CN109979468B - Lightning stroke optical path monitoring system and method - Google Patents
Lightning stroke optical path monitoring system and method Download PDFInfo
- Publication number
- CN109979468B CN109979468B CN201910165412.3A CN201910165412A CN109979468B CN 109979468 B CN109979468 B CN 109979468B CN 201910165412 A CN201910165412 A CN 201910165412A CN 109979468 B CN109979468 B CN 109979468B
- Authority
- CN
- China
- Prior art keywords
- thunder
- lightning
- picture
- audio information
- 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.)
- Active
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 58
- 230000003287 optical effect Effects 0.000 title claims abstract description 43
- 208000025274 Lightning injury Diseases 0.000 title claims abstract description 39
- 238000000034 method Methods 0.000 title claims abstract description 21
- 238000013135 deep learning Methods 0.000 claims abstract description 20
- 238000001514 detection method Methods 0.000 claims abstract description 20
- 230000007613 environmental effect Effects 0.000 claims abstract description 8
- 238000004364 calculation method Methods 0.000 claims description 6
- 230000001960 triggered effect Effects 0.000 claims description 6
- 230000001143 conditioned effect Effects 0.000 claims description 3
- 239000000835 fiber Substances 0.000 claims 1
- 239000013307 optical fiber Substances 0.000 description 7
- 229910052782 aluminium Inorganic materials 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 238000013461 design Methods 0.000 description 3
- 230000005684 electric field Effects 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- XAGFODPZIPBFFR-UHFFFAOYSA-N aluminium Chemical compound [Al] XAGFODPZIPBFFR-UHFFFAOYSA-N 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000002411 adverse Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005266 casting Methods 0.000 description 1
- 238000002485 combustion reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 230000000192 social effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Images
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 lightning stroke optical path monitoring system and a method, belonging to the technical field of lightning monitoring and analysis; the monitoring system comprises a photoelectric sensing unit, a core unit, an image acquisition device and a sound sensor; the photoelectric sensing unit is used for generating a trigger signal when lightning occurs; under the control of the trigger signal, the image acquisition equipment shoots a thunder and lightning picture, and the core unit controls the sound sensor to acquire thunder and lightning audio information; the core unit is used for judging whether the thunder image accords with the thunder characteristic or not through a target detection algorithm based on deep learning, and judging whether the thunder audio information accords with the thunder characteristic or not through an environmental sound identification algorithm based on deep learning when the thunder image accords with the thunder characteristic; when the thunder audio information conforms to the thunder characteristics, an alarm signal is sent out; according to the invention, the accuracy of lightning early warning is improved through double condition judgment of lightning identification and thunder identification, the false alarm rate is reduced, and the reliability of a monitoring system is improved.
Description
Technical Field
The invention belongs to the technical field of lightning monitoring and analysis, and particularly relates to a lightning stroke optical path monitoring system and method for monitoring the shape, scale and direction of a lightning stroke in an all-around manner by using a multi-view camera and a sensor.
Background
The thunder disaster is an irresistible natural disaster, which often causes casualties, and can also cause damages to power supply and distribution systems, communication equipment and civil electric appliances, cause forest fires, combustion and even explosion of storage, oil refineries, oil fields and the like, and cause great economic loss and adverse social effects. Lightning disaster data in the whole country over the years shows that the power industry is more susceptible to lightning disasters and the consequences are more serious compared with other industries. Therefore, the method has to predict, early warn and prevent the thunder and lightning disaster in advance, identify, track, forecast and early warn the areas which are possible to generate or generate the thunder and lightning, and effectively prevent and reduce the thunder and lightning threat.
In order to prevent the damage of thunder and lightning to the power industry, a thunder and lightning detection early warning system is established; at present, most lightning monitoring and early warning systems take an atmospheric electric field instrument as basic equipment, and prejudge thunderstorm weather by analyzing the variation trend of electric field intensity, and have the advantages of wide monitoring range and capability of sending lightning early warning signals before lightning stroke occurs; but has the following disadvantages: firstly, the method for carrying out early warning only by judging whether the electric field strength exceeds the set threshold value often has the condition of high false alarm rate, and the early warning accuracy rate needs to be improved; and secondly, accurate optical image data of lightning stroke points cannot be provided, so that the reason analysis after supporting accidents is not facilitated, or weak points of lightning protection design are investigated and repaired.
