A method and system for controlling unmanned electric locomotives for transporting ore underground in mines

Abstract

The present invention discloses an unmanned driving control method and system for an underground mine electric locomotive, comprising: obtaining underground tunnel structure data, generating a three-dimensional point cloud map, establishing a topological network based on track laying parameters, and marking each track segment with a unique code; calculating a safe operation data set of electric locomotives of different weights in each track segment in combination with the weight of the electric locomotive; calculating an optimal driving path based on a transport task instruction by using an A* algorithm combined with dynamic weights; obtaining the real-time three-dimensional position coordinates and operating posture data of the electric locomotive, retrieving the allowable speed and posture threshold of the corresponding weight in the safe operation data set, and determining the safety risk state by calculating the deviation coefficient; when triggering braking and deceleration, adopting different braking strategies according to the dynamic and static states of the obstacle, and applying to switch to a manual driving mode. The advantages of the present invention are: through path planning and safety risk determination, the safe and efficient operation of the electric locomotive in a complex mine tunnel is ensured, and countermeasures are taken when encountering abnormal situations.

Description

Technical Field

[0001] The present invention relates to unmanned driving control, and in particular to an unmanned driving control method and system for an underground mine electric locomotive. Background Art

[0002] With the development of automation technology, unmanned driving technology is gradually being applied to the control systems of electric locomotives in underground mines. This control method uses sensors, lidar, cameras, GPS, and other technologies to obtain real-time information about the mine's terrain and the locomotive's status. It then uses algorithms for path planning and obstacle detection, automatically controlling the locomotive's movement and parking, thus achieving unmanned driving.

[0003] Traditional methods currently available on the market rely on simple automatic control systems, often lacking in-depth analysis of the complex underground environment and track topology. This results in the system's inability to adapt in real time to dynamic factors such as track slope and curvature changes. These traditional methods often fail to account for the locomotive's weight and specific operating status, neglecting to calculate personalized safe operating parameters for each locomotive. Furthermore, existing systems lag in processing real-time data, unable to promptly obtain the locomotive's precise position and operating posture, resulting in insufficient early warning and emergency response to safety risks. Summary of the Invention

[0004] In order to improve the existing methods and systems, a method and system for unmanned control of electric locomotives for transporting ore underground in mines is provided. This method realizes unmanned control of electric locomotives underground in mines by using a dynamic model and A* algorithm through three-dimensional maps, track topology networks and real-time data of electric locomotives, ensuring safe operation and coping with obstacles and risks.

[0005] In order to achieve the above objects, the technical solution adopted by the present invention is:

[0006] A method for controlling an unmanned electric locomotive for transporting ore underground in a mine, comprising:

[0007] Obtain underground tunnel structure data, generate a 3D point cloud map, establish a topological network including track slope, curvature radius, and turnout location based on track laying parameters, and mark each track segment with a unique code;

[0008] Based on track topology network data and combined with locomotive weight, a dynamic model is used to calculate the maximum safe operating speed, allowable inclination angle threshold, and lateral acceleration threshold of locomotives of different weights on each track section, generating a safe operation data set.

[0009] Based on the transport mission instructions, the mission start point, destination point and cargo information are obtained. According to the real-time status of the track topology network, the optimal driving path is calculated using the A* algorithm combined with dynamic weights.

[0010] Obtain the real-time 3D position coordinates and running posture data of the electric locomotive, match the current track segment code according to the real-time position, retrieve the allowable speed and posture thresholds of the corresponding weight in the safe operation data set, and determine the safety risk status by calculating the deviation coefficient between the real-time speed and the safe speed, and the deviation coefficient between the real-time posture angle and the allowable posture angle;

[0011] Based on the safety risk status, braking and deceleration are triggered, and obstacles ahead are detected at the same time. Segmented deceleration braking is started for static obstacles, emergency braking instructions are triggered for dynamic obstacles, and an application is requested to switch to manual driving mode when an abnormality is detected.

