Unmanned intelligent control system for mine electric locomotive

Abstract

The invention relates to the field of intelligent control, and discloses an intelligent control system for unmanned driving of a mine electric locomotive, and the system comprises an environment sensing module which is used for collecting mine environment information, and generating a real-time environment model through a multi-sensor fusion technology; the positioning navigation module is connected with the environment sensing module and is used for performing path planning and dynamic path optimization according to the real-time environment model; the vehicle control module is connected with the positioning navigation module and the environment sensing module, and is used for controlling the operation of the electric locomotive and executing obstacle avoidance and dynamic adjustment operation; and the communication interface module is connected with the environment sensing module, the positioning navigation module and the vehicle control module. And global path planning is carried out by utilizing a weighted graph model through the positioning navigation module, and the path is optimized in real time by combining a dynamic planning method, so that the path can be dynamically adjusted to adapt to temporary changes of a mine environment, and the electric locomotive is ensured to always efficiently and safely reach a target position.

Description

Technical Field

[0001] The invention relates to the technical field of intelligent control, and in particular to an unmanned intelligent control system for a mine electric locomotive. Background Art

[0002] Mine electric locomotives are an important part of the mine transportation system, and their operating efficiency and reliability have a direct impact on the safety and economy of mine operations. In traditional technologies, the operation of mine electric locomotives mainly relies on manual operation or semi-automatic control. In recent years, with the development of intelligent mines, some automated electric locomotive systems have gradually introduced sensor-based navigation and obstacle detection functions, such as using lidar or cameras to identify mine paths and combining track markings to achieve positioning. However, these technologies are usually limited to specific operating environments, such as fixed track transportation, or more regular mine tunnel structures. On this basis, some path planning and obstacle detection algorithms have also been applied to mine scenarios to improve the autonomy and operating efficiency of electric locomotives.

[0003] Although the existing mine locomotive automation system has alleviated the complexity of manual operation to a certain extent, it still has great limitations when facing the complexity and variability of the mine environment. For example, many systems rely on fixed path planning algorithms and have difficulty coping with dynamic changes in the mine environment, such as sudden equipment obstacles, personnel movement or path blockages.

[0004] In addition, existing obstacle detection and avoidance methods usually rely on simple rule-based algorithms or single sensors, which makes it difficult to strike a balance between real-time performance and accuracy. Especially when facing moving obstacles or multiple obstacle scenarios, the system is prone to obstacle avoidance failure or path replanning delays. At the same time, due to the narrow space, insufficient lighting conditions and strong signal interference in mines, the existing system still has deficiencies in the robustness of environmental perception and the accuracy of path execution. Summary of the invention

[0005] In view of the deficiencies in the prior art, the present invention provides an intelligent control system for an unmanned mine electric locomotive, which solves the problem that mine electric locomotives are difficult to efficiently plan paths, dynamically avoid obstacles and perform real-time control in a complex and changeable mine environment.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: an intelligent control system for unmanned mine electric locomotives, comprising: Environmental perception module, which is used to collect mine environmental information and generate real-time environmental models through multi-sensor fusion technology; A positioning and navigation module, which is connected to the environment perception module and is used for performing path planning and dynamic path optimization according to a real-time environment model; A vehicle control module, which is connected to the positioning navigation module and the environment perception module, and is used to control the operation of the electric locomotive and perform obstacle avoidance and dynamic adjustment operations; The communication interface module is connected with the environment perception module, the positioning navigation module and the vehicle control module to realize data transmission, remote operation and status monitoring.

[0007] Preferably, the environment perception module includes: A variety of sensors, including lidar, ultrasonic sensors, cameras and inertial navigation units, to collect data about the mine environment; The mine environment data includes but is not limited to obstacle information, mine operating equipment status, personnel distribution information, ventilation and gas distribution, temperature and humidity information, and lighting and visibility; The data fusion unit fuses the sensor data through extended Kalman filtering. The filtering process includes: The state prediction stage predicts the vehicle state based on the known system dynamic model; The observation update phase updates the state based on the measured data and satisfies the following formula:

[0008]

[0009] in, is the state vector, is the control input, is the observed value, and For noise.

