CN112288984A - Three-dimensional visual unattended substation intelligent linkage system based on video fusion - Google Patents
Three-dimensional visual unattended substation intelligent linkage system based on video fusion Download PDFInfo
- Publication number
- CN112288984A CN112288984A CN202010961269.1A CN202010961269A CN112288984A CN 112288984 A CN112288984 A CN 112288984A CN 202010961269 A CN202010961269 A CN 202010961269A CN 112288984 A CN112288984 A CN 112288984A
- Authority
- CN
- China
- Prior art keywords
- video
- subsystem
- monitoring center
- alarm
- dimensional
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B17/00—Fire alarms; Alarms responsive to explosion
- G08B17/06—Electric actuation of the alarm, e.g. using a thermally-operated switch
-
- 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
- G08B21/18—Status alarms
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N13/00—Stereoscopic video systems; Multi-view video systems; Details thereof
- H04N13/10—Processing, recording or transmission of stereoscopic or multi-view image signals
- H04N13/106—Processing image signals
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Alarm Systems (AREA)
Abstract
The invention relates to a three-dimensional visual unattended substation intelligent linkage system based on video fusion. The system comprises a 3D video live-action fusion subsystem, an intelligent patrol subsystem, a sensor subsystem, a rail machine patrol subsystem, a door magnet and perimeter alarm subsystem, a dome machine linkage subsystem, a flame identification early warning subsystem and a monitoring center, wherein the subsystems are mutually connected and communicated with the monitoring center. The three-dimensional visual unattended intelligent power transformation linkage system is realized by fusing the three-dimensional video, so that all-weather, all-around and 24-hour uninterrupted intelligent monitoring on the power transformation station is realized, the three-dimensional live view of the power transformation station is randomly browsed and checked, the fault in the power transformation station is alarmed and prompted, a worker can watch the video in a monitoring room, the real-time monitoring and dispatching command on a plurality of power transformation stations in the jurisdiction are realized, the worker is prevented from patrolling power transformation facility equipment every day, and the monitoring capability and the working efficiency are improved.
Description
Technical Field
The invention relates to the field of video image fusion processing and automatic control, in particular to the field of fusion of video data and a three-dimensional model, and realizes panoramic three-dimensional monitoring of a transformer substation, all-weather unattended operation, intelligent abnormality identification and timely alarm linkage disposal through interconnection and mutual control of all sensors.
Background
With the adoption of the construction of high-speed rails in China, about thousands of substations exist in the high-speed rail system in China at present, stable and reliable power supply is provided, and the safe and efficient operation of the whole railway network is guaranteed. In order to ensure the stability of the transformer substations, workers need to be arranged to check and maintain all power supply equipment in the whole power grid, and parameters of the whole equipment of the transformer substations and the surrounding environment of the transformer substations are recorded and analyzed.
The inspection management of the substation staff to the substation mainly comprises checking and recording operation parameters of each device of the substation, and inspecting the internal conditions of the substation and the surrounding environment of the substation, but the inspection is mainly carried out in a mode of manual fixed time or irregular sampling inspection. If some parameters of the transformer substation are abnormal in these periods or accidents (such as fire) occur in the internal and external environments of the transformer substation, if the parameters are not normal in time, measures are taken in time, power supply faults are caused, and inestimable loss is brought.
In order to improve monitoring effect and all-weather monitoring, some intelligent monitoring systems are put into use at present, however, most of the existing intelligent monitoring systems monitor by installing a plurality of cameras in a transformer substation, but only can detect abnormality by observing a screen all weather by a person on duty in a camera monitoring mode, and once an accident occurs, such as a fire, the system cannot automatically identify and cannot actively alarm, so that dangerous case disposal cannot be further performed on the transformer substation, and accident loss is aggravated. After the existing intelligent detection system acquires single-channel video information through a plurality of cameras, nine-grid or sixteen-grid is often adopted to present video images, the video information cannot be correlated, and the random information causes visual fatigue of operators on duty. The video adopts a two-dimensional mode, which is not beneficial to the integral control of the transformer substation field, so that the existing resources of the transformer substation can not be reasonably controlled to take appropriate measures for dangerous situations.
In the prior art, the entrance guard system is used for preventing illegal persons from entering the system through a worker on duty or an entrance guard system, however, the modes cause human resource waste and can not comprehensively avoid illegal invasion. When illegal invasion occurs, the system cannot find and feed back to the monitoring center in time, and cannot track and record the activity track of the invader. When illegal intruders steal and damage the equipment of the transformer substation, the alarm cannot be given in time, so that the serious power supply fault is caused.
In view of this, an intelligent comprehensive linkage platform for unattended operation of a transformer substation needs to be designed, the platform can monitor all equipment of the transformer substation in all weather, video data can be fused in a three-dimensional panoramic model in real time, overall association and comprehensive scheduling are achieved, the internal and external environments of the transformer substation are checked in real time, the real-time performance of equipment operation control is improved, accident potential hazards are discovered in time, continuous and stable operation of the transformer substation is guaranteed, and excessive intervention of operators on duty is basically not needed, so that the operation and maintenance labor cost is reduced.
