CN112686399B - Distribution room fire emergency repair method and system based on augmented reality technology - Google Patents
Distribution room fire emergency repair method and system based on augmented reality technology Download PDFInfo
- Publication number
- CN112686399B CN112686399B CN202011551082.0A CN202011551082A CN112686399B CN 112686399 B CN112686399 B CN 112686399B CN 202011551082 A CN202011551082 A CN 202011551082A CN 112686399 B CN112686399 B CN 112686399B
- Authority
- CN
- China
- Prior art keywords
- information
- equipment
- fire
- scene
- module
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000008439 repair process Effects 0.000 title claims abstract description 116
- 230000003190 augmentative effect Effects 0.000 title claims abstract description 42
- 238000005516 engineering process Methods 0.000 title claims abstract description 36
- 238000000034 method Methods 0.000 title claims abstract description 30
- 230000004044 response Effects 0.000 claims abstract description 10
- 238000011156 evaluation Methods 0.000 claims description 58
- 230000008447 perception Effects 0.000 claims description 41
- 230000007246 mechanism Effects 0.000 claims description 29
- 238000012545 processing Methods 0.000 claims description 25
- 230000003993 interaction Effects 0.000 claims description 21
- 239000007789 gas Substances 0.000 claims description 18
- 238000002955 isolation Methods 0.000 claims description 14
- 230000007480 spreading Effects 0.000 claims description 11
- 230000002159 abnormal effect Effects 0.000 claims description 9
- 238000001914 filtration Methods 0.000 claims description 6
- 238000007499 fusion processing Methods 0.000 claims description 6
- 239000000203 mixture Substances 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000002485 combustion reaction Methods 0.000 claims description 3
- 238000004880 explosion Methods 0.000 claims description 3
- 239000002360 explosive Substances 0.000 claims description 3
- 239000010410 layer Substances 0.000 description 10
- 238000010438 heat treatment Methods 0.000 description 6
- 238000011160 research Methods 0.000 description 3
- 206010000369 Accident Diseases 0.000 description 1
- 241000282414 Homo sapiens Species 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000002355 dual-layer Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000012854 evaluation process Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000009413 insulation Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 239000000779 smoke Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Landscapes
- Alarm Systems (AREA)
Abstract
The utility model provides a method and a system for emergency repair of a fire disaster in a distribution room based on augmented reality technology, which is based on a mixed augmented virtual scene, combines the current operation state of equipment in an emergency place and on-site real-time data acquired by an emergency robot, can clearly control the layer and the association among the equipment under the condition of fire danger, judges the cause and the influence of the occurrence of the current danger by comparing the operation history data of the equipment in the scene, gives an emergency rescue strategy and a prompt according to the rescue knowledge in a system library, provides guidance for the emergency rescue operation, and realizes the rapid emergency repair response of the emergency accident under the accident environment of the power equipment.
Description
Technical Field
The invention relates to the technical field of electric power safety, in particular to a distribution room fire emergency repair method and system based on an augmented reality technology.
Background
The scene that needs emergency rescue such as fire protection, flood and abnormal gas generation exists on the electric power equipment site, wherein the high temperature generated by the electric power failure emergency site fire disaster, hidden high temperature points caused by equipment insulation breakdown, and dangerous factors such as dense smoke, barriers and the like affecting the sight can bring great risk hidden trouble to the safety of the mobile operation terminal for executing the work task on site. Meanwhile, the power equipment has a plurality of field devices and a complex structure, and the power grid equipment is managed by adopting a form and a common database based on a manual basis, so that the difficulties of unclear hierarchy, complex association and the like among the power equipment are faced.
Disclosure of Invention
The invention aims to provide a distribution room fire emergency repair method and system based on an augmented reality technology, which are used for collecting, analyzing and deciding related information of sudden fire danger of a distribution room based on the augmented reality technology, and providing a strategy for providing operation guidance for emergency rescue.
In order to achieve the above purpose, the invention provides a distribution room fire emergency repair system based on augmented reality technology, comprising: the system comprises a scene perception module, a scene history information module, a data processing module, a target evaluation decision module, an alarm module, an enhanced information display module and an interaction module;
the scene perception module acquires scene perception information in real time based on a mixed augmented reality technology;
The scene history information module comprises a virtual model of scene equipment;
The data processing module carries out filtering processing and information fusion processing on the scene perception information acquired by the scene perception module, and provides an evaluation basis for the target evaluation decision module;
the target evaluation decision module introduces an attention mechanism model according to the result obtained by the data processing module to evaluate the fire hazard target and decide the prior rush repair equipment;
the alarm module carries out emergency repair alarm according to the decision result of the target evaluation decision module;
the augmented information display module superimposes abnormal equipment in a real scene and a virtual model in the scene history information module based on a mixed augmented reality technology, and performs equipment attribute information augmented display;
And the interaction module combines the scene history information module and the enhanced information display module to perform scene superposition and display, so as to complete the rush repair interaction of the abnormal equipment.
The scene history information module comprises three-dimensional model information, operation parameter information and equipment attribute information of scene equipment;
The three-dimensional model information at least comprises: inlet wire cabinet, outlet wire cabinet, metering cabinet, PT cabinet, contact cabinet and isolation cabinet;
the operation parameter information at least comprises: planning the geographical position and the rush repair path of the equipment;
the device attribute information includes at least: equipment name, rush repair level, equipment role, main composition, service life, equipment price.
The invention also provides a distribution room fire emergency repair method based on the augmented reality technology, which comprises the following steps:
step S1, a scene perception module acquires scene perception information in real time based on a mixed augmented reality technology;
s2, the data processing module carries out filtering processing and information fusion processing according to the scene perception information acquired by the scene perception module, and sends the processed data to the target evaluation decision module;
s3, a target evaluation decision module introduces a attention mechanism model according to the result obtained by the data processing module to evaluate a fire hazard target and decide out a priority rush repair device;
S4, when a fire condition occurs, the alarm module carries out emergency repair alarm according to the decision result of the target evaluation decision module;
And S5, combining the scene history information module and the enhanced information display module by the interaction module to perform scene superposition and display, and completing the rush repair interaction of the abnormal equipment.
