CN114022850A - Transformer substation fire monitoring method and system and related equipment - Google Patents
Transformer substation fire monitoring method and system and related equipment Download PDFInfo
- Publication number
- CN114022850A CN114022850A CN202210014320.7A CN202210014320A CN114022850A CN 114022850 A CN114022850 A CN 114022850A CN 202210014320 A CN202210014320 A CN 202210014320A CN 114022850 A CN114022850 A CN 114022850A
- Authority
- CN
- China
- Prior art keywords
- monitoring camera
- data
- monitoring
- flame
- area
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 340
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000001514 detection method Methods 0.000 claims abstract description 98
- 238000012549 training Methods 0.000 claims description 63
- 230000000007 visual effect Effects 0.000 claims description 46
- 238000004088 simulation Methods 0.000 claims description 29
- 238000012795 verification Methods 0.000 claims description 17
- 238000004590 computer program Methods 0.000 claims description 15
- 238000005286 illumination Methods 0.000 claims description 7
- 238000013527 convolutional neural network Methods 0.000 claims description 6
- 238000013507 mapping Methods 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 9
- 230000000694 effects Effects 0.000 description 6
- 238000004880 explosion Methods 0.000 description 4
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000002194 synthesizing effect Effects 0.000 description 2
- 239000003990 capacitor Substances 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000003672 processing method Methods 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Fire-Detection Mechanisms (AREA)
Abstract
The invention is suitable for the field of intelligent security and provides a method, a system and related equipment for monitoring fire of a transformer substation, wherein the method comprises the following steps: determining a monitoring area including a transformer substation area, and dividing the monitoring area into a wire area, a transformer substation area and a field area; arranging a high-level monitoring camera in a transformer substation area, arranging a low-level monitoring camera in a field area, and establishing a monitoring data table for the high-level monitoring camera; acquiring a data set to train a flame detection model to obtain a flame detection algorithm; carrying out fire condition identification by using a flame detection algorithm through a high-level monitoring camera; and identifying the fire condition by using a flame detection algorithm through a low-position monitoring camera. The invention realizes the high-precision monitoring of the transformer substation through multi-directional identification, reduces the load of edge equipment and improves the usability and the flexibility.
Description
Technical Field
The invention belongs to the field of intelligent security and particularly relates to a transformer substation fire monitoring method, a transformer substation fire monitoring system and related equipment.
Background
The transformer substation is a place for converting voltage and current, receiving electric energy and distributing electric energy in an electric power system, a large number of electric power equipment such as high-voltage electric wires, current transformers, coupling capacitors, combined filters and the like are generally arranged in the transformer substation, compared with conventional industrial buildings, a building environment formed by the electric power equipment in the transformer substation has the characteristics of density and distinct layers, specifically, part of the high-voltage electric power equipment is arranged on a telegraph pole to be connected with high-voltage electric wires, and part of the high-voltage electric power equipment is in contact with the ground, so that potential safety hazards of easy ignition exist for the high-voltage electric power equipment.
At present, in order to prevent a fire or explosion event from occurring in a transformer substation, a common method requires technicians to regularly and regularly maintain and patrol related equipment, and mostly installs an industrial monitoring system to monitor key areas, although regular manual maintenance and patrol are high-reliability means, problems that personnel are lost or related personnel cannot be timely handled after the fire or explosion event occurs still exist, and for a non-intelligent industrial monitoring system, personnel must be continuously on duty to check monitoring pictures, and fires such as early fire or explosion cannot be well handled.
Disclosure of Invention
The embodiment of the invention provides a method and a system for monitoring fire of a transformer substation and related equipment, and aims to solve the problem that the existing transformer substation monitoring system cannot intelligently and automatically monitor potential safety hazards such as fire and explosion.
In a first aspect, an embodiment of the present invention provides a substation fire monitoring method, where the method includes:
determining a monitoring area comprising a transformer substation area, and dividing the monitoring area into a wire area, the transformer substation area and a field area surrounding the transformer substation area, wherein the transformer substation area is rectangular, the transformer substation area comprises aerial high-altitude equipment and ground equipment, the aerial high-altitude equipment is located in the air, the ground equipment is located on the ground, the wire area is divided into a first wire area and a second wire area, and the first wire area and the second wire area are respectively arranged on two opposite sides of the transformer substation area;
arranging a high-position monitoring camera in the transformer substation area, enabling the visual angle of the high-position monitoring camera to cover the high-altitude equipment, arranging a low-position monitoring camera in the field area, and enabling the visual angle of the low-position monitoring camera to cover the ground equipment;
establishing a monitoring data table comprising a plurality of data fields for the high-order monitoring camera;
acquiring real data with real flame and shooting data shot in an actual scene, acquiring simulation data according to the real data and the shooting data, training a flame detection model by taking the real data, the shooting data and the simulation data as a total data set, storing the flame detection model obtained by training, and taking the flame detection model as a flame detection algorithm; the shooting data is acquired by the high-order monitoring camera and the low-order monitoring camera;
the high-level monitoring camera is used for carrying out flame recognition on the high-level equipment according to the flame detection algorithm, and judging whether the high-level equipment generates a fire condition according to a preset high-level flame judgment rule;
and carrying out flame identification on the ground equipment through the low-position monitoring camera according to the flame detection algorithm, and judging whether the ground equipment generates a fire or not.
Further, the visual angle median line of high-order monitoring camera is more than the water flat line with the horizontal direction parallel and level, just the visual angle median line of high-order monitoring camera aligns high altitude equipment, the visual angle median line of low-order monitoring camera is below the water flat line with the horizontal direction parallel and level, just the visual angle median line of low-order monitoring camera aligns ground equipment.
Furthermore, the method comprises the steps of arranging a high-position monitoring camera in the transformer substation area, enabling the visual angle of the high-position monitoring camera to cover the high-altitude equipment, arranging a low-position monitoring camera in the field area, and enabling the visual angle of the low-position monitoring camera to cover the ground equipment, and specifically comprises the following steps:
the high-order monitoring camera includes main monitoring camera and supplementary monitoring camera set up one respectively on four corners in the transformer substation area main monitoring camera makes all the visual angle range of main monitoring camera covers whole all in the transformer substation area high altitude plant deploy at least one on the boundary in the transformer substation area supplementary monitoring camera makes the visual angle of supplementary monitoring camera covers arbitrary high altitude plant set up at least two in the field area low level monitoring camera makes all the visual angle of low level monitoring camera covers all ground equipment.