Disclosure of Invention
The invention provides a lightning stroke optical path monitoring system and a lightning stroke optical path monitoring method aiming at least one defect or improvement requirement in the prior art and aims to solve the problems that the prior detection early warning system is low in early warning accuracy rate and cannot accurately acquire optical image data of a lightning stroke point for follow-up analysis of a lightning stroke accident.
To achieve the above object, according to one aspect of the present invention, there is provided a lightning stroke optical path monitoring system including a photoelectric sensing unit, a core unit, an image pickup device, and a sound sensor;
the photoelectric sensing unit is used for generating a trigger signal when lightning occurs; under the control of the trigger signal, the image acquisition equipment shoots a thunder picture, and the core unit controls the sound sensor to acquire thunder audio information;
the core unit is used for judging whether the thunder image accords with the thunder characteristic or not through a target detection algorithm based on deep learning, and judging whether the thunder audio information accords with the thunder characteristic or not through an environmental sound identification algorithm based on deep learning when the thunder image accords with the thunder characteristic; and when the thunder audio information conforms to the thunder characteristics, sending an alarm signal.
Preferably, the core unit of the lightning stroke optical path monitoring system is further configured to calculate a lightning distance and a lightning direction when the lightning sound audio information conforms to the lightning sound characteristics, mark the lightning occurrence time, the lightning distance, and the lightning direction information on the lightning picture, and send the marked lightning picture to an external server.
Preferably, the core unit of the lightning stroke optical path monitoring system comprises a carrier plate, and a core board, a time service module and an external memory which are arranged on the carrier plate;
the core board is used for realizing detection and identification of the thunder and lightning picture and thunder information identification, sending an alarm signal when the thunder and lightning picture accords with thunder characteristics and the thunder and lightning audio information accords with thunder characteristics, and marking thunder occurrence time, thunder and lightning distance and direction information on the thunder and lightning picture;
the carrier plate is provided with a power module and a plurality of expansion interfaces; the power supply module is used for converting externally input alternating current into working voltage required by each hardware in the system respectively to realize power supply output facing the system; the expansion interface is mainly used for realizing the data interface expansion between the core board and the image acquisition equipment and between the core board and the external server;
the external memory is used for locally storing thunder audio information, thunder pictures acquired by the image acquisition equipment and the thunder pictures marked by the core board;
the time service module is used for acquiring the initial occurrence time of thunder and lightning and the initial occurrence time of thunder in real time, and the lightning distance is calculated through the thunder and lightning occurrence time difference of the core board.
Preferably, in the lightning stroke optical path monitoring system, the photoelectric sensing unit includes a photoelectric sensor, an amplifier, a filter and a voltage comparator which are connected in sequence;
when lightning occurs, the photoelectric sensor is influenced by the flash to generate a step signal; the step signal is conditioned by an amplifier, a filter and a voltage comparator in sequence to generate a trigger signal.
Preferably, the lightning stroke optical path monitoring system further comprises a temperature sensor, wherein the temperature sensor is in communication connection with the core board and is used for collecting temperature information when lightning occurs; the core board calculates the lightning distance according to the temperature information and the time difference between thunder and lightning; the specific calculation formula is as follows:
wherein S represents the lightning distance in meters; a represents the speed of sound, in meters per second,
t represents the thermodynamic temperature collected by the temperature sensor, and the unit is Kelvin; t represents the time difference between thunder and lightning in seconds.
Preferably, in the lightning stroke optical path monitoring system, the image capturing device includes a plurality of industrial cameras in different orientations, and the sum of the field angles of all the industrial cameras is greater than or equal to 360 ° to realize 360 ° panoramic photography; the thunder and lightning position is calculated according to the thunder and lightning picture collected by the industrial camera and the corresponding camera orientation by the core board, and the calculation formula is as follows:
wherein, A represents the lightning direction and is marked by azimuth angle with the unit of degree; o represents the actual orientation of the industrial camera, expressed in azimuth, in degrees; f denotes the field angle of the industrial camera lens, in degrees; x represents the width of the thunder and lightning picture collected by the industrial camera, and the unit is pixel; and x represents the abscissa value of the central point position of the area occupied by the thunder on the picture, and the unit is a pixel.
