Method for monitoring safe distance of transformer substation through laser point cloud and visible light image
By generating a virtual monitoring model of the substation using lidar and visible light cameras, the problems of uninterrupted monitoring of substation safety distances and environmental adaptability are solved, enabling real-time early warning and accurate acquisition of evacuation routes, thus improving the efficiency and reliability of substation safety management.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-12-04
- Publication Date
- 2026-03-13
AI Technical Summary
Existing technologies cannot achieve 24-hour uninterrupted monitoring of the safety distance of substations, and two-dimensional video images lack accurate spatial depth information, making it impossible to effectively measure distance and volume in harsh environments, resulting in regulatory blind spots and lag.
Data is collected using lidar and visible light cameras to generate fused data, constructing a virtual monitoring model of the substation. This model monitors and delineates safe distances and fire lanes in real time. Laser penetration imaging technology is used to obtain evacuation route information at the fire scene, detect personnel locations in real time, and provide evacuation guidance.
It enables real-time monitoring and early warning of substation safety distances, overcomes smoke obstruction at fire scenes, provides effective evacuation route information and personnel location detection, and improves the real-time performance and accuracy of substation safety management.
Smart Images
Figure CN121661807A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of substation safety distance monitoring technology, specifically a method for monitoring substation safety distances using laser point clouds and visible light images. Background Technology
[0002] As a core hub of the power grid, the safe and stable operation of substations is of paramount importance. Substations contain numerous high-voltage electrical equipment, oil-filled equipment (such as transformers), and potentially leaking sulfur hexafluoride (SF6) gas, posing multiple safety risks including electric shock, fire, and explosion. Therefore, strictly monitoring the safe distances between equipment, between personnel and equipment, and between vehicles and facilities is a crucial aspect of substation safety management.
[0003] Currently, the safety distance management of substations mainly relies on the following methods:
[0004] 1. Manual inspection and visual judgment: Maintenance personnel conduct regular inspections and use their experience to judge whether fire exits are unobstructed and whether safe distances at work sites meet requirements. This method is highly subjective, cannot achieve 24-hour uninterrupted monitoring, and is greatly affected by personnel energy and weather conditions, easily leading to blind spots and delays in supervision.
[0005] 2. Traditional security monitoring: This method uses ordinary visible light cameras for video surveillance. While it provides remote visibility, it essentially shifts "human judgment" from the field to a back-end system, still heavily relying on manual screen monitoring, resulting in low efficiency. More importantly, two-dimensional video images lack precise spatial depth information, making it impossible to quantitatively measure distance, volume, etc., and their effectiveness drops significantly in poor visibility conditions such as nighttime, rain, fog, and smoke.
[0006] Therefore, a method for monitoring the safe distance of substations using laser point clouds and visible light images is proposed. Summary of the Invention
[0007] To address the shortcomings of existing technologies, this invention provides a method for monitoring the safe distance of substations using laser point clouds and visible light images, thus solving the problems mentioned in the background section.
[0008] To achieve the above objectives, the present invention provides the following technical solution: a method for monitoring the safety distance of a substation using laser point clouds and visible light images, comprising the following steps:
[0009] S1: Using fixed-point deployed lidar and visible light cameras, laser point cloud and visible light image data are collected, and the laser point cloud and visible light image data are fused to generate fused data;
[0010] S2: Construct a virtual monitoring model for substations based on fused data;
[0011] S3: In the virtual monitoring model of the substation, the three-dimensional spatial range of the fire lane is defined, and the system monitors in real time whether any target continuously intrudes into the space. Once an intrusion occurs, the volume of the intruder and the cross-sectional area of the blockage are measured. If the threshold is exceeded, an alarm is triggered.
[0012] S4: In the virtual monitoring model of the substation, fire isolation zones are defined for important equipment in the substation, and the distance between other objects and these important equipment is calculated in real time.
[0013] S5: When a fire or toxic gas leak is detected in a specific area, the area is marked as a hazard source in the substation virtual monitoring model. Based on the type and intensity of the hazard source, the spread range of toxic smoke or fire and high temperature is dynamically simulated in the substation virtual monitoring model, and the danger zone and safety zone are delineated in real time.
[0014] S51: When a fire is detected, the laser penetration imager is activated to obtain point cloud data by using laser distance gating imaging technology to penetrate fire and smoke. The preset evacuation routes are analyzed in real time to determine whether they are blocked by flames or collapsed objects. Blockages are detected and identified by point cloud changes, and the road conditions of the evacuation routes within the substation are obtained in real time.