[0012] Preferably, the acquisition of underground tunnel structure data, generation of a three-dimensional point cloud map, establishment of a topological network including track slope, curvature radius, and turnout location based on track laying parameters, and marking of unique codes for each track segment specifically include:

[0013] Use laser scanners to collect 3D data of underground tunnels and generate dense 3D point cloud data;

[0014] Obtain track slope, curvature radius, and turnout location parameters based on track laying parameters;

[0015] Divide the track into several segments based on track characteristics, and establish a topological relationship between the track segments based on the connection relationship between the track segments. Each track segment is associated with necessary attribute information, such as slope, curvature, and turnout;

[0016] Based on the information data of each track segment in the topological network, a unique code is assigned to each track segment.

[0017] Preferably, the generating of the safe operation data set comprises calculating the maximum safe operating speed, allowable inclination angle threshold, and lateral acceleration threshold of electric locomotives of different weights on each track section based on the track topology network data and in combination with the weight of the electric locomotive through a dynamic model. Specifically, the generating of the safe operation data set comprises:

[0018] Based on the constructed track topology network data and combined with the locomotive weight, a dynamic model is constructed, including the locomotive dynamic model and the track dynamic model;

[0019] Based on electric locomotives of different weights, operation simulations are performed separately to obtain simulation operation data;

[0020] Based on simulated operation data, the maximum safe operating speed is calculated in combination with track curvature and slope;

[0021] By calculating the tilt force between the vehicle and the track when the electric locomotive is running on the track, the maximum tilt angle at which the electric locomotive can safely travel is obtained as the allowable tilt angle threshold;

[0022] The maximum lateral acceleration that the electric locomotive can safely withstand is calculated as the lateral acceleration threshold;

[0023] Based on the maximum safe operating speed, allowable inclination angle threshold and lateral acceleration threshold of electric locomotives of different weights on different track sections obtained by simulation calculation, a safe operation data set is generated.

[0024] Preferably, the method of obtaining the mission start point, destination point and cargo information based on the transport mission instruction and calculating the optimal travel path by using the A* algorithm combined with dynamic weights according to the real-time status of the track topology network specifically includes:

[0025] Obtain the starting and ending location data, cargo weight information and transportation priority of the task based on the transportation task instructions;

[0026] Acquire the latest track topology network data in real time, and design heuristic functions and cost functions through the A* algorithm combined with dynamic weights;

[0027] The expansion order is determined by calculating the sum of the cost from the current node to the adjacent node and the heuristic function, and then the node expansion is performed;

[0028] During the path search process, the edge weights are dynamically updated based on the actual status of the track;

[0029] Obtain the shortest path based on the current heuristic function and cost function, and select the optimal driving mode for each track segment on the path;

[0030] Based on the calculated optimal path, the optimal driving path and the satisfaction of transportation requirements are output.

[0031] Preferably, the acquiring of the real-time three-dimensional position coordinates and running posture data of the electric locomotive, matching the current track segment code according to the real-time position, retrieving the allowable speed and posture threshold corresponding to the weight in the safe operation data set, and determining the safety risk state by calculating the deviation coefficient between the real-time speed and the safe speed and the deviation coefficient between the real-time posture angle and the allowable posture angle specifically includes:

[0032] The real-time three-dimensional position coordinates and running posture data of the electric locomotive running according to the optimal driving path are obtained through the positioning sensor device;

[0033] The track segment where the electric locomotive is located is obtained based on the real-time three-dimensional position coordinates of the electric locomotive, and the data information of the track segment is obtained through the unique code of the track segment;

[0034] Based on the safe operation data set, obtain the maximum allowable speed, inclination threshold, and lateral acceleration data of the electric locomotive at the current weight of the track section;

[0035] By comparing the real-time data of the electric locomotive with the allowable threshold in the safe operation data set, the deviation coefficient of the real-time operation status is calculated;

[0036] Based on the calculated deviation coefficient, the safety risk status of the electric locomotive is determined.

