Mining area locomotive positioning method, device, equipment and medium

Abstract

The invention provides a mining area locomotive positioning method, device and equipment and a medium, and the method comprises the steps: marking track position coordinate points switched by different operation scenes based on a constructed mining area electronic map, correspondingly setting a corresponding to-be-switched positioning strategy, and guiding and realizing locomotive operation scene confirmation and locomotive positioning strategy switching; the method comprises the following steps: determining a current track position coordinate point in real time according to an electronic map of a mining area, determining a to-be-operated scene of a locomotive and a corresponding to-be-switched positioning strategy when the locomotive runs to the operation scene to switch the track position coordinate point, and switching the locomotive positioning strategy to realize intelligent positioning of the locomotive. Based on a radar and a point cloud identification positioning strategy, identifying the position of a significant feature object for dynamically correcting the accumulated error of the odometer; wherein the positioning strategy comprises a GNSS positioning strategy of which an operation scene is a sky leakage area and an odometer positioning strategy of a satellite signal shielding area. According to the method provided by the invention, the equipment cost, the maintenance cost and the computing resources are reduced while the accuracy of system positioning is ensured.

Description

Technical Field

[0001] This invention relates to the field of locomotive positioning technology, and in particular to a method, device, equipment and medium for locomotive positioning in mining areas. Background Technology

[0002] Mining locomotives are specialized vehicles that transport ore and run on tracks. Locomotive positioning is crucial for the dispatching system. Currently, locomotive positioning mainly relies on RTK positioning, odometers, or trackside equipment. However, due to the diverse operational scenarios during the mining locomotive's cycle, such as overhead power lines, stations, tunnels, and loading areas, conventional single-method locomotive positioning is not suitable for mining locomotive positioning. Specific problems include: 1) RTK Positioning (Real-Time Kinematics, i.e., Real-Time Dynamic Carrier Phase Differential Measurement). Using RTK positioning technology requires at least two GNSS receivers: one as a base station, installed in an area with good BeiDou satellite signal, and the other as a rover, installed on the vehicle. Although RTK technology can achieve centimeter-level positioning accuracy, its effective range is only within 15 kilometers. To achieve full-range positioning, multiple base stations need to be deployed at fixed intervals along the line. This significantly increases costs when the railway line is long. Furthermore, satellite signals are interfered with when the locomotive is in tunnels, stations, or ore loading areas, severely affecting positioning accuracy.

[0003] 2) Onboard Odometer Positioning. As the locomotive wheels rotate, the sensor receives pulse signals. Since the number of pulses is fixed for one wheel rotation, the distance traveled by the locomotive wheels can be calculated using the number of pulses and the wheel circumference. However, due to factors such as locomotive wheel wear, wheel slippage, wheel spinning, and errors in wheel diameter parameters, odometer positioning suffers from cumulative errors. This error gradually accumulates as the locomotive travels further. Therefore, the locomotive needs to be corrected or the cumulative distance calculation restarted after traveling a certain distance to eliminate the accumulated error. Typically, trackside equipment is relied upon to eliminate cumulative errors, such as positioning transponders, which use the length information between adjacent transponders to correct the onboard odometer's distance measurement value. Additionally, track circuit insulation joints, in conjunction with the track section length, correct distance measurement errors. Although using an odometer can achieve relatively accurate positioning, when the locomotive is transporting a heavy load of ore, wheel slippage can easily occur during braking and traction, resulting in significant counting errors. Timely correction of the cumulative and counting errors of the odometer relies on a large number of trackside devices, which leads to a significant increase in installation and maintenance costs.

[0004] In view of this, there is an urgent need to provide a method for achieving more stable and accurate locomotive positioning by using different positioning strategies based on different operating scenarios. Summary of the Invention

[0005] To overcome the problems existing in the related technologies, this disclosure provides a method, device, equipment and medium for positioning locomotives in mining areas, so as to solve the technical problems in the related technologies.

[0006] This specification provides one or more embodiments of a method for positioning locomotives in a mining area, including the following steps: Based on the constructed electronic map of the mining area, the track position coordinates of different operation scenarios are marked, and corresponding positioning strategies to be switched are set to guide and realize the confirmation of locomotive operation scenarios and the switching of locomotive positioning strategies. The current track position coordinates are determined in real time based on the electronic map of the mining area. When the locomotive reaches the track position coordinates for the change of work scenario, the locomotive will be assigned to a different work scenario and the corresponding positioning strategy to be switched. The locomotive positioning strategy is then switched to achieve intelligent positioning of the locomotive. The location of significant features is identified based on radar and point cloud recognition positioning strategies to dynamically correct the cumulative error of the odometer. The positioning strategies include GNSS positioning strategy for work scenarios with exposed sky areas and odometer positioning strategy for work scenarios with satellite signal obstruction areas.

[0007] Furthermore, the construction of the electronic map of the mining area includes the following steps: Based on the correspondence between the GNSS coordinate information of each discrete GNSS point on the mining track and the track position, the Beidou fixed measurement points are determined, and an electronic map of the mining track is constructed based on the Beidou fixed measurement points. The coordinates of the first track position representing the switching of different operation scenarios are determined, as well as the corresponding positioning strategy to be switched. The coordinates of the first track position and the corresponding positioning strategy are marked on the electronic map of the mine track to guide and realize the confirmation of locomotive operation scenarios and locomotive positioning. Based on the point cloud data collected by lidar on the locomotive operation line, the corresponding feature categories and track position information are marked on the electronic map of the mining area, so as to associate each feature with its track position.