[0015] S52: Real-time detection of personnel location via point cloud; if a person is found to be in a dynamic danger zone or moving toward a danger zone, an alarm and evacuation guidance can be issued via emergency broadcast.
[0016] Preferably, in step S2: constructing a virtual monitoring model of a substation based on fused data, after denoising, registration, and segmentation preprocessing of the fused data, a three-dimensional model of all facilities of the substation, including transformers, circuit breakers, frames, conductors, buildings, and terrain, is generated through the preprocessed data.
[0017] Preferably, in step S3: In the substation virtual monitoring model, the three-dimensional spatial range of the fire lane is defined, and any target continuously intrudes into the space in real time is monitored. Once intrusion occurs, the volume of the intruder and the cross-sectional area of the blockage are measured. If the threshold is exceeded, an alarm is triggered. In this step, the fire lane is divided into functional areas: Early warning zone: A buffer zone is defined outside the boundary of the lane space for early warning; Core intrusion zone: The lane space itself, any intrusion is a violation.
[0018] Preferably, in step S4: in the virtual monitoring model of the substation, the fire isolation zone is defined for important equipment in the substation, and the distance between other objects and these important equipment is calculated in real time. The fire isolation zone includes a basic isolation zone and a dynamic isolation zone. The basic isolation zone follows the fire protection requirements of the substation and is offset outward by a specified distance from the equipment body. The dynamic isolation zone expands the range of the basic isolation zone according to changes in weather temperature and the increased risk of fire spread.
[0019] Preferably, in step S4: in the substation virtual monitoring model, if an object is located outside the isolation zone and the distance is greater than the safe distance, normal monitoring is performed if the object is located outside the isolation zone but the distance is close to the safe distance; if the object is located outside the isolation zone but the distance is close to the safe distance, the operation and maintenance personnel are prompted to pay attention; if the object has entered the isolation zone space but there is still a buffer space between it and the equipment body, an alarm is triggered and relevant personnel are notified to handle it; if the object is very close to the equipment body, it is identified whether it is a high-risk object such as an open flame or flammable material, an audible and visual alarm is triggered, and the fire protection system is activated.
[0020] Preferably, in step S5: when a fire or toxic gas leak is detected in a specific area, the area is marked as a hazard source in the substation virtual monitoring model. Based on the type and intensity of the hazard source, the diffusion range of toxic smoke or fire and high temperature is dynamically simulated in the substation virtual monitoring model. In the step of delineating the danger zone and the safety zone in real time, data fusion is performed by toxic gas detection sensors, thermal imaging cameras, visible light cameras and smoke sensors to identify whether a fire or toxic gas leak has occurred in the specific area.
[0021] Preferably, in step S51: when a fire is discovered, by activating a laser penetration imager and using laser distance-gated imaging technology to penetrate fire and smoke, point cloud data is acquired, and the preset evacuation routes are analyzed in real time to determine whether they are blocked by flames or collapsed objects. Blockages are detected and identified through point cloud changes. In the step of acquiring evacuation route condition information in real time within the substation, the evacuation route condition information is connected to the urban fire command system. The fire command system integrates the evacuation route condition information and distributes it to the frontline fire trucks and firefighter terminals.
[0022] Preferably, in step S52: after obtaining the location of the trapped personnel by detecting the personnel location in real time through point cloud, if it is found that someone is in a dynamic danger zone or moving towards the danger zone, an alarm and evacuation guidance can be issued through emergency broadcast, the location of the trapped personnel is marked in the substation virtual monitoring model.
[0023] This invention provides a method for monitoring the safe distance of a substation using laser point clouds and visible light images, which has the following advantages:
[0024] 1. This substation safety distance monitoring method, which uses laser point cloud and visible light images, can detect the encroachment on the safety distance of substation equipment and fire lanes in real time, and issue early warnings before safety hazards cause accidents, thus achieving prevention.
[0025] 2. This substation safety distance monitoring method, which uses laser point cloud and visible light images, overcomes visual obstacles such as smoke at fire scenes by using laser penetration imaging technology, and can monitor the unobstructed status of evacuation routes and the location of personnel in real time, thus providing assistance for internal personnel evacuation and fire rescue. Attached Figure Description
[0026] Figure 1 This is a schematic diagram of the method of the present invention. Detailed Implementation
[0027] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments.
