CN118816723A - Distance detection method, device and electronic equipment - Google Patents

Abstract

The application discloses a distance detection method, a device and electronic equipment, wherein the method is applied to the field of electrical engineering and comprises the following steps: determining a target model; acquiring coordinate information of a suspension arm of a crane and coordinate information of target equipment in at least one piece of electrical equipment through a target model according to a preset period; and calculating the target distance between the suspension arm and the target equipment according to the coordinate information of the suspension arm and the coordinate information of the target equipment. According to the application, the problem of low accuracy of detection results due to the fact that the infrared light source calibration conditions are harsh and environmental noise exists in the process of detecting the distance between the telescopic boom of the crane and the electrified equipment in the related technology is solved.

Description

Distance detection method, device and electronic equipment

Technical Field

The present application relates to the field of electrical engineering, and more specifically, to a distance detection method, device and electronic equipment.

Background Art

As the hub of the power system, the substation not only has the function of distributing power supply but also can control the rise and fall of voltage. Therefore, once its state is abnormal, it will cause great economic losses and social impact, so it is very necessary to maintain its stable operation. Substations are different from other civil buildings. They not only have a large number of intricately distributed power cables and complex load distribution inside, but also cover a large number of electrical equipment of various types. Due to the continuous equipment update and expansion of existing substations, equipment disassembly and assembly are often required. These tasks are often unable to be solved by manpower, so large machines are used to assist the operation. For example, a crane is driven into the substation work area to disassemble and assemble the equipment by the crane. When the equipment is updated or expanded, batch replacement is often adopted, so that there are live equipment around the substation operation area. At the same time, the crane has a large operating area. Therefore, in order to prevent the crane arm from touching the live equipment in the substation or entering the safe distance of the live equipment during operation, causing casualties, it is necessary to identify the accidental contact of the crane with the live equipment.

At present, the existing method to prevent the crane boom from accidentally touching live equipment is to use infrared light to detect the safe distance between the crane telescopic arm and the live equipment. However, it is necessary to calibrate the infrared light source to the live equipment in real time during the crane operation, otherwise the measurement result cannot be obtained. This detection method is time-consuming and labor-intensive, which reduces the working efficiency of the crane and the working efficiency of the substation operation.

In the process of detecting the distance between the telescopic boom of a crane and live equipment in the related technology, due to the harsh conditions for the calibration of the infrared light source and the existence of environmental noise, the detection result accuracy is low, and no effective solution has been proposed yet.

Summary of the invention

The main purpose of the present application is to provide a distance detection method, device and electronic equipment to solve the problem of low detection result accuracy due to harsh infrared light source calibration conditions and the presence of environmental noise in the process of detecting the distance between the telescopic boom of a crane and live equipment in the related art.

In order to achieve the above-mentioned purpose, according to one aspect of the present application, a distance detection method is provided, the method comprising: determining a target model, wherein the target model is a three-dimensional digital twin model constructed based on first point cloud data of a substation, and the substation comprises at least a crane and at least one electrical device; obtaining coordinate information of the boom of the crane and coordinate information of a target device in the at least one electrical device through the target model according to a preset period; and calculating a target distance between the boom and the target device based on the coordinate information of the boom and the coordinate information of the target device.

Furthermore, determining the target model includes: scanning the substation by means of three-dimensional laser scanning technology to obtain first point cloud data of the substation; deleting ground point cloud data in the first point cloud data, and denoising the first point cloud data to obtain second point cloud data; extracting third point cloud data of the at least one electrical device from the second point cloud data; deploying a positioning device at a preset position of the substation, and obtaining positioning information of the at least one electrical device by communicating with the positioning device; and determining the target model based on the positioning information of the at least one electrical device and the third point cloud data of the at least one electrical device.

Furthermore, the ground point cloud data in the first point cloud data is deleted, and the first point cloud data is denoised to obtain the second point cloud data, including: gridding the first point cloud data, and calculating the ground height of each grid in the first point cloud data based on a probability statistics method; for each grid in the first point cloud data, deleting the point cloud data in the grid that is lower than the ground height, and deleting the point cloud data in the grid that is higher than a preset height to obtain the fourth point cloud data; calculating the target distance between the target point and the neighboring point in the fourth point cloud data based on Gaussian distribution; and denoising the fourth point cloud data according to the target distance to obtain the second point cloud data.

Furthermore, the equipment types of the at least one electrical equipment include at least: power lines, poles and insulators, and extracting the third point cloud data of the at least one electrical equipment from the second point cloud data includes:

The second point cloud data is classified by the first model to obtain fifth point cloud data and sixth point cloud data, wherein the fifth point cloud data is point cloud data belonging to the power line, the sixth point cloud data is point cloud data not belonging to the power line, and the first model is a model obtained by training the first preset model with known point cloud data of the power line; the fifth point cloud data is processed by three-dimensional reconstruction and point cloud automatic tracking to determine the point cloud data of each power line; the sixth point cloud data is clustered by region growing to determine the target area where the pole tower is located, and the top point cloud data of the pole tower and the bottom point cloud data of the pole tower are determined based on the point cloud data of the target area to obtain the point cloud data of the pole tower; feature extraction is performed on the point cloud data of the pole tower, and the extracted feature vectors are classified and segmented to obtain the point cloud data of the insulator; the third point cloud data of the target device is determined based on the point cloud data of the power line, the point cloud data of the pole tower and the point cloud data of the insulator.

Furthermore, the fifth point cloud data is processed by three-dimensional reconstruction and point cloud automatic tracking to determine the point cloud data of each power line, including: determining the spatial characteristics of the power line by three-dimensionally reconstructing the fifth point cloud data; determining the conductor information of the power line according to the spatial characteristics of the power line, and classifying the fifth point cloud data according to the conductor information to obtain point cloud data of N types of power lines; tracking and clustering the point cloud data of the N types of power lines respectively by point cloud automatic tracking, and fitting the point cloud data of each power line by Hough transform.

Furthermore, feature extraction is performed on the point cloud data of the pole tower, and the extracted feature vectors are classified and segmented to obtain the point cloud data of the insulator, including: inputting the point cloud data of the pole tower into a second preset model to extract a global feature vector; classifying the global feature vector to obtain a classified feature vector; fusing the deep feature vector and the low-level feature vector in the classified feature vector to obtain a fused feature vector; and segmenting the fused feature vector to obtain the point cloud data of the insulator.

Further, the coordinate information of the boom at least includes: the coordinate value of the boom head end and the coordinate value of the boom tail end, and the target distance between the boom and the target device is calculated based on the coordinate information of the boom and the coordinate information of the target device, including: calculating the length of the boom based on the coordinate value of the boom tail end and the coordinate value of the boom head end; calculating the first distance between the boom tail end and the target device based on the coordinate value of the boom tail end and the coordinate information of the target device; calculating the second distance between the boom head end and the target device based on the coordinate value of the boom head end and the coordinate information of the target device; calculating the target value based on the coordinate value of the boom head end, the coordinate value of the boom tail end and the coordinate information of the target device; calculating the target distance based on the length of the boom, the first distance, the second distance and the target value.

Furthermore, after calculating the target distance between the boom and the target device based on the coordinate information of the boom and the coordinate information of the target device, the method also includes: determining at least one safety distance of the target device based on the device type of the target device, wherein each safety distance corresponds to a different alarm level; when the target distance is less than the target safety distance in the at least one safety distance, generating an alarm message based on the alarm level corresponding to the target safety distance; determining processing measures based on the alarm information and the alarm level, and controlling the target device and/or the crane to execute the processing measures.

In order to achieve the above-mentioned purpose, according to another aspect of the present application, a distance detection device is provided, which includes: a first determination unit, used to determine a target model, wherein the target model is a three-dimensional digital twin model constructed based on first point cloud data of a substation, and the substation includes at least a crane and at least one electrical device; an acquisition unit, used to acquire the coordinate information of the boom of the crane and the coordinate information of a target device in the at least one electrical device through the target model according to a preset period; and a calculation unit, used to calculate the target distance between the boom and the target device based on the coordinate information of the boom and the coordinate information of the target device.