The scene perception information at least comprises: temperature information, humidity information, harmful gas information, image and video information;
The scene sensing module acquires scene local temperature information in real time through a temperature sensor of the scene emergency robot; the scene sensing module acquires scene local humidity information in real time through a humidity sensor of the scene emergency robot; the scene perception module acquires scene local harmful gas information in real time through a gas sensor of the scene emergency robot; and the scene perception module acquires scene images and video information in real time through the in-site camera.
The fire hazard target evaluation comprises: evaluating fire severity, evaluating fire spread trend, and evaluating surrounding equipment impact;
The method for evaluating fire severity comprises the following steps: fire severity level is determined from the area of the fire, the height of the flame, and the location of the source of the fire by analyzing the source of the fire image, the scene image of the electrical room, the temperature, and the harmful gases: casualties occur, and/or explosions occur to a high level; equipment is scrapped and/or large-scale power failure is high-grade; small-scale power outages, and/or component damage to a medium level; the part is damaged to a low level; only alarms, and/or local bursts are low-level;
the method for evaluating the fire spread trend comprises the following steps: the fire spread trend grade is determined by analyzing the fire source image, the scene image of the distribution room and the temperature and by the distance between the fire source position and equipment around the fire source: the fire source is high-grade near the inflammable and explosive object; the equipment around the fire source is safe and controllable, and/or the distance is moderate; the fire sources are relatively independent and/or are not easy to cause other combustion to be low-grade;
The method for evaluating the influence of surrounding equipment comprises the following steps: determining equipment rush-repair grades according to equipment attributes, equipment faults and fire source positions: the high-voltage wire inlet cabinet and the high-voltage wire outlet cabinet are of grade A; the metering cabinet and the PT cabinet are of class B; the contact cabinet and the isolation cabinet are of grade C; the low-voltage wire inlet cabinet, the low-voltage wire outlet cabinet and the equipment at the rear side are of grade D.
The target evaluation decision module utilizes a double-layer attention mechanism to evaluate fire hazard targets and decides out priority rush repair equipment, and the method comprises the following steps:
Taking scene perception information as input information, and calculating to obtain fire severity level, fire spreading trend level and equipment rush-repair level through a first layer of attention mechanism network;
and taking the disaster severity level, the fire spreading trend level and the equipment rush-repair level as input information, and calculating through a second-layer attention mechanism network to obtain a rush-repair equipment target.
The attention mechanism network computing method comprises the following steps:
The attention profile α i is calculated using a scaled dot product model:
Wherein X i is input information, when calculating fire severity level, the input information at least comprises flame coverage area, flame height, flame temperature and harmful gas content, when calculating fire spreading trend level, the input information at least comprises flame coverage area, flame height, flame temperature and flame source position and equipment distance around the flame source, when calculating equipment rush-repair level, the input information at least comprises equipment attribute, equipment fault and flame source position, when calculating rush-repair equipment target, the input information comprises disaster severity level, fire spreading trend level and equipment rush-repair level; q is a key value corresponding to input information X i; d is the dimension of the input information X i;
After the attention distribution α i is obtained, the input information X i is encoded by adopting a soft attention mechanism, so as to obtain an evaluation result C 1:
the method for alarming the emergency repair by the alarm module comprises the following steps:
When the equipment first-aid repair grade A appears, the power supply office dispatch telephone should be immediately dialed to request the quick and urgent power-off operation of the outside line, and the current accident situation is notified at the same time, so that the response time of the opposite party is improved, the opposite party cannot be put out for rescue near a fire disaster point, and the power supply office dispatch room can take the first-aid repair and put out for rescue after power failure;
when the B level of the equipment is in emergency repair, the power supply of the high-voltage incoming line cabinet is cut off immediately, a power supply bureau dispatch telephone is dialed, the quick and emergency power-off operation of the external line is requested, and the current accident situation is informed at the same time, so that the response time of the other party is improved;
when the equipment rush-repair grade C appears, the power supply of the upper-level high-voltage switch cabinet should be immediately cut off;
When the level D of the equipment is in emergency repair, the power supply of the upper-level low-voltage switch cabinet and the corresponding high-voltage switch cabinet should be immediately cut off.
The method for carrying out the rush repair interaction by the interaction module comprises the following steps:
According to the equipment rush-repair grade obtained by the target evaluation decision-making module, selecting rush-repair equipment;
according to the selected rush-repair equipment, obtaining operation parameter information in a scene history information module, and guiding the robot to reach a destination;
the enhancement information display module performs model and information superposition according to the corresponding rush repair equipment;
and sending an instruction to command the robot to perform rush repair operation according to the prompt of the enhanced information content of the enhanced information display module.
The invention has the following advantages: based on the hybrid enhanced virtual scene, the device running state of the current emergency place and the field real-time data acquired by the emergency robot are combined, the layer and the association among devices can be clear under the condition of fire danger, the reasons and the influences of the current danger are judged by reasoning through comparing the device running history data of the scene, an emergency rescue strategy and prompts are given according to the rescue knowledge in a system library, guidance is provided for emergency rescue operation, and quick rescue response of emergency accidents under the accident environment of the power equipment is realized.
Drawings
Fig. 1 is a schematic diagram of a fire emergency repair system for a distribution room based on an augmented reality technology in an embodiment of the invention.
Detailed Description
The following describes a preferred embodiment of the present invention in detail with reference to fig. 1.