[0008] Furthermore, coded signs with high reflective stripes are installed as trackside features next to tracks without any features within a preset distance, ensuring that there is at least one feature every 2km of track; and the spacing between trackside features of the same type is greater than 2km.

[0009] Furthermore, the locomotive positioning and position correction steps based on the GNSS positioning strategy are as follows: Based on the coordinates of the GNSS point currently received by the locomotive, determine the two BeiDou positioning points closest to the GNSS point, use them as the two endpoints of a Glink, and form a Glink segment; Generate a circle with a preset radius centered on the GNSS point, and obtain the two intersection points of this circle with the Glink segment; Based on the orbital position coordinates of the two endpoints of the Glink segment and the coordinates of the GNSS point, the perpendicular intersection point from the GNSS point to the Glink segment and the corresponding perpendicular distance are calculated and determined. Based on the Pythagorean theorem, the distance between the perpendicular intersection point and the two intersection points is calculated and determined, thereby determining the distance from each of the two endpoints to the nearest intersection point. The track position values ​​of the two intersection points are determined based on the distances from the two endpoints to the nearest intersection point. Furthermore, the intersection point in the locomotive's direction of travel is determined as the locomotive's current positioning result on the track, based on the locomotive's direction of travel.

[0010] Furthermore, it also includes the following steps: When the operating scenario is an area with no sky, and the vehicle is stationary, after obtaining the initial positioning position using the GNSS positioning strategy, the odometer will then be used to maintain the positioning. During operation, the GNSS positioning result obtained by the GNSS positioning strategy is compared with the odometer positioning result. If the positioning deviation between the two is greater than a threshold, the GNSS positioning result of the vehicle is used as the current positioning result of the vehicle, thereby correcting the odometer positioning result.

[0011] Furthermore, The steps for implementing a radar and point cloud-based localization strategy to identify the location of significant features for dynamically correcting the cumulative error of high-speed transmission include: A target detection network is used to detect and identify features at locations with fixed or obvious characteristics in the orbital environment to determine their category and orbital location information; The distance from the locomotive to the center of the feature object is determined by the locomotive lidar, and the absolute position of the locomotive is determined by combining the track position information of the feature object, so as to correct the cumulative error of the odometer.

[0012] This specification provides one or more embodiments of a mining locomotive positioning device, comprising: The positioning strategy setting module is used to mark the track position coordinates of different operation scenarios based on the constructed electronic map of the mining area, and set the corresponding positioning strategy to be switched, which is used to guide and realize the confirmation of locomotive operation scenario and the switching of locomotive positioning strategy. The operation scenario and positioning strategy module is used to determine the current track position coordinates in real time during locomotive operation. Based on the electronic map of the mining area, when the locomotive reaches the track position coordinates for operation scenario switching, it determines the upcoming operation scenario and the corresponding positioning strategy to be switched, and switches to the corresponding positioning strategy to achieve intelligent positioning of the locomotive. It also uses radar and point cloud recognition positioning strategies to identify the positions of significant features to dynamically correct the cumulative error of the odometer. The positioning strategies include a GNSS positioning strategy for operation scenarios with exposed sky areas and an odometer positioning strategy for operation scenarios with satellite signal obstruction areas.

[0013] Furthermore, a GNSS positioning module is also set up for locomotive positioning and positioning position correction based on the GNSS positioning strategy; The GNSS positioning module is specifically configured to obtain the two closest BeiDou positioning points to the GNSS point based on the GNSS coordinates currently received by the locomotive, using these points as the two endpoints of a Glink segment. A circle with a preset radius is generated around the GNSS point, and the two intersection points of this circle with the Glink segment are determined. Based on the track position coordinates of the two endpoints of the Glink segment and the coordinates of the GNSS point, the perpendicular intersection point from the GNSS point to the Glink segment and its corresponding perpendicular distance are calculated. The distance between the perpendicular intersection point and the two intersection points is calculated using the Pythagorean theorem, thus determining the distances from each endpoint to the nearest intersection point. The track position values ​​of the two intersection points are then determined based on the distances from the two endpoints to the nearest intersection point. Finally, based on the locomotive's direction of travel, the intersection point in the locomotive's direction of travel is determined as the locomotive's current positioning result on the track.

[0014] This specification provides one or more embodiments of a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the mining locomotive positioning method as described in any of the preceding embodiments.

[0015] This specification provides one or more embodiments of a computer-readable storage medium storing a computer program that, when executed by a processor, implements the mining locomotive positioning method as described in any of the preceding embodiments.