[0037] Preferably, the triggering of braking and deceleration based on the safety risk state, detecting obstacles ahead, initiating segmented deceleration braking for static obstacles, triggering emergency braking instructions for dynamic obstacles, and applying for switching to manual driving mode when abnormalities are detected specifically include:

[0038] Based on the determination that the electric locomotive is in a safety risk state, the braking and acceleration operations are triggered, and the obstacles ahead are detected by the laser radar;

[0039] Based on the detection results, if it is a static obstacle, the electric locomotive adopts a segmented deceleration and braking strategy, gradually decelerating in multiple stages based on the distance between the obstacle and the electric locomotive;

[0040] Based on the detection results, if it is a dynamic obstacle, the electric locomotive's automatic braking system will perform emergency braking and quickly decelerate to a stop state;

[0041] When an abnormal situation that cannot be handled by the electric locomotive occurs, an instruction to switch to manual driving mode is issued, the automatic driving system stops working, and the driver intervenes to control the operation of the electric locomotive.

[0042] Furthermore, an unmanned driving control system for an underground mine electric locomotive is proposed, comprising:

[0043] 3D data acquisition module: The 3D data acquisition module uses a laser scanner to obtain 3D data of underground tunnels and generate dense 3D point cloud maps, providing basic data for the construction of the track topology network;

[0044] Track topology network module: The track topology network module establishes a network containing the topological relationship of each track segment based on the track laying parameters, and marks it with a unique code to provide structural information of the underground track;

[0045] Simulation operation module: The simulation operation module combines the locomotive weight and track topology data, uses a dynamic model to calculate the safe operation parameters of locomotives of different weights on each track section, and generates a safe operation data set such as the maximum safe speed, allowable inclination angle, and lateral acceleration threshold;

[0046] Path planning module: Based on the transport task instructions and the real-time status of the track topology network, the path planning module uses the A* algorithm combined with dynamic weights to calculate the optimal driving path and output the matching status of the optimal path with the transport requirements;

[0047] Risk judgment module: The risk judgment module obtains the three-dimensional position and posture data of the electric locomotive in real time through the positioning sensor, matches the current track segment code, and determines the safety risk status of the electric locomotive;

[0048] Braking module: The braking module uses laser radar and other devices to detect obstacles in front, and executes segmented deceleration braking or emergency braking instructions based on the static or dynamic characteristics of the obstacles;

[0049] Processor: The processor is used to process the calculation process of each formula and the construction calculation process of each model.

[0050] Compared with the prior art, the advantages of the present invention are:

[0051] Based on the construction of a three-dimensional point cloud map and a track topology network, it is possible to accurately capture the structural information of the complex underground environment and provide reliable data support for the safe operation of electric locomotives. Through the use of dynamic models, the maximum safe speed, allowable tilt angle, lateral acceleration and other key parameters of electric locomotives of different weights in each track section can be dynamically calculated to ensure the stability and safety of the electric locomotive. The A* algorithm is used in combination with real-time track status for path planning, allowing the electric locomotive to optimize the driving path according to the actual transportation task and improve transportation efficiency. In addition, the operating status of the electric locomotive is monitored in real time, safety risks are judged in a timely manner, and detection systems such as lidar are used to accurately identify obstacles ahead. It can effectively take segmented deceleration or emergency braking measures to minimize accidents. When encountering an abnormality, the system can also automatically switch to manual driving mode to ensure emergency response capabilities in complex environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 A schematic diagram of the method proposed in the present invention;

[0053] Figure 2 This is a schematic diagram of the track topology network proposed by the present invention;

[0054] Figure 3 This is a schematic diagram of the safe operation data set proposed by the present invention;

[0055] Figure 4 This is a schematic diagram of the optimal driving path proposed by the present invention;

[0056] Figure 5 This is a schematic diagram of the security risk status determination proposed by the present invention;

[0057] Figure 6 This is a schematic diagram of the braking instruction proposed by the present invention. DETAILED DESCRIPTION

[0058] The following description is intended to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are merely examples, and those skilled in the art may conceive of other obvious variations.