The mixed augmented reality technology is utilized to manage the power equipment, and the panoramic display of the emergency rescue scene power equipment can be realized based on the synchronous positioning and map building (SLAM) technology. According to specific state information, inherent information and position information of different electric power equipment, a virtual model is directly overlapped on corresponding real electric power equipment through a mixed augmented reality technology, so that the spatial position relation and the electric power connection relation of equipment objects can be fully reflected, and further, an inspection personnel can remotely guide the operation of a robot to realize quick emergency repair response of emergency accidents under the accident environment of the electric power equipment.
At present, the research on a power distribution room fire emergency repair strategy method based on an augmented reality technology is less, the augmented reality display technology is mostly researched, and how the augmented reality technology provides guidance help for power emergency repair operation is seldom considered (how to clear the conditions of hierarchy, association and the like among devices under the condition of fire danger through a superposition device virtual model, and instruct a robot to carry out simple operations such as disconnection and the like on the devices according to the corresponding repair strategy). However, the research of the emergency repair strategy method of the power distribution station based on the augmented reality technology not only relates to the problems of scene perception, data processing, enhanced information display technology and the like, but also adopts a attention mechanism to carry out a target evaluation process and an interactive part emergency repair strategy model, so that the comprehensive consideration of the research literature of the part is less.
In summary, it is necessary to invent a power distribution room fire emergency repair strategy method based on augmented reality technology to solve the problem of rapid emergency repair response of emergency accidents in the fire accident environment of power distribution room equipment.
The invention provides a distribution room fire emergency repair system based on an augmented reality technology, which comprises: the system comprises a scene sensing module, a scene history information module, a data processing module, a target evaluation decision module, an alarm module, an enhanced information display module and an interaction module, wherein the scene sensing module is used for acquiring scene sensing information in real time by an emergency robot with a sensing sensor and a scene camera based on a mixed augmented reality technology; the scene history information module comprises three-dimensional model information, operation parameter information and attribute information of scene equipment; the data processing module carries out filtering processing and information fusion processing on the data information acquired by the scene perception module and provides an evaluation basis for the target evaluation decision module; the target evaluation decision module introduces an attention mechanism model according to the result obtained by the data processing module to evaluate the fire hazard target and decide the prior rush repair equipment; the alarm module carries out emergency repair alarm according to the result of the target evaluation decision module; the augmented information display module is used for carrying out virtual model superposition in the scene history information module on abnormal equipment in a real scene based on a mixed augmented reality technology and carrying out equipment attribute information augmented display; the interaction module is used for switching the system into an emergency repair mode, and a worker orders the robot according to the system prompt, and performs scene superposition and display to complete the emergency repair interaction by combining the scene history information module and the enhanced information display module.
Further, the scene perception module acquires scene images and video information in real time through a camera sensor of the scene emergency robot; the scene sensing module acquires scene local temperature information in real time through a temperature sensor of the scene emergency robot; the scene sensing module acquires scene local humidity information in real time through a humidity sensor of the scene emergency robot; the scene perception module acquires scene local harmful gas information in real time through a gas sensor of the scene emergency robot; and the scene perception module acquires scene images and video information in real time through the in-site camera.
The scene history information module comprises three-dimensional model information, operation parameter information and attribute information of scene equipment. The three-dimensional model information includes: model information of the incoming line cabinet, the outgoing line cabinet, the metering cabinet, the PT cabinet, the connecting cabinet and the isolation cabinet; the operation parameter information includes: planning information of equipment geographical position and rush repair path; the device attribute information includes: equipment name, rush repair level, equipment action, main composition, service life and equipment price attribute information.
The attention mechanism introduced by the target evaluation decision module essentially references the selective visual attention mechanism of human beings, so that the target selection of the current task is focused on a certain degree by selecting the more critical index from a plurality of evaluation indexes.
The fire hazard target evaluation mainly surrounds the fire severity, the fire spread trend and the surrounding equipment influence evaluation. The fire severity level is determined by analyzing data such as fire source images, distribution room scene images, temperatures, harmful gases and the like, and determining fire severity level according to the fire passing area, the fire height, the fire source position and the like; the fire spreading trend is analyzed by data such as a fire source image, a distribution room scene image, temperature and the like, and the fire spreading trend grade is determined by the distance between the position of the fire source and equipment around the fire source; the surrounding equipment influences the equipment rush repair grade determined according to equipment attributes, equipment faults, fire source positions and the like.
The target evaluation decision module of the attention introducing mechanism model utilizes a double-layer attention mechanism: firstly, obtaining fire disaster severity level, fire disaster spread trend level and equipment first-aid repair level from perception information data through a first-layer attention mechanism network; secondly, the fire disaster severity, the fire disaster spreading trend and the surrounding equipment influence evaluation result are obtained through a second-layer attention mechanism network to obtain a first-aid repair equipment target.
The fire severity results in the target evaluation decision module are classified into five levels of high, medium, low and low; the fire spread trend results in the target evaluation decision module are classified into three grades, namely high, medium and low; and the device rush repair grade result in the target evaluation decision module is divided into A, B, C, D grades.
As shown in fig. 1, in one embodiment of the present invention, a power distribution room fire emergency repair method based on augmented reality technology is provided, which includes the following steps:
Step S1, a scene perception module 1 acquires images and video information acquired by a camera and key information such as temperature, humidity and harmful gas generated in a fire disaster scene through a scene camera and a perception sensor carried by an emergency robot, wherein the scene perception module comprises a camera ZED2 binocular stereo camera (sensors: an accelerometer, a gyroscope, a sunny rain gauge and a magnetometer), a temperature sensor, a humidity sensor and a gas sensor.
And step S2, the data processing module 3 performs filtering processing and information fusion processing according to the information acquired by the scene perception module 1, and provides data information basis for the target evaluation decision module 4.
And S3, introducing a attention mechanism model according to the result obtained by the data processing module by the target evaluation decision module 4, and evaluating a fire hazard target to decide out the priority repair equipment.