Disclosure of Invention
In summary, the present invention aims to provide an unattended intelligent linkage system for a three-dimensional transformer substation based on a video fusion technology, which can splice and fuse video information into a three-dimensional model to monitor and identify various devices, surrounding environments, illegal invasion, etc. of the transformer substation, and in a three-dimensional real scene, the system can perform panoramic stereo observation, linkage, monitoring and alarming, thereby improving the basis of overall control, ensuring the continuous and stable operation of the transformer substation, realizing unattended operation, and greatly saving the labor cost.
The technical scheme adopted by the invention is as follows:
the utility model provides a three-dimensional visual unmanned on duty transformer substation intelligence linked system based on video fusion, its integrated multinomial subsystem realizes each item demand respectively, and the subsystem mainly includes: the system comprises a 3D video live-action fusion subsystem, an intelligent patrol subsystem, a sensor subsystem, a rail machine patrol subsystem, a door magnet and perimeter alarm subsystem, a ball machine linkage subsystem and a flame identification and early warning subsystem. And all the subsystems are interconnected and communicated with the monitoring center.
Further, the 3D video live-action fusion subsystem aims to construct a real-time panoramic stereo scene of the transformer station by fusing video data in a three-dimensional panoramic model in real time. The 3D video live-action fusion subsystem comprises a video acquisition module, a video fusion module and a video display module. And visually displaying the point positions, the number and the video coverage area of each path of camera in the substation in a three-dimensional scene. The video acquisition module comprises a plurality of video image acquisition devices (such as cameras) which are connected with the monitoring center in a wired or wireless mode to exchange information. The video image acquisition equipment is arranged at an outlet of a transformer substation, near power supply equipment of the transformer substation and the like. And the multi-channel video information acquired by the video acquisition module is transmitted to the video fusion module through the data transmission link, the multi-channel videos are fused in the three-dimensional model, and the video display module browses and checks the multi-channel videos. Preferably, the multi-channel video can be fused in the three-dimensional model by using the technology disclosed in the patent "an efficient GPU three-dimensional video fusion rendering method" (patent publication No. CN 104616243A).
The patent "an efficient GPU three-dimensional video fusion drawing method" is an efficient GPU three-dimensional video fusion drawing method, and the method comprises the following steps: acquiring video data input by a plurality of paths of video streams through a video object buffer area; performing extensible hierarchical decoding in a GPU, wherein a decoding thread is controlled and driven by the visual characteristic of a corresponding three-dimensional scene part on which a video object depends; after decoding, binding and storing all image sequences and texture identification serial numbers obtained by decoding corresponding time segments according to the synchronous time in an image texture buffer area; sampling the texture in the image texture buffer area, mapping the texture to the surface of an object in a three-dimensional scene, completing other operations related to realistic drawing, and finally outputting a virtual-real fusion drawing result based on a video.
Furthermore, the intelligent patrol subsystem is mainly used for patrolling and processing various equipment parameters, surrounding environments and internal abnormal conditions of the substation. In the three-dimensional live-action scene, a patrol path is randomly established in advance according to needs, and equipment is automatically patrolled. In the three-dimensional live-action scene after the video is fused, the intelligent patrol subsystem walks into the system according to the patrol visual angle of the staff and checks the running state of each device. The intelligent patrol subsystem comprises an automatic identification module and an automatic alarm module. The range identified by the automatic identification module comprises various preset dial readings, equipment switch states and the like. For dial plate reading, the module identifies a dial plate for a single-frame image in a video, and automatically calculates according to the position and angle information of each pointer of the dial plate and the reading rule of the dial plate to obtain the dial plate reading; for the device on-off state, the module automatically recognizes two states (on, off) based on a deep learning model of the neural network. And after the abnormity is found, the abnormal information and the video image of the abnormal information are fed back to the monitoring center, the position is marked in the three-dimensional scene, and the alarm equipment in the automatic alarm module is triggered to realize linkage.
Furthermore, the sensor subsystem aims to integrate various sensors, increase accurate grasping of internal environment parameters of the substation and timely handle abnormal conditions. The subsystem comprises a smoke sensor, a temperature sensor, a humidity sensor, a pressure sensor and the like. Each sensor is connected to the Internet of things, and output information is directly transmitted to a data analysis module of the monitoring center. The data analysis module analyzes each detection result in real time, marks abnormal information in the three-dimensional video fusion scene in time, triggers the alarm equipment of the monitoring center and informs workers of processing in time. The data analysis module is located the surveillance center, with being located the power control equipment UNICOM of surveillance center, and the data analysis module obtains the severity grade of abnormal information according to the sensor, carries out strict control to the power.
Furthermore, the track machine patrol subsystem aims at dynamically and circularly patrolling each main instrument panel of the substation, automatically identifying the reading of the instrument panel and analyzing and alarming for abnormity. And (3) identifying the reading of the equipment instrument by using a mode of routing inspection by using the rail machine and the camera and using a digital image algorithm technology, and if the reading is not in a safe area, stopping the operation of the rail machine in time and uploading the reading to a monitoring center. In a real-time three-dimensional scene, the position and the abnormal value of abnormal equipment are marked, the browsing visual angle of the system is adjusted in time, the equipment information is browsed and checked, the condition is confirmed, and further alarm processing is carried out.