[0059] An unmanned driving control system for an electric locomotive transporting ore in an underground mine, comprising:

[0060] 3D data acquisition module: The 3D data acquisition module uses a laser scanner to obtain 3D data of underground tunnels and generate dense 3D point cloud maps, providing basic data for the construction of the track topology network;

[0061] Track topology network module: The track topology network module establishes a network containing the topological relationship of each track segment based on the track laying parameters, and marks it with a unique code to provide structural information of the underground track;

[0062] Simulation operation module: The simulation operation module combines the locomotive weight and track topology data, uses a dynamic model to calculate the safe operation parameters of locomotives of different weights on each track section, and generates a safe operation data set such as the maximum safe speed, allowable inclination angle, and lateral acceleration threshold;

[0063] Path planning module: Based on the transport task instructions and the real-time status of the track topology network, the path planning module uses the A* algorithm combined with dynamic weights to calculate the optimal driving path and output the matching status of the optimal path with the transport requirements;

[0064] Risk judgment module: The risk judgment module obtains the three-dimensional position and posture data of the electric locomotive in real time through the positioning sensor, matches the current track segment code, and determines the safety risk status of the electric locomotive;

[0065] Braking module: The braking module uses laser radar to detect obstacles in front and executes segmented deceleration braking or emergency braking instructions according to the static or dynamic characteristics of the obstacles;

[0066] Processor: The processor is used to process the calculation process of each formula and the construction calculation process of each model.

[0067] See Figure 1 As shown, a method for controlling an unmanned electric locomotive for transporting ore underground in a mine comprises:

[0068] Step 1: Obtain underground tunnel structure data, generate a 3D point cloud map, establish a topological network including track slope, curvature radius, and turnout location based on track laying parameters, and mark each track segment with a unique code;

[0069] Step 2: Based on the track topology network data and the weight of the electric locomotive, a dynamic model is used to calculate the maximum safe operating speed, allowable inclination angle threshold, and lateral acceleration threshold of electric locomotives of different weights on each track section to generate a safe operation data set.

[0070] Step 3: Based on the transport mission instructions, the starting point, destination, and cargo information of the mission are obtained. Based on the real-time status of the track topology network, the optimal travel path is calculated using the A* algorithm combined with dynamic weights.

[0071] Step 4: Obtain the real-time 3D position coordinates and running posture data of the electric locomotive, match the current track segment code based on the real-time position, retrieve the allowable speed and posture thresholds for the corresponding weight in the safe operation data set, and determine the safety risk status by calculating the deviation coefficient between the real-time speed and the safe speed, and the deviation coefficient between the real-time posture angle and the allowable posture angle;

[0072] Step 5: Trigger braking and deceleration based on safety risk conditions, detect obstacles ahead at the same time, initiate segmented deceleration braking for static obstacles, trigger emergency braking commands for dynamic obstacles, and apply to switch to manual driving mode when abnormalities are detected.

[0073] See Figure 2 As shown, the underground tunnel structure data is obtained, a 3D point cloud map is generated, and a topological network including track slope, curvature radius, and turnout location is established based on the track laying parameters. The unique code of each track segment is marked. Specifically,

[0074] Use laser scanners to collect 3D data of underground tunnels and generate dense 3D point cloud data;

[0075] Obtain track slope, curvature radius, and turnout location parameters based on track laying parameters;

[0076] Divide the track into several segments based on track characteristics, and establish a topological relationship between the track segments based on the connection relationship between the track segments. Each track segment is associated with necessary attribute information, such as slope, curvature, and turnout;

[0077] Based on the information data of each track segment in the topological network, a unique code is assigned to each track segment.

[0078] Specifically, the track's geometric features are extracted from the 3D point cloud data. Based on the track's laying parameters, the slope, curvature radius, and location parameters of the turnouts are calculated. Based on the track's geometric variations, the track is divided into several segments, such as straight segments, curved segments, and ramp segments. The connections between the segments are analyzed to construct a topological graph. Topological relationships are defined based on the connection patterns, turnouts, and intersections between track segments. Each track segment has a connection relationship with its adjacent segments, represented as a graph.

[0079] Through the information of each track segment in the topological network, a unique code is assigned to each track segment. This code can not only distinguish different track segments, but also associate them with specific attributes.