[0016] The present disclosure provides a method, apparatus, equipment, and medium for positioning locomotives in mining areas. Its advantages lie in determining the switching points of different operational scenarios by marking track coordinates on an electronic map of the mining area to indicate these scenarios. A corresponding positioning strategy is then set to achieve a more accurate positioning strategy for switching to the corresponding operational scenario, enabling more precise positioning and error correction for the locomotive during operation. The method in this embodiment combines the advantages of sensors such as BeiDou, high-speed transmission, and lidar to achieve precise locomotive positioning in mining areas, improving the stability and accuracy of system positioning in operational scenarios such as tunnels, satellite signal obstruction areas, and ore loading areas. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in one or more embodiments of this specification or in the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments recorded in this specification. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 A flowchart illustrating a method for positioning locomotives in a mining area, provided for one or more embodiments of this specification; Figure 2 A GNSS positioning strategy scenario diagram provided for one or more embodiments of this specification; Figure 3 Example diagram illustrating locomotive positioning using the point cloud recognition and positioning strategy provided in one or more embodiments of this specification; Figure 4 A schematic diagram illustrating a locomotive operation scenario provided in one or more embodiments of this specification; Figure 5 A schematic diagram illustrating a second scenario of locomotive operation provided in one or more embodiments of this specification; Figure 6 A block diagram of a locomotive positioning device for a mining area provided for one or more embodiments of this specification; Figure 7 This is a schematic diagram of the structure of a computer device provided for one or more embodiments of this specification. Detailed Implementation

[0019] To enable those skilled in the art to better understand the technical solutions in one or more embodiments of this specification, the technical solutions in one or more embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this specification, and not all of the embodiments. Based on one or more embodiments of this specification, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of this invention.

[0020] Definitions: GNSS (Global Navigation Satellite System) is a system that provides users with global coverage, all-weather three-dimensional positioning and timing services through a space constellation composed of multiple satellites. As a basic positioning module, GNSS receives BeiDou satellite signals and combines them with Glink positioning tables (an electronic map composed of BeiDou positioning points) to achieve coarse-grained positioning of vehicles. The Glink calibration table can include an index, Glink length, Glink direction; starting point location (Link number, calibration point offset, calibration point geographic coordinates - longitude * 1e7, calibration point geographic coordinates - latitude * 1e7, calibration point geographic coordinates - altitude (cm)), ending point location (calibration point Link number, calibration point offset, calibration point geographic coordinates - longitude * 1e7, calibration point geographic coordinates - latitude * 1e7, calibration point geographic coordinates - altitude (cm)), etc.; the electronic map consists of multiple Excel tables (such as signal table, link table, logical section table, Glink table, etc.); saving these tables as .Fs binary files forms the electronic map.

[0021] LinkOffset: Use linkOffset to accurately represent the track position. For example, linkOffset=(54, 12800) means that it is located on link54 and the relative offset is 128m. The positioning result in this technology is this linkOffset.

[0022] Beidou fixed measurement points are used to represent the combined information of GNSS coordinates (latitude, longitude, altitude) and orbital position linkOffset. They are determined by human measurement and the electronic map of the mining area is constructed using Beidou fixed measurement points. The linkOffset distance between two adjacent Beidou fixed measurement points is similar to the planar distance of GNSS coordinates (error not greater than 1m). In this invention, it is fixed at 40m (the fixed measurement of the link endpoint is not limited by this distance).

[0023] The present invention will now be described in detail with reference to specific embodiments and accompanying drawings.

[0024] Method Implementation Examples According to embodiments of the present invention, a method for positioning locomotives in mining areas is provided, such as... Figure 1 The diagram shown is a flowchart of the locomotive positioning method in a mining area provided in this embodiment. The locomotive positioning method in a mining area according to this embodiment includes the following steps: Step S1: Based on the constructed electronic map of the mining area, mark the track position coordinates for switching between different operation scenarios, and set the corresponding positioning strategies to be switched, which are used to guide and realize the confirmation of locomotive operation scenarios and the switching of locomotive positioning strategies.

[0025] Step S2: Determine the current track position coordinates in real time based on the electronic map of the mining area. When the train reaches the track position coordinates for switching work scenarios, determine the work scenario to be performed by the locomotive and the corresponding positioning strategy to be switched. Switch to the corresponding locomotive positioning strategy to achieve intelligent locomotive positioning. Identify the positions of significant features based on radar and point cloud recognition positioning strategies to dynamically correct the cumulative error of the odometer. The positioning strategies include GNSS positioning strategy for work scenarios with exposed sky areas and odometer positioning strategy for work scenarios with satellite signal obstruction areas.

[0026] The locomotive positioning method provided in this embodiment addresses the various operational scenarios within a mining area, including open-pit sections, stations, tunnels, and loading areas. For example, in open-pit sections, where there is no obstruction and satellite signal strength is high, the locomotive uses a GNSS-based positioning method. However, in loading areas, tunnels, and stations where satellite signals are weak and locomotive speed is low and constant, an odometer-based positioning strategy is employed. Furthermore, radar and point cloud recognition strategies are used to identify fixed or prominent features in the track environment. The cumulative error of the speed transmission is corrected based on the precise location of these features on an electronic map. This allows for robust positioning without relying on a large number of trackside devices. The method eliminates and corrects cumulative errors in position holding and rapid transmission. Based on this, according to different operating scenarios, the track position coordinates of different operating scenario switching are marked on the electronic map of the mining area to determine the switching points of the operating scenarios, and the corresponding positioning strategy to be switched is set to achieve a more accurate positioning strategy when switching to the corresponding operating scenario, so as to achieve more accurate positioning and positioning error correction of the locomotive during operation. The method provided in this embodiment combines the advantages of Beidou, rapid transmission, lidar and other sensors to achieve accurate locomotive positioning in the mining area and improve the stability and accuracy of the system positioning of the locomotive in operating scenarios such as passing through tunnels, satellite signal blockage areas, and ore loading areas.