Furthermore, the data field comprises a camera number, alarm time and a current zone bit, and the current zone bit is used for marking that the camera is in a direct sunlight state or a non-direct sunlight state.
Furthermore, the step of acquiring real data with real flames and shooting data shot in an actual scene, acquiring simulation data according to the real data and the shooting data, training a flame detection model by using the real data, the shooting data and the simulation data as a total data set, storing the flame detection model obtained by training, and using the flame detection model as a flame detection algorithm includes the following substeps:
acquiring a flame image with real flame, recording the flame image as the real data, acquiring an actual shooting image of the transformer substation area as shooting data, and randomly mapping the flame image in the real data to the actual shooting image in the shooting data to obtain the simulation data;
taking the real data, the shooting data and the simulation data as training data sets, and dividing the training data sets into a first training set and a first verification set according to a first proportion;
defining the number of the high-level monitoring cameras as N, and continuously dividing the first training set for N times by using a second proportion to obtain N groups of actual training sets and actual verification sets;
establishing a flame detection model based on a convolutional neural network, respectively training the flame detection model for N times by using a plurality of groups of actual training sets and actual verification sets, and outputting N flame detection algorithms which accord with a preset accuracy threshold;
and respectively setting N flame detection algorithms in different high-level monitoring cameras, and setting the flame detection algorithm with the highest accuracy in the low-level monitoring camera.
Furthermore, the high-level monitoring camera is used for carrying out flame identification on the high-level equipment according to the flame detection algorithm, and judging whether the high-level equipment generates a fire condition according to a preset high-level flame judgment rule, wherein the steps are as follows:
the high-level monitoring camera carries out flame recognition on the high-altitude equipment according to the flame detection algorithm, wherein the fire condition is judged according to the high-level flame judgment rule, and the high-level flame judgment rule specifically comprises the following steps:
if the main monitoring camera firstly identifies flames and records the flames in the monitoring data table corresponding to the main monitoring camera, further checking whether fire records at the same time exist in the monitoring data tables corresponding to the other high-level monitoring cameras in the non-sunlight direct-radiation state, and if yes, judging that the fire occurs;
if the auxiliary monitoring camera firstly identifies flames and records the flames in the monitoring data table corresponding to the auxiliary monitoring camera, whether fire records at the same time exist in the monitoring data table corresponding to the main monitoring camera in the non-sunlight direct-radiation state or not is checked, and if yes, the fire is judged to occur.
Furthermore, before carrying out flame identification through the high monitoring camera and the low monitoring camera, the method further comprises:
judging the illumination condition of the current environment, wherein:
if the environment is daytime, the high-order monitoring camera and the low-order monitoring camera use a preset exposure adjustment algorithm to perform flame identification;
and if the environment is at night, the high-level monitoring camera and the low-level monitoring camera perform flame identification by using a preset night enhancement algorithm.
In a second aspect, an embodiment of the present invention further provides a substation fire monitoring system, including:
the system comprises a region dividing module, a monitoring module and a control module, wherein the region dividing module is used for determining a monitoring region comprising a transformer substation region, and dividing the monitoring region into a wire region, a transformer substation region and a field region, the transformer substation region is rectangular, the transformer substation region comprises aerial high-altitude equipment and ground equipment, the aerial high-altitude equipment and the ground equipment are located in the air, the wire region is divided into a first wire region and a second wire region, and the first wire region and the second wire region are respectively and oppositely arranged on two sides of the transformer substation region;
the camera position confirming module is used for setting a high-position monitoring camera in the transformer substation area, wherein the high-position monitoring camera comprises a main monitoring camera and an auxiliary monitoring camera, the visual angle of the high-position monitoring camera covers the high-altitude equipment, a low-position monitoring camera is arranged in the field area, and the visual angle of the low-position monitoring camera covers the ground equipment;
the data table establishing module is used for establishing a monitoring data table for the high-order monitoring camera;
the detection algorithm training module is used for acquiring real data and shooting data, acquiring simulation data according to the real data and the shooting data, training a flame detection model by taking the real data, the shooting data and the simulation data as a total data set, and storing the flame detection model obtained by training as a flame detection algorithm;
the high-level monitoring module is used for identifying flames of the high-level equipment through the high-level monitoring camera according to the flame detection algorithm and judging whether the high-level equipment generates fire conditions according to a preset high-level flame judgment rule;
and the low-level monitoring module is used for identifying the flame of the ground equipment through the low-level monitoring camera according to the flame detection algorithm and judging whether the ground equipment generates a fire or not.
In a third aspect, an embodiment of the present invention further provides a computer device, including: a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the substation fire monitoring method as described in any one of the above embodiments when executing the computer program.
In a fourth aspect, embodiments of the present invention further provide a computer-readable storage medium, where a computer program is stored, and when the computer program is executed by a processor, the computer program implements the steps in the substation fire monitoring method according to any one of the above embodiments.
The invention has the advantages that the invention has an auxiliary effect for realizing high-precision safety monitoring of the transformer substation due to the adoption of a multi-azimuth identification scheme, and simultaneously, the neural network with lower load is used as a flame identification algorithm in the edge equipment, thereby improving the usability of the edge equipment and leading the intelligent monitoring system to be more flexibly adapted to the actual requirements.
Drawings
Fig. 1 is a block flow diagram of a method for fire monitoring of a substation provided by an embodiment of the present invention;
FIG. 2 is a schematic top view of a monitoring area provided by an embodiment of the present invention;
fig. 3 is a schematic view of a monitoring camera provided in an embodiment of the present invention;
fig. 4 is a schematic diagram of a deployment point location of a monitoring camera according to an embodiment of the present invention;
fig. 5 is a block diagram of a sub-flow of step S104 in the method for monitoring fire at a substation according to the embodiment of the present invention;
fig. 6 is a schematic structural diagram of a substation fire monitoring system 200 according to an embodiment of the present invention;
fig. 7 is a schematic structural diagram of a computer device according to an embodiment of the present 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.