The mode of the track machine and the camera for inspection refers to that the camera is pushed to continuously inspect on a preset route of the track machine, the camera automatically pauses for a plurality of times at certain preset positions, the angle of the camera is adjusted, and the reading of certain devices at the positions is shot or the current state of the devices is identified.
The method comprises the steps of identifying a dial plate by using a single-frame image in a video, and automatically calculating according to the reading rule of the dial plate by combining the position and angle information of each pointer of the dial plate to obtain the reading of the dial plate.
Further, the door magnetism and perimeter alarm subsystem is mainly used for controlling and managing the gates of the entrances and exits of the substation and the external environment of a key area. The subsystem comprises all door magnetic control modules arranged in a substation and a boundary line enclosing a security key area, wherein the modules are additionally marked in a three-dimensional real scene, and the system can obviously see the modules. Data collected by the door magnet and perimeter alarm subsystem are uniformly accessed to a data analysis module of the monitoring center as data input, the data are analyzed, and the monitoring center can send a control command to the subsystem to control door magnet and perimeter alarm service.
Further, the ball machine linkage subsystem is mainly used for continuously responding to the area concerned by the user by adjusting the posture of the ball machine according to the abnormal information position (the equipment position information of the door magnet and perimeter alarm subsystem, the sensor subsystem and other subsystems). The subsystem comprises all security dome cameras, a video processing and analyzing module and an alarm device, wherein all the security dome cameras are connected with the video processing and analyzing module, the video processing and analyzing module performs data interaction with a monitoring center, abnormal information positioning is performed, and three-dimensional linkage with the dome cameras is achieved. The alarm device is used for alarming when the video analysis part of the monitoring center finds abnormality.
The video processing and analyzing module of the ball machine linkage subsystem processes and analyzes video data of a plurality of cameras in the system, whether abnormal information exists in videos played by the cameras is checked, if abnormal information exists, the position coordinate of the abnormal information is calculated, the coordinate is transmitted to the ball machine, and the ball machine is aimed at the installation position and orientation coordinate information of the ball machine. And calculating the angle of the ball machine which should rotate by combining the position information of the target point, and then playing the video.
Further, the flame early warning and identifying subsystem mainly has the functions of carrying out flame detection on video information and finding out the fire in time and comprises various security cameras, a ball machine and an alarm device. Preferably, the fire identification processing part is realized by the technology disclosed in the patent 3D stereoscopic fire identification method and system (patent publication number: CN 109002746A). The 3D fire identification method and system provide a 3D fire identification method and system, and can conveniently and effectively analyze and alarm fire in the video.
The invention has the beneficial effects that: through fusing three-dimensional videos, the three-dimensional visual unattended intelligent substation linkage system is built, all-weather, all-directional and 24-hour uninterrupted intelligent monitoring on the substation is achieved, the three-dimensional real scene of the substation is browsed and checked at will, faults in the substation are alarmed and prompted, emergency state automatic control can be set, a worker can watch videos in a monitoring room, real-time monitoring and dispatching command on a plurality of substations in the jurisdiction are achieved, the worker is prevented from patrolling substation facility equipment for at least 2 times every day, and monitoring capacity and working efficiency are improved.
Drawings
Fig. 1 is a schematic diagram of the principle framework of the present invention.
Fig. 2 is a schematic flow chart of the system of the present invention.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, the present invention shall be described in further detail with reference to the following detailed description and accompanying drawings.
Fig. 1 is a schematic diagram of the principle framework of the present invention. As shown in the figure, the technical scheme adopted by the invention is to integrate multiple subsystems, which respectively realize various functions, and the subsystems mainly comprise: the system comprises a 3D video live-action fusion subsystem, an intelligent patrol subsystem, a sensor subsystem, a rail machine patrol subsystem, a door magnet and perimeter alarm subsystem, a ball machine linkage subsystem and a flame identification early warning subsystem. Each subsystem is associated with the monitoring center and comprises each functional module.
And the monitoring center is provided with a power supply control device, a data analysis module and an alarm device. The power supply control equipment is used for controlling the power supply switches of some abnormal equipment after various detection equipment detects serious abnormal data or serious accidents such as flame alarm and the like, so that serious loss is avoided. The data analysis module analyzes each detection result of each subsystem in real time, marks abnormal information in a three-dimensional video fusion scene in time, triggers alarm equipment of a monitoring center and informs workers of processing in time. The data analysis module is also communicated with the power supply control equipment, and the data analysis module strictly controls the power supply according to the severity level of the abnormal information acquired by the sensor. The alarm device is used for responding to perimeter intrusion and sending a standby alarm after identifying flame or sensor data abnormity.
