Electric power construction safety early warning and intelligent sudden stop device based on multi-sensor fusion

Abstract

The invention provides a power construction safety early warning and intelligent sudden stop device based on multi-sensor fusion. The power construction safety early warning and intelligent sudden stop device comprises a power construction data acquisition module, a power construction data fusion module and a power construction data processing module, according to the invention, the position, speed and azimuth angle data, field three-dimensional point cloud data and field high-definition image information data of all objects in the power construction field are acquired through the power construction data fusion module, and the data can be acquired in the extreme weather such as smog or in the normal weather. Compared with real-time field data information obtained through manual detection, other image detection and laser radar and high-definition camera fusion detection, the method is more comprehensive and accurate, so that the risk identification rate is greatly improved, potential safety risks are avoided, the workload of manual inspection can be greatly reduced, the construction efficiency is improved, and the cost is reduced.

Description

Technical Field

[0001] The present invention belongs to the technical field of electric power construction safety risk detection, and specifically relates to an electric power construction safety early warning and intelligent emergency stop device based on multi-sensor fusion. Background Art

[0002] Currently, the actual operation of identifying unsafe behaviors of power construction workers at power construction sites mainly relies on manual inspections of the construction sites and observing and recording whether the construction workers are performing construction work safely. A small number of methods rely on computer vision to identify and analyze the behaviors of construction workers and issue early warnings for identified dangerous behaviors.

[0003] There are also multi-source data fusion methods (such as the fusion of LiDAR and high-definition cameras) to identify dangerous behaviors of construction workers and issue early warnings, but they cannot directly stop the smart power equipment used by construction workers. This can easily lead to unsafe behaviors by the time the early warning is issued, leading to accidents. Moreover, although the fusion of LiDAR and high-definition cameras alone is more accurate than obtaining information from a single image, the perception capabilities of LiDAR and high-definition cameras are greatly reduced or even fail in the presence of smoke, and they are greatly affected by extreme weather.

[0004] Therefore, it is necessary to design a power construction safety warning and intelligent emergency stop device based on multi-sensor fusion that can comprehensively and accurately identify risks in extreme weather, reduce the workload of manual inspections, and improve construction efficiency and safety to solve the current technical problems. Summary of the invention

[0005] In response to the shortcomings in the prior art, the present invention provides an electric power construction safety warning and intelligent emergency stop device based on multi-sensor fusion, which can comprehensively and accurately identify risks in extreme weather, reduce the workload of manual inspections, and improve construction efficiency and safety.

[0006] The technical solution of the present invention is: a power construction safety early warning and intelligent emergency stop device based on multi-sensor fusion, comprising: The power construction data acquisition module is used to obtain the position, speed, azimuth data, on-site three-dimensional point cloud data and on-site high-definition image information data of objects at the power construction site; The power construction data fusion module pre-processes the position, speed, azimuth data, on-site 3D point cloud data and on-site high-definition image information data of all objects on the power construction site, and fuses the pre-processed position, speed and azimuth data, on-site 3D point cloud data and on-site high-definition image information data of all objects on the site to obtain fused data; and The power construction data processing module collects and prepares image data sets for training and testing according to the safety regulations of the power construction site, performs image classification and target recognition on the image data sets based on the YOLOv8 real-time target detection algorithm, converts the images in the above image data into feature information that can be processed by the machine learning algorithm, stores the feature information, and divides the risk level according to the feature information, performs image classification and target recognition on the fused data based on the YOLOv8 real-time target detection algorithm, obtains the feature information of the target, generates detection information based on the target feature information, matches it with the above stored feature information, obtains the matching result and risk level, and outputs a safety warning signal and an emergency stop signal according to the risk level.

[0007] The electric power construction data acquisition module includes: Millimeter wave radar module, used to transmit microwave beams to the power construction site, and obtain real-time position, speed, and azimuth data of objects at the power construction site; A laser radar module is used to scan the power construction site to obtain three-dimensional point cloud data of the power construction site; and The infrared camera module is used to photograph the power construction site and obtain image information data of the power construction site.