Preferably, the lightning stroke optical path monitoring system further includes an optical fiber transceiver, and the core board sends the marked lightning picture to an external server through the optical fiber transceiver.
Preferably, the lightning stroke optical path monitoring system further includes a camera bracket and a chassis;
the camera bracket comprises a supporting rod and a camera fixing part arranged at the top end of the supporting rod; the industrial cameras are uniformly arranged on the oblique side surface of the camera fixing part so as to ensure that four industrial cameras can monitor the surrounding area by 360 degrees; the case is hung on the supporting rod, the core unit is installed inside the case, and the photoelectric sensor and the microphone are installed in the case part.
According to another aspect of the present invention, there is also provided a lightning stroke optical path monitoring method, comprising the steps of:
s1: acquiring a trigger signal generated by triggering of flash when lightning occurs; collecting thunder and lightning pictures and thunder and lightning audio information under the control of the trigger signal;
s2: judging whether the thunder and lightning picture accords with thunder and lightning characteristics or not through a target detection algorithm based on deep learning; when the thunder picture accords with the thunder features, whether the thunder audio information accords with the thunder features or not is judged through an environment sound recognition algorithm based on deep learning;
s3: when the thunder audio information conforms to the thunder characteristics, sending an alarm signal, calculating the thunder distance and the thunder direction, and marking the thunder occurrence time, the thunder distance and the thunder direction on a thunder picture; and sending the marked thunder and lightning picture to an external server.
Preferably, in the lightning stroke optical path monitoring method, in step S2, when the lightning picture does not conform to the lightning characteristics, it is determined that the lightning picture is triggered by mistake and the lightning picture is deleted;
in step S3, when the thunder audio information does not conform to the thunder features, it is determined that the thunder distance is too far, and the thunder image and the thunder audio information are stored.
In general, compared with the prior art, the above technical solution contemplated by the present invention can achieve the following beneficial effects:
(1) the lightning stroke optical path monitoring system and the lightning stroke optical path monitoring method respectively collect lightning pictures and lightning sound audio information when lightning occurs, and firstly judge whether the lightning pictures conform to lightning characteristics; when the thunder audio information accords with the thunder characteristics, further judging that the thunder audio information accords with the thunder characteristics; only if the lightning characteristic and the thunder characteristic are simultaneously met, an alarm signal is sent out; the accuracy of lightning early warning is improved through double condition judgment, the false alarm rate is reduced, and the reliability of a monitoring system is improved; in addition, the lightning distance and the lightning direction are calculated, the information is marked on a lightning picture, and the marked lightning picture can be used for follow-up analysis of lightning accidents;
(2) the lightning stroke optical path monitoring system and the lightning stroke optical path monitoring method can carry out all-dimensional monitoring on key facilities within a range of several kilometers, give out an alarm when a lightning stroke accident occurs, and captured image data can also support reason analysis after the accident and investigate and repair weak points of lightning protection design.
Drawings
FIG. 1 is a logic block diagram of a lightning strike optical path monitoring system provided by an embodiment of the invention;
FIG. 2 is a schematic diagram of a component structure of a lightning stroke optical path monitoring system provided by an embodiment of the invention;
FIG. 3 is a schematic diagram of an appearance structure of a lightning stroke optical path monitoring system provided by an embodiment of the invention; wherein, 1-camera support; 2-a support rod; 3-a camera mount; 4-casting aluminum waterproof case;
FIG. 4 is a flow chart of a lightning strike optical path monitoring method provided by an embodiment of the invention;
FIG. 5 is a flowchart of a monitoring method based on a lightning stroke optical path monitoring system according to an embodiment of the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. In addition, the technical features involved in the embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
FIG. 1 is a logic block diagram of a lightning strike optical path monitoring system provided by an embodiment of the invention; FIG. 2 is a schematic diagram of a component structure of a lightning stroke optical path monitoring system provided by an embodiment of the invention; FIG. 3 is a schematic diagram of an appearance structure of a lightning stroke optical path monitoring system provided by an embodiment of the invention; as shown in fig. 1 to 3, the lightning stroke optical path monitoring system provided in this embodiment includes a core unit, a photoelectric sensing unit, a plurality of industrial cameras, a sound pickup, and a cast aluminum waterproof case;
the number of the industrial cameras is determined by the field angle of the cameras, and the sum of the field angles of all the industrial cameras is only required to be more than or equal to 360 degrees, so that 360-degree panoramic shooting is realized; in the embodiment, 4 industrial cameras are adopted, the focal length of a lens of each industrial camera is 2.8mm, the field angle is 100 degrees, the communication interface of each industrial camera is USB2.0, and the industrial cameras are connected with a core unit through a USB concentrator; the industrial camera is mounted on a camera support, and the structure of the camera support is as shown in fig. 3, and comprises a support rod and a camera fixing part mounted at the top end of the support rod; the four industrial cameras are uniformly arranged on the oblique side face of the camera fixing part so as to ensure that the four industrial cameras can monitor the surrounding area at 360 degrees; the camera fixing part comprises four supporting seats, and a mounting hole is formed in the oblique side face of each supporting seat and used for butting an industrial camera; the number of the supporting seats on the camera fixing part changes along with the number of the industrial cameras; the core unit is placed inside the cast-aluminum waterproof case, the photoelectric sensing unit, the pickup and the temperature sensor are installed outside the case, and the cast-aluminum waterproof case is hung on the supporting rod, so that the stability is ensured, and meanwhile, the cast-aluminum waterproof case is convenient to detach and maintain.