The 3D video live-action fusion subsystem comprises a video acquisition module, a video fusion module and a video display module. The video acquisition module adopts one or more digital high-definition cameras, such as CCD (charge coupled device) cameras, and a power supply device arranged in the transformer substation, and is used for continuously acquiring video image data of a certain range of the transformer substation and transmitting the video image data to the video fusion module through a video transmission line. The video fusion module adopts an efficient GPU three-dimensional video fusion drawing method for received video data, combines a three-dimensional live-action model of the transformer substation, realizes panoramic stitching of videos aiming at a video coverage range, is accurately matched and fused with the three-dimensional model of the transformer substation, is displayed in a three-dimensional geographic information (3D GIS) video fusion platform through a video display module, restores a single local independent video into a global true scene, and realizes synchronous display of the videos and the scenes in a three-dimensional transformer substation scene. When abnormal dangerous situations (fire, smoke and the like) occur, the sensor subsystem monitors and discovers the abnormality, transmits the position information of the dangerous situations to the monitoring center in time, and the monitoring center automatically calls the nearest camera and adjusts the posture of the camera to a proper angle, so that the disaster situation can be clearly displayed on the security and protection command system platform at the first time. In addition, the data detected by other subsystems are uniformly sorted by a data analysis module of the monitoring center, abnormal information can be screened and sent to the monitoring center, and the abnormal information is printed and displayed on the platform. The abnormal warning is divided into a plurality of levels, the warning information of the high level triggers the alarm system of the command system, and the warning information of the low level is output to the monitoring center.
The video fusion module adopts a video card to perform a video processing algorithm, such as GTX1080ti by intel, and has a strong video encoding and decoding processing capability, and of course, other video cards can also achieve the purpose of the present invention, such as RTX2080 Ti.
Video data, high-voltage chamber data, various detection data of a temperature sensor, a smoke sensor and a humidor are accessed into a data analysis module of the monitoring center, and in three-dimensional geographic information, the devices are marked in the system by adopting different icons. The temperature sensor can adopt a constant temperature type detector or a differential temperature type detector, the smoke sensor also has an encoding type, a switch type and the like, other devices of various sensors are not listed one by one, and threshold parameters of various detectors, such as a temperature threshold, a smoke threshold, a pressure threshold, a humidity threshold and the like, are preset in the data analysis module. The smoke threshold value can be set to be 0, namely, when the smoke value sensed by the smoke sensor is output as long as any value is not 0, the smoke sensor gives an alarm to a command center. After the pressure threshold, the humidity threshold and the temperature threshold are set, a series of reactions are triggered after the numerical values output by the corresponding sensors are not smaller than the corresponding thresholds, the thresholds are set to be in certain levels, for example, the lowest level can be printed and output on a screen only in a monitoring center, the middle level can sound an alarm and the like, and the most serious level can even directly control a power switch of the whole substation.
In this embodiment, the door magnet and the perimeter alarm subsystem, wherein the door magnet system is installed at a door and window position of a substation, the door magnet mainly comprises a switch part and a magnet part, when the switch part and the magnet part are very close to each other, that is, when a door or a window is in a closed state, the door magnet switch is in a working state, an alarm sound is emitted after an attack of a forced intruder is received, the alarm information is sent to a monitoring center, a worker of the monitoring center clicks the information, the three-dimensional geographic information system can automatically fly to the position where the abnormality occurs, and in a three-dimensional field, the fusion video is combined, the ambient environment condition of the alarm position is checked, the alarm information is confirmed, and further processing is performed. In the implementation process of the perimeter alarm system, substation workers can draw boundary lines in important areas in a substation according to needs, the boundary lines are graded according to severity, for example, the boundary lines are graded into three grades, the outermost periphery is primary caution, the middle grade is guard-up, the innermost layer is severe caution, the monitoring range of the camera is not smaller than the monitoring perimeter, and when a user enters the perimeter range, the boundary lines are respectively and correspondingly processed according to the previous grade. When the video analysis module sends the most severe warning, the three-dimensional GIS system can directly turn the browsing visual angle to the position, and the staff can confirm the field situation at the first time and process the situation in time. This perimeter warning function, staff can manual cancellation to the legal entering of transformer substation staff when power system inspection maintenance.
In this implementation, the intelligent patrol sub-system, wherein the patrol route is designed comprehensively by the substation staff according to the stability, vulnerability and other states of each equipment in the substation, and certainly, the patrol route may be multiple. When the system is used, a worker selects a certain path, the total patrol time is set, the system can call the cameras along the path along the patrol path, and the video information is checked in real time in the three-dimensional geographic information real scene. After the staff finds a problem in the tour, the tour can be suspended. The subsystem performs data interaction with a data analysis module of the monitoring center, stores the screenshot of the abnormal information, analyzes, identifies and records, and displays and processes the screenshot in the monitoring center.
In the implementation, the ball machine is linked with the subsystems, and the ball machine can be various security cameras and ball machines, and can realize 360-degree rotation shooting. The ball machine is arranged on a high pole which is spaced from the transformer substation at a proper distance and is spacious at the periphery. In the three-dimensional panoramic video, after a worker finds a problem or the overall platform system receives abnormal alarm information, a user clicks the alarm information, the system finds a dome camera at a corresponding position, automatically adjusts the angle and the focal length, and merges the video into a three-dimensional model again for playing.