[0008] The electric power construction safety warning and intelligent emergency stop device based on multi-sensor fusion also includes an acoustic and visual alarm module, which emits sound and / or light and / or vibration alarm signals when obtaining the safety warning signal issued by the electric power construction data processing module.

[0009] The electric power construction safety warning and intelligent emergency stop device based on multi-sensor fusion also includes an emergency stop module, which cuts off the power supply to the corresponding electric power construction tool for emergency stop when the emergency stop module obtains the emergency stop signal sent by the electric power construction data processing module.

[0010] The electric power construction data fusion module pre-processes the position, speed, azimuth data, on-site three-dimensional point cloud data and on-site high-definition image information data of all objects at the construction site, including removing noise points in the data acquisition process, removing empty target signals, and separating ground points from non-ground points in the data.

[0011] The power construction data fusion module performs data fusion on the position, speed and azimuth data of all objects on site after preprocessing, the three-dimensional point cloud data on site, and the high-definition image information data on site. The data fusion includes the following steps: S1, extracting the feature point cloud of millimeter wave radar; S2, converting the extracted feature point cloud of the millimeter-wave radar into the laser radar coordinate system, fusing the millimeter-wave radar data with the laser radar data to obtain more accurate three-dimensional point cloud data after fusion; S3 maps each point in the 3D laser point cloud data to the pixel position of the corresponding image, so that the on-site 3D point cloud data is aligned with the high-definition image information, ensuring that the 3D point cloud data and the high-definition image information are in the same coordinate system and represent the same scene.

[0012] The electric power construction safety warning and intelligent emergency stop device based on multi-sensor fusion includes a panel assembly, screw holes are arranged at both ends of the panel assembly, a support plate is arranged at the bottom of the panel assembly, a retractable bracket is arranged at the bottom of the support plate, and an adjustable foot pad is arranged at the bottom of the retractable bracket; the electric power construction data acquisition module, the electric power construction data fusion module and the electric power construction data processing module are all arranged on the panel assembly.

[0013] The group board is provided with an audible and visual alarm module and an emergency stop module.

[0014] Beneficial effects of the present invention: (1) In the present invention, the position, speed, azimuth data, on-site three-dimensional point cloud data and on-site high-definition image information data of all objects at the power construction site are obtained through the power construction data fusion module. Whether in extreme weather such as smoke or in normal weather, the real-time on-site data information obtained by manual detection, other image detection and laser radar, high-definition camera fusion detection is more comprehensive and accurate, which greatly improves the risk identification rate, avoids potential safety risks, and can significantly reduce the workload of manual inspections, improve construction efficiency and reduce costs; (2) The feature information of the target is obtained by using the YOLOv8 real-time target detection algorithm. Based on the target feature information, detection information is generated and matched with the above-mentioned stored feature information to obtain the matching result and risk level. According to the risk level, a safety warning signal and an emergency stop signal are output, and a warning is issued to control the power supply of the power construction tools, thereby greatly improving the safety of power construction. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a principle block diagram of the electric power construction safety warning and intelligent emergency stop device based on multi-sensor fusion in the present invention.

[0016] Figure 2 This is an algorithm flow chart of the electric power construction safety warning and intelligent emergency stop device based on multi-sensor fusion in the present invention.

[0017] Figure 3 It is a structural schematic diagram of the electric power construction safety warning and intelligent emergency stop device based on multi-sensor fusion in the present invention. DETAILED DESCRIPTION

[0018] Various exemplary embodiments of the present invention will now be described in detail with reference to the accompanying drawings. The description of the exemplary embodiments is merely illustrative and is not intended to be any limitation on the present invention and its application or use. The present invention can be implemented in many different forms and is not limited to the embodiments described herein. These embodiments are provided to make the present invention thorough and complete and to fully express the scope of the present invention to those skilled in the art. It should be noted that unless otherwise specifically stated, the relative arrangement of the parts and steps, the composition of the materials, the numerical expressions and the numerical values ​​set forth in these embodiments should be interpreted as being merely exemplary and not as limitations.