[0080] See Figure 3 As shown in the figure, based on the track topology network data and the weight of the electric locomotive, the maximum safe operating speed, allowable inclination angle threshold, and lateral acceleration threshold of electric locomotives of different weights on each track section are calculated through a dynamic model. The generated safe operation data set specifically includes:

[0081] Based on the constructed track topology network data and combined with the locomotive weight, a dynamic model is constructed, including the locomotive dynamic model and the track dynamic model;

[0082] Based on electric locomotives of different weights, operation simulations are performed separately to obtain simulation operation data;

[0083] Based on simulated operation data, the maximum safe operating speed is calculated in combination with track curvature and slope;

[0084] By calculating the tilt force between the vehicle and the track when the electric locomotive is running on the track, the maximum tilt angle at which the electric locomotive can safely travel is obtained as the allowable tilt angle threshold;

[0085] The maximum lateral acceleration that the electric locomotive can safely withstand is calculated as the lateral acceleration threshold;

[0086] Based on the maximum safe operating speed, allowable inclination angle threshold and lateral acceleration threshold of electric locomotives of different weights on different track sections obtained by simulation calculation, a safe operation data set is generated.

[0087] Specifically, the locomotive's dynamic model describes its running state on the track, including its force analysis, acceleration, and speed changes. When the locomotive travels on a curved track, the centrifugal and lateral forces on the locomotive increase, affecting its driving stability. The gravity component exerted by the slope on the locomotive affects its acceleration and stability. The friction of the track itself creates resistance on the locomotive.

[0088] By modifying the locomotive's weight, the operation simulation under different working conditions is carried out to obtain the dynamic response of the locomotive on the track. During the simulation process, the relationship between the dynamic behavior of the locomotive and the geometric characteristics of the track can be considered to obtain the operation data under various conditions.

[0089] The maximum safe operating speed is limited by the curvature and slope of the track and the dynamic characteristics of the electric locomotive. The maximum safe speed is derived based on the lateral acceleration and centrifugal force. The formula is:

[0090] ;

[0091] in, is the maximum safe speed, Track curvature radius, is the slope, is the acceleration due to gravity, is the friction coefficient;

[0092] When a locomotive runs on a track, the presence of slope and curvature will generate a tilting force, which in turn affects the stability of the locomotive. By calculating the tilting force between the locomotive and the track, the maximum allowable tilt angle can be obtained.

[0093] When an electric locomotive travels on a curved track, it is subject to the lateral centrifugal force, the magnitude of which determines the maximum permissible lateral acceleration;

[0094] The calculation results of the maximum safe operating speed, allowable inclination angle threshold and lateral acceleration threshold of electric locomotives of different weights on different track sections are summarized to generate a complete safe operation data set.

[0095] See Figure 4 As shown in the figure, based on the transport task instructions, the task start point, end point and cargo information are obtained. According to the real-time status of the track topology network, the optimal driving path is calculated by the A* algorithm combined with dynamic weights. Specifically, it includes:

[0096] Obtain the starting and ending location data, cargo weight information and transportation priority of the task based on the transportation task instructions;

[0097] Acquire the latest track topology network data in real time, and design heuristic functions and cost functions through the A* algorithm combined with dynamic weights;

[0098] The expansion order is determined by calculating the sum of the cost from the current node to the adjacent node and the heuristic function, and then the node expansion is performed;

[0099] During the path search process, the edge weights are dynamically updated based on the actual status of the track;

[0100] Obtain the shortest path based on the current heuristic function and cost function, and select the optimal driving mode for each track segment on the path;

[0101] Based on the calculated optimal path, the optimal driving path and the satisfaction of transportation requirements are output.