Furthermore, the first determination unit includes: a scanning subunit, used to scan the substation by three-dimensional laser scanning technology to obtain first point cloud data of the substation; a processing subunit, used to delete ground point cloud data in the first point cloud data, and perform denoising on the first point cloud data to obtain second point cloud data; an extraction subunit, used to extract third point cloud data of the at least one electrical device from the second point cloud data; an acquisition subunit, used to deploy a positioning device at a preset position of the substation, and obtain the positioning information of the at least one electrical device by communicating with the positioning device; a determination subunit, used to determine the target model based on the positioning information of the at least one electrical device and the third point cloud data of the at least one electrical device.

Furthermore, the processing subunit includes: a first calculation module, used to grid the first point cloud data, and calculate the ground height of each grid in the first point cloud data based on a probability statistics method; a first processing module, used to delete the point cloud data in the grid that is lower than the ground height, and delete the point cloud data in the grid that is higher than a preset height for each grid in the first point cloud data, to obtain fourth point cloud data; a second calculation module, used to calculate the target distance between the target point and the neighboring point in the fourth point cloud data based on Gaussian distribution; a second processing module, used to denoise the fourth point cloud data according to the target distance, to obtain the second point cloud data.

Furthermore, the equipment types in the at least one electrical equipment include at least: power lines, poles and insulators, and the extraction subunit includes: a classification module, which is used to classify the second point cloud data through a first model to obtain fifth point cloud data and sixth point cloud data, wherein the fifth point cloud data is point cloud data belonging to the power line, and the sixth point cloud data is point cloud data that does not belong to the power line, and the first model is a model obtained by training a first preset model with known power line point cloud data; a third processing module, which is used to process the fifth point cloud data through three-dimensional reconstruction and point cloud automatic tracking to determine the point cloud data of each power line. a clustering module, used for clustering the sixth point cloud data by region growing, determining the target area where the pole tower is located, and determining the top point cloud data of the pole tower and the bottom point cloud data of the pole tower according to the point cloud data of the target area, so as to obtain the point cloud data of the pole tower; an extraction module, used for performing feature extraction on the point cloud data of the pole tower, and performing classification and segmentation processing on the extracted feature vectors, so as to obtain the point cloud data of the insulator; a determination module, used for determining the third point cloud data of the target device according to the point cloud data of the power line, the point cloud data of the pole tower and the point cloud data of the insulator.

Furthermore, the third processing module includes: a determination submodule, used to determine the spatial characteristics of the power lines by performing three-dimensional reconstruction on the fifth point cloud data; a first classification submodule, used to determine the conductor information of the power lines based on the spatial characteristics of the power lines, and classify the fifth point cloud data based on the conductor information to obtain point cloud data of N types of power lines; a clustering submodule, used to track and cluster the point cloud data of the N types of power lines respectively through point cloud automatic tracking, and fit the point cloud data of each power line through Hough transform.

Furthermore, the extraction module includes: an extraction submodule, used to input the point cloud data of the pole tower into a second preset model to extract a global feature vector; a second classification submodule, used to classify the global feature vector to obtain a classified feature vector; a fusion submodule, used to fuse the deep feature vector and the low-level feature vector in the classified feature vector to obtain a fused feature vector; and a segmentation submodule, used to segment the fused feature vector to obtain point cloud data of the insulator.

Furthermore, the coordinate information of the boom at least includes: the coordinate value of the boom head end and the coordinate value of the boom tail end, and the calculation unit includes: a first calculation subunit, used to calculate the length of the boom based on the coordinate value of the boom tail end and the coordinate value of the boom head end; a second calculation subunit, used to calculate the first distance between the boom tail end and the target device based on the coordinate value of the boom tail end and the coordinate information of the target device; a third calculation subunit, used to calculate the second distance between the boom head end and the target device based on the coordinate value of the boom head end and the coordinate information of the target device; a fourth calculation subunit, used to calculate the target value based on the coordinate value of the boom head end, the coordinate value of the boom tail end and the coordinate information of the target device; a fifth calculation subunit, used to calculate the target distance based on the length of the boom, the first distance, the second distance and the target value.

Furthermore, the device also includes: a second determination unit, used to determine at least one safety distance of the target device according to the device type of the target device after calculating the target distance between the boom and the target device according to the coordinate information of the boom and the coordinate information of the target device, wherein each safety distance corresponds to a different alarm level; a generation unit, used to generate an alarm message according to the alarm level corresponding to the target safety distance when the target distance is less than the target safety distance in the at least one safety distance; a control unit, used to determine a processing measure according to the alarm information and the alarm level, and control the target device and/or the crane to execute the processing measure.

In order to achieve the above-mentioned purpose, according to one aspect of the present application, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, it implements any one of the distance detection methods described above, and when the computer program is executed by the processor, it implements the steps of the distance detection method described in each embodiment of the present application.

In order to achieve the above-mentioned purpose, according to one aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium includes stored computer instructions, wherein when the computer instructions are executed by a processor, any one of the above-mentioned distance detection methods is implemented.

In order to achieve the above-mentioned purpose, according to one aspect of the present application, an electronic device is provided, including one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by one or more processors, the one or more processors implement any of the distance detection methods described above.

Through this application, the following steps are adopted: determining a target model, wherein the target model is a three-dimensional digital twin model constructed according to the first point cloud data of the substation, and the substation includes at least a crane and at least one electrical device; obtaining the coordinate information of the crane's boom and the coordinate information of the target device in the at least one electrical device through the target model according to a preset period; calculating the target distance between the boom and the target device according to the coordinate information of the boom and the coordinate information of the target device, solving the problem of low accuracy of the detection result due to the harsh conditions of infrared light source calibration and the presence of environmental noise in the process of detecting the distance between the telescopic boom of the crane and the live equipment in the related technology. By obtaining the first point cloud data of the substation work area, a three-dimensional digital twin model of the substation work area can be constructed, and the operation of the crane boom and electrical equipment can be simulated through the three-dimensional digital twin model, so that the shortest distance between the boom and the electrical equipment can be calculated, and then the crane boom can be judged according to the shortest distance. Whether there is a risk of accidentally touching the electrical equipment, there is no need to continuously calibrate the infrared light source, so as to improve the efficiency of detecting whether the crane accidentally touches the electrical equipment, and further achieve the effect of improving the working efficiency of the substation.

BRIEF DESCRIPTION OF THE DRAWINGS

The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

FIG1 is a flow chart of a distance detection method provided according to Embodiment 1 of the present application;

FIG2 is a schematic diagram of an optional distance detection method provided according to Embodiment 1 of the present application;

FIG3 is a schematic diagram of a distance detection device provided according to Embodiment 2 of the present application;

FIG. 4 is a schematic diagram of an electronic device for detecting distance provided according to Embodiment 5 of the present application.

DETAILED DESCRIPTION

It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

It should be noted that the user information (including but not limited to user device information, user personal information, collected data, used data, generated data, processed data, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, collected information, used information, generated information, processed information, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of relevant data are in compliance with the relevant laws, regulations and standards of relevant countries and regions, necessary confidentiality measures are taken, and public order and good morals are not violated, and corresponding operation portals are provided for users to choose to authorize or refuse. For example, an interface is set between this system and relevant users or organizations. Before obtaining relevant information, it is necessary to send an acquisition request to the aforementioned user or organization through the interface, and obtain relevant information after receiving the consent information fed back by the aforementioned user or organization.

It should be noted that this application provides users with corresponding operation entrances for them to choose to agree or reject the automated decision-making results; if the user chooses to reject, the expert decision-making process will be entered.