The photoelectric sensing unit is used for generating a trigger signal when lightning occurs; under the control of a trigger signal, four industrial cameras simultaneously shoot thunder and lightning pictures in the sky at different angles, and a core unit starts a microphone to collect thunder and lightning audio information; the microphone is a sound sensor module and is used for converting thunder into an electric signal for the core unit to identify, so that the thunder monitoring function is realized;
the method comprises the steps that a core unit firstly screens pictures which capture thunder images from pictures shot by four industrial cameras, then judges whether the thunder images accord with thunder features or not through a target detection algorithm based on deep learning, and judges whether thunder audio information accords with the thunder features or not through an environmental sound recognition algorithm based on the deep learning when the thunder images accord with the thunder features; and when the thunder audio information accords with the thunder characteristics, sending an alarm signal, calculating the thunder distance and the thunder direction, and marking the thunder occurrence time, the thunder distance and the thunder direction information on a thunder picture. Regarding a target detection algorithm based on deep learning, the embodiment firstly acquires a large number of real lightning pictures and calibrates the lightning position on each lightning picture to generate a training set, and then trains a neural network model through the training set to obtain a target detection model for lightning detection; regarding the environmental sound recognition algorithm based on deep learning, the embodiment collects a large amount of real thunder audio data, inputs the thunder audio data into a deep belief network for training, and obtains the thunder detection model for thunder recognition.
The lightning stroke optical path monitoring system provided by the implementation collects lightning pictures and lightning sound audio information when lightning occurs through the industrial camera and the sound pick-up respectively; the method comprises the following steps that a core unit firstly judges whether a thunder and lightning picture meets thunder and lightning characteristics; when the thunder audio information accords with the thunder characteristics, further judging that the thunder audio information accords with the thunder characteristics; only after the lightning characteristics and the thunder characteristics are simultaneously met, the core unit sends out an alarm signal; the accuracy of lightning early warning is improved through double condition judgment, the false alarm rate is reduced, and the reliability of a monitoring system is improved; in addition, the lightning distance and the lightning direction are calculated, the information is marked on a lightning picture, and the marked lightning picture can be used for follow-up analysis of lightning accidents.
As shown in fig. 2, the photoelectric sensing unit includes a photoelectric sensor, an amplifier, a filter, and a voltage comparator for generating a trigger signal when a lightning occurs; when thunder and lightning occur, the photoelectric sensor is influenced by the flash to generate a step signal, and the step signal is conditioned by the amplifier, the filter and the voltage comparator to obtain a trigger signal; the voltage comparator is respectively connected with the external trigger interfaces of the four industrial cameras and the digital I/O port of the core unit, and sends the generated trigger signals to the industrial cameras and the core unit at the same time; after the trigger signal is received, the four industrial cameras facing different directions shoot lightning pictures of the sky at different angles simultaneously and send the lightning pictures to the core unit.
