origin difference.
4. lightning stroke optical path as claimed in claim 1 or 3 monitors system, which is characterized in that the photoelectric sensing unit packet
Include the photoelectric sensor being sequentially connected, amplifier, filter and voltage comparator;
When thunder and lightning occurs, the photoelectric sensor is influenced to generate step signal by flash of light;The step signal is successively through amplifying
Trigger signal is generated after device, filter and voltage comparator conditioning.
5. lightning stroke optical path monitors system as claimed in claim 3, which is characterized in that it includes more that described image, which acquires equipment,
The industrial camera of a difference direction, the sum of field angle of all industrial cameras is more than or equal to 360 °, to realize 360 ° of panoramic shootings;
The thunder and lightning picture and corresponding camera direction that core board is acquired according to industrial camera calculate thunder and lightning orientation, calculation formula are as follows:
Wherein, A indicates thunder and lightning orientation, is indicated with azimuth;O indicates the practical direction of industrial camera, is indicated with azimuth;F table
Show the field angle of industrial camera lens;X indicates the width of the thunder and lightning picture of industrial camera acquisition;X indicates thunder and lightning on picture
Shared regional center point position abscissa value.
6. lightning stroke optical path as claimed in claim 3 or 5 monitors system, which is characterized in that it further include temperature sensor, institute
It states temperature sensor and core board communicates to connect, for acquiring air themperature information when thunder and lightning occurs;Core board is according to
Temperature information and thunder calculate thunder and lightning distance with the thunder and lightning time difference;Specific formula for calculation are as follows:
Wherein, S indicates thunder and lightning distance;A indicates the velocity of sound,T indicates the thermodynamic temperature of temperature sensor acquisition;t
Indicate thunder and thunder and lightning time difference.
7. lightning stroke optical path monitors system as claimed in claim 6, which is characterized in that further include fiber optical transceiver, core
Thunder and lightning picture after label is sent to external server by the fiber optical transceiver by plate.
8. lightning stroke optical path monitors system as claimed in claim 7, which is characterized in that further include camera support and cabinet;
The camera support includes support rod and the camera fixed part for being mounted on the supporting bar top;Industrial camera is uniformly pacified
On the prism of the camera fixed part;The cabinet is hung on support rod, and core cell is mounted on cabinet inside, light
Electric sensing unit, sound pick-up and temperature sensor are mounted on outside cabinet.
9. a kind of lightning stroke optical path monitoring method, which comprises the following steps:
S1: the trigger signal generated when thunder and lightning occurs by flash of light triggering is obtained;Thunder and lightning is acquired under the control of the trigger signal
Picture and thunder audio-frequency information;
S2: judge whether the thunder and lightning picture meets Characteristics of Lightning by the algorithm of target detection based on deep learning;Work as thunder and lightning
When picture meets Characteristics of Lightning, whether the thunder audio-frequency information is judged by the ambient sound recognizer based on deep learning
Meet thunder feature;
S3: when thunder audio-frequency information meets thunder feature, issuing alarm signal, calculates thunder and lightning distance and thunder and lightning orientation, and will
Thunder and lightning time of origin, thunder and lightning distance and bearing label are on thunder and lightning picture.
10. as claimed in claim 9 lightning stroke optical path monitoring method, which is characterized in that in step S2, when thunder and lightning picture not
When meeting Characteristics of Lightning, then determines false triggering and delete thunder and lightning picture;
In step S3, when thunder audio-frequency information does not meet thunder feature, then determine thunder and lightning hypertelorism, and by thunder and lightning picture and
Thunder audio-frequency information stores.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910165412.3A CN109979468B (en) | 2019-03-05 | 2019-03-05 | Lightning stroke optical path monitoring system and method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910165412.3A CN109979468B (en) | 2019-03-05 | 2019-03-05 | Lightning stroke optical path monitoring system and method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109979468A true CN109979468A (en) | 2019-07-05 |