In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

Embodiment 1

The present invention is described below in conjunction with preferred implementation steps. FIG. 1 is a flow chart of a distance detection method provided according to Embodiment 1 of the present application. As shown in FIG. 1 , the method includes the following steps:

Step S101, determining a target model, wherein the target model is a three-dimensional digital twin model constructed based on first point cloud data of a substation, and the substation includes at least a crane and at least one electrical device.

As substations are constantly updating and expanding their equipment, it is often necessary to dismantle equipment in substations. The dismantling of some equipment cannot be done by manpower, so a crane is needed to assist the operation. Since the operating area of the crane is large, in order to prevent the boom from touching the electrical equipment in the substation or entering the safe distance of the electrical equipment during operation, causing casualties, it is necessary to detect the distance between the crane and the electrical equipment in the substation working area, so as to identify whether the crane accidentally touches the electrical equipment. A distance detection method provided in this embodiment 1 can be applied to detect the distance between the crane and electrical equipment in the substation working area. Electrical equipment refers to equipment used for power generation, transmission, distribution and energization, including but not limited to: motors, generators, transformers, circuit breakers, switches, cables, junction boxes, low voltage or high voltage equipment, etc.

In this first embodiment, in order to detect whether the crane is in contact with the target equipment in the electrical equipment, it is necessary to map the actual environment of the substation operation area, as well as the actual structure and actual position of each electrical equipment in the operation area into three-dimensional space, and construct a three-dimensional digital twin model of the substation operation area (that is, the above-mentioned target model), so as to simulate the operation status of the crane and electrical equipment through the three-dimensional digital twin model, and judge whether the crane and electrical equipment are in contact based on the equipment information in the three-dimensional digital twin model.

Step S102: acquiring coordinate information of a crane boom and coordinate information of a target device in at least one electrical device through a target model according to a preset period.

In the first embodiment, since the crane boom will telescope and move with the progress of the crane hoisting operation, in order to accurately calculate the distance between the crane and the target device, it is necessary to determine the detection cycle (i.e., the above-mentioned preset cycle, for example, 2 seconds, 30 seconds, etc., which is not specifically limited in the first embodiment), and install a positioning device (for example, a satellite sensor) on the crane boom, and communicate with the satellite sensor in real time after each detection cycle to obtain the coordinate information of the crane boom. At the same time, in order to calculate the distance between the crane and the electrical equipment, it is necessary to obtain the coordinate information of the target device through the position mapping relationship established in the target model after each detection cycle, so that the distance between the crane and the target device can be calculated based on the coordinate information of the crane boom and the coordinate information of the target device.

Step S103, calculating the target distance between the crane arm and the target device according to the coordinate information of the crane arm and the coordinate information of the target device.

In the first embodiment, in order to detect whether the crane accidentally touches the target device in the substation electrical equipment, it is necessary to calculate the shortest distance between the crane and the target device (i.e., the target distance mentioned above) based on the coordinate information of the crane's boom and the coordinate information of the target device, so as to judge whether the crane accidentally touches the target device based on the target distance. Exemplarily, if the target distance is less than the preset working safety distance, it is determined that the crane may contact the energized target device; if the target distance is greater than or equal to the preset working safety distance, it is determined that the crane and the energized target device are currently in a safe state, and there is no risk of the crane accidentally touching the energized target device.

In summary, the distance detection method provided in the first embodiment of the present application determines a target model, wherein the target model is a three-dimensional digital twin model constructed according to the first point cloud data of the substation, and the substation includes at least a crane and at least one electrical device; the coordinate information of the crane's boom and the coordinate information of the target device in at least one electrical device are obtained through the target model according to a preset period; the target distance between the boom and the target device is calculated based on the coordinate information of the boom and the coordinate information of the target device, which solves the problem of low accuracy of the detection result due to the harsh conditions for calibrating the infrared light source and the presence of environmental noise in the process of detecting the distance between the telescopic boom of the crane and the live equipment in the related technology. By obtaining the first point cloud data of the substation work area, a three-dimensional digital twin model of the substation work area can be constructed, and the operation of the crane boom and the electrical equipment can be simulated through the three-dimensional digital twin model, so that the shortest distance between the boom and the electrical equipment can be calculated, and then the crane boom can be judged according to the shortest distance. Whether there is a risk of accidentally touching the electrical equipment, there is no need to continuously calibrate the infrared light source, so as to improve the efficiency of detecting whether the crane accidentally touches the electrical equipment, and further achieve the effect of improving the working efficiency of the substation.

Optionally, in the distance detection method provided in Example 1 of the present application, determining the target model includes: scanning the substation by means of three-dimensional laser scanning technology to obtain first point cloud data of the substation; deleting the ground point cloud data in the first point cloud data, and denoising the first point cloud data to obtain second point cloud data; extracting third point cloud data of at least one electrical device from the second point cloud data; deploying a positioning device at a preset position of the substation, and obtaining positioning information of at least one electrical device by communicating with the positioning device; and determining the target model based on the positioning information of at least one electrical device and the third point cloud data of at least one electrical device.

In an optional embodiment, the substation work area can be scanned by three-dimensional laser scanning technology to obtain the first point cloud data of the substation. In order to reduce the data size of the first point cloud data and improve the data quality of the point cloud data, the point cloud data below the ground in the first point cloud data (i.e., the above-mentioned ground point cloud data) can be deleted, and the point cloud data after deleting the ground point cloud data can be denoised to delete irrelevant data points to obtain the above-mentioned second point cloud data. The third point cloud data of each electrical device is extracted from the second point cloud data.

Then, a positioning device (e.g., a satellite sensor, etc.) is installed at the boundary position of the substation operation area (i.e., the above-mentioned preset position), and the longitude and latitude of each electrical device are obtained through real-time communication with the positioning device. At the same time, the positioning information of each electrical device in the actual production environment is obtained by combining the layout and structure of each electrical device in the substation operation area and the position information of the boundary position of the operation area. Alternatively, a satellite sensor can be installed before each electrical device is powered on, and the positioning information of each electrical device in the actual production environment can be obtained by real-time communication with the satellite sensor.

Finally, a three-dimensional digital twin model is constructed based on the third point cloud data of each electrical device, and a position mapping relationship is established between the positioning information of each electrical device and the three-dimensional digital twin model. The positioning information of each electrical device is mapped to the corresponding three-dimensional position coordinate value to obtain the above-mentioned target model.

By acquiring the point cloud data of the substation, deleting the ground point cloud data, and performing denoising processing, redundant data can be reduced, data quality can be improved, and data processing efficiency can be improved. At the same time, by mapping the positioning information of each electrical equipment to the three-dimensional model, the distance between the crane and the electrical equipment can be calculated through the three-dimensional model without the need for real-time infrared calibration, thereby improving the efficiency of detecting accidental collisions of electrical equipment.

Optionally, in the distance detection method provided in Example 1 of the present application, the ground point cloud data in the first point cloud data is deleted, and the first point cloud data is denoised to obtain second point cloud data, including: gridding the first point cloud data, and calculating the ground height of each grid in the first point cloud data based on a probability statistics method; for each grid in the first point cloud data, deleting the point cloud data below the ground height in the grid, and deleting the point cloud data above a preset height in the grid to obtain fourth point cloud data; calculating the target distance between the target point and the neighboring point in the fourth point cloud data based on Gaussian distribution; and denoising the fourth point cloud data according to the target distance to obtain second point cloud data.

Since the initially extracted first point cloud data contains a large amount of ground point cloud data, which has no effect on subsequent modeling and affects the processing speed of subsequent point cloud data, it is necessary to segment the ground point cloud data from the first point cloud data in advance.