The core unit comprises a core board, a time service module, an external memory and a carrier board;
the core board is used for realizing detection and identification of the thunder and lightning picture and thunder information identification, and the core board in the embodiment adopts Jetson TX2 in English Winda;
the carrier plate is provided with a power module and a plurality of expansion interfaces; the power supply module is used for converting externally input alternating current into working voltage required by each hardware in the system respectively to realize power supply output facing the system; the expansion interface is mainly used for realizing data interface expansion between the core board and the industrial camera and between the core board and an external server, and the interface types include but are not limited to internet access, USB interface and the like;
the time service module is used for acquiring time in real time, and the core board determines the initial lightning occurrence time and the initial thunder occurrence time through the time service module, so that the lightning distance is calculated according to the thunder and lightning time difference.
The external memory is used for locally storing thunder audio information, thunder pictures acquired by the industrial camera and the thunder pictures marked by the core board; the external memory adopts an SSD solid state disk.
After receiving the trigger signal, the core board starts a sound pick-up, and simultaneously starts an internal timer of the core board, and the sound pick-up stops recording for 15 seconds; judging whether the shot thunder image accords with thunder features or not through a target detection algorithm based on deep learning, if so, starting a time service module to obtain the initial thunder occurrence time, judging whether the recording accords with the thunder features or not through an environmental sound recognition algorithm based on deep learning by recording the last 15 seconds, if so, obtaining the initial thunder occurrence time through the time service module, and then calculating the thunder distance and the thunder direction; if the thunder and lightning picture does not accord with the thunder and lightning characteristics, judging that the picture is triggered by mistake and deleting the picture; if the picture conforms to the thunder and lightning characteristics but the recording does not conform to the thunder and lightning characteristics, the picture and the recording are only stored in an external memory if the thunder and lightning distance is considered to be too far; only if the thunder and lightning picture accords with the thunder and lightning characteristics, the information such as the calibration time, the direction, the distance and the like on the thunder and lightning picture is sent to an external server, and data is backed up in an external memory.
The core board takes the actual orientation of an industrial camera containing a thunder image in a shot picture as a reference, and calculates a thunder azimuth A by taking the relative position occupied by thunder in the picture as a judgment basis, wherein the calculation formula is as follows:
wherein, A represents the lightning direction and is marked by azimuth angle with the unit of degree; o represents the actual orientation of the industrial camera, expressed in azimuth, in degrees; f denotes the field angle of the industrial camera lens, in degrees; x represents the width of the thunder and lightning picture collected by the industrial camera, and the unit is pixel; and x represents the abscissa value of the central point position of the area occupied by the thunder on the picture, and the unit is a pixel.
As a preferable preference of this embodiment, the monitoring system further includes a temperature sensor, and the temperature sensor is in communication connection with the core board and is used for collecting temperature information when lightning occurs; the core board calculates the lightning distance S according to the temperature information and the thunder and lightning time difference; in air, the sound velocity formula can be simplified as:
wherein a represents the sound velocity in meters per second; t represents the thermodynamic temperature collected by the temperature sensor, and the unit is Kelvin;
therefore, the formula for calculating the lightning distance S is:
wherein t represents the difference between the initial occurrence time of lightning and the initial occurrence time of thunder; when the precision requirement is not high, the sound velocity empirical value a can be directly used for calculating the lightning distance, namely the lightning distance S is t multiplied by 340, and in this case, a temperature sensor is not needed.
As a preferable preference of the embodiment, the monitoring system further comprises an optical fiber transceiver arranged in the cast-aluminum waterproof case, and the core unit is in communication connection with an external server through the optical fiber transceiver so as to send the lightning pictures marked with the lightning occurrence time, the lightning azimuth and the distance information to the external server; the optical fiber transceiver converts an Ethernet interface on the core unit into an optical fiber interface, so that the monitoring system and the external server communicate through optical fibers.
The embodiment also provides a lightning stroke optical path monitoring method, as shown in fig. 4, including the following steps:
s101: acquiring a trigger signal generated by triggering of flash when lightning occurs; collecting thunder and lightning pictures and thunder and lightning audio information under the control of a trigger signal;
s102: judging whether the thunder and lightning picture accords with thunder and lightning characteristics or not through a target detection algorithm based on deep learning; when the thunder picture accords with the thunder features, whether the thunder audio information accords with the thunder features or not is judged through an environment sound recognition algorithm based on deep learning;
when the thunder and lightning picture does not accord with the thunder and lightning characteristics, judging that the thunder and lightning picture is triggered by mistake and deleting the thunder and lightning picture;
s103: when the thunder audio information conforms to the thunder characteristics, sending an alarm signal, calculating the thunder distance and the thunder direction, and marking the thunder occurrence time, the thunder distance and the thunder direction on a thunder picture; sending the marked thunder and lightning picture to an external server;
and when the thunder audio information does not accord with the thunder features, judging that the thunder distance is too far, and storing the thunder picture and the thunder audio information.