[0028] Please see Figure 1 This invention provides a technical solution: a method for monitoring the safety distance of a substation using laser point clouds and visible light images, comprising the following steps:
[0029] S1: Using fixed-point deployed lidar and visible light cameras, laser point cloud and visible light image data are collected, and the laser point cloud and visible light image data are fused to generate fused data;
[0030] S2: After denoising, registration, and segmentation preprocessing of the fused data, a three-dimensional model of all facilities in the substation, including transformers, circuit breakers, frames, conductors, buildings, and terrain, is generated from the preprocessed data.
[0031] S3: In the virtual monitoring model of the substation, the three-dimensional spatial range of the fire lane is defined, and the system monitors in real time whether any target continuously intrudes into the space. Once an intrusion occurs, the volume of the intruder and the cross-sectional area of the blockage are measured. If the threshold is exceeded, an alarm is triggered.
[0032] S4: In the virtual monitoring model of the substation, fire isolation zones are defined for important equipment in the substation, and the distance between other objects and these important equipment is calculated in real time.
[0033] S5: When a fire or toxic gas leak is detected in a specific area, the area is marked as a hazard source in the substation virtual monitoring model. Based on the type and intensity of the hazard source, the spread range of toxic smoke or fire and high temperature is dynamically simulated in the substation virtual monitoring model, and the danger zone and safety zone are delineated in real time.
[0034] S51: When a fire is detected, the laser penetration imager is activated to obtain point cloud data by using laser distance gating imaging technology to penetrate fire and smoke. The preset evacuation routes are analyzed in real time to determine whether they are blocked by flames or collapsed objects. Blockages are detected and identified by point cloud changes, and the road conditions of the evacuation routes within the substation are obtained in real time.
[0035] S52: Real-time detection of personnel location via point cloud; if a person is found to be in a dynamic danger zone or moving toward a danger zone, an alarm and evacuation guidance can be issued via emergency broadcast.
[0036] Among them, S3: In the virtual monitoring model of the substation, the three-dimensional spatial range of the fire lane is defined, and any target continuously intrudes into the space in real time. Once intrusion occurs, the volume of the intruder and the cross-sectional area of the blockage are measured. If the threshold is exceeded, an alarm is triggered. In the process of dividing the fire lane into functional areas, the warning zone is defined as a buffer zone outside the boundary of the lane space for early warning; the core intrusion zone is the lane space itself, and any intrusion is a violation.
[0037] S4: In the virtual monitoring model of the substation, the fire isolation zone is defined for important equipment in the substation, and the distance between other objects and these important equipment is calculated in real time. The fire isolation zone includes a basic isolation zone and a dynamic isolation zone. The basic isolation zone follows the fire protection requirements of the substation and is set at a specified distance outside the equipment body. The dynamic isolation zone expands the scope of the basic isolation zone according to changes in weather temperature and the increased risk of fire spread.
[0038] S4: In the virtual monitoring model of the substation, fire isolation zones are defined for important equipment in the substation. In the step of calculating the distance between other objects and these important equipment in real time, if the object is located outside the isolation zone and the distance is greater than the safe distance, normal monitoring is carried out; if the object is located outside the isolation zone but the distance is close to the safe distance, the operation and maintenance personnel are prompted to pay attention; if the object has entered the isolation zone space but there is still a buffer space between it and the equipment body, an alarm is triggered and relevant personnel are notified to handle it; if the object is very close to the equipment body, it is identified whether it is a high-risk object such as open flame or flammable material, triggering an audible and visual alarm and activating the fire protection system.
[0039] S5: When a fire or toxic gas leak is detected in a specific area, the area is marked as a hazard source in the substation virtual monitoring model. Based on the type and intensity of the hazard source, the diffusion range of toxic smoke or fire and high temperature is dynamically simulated in the substation virtual monitoring model. In the step of delineating the danger zone and the safety zone in real time, data fusion is performed by toxic gas detection sensors, thermal imaging cameras, visible light cameras and smoke sensors to identify whether a fire or toxic gas leak has occurred in the specific area.
[0040] Among them, S51: When a fire is discovered, the laser penetration imager is activated to obtain point cloud data by using laser distance gating imaging technology to penetrate fire and smoke. The preset evacuation routes are analyzed in real time to see if they are blocked by flames or collapsed objects. Blockages are detected and identified by point cloud changes. In the step of obtaining evacuation route condition information in real time within the substation, the evacuation route condition information is connected to the city fire command system. The fire command system integrates the evacuation route condition information and distributes it to the front-line fire trucks and firefighter terminals.