The fire hazard target evaluation mainly surrounds fire severity, fire spread trend and surrounding equipment influence evaluation;
Assessing fire severity comprises: fire severity levels (divided into five levels of high, medium, low and low) are determined from the area of the overfire, the height of the flame, the location of the flame, etc. by analyzing data of the fire source image, the scene image of the distribution room, the temperature, the harmful gas, etc.: the occurrence of casualties, explosion and the like are high-grade, equipment rejection, large-range power failure and the like are high-grade, small-range power failure, part damage and the like are medium-grade, part damage and the like are low-grade, and only alarms and local bursts are low-grade;
Assessing the trend of fire spread includes: through analyzing data such as a fire source image, a distribution room scene image, temperature and the like, fire spread trend grades (comprising high, medium and low grades) are determined according to the distances between the positions of the fire sources and equipment around the fire sources: the fire source is close to objects such as inflammable and explosive objects and the like, the equipment around the fire source is safe and controllable, the distance is proper and the like, the fire source is relatively independent, other combustion is not easy to cause and the like, and the fire source is low;
assessing the surrounding device impact includes: determining equipment rush-repair grades (which are A, B, C, D grades) according to equipment attributes, equipment faults, fire source positions and the like: the key equipment such as a high-voltage wire inlet cabinet, a high-voltage wire outlet cabinet and the like is A grade, the equipment such as a metering cabinet, a PT cabinet and the like is B grade, the equipment such as a contact cabinet, an isolation cabinet and the like is C grade, and the equipment such as a low-voltage wire inlet cabinet, a low-voltage wire outlet cabinet and the equipment at the rear side are D grade;
In this embodiment, the objective evaluation decision module performs fire hazard objective evaluation by using a dual-layer attention mechanism, and decides out the priority rush repair device. Firstly, calculating perception information data through a first-layer attention mechanism network to obtain fire severity level, fire spread trend level and equipment first-aid repair level; and secondly, calculating the fire severity, the fire spreading trend and the influence evaluation results of surrounding equipment through a second-layer attention mechanism network to obtain a first-aid repair equipment target.
The method comprises the following specific steps:
1. firstly, judging whether the obtained original perception information data has a data missing problem or not: when the original perception information data does not have the problem of missing, the original perception information data is used as complete perception information data for preprocessing operation; if the missing problem exists, the missing data are complemented according to the average value of the adjacent data in the fixed range;
2. Aiming at the evaluation data of fire severity, fire spread trend and influence of surrounding equipment, the evaluation result is obtained by using an attention mechanism based on the corresponding basic data;
Assessment of fire severity: taking corresponding sequence information such as flame coverage area, flame height, flame temperature, harmful gas content and the like as input information X i, and calculating attention distribution alpha i by using a scaling dot product model;
Assessment of the trend of fire spread: using corresponding sequence information such as flame coverage area, flame height, flame temperature, flame source position, flame source surrounding equipment distance and the like as input information X i, and calculating attention distribution alpha i by using a scaling dot product model;
Evaluation equipment rush repair grade: using corresponding sequence information such as equipment attribute, equipment fault, fire source position and the like as input information X i, and calculating attention distribution alpha i by using a scaling dot product model;
Wherein the model parameter q is a key value corresponding to the input information X i, and d is a dimension of the input information X i.
After the attention distribution alpha i corresponding to the basic sequence information is obtained, the input information X is encoded by adopting a soft attention mechanism, and an evaluation result C 1 is obtained:
3. After the fire severity, the fire spreading trend and the surrounding equipment influence evaluation results are obtained, the attention distribution of the respective evaluation results is obtained by using a second-layer attention network according to the same principle, and the final calculation result is obtained by using a soft attention mechanism, so that the prior repair equipment is decided.
And S4, when a fire occurs, the alarm module 5 judges whether the safety range is exceeded according to the result of the target evaluation decision module 4, carries out emergency repair alarm, and takes different measures according to the emergency repair grades of different equipment.
When the equipment first-aid repair A class appears, the power supply office dispatch telephone should be immediately dialed to request the quick and urgent power-off operation of the external line, and the current accident situation is informed at the same time, so that the response time of the other party is improved. The fire disaster can not be extinguished near the fire disaster, and the emergency repair and the rescue can be carried out after the power supply bureau dispatch room fails. And according to the field situation, the emergency robot or the emergency repair personnel take corresponding measures according to the evaluation situation.
When the B-level equipment is in emergency repair, the power supply of the high-voltage incoming line cabinet is immediately cut off, a power supply bureau dispatch telephone is dialed, the quick and emergency power-off operation of the external line is requested, and the current accident situation is informed at the same time, so that the response time of the other party is improved. And according to the field situation, the emergency robot or the emergency repair personnel take corresponding measures according to the evaluation situation.
When the equipment is in the class C of rush repair, the power supply of the upper high-voltage switch cabinet is cut off immediately, and an emergency robot or a rush repair person takes corresponding measures according to the field condition and the evaluation condition.
When the level D of the equipment is in emergency repair, the power supply of the upper-level low-voltage switch cabinet and the corresponding high-voltage switch cabinet should be immediately cut off, and corresponding measures are taken by emergency robots or emergency repair personnel according to the field conditions and the evaluation conditions.
S5, switching the system into an emergency repair mode, and combining the scene history information module and the enhanced information display module by the interaction module 7 to perform scene superposition and display to complete emergency repair interaction, wherein the specific steps are as follows:
(1) According to the equipment rush-repair grade obtained by the target evaluation decision-making module 4, selecting to perform rush-repair equipment;
(2) According to the selection of the rush repair equipment, the operation parameter information in the scene history information module 2 is obtained, and the robot is guided to reach the destination;
(3) The enhanced information display module 6 performs model and information superposition according to the corresponding rush repair equipment;
(4) And according to the enhanced information content prompt of the enhanced information display module 6, sending an instruction to instruct the robot to carry out the rush repair operation.