[0027] In this embodiment, the steps for constructing the electronic map of the mining area are as follows: Step 101: Determine the BeiDou positioning points based on the correspondence between the GNSS coordinate information of each discrete GNSS point on the mine track and the track position linkOffset, and construct an electronic map of the mine track based on the BeiDou positioning points; Step 102: Determine the first track position coordinates representing the switching of different operation scenarios, as well as the corresponding positioning strategy to be switched, and mark them on the electronic track map of the mining area to guide and realize the confirmation of locomotive operation scenarios and locomotive positioning.

[0028] Step 103: Based on the 156-line lidar with ROI function installed on the top of the locomotive, collect point cloud features (such as trackside signs, ore loading racks, etc.) on the locomotive's operating line, and mark the category and track position information of the corresponding features on the electronic map of the mining area to associate each feature with its track position (i.e., linkOffset value).

[0029] In this embodiment, for tracks without any features within 1km, coded signs with highly reflective stripes are installed beside the track as trackside features, ensuring that at least one feature exists every 2km. Features are assigned categories sequentially according to the track's logical ascending direction, and the distance between features of the same category is ensured to be greater than 2km, for example, using highly reflective coded signs. This prevents features from being too close together, which could lead to confusion between the positions of two features during identification, causing errors in feature position recognition and consequently, errors in locomotive position confirmation.

[0030] For example, suppose there are no obvious trackside features within 10km of the track starting from position 0km. If a coded sign A is placed between 0-2km (located at 1.8km), and this sign is placed again between 2-4km (located at 2km); Scenario 1: When the mine car has traveled 1.8km, the radar point cloud identifies the sign and corrects the car's position to the link offset corresponding to 1.8km based on the distance. Then, when the mine car has traveled 2.0km, the radar point cloud identifies the sign again. At this point, it is possible that the car's position has been shifted to the link offset corresponding to 1.8km, but in reality, the car's position should be at 2.0km. That is, the car's position has been shifted by 200m due to the sign. Scenario 2: If the sign at 1.8km is not recognized due to dirt, but the sign at 2.0km is recognized, the vehicle's position will be moved to the 1.8km position, but in reality, the mining truck is at the 2.0km position at this time; Therefore, when installing similar features on a line, in terms of feature utilization and safety, it is necessary to ensure that the spacing between the same features is longer to avoid problems caused by them being too close together.

[0031] In this embodiment, the locomotive positioning methods for different work scenarios are pre-marked on the electronic map. The locomotive queries and determines the coordinates of the scene switching location and the corresponding locomotive positioning strategy based on its current location (linkOffset). This enables intelligent switching of the corresponding positioning strategy for different work scenarios. After the positioning method is switched, the initial position of the locomotive in the corresponding work scenario uses the last updated positioning result of the previous work scenario, thereby achieving smooth and continuous positioning.

[0032] In this embodiment, GNSS-based positioning relies on an electronic map composed of BeiDou positioning points. In the electronic map, the latitude and longitude values ​​and the linkOffset value of each BeiDou positioning point correspond to and are related to each other. Therefore, the locomotive positioning and positioning position correction steps based on the GNSS positioning strategy are as follows: Step 210: Based on the coordinate values ​​of the GNSS point currently received by the locomotive, determine the two Beidou fixed measurement points closest to the GNSS point, and use them as the two endpoints of a Glink to form a Glink segment; wherein, the coordinate values ​​of the GNSS point are the latitude and longitude values ​​received by the GNSS receiver installed at the top of the locomotive.

[0033] In one embodiment, reference Figure 2 The diagram shown is a scenario diagram of the GNSS positioning strategy provided in this embodiment. Two adjacent BeiDou positioning points are the two endpoints of a Glink segment, GlinkA and GlinkB.

[0034] Step 211: Using the GNSS point as the center, preset the radius. Generate a circle, obtain the two intersection points of the circle and the Glink segment, and determine them as link1 / offset1 and link2 / offset2; refer to Figure 2 Based on the two intersection points inter1 and inter2 obtained, it can be determined that the current position of the locomotive is between track position link1 / offset1 and track position link2 / offset2.

[0035] Step 212: Based on the linkOffset values ​​(orbit position coordinates) of the endpoints GlinkA and GlinkB of the Glink segment, and the GNSS coordinates, calculate and determine the perpendicular intersection point from the GNSS point to the Glink segment and the corresponding perpendicular distance. Based on the Pythagorean theorem, calculate and determine the distance between the perpendicular intersection point and the two intersection points, thereby determining the distances from the endpoints GlinkA and GlinkB to the nearest intersection points. refer to Figure 2 Based on the GNSS point and the Glink segment formed by endpoints GlinkA and GlinkB, draw a perpendicular line to the Glink segment. The perpendicular intersection point of the GNSS point on the Glink segment can be calculated. Coordinates and distance and the endpoint GlinkA to the vertical intersection point distance and the perpendicular intersection point of endpoint GlinkB distance Then, according to the Pythagorean theorem, the nearest intersection point from endpoint GlinkA can be calculated based on the coordinates of endpoints GlinkA and GlinkB. inter Distance of 1 and the endpoint GlinkB to the nearest intersection inter Distance of 2 Specifically, it is calculated using the following formula: ; ; in, Let be the radius of the circle; Step 213: Determine the track position values ​​of the two intersection points based on the distances from the two endpoints to the nearest intersection point, and determine the current positioning result of the locomotive on the track based on the locomotive's direction of travel; That is, according to and The linkOffset values ​​of intersection points inter1 and inter2 can be determined, and based on the locomotive's direction of travel, the intersection point in the locomotive's direction of travel can be determined as the locomotive's current positioning result on the track (using linkOffset to represent the locomotive's positioning result). In this embodiment, since the GNSS receiver is installed above the front of the train, considering GNSS signal deviation, the actual position should be within the range of a circle with the received GNSS point as the center and a fixed distance as the radius. Therefore, if the train moves forward and the endpoint GlinkA is in front of the train, the linkOffset value of the intersection point inter1 closest to point A is needed to determine the train's current position.