[0102] Specifically, the A* algorithm determines the path search direction through a cost function and a heuristic function. The cost function represents the actual cost from the starting point to the current node, which usually includes:

[0103] The cost of running a track section is calculated based on factors such as slope, curvature, and length;

[0104] The impact of cargo weight on traction, the increased weight leads to increased driving costs;

[0105] The formula is:

[0106] ;

[0107] in, is the cost function, is the path cost from the starting point to the current node n, is the weight of the cargo, Costs related to the weight of the goods;

[0108] The heuristic function is the estimated cost from the current node to the target node, which provides the "direction" of the path search. The heuristic function can be designed based on the geometric distance between nodes in the track topology network;

[0109] The A* algorithm uses a comprehensive cost function to evaluate the priority of each node and determine the order of expansion. When the target node is added to the closed list, the path search terminates and the A* algorithm successfully finds the shortest path.

[0110] See Figure 5 As shown, the real-time 3D position coordinates and running posture data of the electric locomotive are obtained, the current track segment code is matched according to the real-time position, the allowable speed and posture threshold corresponding to the weight in the safe operation data set are retrieved, and the deviation coefficient between the real-time speed and the safe speed and the deviation coefficient between the real-time posture angle and the allowable posture angle are calculated to determine the safety risk status. Specifically, the following are included:

[0111] The real-time three-dimensional position coordinates and running posture data of the electric locomotive running according to the optimal driving path are obtained through the positioning sensor device;

[0112] The track segment where the electric locomotive is located is obtained based on the real-time three-dimensional position coordinates of the electric locomotive, and the data information of the track segment is obtained through the unique code of the track segment;

[0113] Based on the safe operation data set, obtain the maximum allowable speed, inclination threshold, and lateral acceleration data of the electric locomotive at the current weight of the track section;

[0114] By comparing the real-time data of the electric locomotive with the allowable threshold in the safe operation data set, the deviation coefficient of the real-time operation status is calculated;

[0115] Based on the calculated deviation coefficient, the safety risk status of the electric locomotive is determined.

[0116] Specifically, based on the real-time position coordinates of the electric locomotive, the track segment where the electric locomotive is located is first determined. Once the track segment where the electric locomotive is located is determined, the safe operation parameters of the track segment can be obtained from a pre-built safe operation data set. By comparing the real-time data of the electric locomotive with the allowable thresholds in the safe operation data set, the real-time operating state deviation coefficient of the electric locomotive can be calculated, including the real-time speed deviation coefficient, the real-time inclination deviation coefficient, and the real-time lateral acceleration deviation coefficient.

[0117] According to safety standards, a tolerance threshold for the deviation coefficient is set. If a deviation coefficient exceeds the predetermined safety threshold, the electric locomotive is considered to be in a high-risk state.

[0118] See Figure 6 As shown, based on the safety risk state, braking and deceleration are triggered, and obstacles ahead are detected. Segmented deceleration braking is initiated for static obstacles, emergency braking instructions are triggered for dynamic obstacles, and switching to manual driving mode is requested when an abnormality is detected. Specifically, the following are included:

[0119] Based on the determination that the electric locomotive is in a safety risk state, the braking and acceleration operations are triggered, and the obstacles ahead are detected by the laser radar;

[0120] Based on the detection results, if it is a static obstacle, the electric locomotive adopts a segmented deceleration and braking strategy, gradually decelerating in multiple stages based on the distance between the obstacle and the electric locomotive;

[0121] Based on the detection results, if it is a dynamic obstacle, the electric locomotive's automatic braking system will perform emergency braking and quickly decelerate to a stop state;

[0122] When an abnormal situation that cannot be handled by the electric locomotive occurs, an instruction to switch to manual driving mode is issued, the automatic driving system stops working, and the driver intervenes to control the operation of the electric locomotive.

[0123] Specifically, if a static obstacle is detected, the electric locomotive will adopt a segmented deceleration and braking strategy based on the distance to the obstacle. According to the distance to the obstacle, it is divided into multiple deceleration segments and adopts a progressive deceleration strategy. The formula is:

[0124] ;

[0125] in, is the braking speed at time t, is the current speed, is the deceleration coefficient, The deceleration time is the time during which the vehicle speed is gradually reduced until the locomotive comes to a complete stop.

[0126] If a dynamic obstacle is detected, the electric locomotive will perform emergency braking through the automatic braking system and quickly slow down to a stop;

[0127] If the electric locomotive encounters an abnormal situation that cannot be handled, the system will issue an instruction to switch to manual driving mode and stop the automatic driving system.