Referring to fig. 1, fig. 1 is a block flow diagram of a method for monitoring a fire in a substation according to an embodiment of the present invention, which specifically includes the following steps:
s101, determining a monitoring area comprising a transformer substation area, dividing the monitoring area into an electric wire area, a transformer substation area and a field area surrounding the transformer substation area, wherein the transformer substation area is rectangular, the transformer substation area comprises aerial high-altitude equipment and ground equipment, the ground equipment is located on the ground, the electric wire area is divided into a first electric wire area and a second electric wire area, and the first electric wire area and the second electric wire area are respectively arranged on two opposite sides of the transformer substation area.
Specifically, referring to fig. 2, fig. 2 is a schematic top view of a monitoring area provided in an embodiment of the present invention, the substation area is rectangular, the electric wire area includes a first electric wire area and a second electric wire area, in an actual building structure of the substation, ground equipment disposed on the ground and aerial high-altitude equipment disposed in the air for connecting high-voltage electric wires are deployed, and meanwhile, the high-voltage electric wires of the substation for transmitting electric power are connected to the aerial equipment and are located in the air and extend to both sides of the substation, and the electric wire area belongs to the field area below the three-dimensional structure, so that the substation area is surrounded by the field area in a horizontal position.
S102, arranging a high-position monitoring camera in the transformer substation area, enabling the visual angle of the high-position monitoring camera to cover the high-altitude equipment, arranging a low-position monitoring camera in the field area, and enabling the visual angle of the low-position monitoring camera to cover the ground equipment.
Specifically, referring to fig. 3 and 4, fig. 3 is a schematic view of a viewing angle of a monitoring camera provided by an embodiment of the present invention, and fig. 4 is a schematic view of a deployment position of the monitoring camera provided by an embodiment of the present invention, in an embodiment of the present invention, taking an example that both the upper and lower and left and right viewing angle ranges of the high monitoring camera are 90 degrees, the high monitoring camera and the low monitoring camera are both fixed in the air having a certain distance from the ground when deployed, for the high monitoring camera, a middle line of an upper and lower viewing angle thereof should be higher than a horizontal line of a deployment position thereof which is flush with the horizontal ground direction, so that the upper and lower viewing angles of the high monitoring camera can be aligned integrally and cover all the high-altitude devices captured by the high monitoring camera, for the low monitoring camera, the middle line of the upper and lower viewing angles thereof should be lower than the horizontal line of the deployment position thereof which is flush with the horizontal ground direction, the upper and lower visual angles of the low-position monitoring camera can be integrally aligned and all the ground equipment captured by the low-position monitoring camera can be covered, optionally, when the transformer substation area is irregular in shape and the included angle between two sides forming the boundary of the transformer substation area is larger than 90 degrees, the high-position monitoring camera can also select a wide-angle camera with a larger visual angle, and the number of the wide-angle cameras can also be selected according to actual needs.
Wherein, the high-order monitoring camera also includes the main monitoring camera and the auxiliary monitoring camera, the position of the main monitoring camera is on the corner of the transformer substation area, the transformer substation area includes four corners, for four main monitoring cameras, in the embodiment of the invention, the main monitoring cameras are respectively marked as the camera 1, the camera 2, the camera 3 and the camera 4, the corresponding left and right visual angle ranges are respectively a, b, c and d, for each main monitoring camera, the middle line of the left and right visual angles should be aligned with the center of the transformer substation area, so that the visual angle ranges of all the main monitoring cameras cover all the high-altitude equipment in the whole transformer substation area, the aim is to carry out the omnibearing monitoring to the high-altitude equipment, and simultaneously, in order to reduce the influence caused by the direct sunlight, the main monitoring cameras are all adjusted to different directions, the system can ensure that at least 2 main monitoring cameras face away from the sunlight when the sunlight irradiates at different angles, so as to obtain better detection effect;
the auxiliary monitoring cameras are positioned on a boundary line between the transformer substation area and the field area, and are used for monitoring positions of fire hidden dangers in the high-altitude equipment in a key mode, so that the number of the auxiliary monitoring cameras and left and right visual angles can be set according to actual requirements.
In the embodiment of the present invention, the number of the low-position monitoring cameras is at least two, and the range of the left and right viewing angles should be as large as possible, taking the case of setting two low-position monitoring cameras in the field area, which are respectively marked as a camera 9 and a camera 10, the corresponding range of the left and right viewing angles is i and j, the positions of the camera 9 and the camera 10 should be set relative to the substation area, and the median lines of the left and right viewing angles should be aligned with the substation area, so that the viewing angles of all the low-position monitoring cameras cover all the ground equipment, optionally, under the condition that the viewing angles of the cameras are limited or the substation area is too large, a plurality of the low-position monitoring cameras may be set.
S103, establishing a monitoring data table comprising a plurality of data fields for the high-order monitoring camera.
The data fields in the monitoring data table comprise camera numbers, alarm time and current zone bits, wherein the current zone bits are used for marking illumination states and can be divided into a non-direct sunlight state or a direct sunlight state according to the actual conditions of the cameras.
S104, acquiring real data with real flames and shooting data shot in an actual scene, acquiring simulation data according to the real data and the shooting data, training a flame detection model by taking the real data, the shooting data and the simulation data as a total data set, storing the flame detection model obtained through training, and taking the flame detection model as a flame detection algorithm.
Specifically, referring to fig. 5, fig. 5 is a sub-flow diagram of step S104 in the method for monitoring a fire in a substation according to the embodiment of the present invention, and includes the following sub-steps:
s1041, acquiring a flame image with real flame, recording the flame image as the real data, acquiring an actual shooting image of the transformer substation area as shooting data, and randomly mapping the flame image in the real data to the actual shooting image in the shooting data to obtain the simulation data.