[0036] The advantage of this embodiment in determining the locomotive's current position on the track using the above calculation method is that, since the error of the GNSS signal is between 0m and 5m (the faster the vehicle speed or the worse the satellite signal, the greater this error), the above GNSS positioning strategy can better tolerate the problem of Beidou satellite signal deviation (i.e., the deviation between the actual received GNSS latitude and longitude values ​​and the actual position).

[0037] When the operating scenario is an area with no sky, and the vehicle is stationary, after obtaining the initial positioning position using the GNSS positioning strategy, the odometer will then be used to maintain the positioning. During operation, the GNSS positioning result obtained by the GNSS positioning strategy is compared with the odometer positioning result. If the positioning deviation between the two is greater than a threshold, the GNSS positioning result of the vehicle is used as the current positioning result of the vehicle, thereby correcting the odometer positioning result.

[0038] In this preferred embodiment, when the operating scenario is an area with no clear sky and the vehicle is stationary, the specific process of realizing intelligent positioning and position correction of the locomotive based on the GNSS positioning strategy includes the following steps: Step 21: When the locomotive runs into the open sky area, the GNSS positioning strategy is used to determine the current position of the locomotive, and the odometer is used to track the position of the locomotive during its operation. Step 22: According to the preset time period, locate the locomotive based on the GNSS positioning strategy, and compare the positioning result (location information) with the odometer positioning result. If the position deviation exceeds the preset value, replace the odometer positioning result with the positioning result determined by the GNSS positioning strategy; if it does not exceed the preset value, continue to use the odometer to track the locomotive's position during operation.

[0039] In this embodiment, the specific positioning implementation process of the odometer positioning strategy is as follows: Based on the positioning and holding unit of the odometer, if the number of pulses received within the odometer measurement time T is n, then the locomotive's travel distance d within time T can be calculated according to the wheel radius r and the number of pulses N for one revolution, as shown in the following formula:

[0040] In one embodiment, assuming the locomotive's track position at the start of the odometer reading is link1 / offset1, then the logical direction is added to the travel distance. Then the current track position linkOffset of the locomotive can be obtained, thereby achieving locomotive positioning maintenance.

[0041] In this embodiment, the steps for dynamically correcting the cumulative error of the odometer by identifying the location of significant features based on radar and point cloud recognition and positioning strategies include: Step 310: Use a target detection network to detect and identify features at locations with fixed or obvious track environment characteristics to determine their category and track position information; Step 311: Determine the distance from the locomotive to the center of the feature object based on the locomotive lidar, and combine it with the track position information of the feature object to determine the absolute position of the locomotive, so as to correct the cumulative error of the odometer.

[0042] Furthermore, in this embodiment, the absolute position of the locomotive determined based on the above-mentioned point cloud recognition and positioning strategy can be used to correct the cumulative error of the odometer when the locomotive is running in a satellite signal obstruction area.

[0043] In one embodiment, the method of identifying the location of salient features based on radar and point cloud recognition and positioning strategies to dynamically correct the cumulative error of high-speed transmission specifically includes the following steps: Step 3110: Point cloud annotation and deep learning model training; collect and annotate point cloud frames within 200m of the feature object, annotate the 3D coordinates and category of the feature object, use the target detection module (such as the publicly available 3D target detection method PointPillar) as the point cloud feature object detector, and train the target detection module until the recognition rate of the feature object within the preset distance (such as 100m) reaches a stable level of more than 98%, then the trained target detection module is obtained.

[0044] Step 3120: Feature identification; Based on the 3D detection box and feature point cloud identified by the target detection module, the overlap rate of the two point clouds is calculated by semantic verification with the stored preset comparison feature point cloud through the point cloud similarity judgment method. If the overlap rate is greater than the preset threshold, the feature category is obtained.

[0045] The point cloud similarity judgment method in this embodiment can use the voxel mesh method to convert the point cloud into a voxel mesh for comparison to determine the voxel overlap rate.

[0046] Step 3130: Based on the current track position of the locomotive, use the electronic map of the mining area to find and determine the corresponding category of features and their track position information within a preset distance before and after the current track position; Step 3140: Determine the distance from the locomotive to the center of the feature object based on the locomotive lidar, and combine it with the track position information of the feature object to determine the absolute position of the locomotive, so as to correct the cumulative error of the odometer.

[0047] In a specific example, refer to Figure 3 The diagram shown is an example of locomotive positioning implemented using the point cloud recognition and positioning strategy provided in this embodiment. The specific steps for using a target detection network to detect and identify features at locations with fixed or obvious track environment characteristics to determine their category and track position information are as follows: Assume the locomotive is currently in the following position: The model detected features of category 10 and their 3D bounding boxes, and queried their current locations on the electronic map of the mining area. Within a preset track distance (e.g., 600m, the specific range is set according to the spacing of the features), the positions of the markers and their tracks that are consistent with this category are defined, and the corresponding positions are assumed to be as follows. Value. Specific examples. Figure 3 .