The scene history information module 2 comprises three-dimensional model information (an incoming line cabinet, an outgoing line cabinet, a metering cabinet, a PT cabinet, a contact cabinet and an isolation cabinet) of scene equipment, operation parameter information (equipment geographic position and rush repair path planning) and attribute information (relevant information such as equipment name, rush repair grade, equipment effect, main composition, service life, equipment price and the like).
The enhanced information display module 6 is configured to perform virtual model superposition in the scene history information module 2 on the abnormal device in the real scene based on the mixed augmented reality technology, and perform enhanced display on the device attribute information, where the model and the information superposition specifically include:
The inlet wire cabinet stack information contains: the incoming line cabinet is a switch cabinet for introducing power from the outside, 10KV power is introduced from a power supply network, and electric energy is sent to the bus through the incoming line cabinet. The incoming line cabinet is composed of components such as a vacuum circuit breaker, an isolating switch, a current transformer, a lightning arrester, an electrified display, a voltage transformer and the like.
The outlet cabinet superposition information comprises: the outlet cabinet is a switch cabinet for distributing electric energy from a bus, distributes a main power supply to all the power utilization branch switches, and switches on and off branch power supplies for all the branch overcurrent overload protection boxes. The outlet cabinet mainly comprises a current transformer, an isolating switch, a circuit breaker, a disconnecting link, an electrified display and the like.
The measurement cabinet superposition information comprises: the metering cabinet is an electric energy metering device, and the electricity consumption of the load is reflected through devices such as a current transformer, a voltage transformer, an electric energy meter, a fuse, an electrified display and the like.
PT cabinet stack information contains: the PT cabinet is a voltage transformer cabinet and is directly arranged on a bus for detecting voltage, and the PT cabinet mainly comprises devices such as a voltage transformer, an isolating switch, a fuse, a lightning arrester and the like.
The contact cabinet superposition information comprises: the connecting cabinet is also called a bus sectional cabinet and is used for connecting equipment of two sections of buses. When two power supplies are powered on simultaneously, the contact cabinet is disconnected, when one power supply is powered off due to accident, the contact cabinet is automatically connected to ensure the power utilization of a user, and when the power is restored, the contact cabinet is automatically disconnected and is in a standby state. The contact cabinet is mainly composed of an isolating switch, a circuit breaker, a current transformer, an electrified display and the like.
The isolation cabinet superposition information comprises: the isolation cabinet is mainly used for isolating buses or powered equipment at two ends and power supply equipment, and provides visible endpoints for operators, so that overhaul and maintenance work are facilitated. The isolation cabinet mainly comprises a circuit breaker, an isolation switch, a grounding switch, a current transformer, a voltage transformer, a lightning arrester, an electrified display and the like.
In this embodiment, the first-aid repair interaction performed by the interaction module 7 specifically includes the following steps:
when emergency rescue hierarchical alarm occurs, the system is switched to an emergency rescue mode, and a prompt box is popped up: "equipment failure, please select rush repair equipment", select to rush repair equipment according to equipment rush repair priority:
Selecting a high-voltage wire inlet cabinet (same low-voltage wire inlet cabinet):
(1) Obtaining the position of the high-voltage wire inlet cabinet and path planning information according to the scene history information module, and guiding the robot to reach a destination through arrow navigation;
(2) After the robot reaches the destination, stopping moving, and popping up a prompt box by the system: whether to carry out a high-voltage incoming line cabinet model and enhancing information superposition. The superposition information is displayed according to the content of the enhancement information;
(3) After the superposition information is displayed, a system pops up a prompt box: "please send instruction to command robot to perform rush repair operation". The operation content comprises: the breaker is opened, the isolating switch is disconnected, and the lightning arrester is cut off;
(4) After the robot is operated, the robot stops moving, and pops up a prompt box: please wait for further rush repair by staff. The operation of staff can be divided into according to the fault type of the mutual inductor: heating the joint, screwing the terminal or shorting the terminal; fusing the fuse, replacing the fuse, and closing the breaker.
Selecting a high-voltage outlet cabinet (same low-voltage outlet cabinet):
(1) Obtaining the position of the high-voltage outlet cabinet and path planning information according to the scene history information module, and guiding the robot to reach a destination through arrow navigation;
(2) After the robot reaches the destination, stopping moving, and popping up a prompt box: whether to carry out high-voltage outlet cabinet model and enhancement information superposition, wherein the superposition information is according to the content of the enhancement information display module;
(3) After the superposition information is displayed, a system pops up a prompt box: "please send instruction to command robot to perform rush repair operation". The operation content comprises: the breaker is opened and the isolating switch is disconnected;
(4) After the robot is operated, the robot stops moving, and pops up a prompt box: please wait for further rush repair by staff. The operation of staff can be divided into according to the fault type of the mutual inductor: heating the joint, screwing the terminal or shorting the terminal; fusing the fuse, replacing the fuse, and closing the breaker.
Selecting a metering cabinet:
(1) Obtaining the position of the metering cabinet and path planning information according to the scene history information module, and guiding the robot to reach a destination through arrow navigation;
(2) After the robot reaches the destination, stopping moving, and popping up a prompt box: whether to carry out metering cabinet model and enhanced information superposition or not, and the superposition information is displayed according to the content of the enhanced information;
(3) After the superposition information is displayed, a system pops up a prompt box: "please send instruction to command robot to perform rush repair operation". The operation content comprises: the breaker is opened;
(4) After the robot is operated, the robot stops moving, and pops up a prompt box: please wait for further rush repair by staff. The operation of staff can be divided into according to the fault type of the mutual inductor: heating the joint, screwing the terminal or shorting the terminal; fusing the fuse, replacing the fuse, and closing the breaker.