The image with the real flame is specifically an image of conditions such as an upward viewing angle, equipment ignition in a similar transformer substation on which an electric wire is ignited, and the like, and can also be an image of flame generated by computer equipment in a capturing and synthesizing manner and the like, and the image is recorded as the real data; the actual image of the transformer substation area is obtained by shooting, and illustratively, the transformer substation area can be shot by the position of a deployed camera to obtain the shooting data; and capturing the flame image in the real data in a computer processing mode to obtain a flame map, and synthesizing the flame map into the shooting data to obtain the simulation data of the fire condition in the transformer substation.
S1042, the real data, the shooting data and the simulation data are used as training data sets, and the training data sets are divided into a first training set and a first verification set according to a first proportion.
The first proportion is a preset proportion for dividing the training data set, and can be set according to actual needs.
S1043, defining the number of the high-order monitoring cameras to be N, and continuously dividing the first training set for N times by using a second proportion to obtain N groups of actual training sets and actual verification sets.
Illustratively, in the embodiment of the present invention, the number N of the high-order monitoring cameras is 8, the size of the second ratio is related to the size of N, and is used to divide the first training set to obtain N groups of actual training sets and actual verification sets, where N is 8, 8 groups of actual training sets and actual verification sets are obtained in total, it should be noted that the first ratio and the second ratio are not uniform in time-averaged ratio, and when a large number of different types of images are included in the training data sets, the data amounts in the plurality of groups of actual training sets and actual verification sets are also different.
S1044, establishing a flame detection model based on a convolutional neural network, performing N times of training on the flame detection model by using a plurality of groups of actual training sets and actual verification sets, and outputting N flame detection algorithms which accord with preset accuracy thresholds.
The flame detection model based on the Convolutional Neural Network (CNN) can be formed by any Neural Network model capable of identifying a target, in the embodiment of the invention, the process of training the flame detection model is divided into a plurality of times, the actual training set and the actual verification set used each time are different, under the condition that the data amount used by control training and the data expression are different, the flame detection model obtained by each training inevitably has difference in the detection capability of the flame in an image, when 8 groups of the actual training sets and the actual verification sets are used for respectively training the flame detection model, according to the identification accuracy of the flame reached by the flame detection model, one accuracy threshold value is set, and the flame detection model with the accuracy reaching the accuracy threshold value after each training is stored, and storing the flame detection algorithm available for the camera equipment, and obtaining 8 flame detection degree algorithms with different recognition accuracies and reaching the preset accuracy threshold value according to the training times N.
S1045, respectively arranging the N flame detection algorithms in different high-level monitoring cameras, and arranging the flame detection algorithm with the highest accuracy in the low-level monitoring camera.
In the embodiment of the invention, the obtained 8 flame detection algorithms with different identification accuracies are respectively used in different high-order monitoring cameras, wherein one flame accuracy algorithm with the highest accuracy is used in all the low-order monitoring cameras according to the high-low sequence of the identification accuracies.
S105, carrying out flame identification on the high-altitude equipment through the high-level monitoring camera according to the flame detection algorithm, and judging whether the high-altitude equipment generates a fire condition according to a preset high-level flame judgment rule.
Specifically, because the flame detection algorithms with different recognition accuracies are used in different high-level monitoring cameras, the recognition results of flames recognized in different viewing angles may be different, in the embodiment of the present invention, according to the position where the high-level monitoring camera is set, flame judgment needs to be performed through the cooperation of the main monitoring camera and the auxiliary monitoring camera according to the preset high-level flame judgment rule, specifically, the preset high-level flame judgment rule specifically is as follows:
A. if the main monitoring camera firstly identifies flames and records the flames in the monitoring data table of the main monitoring camera, whether fire records at the same time exist in the monitoring data tables corresponding to other high-order monitoring cameras in the non-direct sunlight state is further checked, and if the fire records exist, the occurrence of the fire is judged.
Specifically, the main monitoring cameras are used for covering the high-altitude equipment, the auxiliary monitoring cameras are used for monitoring mainly areas prone to fire, based on the above view angle settings, if one main monitoring camera firstly recognizes the fire in the view angle of the main monitoring camera and records the fire in the monitoring data table of the main monitoring camera according to the alarm time, then whether the monitoring data table corresponding to all other high-level monitoring cameras has the fire record in the same time or not is further checked, wherein for the high-level monitoring camera with the current flag bit in the direct sunlight state in the monitoring data table, because the flame detection algorithm is easier to judge the fire when the sunlight is direct, and when at least one high-level monitoring camera in the non-direct sunlight state detects the fire and records the fire, and judging that the fire occurs by at least two high-level monitoring cameras under the current condition, wherein the judgment of only one camera has higher reliability, and then the high-level monitoring cameras can externally inform that the fire occurs through an alarm channel.
B. If the auxiliary monitoring cameras firstly recognize flames and record the flames in the monitoring data tables of the auxiliary monitoring cameras, whether fire records at the same time exist in the monitoring data tables corresponding to the main monitoring cameras in the non-sunlight direct-radiation state or not is checked, and if the fire records exist, the occurrence of the fire is judged.
Because the auxiliary monitoring camera is used for monitoring the area which is easy to generate the fire, if one auxiliary monitoring camera firstly identifies the flame and records the flame in the monitoring data table, whether the monitoring data table corresponding to the main monitoring camera in the non-sunlight direct-radiation state has the fire record in the same time or not is checked, because the main monitoring camera covers all the high-altitude equipment at the visual angle, if at least one main monitoring camera records the fire in the same time, the fire at the position is judged, and then the high-level monitoring camera can externally inform the fire generation through the alarm channel.
S106, carrying out flame identification on the ground equipment through the low-level monitoring camera according to the flame detection algorithm, and judging whether the ground equipment generates a fire or not.
For the low-position monitoring camera, the flame detection algorithm with the highest accuracy is used for identifying flames in visual angles, for the low-position monitoring camera with the upper visual angle and the lower visual angle below a horizontal line, the influence of direct sunlight can be ignored, so that the ground equipment in the visual angles can be immediately judged to have a fire condition when the low-position monitoring camera detects the flames, and the alarm channel is used for externally informing that the fire condition occurs.