In an optional embodiment, considering the undulation of the ground of the substation, the first point cloud data of the substation can be gridded, and the xy plane in the three-dimensional space including the x-axis, y-axis and z-axis is divided into grids of preset area (for example, divided into grids of 5 meters × 5 meters. It should be noted that the grid size can be flexibly adjusted according to the actual situation of the substation or other spatial areas, and is not specifically limited in this embodiment 1), and the ground height of each grid is counted based on the probability statistics method, and the point cloud data below the ground height in each grid is deleted, and then all grids are merged to obtain the point cloud data after the ground point cloud data is separated. Then, based on the ground height of each grid and referring to the height of the electrical equipment of the substation, a preset height above the ground (for example, 15 meters, not specifically limited in this embodiment 1) is selected as the highest height of the point cloud data, and the point cloud data of each grid exceeding the highest height is deleted from the point cloud data after the ground point cloud data is separated to obtain the above-mentioned fourth point cloud data.

In an optional embodiment, the ground height of each grid can be calculated based on probability statistics. Specifically, the probability of point cloud data existing in each height interval in the substation scene is counted, and the number of point cloud data in the interval is bins, the total number of all point cloud data is N, and the interval width is deltaZ. The probability statistics result f can be expressed as: Among them, the height with the highest probability is the ground height.

In an optional embodiment, the fourth point cloud data can be denoised based on statistical filtering. Specifically, the average distance between each point in the point cloud data and its neighboring points is considered to be a Gaussian distribution, and a preset distance threshold is set according to the mean and variance of the Gaussian distribution. If the average value of the distance between point Pi and all neighboring points k is greater than the preset distance threshold, point Pi is determined to be an outlier. All outliers in the fourth point cloud data are calculated, and the outliers in the fourth point cloud data are removed to obtain the second point cloud data.

Optionally, in the distance detection method provided in the first embodiment of the present application, the device types in the at least one electrical device include at least: power lines, poles and insulators, and extracting third point cloud data of at least one electrical device from the second point cloud data includes: classifying the second point cloud data by the first model to obtain fifth point cloud data and sixth point cloud data, wherein the fifth point cloud data is point cloud data belonging to the power lines, and the sixth point cloud data is point cloud data not belonging to the power lines, and the first model is a model obtained by training the first preset model with known power line point cloud data; and obtaining the third point cloud data of the at least one electrical device from the second point cloud data by the third model. The fifth point cloud data is processed by three-dimensional reconstruction and point cloud automatic tracking to determine the point cloud data of each power line; the sixth point cloud data is clustered by region growing to determine the target area where the tower is located, and the top point cloud data of the tower and the bottom point cloud data of the tower are determined based on the point cloud data of the target area to obtain the point cloud data of the tower; features are extracted from the point cloud data of the tower, and the extracted feature vectors are classified and segmented to obtain the point cloud data of the insulator; the third point cloud data of the target device is determined based on the point cloud data of the power line, the point cloud data of the tower and the point cloud data of the insulator.

In the first embodiment of the present invention, in order to extract point cloud data of different electrical equipment, first, the second point cloud data can be classified to obtain fifth point cloud data belonging to the power line and sixth point cloud data not belonging to the power line; then, the fifth point cloud data is processed by automatic point cloud tracking to determine the point cloud data of each power line, and the sixth point cloud data is processed by clustering to obtain the point cloud data of the tower; finally, the preset model is used to extract feature information of the point cloud data on the surface of the tower from the point cloud data of the tower, the point cloud data on the surface of the tower is classified, the point cloud data corresponding to different types of insulating materials are determined, and the point cloud data on the surface of the tower is segmented according to the point cloud data corresponding to different types of insulating materials to obtain point cloud data of insulators of different types of insulating materials.

In an optional embodiment, the process of obtaining the point cloud data of the tower by clustering the sixth point cloud data can be as follows. For the sixth point cloud of non-power lines, a raster image can be constructed using horizontal projection, and regional growth can be used for clustering on this basis. Prior information is used to eliminate point cloud data clusters other than the tower, and the target area where the tower is located is determined. Then, within the scope of the target area, the top point cloud data of the tower is extracted upward from a preset height using regional growth. Through spatial proximity search, the lowest point of the power line near each tower is obtained, and the bottom point cloud data of the tower is obtained. The tower height is calculated based on the top point cloud data of the tower and the bottom point cloud data of the tower, as well as the center position of the tower and the line span. A vertical plane of power lines near the tower is constructed, and the point cloud data related to the tower in the target area is projected onto the vertical plane. The tower body, tower top and tower body connection points are fitted and extracted by combining the Random Sample Consensus Line (RANSAC) algorithm, and the topology is constructed to restore the tower structure. The structural position of the tower top is determined by combining the width difference between the tower body and the tower top and the elevation distribution characteristics, and the above-mentioned point cloud data of the tower is obtained.

By extracting point cloud data of different types of electrical equipment separately, the extraction accuracy of power lines, poles, and three-dimensional insulators is improved, which is conducive to building a more accurate target model, thereby improving the accuracy of simulating the boom and electrical equipment in the target model, and further achieving the effect of improving the accuracy of detecting whether the crane boom accidentally touches live equipment.

Optionally, in the distance detection method provided in Example 1 of the present application, the fifth point cloud data is processed by three-dimensional reconstruction and point cloud automatic tracking to determine the point cloud data of each power line, including: determining the spatial characteristics of the power lines by three-dimensionally reconstructing the fifth point cloud data; determining the conductor information of the power lines based on the spatial characteristics of the power lines, and classifying the fifth point cloud data based on the conductor information to obtain point cloud data of N types of power lines; tracking and clustering the point cloud data of N types of power lines respectively through point cloud automatic tracking, and fitting the point cloud data of each power line through Hough transform.

In an optional embodiment, the direction of the power line can be determined according to the spatial characteristics of the power line itself, the fifth point cloud data belonging to the power line is three-dimensionally reconstructed, and each power line is classified according to the spatial structural characteristics of the reconstructed point cloud data. Exemplarily, when the number of conductors in the power line is less than 3, the power line is classified as a lightning protection line, and when the number of conductors in the power line is greater than or equal to 3, the power line is classified as a transmission line.

Then, since the point cloud data of a single power line are closely connected, the distance between two points is small, and the distance between point cloud data that do not belong to a power line is large, on the basis of accurate classification of the point cloud data of each power line, the point cloud automatic tracking method can be used to track, cluster and identify the point cloud data on each power line, so as to prepare for the fitting of the power lines.

Finally, Hough Transform is used to extract the straight line model. The curve in the three-dimensional rectangular coordinate system is converted into a point in the polar coordinate system through the duality of point and line. The line corresponding to the three-dimensional rectangular coordinate system is found in the polar coordinate system to obtain the point cloud data of each power line.

Optionally, in the distance detection method provided in Example 1 of the present application, feature extraction is performed on the point cloud data of the pole tower, and the extracted feature vectors are classified and segmented to obtain point cloud data of the insulator, including: inputting the point cloud data of the pole tower into a second preset model to extract global feature vectors; classifying the global feature vectors to obtain classified feature vectors; fusing deep feature vectors and low-level feature vectors in the classified feature vectors to obtain fused feature vectors; and segmenting the fused feature vectors to obtain point cloud data of the insulator.

In an optional embodiment, the PointNet++ model is divided into two types according to the task: a classification network and a segmentation network. The input and output are respectively consistent with the two networks in PointNet. PointNet++ will first sample and group the point cloud data of the tower, and use the basic PointNet network to extract features (including MSG and MRG) in each group, extract local feature vectors from different scales, and extract global feature vectors to obtain the above-mentioned feature vectors.

Then, for the classification problem, after using the PointNet network to extract the global feature vector, the classification network uses a small PointNet model and a fully connected network (FCN) to calculate the classification score based on the global feature vector, that is, the probability score that the point cloud data belongs to different types of insulator materials. The category of the global feature vector is determined according to the material type corresponding to the highest classification probability, and the above-mentioned classified feature vector is obtained.