Selecting a PT cabinet:
(1) Obtaining the position of the PT cabinet and path planning information according to the scene history information module, and guiding the robot to reach a destination through arrow navigation;
(2) After the robot reaches the destination, stopping moving, and popping up a prompt box: whether to carry out PT cabinet model and enhanced information superposition, the superposition information is displayed according to the content of the enhanced information;
(3) After the superposition information is displayed, a system pops up a prompt box: "please send instruction to command robot to perform rush repair operation". The operation content comprises: the breaker is opened, the isolating switch is disconnected, and the lightning arrester is cut off;
(4) After the robot is operated, the robot stops moving, and pops up a prompt box: please wait for further rush repair by staff. The operation of staff can be divided into according to the fault type of the mutual inductor: heating the joint, screwing the terminal or shorting the terminal; fusing the fuse, replacing the fuse, and closing the breaker. According to the fault types of the bus, the bus is divided into: reclosing to switch the standby bus to supply power; reclosing-fault element processing is not performed, and the circuit breaker is closed.
Selecting a contact cabinet:
(1) Obtaining the position of the contact cabinet and path planning information according to the scene history information module, and guiding the robot to reach a destination through arrow navigation;
(2) After the robot reaches the destination, stopping moving, and popping up a prompt box: whether to carry out the contact cabinet model and the enhancement information superposition, the superposition information is according to the content of the enhancement information display module;
(3) After the superposition information is displayed, a system pops up a prompt box: "please send instruction to command robot to perform rush repair operation". The operation content comprises: the breaker is opened and the isolating switch is disconnected;
(4) After the robot is operated, the robot stops moving, and pops up a prompt box: please wait for further rush repair by staff. The operation of staff can be divided into according to the fault type of the mutual inductor: heating the joint, screwing the terminal or shorting the terminal; fusing the fuse, replacing the fuse, and closing the breaker. According to the fault types of the bus, the bus is divided into: reclosing to switch the standby bus to supply power; reclosing-fault element processing is not performed, and the circuit breaker is closed.
Selecting an isolation cabinet:
(1) Obtaining the position of the isolation cabinet and path planning information according to the scene history information module, and guiding the robot to reach a destination through arrow navigation;
(2) After the robot reaches the destination, stopping moving, and popping up a prompt box: whether to carry out the isolation cabinet model and the enhancement information superposition or not, and the superposition information is displayed according to the content of the enhancement information;
(3) After the superposition information is displayed, a system pops up a prompt box: "please send instruction to command robot to perform rush repair operation". The operation content comprises: the breaker is opened, the isolating switch is disconnected, the lightning arrester is cut off, and the grounding switch is disconnected;
(4) After the robot is operated, the robot stops moving, and pops up a prompt box: please wait for further rush repair by staff. The operation of staff can be divided into according to the fault type of the mutual inductor: heating the joint, screwing the terminal or shorting the terminal; fusing the fuse, replacing the fuse, and closing the breaker. According to the fault types of the bus, the bus is divided into: reclosing to switch the standby bus to supply power; reclosing-fault element processing is not performed, and the circuit breaker is closed.
After the emergency repair operation is finished, referring to the fire source cause evaluation, the scene is checked, other fire hazards are eliminated, omission is prevented, secondary accidents are caused, and the scene is protected, so that the accident cause is checked.
By the cooperative work among the modules, the invention judges the cause and influence of the current dangerous situation by comparing the operation history data of the scene equipment, gives out an emergency rescue strategy and prompt according to rescue knowledge in a system library, and provides guidance for emergency rescue operation.
It should be noted that, in the embodiments of the present invention, the directions or positional relationships indicated by the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. are based on the directions or positional relationships shown in the drawings, are merely for convenience of describing the embodiments, and do not indicate or imply that the devices or elements referred to must have a specific orientation, be configured and operated in a specific orientation, and thus should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
While the present invention has been described in detail through the foregoing description of the preferred embodiment, it should be understood that the foregoing description is not to be considered as limiting the invention. Many modifications and substitutions of the present invention will become apparent to those of ordinary skill in the art upon reading the foregoing. Accordingly, the scope of the invention should be limited only by the attached claims.
Claims (7)
1. Distribution room fire emergency repair system based on augmented reality technique, characterized by comprising: the system comprises a scene perception module, a scene history information module, a data processing module, a target evaluation decision module, an alarm module, an enhanced information display module and an interaction module;
the scene perception module acquires scene perception information in real time based on a mixed augmented reality technology;
The scene history information module comprises a virtual model of scene equipment;
The data processing module carries out filtering processing and information fusion processing on the scene perception information acquired by the scene perception module, and provides an evaluation basis for the target evaluation decision module;
the target evaluation decision module introduces an attention mechanism model according to the result obtained by the data processing module to evaluate the fire hazard target and decide the prior rush repair equipment;
the alarm module carries out emergency repair alarm according to the decision result of the target evaluation decision module;
the augmented information display module superimposes abnormal equipment in a real scene and a virtual model in the scene history information module based on a mixed augmented reality technology, and performs equipment attribute information augmented display;
The interaction module combines the scene history information module and the enhanced information display module to perform scene superposition and display, and completes the rush repair interaction of the abnormal equipment;
the target evaluation decision module utilizes a double-layer attention mechanism to evaluate fire hazard targets and decides out priority rush repair equipment, and the method comprises the following steps:
Taking scene perception information as input information, and calculating to obtain fire severity level, fire spreading trend level and equipment rush-repair level through a first layer of attention mechanism network;
Taking the disaster severity level, the fire spreading trend level and the equipment rush-repair level as input information, and calculating through a second-layer attention mechanism network to obtain a rush-repair equipment target;
the attention mechanism network computing method comprises the following steps:
computing attention distribution using scaled dot product model ：
Wherein,The fire disaster emergency repair method comprises the steps that input information is used for calculating a fire disaster severity level, wherein the input information at least comprises a flame coverage area, a flame height, a flame temperature and harmful gas content, when the fire disaster emergency trend level is calculated, the input information at least comprises the flame coverage area, the flame height, the flame temperature, a flame source position and a device distance around the flame source, when the device emergency repair level is calculated, the input information at least comprises a device attribute, a device fault and a flame source position, and when the emergency repair device target is calculated, the input information comprises the fire disaster severity level, the fire disaster emergency trend level and the device emergency repair level; To input information The corresponding key value; To input information Is a dimension of (2);
obtaining the attention distribution Then, the soft attention mechanism is adopted for inputting informationCoding to obtain evaluation result：
。
2. The augmented reality technology-based power distribution room fire emergency repair system according to claim 1, wherein the scene history information module comprises three-dimensional model information, operation parameter information and equipment attribute information of scene equipment;
The three-dimensional model information at least comprises: inlet wire cabinet, outlet wire cabinet, metering cabinet, PT cabinet, contact cabinet and isolation cabinet;
the operation parameter information at least comprises: planning the geographical position and the rush repair path of the equipment;
the device attribute information includes at least: equipment name, rush repair level, equipment role, main composition, service life, equipment price.