Preferably, through the high level monitoring camera with before the low level monitoring camera carries out flame identification, still include the step:
judging the illumination condition of the current environment, wherein:
and if the environment is daytime, the high-order monitoring camera and the low-order monitoring camera use a preset exposure adjustment algorithm to perform flame identification.
And if the environment is at night, the high-level monitoring camera and the low-level monitoring camera perform flame identification by using a preset night enhancement algorithm.
The method for judging the ambient illumination can be that equipment such as a light sensor is utilized, and the ambient illumination can be judged by combining a plurality of light sensors under the condition that a plurality of cameras with different viewing angles are deployed; or the judgment of the ambient light can be carried out according to the preset sunrise and sunset time.
The preset exposure adjustment algorithm and the preset night image enhancement algorithm can be the existing image processing method which can realize exposure adjustment and night image enhancement, can be used by camera equipment independently, and can meet the light performance requirements of edge equipment such as cameras and the like when in use.
The invention has the advantages that the invention has an auxiliary effect for realizing high-precision safety monitoring of the transformer substation due to the adoption of a multi-azimuth identification scheme, and simultaneously, the neural network with lower load is used as a flame identification algorithm in the edge equipment, thereby improving the usability of the edge equipment and leading the intelligent monitoring system to be more flexibly adapted to the actual requirements.
Referring to fig. 6, fig. 6 is a schematic structural diagram of a substation fire monitoring system 200 according to an embodiment of the present invention, where the substation fire monitoring system 200 includes:
the system comprises a region dividing module 201, a monitoring region and a control module, wherein the monitoring region comprises a transformer substation region, the transformer substation region is divided into a wire region, a transformer substation region and a field region, the transformer substation region is rectangular, the transformer substation region comprises aerial high-altitude equipment and ground equipment, the aerial high-altitude equipment and the ground equipment are located in the air, the wire region is divided into a first wire region and a second wire region, and the first wire region and the second wire region are respectively and oppositely arranged on two sides of the transformer substation region;
the camera position confirming module 202 is used for setting a high-position monitoring camera in the transformer substation area, wherein the high-position monitoring camera comprises a main monitoring camera and an auxiliary monitoring camera, the visual angle of the high-position monitoring camera covers the high-altitude equipment, a low-position monitoring camera is arranged in the field area, and the visual angle of the low-position monitoring camera covers the ground equipment;
a data table establishing module 203, configured to establish a monitoring data table for the high-order monitoring camera;
the detection algorithm training module 204 is configured to acquire real data and shooting data, acquire simulation data according to the real data and the shooting data, train a flame detection model by using the real data, the shooting data, and the simulation data as a total data set, and store the flame detection model obtained through training as a flame detection algorithm;
the high-level monitoring module 205 is configured to perform flame recognition on the high-level equipment through the high-level monitoring camera according to the flame detection algorithm, and judge whether the high-level equipment generates a fire condition according to a preset high-level flame judgment rule;
and the low-position monitoring module 206 is used for identifying the flame of the ground equipment through the low-position monitoring camera according to the flame detection algorithm and judging whether the ground equipment generates a fire or not.
The substation fire monitoring system 200 can implement the steps in the substation fire monitoring method in the above embodiment, and can implement the same technical effects, which are described in the above embodiment and not described herein again.
Referring to fig. 7, fig. 7 is a schematic structural diagram of a computer device provided in an embodiment of the present invention, where the computer device 300 includes: a memory 302, a processor 301, and a computer program stored on the memory 302 and executable on the processor 301.
The processor 301 calls the computer program stored in the memory 302 to execute the steps in the park management method provided by the embodiment of the present invention, please refer to fig. 1, which specifically includes:
s101, determining a monitoring area comprising a transformer substation area, and dividing the monitoring area into a wire area, the transformer substation area and a field area surrounding the transformer substation area, wherein the transformer substation area is rectangular, the transformer substation area comprises aerial high-altitude equipment and ground equipment, the aerial high-altitude equipment is located in the air, the ground equipment is located on the ground, the wire area is divided into a first wire area and a second wire area, and the first wire area and the second wire area are respectively arranged on two opposite sides of the transformer substation area;
s102, arranging a high-position monitoring camera in the transformer substation area, enabling the visual angle of the high-position monitoring camera to cover the high-altitude equipment, arranging a low-position monitoring camera in the field area, and enabling the visual angle of the low-position monitoring camera to cover the ground equipment.
Further, the visual angle median line of high-order monitoring camera is more than the water flat line with the horizontal direction parallel and level, just the visual angle median line of high-order monitoring camera aligns high altitude equipment, the visual angle median line of low-order monitoring camera is below the water flat line with the horizontal direction parallel and level, just the visual angle median line of low-order monitoring camera aligns ground equipment.
Furthermore, the method comprises the steps of arranging a high-position monitoring camera in the transformer substation area, enabling the visual angle of the high-position monitoring camera to cover the high-altitude equipment, arranging a low-position monitoring camera in the field area, and enabling the visual angle of the low-position monitoring camera to cover the ground equipment, and specifically comprises the following steps:
the high-order monitoring camera includes main monitoring camera and supplementary monitoring camera set up one respectively on four corners in the transformer substation area main monitoring camera makes all the visual angle range of main monitoring camera covers whole all in the transformer substation area high altitude plant deploy at least one on the boundary in the transformer substation area supplementary monitoring camera makes the visual angle of supplementary monitoring camera covers arbitrary high altitude plant set up at least two in the field area low level monitoring camera makes all the visual angle of low level monitoring camera covers all ground equipment.
S103, establishing a monitoring data table comprising a plurality of data fields for the high-order monitoring camera.
Furthermore, the data field comprises a camera number, alarm time and a current zone bit, and the current zone bit is used for marking that the camera is in a direct sunlight state or a non-direct sunlight state.
S104, acquiring real data with real flames and shooting data shot in an actual scene, acquiring simulation data according to the real data and the shooting data, training a flame detection model by taking the real data, the shooting data and the simulation data as a total data set, storing the flame detection model obtained by training, and taking the flame detection model as a flame detection algorithm; the shooting data are acquired through the high-order monitoring camera and the low-order monitoring camera.