[0041] Among them, S52: After obtaining the location of the trapped personnel in the step of real-time detection of personnel location through point cloud, if it is found that someone is in a dynamic danger zone or moving towards the danger zone, an alarm and evacuation guidance can be issued through emergency broadcast, the location of the trapped personnel is marked in the virtual monitoring model of the substation.
[0042] Example 1: A fire breaks out in the capacitor bank of a substation, producing a large amount of thick smoke. It is necessary to quickly evacuate the personnel in the station and guide the firefighters to carry out efficient rescue.
[0043] Step 1: The thermal imaging camera detects an abnormally high temperature point (over 300°C) in the capacitor bank area, while the visible light camera identifies open flames and dense smoke. The fire is confirmed through data fusion, and the capacitor bank is immediately marked as a hazard source in the virtual model.
[0044] Step 2: Based on the size of the flames and the factors that cause the smoke to spread, combined with real-time wind speed and direction data, dynamically simulate the high-temperature radiation zone and the smoke-filled zone in the virtual model, and delineate them as danger zones.
[0045] Step 3: Scan the main evacuation routes using a laser penetration imager. Laser distance gating technology effectively penetrates the smoke to obtain clear point cloud data. By comparing the data with the pre-fire model, analyze whether the routes are unobstructed.
[0046] Step 4: Detect in real time using point cloud data that some trapped individuals are approaching the danger zone, and immediately issue a voice warning via the emergency broadcast system in the area: "The path ahead is dangerous. Please immediately follow the following route to escape."
[0047] Step 5: Send information such as the location of the fire source, evacuation route, location of fire water source, fire-fighting facilities, and real-time danger zone delineation to the fire emergency command center. The fire emergency command center can clearly grasp the situation inside the fire scene through the command terminal.
[0048] Example 2: Emergency Response to SF6 Gas Leakage;
[0049] Step 1: The SF6 gas concentration sensor installed in the GIS room detects that the concentration exceeds the standard, triggers an alarm, and marks the GIS room as a hazardous source in the virtual model;
[0050] Step 2: Based on the leakage rate, gas density, and indoor ventilation conditions, simulate the diffusion range and concentration distribution of SF6 gas, and delineate the danger zone in the virtual model;
[0051] Step 3: Identify the direction in which maintenance personnel are heading towards the danger zone using point cloud data, determine that the personnel's movement trajectory will enter the danger zone in 10 seconds, and immediately broadcast an alarm message through nearby broadcasting equipment;
[0052] Step 4: Use a virtual model to dynamically plan a route around the danger zone for emergency responders, and broadcast the route information through broadcasts and nearby display devices.
[0053] All standard parts used in this application can be purchased from the market, and can be customized according to the description and drawings. The specific connection methods of each part adopt conventional methods such as bolts, rivets, and welding that are mature in the prior art. The machinery, parts and equipment all adopt conventional models in the prior art. The installation methods between equipment are also the same as conventional installation methods in the prior art. For example, the two ends of shaft-shaped parts are connected by bearings, the connection position of valve components is provided with anti-leakage rubber strips, the outside of threaded rods or lead rods is provided with dust covers, and the equipment can be driven by either built-in batteries or external power supply. The control method is automatic control by a controller. The control circuit of the controller can be implemented by simple programming by those skilled in the art and is common knowledge in the field. Since this invention is mainly used to protect mechanical devices, this invention will not explain the control method and circuit connection in detail. The external controller mentioned in the specification can play a control role for the electrical components mentioned herein, and the external controller is a conventional known device.
[0054] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.
Claims
1. A method for monitoring the safety distance of a substation using laser point clouds and visible light images, characterized in that: Includes the following steps: S1: Using fixed-point deployed lidar and visible light cameras, laser point cloud and visible light image data are collected, and the laser point cloud and visible light image data are fused to generate fused data; S2: Construct a virtual monitoring model for substations based on fused data; S3: In the virtual monitoring model of the substation, the three-dimensional spatial range of the fire lane is defined, and the system monitors in real time whether any target continuously intrudes into the space. Once an intrusion occurs, the volume of the intruder and the cross-sectional area of the blockage are measured. If the threshold is exceeded, an alarm is triggered. S4: In the virtual monitoring model of the substation, fire isolation zones are defined for important equipment in the substation, and the distance between other objects and these important equipment is calculated in real time. S5: When a fire or toxic gas leak is detected in a specific area, the area is marked as a hazard source in the substation virtual monitoring model. Based on the type and intensity of the hazard source, the spread range of toxic smoke or fire and high temperature is dynamically simulated in the substation virtual monitoring model, and the danger zone and safety zone are delineated in real time. S51: When a fire is detected, the laser penetration imager is activated to obtain point cloud data by using laser distance gating imaging technology to penetrate fire and smoke. The preset evacuation routes are analyzed in real time to determine whether they are blocked by flames or collapsed objects. Blockages are detected and identified by point cloud changes, and the road conditions of the evacuation routes within the substation are obtained in real time. S52: Real-time detection of personnel location via point cloud; if a person is found to be in a dynamic danger zone or moving toward a danger zone, an alarm and evacuation guidance can be issued via emergency broadcast.