Finally, for the segmentation problem, the high-dimensional points in the classified feature vector are inversely interpolated to obtain the same points as the low-dimensional ones, and then the PointNet model is used to extract the deep feature vector. The segmentation network continuously fuses the deep feature vector with the low-level feature map information (that is, the above-mentioned low-level feature vector) through the skip link operation, and the segmentation obtains the point cloud data corresponding to different categories of insulator materials, that is, the point cloud data of the insulator mentioned above.

Optionally, in the distance detection method provided in Example 1 of the present application, the above-mentioned coordinate information of the boom includes at least: the coordinate value of the head end of the boom and the coordinate value of the tail end of the boom, and the target distance between the boom and the target device is calculated based on the coordinate information of the boom and the coordinate information of the target device, including: calculating the length of the boom based on the coordinate value of the tail end of the boom and the coordinate value of the head end of the boom; calculating the first distance between the tail end of the boom and the target device based on the coordinate value of the tail end of the boom and the coordinate information of the target device; calculating the second distance between the head end of the boom and the target device based on the coordinate value of the head end of the boom and the coordinate information of the target device; calculating the target value based on the coordinate value of the head end of the boom, the coordinate value of the tail end of the boom and the coordinate information of the target device; calculating the target distance based on the length of the boom, the first distance, the second distance and the target value.

In an optional embodiment, the calculation formula for calculating the length of the boom according to the coordinate value of the boom tail end and the coordinate value of the boom head end may be as shown in Formula 1:

Wherein, (x ₁ , y ₁ , z ₁ ) is the three-dimensional position coordinate value of the boom tail end a in the current cycle, (x ₂ , y ₂ , z ₂ ) is the three-dimensional position coordinate value of the boom head end b in the current cycle, and d _ab is the length of the boom. The calculation formula for calculating the first distance between the boom tail end and the target device can be shown in Formula 2,

Wherein, (x ₁ , y ₁ , z ₁ ) is the three-dimensional position coordinate value of the boom tail end a in the current cycle, (x ₃ , y ₃ , z ₃ ) is the three-dimensional position coordinate value of the target device s, and d _as represents the first distance mentioned above. The calculation formula for calculating the second distance between the boom head end and the target device can be shown in Formula 3,

Wherein, (x ₂ , y ₂ , z ₂ ) is the three-dimensional position coordinate value of the boom head end b in the current cycle, (x ₃ , y ₃ , z ₃ ) is the three-dimensional position coordinate value of the target device s, and d _bs represents the second distance mentioned above. The calculation formula for calculating the target value can be shown in Formula 4,

Wherein, (x ₁ , y ₁ , z ₁ ) is the three-dimensional position coordinate value of the boom tail end a in the current cycle, (x ₂ , y ₂ , z ₂ ) is the three-dimensional position coordinate value of the boom head end b in the current cycle, (x ₃ , y ₃ , z ₃ ) is the three-dimensional position coordinate value of the target device s, and t represents the above target value. The calculation formula for calculating the target distance can be shown in Formula 5,

Wherein, d _ab represents the length of the boom, d _as represents the first distance, d _bs represents the second distance, A represents the angle between the boom and the horizontal ground, and L represents the above-mentioned target distance.

Optionally, in the distance detection method provided in Example 1 of the present application, after calculating the target distance between the boom and the target device based on the coordinate information of the boom and the coordinate information of the target device, the above method also includes: determining at least one safety distance of the target device based on the device type of the target device, wherein each safety distance corresponds to a different alarm level; when the target distance is less than the target safety distance in at least one safety distance, generating an alarm information based on the alarm level corresponding to the target safety distance; determining a processing measure based on the alarm information and the alarm level, and controlling the target device and/or the crane to execute the processing measure.

In an optional embodiment, the operating safety distance between the electrical equipment of each equipment type and the boom (i.e., the above-mentioned safety distance) can be determined in combination with the equipment type of the electrical equipment in the substation. Exemplarily, the safety distance between a certain type of electrical equipment and the boom can include 1 meter, 2 meters, and 5 meters, wherein the alarm level corresponding to 1 meter is an emergency alarm, which is the highest level of alarm, the alarm level corresponding to 2 meters is a major alarm, and the alarm level corresponding to 5 meters is a general alarm. Then, when it is detected in any detection cycle that the target distance between the boom and the target equipment is less than the operating safety distance corresponding to the equipment type of the target equipment (i.e., the above-mentioned target safety distance), an alarm message is generated according to the alarm level corresponding to the target safety distance, and an alarm is issued to prevent the crane boom from accidentally touching the live electrical equipment. Finally, the corresponding emergency treatment measures can be determined according to the alarm information, and the target equipment and/or the crane can be controlled to execute the treatment measures.

Optionally, the distance detection method provided in the first embodiment of the present invention can be applied to a large-scale machinery accidental collision equipment identification system for a substation. The structure diagram of the system can be shown in Figure 2, which includes: a three-dimensional position acquisition module 201, a shortest distance calculation module 202, a determination module 203 and an alarm module 204.

The three-dimensional position acquisition module 201 includes an electrical equipment three-dimensional position acquisition submodule 2011 and a crane boom three-dimensional position acquisition submodule 2012. The electrical equipment three-dimensional position acquisition submodule 2011 is used to construct a three-dimensional digital twin model corresponding to the substation operation area according to the actual environment of the substation operation area, as well as the actual structure and actual position of each electrical equipment in the operation area, and map the actual position of each electrical equipment to the corresponding three-dimensional coordinate value of the three-dimensional digital twin model; the crane boom three-dimensional position acquisition submodule 2012 is used to obtain the actual position of the boom head end and the actual position of the boom tail end of the crane during the hoisting operation in the actual environment of the substation operation area at intervals of each detection cycle after determining the detection cycle, and map the actual position of the boom head end and the actual position of the boom tail end to the three-dimensional digital twin model to obtain the three-dimensional coordinate value of the boom head end and the three-dimensional coordinate value of the boom tail end.

The shortest distance calculation module 202 is used to calculate the shortest distance from the boom to each electrical device in each detection cycle (i.e., the target distance mentioned above) based on the three-dimensional coordinate values of each electrical device and the three-dimensional coordinate values of the head end and the tail end of the boom in each detection cycle.

The determination module 203 is used to determine whether the shortest distance from the boom to the electrical equipment exceeds the operating safety distance; if it exceeds the operating safety distance, determine the alarm level corresponding to the operating safety distance, generate alarm information and transmit it to the alarm module 204.

The alarm module 204 is used to receive the alarm information sent by the determination module 203 and issue an alarm message according to the alarm level of the alarm information.

It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

Embodiment 2

The second embodiment of the present application also provides a distance detection device. It should be noted that the distance detection device of the second embodiment of the present application can be used to execute the distance detection method provided in the first embodiment of the present application. The distance detection device provided in the second embodiment of the present application is introduced below.

Fig. 3 is a schematic diagram of a distance detection device according to Embodiment 2 of the present application. As shown in Fig. 3 , the device includes: a first determining unit 301 , an acquiring unit 302 , and a calculating unit 303 .

Specifically, the first determination unit 301 is used to determine the target model, wherein the target model is a three-dimensional digital twin model constructed according to the first point cloud data of the substation, and the substation includes at least a crane and at least one electrical equipment.

The acquisition unit 302 is used to acquire the coordinate information of the boom of the crane and the coordinate information of the target device in at least one electrical device through the target model according to a preset period.

The calculation unit 303 is used to calculate the target distance between the crane arm and the target device according to the coordinate information of the crane arm and the coordinate information of the target device.