Fig. 5 is a flowchart of a monitoring method based on the above lightning stroke optical path monitoring system provided in this embodiment, and as shown in fig. 5, the flowchart includes:
s201: the method comprises the following steps that a photoelectric sensing unit monitors a lightning occurrence event in real time, when lightning occurs, the photoelectric sensor is influenced by flash to generate a trigger signal and sends the trigger signal to a core unit and an industrial camera; the industrial camera shoots a thunder and lightning picture under the control of the trigger signal;
s202: the core unit circularly waits for a trigger signal, starts a sound pick-up after receiving the trigger signal, and simultaneously starts a timer in the core board to set the recording time of the sound pick-up; simultaneously, receiving a thunder and lightning picture shot by an industrial camera, and entering a target detection algorithm queue;
s203: judging whether the picture meets the lightning characteristics or not through a target detection algorithm based on deep learning, if not, judging that the picture is triggered by mistake, stopping recording, and deleting the recording file and the lightning picture; if the thunder and lightning picture accords with the thunder and lightning characteristics, judging whether the recording needs to be stopped in advance; if yes, stopping recording and deleting the recording file; when thunder and lightning occur intensively, the time interval of two or more times of thunder and lightning is too small, the last thunder and lightning occurrence time is earlier than the thunder and lightning occurrence time, the thunder and lightning recording file corresponding to the first thunder and lightning is deleted, and the recording file triggered by the last thunder and lightning is used as the thunder and lightning information common to the two thunder and lightning; if not, judging whether the recording time reaches the set time or not; entering an environmental sound identification queue when the set recording time is reached; otherwise, continuing recording;
s204: judging whether the thunder audio information accords with the thunder characteristics or not through an environmental sound recognition algorithm based on deep learning; if not, judging that the lightning distance is too far, and storing the lightning picture and the recording in an external memory; if yes, entering the next step;
s205: calculating the lightning direction and distance, and calibrating the information such as the lightning occurrence time, the lightning direction and distance on a lightning picture;
s206: and sending the calibrated thunder and lightning picture to an external server and backing up the thunder and lightning picture in an external memory.
Compared with the existing lightning detection and early warning system, the lightning stroke optical path monitoring system and method provided by the invention improve the accuracy of lightning early warning, reduce the false alarm rate and improve the reliability of the monitoring system by judging the double conditions of lightning recognition and thunder recognition; the lightning protection system can monitor key facilities within a range of several kilometers in all directions, alarm is given out when a lightning accident happens, and captured image data can also support reason analysis after the accident, and weak points of lightning protection design are investigated and repaired.
It will be understood by those skilled in the art that the foregoing is only a preferred embodiment of the present invention, and is not intended to limit the invention, and that any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (8)
1. A lightning stroke optical path monitoring system is characterized by comprising a photoelectric sensing unit, a core unit, an image acquisition device and a sound sensor;
the photoelectric sensing unit is used for generating a trigger signal when lightning occurs; under the control of the trigger signal, the image acquisition equipment shoots a thunder picture, and the core unit starts the sound sensor to acquire thunder audio information;
the core unit is used for judging whether the thunder image accords with the thunder characteristic or not through a target detection algorithm based on deep learning, and judging whether the thunder audio information accords with the thunder characteristic or not through an environmental sound identification algorithm based on deep learning when the thunder image accords with the thunder characteristic; when the thunder audio information conforms to the thunder characteristics, an alarm signal is sent out;
the image acquisition equipment comprises a plurality of industrial cameras in different orientations, and the sum of the field angles of all the industrial cameras is greater than or equal to 360 degrees so as to realize 360-degree panoramic shooting; the core unit also calculates the lightning direction according to the lightning pictures collected by the industrial camera and the corresponding camera orientation, and the calculation formula is as follows:
wherein A represents the lightning azimuth, represented by the azimuth angle; o represents the actual orientation of the industrial camera taking the lightning picture, expressed in azimuth; f denotes an angle of view of the industrial camera lens; x represents the width of the thunder and lightning picture collected by the industrial camera; x represents the abscissa value of the central point position of the area occupied by the thunder on the picture;
the system also includes a camera support and a chassis;
the camera bracket comprises a supporting rod and a camera fixing part arranged at the top end of the supporting rod; industrial cameras are uniformly mounted on the inclined side of the camera fixing part to have different orientations; the case is hung on the supporting rod, the core unit is installed inside the case, and the photoelectric sensing unit and the sound sensor are installed outside the case.