CN109979468B CN109979468B (en) | 2020-11-06 |
Family
ID=67077935
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910165412.3A Active CN109979468B (en) | 2019-03-05 | 2019-03-05 | Lightning stroke optical path monitoring system and method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109979468B (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110568273A (en) * | 2019-08-02 | 2019-12-13 | 国网浙江省电力有限公司嘉兴供电公司 | Lightning monitoring system and method based on ubiquitous power Internet of things |
CN112396116A (en) * | 2020-11-24 | 2021-02-23 | 武汉三江中电科技有限责任公司 | Thunder and lightning detection method and device, computer equipment and readable medium |
CN112744212A (en) * | 2019-10-30 | 2021-05-04 | 比亚迪股份有限公司 | Vehicle control method and device and vehicle |
CN113960375A (en) * | 2021-10-18 | 2022-01-21 | 特斯联科技集团有限公司 | Artificial intelligent lightning detection system and method for early warning of forest and grassland fire |
CN114827466A (en) * | 2022-04-20 | 2022-07-29 | 武汉三江中电科技有限责任公司 | Human eye-imitated equipment image acquisition device and image acquisition method |
CN115116199A (en) * | 2022-06-27 | 2022-09-27 | 中科纯元(珠海)科技有限公司 | Thunder and lightning disaster monitoring system based on Internet of things |
CN117929861A (en) * | 2024-03-21 | 2024-04-26 | 云南能源投资股份有限公司 | Lightning detection method, device and equipment for wind power plant and storage medium |
Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP1611464A1 (en) * | 2003-03-24 | 2006-01-04 | Vaisala Oyj | System and method for spectral corrected lightning detection |
CN101545934A (en) * | 2009-04-29 | 2009-09-30 | 中国气象局气象探测中心 | Optical acoustic thunder and lightning detecting process and detector |
CN102680939A (en) * | 2012-04-06 | 2012-09-19 | 国网电力科学研究院武汉南瑞有限责任公司 | Method and device for positioning thunder based on sound-light-electricity synchronous observation |
CN102884400A (en) * | 2010-05-14 | 2013-01-16 | 索尼公司 | Information processing device, information processing system, and program |
CN103728503A (en) * | 2013-12-31 | 2014-04-16 | 国网电力科学研究院武汉南瑞有限责任公司 | Automatic lightning stroke three-dimensional discharge path recording system and method for ancient architectural complex |
CN104459349A (en) * | 2013-09-12 | 2015-03-25 | 龙源电力集团股份有限公司 | Wind power plant thunder and lightning monitoring system and method |
CN204795328U (en) * | 2015-07-10 | 2015-11-18 | 深圳市家贺光电有限公司 | Panoramic picture's industry camera is looked over through WIFI in real time |
CN105791917A (en) * | 2014-12-24 | 2016-07-20 | 中国电信股份有限公司 | Method and device for controlling shutdown of outdoor advertisement for lightning protection |
CN106442558A (en) * | 2016-10-21 | 2017-02-22 | 上海梓威自动化科技有限公司 | Mechanical vision detection device |
CN106707371A (en) * | 2016-11-21 | 2017-05-24 | 深圳市气象服务中心 | Lightning monitoring early-warning and alert service system and early warning method thereof |
CN107707870A (en) * | 2016-08-09 | 2018-02-16 | 李艳超 | A kind of thunder and lightning IMAQ positioning detection device |
CN108872754A (en) * | 2018-08-06 | 2018-11-23 | 重庆市亨特尔电力科技有限公司 | A kind of comprehensive on-line monitoring system |
-
2019
- 2019-03-05 CN CN201910165412.3A patent/CN109979468B/en active Active
Patent Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP1611464A1 (en) * | 2003-03-24 | 2006-01-04 | Vaisala Oyj | System and method for spectral corrected lightning detection |
CN101545934A (en) * | 2009-04-29 | 2009-09-30 | 中国气象局气象探测中心 | Optical acoustic thunder and lightning detecting process and detector |
CN102884400A (en) * | 2010-05-14 | 2013-01-16 | 索尼公司 | Information processing device, information processing system, and program |
CN102680939A (en) * | 2012-04-06 | 2012-09-19 | 国网电力科学研究院武汉南瑞有限责任公司 | Method and device for positioning thunder based on sound-light-electricity synchronous observation |
CN104459349A (en) * | 2013-09-12 | 2015-03-25 | 龙源电力集团股份有限公司 | Wind power plant thunder and lightning monitoring system and method |
CN103728503A (en) * | 2013-12-31 | 2014-04-16 | 国网电力科学研究院武汉南瑞有限责任公司 | Automatic lightning stroke three-dimensional discharge path recording system and method for ancient architectural complex |
CN105791917A (en) * | 2014-12-24 | 2016-07-20 | 中国电信股份有限公司 | Method and device for controlling shutdown of outdoor advertisement for lightning protection |
CN204795328U (en) * | 2015-07-10 | 2015-11-18 | 深圳市家贺光电有限公司 | Panoramic picture's industry camera is looked over through WIFI in real time |
CN107707870A (en) * | 2016-08-09 | 2018-02-16 | 李艳超 | A kind of thunder and lightning IMAQ positioning detection device |
CN106442558A (en) * | 2016-10-21 | 2017-02-22 | 上海梓威自动化科技有限公司 | Mechanical vision detection device |