The distance detection device provided in the second embodiment of the present application determines the target model through the first determination unit 301, wherein the target model is a three-dimensional digital twin model constructed according to the first point cloud data of the substation, and the substation includes at least a crane and at least one electrical equipment; the acquisition unit 302 acquires the coordinate information of the crane's boom and the coordinate information of the target device in at least one electrical equipment through the target model according to a preset period; the calculation unit 303 calculates the target distance between the boom and the target device based on the coordinate information of the boom and the coordinate information of the target device, which solves the problem of low accuracy of the detection result in the process of detecting the distance between the telescopic boom of the crane and the live equipment in the related art due to the harsh conditions for the calibration of the infrared light source and the presence of environmental noise. By obtaining the first point cloud data of the substation work area, a three-dimensional digital twin model of the substation work area can be constructed. The operation of the crane boom and electrical equipment can be simulated through the three-dimensional digital twin model, so that the shortest distance between the boom and the electrical equipment can be calculated. Then, based on the shortest distance, it can be determined whether there is a risk of the crane boom accidentally hitting the electrical equipment. There is no need to continuously calibrate the infrared light source, thereby improving the efficiency of detecting whether the crane accidentally hits electrical equipment, and further improving the working efficiency of the substation.

Optionally, in the distance detection device provided in Example 2 of the present application, the above-mentioned first determination unit 301 includes: a scanning subunit, used to scan the substation through three-dimensional laser scanning technology to obtain first point cloud data of the substation; a processing subunit, used to delete the ground point cloud data in the first point cloud data, and denoise the first point cloud data to obtain second point cloud data; an extraction subunit, used to extract third point cloud data of at least one electrical device from the second point cloud data; an acquisition subunit, used to deploy a positioning device at a preset position of the substation, and obtain the positioning information of at least one electrical device by communicating with the positioning device; a determination subunit, used to determine the target model based on the positioning information of at least one electrical device and the third point cloud data of at least one electrical device.

Optionally, in the distance detection device provided in Example 2 of the present application, the above-mentioned processing subunit includes: a first calculation module, used to grid the first point cloud data, and calculate the ground height of each grid in the first point cloud data based on a probability statistics method; a first processing module, used to delete the point cloud data below the ground height in the grid and delete the point cloud data above a preset height in the grid for each grid in the first point cloud data, to obtain fourth point cloud data; a second calculation module, used to calculate the target distance between the target point and the neighboring point in the fourth point cloud data based on Gaussian distribution; a second processing module, used to denoise the fourth point cloud data according to the target distance to obtain second point cloud data.

Optionally, in the distance detection device provided in the second embodiment of the present application, the device types in the at least one electrical device include at least: power lines, poles and insulators, and the extraction subunit includes: a classification module, which is used to classify the second point cloud data through the first model to obtain fifth point cloud data and sixth point cloud data, wherein the fifth point cloud data is point cloud data belonging to the power line, and the sixth point cloud data is point cloud data that does not belong to the power line, and the first model is a model obtained by training the first preset model with known power line point cloud data; a third processing module is used to classify the second point cloud data through the first model to obtain fifth point cloud data and sixth point cloud data. The five point cloud data are processed to determine the point cloud data of each power line; the clustering module is used to cluster the sixth point cloud data through regional growth to determine the target area where the pole tower is located, and determine the top point cloud data of the pole tower and the bottom point cloud data of the pole tower based on the point cloud data of the target area to obtain the point cloud data of the pole tower; the extraction module is used to extract features from the point cloud data of the pole tower, and classify and segment the extracted feature vectors to obtain the point cloud data of the insulator; the determination module is used to determine the third point cloud data of the target device based on the point cloud data of the power line, the point cloud data of the pole tower and the point cloud data of the insulator.

Optionally, in the distance detection device provided in Example 2 of the present application, the above-mentioned third processing module includes: a determination submodule, used to determine the spatial characteristics of the power lines by performing three-dimensional reconstruction of the fifth point cloud data; a first classification submodule, used to determine the conductor information of the power lines based on the spatial characteristics of the power lines, and classify the fifth point cloud data based on the conductor information to obtain point cloud data of N types of power lines; a clustering submodule, used to track and cluster the point cloud data of N types of power lines respectively through point cloud automatic tracking, and fit the point cloud data of each power line through Hough transform.

Optionally, in the distance detection device provided in Example 2 of the present application, the above-mentioned extraction module includes: an extraction submodule, used to input the point cloud data of the pole tower into the second preset model to extract the global feature vector; a second classification submodule, used to classify the global feature vector to obtain the classified feature vector; a fusion submodule, used to fuse the deep feature vector and the low-level feature vector in the classified feature vector to obtain the fused feature vector; a segmentation submodule, used to segment the fused feature vector to obtain the point cloud data of the insulator.

Optionally, in the distance detection device provided in Example 2 of the present application, the above-mentioned coordinate information of the boom includes at least: the coordinate value of the head end of the boom and the coordinate value of the tail end of the boom, and the above-mentioned calculation unit 303 includes: a first calculation subunit, used to calculate the length of the boom based on the coordinate value of the tail end of the boom and the coordinate value of the head end of the boom; a second calculation subunit, used to calculate the first distance between the tail end of the boom and the target device based on the coordinate value of the tail end of the boom and the coordinate information of the target device; a third calculation subunit, used to calculate the second distance between the head end of the boom and the target device based on the coordinate value of the head end of the boom and the coordinate information of the target device; a fourth calculation subunit, used to calculate the target value based on the coordinate value of the head end of the boom, the coordinate value of the tail end of the boom and the coordinate information of the target device; a fifth calculation subunit, used to calculate the target distance based on the length of the boom, the first distance, the second distance and the target value.

Optionally, in the distance detection device provided in Example 2 of the present application, the above-mentioned device also includes: a second determination unit, used to determine at least one safety distance of the target device according to the device type of the target device after calculating the target distance between the crane arm and the target device based on the coordinate information of the crane arm and the coordinate information of the target device, wherein each safety distance corresponds to a different alarm level; a generation unit, used to generate an alarm message according to the alarm level corresponding to the target safety distance when the target distance is less than the target safety distance in at least one safety distance; a control unit, used to determine a processing measure based on the alarm information and the alarm level, and control the target device and/or the crane to execute the processing measure.

The distance detection device includes a processor and a memory. The first determination unit 301, the acquisition unit 302 and the calculation unit 303 are all stored in the memory as program units. The processor executes the program units stored in the memory to implement corresponding functions.

The processor includes a kernel, and the kernel calls the corresponding program unit from the memory. One or more kernels can be set, and the accuracy of the detection result of the distance between the crane and the electrical equipment can be improved by adjusting the kernel parameters.

The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and/or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

Embodiment 3 of the present invention provides a computer-readable storage medium on which a program is stored. When the program is executed by a processor, a distance detection method is implemented.

A fourth embodiment of the present invention provides a processor, which is used to run a program, wherein the distance detection method is executed when the program is running.

As shown in Figure 4, embodiment five of the present invention provides an electronic device, the device includes a processor, a memory, and a program stored in the memory and executable on the processor, and the processor implements the following steps when executing the program: by determining a target model, wherein the target model is a three-dimensional digital twin model constructed based on first point cloud data of a substation, and the substation includes at least a crane and at least one electrical device; obtaining coordinate information of a boom of the crane and coordinate information of a target device in at least one electrical device through the target model according to a preset period; and calculating a target distance between the boom and the target device based on the coordinate information of the boom and the coordinate information of the target device.

When the processor executes the program, the following steps are also implemented: determining the target model, including: scanning the substation through three-dimensional laser scanning technology to obtain first point cloud data of the substation; deleting the ground point cloud data in the first point cloud data, and denoising the first point cloud data to obtain second point cloud data; extracting third point cloud data of at least one electrical device from the second point cloud data; deploying a positioning device at a preset position of the substation, and obtaining positioning information of at least one electrical device by communicating with the positioning device; determining the target model based on the positioning information of at least one electrical device and the third point cloud data of at least one electrical device.