Furthermore, the step of acquiring real data with real flames and shooting data shot in an actual scene, acquiring simulation data according to the real data and the shooting data, training a flame detection model by using the real data, the shooting data and the simulation data as a total data set, storing the flame detection model obtained by training, and using the flame detection model as a flame detection algorithm includes the following substeps:
acquiring a flame image with real flame, recording the flame image as the real data, acquiring an actual shooting image of the transformer substation area as shooting data, and randomly mapping the flame image in the real data to the actual shooting image in the shooting data to obtain the simulation data;
taking the real data, the shooting data and the simulation data as training data sets, and dividing the training data sets into a first training set and a first verification set according to a first proportion;
defining the number of the high-level monitoring cameras as N, and continuously dividing the first training set for N times by using a second proportion to obtain N groups of actual training sets and actual verification sets;
establishing a flame detection model based on a convolutional neural network, respectively training the flame detection model for N times by using a plurality of groups of actual training sets and actual verification sets, and outputting N flame detection algorithms which accord with a preset accuracy threshold;
and respectively setting N flame detection algorithms in different high-level monitoring cameras, and setting the flame detection algorithm with the highest accuracy in the low-level monitoring camera.
S105, carrying out flame identification on the high-altitude equipment through the high-level monitoring camera according to the flame detection algorithm, and judging whether the high-altitude equipment generates a fire condition according to a preset high-level flame judgment rule.
Furthermore, the high-level monitoring camera is used for carrying out flame identification on the high-level equipment according to the flame detection algorithm, and judging whether the high-level equipment generates a fire condition according to a preset high-level flame judgment rule, wherein the steps are as follows:
the high-level monitoring camera carries out flame recognition on the high-altitude equipment according to the flame detection algorithm, wherein the fire condition is judged according to the high-level flame judgment rule, and the high-level flame judgment rule specifically comprises the following steps:
if the main monitoring camera firstly identifies flames and records the flames in the monitoring data table corresponding to the main monitoring camera, further checking whether fire records at the same time exist in the monitoring data tables corresponding to the other high-level monitoring cameras in the non-sunlight direct-radiation state, and if yes, judging that the fire occurs;
if the auxiliary monitoring camera firstly identifies flames and records the flames in the monitoring data table corresponding to the auxiliary monitoring camera, whether fire records at the same time exist in the monitoring data table corresponding to the main monitoring camera in the non-sunlight direct-radiation state or not is checked, and if yes, the fire is judged to occur.
S106, carrying out flame identification on the ground equipment through the low-level monitoring camera according to the flame detection algorithm, and judging whether the ground equipment generates a fire or not.
Furthermore, before carrying out flame identification through the high monitoring camera and the low monitoring camera, the method further comprises:
judging the illumination condition of the current environment, wherein:
if the environment is daytime, the high-order monitoring camera and the low-order monitoring camera use a preset exposure adjustment algorithm to perform flame identification;
and if the environment is at night, the high-level monitoring camera and the low-level monitoring camera perform flame identification by using a preset night enhancement algorithm.
The computer device 300 provided in the embodiment of the present invention can implement the steps in the transformer substation fire monitoring method in the above embodiment, and can implement the same technical effects, and reference is made to the description in the above embodiment, which is not repeated herein.
The embodiment of the invention also provides a computer-readable storage medium, wherein a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the computer program realizes each process and step in the transformer substation fire monitoring method provided by the embodiment of the invention, and can realize the same technical effect, and in order to avoid repetition, the computer program is not repeated.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal (such as a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present invention.
While the present invention has been described with reference to the preferred embodiments, it is to be understood that the invention is not limited to the disclosed embodiments, which are illustrative, but not restrictive, and that various changes may be made therein by those skilled in the art without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (10)
1. A fire monitoring method for a transformer substation is characterized by comprising the following steps:
determining a monitoring area comprising a transformer substation area, and dividing the monitoring area into a wire area, the transformer substation area and a field area surrounding the transformer substation area, wherein the transformer substation area is rectangular, the transformer substation area comprises aerial high-altitude equipment and ground equipment, the aerial high-altitude equipment is located in the air, the ground equipment is located on the ground, the wire area is divided into a first wire area and a second wire area, and the first wire area and the second wire area are respectively arranged on two opposite sides of the transformer substation area;
arranging a high-position monitoring camera in the transformer substation area, enabling the visual angle of the high-position monitoring camera to cover the high-altitude equipment, arranging a low-position monitoring camera in the field area, and enabling the visual angle of the low-position monitoring camera to cover the ground equipment;
establishing a monitoring data table comprising a plurality of data fields for the high-order monitoring camera;
acquiring real data with real flame and shooting data shot in an actual scene, acquiring simulation data according to the real data and the shooting data, training a flame detection model by taking the real data, the shooting data and the simulation data as a total data set, storing the flame detection model obtained by training, and taking the flame detection model as a flame detection algorithm; the shooting data is acquired by the high-order monitoring camera and the low-order monitoring camera;
the high-level monitoring camera is used for carrying out flame recognition on the high-level equipment according to the flame detection algorithm, and judging whether the high-level equipment generates a fire condition according to a preset high-level flame judgment rule;
and carrying out flame identification on the ground equipment through the low-position monitoring camera according to the flame detection algorithm, and judging whether the ground equipment generates a fire or not.
2. The substation fire monitoring method according to claim 1, wherein the view angle median line of the high monitoring camera is above a horizontal line level with the horizontal direction, and the view angle median line of the high monitoring camera is aligned with the high-altitude device, the view angle median line of the low monitoring camera is below the horizontal line level with the horizontal direction, and the view angle median line of the low monitoring camera is aligned with the ground device.
3. The substation fire monitoring method according to claim 2, wherein the step of arranging a high-level monitoring camera in the substation area, enabling a viewing angle of the high-level monitoring camera to cover the high-altitude equipment, and arranging a low-level monitoring camera in the field area, and enabling a viewing angle of the low-level monitoring camera to cover the ground equipment specifically comprises the steps of:
the high-order monitoring camera includes main monitoring camera and supplementary monitoring camera the position of four angles in transformer substation area sets up one respectively main monitoring camera makes all the visual angle range of main monitoring camera covers whole all in the transformer substation area high altitude plant deploy at least one on the regional border of transformer substation supplementary monitoring camera makes the visual angle of supplementary monitoring camera cover arbitrary high altitude plant the open-air region sets up at least two low level monitoring camera makes all the visual angle of low level monitoring camera covers all ground equipment.