Wherein, ball machine automatic adjustment to shoot fixed position, realize the concrete step of linkage as follows:
1) and calibrating the position of the dome camera in the three-dimensional geographic information system.
2) And calculating the optimal setting parameters capable of shooting the fixed position according to the internal parameters of the dome camera.
3) And adjusting the ball machine to the optimal position and orientation according to the set parameters.
4) And adjusting video fusion parameters, and fusing the video into the three-dimensional geographic information system again.
5) And setting the browsing visual angle of the three-dimensional geographic information system to the position where the dome camera is arranged, wherein the orientation of the browsing visual angle is consistent with that of the dome camera.
Fig. 2 is a schematic flow chart of the system of the present invention. In the invention, various sensors, security cameras, ball machines and other equipment are marked in the three-dimensional geographic information of the substation, so that interconnection and intercommunication with a monitoring center are realized, and all the equipment realize linkage, specifically the following steps:
1) the abnormal temperature of the equipment is linked with the camera: the temperature sensor is used for monitoring the temperature of the equipment in the sensor subsystem, when the temperature of the equipment exceeds a warning value, sound alarm is triggered, alarm information is uploaded to the monitoring center, the monitoring center marks the position of an abnormal point in the 3D video live-action fusion subsystem automatically according to the alarm position information, alarm is triggered, the 3D video live-action fusion subsystem is linked with a camera nearby through the ball machine linkage subsystem according to the position of the sensor, the visual angle is adjusted to the position of the equipment sending the temperature abnormality, a worker confirms the problem, and a maintenance worker is dispatched to perform emergency maintenance.
2) The rail machine is linked with the camera: in a track machine inspection subsystem, in a track machine and camera inspection mode, the reading of an equipment instrument is identified by using a deep learning technology, the track machine stops running in time when the reading is not in a safe area, and the reading is uploaded to a monitoring center. In the 3D video live-action fusion subsystem, the position and the abnormal numerical value of abnormal equipment are marked, the visual angle of a camera is called and adjusted in time, the equipment condition is browsed and checked, the condition is confirmed, an alarm is given, and maintenance personnel are dispatched in time for emergency maintenance.
3) The abnormal warning area is linked with the monitoring center: the video analysis module of the door sensor and perimeter alarm subsystem detects that suspicious personnel are in the hard alarm area, sends information to the monitoring center, links with the alarm equipment of the monitoring center, links with the camera, adjusts the visual angle of the camera, can clearly see the behavior of the suspicious personnel in the hard alarm area, and takes appropriate action in time according to the situation.
4) Linkage of abnormal flame and a monitoring center: the video analysis module of the flame identification early warning subsystem detects the flame, sends abnormity to the monitoring center, marks the position of the fire source in the 3D video live-action fusion subsystem, triggers an alarm, and the monitoring center links with a camera nearby in real time to call video confirmation information and takes measures in time (if the situation is urgent, the switch can be directly switched off and the power is cut off)
5) The smoke control abnormity is linked with the monitoring center: the smoke sensor of the sensor subsystem continuously detects the concentration of smoke, the data analysis module of the sensor processes the data, an abnormal result is transmitted to the monitoring center, if the abnormal result occurs, an alarm is given out, the abnormal position of the smoke is output, the camera is linked, the visual angle of the camera is adjusted, the position is marked in the 3D video live-action fusion subsystem, and the alarm is triggered.
6) The door magnetism is unusual to be linked with the surveillance center: after the door magnet part of the door magnet and the door magnet part of the perimeter alarm subsystem are illegally intruded, the door magnet and the door magnet part are uploaded to a monitoring center, a camera is linked, the visual angle of the camera is adjusted, an alarm is triggered, and the condition is confirmed by the staff of the monitoring center and abnormal conditions are timely processed.
7) The high-pressure chamber is abnormal and linked with the monitoring center: the pressure sensor of the sensor subsystem detects pressure abnormity and transmits abnormal information to the monitoring center in real time, the abnormal information is output and displayed, the camera is linked, the visual angle of the camera is adjusted, an alarm is triggered, and the staff of the monitoring center confirms the condition and timely handles the abnormity.
8) Integral linkage: the 3D video live-action fusion subsystem is used for monitoring areas in a key mode, splicing panoramic videos in real time, fusing the panoramic videos into three-dimensional geographic information, viewing live-action videos in real time, carrying out three-dimensional overall control, linking all paths of cameras and alarm equipment after problems are found, confirming abnormal alarms in time, linking all resources used in all modes, commanding and scheduling in a unified mode, and eliminating dangerous cases.
The foregoing disclosure of the specific embodiments of the present invention and the accompanying drawings is directed to an understanding of the present invention and its implementation, and it will be appreciated by those skilled in the art that various alternatives, modifications, and variations may be made without departing from the spirit and scope of the invention. The present invention should not be limited to the disclosure of the embodiments and drawings in the specification, and the scope of the present invention is defined by the scope of the claims.