CN106707371A (en) * | 2016-11-21 | 2017-05-24 | 深圳市气象服务中心 | Lightning monitoring early-warning and alert service system and early warning method thereof |
CN108872754A (en) * | 2018-08-06 | 2018-11-23 | 重庆市亨特尔电力科技有限公司 | A kind of comprehensive on-line monitoring system |
Non-Patent Citations (1)
Title |
---|
叶江荣: "雷电的声、光信号监测及定位研究", 《浙江大学》 * |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110568273A (en) * | 2019-08-02 | 2019-12-13 | 国网浙江省电力有限公司嘉兴供电公司 | Lightning monitoring system and method based on ubiquitous power Internet of things |
CN110568273B (en) * | 2019-08-02 | 2022-04-15 | 国网浙江省电力有限公司嘉兴供电公司 | Lightning monitoring system and method based on ubiquitous power Internet of things |
CN112744212A (en) * | 2019-10-30 | 2021-05-04 | 比亚迪股份有限公司 | Vehicle control method and device and vehicle |
CN112396116A (en) * | 2020-11-24 | 2021-02-23 | 武汉三江中电科技有限责任公司 | Thunder and lightning detection method and device, computer equipment and readable medium |
CN113960375A (en) * | 2021-10-18 | 2022-01-21 | 特斯联科技集团有限公司 | Artificial intelligent lightning detection system and method for early warning of forest and grassland fire |
CN114827466A (en) * | 2022-04-20 | 2022-07-29 | 武汉三江中电科技有限责任公司 | Human eye-imitated equipment image acquisition device and image acquisition method |
CN114827466B (en) * | 2022-04-20 | 2023-07-04 | 武汉三江中电科技有限责任公司 | Human eye-like equipment image acquisition device and image acquisition method |
CN115116199A (en) * | 2022-06-27 | 2022-09-27 | 中科纯元(珠海)科技有限公司 | Thunder and lightning disaster monitoring system based on Internet of things |
CN115116199B (en) * | 2022-06-27 | 2023-10-03 | 圣其安全技术(北京)有限公司 | Thunder and lightning disaster monitoring system based on Internet of things |
CN117929861A (en) * | 2024-03-21 | 2024-04-26 | 云南能源投资股份有限公司 | Lightning detection method, device and equipment for wind power plant and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN109979468B (en) | 2020-11-06 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109979468A (en) | A kind of lightning stroke optical path monitoring system and method | |
CN110321853B (en) | Distributed cable external-damage-prevention system based on video intelligent detection | |
CN108319926A (en) | A kind of the safety cap wearing detecting system and detection method of building-site | |
CN106251568A (en) | A kind of fire alarm safety-protection system based on ultraviolet and image detecting technique and method | |
CN110648489B (en) | Storehouse early warning system based on infrared thermal imaging ignition point identification | |
WO2012126272A1 (en) | Full-view lightning event observation system and method | |
CN103795987B (en) | Embedded video collecting and processing system and implementation method thereof | |
KR101076734B1 (en) | Device for monitoring forest fire of information analysis type and method therefor | |
CN104284162A (en) | Video retrieval method and system | |
JP2019129735A (en) | Harmful animal capture support system | |
CN104574745A (en) | Security and protection monitoring system based on physiological feature | |
CN108806144A (en) | A kind of community alarm system based on 5G networks | |
KR102105275B1 (en) | Inverter Protection Monitoring System for Photovoltaic Power Generation | |
CN116743970A (en) | Intelligent management platform with video AI early warning analysis | |
CN209433517U (en) | It is a kind of based on more flame images and the fire identification warning device for combining criterion | |
KR101695369B1 (en) | Monitoring system having remote monitoring function | |
CN106710120A (en) | Front-end distributed forest smoke and fire identifying, locating and intelligent sensing system | |
KR101286200B1 (en) | Automatic recognition and response system of the armed robbers and the methods of the same | |
CN109120442A (en) | A kind of intelligent measurement management communication system and its control method | |
CN103728503A (en) | Automatic lightning stroke three-dimensional discharge path recording system and method for ancient architectural complex | |
JP2016119614A (en) | Dynamic body detection device, dynamic body detection method and dynamic body detection program | |
CN209805983U (en) | Data center computer room warning snapshot monitoring system | |
CN111726412A (en) | Intelligent building monitored control system based on big data | |
CN110481600B (en) | Unmanned autonomous comprehensive alarm system | |
KR101256452B1 (en) | The forest fire monitoring system and method |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: Lightning strike optical path monitoring system and method Effective date of registration: 20220331 Granted publication date: 20201106 Pledgee: Wuhan area branch of Hubei pilot free trade zone of Bank of China Ltd. Pledgor: WUHAN SANJIANG CLP TECHNOLOGY Co.,Ltd. Registration number: Y2022420000094 |