[0019] The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different parts. The words "include" or "comprise" and similar words mean that the elements before the word include the elements listed after the word, and do not exclude the possibility of including other elements. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0020] like Figure 1 and 2As shown, the electric power construction safety warning and intelligent emergency stop device based on multi-sensor fusion includes: an electric power construction data acquisition module 10, which is used to obtain the position, speed, azimuth data, on-site three-dimensional point cloud data and on-site high-definition image information data of objects on the electric power construction site; an electric power construction data fusion module 20, which pre-processes the position, speed, azimuth data, on-site three-dimensional point cloud data and on-site high-definition image information data of all objects on the electric power construction site, and fuses the position, speed and azimuth data, on-site three-dimensional point cloud data and on-site high-definition image information data of all objects on the site after pre-processing to obtain fused data; and an electric power construction data processing module 30, which collects and prepares image data sets for training and testing according to safety regulations of the electric power construction site, performs image classification and target recognition on the image data sets based on the YOLOv8 real-time target detection algorithm, converts images in the above image data into feature information that can be processed by a machine learning algorithm, stores the feature information, divides the risk level according to the feature information, and performs image classification and target recognition on the fused data based on the YOLOv8 real-time target detection algorithm to obtain target The characteristic information of the target is obtained, and detection information is generated based on the target characteristic information, and matched with the above-mentioned stored characteristic information to obtain matching results and risk levels, and a safety warning signal and an emergency stop signal are output according to the risk level; in this embodiment, the position, speed, azimuth data, on-site three-dimensional point cloud data and on-site high-definition image information data of all objects at the power construction site are obtained through the power construction data fusion module 20. Whether in extreme weather such as smoke or in normal weather, it can be more comprehensive and accurate than the real-time on-site data information obtained by manual detection, other image detection and laser radar, and high-definition camera fusion detection, so that the risk identification rate is greatly improved, potential safety risks are avoided, and the workload of manual inspections can be greatly reduced, so as to improve construction efficiency and reduce costs; the characteristic information of the target is obtained by obtaining the characteristic information of the target based on the YOLOv8 real-time target detection algorithm, and detection information is generated based on the target characteristic information, and matched with the above-mentioned stored characteristic information to obtain matching results and risk levels, and a safety warning signal and an emergency stop signal are output according to the risk level, and a warning is issued and the power supply of the power construction tools is controlled to be cut off, which greatly improves the safety of power construction.

[0021] In some embodiments, the power construction data acquisition module 10 includes: a millimeter wave radar module 11, which is used to transmit microwave beams to the power construction site, and obtain real-time position, speed, and azimuth data of objects at the power construction site; a laser radar module 12, which is used to scan the power construction site to obtain three-dimensional point cloud data of the power construction site; and an infrared camera module 13, which is used to photograph the power construction site and obtain image information data of the power construction site; the millimeter wave radar module 11 has a strong ability to penetrate fog, smoke, and dust, can work in most weather conditions, has all-weather working capabilities, and has strong anti-interference capabilities, and can effectively resist electromagnetic interference and other types of interference. By integrating the laser radar module 12, the millimeter wave radar module 11 and the infrared camera module 13, more accurate data can be obtained.

[0022] In some embodiments, the power construction safety warning and intelligent emergency stop device based on multi-sensor fusion also includes a sound and light alarm module 40, which is connected to the power construction data processing module 30. When the sound and light alarm module 40 obtains the safety warning signal issued by the power construction data processing module 20, it emits sound and / or light and / or vibration alarm signals, and alerts on-site personnel by issuing alarm signals.

[0023] In some embodiments, the power construction safety warning and intelligent emergency stop device based on multi-sensor fusion also includes an emergency stop module 50, which is connected to the power construction data processing module 30. When the emergency stop module 50 obtains the emergency stop signal sent by the power construction data processing module 30, it cuts off the power to the corresponding power construction tools for emergency stop; the emergency stop module 50 is used to cut off the power to the power construction tools that need electricity and to perform emergency stop processing on the intelligent power construction tools, such as: emergency stop processing on robots related to power construction.