Claims (10)
1. A three-dimensional visual unattended substation intelligent linkage system based on video fusion is characterized by comprising a 3D video live-action fusion subsystem, an intelligent patrol subsystem, a sensor subsystem, a rail machine patrol subsystem, a door magnet and perimeter alarm subsystem, a dome camera linkage subsystem, a flame identification and early warning subsystem and a monitoring center, wherein all the subsystems are mutually connected and communicated with the monitoring center;
the 3D video live-action fusion subsystem constructs a real-time panoramic stereo scene of the transformer substation by fusing video data in a three-dimensional panoramic model in real time;
the intelligent patrol subsystem patrols and processes various equipment parameters, surrounding environments and internal abnormal conditions of the transformer substation, and feeds abnormal information and video images of the abnormal information back to the monitoring center;
the sensor subsystem monitors the internal environmental parameters of the transformer substation through various sensors and sends the parameters to a monitoring center;
the track machine patrol subsystem dynamically rounds each main instrument panel of the transformer substation, automatically identifies the reading of the instrument panel, and analyzes and alarms abnormity;
the door magnetism and perimeter alarm subsystem controls and manages a door of an entrance and an exit of the transformer substation and the external environment of a key area, marks the door magnetism and a perimeter in a three-dimensional real scene, and sends acquired data to a monitoring center;
the dome camera linkage subsystem continuously responds to the area concerned by the user by adjusting the posture of the dome camera according to the abnormal information position;
the flame early warning and identifying subsystem carries out flame detection on the video information, finds a flame in time and feeds the flame back to the monitoring center;
the monitoring center monitors the operation of each subsystem, marks abnormal information in the three-dimensional video fusion scene in time, and triggers the alarm device to inform workers of processing in time.
2. The method according to claim 1, wherein the 3D video live-action fusion subsystem comprises a video capture module, a video fusion module and a video display module, wherein the video capture module obtains multiple channels of video information, transmits the multiple channels of video information to the video fusion module through a data transmission link, fuses the multiple channels of video information in the three-dimensional model, and views the multiple channels of video information on the video display module.
3. The method of claim 1, wherein the intelligent patrol sub-system comprises an automatic identification module and an automatic alarm module; the automatic identification module identifies dial plate reading and equipment switch state; for dial reading, the automatic identification module identifies the dial from a single-frame image in the video, and according to the position and angle information of each pointer of the dial, the automatic identification module combines the reading rule of the dial to further automatically calculate to obtain the dial reading; for the on-off state of the equipment, the automatic identification module automatically identifies the on-off state based on a deep learning model of a neural network; after the abnormity is found out, the automatic identification module feeds the abnormal information and the video image of the abnormal information back to the monitoring center, marks the position in the three-dimensional scene, and triggers the alarm equipment in the automatic alarm module to realize linkage.
4. The method according to claim 1, wherein the sensor subsystem comprises a flue gas sensor, a temperature sensor, a humidity sensor and a pressure sensor, each sensor is connected to the Internet of things, and output information is directly transmitted to a data analysis module of the monitoring center.
5. The method according to claim 1, wherein the rail machine patrol subsystem adopts a rail machine plus camera patrol mode, utilizes a digital image algorithm technology to recognize the reading of the equipment instrument, stops the operation of the rail machine in time if the reading is not in a safe area, and uploads the reading to the monitoring center.
6. The method of claim 1, wherein the door sensor and perimeter alarm subsystem comprises all door sensor control modules disposed in the substation and the perimeter lines enclosing the security key zone, both the door sensor control modules and the perimeter lines being marked in a three-dimensional real scene; data collected by the door magnet and perimeter alarm subsystems are uniformly accessed to a data analysis module of the monitoring center as data input so as to analyze the data; the monitoring center sends control commands to the door magnet and perimeter alarm subsystems to control door magnet and perimeter alarm services.
7. The method of claim 1, wherein the dome camera linkage subsystem includes each security dome camera, a video processing and analysis module, and an alarm device; each security ball machine is connected with the video processing and analyzing module; the video processing and analyzing module performs data interaction with the monitoring center, performs abnormal information positioning and realizes three-dimensional linkage with the dome camera; the alarm device is used for alarming when the video analysis part of the monitoring center finds abnormality.
8. The method according to claim 1, wherein after the fire early warning identification subsystem detects a fire, an abnormality is sent to a monitoring center, the position of a fire source is marked in the 3D video live-action fusion subsystem and an alarm is triggered, the monitoring center is linked with a nearby camera in real time to retrieve video confirmation information, and corresponding measures are taken in time.
9. The method according to claim 1, characterized in that a power supply control device and a data analysis module are arranged in the monitoring center; the power supply control equipment is used for controlling the power supply switches of some abnormal equipment to avoid serious loss after various detection equipment detects serious data abnormality or a flame alarm accident; the data analysis module analyzes various detection results of the sensor subsystem and the door magnet and perimeter alarm subsystem in real time, marks abnormal information in a three-dimensional video fusion scene in time, triggers alarm equipment of a monitoring center and informs workers of processing in time; the data analysis module is also communicated with the power supply control equipment, and the data analysis module strictly controls the power supply according to the severity level of the abnormal information acquired by the sensor.