2. The method for monitoring substation safety distances using laser point clouds and visible light images according to claim 1, characterized in that: In step S2: the virtual monitoring model of the substation is constructed based on fused data. After the fused data is preprocessed by denoising, registration and segmentation, a three-dimensional model of all facilities of the substation, including transformers, circuit breakers, frames, conductors, buildings and terrain, is generated through the preprocessed data.
3. The method for monitoring substation safety distances using laser point clouds and visible light images according to claim 1, characterized in that: S3: In the virtual monitoring model of the substation, the three-dimensional spatial range of the fire lane is defined, and any target continuously intrudes into the space in real time. Once intrusion occurs, the volume of the intruder and the cross-sectional area of the blockage are measured. If the threshold is exceeded, an alarm is triggered. In this step, the fire lane is divided into functional areas: Early warning zone: A buffer zone is defined outside the boundary of the lane space for early warning; Core intrusion zone: The lane space itself, any intrusion is a violation.
4. The method for monitoring substation safety distances using laser point clouds and visible light images according to claim 1, characterized in that: S4: In the virtual monitoring model of the substation, the fire isolation zone is defined for important equipment in the substation, and the distance between other objects and these important equipment is calculated in real time. The fire isolation zone includes a basic isolation zone and a dynamic isolation zone. The basic isolation zone follows the fire protection requirements of the substation and is offset outward by a specified distance from the equipment body. The dynamic isolation zone expands the range of the basic isolation zone according to changes in weather temperature and the increased risk of fire spread.
5. The method for monitoring substation safety distances using laser point clouds and visible light images according to claim 1, characterized in that: S4: In the substation virtual monitoring model, in the step of defining fire isolation zones for important equipment in the substation and calculating the distance between other objects and these important equipment in real time, if the object is located outside the isolation zone and the distance is greater than the safe distance, normal monitoring is performed; if the object is located outside the isolation zone but the distance is close to the safe distance, the operation and maintenance personnel are prompted to pay attention; if the object has invaded the isolation zone space but there is still a buffer space between it and the equipment body, an alarm is triggered and relevant personnel are notified to handle it. When an object is very close to the device, the system identifies whether it is a high-risk object such as an open flame or flammable material, triggers an audible and visual alarm, and activates the fire suppression system.
6. The method for monitoring substation safety distances using laser point clouds and visible light images according to claim 1, characterized in that: S5: When a fire or toxic gas leak is detected in a specific area, the area is marked as a hazard source in the substation virtual monitoring model. Based on the type and intensity of the hazard source, the diffusion range of toxic smoke or fire and high temperature is dynamically simulated in the substation virtual monitoring model, and the danger zone and safety zone are delineated in real time. In this step, data fusion is performed by toxic gas detection sensors, thermal imaging cameras, visible light cameras and smoke sensors to identify whether a fire or toxic gas leak has occurred in the specific area.
7. The method for monitoring substation safety distances using laser point clouds and visible light images according to claim 1, characterized in that: S51: When a fire is discovered, a laser penetration imager is activated to obtain point cloud data by using laser distance-gated imaging technology to penetrate fire and smoke. The preset evacuation routes are analyzed in real time to determine whether they are blocked by flames or collapsed objects. Blockages are detected and identified by point cloud changes. In the step of obtaining evacuation route condition information in real time within the substation, the evacuation route condition information is connected to the city fire command system. The fire command system integrates the evacuation route condition information and distributes it to the front-line fire trucks and firefighter terminals.
8. The method for monitoring substation safety distances using laser point clouds and visible light images according to claim 1, characterized in that: S52: After obtaining the location of the trapped personnel in the step of real-time detection of personnel location through point cloud, if it is found that someone is in a dynamic danger zone or moving towards the danger zone, an alarm and evacuation guidance can be issued through emergency broadcast, the location of the trapped personnel is marked in the virtual monitoring model of the substation.