[0048] Combining the distance from the origin of the lidar coordinates (i.e., the current track position of the locomotive) to the center of the 3D detection frame By determining the locomotive's running direction, the locomotive track position can be obtained. The specific calculation method is as follows: ; And through the obtained locomotive track position Using the current track position of the locomotive, the cumulative error of the odometer is corrected. After correcting the current position of the locomotive, the speed transmission is recounted, thereby achieving robust locomotive positioning and eliminating and correcting the cumulative error of the locomotive speed transmission. In this way, without relying on trackside equipment such as transponders, the odometer error is accurately corrected by using onboard LiDAR to identify features, reducing dependence on trackside equipment and reducing equipment and maintenance costs.

[0049] In this embodiment, since there are multiple operating scenarios during the operation of locomotives in the mining area, the following describes the switching of locomotive positioning strategies and the implementation of locomotive positioning through specific scenario switching. Scenario 1: The work environment changes from an open-air area to a station area or tunnel area, and after leaving this scenario, the user will enter an open-air area; see reference. Figure 4 The image shown is a schematic diagram of a locomotive operation scenario provided in this embodiment. A1. Phase 1: Based on the electronic map of the mining area, when the locomotive approaches the station or tunnel entrance, the locomotive positioning method is switched from GNSS positioning strategy to odometer positioning strategy based on the set track position coordinates, and the locomotive positioning is maintained through the odometer. A2. Phase Two: When the locomotive enters the station or tunnel, the odometer continues to be used for positioning and positioning is achieved based on the point cloud recognition positioning strategy, thereby correcting the cumulative error of the odometer. A3. Phase 3: When the locomotive approaches the station or tunnel exit, the locomotive positioning method will switch from the odometer positioning strategy to the GNSS positioning strategy based on the coordinates of the switched track position. When the locomotive system receives the GNSS signal again and the GNSS signal is stable, the locomotive positioning method will switch to the positioning strategy.

[0050] Scenario 2: The work scenario changes from the open-pit area to the ore loading area, and the worker exits this scenario and then re-enters the open-pit area; see reference. Figure 5 The diagram shown is a schematic representation of scenario two of locomotive operation provided in this embodiment. B1, Phase 1: Based on the electronic map of the mining area, the locomotive approaches the loading operation area. Based on the set track switching position coordinates, the locomotive first switches to low constant speed mode. B2, Phase Two: After the target detection module identifies the gantry with category 1 at the entrance of the ore loading operation area and the point cloud, it can determine the position of the gantry and correct the cumulative error of the current locomotive speed transmission, determine the position of the locomotive, and switch the locomotive positioning method from GNSS positioning strategy to odometer positioning strategy, continue to use odometer for positioning maintenance, and realize train positioning in the ore loading operation area according to the point cloud recognition positioning strategy, and realize the correction of the cumulative error of odometer; B3. Phase 3: As the locomotive approaches the exit of the ore loading area, the locomotive positioning method will switch from the odometer positioning strategy to the GNSS positioning strategy based on the coordinates of the switched track position. Once the locomotive system receives the GNSS signal again and the GNSS signal is stable, the locomotive positioning method will switch to the positioning strategy.

[0051] The locomotive positioning method provided in this embodiment combines the advantages of Beidou, high-speed transmission, and lidar sensors to improve the accuracy of system positioning of locomotives in different scenarios (tunnels, satellite signal obstruction areas, and ore loading areas). Furthermore, by switching and cross-using various positioning strategies according to the locomotive's operating scenario, and without relying on trackside equipment such as transponders and RTK devices, the method uses onboard lidar to identify feature objects to accurately correct odometer errors. Compared with locomotive positioning methods that fuse multi-source information, this method reduces equipment costs, maintenance costs, and computing resources while ensuring the accuracy of system positioning.

[0052] Device Examples According to embodiments of the present invention, a locomotive positioning device for mining areas is provided, such as... Figure 6 The diagram shown is a block diagram of a mining locomotive positioning device provided in this embodiment. According to this embodiment of the invention, the mining locomotive positioning device includes: The positioning strategy setting module 10 is used to mark the track position coordinates of different operation scenarios based on the constructed electronic map of the mining area, and set the corresponding positioning strategy to be switched, so as to guide and realize the confirmation of locomotive operation scenario and the switching of locomotive positioning strategy.

[0053] The operation scenario and positioning strategy module 20 is used to determine the current track position coordinates in real time during locomotive operation. Based on the electronic map of the mining area, when the locomotive reaches the track position coordinates for operation scenario switching, it determines the operation scenario to be performed and the corresponding positioning strategy to be switched. It switches to the corresponding positioning strategy to achieve intelligent positioning of the locomotive. It also identifies the position of significant features based on radar and point cloud recognition positioning strategies to dynamically correct the cumulative error of the odometer. The positioning strategies include a GNSS positioning strategy for operation scenarios with exposed sky areas and an odometer positioning strategy for operation scenarios with satellite signal obstruction areas.