10. The method of claim 1, wherein each subsystem is interconnected with a monitoring center to achieve linkage, and the linkage comprises: the device temperature abnormity is linked with the camera, the rail machine is linked with the camera, the alarm area abnormity is linked with the monitoring center, the flame abnormity is linked with the monitoring center, the smoke control abnormity is linked with the monitoring center, the door magnet abnormity is linked with the monitoring center, the high pressure chamber abnormity is linked with the monitoring center, and the device temperature abnormity is linked with the camera, the rail machine is linked with the camera, the alarm area abnormity is linked with the monitoring center, the flame.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010249958X | 2020-04-01 | ||
| CN202010249958 | 2020-04-01 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112288984A true CN112288984A (en) | 2021-01-29 |
Family
ID=74420911
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010961269.1A Pending CN112288984A (en) | 2020-04-01 | 2020-09-14 | Three-dimensional visual unattended substation intelligent linkage system based on video fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112288984A (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112927459A (en) * | 2021-03-09 | 2021-06-08 | 湖南农业大学 | Sudoku fire behavior prediction method based on unmanned aerial vehicle vision and application |
| CN113112635A (en) * | 2021-04-12 | 2021-07-13 | 滁州博格韦尔电气有限公司 | Conventional inspection system for intelligent equipment |
| CN113162229A (en) * | 2021-03-24 | 2021-07-23 | 北京潞电电气设备有限公司 | Monitoring device and method thereof |
| CN113259624A (en) * | 2021-03-24 | 2021-08-13 | 北京潞电电气设备有限公司 | Monitoring equipment and method thereof |
| CN113259625A (en) * | 2021-03-24 | 2021-08-13 | 北京潞电电气设备有限公司 | Monitoring system and method thereof |
| CN113724402A (en) * | 2021-11-02 | 2021-11-30 | 长沙能川信息科技有限公司 | Three-dimensional scene fusion method for transformer substation video |
| CN114023048A (en) * | 2021-11-27 | 2022-02-08 | 安徽博达项目管理咨询有限公司 | Engineering supervision system based on artificial intelligence data processing and visual analysis |
| CN114462536A (en) * | 2022-02-09 | 2022-05-10 | 国网宁夏电力有限公司吴忠供电公司 | Method and system for generating labeled data set in entity scene |
| CN114942740A (en) * | 2022-07-12 | 2022-08-26 | 江苏润和软件股份有限公司 | Transformer substation auxiliary equipment online real-time monitoring method and system based on artificial intelligence |
| CN115346303A (en) * | 2022-08-16 | 2022-11-15 | 河南金数网科信息技术有限公司 | Visual campus management system based on internet of things node and GIS |
| CN115695736A (en) * | 2022-12-14 | 2023-02-03 | 广东泰一高新技术发展有限公司 | Intelligent security command system and security command method based on three-dimensional model analysis |
| CN116612594A (en) * | 2023-05-11 | 2023-08-18 | 深圳市云之音科技有限公司 | Intelligent monitoring and outbound system and method based on big data |
| CN117647284A (en) * | 2024-01-29 | 2024-03-05 | 山东凯莱电气设备有限公司 | Monitoring and early warning system and method for electric automatic power distribution cabinet |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103488154A (en) * | 2013-10-09 | 2014-01-01 | 国家电网公司 | Remote comprehensive monitoring system for transformer substation operating environment and linkage control method thereof |
| WO2014139416A1 (en) * | 2013-03-11 | 2014-09-18 | 成都百威讯科技有限责任公司 | Emergent abnormal event intelligent identification alarm device and system |
| CN104155959A (en) * | 2014-08-26 | 2014-11-19 | 国家电网公司 | Unattended comprehensive monitoring system for transformer substation |
| CN106787186A (en) * | 2016-12-16 | 2017-05-31 | 邵劭 | Ultra-high voltage transformer station comprehensive intelligent managing and control system based on three-dimensional live integration |
| CN109546749A (en) * | 2018-12-11 | 2019-03-29 | 北京安美智享科技有限公司 | One kind is for rail traction for electric substation's auxiliary monitoring system |
| CN110290350A (en) * | 2019-06-26 | 2019-09-27 | 广东康云科技有限公司 | A kind of real-time status monitoring method, system and the storage medium of crusing robot |
-
2020
- 2020-09-14 CN CN202010961269.1A patent/CN112288984A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2014139416A1 (en) * | 2013-03-11 | 2014-09-18 | 成都百威讯科技有限责任公司 | Emergent abnormal event intelligent identification alarm device and system |
| CN103488154A (en) * | 2013-10-09 | 2014-01-01 | 国家电网公司 | Remote comprehensive monitoring system for transformer substation operating environment and linkage control method thereof |
| CN104155959A (en) * | 2014-08-26 | 2014-11-19 | 国家电网公司 | Unattended comprehensive monitoring system for transformer substation |
| CN106787186A (en) * | 2016-12-16 | 2017-05-31 | 邵劭 | Ultra-high voltage transformer station comprehensive intelligent managing and control system based on three-dimensional live integration |