When the processor executes the program, the following steps are also implemented: deleting the ground point cloud data in the first point cloud data, and denoising the first point cloud data to obtain second point cloud data, including: gridding the first point cloud data, and calculating the ground height of each grid in the first point cloud data based on a probability statistics method; for each grid in the first point cloud data, deleting the point cloud data below the ground height in the grid, and deleting the point cloud data above a preset height in the grid to obtain fourth point cloud data; calculating the target distance between the target point and the neighboring point in the fourth point cloud data based on a Gaussian distribution; and denoising the fourth point cloud data according to the target distance to obtain second point cloud data.

When the processor executes the program, the following steps are also implemented: the device types in the at least one electrical device mentioned above include at least: power lines, poles and insulators, and the third point cloud data of at least one electrical device is extracted from the second point cloud data, including: classifying the second point cloud data through the first model to obtain fifth point cloud data and sixth point cloud data, wherein the fifth point cloud data is point cloud data belonging to the power line, and the sixth point cloud data is point cloud data not belonging to the power line, and the first model is a model obtained by training the first preset model with known power line point cloud data; through three-dimensional reconstruction and The fifth point cloud data is processed by automatic point cloud tracking to determine the point cloud data of each power line; the sixth point cloud data is clustered by region growing to determine the target area where the tower is located, and the top point cloud data of the tower and the bottom point cloud data of the tower are determined based on the point cloud data of the target area to obtain the point cloud data of the tower; feature extraction is performed on the point cloud data of the tower, and the extracted feature vectors are classified and segmented to obtain the point cloud data of the insulator; the third point cloud data of the target device is determined based on the point cloud data of the power line, the point cloud data of the tower and the point cloud data of the insulator.

When the processor executes the program, the following steps are also implemented: the fifth point cloud data is processed through three-dimensional reconstruction and point cloud automatic tracking to determine the point cloud data of each power line, including: the spatial characteristics of the power line are determined by three-dimensional reconstruction of the fifth point cloud data; the conductor information of the power line is determined according to the spatial characteristics of the power line, and the fifth point cloud data is classified according to the conductor information to obtain point cloud data of N types of power lines; the point cloud data of the N types of power lines are tracked and clustered respectively through point cloud automatic tracking, and the point cloud data of each power line is fitted through Hough transform.

When the processor executes the program, the following steps are also implemented: feature extraction is performed on the point cloud data of the pole tower, and the extracted feature vectors are classified and segmented to obtain the point cloud data of the insulator, including: inputting the point cloud data of the pole tower into the second preset model to extract the global feature vector; classifying the global feature vector to obtain the classified feature vector; fusing the deep feature vector and the low-level feature vector in the classified feature vector to obtain the fused feature vector; segmenting the fused feature vector to obtain the point cloud data of the insulator.

When the processor executes the program, the following steps are also implemented: the above-mentioned coordinate information of the boom includes at least: the coordinate value of the head end of the boom and the coordinate value of the tail end of the boom, and the target distance between the boom and the target device is calculated based on the coordinate information of the boom and the coordinate information of the target device, including: calculating the length of the boom based on the coordinate value of the tail end of the boom and the coordinate value of the head end of the boom; calculating the first distance between the tail end of the boom and the target device based on the coordinate value of the tail end of the boom and the coordinate information of the target device; calculating the second distance between the head end of the boom and the target device based on the coordinate value of the head end of the boom and the coordinate information of the target device; calculating the target value based on the coordinate value of the head end of the boom, the coordinate value of the tail end of the boom and the coordinate information of the target device; calculating the target distance based on the length of the boom, the first distance, the second distance and the target value.

When the processor executes the program, the following steps are also implemented: after calculating the target distance between the boom and the target device based on the coordinate information of the boom and the coordinate information of the target device, the above method also includes: determining at least one safety distance of the target device based on the device type of the target device, wherein each safety distance corresponds to a different alarm level; when the target distance is less than the target safety distance in at least one safety distance, generating an alarm message based on the alarm level corresponding to the target safety distance; determining processing measures based on the alarm information and the alarm level, and controlling the target device and/or the crane to execute the processing measures.

The devices in this article can be servers, PCs, PADs, mobile phones, etc.

The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing an initialization program having the following method steps: by determining a target model, wherein the target model is a three-dimensional digital twin model constructed based on first point cloud data of a substation, and the substation includes at least a crane and at least one electrical device; obtaining coordinate information of a crane boom and coordinate information of a target device in at least one electrical device through the target model according to a preset period; and calculating a target distance between the boom and the target device based on the coordinate information of the boom and the coordinate information of the target device.

When executed on a data processing device, it is also suitable for executing a program that initializes the following method steps: determining a target model, including: scanning the substation through three-dimensional laser scanning technology to obtain first point cloud data of the substation; deleting ground point cloud data in the first point cloud data, and denoising the first point cloud data to obtain second point cloud data; extracting third point cloud data of at least one electrical device from the second point cloud data; deploying a positioning device at a preset position of the substation, and obtaining positioning information of at least one electrical device by communicating with the positioning device; determining the target model based on the positioning information of at least one electrical device and the third point cloud data of at least one electrical device.

When executed on a data processing device, it is also suitable for executing a program initialized with the following method steps: deleting ground point cloud data in the first point cloud data, and denoising the first point cloud data to obtain second point cloud data, including: gridding the first point cloud data, and calculating the ground height of each grid in the first point cloud data based on a probability statistics method; for each grid in the first point cloud data, deleting the point cloud data below the ground height in the grid, and deleting the point cloud data above the preset height in the grid to obtain fourth point cloud data; calculating the target distance between the target point and the neighboring point in the fourth point cloud data based on Gaussian distribution; denoising the fourth point cloud data according to the target distance to obtain second point cloud data.

When executed on a data processing device, the method is also suitable for executing a program that is initialized with the following method steps: the device types in the at least one electrical device mentioned above include at least: power lines, poles and insulators, and the third point cloud data of at least one electrical device is extracted from the second point cloud data, including: classifying the second point cloud data through the first model to obtain fifth point cloud data and sixth point cloud data, wherein the fifth point cloud data is point cloud data belonging to the power line, and the sixth point cloud data is point cloud data that does not belong to the power line, and the first model is a model obtained by training the first preset model using known power line point cloud data ; The fifth point cloud data is processed through three-dimensional reconstruction and point cloud automatic tracking to determine the point cloud data of each power line; the sixth point cloud data is clustered through regional growth to determine the target area where the tower is located, and the top point cloud data of the tower and the bottom point cloud data of the tower are determined based on the point cloud data of the target area to obtain the point cloud data of the tower; feature extraction is performed on the point cloud data of the tower, and the extracted feature vectors are classified and segmented to obtain the point cloud data of the insulator; the third point cloud data of the target device is determined based on the point cloud data of the power line, the point cloud data of the tower and the point cloud data of the insulator.

When executed on a data processing device, it is also suitable for executing an initialization program having the following method steps: processing the fifth point cloud data through three-dimensional reconstruction and point cloud automatic tracking to determine the point cloud data of each power line, including: determining the spatial characteristics of the power line by three-dimensionally reconstructing the fifth point cloud data; determining the conductor information of the power line based on the spatial characteristics of the power line, and classifying the fifth point cloud data based on the conductor information to obtain point cloud data of N types of power lines; tracking and clustering the point cloud data of N types of power lines respectively through point cloud automatic tracking, and fitting the point cloud data of each power line through Hough transform.

When executed on a data processing device, it is also suitable for executing a program initialized with the following method steps: extracting features from the point cloud data of the pole tower, and classifying and segmenting the extracted feature vectors to obtain point cloud data of the insulator, including: inputting the point cloud data of the pole tower into a second preset model to extract a global feature vector; classifying the global feature vector to obtain a classified feature vector; fusing the deep feature vector and the low-level feature vector in the classified feature vector to obtain a fused feature vector; segmenting the fused feature vector to obtain point cloud data of the insulator.