4. The substation fire monitoring method of claim 3, wherein the data fields comprise a camera number, an alarm time, and a current flag for marking whether the camera is in a direct sunlight state or a non-direct sunlight state.
5. The substation fire monitoring method according to claim 4, wherein the step of acquiring real data with real flames and shot data shot in an actual scene, acquiring simulation data according to the real data and the shot data, training a flame detection model by using the real data, the shot data and the simulation data as a total data set, storing the trained flame detection model, and using the flame detection model as a flame detection algorithm comprises the following substeps:
acquiring a flame image with real flame, recording the flame image as the real data, acquiring an actual shooting image of the transformer substation area as shooting data, and randomly mapping the flame image in the real data to the actual shooting image in the shooting data to obtain the simulation data;
taking the real data, the shooting data and the simulation data as training data sets, and dividing the training data sets into a first training set and a first verification set according to a first proportion;
defining the number of the high-level monitoring cameras as N, and continuously dividing the first training set for N times by using a second proportion to obtain N groups of actual training sets and actual verification sets;
establishing a flame detection model based on a convolutional neural network, respectively training the flame detection model for N times by using a plurality of groups of actual training sets and actual verification sets, and outputting N flame detection algorithms which accord with a preset accuracy threshold;
and respectively setting N flame detection algorithms in different high-level monitoring cameras, and setting the flame detection algorithm with the highest accuracy in the low-level monitoring camera.
6. The substation fire monitoring method according to claim 5, wherein in the step of identifying flames of the high-altitude equipment by the high-altitude monitoring camera according to the flame detection algorithm and judging whether the high-altitude equipment is in a fire situation according to a preset high-altitude flame judgment rule, the high-altitude flame judgment rule is specifically as follows:
if the main monitoring camera firstly identifies flames and records the flames in the monitoring data table corresponding to the main monitoring camera, further checking whether fire records at the same time exist in the monitoring data tables corresponding to the other high-level monitoring cameras in the non-sunlight direct-radiation state, and if yes, judging that the fire occurs;
if the auxiliary monitoring camera firstly identifies flames and records the flames in the monitoring data table corresponding to the auxiliary monitoring camera, whether fire records at the same time exist in the monitoring data table corresponding to the main monitoring camera in the non-sunlight direct-radiation state or not is checked, and if yes, the fire is judged to occur.
7. The substation fire monitoring method according to claim 5, wherein before the flame identification is performed by the high-level monitoring camera and the low-level monitoring camera, the method further comprises:
judging the illumination condition of the current environment, wherein:
if the environment is daytime, the high-order monitoring camera and the low-order monitoring camera use a preset exposure adjustment algorithm to perform flame identification;
and if the environment is at night, the high-level monitoring camera and the low-level monitoring camera perform flame identification by using a preset night enhancement algorithm.
8. A fire monitoring system of a transformer substation is characterized by comprising:
the system comprises a region dividing module, a monitoring module and a control module, wherein the region dividing module is used for determining a monitoring region comprising a transformer substation region, and dividing the monitoring region into a wire region, the transformer substation region and a field region surrounding the transformer substation region, the transformer substation region is rectangular, the transformer substation region comprises aerial high-altitude equipment and ground equipment, the aerial high-altitude equipment and the ground equipment are located in the air, the wire region is divided into a first wire region and a second wire region, and the first wire region and the second wire region are respectively arranged on two opposite sides of the transformer substation region;
the camera point location confirming module is used for arranging a high-position monitoring camera in the transformer substation area, enabling the visual angle of the high-position monitoring camera to cover the high-altitude equipment, arranging a low-position monitoring camera in the field area, and enabling the visual angle of the low-position monitoring camera to cover the ground equipment;
the data table establishing module is used for establishing a monitoring data table comprising a plurality of data fields for the high-order monitoring camera;
the detection algorithm training module is used for acquiring real data with real flames and shooting data shot in an actual scene, acquiring simulation data according to the real data and the shooting data, training a flame detection model by taking the real data, the shooting data and the simulation data as a total data set, storing the flame detection model obtained by training, and taking the flame detection model as a flame detection algorithm; the shooting data is acquired by the high-order monitoring camera and the low-order monitoring camera;
the high-level monitoring module is used for identifying flames of the high-level equipment through the high-level monitoring camera according to the flame detection algorithm and judging whether the high-level equipment generates fire conditions according to a preset high-level flame judgment rule;
and the low-level monitoring module is used for identifying the flame of the ground equipment through the low-level monitoring camera according to the flame detection algorithm and judging whether the ground equipment generates a fire or not.