[0128] It should be noted that the order in which the embodiments of the present invention are described above is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. Furthermore, the foregoing descriptions of specific embodiments of this specification are provided. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order or sequential sequence shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0129] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

[0130] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for controlling an unmanned electric locomotive for transporting ore underground in a mine, characterized in that: include: Obtain underground tunnel structure data, generate a 3D point cloud map, establish a topological network including track slope, curvature radius, and turnout location based on track laying parameters, and mark each track segment with a unique code; Based on track topology network data and combined with locomotive weight, a dynamic model is used to calculate the maximum safe operating speed, allowable inclination angle threshold, and lateral acceleration threshold of locomotives of different weights on each track section, generating a safe operation data set. Based on the transport mission instructions, the mission start point, destination point and cargo information are obtained. According to the real-time status of the track topology network, the optimal driving path is calculated using the A* algorithm combined with dynamic weights. Obtain the real-time 3D position coordinates and running posture data of the electric locomotive, match the current track segment code according to the real-time position, retrieve the allowable speed and posture thresholds of the corresponding weight in the safe operation data set, and determine the safety risk status by calculating the deviation coefficient between the real-time speed and the safe speed, and the deviation coefficient between the real-time posture angle and the allowable posture angle; Based on the safety risk status, braking and deceleration are triggered, and obstacles ahead are detected at the same time. Segmented deceleration braking is started for static obstacles, emergency braking instructions are triggered for dynamic obstacles, and an application is requested to switch to manual driving mode when an abnormality is detected.

2. The unmanned driving control method for an underground mine electric locomotive according to claim 1, characterized in that: The acquisition of underground tunnel structure data, generation of a three-dimensional point cloud map, establishment of a topological network including track slope, curvature radius, and turnout location based on track laying parameters, and marking of unique codes for each track segment specifically include: Use laser scanners to collect 3D data of underground tunnels and generate dense 3D point cloud data; Obtain track slope, curvature radius, and turnout location parameters based on track laying parameters; Divide the track into several segments based on track characteristics, and establish a topological relationship between the track segments based on the connection relationship between the track segments. Each track segment is associated with attribute information. The track characteristics include slope, curvature, and turnouts. Based on the information data of each track segment in the topological network, a unique code is assigned to each track segment.

3. The unmanned driving control method for an underground mine electric locomotive according to claim 1, characterized in that: Based on the track topology network data and combined with the weight of the electric locomotive, the maximum safe operating speed, allowable inclination angle threshold, and lateral acceleration threshold of electric locomotives of different weights on each track section are calculated through a dynamic model to generate a safe operation data set. Specifically, the following steps are involved: Based on the constructed track topology network data and combined with the locomotive weight, a dynamic model is constructed, including the locomotive dynamic model and the track dynamic model; Based on electric locomotives of different weights, operation simulations are performed separately to obtain simulation operation data; Based on simulated operation data, the maximum safe operating speed is calculated in combination with track curvature and slope; By calculating the tilt force between the vehicle and the track when the electric locomotive is running on the track, the maximum tilt angle at which the electric locomotive can safely travel is obtained as the allowable tilt angle threshold; The maximum lateral acceleration that the electric locomotive can safely withstand is calculated as the lateral acceleration threshold; Based on the maximum safe operating speed, allowable inclination angle threshold and lateral acceleration threshold of electric locomotives of different weights on different track sections obtained by simulation calculation, a safe operation data set is generated.

4. The unmanned driving control method for an underground mine electric locomotive according to claim 1, characterized in that: The method of obtaining the mission start point, destination point and cargo information based on the transport mission instruction and calculating the optimal driving path by using the A* algorithm combined with dynamic weights according to the real-time status of the track topology network specifically includes: Obtain the starting and ending location data, cargo weight information and transportation priority of the task based on the transportation task instructions; Acquire the latest track topology network data in real time, and design heuristic functions and cost functions through the A* algorithm combined with dynamic weights; The expansion order is determined by calculating the sum of the cost from the current node to the adjacent node and the heuristic function, and then the node expansion is performed; During the path search process, the edge weights are dynamically updated based on the actual status of the track; Obtain the shortest path based on the current heuristic function and cost function, and select the optimal driving mode for each track segment on the path; Based on the calculated optimal path, the optimal driving path and the satisfaction of transportation requirements are output.