3. An augmented reality technology-based power distribution room fire emergency repair method implemented by using the augmented reality technology-based power distribution room fire emergency repair system as claimed in claim 1 or 2, comprising the following steps:
step S1, a scene perception module acquires scene perception information in real time based on a mixed augmented reality technology;
s2, the data processing module carries out filtering processing and information fusion processing according to the scene perception information acquired by the scene perception module, and sends the processed data to the target evaluation decision module;
s3, a target evaluation decision module introduces a attention mechanism model according to the result obtained by the data processing module to evaluate a fire hazard target and decide out a priority rush repair device;
S4, when a fire condition occurs, the alarm module carries out emergency repair alarm according to the decision result of the target evaluation decision module;
And S5, combining the scene history information module and the enhanced information display module by the interaction module to perform scene superposition and display, and completing the rush repair interaction of the abnormal equipment.
4. The augmented reality technology-based power distribution room fire emergency repair method according to claim 3, wherein the scene perception information at least comprises: temperature information, humidity information, harmful gas information, image and video information;
The scene sensing module acquires scene local temperature information in real time through a temperature sensor of the scene emergency robot; the scene sensing module acquires scene local humidity information in real time through a humidity sensor of the scene emergency robot; the scene perception module acquires scene local harmful gas information in real time through a gas sensor of the scene emergency robot; and the scene perception module acquires scene images and video information in real time through the in-site camera.
5. The augmented reality technology-based power distribution room fire emergency repair method of claim 4, wherein the fire hazard target evaluation comprises: evaluating fire severity, evaluating fire spread trend, and evaluating surrounding equipment impact;
The method for evaluating fire severity comprises the following steps: fire severity level is determined from the area of the fire, the height of the flame, and the location of the source of the fire by analyzing the source of the fire image, the scene image of the electrical room, the temperature, and the harmful gases: casualties occur, and/or explosions occur to a high level; equipment is scrapped and/or large-scale power failure is high-grade; small-scale power outages, and/or component damage to a medium level; the part is damaged to a low level; only alarms, and/or local bursts are low-level;
the method for evaluating the fire spread trend comprises the following steps: the fire spread trend grade is determined by analyzing the fire source image, the scene image of the distribution room and the temperature and by the distance between the fire source position and equipment around the fire source: the fire source is high-grade near the inflammable and explosive object; the equipment around the fire source is safe and controllable, and/or the distance is moderate; the fire sources are relatively independent and/or are not easy to cause other combustion to be low-grade;
The method for evaluating the influence of surrounding equipment comprises the following steps: determining equipment rush-repair grades according to equipment attributes, equipment faults and fire source positions: the high-voltage wire inlet cabinet and the high-voltage wire outlet cabinet are of grade A; the metering cabinet and the PT cabinet are of class B; the contact cabinet and the isolation cabinet are of grade C; the low-voltage wire inlet cabinet, the low-voltage wire outlet cabinet and the equipment at the rear side are of grade D.
6. The augmented reality technology-based power distribution room fire emergency repair method according to claim 5, wherein the method for performing emergency repair alarm by the alarm module comprises the following steps:
When the equipment first-aid repair grade A appears, the power supply office dispatch telephone should be immediately dialed to request the quick and urgent power-off operation of the outside line, and the current accident situation is notified at the same time, so that the response time of the opposite party is improved, the opposite party cannot be put out for rescue near a fire disaster point, and the power supply office dispatch room can take the first-aid repair and put out for rescue after power failure;
when the B level of the equipment is in emergency repair, the power supply of the high-voltage incoming line cabinet is cut off immediately, a power supply bureau dispatch telephone is dialed, the quick and emergency power-off operation of the external line is requested, and the current accident situation is informed at the same time, so that the response time of the other party is improved;
when the equipment rush-repair grade C appears, the power supply of the upper-level high-voltage switch cabinet should be immediately cut off;
When the level D of the equipment is in emergency repair, the power supply of the upper-level low-voltage switch cabinet and the corresponding high-voltage switch cabinet should be immediately cut off.