[0024] In some embodiments, the power construction data fusion module 20 pre-processes the position, speed, azimuth data, on-site three-dimensional point cloud data and on-site high-definition image information data of all objects at the construction site, including removing noise points in the data acquisition process, removing empty target signals, and separating ground points from non-ground points in the data. By pre-processing the data, the data quality can be improved, ensuring the accuracy and reliability of subsequent detection.

[0025] In some embodiments, the power construction data fusion module 20 performs data fusion on the pre-processed position, speed and azimuth data of all objects on site, the site three-dimensional point cloud data, and the site high-definition image information data. The data fusion includes the following steps: S1, extracting the feature point cloud of millimeter wave radar; S2, converting the extracted feature point cloud of the millimeter-wave radar into the laser radar coordinate system, fusing the millimeter-wave radar data with the laser radar data to obtain more accurate three-dimensional point cloud data after fusion; S3 maps each point in the 3D laser point cloud data to the pixel position of the corresponding image, so that the on-site 3D point cloud data is aligned with the high-definition image information, ensuring that the 3D point cloud data and the high-definition image information are in the same coordinate system and represent the same scene.

[0026] In some embodiments, the correspondence between the point cloud and the image is obtained based on the feature matching algorithm, and data registration is performed. In the process of image classification and target recognition, the YOLOv8 real-time target detection algorithm is used to improve the recognition accuracy, which includes the following steps: S1, data preparation: According to the safety regulations of the power construction site, collect and prepare image datasets for training and testing, ensure that the dataset contains images of various categories and each image has the correct label or annotation; S2, feature extraction: use the YOLOv8 real-time target detection algorithm to convert the images in the above image data into feature information that can be processed by the machine learning algorithm, store the feature information, and obtain the risk level; S3, feature matching: use the YOLOv8 real-time target detection algorithm to extract data features from the input data, obtain target feature information, and match the target feature information with the stored feature information; S4 Security Warning: Output the risk level based on the matching results, and issue a security warning based on the risk level; S5 emergency stop: When the warning information appears, the system will automatically remotely connect the emergency stop control circuit of the relevant working intelligent power construction tools to perform emergency stop processing.

[0027] In the above embodiment, in the process of risk level classification, the process includes collecting and preparing image data sets for training and testing according to the safety regulations of the power construction site according to the importance and severity of the safety regulations, and classifying the risk levels of the feature information obtained by the YOLOv8 real-time target detection algorithm, such as high, medium, and low; matching the feature information obtained by the fusion data with the stored feature information according to the YOLOv8 real-time target detection algorithm to obtain the risk level of the construction behavior.

[0028] In some embodiments, Figure 3As shown, the electric power construction safety warning and intelligent emergency stop device based on multi-sensor fusion includes a panel assembly 60, screw holes 70 are arranged at both ends of the panel assembly 60, a support plate 80 is arranged at the bottom of the panel assembly 60, a retractable bracket 90 is arranged at the bottom of the support plate 80, and an adjustable foot pad 100 is arranged at the bottom of the retractable bracket 90; the electric power construction data acquisition module 10, the electric power construction data fusion module 20 and the electric power construction data processing module 30 are all arranged on the panel assembly 60, and the retractable bracket 90 is detachably assembled and connected to the support plate 80, which has great artificial mobility, can be portable disassembled and assembled, and can adjust the angle of data acquisition, greatly improving the safety of electric power construction.

[0029] In some embodiments, the assembly panel 60 is provided with an audible and visual alarm module 40 and an emergency stop module 50 .

[0030] So far, various embodiments of the present invention have been described in detail. In order to avoid obscuring the concept of the present invention, some details known in the art are not described. Based on the above description, those skilled in the art can fully understand how to implement the technical solution disclosed here.

[0031] The above-mentioned embodiments only express some implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the invention patent. It should be pointed out that for ordinary technicians in this field, several modifications and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be based on the attached claims.