[0054] The mining locomotive positioning device provided in this embodiment determines the switching point of the operation scenario by marking the track position coordinates of different operation scenario switching on the electronic map of the mining area through the positioning strategy setting module 10, and sets the corresponding positioning strategy to be switched. The operation scenario and positioning strategy module 20 realizes the corresponding operation scenario switching to a more accurate positioning strategy, so that the locomotive can achieve more accurate positioning during operation. In addition, the positioning strategy of radar and point cloud recognition identifies fixed or obvious features in the track environment, and corrects the cumulative error of the speed transmission according to the precise position of the feature in the electronic map. In this way, the positioning is robustly maintained and the cumulative error of the speed transmission is eliminated and corrected without relying on a large number of trackside equipment. The method provided in this embodiment combines the advantages of Beidou, speed transmission, lidar and other sensors to achieve accurate positioning of mining locomotives and improve the stability and accuracy of system positioning when the locomotive passes through tunnels, satellite signal blockage areas, loading operation areas and other operation scenarios.

[0055] In this embodiment, an electronic map construction module for constructing an electronic map of the mining area is also provided, including a track electronic map construction unit, a first marker unit, and a second marker unit; The track electronic map construction unit determines the BeiDou positioning points based on the correspondence between the GNSS coordinate information of each discrete GNSS point on the track in the mining area and the track position linkOffset, and constructs the track electronic map of the mining area based on the BeiDou positioning points. The first marking unit is used to mark the first track position coordinates of different operation scenarios and the corresponding positioning strategy to be switched to the electronic map of the mine track, so as to guide and realize the confirmation of locomotive operation scenario and locomotive positioning.

[0056] The second marking unit is used to collect obvious features on the locomotive's operating line using a 156-line lidar with ROI function installed on the top of the locomotive, and to mark the category and track position information of the features on the electronic map of the mining area, so as to associate each feature with its track position.

[0057] In this embodiment, the locomotive positioning methods for different work scenarios are pre-marked on the electronic map. The locomotive queries and determines the coordinates of the scene switching location and the corresponding locomotive positioning strategy based on its current location (linkOffset). This enables intelligent switching of the corresponding positioning strategy for different work scenarios. After the positioning method is switched, the initial position of the locomotive in the corresponding work scenario uses the last updated positioning result of the previous work scenario, thereby achieving smooth and continuous positioning.

[0058] In this embodiment, GNSS-based positioning relies on an electronic map composed of BeiDou positioning points. In this electronic map, the latitude and longitude values ​​and the linkOffset value of each BeiDou positioning point correspond and are correlated. Therefore, this embodiment also includes a GNSS positioning module for locomotive positioning and position correction based on the GNSS positioning strategy. The specific configuration is as follows: Based on the GNSS coordinates currently received by the locomotive, the two BeiDou positioning points closest to the GNSS point are obtained and used as the two endpoints of a Glink, forming a Glink segment; with the GNSS point as the center, a preset radius is established. Generate a circle and determine the two intersection points of the circle and the Glink segment. Based on the track position coordinates of the two endpoints of the Glink segment and the coordinates of the GNSS point, calculate the perpendicular intersection point from the GNSS point to the Glink segment and the corresponding perpendicular distance. Then, based on the Pythagorean theorem, calculate the distance between the perpendicular intersection point and the two intersection points, thereby determining the distances from endpoints GlinkA and GlinkB to their nearest intersection points. Next, determine the track position values ​​of the two intersection points based on the distances from the two endpoints to their nearest intersection points. Based on the locomotive's direction of travel, the intersection point in the locomotive's direction of travel can be determined as the locomotive's current positioning result on the track. That is, according to and The intersection point can then be determined. inter 1 and intersection inter 2 of linkOffset The value can be used to determine the current track position of the locomotive based on its direction of travel.

[0059] The advantage of this embodiment in determining the locomotive's current position on the track using the aforementioned GNSS positioning module is that, since the error of the GNSS signal is between 0m and 5m (the faster the vehicle speed or the worse the satellite signal, the greater this error), the aforementioned GNSS positioning strategy can better tolerate the problem of BeiDou satellite signal deviation (i.e., the deviation between the actual received GNSS latitude and longitude values ​​and the actual position).

[0060] After obtaining the initial positioning position using a GNSS positioning module, an odometer will then be used to maintain the position. Simultaneously, the subsequently calculated GNSS positioning results will be used to verify the odometer positioning results; if the positioning deviation between the two exceeds a certain range, the odometer positioning result will be corrected.

[0061] The embodiments of the present invention are device embodiments corresponding to the above method embodiments. The specific operations of each module processing step can be understood with reference to the description of the method embodiments, and will not be repeated here.

[0062] like Figure 7As shown, the present invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the mining locomotive positioning method described in the above embodiments.

[0063] The present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the mining locomotive positioning method described in the above embodiments.

[0064] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0065] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, for apparatus or system embodiments, since they are basically similar to method embodiments, the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments. The apparatus and system embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0066] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features. These modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention, and the contents not described in detail in the specification of the present invention are well known to those skilled in the art.

Claims

1. A method of positioning a mine site vehicle, the method comprising: The method comprises the following steps: Based on the constructed mine area electronic map, mark the track position coordinate points of different operation scene switching, and set the corresponding to-be-switched positioning strategy, which is used to guide and realize the locomotive operation scene confirmation and the switching of the locomotive positioning strategy; According to the mine area electronic map, the current track position coordinate point is determined in real time. When running to the operation scene switching track position coordinate point, the operation scene of the locomotive to be operated and the corresponding to-be-switched positioning strategy are determined, and the positioning strategy of the locomotive is switched to realize the intelligent positioning of the locomotive, and the position of the significant feature object is determined based on the radar and the point cloud recognition positioning strategy to dynamically correct the cumulative error of the odometer; wherein the positioning strategy includes the GNSS positioning strategy of the operation scene of the mine area electronic map, and the odometer positioning strategy of the operation scene of the satellite signal shielding area.