When executed on a data processing device, it is also suitable for executing a program initialized with the following method steps: the above-mentioned coordinate information of the boom at least includes: the coordinate value of the head end of the boom and the coordinate value of the tail end of the boom, and the target distance between the boom and the target device is calculated based on the coordinate information of the boom and the coordinate information of the target device, including: calculating the length of the boom based on the coordinate value of the tail end of the boom and the coordinate value of the head end of the boom; calculating the first distance between the tail end of the boom and the target device based on the coordinate value of the tail end of the boom and the coordinate information of the target device; calculating the second distance between the head end of the boom and the target device based on the coordinate value of the head end of the boom and the coordinate information of the target device; calculating the target value based on the coordinate value of the head end of the boom, the coordinate value of the tail end of the boom and the coordinate information of the target device; calculating the target distance based on the length of the boom, the first distance, the second distance and the target value.

When executed on a data processing device, it is also suitable for executing an initialized program having the following method steps: after calculating the target distance between the boom and the target device based on the coordinate information of the boom and the coordinate information of the target device, the above method also includes: determining at least one safety distance of the target device based on the device type of the target device, wherein each safety distance corresponds to a different alarm level; when the target distance is less than the target safety distance in at least one safety distance, generating an alarm message based on the alarm level corresponding to the target safety distance; determining processing measures based on the alarm information and the alarm level, and controlling the target device and/or the crane to execute the processing measures.

Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

The present application is described with reference to the flowchart and/or block diagram of the method, device (system) and computer program product according to the embodiment of the present application. It should be understood that each process and/or box in the flowchart and/or block diagram, and the combination of the process and/or box in the flowchart and/or block diagram can be realized by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce a device for realizing the function specified in one process or multiple processes in the flowchart and/or one box or multiple boxes in the block diagram.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device that implements the functions specified in one or more processes in the flowchart and/or one or more boxes in the block diagram.

These computer program instructions may also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more processes in the flowchart and/or one or more boxes in the block diagram.

In a typical configuration, a computing device includes one or more processors (CPU), input/output interfaces, network interfaces, and memory.

The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and/or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims (10)

1. A method for detecting a distance, comprising:

determining a target model, wherein the target model is a three-dimensional digital twin model constructed according to first point cloud data of a transformer substation, and the transformer substation at least comprises a crane and at least one electrical device;

Acquiring coordinate information of a suspension arm of the crane and coordinate information of target equipment in the at least one electrical equipment through the target model according to a preset period;

and calculating the target distance between the suspension arm and the target equipment according to the coordinate information of the suspension arm and the coordinate information of the target equipment.

2. The method of claim 1, wherein determining the object model comprises:

scanning the transformer substation through a three-dimensional laser scanning technology to acquire first point cloud data of the transformer substation;

Deleting the ground point cloud data in the first point cloud data, and denoising the first point cloud data to obtain second point cloud data;

extracting third point cloud data of the at least one electrical device from the second point cloud data;

A positioning device is deployed at a preset position of the transformer substation, and positioning information of the at least one electrical device is obtained through communication with the positioning device;

And determining the target model according to the positioning information of the at least one electric device and the third point cloud data of the at least one electric device.

3. The method of claim 2, wherein deleting the ground point cloud data from the first point cloud data and denoising the first point cloud data to obtain second point cloud data comprises:

performing gridding processing on the first point cloud data, and calculating the ground height of each grid in the first point cloud data based on a probability statistics method;

Deleting the point cloud data lower than the ground height in the grids aiming at each grid in the first point cloud data, and deleting the point cloud data higher than the preset height in the grids to obtain fourth point cloud data;

Calculating a target distance between a target point and a neighborhood point in the fourth point cloud data based on Gaussian distribution;

And denoising the fourth point cloud data according to the target distance to obtain the second point cloud data.

4. The method of claim 2, wherein the device types in the at least one electrical device include at least: the power line, the pole tower and the insulator, the third point cloud data of the at least one electrical device is extracted from the second point cloud data, and the method comprises the following steps:

Classifying the second point cloud data through a first model to obtain fifth point cloud data and sixth point cloud data, wherein the fifth point cloud data is point cloud data belonging to the power line, the sixth point cloud data is point cloud data not belonging to the power line, and the first model is a model obtained by training a first preset model by adopting known power line point cloud data;

processing the fifth point cloud data through three-dimensional reconstruction and automatic point cloud tracking, and determining the point cloud data of each power line;

Clustering the sixth point cloud data through region growing, determining a target region where the tower is located, and determining the top point cloud data of the tower and the bottom point cloud data of the tower according to the point cloud data of the target region to obtain the point cloud data of the tower;

Extracting characteristics of the point cloud data of the pole tower, and classifying and dividing the extracted characteristic vectors to obtain the point cloud data of the insulator;

And determining third point cloud data of the target equipment according to the point cloud data of the power line, the point cloud data of the pole tower and the point cloud data of the insulator.

5. The method of claim 4, wherein processing the fifth point cloud data by three-dimensional reconstruction and point cloud automatic tracking to determine point cloud data for each power line comprises:

determining spatial features of the power line by performing three-dimensional reconstruction on the fifth point cloud data;

Determining wire information of the power line according to the spatial characteristics of the power line, and classifying the fifth point cloud data according to the wire information to obtain point cloud data of N types of power lines;

And tracking and clustering the point cloud data of the N types of power lines respectively through automatic point cloud tracking, and fitting the point cloud data of each power line through Hough transformation.

6. The method according to claim 4, wherein the feature extraction is performed on the point cloud data of the tower, and the classification processing and the segmentation processing are performed on the extracted feature vector, so as to obtain the point cloud data of the insulator, and the method comprises:

Inputting the point cloud data of the tower into a second preset model, and extracting a global feature vector;

classifying the global feature vector to obtain a classified feature vector;

Fusing a deep feature vector and a low-level feature vector in the classified feature vectors to obtain fused feature vectors;

and dividing the fused feature vectors to obtain the point cloud data of the insulator.

7. The method according to claim 1, characterized in that the coordinate information of the boom comprises at least: the calculating the target distance between the boom and the target device according to the coordinate information of the boom and the coordinate information of the target device comprises the following steps:

Calculating the length of the suspension arm according to the coordinate value of the tail end of the suspension arm and the coordinate value of the head end of the suspension arm;

calculating a first distance between the tail end of the suspension arm and the target equipment according to the coordinate value of the tail end of the suspension arm and the coordinate information of the target equipment;

Calculating a second distance between the boom head end and the target equipment according to the coordinate value of the boom head end and the coordinate information of the target equipment;

Calculating a target value according to the coordinate value of the boom head end, the coordinate value of the boom tail end and the coordinate information of the target equipment;

And calculating the target distance according to the length of the suspension arm, the first distance, the second distance and the target value.

8. The method of claim 1, wherein after calculating a target distance between the boom and the target device from the coordinate information of the boom and the coordinate information of the target device, the method further comprises:

Determining at least one safety distance of the target equipment according to the equipment type of the target equipment, wherein each safety distance corresponds to a different alarm level;

Generating alarm information according to an alarm level corresponding to the target safety distance under the condition that the target distance is smaller than the target safety distance in the at least one safety distance;

and determining a processing measure according to the alarm information and the alarm level, and controlling the target equipment and/or the crane to execute the processing measure.

9. A distance detecting device, comprising:

The first determining unit is used for determining a target model, wherein the target model is a three-dimensional digital twin model constructed according to first point cloud data of a transformer substation, and the transformer substation at least comprises a crane and at least one electrical device;

the acquisition unit is used for acquiring coordinate information of a suspension arm of the crane and coordinate information of target equipment in the at least one electrical equipment through the target model according to a preset period;

And the calculating unit is used for calculating the target distance between the suspension arm and the target equipment according to the coordinate information of the suspension arm and the coordinate information of the target equipment.

10. An electronic device comprising one or more processors and a memory for storing one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of detecting distance of any of claims 1-8.