Claims

1. A power construction safety warning and intelligent emergency stop device based on multi-sensor fusion, characterized in that: include: The power construction data acquisition module is used to obtain the position, speed, azimuth data, on-site three-dimensional point cloud data and on-site high-definition image information data of objects at the power construction site; The power construction data fusion module pre-processes the position, speed, azimuth data, on-site 3D point cloud data and on-site high-definition image information data of all objects on the power construction site, and fuses the pre-processed position, speed and azimuth data, on-site 3D point cloud data and on-site high-definition image information data to obtain fused data; as well as, The power construction data processing module collects and prepares image data sets for training and testing according to the safety regulations of the power construction site, performs image classification and target recognition on the image data sets based on the YOLOv8 real-time target detection algorithm, converts the images in the above image data into feature information that can be processed by the machine learning algorithm, stores the feature information, and divides the risk level according to the feature information, performs image classification and target recognition on the fused data based on the YOLOv8 real-time target detection algorithm, obtains the feature information of the target, generates detection information based on the target feature information, matches it with the above stored feature information, obtains the matching result and risk level, and outputs a safety warning signal and an emergency stop signal according to the risk level.

2. The electric power construction safety early warning and intelligent emergency stop device based on multi-sensor fusion according to claim 1 is characterized in that: The electric power construction data acquisition module includes: Millimeter wave radar module, used to transmit microwave beams to the power construction site, and obtain real-time position, speed, and azimuth data of objects at the power construction site; A laser radar module is used to scan the power construction site to obtain three-dimensional point cloud data of the power construction site; and The infrared camera module is used to photograph the power construction site and obtain image information data of the power construction site.

3. The electric power construction safety early warning and intelligent emergency stop device based on multi-sensor fusion according to claim 1 is characterized in that: It also includes an audible and visual alarm module, which emits audible and / or visual and / or vibration alarm signals when acquiring the safety early warning signal emitted by the electric power construction data processing module.

4. The electric power construction safety early warning and intelligent emergency stop device based on multi-sensor fusion according to claim 1 is characterized in that: It also includes an emergency stop module, which cuts off the power supply to the corresponding electric construction tool for emergency stop when receiving the emergency stop signal sent by the electric construction data processing module.

5. The electric power construction safety early warning and intelligent emergency stop device based on multi-sensor fusion according to claim 1 is characterized in that: The electric power construction data fusion module pre-processes the position, speed, azimuth data, on-site three-dimensional point cloud data and on-site high-definition image information data of all objects at the construction site, including removing noise points in the data acquisition process, removing empty target signals, and separating ground points from non-ground points in the data.

6. The electric power construction safety early warning and intelligent emergency stop device based on multi-sensor fusion according to claim 1 is characterized in that: The power construction data fusion module performs data fusion on the position, speed and azimuth data of all objects on site after preprocessing, the three-dimensional point cloud data on site, and the high-definition image information data on site. The data fusion includes the following steps: S1, extracting the feature point cloud of millimeter wave radar; S2, converting the extracted feature point cloud of the millimeter-wave radar into the laser radar coordinate system, fusing the millimeter-wave radar data with the laser radar data to obtain more accurate three-dimensional point cloud data after fusion; S3 maps each point in the 3D laser point cloud data to the pixel position of the corresponding image, so that the on-site 3D point cloud data is aligned with the high-definition image information, ensuring that the 3D point cloud data and the high-definition image information are in the same coordinate system and represent the same scene.

7. The electric power construction safety early warning and intelligent emergency stop device based on multi-sensor fusion according to claim 1 is characterized in that: It includes a group plate, both ends of which are provided with screw holes, the bottom of which is provided with a support plate, the bottom of which is provided with a retractable bracket, and the bottom of which is provided with an adjustable foot pad; the power construction data acquisition module, the power construction data fusion module and the power construction data processing module are all arranged on the group plate.

8. The electric power construction safety early warning and intelligent emergency stop device based on multi-sensor fusion according to claim 7 is characterized in that: The group board is provided with an audible and visual alarm module and an emergency stop module.

Images