2. The mine site vehicle positioning method of claim 1, wherein, The construction of the mine area electronic map comprises the following steps: Based on the corresponding relationship between the GNSS coordinate information of each discrete GNSS point of the mine area track and the track position, the Beidou surveying point is determined, and the mine area track electronic map is constructed based on the Beidou surveying point; Determine the first track position coordinate point representing the switching of different operation scenes, and the corresponding to-be-switched positioning strategy, and mark the first track position coordinate point and the corresponding positioning strategy to the mine area track electronic map, which is used to guide and realize the confirmation of the locomotive operation scene and the positioning of the locomotive; Based on the laser radar, the point cloud of the obvious feature object on the locomotive operation line is collected, the category and track position information of the corresponding feature object are marked on the mine area electronic map, and the association between each feature object and its track position is realized.

3. The mine site vehicle positioning method of claim 2, wherein, Further comprising the steps: Install a coding plate with high reflective strips as a trackside feature within a preset distance without feature objects, ensure that there is at least one feature object every 2km of track; and the setting interval distance between trackside feature objects of the same category is greater than 2km.

4. The mine location method of claim 1 wherein, The steps of the locomotive positioning based on the GNSS positioning strategy and the positioning position correction are as follows: According to the coordinate value of the GNSS point currently received by the locomotive, determine the two Beidou surveying points closest to the GNSS point as the two endpoints of a Glink, and form a Glink segment; Generate a circle with the GNSS point as the center and a preset radius, obtain the two intersection points of the circle and the Glink segment; Based on the track position coordinate values of the two endpoints of the Glink segment and the coordinate value of the GNSS point, calculate and determine the vertical intersection point of the GNSS point to the Glink segment and the corresponding vertical distance, and calculate the distance between the vertical intersection point and the two intersection points based on the Pythagorean theorem, so as to determine the distance from the two endpoints to the adjacent intersection points respectively; According to the obtained distance from the two endpoints to the adjacent intersection points, determine the track position values of the two intersection points respectively, and according to the direction of the locomotive, determine the intersection point in the direction of the locomotive as the positioning result of the locomotive on the track.

5. The mine location method of claim 1 wherein, Further comprising the steps: When the working scene is a leaky area, the vehicle is in a static state, and after the initial positioning position is obtained by using the GNSS positioning strategy, the odometer is used for positioning maintenance. During operation, the GNSS positioning result obtained by the GNSS positioning strategy is compared with the odometer positioning result. If the positioning deviation of the two is greater than a threshold value, the GNSS positioning result of the train is used as the current train positioning result to correct the odometer positioning result.

6. The mine location method of claim 1 wherein, The implementation steps of the radar and point cloud recognition positioning strategy for recognizing the position of a significant feature object for dynamically correcting the cumulative error of the speedometer include: The target detection network is used to detect and recognize the feature object at the position with fixed or obvious track environment features to determine the category and track position information of the feature object. The distance from the current locomotive to the center of the feature object is determined based on the locomotive laser radar, and the absolute position of the locomotive is determined in combination with the track position information of the feature object, so as to correct the cumulative error of the odometer.

7. A mine site vehicle positioning apparatus, characterized by, It includes: A positioning strategy setting module is configured to mark the track position coordinate points of different working scene switches based on the constructed mine area electronic map, and set the corresponding to-be-switched positioning strategy corresponding to the to-be-switched positioning strategy, so as to guide and realize the locomotive working scene confirmation and the switching of the locomotive positioning strategy. A working scene and positioning strategy module is configured to determine the current track position coordinate point in real time during the locomotive operation, and determine the working scene and the corresponding to-be-switched positioning strategy of the locomotive when running to the working scene switching track position coordinate point according to the mine area electronic map, so as to switch to the corresponding positioning strategy for realizing the intelligent positioning of the locomotive, and dynamically correct the cumulative error of the odometer based on the radar and point cloud recognition positioning strategy for recognizing the position of a significant feature object.

8. The mine vehicle positioning apparatus of claim 7 wherein, A GNSS positioning module is further configured for locomotive positioning and positioning position correction based on the GNSS positioning strategy. The GNSS positioning module is specifically configured to obtain two Beidou survey points closest to the GNSS point as two endpoints of a Glink based on the GNSS coordinate value currently received by the locomotive, and form a Glink segment. A circle with a preset radius is generated with the GNSS point as the center to determine two intersection points of the circle and the Glink segment, calculate and determine the vertical intersection point of the GNSS point to the Glink segment and the corresponding vertical distance based on the track position coordinate values of the two endpoints of the Glink segment and the coordinate value of the GNSS point, and determine the distance from the two endpoints to the adjacent intersection points based on the Pythagorean theorem, so as to determine the track position values of the two intersection points respectively according to the obtained distances from the two endpoints to the adjacent intersection points, and determine the intersection point in the direction of locomotive travel as the positioning result of the locomotive on the track according to the direction of locomotive travel.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The processor executes the computer program to realize the mine locomotive positioning method of any one of claims 1 to 6.

10. A computer-readable storage medium storing a computer program, the computer program comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1 to 9. The computer program is executed by the processor to realize the mine locomotive positioning method of any one of claims 1 to 6.

Images