9. A computer device, comprising: memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps in the substation fire monitoring method according to any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon a computer program which, when being executed by a processor, carries out the steps of the substation fire monitoring method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210014320.7A CN114022850B (en) | 2022-01-07 | 2022-01-07 | Transformer substation fire monitoring method and system and related equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210014320.7A CN114022850B (en) | 2022-01-07 | 2022-01-07 | Transformer substation fire monitoring method and system and related equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114022850A true CN114022850A (en) | 2022-02-08 |
| CN114022850B CN114022850B (en) | 2022-05-03 |
Family
ID=80069715
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210014320.7A Active CN114022850B (en) | 2022-01-07 | 2022-01-07 | Transformer substation fire monitoring method and system and related equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114022850B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115424404A (en) * | 2022-09-06 | 2022-12-02 | 湖南省永神科技有限公司 | Lighting system with fire alarm function |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080191886A1 (en) * | 2006-12-12 | 2008-08-14 | Industrial Technology Research Institute | Flame detecting method and device |
| EP2075037A1 (en) * | 2007-12-27 | 2009-07-01 | Union Fenosa Distribucion, S.A. | Integral fire safety system in high-voltage substations |
| CN101650866A (en) * | 2009-09-22 | 2010-02-17 | 华南理工大学 | Fire detecting system applied to unmanned helicopter and fire detecting method thereof |
| CN105279331A (en) * | 2015-10-23 | 2016-01-27 | 国家电网公司 | Substation site monitoring camera constructing, deploying and modeling method |
| CN206907184U (en) * | 2017-07-28 | 2018-01-19 | 国网安徽省电力公司检修公司 | A kind of outside transformer substation fire automatic monitoring early warning system |
| JP2018072881A (en) * | 2016-10-24 | 2018-05-10 | ホーチキ株式会社 | Fire disaster monitoring system |
| CN111091072A (en) * | 2019-11-29 | 2020-05-01 | 河海大学 | YOLOv 3-based flame and dense smoke detection method |
| US20200141653A1 (en) * | 2018-11-02 | 2020-05-07 | Honeywell International Inc. | Flame analytics system |
| CN111541877A (en) * | 2020-05-18 | 2020-08-14 | 国网河南省电力公司南阳供电公司 | Automatic monitoring system for substation equipment |
| WO2021034726A1 (en) * | 2019-08-16 | 2021-02-25 | David Bonn | Flame finding with automated image analysis |
| US20210173414A1 (en) * | 2019-11-22 | 2021-06-10 | JAR Scientific LLC | Cooperative unmanned autonomous aerial vehicles for power grid inspection and management |
| CN113012383A (en) * | 2021-03-26 | 2021-06-22 | 深圳市安软科技股份有限公司 | Fire detection alarm method, related system, related equipment and storage medium |
-
2022
- 2022-01-07 CN CN202210014320.7A patent/CN114022850B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080191886A1 (en) * | 2006-12-12 | 2008-08-14 | Industrial Technology Research Institute | Flame detecting method and device |
| EP2075037A1 (en) * | 2007-12-27 | 2009-07-01 | Union Fenosa Distribucion, S.A. | Integral fire safety system in high-voltage substations |
| CN101650866A (en) * | 2009-09-22 | 2010-02-17 | 华南理工大学 | Fire detecting system applied to unmanned helicopter and fire detecting method thereof |
| CN105279331A (en) * | 2015-10-23 | 2016-01-27 | 国家电网公司 | Substation site monitoring camera constructing, deploying and modeling method |
| JP2018072881A (en) * | 2016-10-24 | 2018-05-10 | ホーチキ株式会社 | Fire disaster monitoring system |
| CN206907184U (en) * | 2017-07-28 | 2018-01-19 | 国网安徽省电力公司检修公司 | A kind of outside transformer substation fire automatic monitoring early warning system |
| US20200141653A1 (en) * | 2018-11-02 | 2020-05-07 | Honeywell International Inc. | Flame analytics system |
| WO2021034726A1 (en) * | 2019-08-16 | 2021-02-25 | David Bonn | Flame finding with automated image analysis |
| US20210173414A1 (en) * | 2019-11-22 | 2021-06-10 | JAR Scientific LLC | Cooperative unmanned autonomous aerial vehicles for power grid inspection and management |
| CN111091072A (en) * | 2019-11-29 | 2020-05-01 | 河海大学 | YOLOv 3-based flame and dense smoke detection method |
| CN111541877A (en) * | 2020-05-18 | 2020-08-14 | 国网河南省电力公司南阳供电公司 | Automatic monitoring system for substation equipment |
| CN113012383A (en) * | 2021-03-26 | 2021-06-22 | 深圳市安软科技股份有限公司 | Fire detection alarm method, related system, related equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 郑晓琼等: "变电站室外火灾自动监测预警系统的应用研究", 《电力安全技术》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115424404A (en) * | 2022-09-06 | 2022-12-02 | 湖南省永神科技有限公司 | Lighting system with fire alarm function |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114022850B (en) | 2022-05-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109484935A (en) | A kind of lift car monitoring method, apparatus and system | |
| CN108474657B (en) | Environment information acquisition method, ground station and aircraft | |
| CN108846418A (en) | A kind of positioning of cable machinery temperature anomaly and recognition methods | |
| US8705890B2 (en) | Image alignment | |
| CN114022850B (en) | Transformer substation fire monitoring method and system and related equipment | |
| CN202268048U (en) | Security monitoring system | |
| CN105407276A (en) | Photographing method and equipment | |
| CN103106766A (en) | Forest fire identification method and forest fire identification system | |
| CN111062234A (en) | Monitoring method, intelligent terminal and computer readable storage medium | |
| CN111368741A (en) | High-altitude parabolic detection system | |
| CN105868748A (en) | Data service platform on basis of cloud processing | |
| CN110572570B (en) | Intelligent recognition shooting method and system for multi-person scene and storage medium | |
| CN112184628B (en) | Infrared duplex wave image and cloud early warning system and method for flood prevention and danger detection of dike | |
| CN114268736A (en) | Tower footing dome camera shooting method with high space coverage | |
| CN112969034A (en) | Method and device for verifying point distribution scheme of camera device and readable storage medium | |
| CN112671104A (en) | Transformer substation multidimensional scene control platform facing complex scene | |
| CN113096337B (en) | Moving target identification processing method for complex background and intelligent security system | |
| CN105933676A (en) | Remote control platform based on image analysis | |
| CN105869330A (en) | Security protection monitor for preventing illegal encroachment on office building | |
| CN116153015A (en) | Monitoring system and monitoring method for monitoring forest fire prevention based on 5G video | |
| CN205610774U (en) | Automatic portrait system of calling roll of prison | |
| Tamaki et al. | An automatic compensation system for unclear area in 360-degree images using pan-tilt camera | |
| CN114339168A (en) | Regional security monitoring method and device, electronic equipment and storage medium | |
| CN114550046A (en) | Fire hazard identification method, device, processor, storage medium and electronic equipment | |
| CN210183095U (en) | Intelligent patrol auxiliary system for transformer substation |
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 | ||
| PP01 | Preservation of patent right |
Effective date of registration: 20240109 Granted publication date: 20220503 |
|
| PP01 | Preservation of patent right |