2. The lightning strike optical path monitoring system of claim 1, wherein the core unit is further configured to calculate a lightning distance and orientation when the lightning sound audio information conforms to the lightning sound characteristics, tag the lightning occurrence time, lightning distance, and orientation information on the lightning picture, and send the tagged lightning picture to an external server.
3. The lightning strike optical path monitoring system of claim 2, wherein the core unit comprises a carrier board, and a core board, a time service module and an external memory arranged on the carrier board;
the core board is used for realizing detection and identification of the thunder and lightning picture and thunder information identification, sending an alarm signal when the thunder and lightning picture accords with thunder characteristics and the thunder and lightning audio information accords with thunder characteristics, and marking thunder occurrence time, thunder and lightning distance and direction information on the thunder and lightning picture;
the carrier plate is provided with a power module and a plurality of expansion interfaces; the power supply module is used for converting externally input alternating current into working voltage required by each hardware in the system respectively to realize power supply output facing the system; the expansion interface is mainly used for realizing the data interface expansion between the core board and the image acquisition equipment and between the core board and the external server;
the external memory is used for locally storing thunder audio information, thunder pictures acquired by the image acquisition equipment and the thunder pictures marked by the core board;
the time service module is used for acquiring the initial occurrence time of thunder and lightning and the initial occurrence time of thunder in real time, and the lightning distance is calculated through the thunder and lightning occurrence time difference of the core board.
4. The lightning strike optical path monitoring system of claim 1 or 3, wherein the photo-sensing unit comprises a photo-sensor, an amplifier, a filter and a voltage comparator connected in series;
when lightning occurs, the photoelectric sensor is influenced by the flash to generate a step signal; the step signal is conditioned by an amplifier, a filter and a voltage comparator in sequence to generate a trigger signal.
5. The lightning strike optical path monitoring system of claim 3, further comprising a temperature sensor communicatively coupled to the core board for collecting air temperature information during a lightning strike; the core board calculates the lightning distance according to the temperature information and the time difference between thunder and lightning; the specific calculation formula is as follows:
wherein S represents a lightning distance; a represents the speed of sound and a represents,
t represents the thermodynamic temperature collected by the temperature sensor; t represents the time difference between thunder and lightning.
6. The lightning strike optical path monitoring system of claim 5, further comprising a fiber optic transceiver through which the core board transmits the marked lightning picture to an external server.
7. A lightning stroke optical path monitoring method is characterized by comprising the following steps:
s1: acquiring a trigger signal generated by triggering of flash when lightning occurs; collecting thunder and lightning pictures and thunder and lightning audio information under the control of the trigger signal; the collection of the thunder and lightning pictures is realized based on a plurality of industrial cameras with different orientations, the industrial cameras with different orientations are uniformly arranged on the inclined side surface of the camera fixing part of the camera support, and the sum of the field angles of all the industrial cameras is more than or equal to 360 degrees so as to realize 360-degree panoramic shooting; the camera fixing part is arranged at the top end of a supporting rod and forms a camera bracket together with the supporting rod;
s2: judging whether the thunder and lightning picture accords with thunder and lightning characteristics or not through a target detection algorithm based on deep learning; when the thunder picture accords with the thunder features, whether the thunder audio information accords with the thunder features or not is judged through an environment sound recognition algorithm based on deep learning;
s3: when the thunder audio information conforms to the thunder characteristics, sending an alarm signal, calculating the thunder distance and the thunder direction, and marking the thunder occurrence time, the thunder distance and the thunder direction on a thunder picture; the calculation formula of the lightning direction is as follows:
wherein A represents the lightning azimuth, represented by the azimuth angle; o represents the actual orientation of the industrial camera taking the lightning picture, expressed in azimuth; f denotes an angle of view of the industrial camera lens; x represents the width of the thunder and lightning picture collected by the industrial camera; and x represents the abscissa value of the position of the central point of the area occupied by the thunder on the picture.