7. The augmented reality technology-based power distribution room fire emergency repair method according to claim 6, wherein the method for performing emergency repair interaction by the interaction module comprises the following steps:
According to the equipment rush-repair grade obtained by the target evaluation decision-making module, selecting rush-repair equipment;
according to the selected rush-repair equipment, obtaining operation parameter information in a scene history information module, and guiding the robot to reach a destination;
the enhancement information display module performs model and information superposition according to the corresponding rush repair equipment;
and sending an instruction to command the robot to perform rush repair operation according to the prompt of the enhanced information content of the enhanced information display module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011551082.0A CN112686399B (en) | 2020-12-24 | 2020-12-24 | Distribution room fire emergency repair method and system based on augmented reality technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011551082.0A CN112686399B (en) | 2020-12-24 | 2020-12-24 | Distribution room fire emergency repair method and system based on augmented reality technology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112686399A CN112686399A (en) | 2021-04-20 |
| CN112686399B true CN112686399B (en) | 2024-07-05 |
Family
ID=75452577
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011551082.0A Active CN112686399B (en) | 2020-12-24 | 2020-12-24 | Distribution room fire emergency repair method and system based on augmented reality technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112686399B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113421356B (en) * | 2021-07-01 | 2023-05-12 | 北京华信傲天网络技术有限公司 | Inspection system and method for equipment in complex environment |
| CN113591803A (en) * | 2021-09-14 | 2021-11-02 | 广州健新科技有限责任公司 | Intelligent remote inspection method and system for power distribution room based on edge cloud cooperation technology |
| CN114792194B (en) * | 2022-03-16 | 2023-04-18 | 深圳森磊弘泰消防科技有限公司 | Whole fire control safety intelligent system of building |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110311468A (en) * | 2019-06-26 | 2019-10-08 | 广东康云科技有限公司 | Substation's three-dimensional live abnormality monitoring method, system, device and storage medium |
| CN111815000A (en) * | 2020-07-10 | 2020-10-23 | 国网上海市电力公司 | Method and system for reproducing power scene and computer readable storage medium |
| CN111832924A (en) * | 2020-06-30 | 2020-10-27 | 北方工业大学 | Dynamic risk assessment method and device for community gas system based on graph neural network |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11227330B2 (en) * | 2010-09-03 | 2022-01-18 | Lee Martin Stewart | Determining a part having an anomaly in equipment and initiating an electronic transaction for replacing the part using a three-dimensional (3D) model of the equipment |
| US9940823B2 (en) * | 2016-02-29 | 2018-04-10 | International Business Machines Corporation | System, method, and recording medium for emergency identification and management using smart devices and non-smart devices |
| CN105788390A (en) * | 2016-04-29 | 2016-07-20 | 吉林医药学院 | Medical anatomy auxiliary teaching system based on augmented reality |
| CN108090572B (en) * | 2017-12-01 | 2022-05-06 | 大唐国信滨海海上风力发电有限公司 | Control method of offshore wind farm augmented reality system |
| US10952058B2 (en) * | 2018-01-02 | 2021-03-16 | Titan Health & Security Technologies, Inc. | Systems and methods for providing augmented reality emergency response solutions |
| CN108161904B (en) * | 2018-01-09 | 2019-12-03 | 青岛理工大学 | Robot online teaching device, system, method and equipment based on augmented reality |
| CN110928418A (en) * | 2019-12-11 | 2020-03-27 | 北京航空航天大学 | Aviation cable auxiliary assembly method and system based on MR |
| CN111612671B (en) * | 2020-04-27 | 2023-11-07 | 深圳市城市公共安全技术研究院有限公司 | Emergency drilling system |
-
2020
- 2020-12-24 CN CN202011551082.0A patent/CN112686399B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110311468A (en) * | 2019-06-26 | 2019-10-08 | 广东康云科技有限公司 | Substation's three-dimensional live abnormality monitoring method, system, device and storage medium |
| CN111832924A (en) * | 2020-06-30 | 2020-10-27 | 北方工业大学 | Dynamic risk assessment method and device for community gas system based on graph neural network |
| CN111815000A (en) * | 2020-07-10 | 2020-10-23 | 国网上海市电力公司 | Method and system for reproducing power scene and computer readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112686399A (en) | 2021-04-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112686399B (en) | Distribution room fire emergency repair method and system based on augmented reality technology | |
| KR102145266B1 (en) | System and method for monitoring power system | |
| Nazaripouya | Power grid resilience under wildfire: A review on challenges and solutions | |
| CN113077161A (en) | Emergency repair decision method for emergency robot in power distribution room | |
| CN109546750A (en) | Substation's supplementary controlled system, method and device | |
| CN106530182A (en) | Protective method for electrical fire hazards based on three-proofing means | |
| CN114268167A (en) | Transformer substation system based on digital twinning technology | |
| Serrano et al. | Fighting against wildfires in power systems: Lessons and resilient practices from the chilean and brazilian experiences | |
| Shahinzadeh et al. | An agile black-out detection and response paradigm in smart grids incorporating iot-oriented initiatives and fog-computing platform | |
| CN106525123A (en) | Electrical fire-fighting safety detection method | |
| CN112701786B (en) | 220kV and below electric voltage class skid-mounted electronic control integrated transformer substation | |
| KR102579941B1 (en) | Incoming panels for power facility protection that can detect and block phase loss remotely using a smart wave power remote controller | |
| CN108279360A (en) | Singlephase earth fault circuit monitoring system | |
| CN114725545A (en) | Container type energy storage system with active/passive intelligent safety protection | |
| CN113990132A (en) | Power transformation and distribution operation and maintenance integrated practical training system and practical training method | |
| JP2015055592A (en) | Automatic insulation resistance measurement system | |
| CN219304181U (en) | New energy box-type transformer station | |
| CN219122770U (en) | Multistage auxiliary equipment linkage system of pumped storage power station based on linkage body | |
| Mustajärvi | Standard design criteria for electrical substations | |
| CN209389780U (en) | Substation's supplementary controlled system | |
| CN208939664U (en) | The monitoring of non-tune scope tube opposite side route earthing knife-switch and fool proof line protection system | |
| Zampell et al. | Safety Considerations While Working at a Private or Public Utility | |
| Cheng et al. | Research and application of Substation Fire Protection System based on big data | |
| Abumuaileq et al. | Study of Standard Grid Substation | |
| Liew | Electrical substation design and engineering |
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 |