5. The unmanned driving control method for an underground mine electric locomotive according to claim 1, characterized in that: The method of obtaining the real-time three-dimensional position coordinates and running posture data of the electric locomotive, matching the current track segment code according to the real-time position, retrieving the allowable speed and posture threshold corresponding to the weight in the safe operation data set, and determining the safety risk status by calculating the deviation coefficient between the real-time speed and the safe speed and the deviation coefficient between the real-time posture angle and the allowable posture angle specifically includes: The real-time three-dimensional position coordinates and running posture data of the electric locomotive running according to the optimal driving path are obtained through the positioning sensor device; The track segment where the electric locomotive is located is obtained based on the real-time three-dimensional position coordinates of the electric locomotive, and the data information of the track segment is obtained through the unique code of the track segment; Based on the safe operation data set, obtain the maximum allowable speed, inclination threshold, and lateral acceleration data of the electric locomotive at the current weight of the track section; By comparing the real-time data of the electric locomotive with the allowable threshold in the safe operation data set, the deviation coefficient of the real-time operation status is calculated; Based on the calculated deviation coefficient, the safety risk status of the electric locomotive is determined.

6. The unmanned driving control method for an underground mine electric locomotive according to claim 1, characterized in that: The triggering of braking and deceleration based on the safety risk state, detecting obstacles ahead, initiating segmented deceleration braking for static obstacles, triggering emergency braking instructions for dynamic obstacles, and applying for switching to manual driving mode when abnormalities are detected specifically include: Based on the determination that the electric locomotive is in a safety risk state, the braking and acceleration operations are triggered, and the obstacles ahead are detected by the laser radar; Based on the detection results, if it is a static obstacle, the electric locomotive adopts a segmented deceleration and braking strategy, gradually decelerating in multiple stages based on the distance between the obstacle and the electric locomotive; Based on the detection results, if it is a dynamic obstacle, the electric locomotive's automatic braking system will perform emergency braking and quickly decelerate to a stop state; When an abnormal situation that cannot be handled by the electric locomotive occurs, an instruction to switch to manual driving mode is issued, the automatic driving system stops working, and the driver intervenes to control the operation of the electric locomotive.

7. An unmanned driving control system for an electric locomotive transporting ore in an underground mine, used to implement an unmanned driving control method for an electric locomotive transporting ore in an underground mine according to any one of claims 1 to 6, characterized in that: include: 3D data acquisition module: The 3D data acquisition module uses a laser scanner to obtain 3D data of underground tunnels and generate dense 3D point cloud maps, providing basic data for the construction of the track topology network; Track topology network module: The track topology network module establishes a network containing the topological relationship of each track segment based on the track laying parameters, and marks it with a unique code to provide structural information of the underground track; Simulation operation module: The simulation operation module combines the locomotive weight and track topology data, uses a dynamic model to calculate the safe operation parameters of locomotives of different weights on each track section, and generates a safe operation data set such as the maximum safe speed, allowable inclination angle, and lateral acceleration threshold; Path planning module: Based on the transport task instructions and the real-time status of the track topology network, the path planning module uses the A* algorithm combined with dynamic weights to calculate the optimal driving path and output the matching status of the optimal path with the transport requirements; Risk judgment module: The risk judgment module obtains the three-dimensional position and posture data of the electric locomotive in real time through the positioning sensor, matches the current track segment code, and determines the safety risk status of the electric locomotive; Braking module: The braking module uses laser radar and other devices to detect obstacles in front, and executes segmented deceleration braking or emergency braking instructions based on the static or dynamic characteristics of the obstacles; Processor: The processor is used to process the calculation process of each formula and the construction calculation process of each model.

Images