| CN109546749A (en) * | 2018-12-11 | 2019-03-29 | 北京安美智享科技有限公司 | One kind is for rail traction for electric substation's auxiliary monitoring system |
| CN110290350A (en) * | 2019-06-26 | 2019-09-27 | 广东康云科技有限公司 | A kind of real-time status monitoring method, system and the storage medium of crusing robot |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112927459A (en) * | 2021-03-09 | 2021-06-08 | 湖南农业大学 | Sudoku fire behavior prediction method based on unmanned aerial vehicle vision and application |
| CN113162229A (en) * | 2021-03-24 | 2021-07-23 | 北京潞电电气设备有限公司 | Monitoring device and method thereof |
| CN113259624A (en) * | 2021-03-24 | 2021-08-13 | 北京潞电电气设备有限公司 | Monitoring equipment and method thereof |
| CN113259625A (en) * | 2021-03-24 | 2021-08-13 | 北京潞电电气设备有限公司 | Monitoring system and method thereof |
| CN113112635A (en) * | 2021-04-12 | 2021-07-13 | 滁州博格韦尔电气有限公司 | Conventional inspection system for intelligent equipment |
| CN113724402A (en) * | 2021-11-02 | 2021-11-30 | 长沙能川信息科技有限公司 | Three-dimensional scene fusion method for transformer substation video |
| CN113724402B (en) * | 2021-11-02 | 2022-02-15 | 长沙能川信息科技有限公司 | Three-dimensional scene fusion method for transformer substation video |
| CN114023048A (en) * | 2021-11-27 | 2022-02-08 | 安徽博达项目管理咨询有限公司 | Engineering supervision system based on artificial intelligence data processing and visual analysis |
| CN114462536A (en) * | 2022-02-09 | 2022-05-10 | 国网宁夏电力有限公司吴忠供电公司 | Method and system for generating labeled data set in entity scene |
| CN114942740A (en) * | 2022-07-12 | 2022-08-26 | 江苏润和软件股份有限公司 | Transformer substation auxiliary equipment online real-time monitoring method and system based on artificial intelligence |
| CN114942740B (en) * | 2022-07-12 | 2022-10-21 | 江苏润和软件股份有限公司 | Transformer substation auxiliary equipment online real-time monitoring method and system based on artificial intelligence |
| CN115346303A (en) * | 2022-08-16 | 2022-11-15 | 河南金数网科信息技术有限公司 | Visual campus management system based on internet of things node and GIS |
| CN115695736A (en) * | 2022-12-14 | 2023-02-03 | 广东泰一高新技术发展有限公司 | Intelligent security command system and security command method based on three-dimensional model analysis |
| CN116612594A (en) * | 2023-05-11 | 2023-08-18 | 深圳市云之音科技有限公司 | Intelligent monitoring and outbound system and method based on big data |
| CN117647284A (en) * | 2024-01-29 | 2024-03-05 | 山东凯莱电气设备有限公司 | Monitoring and early warning system and method for electric automatic power distribution cabinet |
| CN117647284B (en) * | 2024-01-29 | 2024-04-16 | 山东凯莱电气设备有限公司 | Monitoring and early warning system and method for electric automatic power distribution cabinet |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112288984A (en) | Three-dimensional visual unattended substation intelligent linkage system based on video fusion | |
| KR101949525B1 (en) | Safety management system using unmanned detector | |
| CN111770266B (en) | Intelligent visual perception system | |
| CN207301750U (en) | Power grid construction intelligence control platform system | |
| CN206894809U (en) | Electric power safety operation and O＆M intelligent monitoring system | |
| CN101388130B (en) | Multi-grade stereo anti-intruding system, apparatus and implementing method based on wireless sensing net | |
| CN104581087B (en) | A kind of power transmission line intelligent remote monitoring system based on Internet of Things | |
| US20090122144A1 (en) | Method for detecting events at a secured location | |
| KR102554662B1 (en) | Safety management system using unmanned detector | |
| CN204129891U (en) | A kind of high ferro anti-intrusion system along the line | |
| CN205862512U (en) | Household security system based on Internet of Things | |
| CN105607617A (en) | Security fault diagnosis system and method based on Internet of Things | |
| CN106003040A (en) | Transformer substation inspection robot system with obstacle avoidance function | |
| CN104454011A (en) | Coal face rock burst alarming method based on images | |
| CN210222962U (en) | Intelligent electronic fence system | |
| CN104454012A (en) | Coal mine driving face rock burst alarming method based on images | |
| CN116165981A (en) | Intelligent monitoring system for industrial industry safety production | |
| CN112634579A (en) | Transformer substation security early warning linkage system | |
| CN112671104A (en) | Transformer substation multidimensional scene control platform facing complex scene | |
| CN112634562A (en) | Intelligent electric power security system | |
| KR101005568B1 (en) | Intelligent security system | |
| CN203135930U (en) | Substation double-vision on-line monitoring intelligent early-warning system | |
| CN211630273U (en) | Intelligent image recognition device for railway environment | |
| CN203206397U (en) | Remote visual integrated monitoring system for power distribution network | |
| CN112583769A (en) | Operation monitoring system of station |
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 |