8. The lightning stroke optical path monitoring method according to claim 7, wherein in step S2, when the lightning picture does not conform to the lightning characteristics, it is determined that the lightning picture is triggered by mistake and the lightning picture is deleted;
in step S3, when the thunder audio information does not conform to the thunder features, it is determined that the thunder distance is too far, and the thunder image and the thunder audio information are stored.
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 CN109979468A (en) | 2019-07-05 |
| CN109979468B true 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) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN112744212B (en) * | 2019-10-30 | 2022-09-09 | 比亚迪股份有限公司 | Vehicle control method and device and vehicle |
| CN112396116B (en) * | 2020-11-24 | 2021-12-07 | 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 |
| 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 |
| 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 |
Family Cites Families (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6735525B1 (en) * | 2003-03-24 | 2004-05-11 | Vaisala Oyj | Systems and methods 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 |
| JP2011244058A (en) * | 2010-05-14 | 2011-12-01 | Sony Corp | 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 |
| CN104459349B (en) * | 2013-09-12 | 2017-10-20 | 龙源电力集团股份有限公司 | Wind power plant lightning monitoring system and method |
| CN103728503B (en) * | 2013-12-31 | 2015-08-12 | 国网电力科学研究院武汉南瑞有限责任公司 | A kind of three-dimensional discharge path automatic production record of thunderbolt and recording method thereof being applied to ancient buildings |
| CN105791917B (en) * | 2014-12-24 | 2019-04-09 | 中国电信股份有限公司 | Lightning-arrest method and device is shut down in control outdoor advertising |
| 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 |
| CN106707371B (en) * | 2016-11-21 | 2019-06-07 | 深圳市气象服务中心 | A kind of lightning monitoring early warning and guard service system and method for early warning |
| 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
Also Published As
| Publication number | Publication date |
|---|---|
| CN109979468A (en) | 2019-07-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109979468B (en) | Lightning stroke optical path monitoring system and method | |
| JP4844844B2 (en) | Vibration measurement system and computer program | |
| KR101660456B1 (en) | Monitoring apparatus for photovoltaic generating system | |
| CN110418957B (en) | Method and device for monitoring the condition of a facility having an operating means | |
| CN111982291B (en) | Fire point positioning method, device and system based on unmanned aerial vehicle | |
| CN110516522B (en) | Inspection method and system | |
| CN112740023A (en) | Machine learning system and data fusion for optimizing deployment conditions for detecting corrosion under heat preservation layer | |
| CN104410839B (en) | A kind of mobile power transmission line bar tower region mountain fire and disaster of mountain massif coast on-line monitoring system and monitoring method | |
| CN111046121B (en) | Environment monitoring method, device and system | |
| CN111445522B (en) | Passive night vision intelligent lightning detection system and intelligent lightning detection method | |
| KR101004023B1 (en) | Non contact rock fall detection apparatus using photo sensors | |
| KR101453336B1 (en) | Non contact displacement measurement system | |
| CN114255405A (en) | Hidden danger target identification method and device | |
| CN114413854B (en) | Real-scene three-dimensional image checking system based on oblique photography | |
| CN103728503B (en) | A kind of three-dimensional discharge path automatic production record of thunderbolt and recording method thereof being applied to ancient buildings | |
| KR101004024B1 (en) | Non contact rock fall detection method using photo sensors | |
| CN112326039B (en) | Photovoltaic power plant patrols and examines auxiliary system | |
| CN109785562A (en) | A kind of vertical photoelectricity ground based threats warning system and suspicious object recognition methods | |
| CN102082905A (en) | Method for detecting position of camera optic axis | |
| KR102078877B1 (en) | Photovoltaic module thermal imaging system with trio imaging device | |
| US20220103762A1 (en) | Imaging apparatus, imaging system, and imaging method | |
| CN211348438U (en) | Automatic lightning channel observation system | |
| KR20210122764A (en) | Diagnostic method for facilities of power transmission using unmaned aerial vehicle | |
| CN112556650A (en) | Telegraph pole inclination detection protection device and detection method thereof | |
| CN111736140A (en) | Object detection method and camera 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 | ||
| 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 |