[0010] Preferably, the positioning and navigation module includes: A path planning unit, which uses a graph search algorithm to generate the optimal path from the starting point to the target point based on the mine terrain data; The mine topographic data includes, but is not limited to: walls and support structures, fixed facilities and track conditions; The dynamic path optimization unit optimizes the path cost by dynamic programming method. The goal is to minimize the total path cost of the vehicle from the starting point to the end point, where the path cost is determined by the combined influence of the current position and control input, expressed as:

[0011] in, represents the path cost, is the penalty factor, Represents the path continuity error.

[0012] Preferably, the vehicle control module comprises: An obstacle avoidance control unit generates an obstacle avoidance path by calculating the attraction and repulsion between the vehicle's running target and the obstacle, wherein: The attraction forces the vehicle to approach the target point, and its force is proportional to the distance between the vehicle's current position and the target point; The repulsive force keeps the vehicle away from obstacles. Its strength is inversely proportional to the distance between the vehicle and the obstacle. When the distance is less than the safe range, the repulsive force increases rapidly, as shown in the following:

[0013] in, is the total potential field function, is the attractive potential field function, is the repulsive potential field function, the attractive potential field and the repulsive potential field are defined as:

[0014]

[0015] in, is the target point position, is the obstacle position, is the proportionality coefficient of the attractive potential field, is the proportionality coefficient of the repulsive potential field, is the range of the repulsive potential field, indicating the safe distance of obstacles, is the Euclidean distance between the vehicle’s current position and the target point’s position, is the Euclidean distance between the vehicle’s current position and the obstacle’s position; The dynamic adjustment unit optimizes the vehicle operating parameters in real time based on the prediction model so that the vehicle's operating trajectory conforms to the target path while meeting the requirements of stability and energy consumption optimization.

[0016] Preferably, the communication interface module includes: Data transmission unit, which uses wireless communication technologies, including 5G and industrial protocols, to ensure real-time transmission of environmental data and vehicle operation data; Remote operation unit, which can remotely issue task instructions through cloud server; The status monitoring unit is used to transmit the vehicle position, speed, running path and obstacle information to the remote monitoring platform in real time.

[0017] Preferably, the environment model generated by the environment perception module includes a three-dimensional map and obstacle distribution information, and the resolution of the map can be dynamically adjusted according to the needs of mine operations.

[0018] Preferably, the positioning and navigation module supports dynamic learning of path planning and obstacle avoidance algorithms, and optimizes algorithm performance through historical data of mine operations.

[0019] Preferably, the dynamic adjustment unit in the vehicle control module is capable of coordinating multiple optimization objectives, including maximizing operating efficiency and minimizing energy consumption.

[0020] Preferably, the communication interface module supports task priority scheduling, can automatically allocate computing resources according to the urgency of the task, and give priority to processing critical task instructions.

[0021] Preferably, the system is designed in a modular manner, each module operates independently and works in coordination through a communication interface module, supporting functional expansion and independent upgrading.

[0022] The present invention provides an intelligent control system for unmanned mine electric locomotives. It has the following beneficial effects: 1. The present invention uses a positioning and navigation module, utilizes a weighted graph model to perform global path planning, and combines a dynamic programming method to optimize the path in real time, thereby being able to dynamically adjust the path to adapt to temporary changes in the mine environment, ensuring that the electric locomotive can always reach the target location efficiently and safely.

[0023] 2. The artificial potential field method and model predictive control technology of the present invention realize the organic combination of dynamic obstacle avoidance and real-time vehicle adjustment, thereby generating an obstacle avoidance path in real time. At the same time, future state prediction dynamically optimizes the speed and direction of the vehicle, thereby ensuring smooth operation in complex mine environments.

[0024] 3. Through efficient collaboration between modules, the present invention maintains stable operation in harsh conditions such as narrow space, low light and high noise interference. Its environmental perception module dynamically generates high-resolution three-dimensional maps, and the vehicle control module accurately avoids obstacles and optimizes path execution. It can be widely used in various mine operation scenarios, including material transportation, equipment inspection and dynamic monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 It is a schematic diagram of the system module of the present invention; Figure 2 This is a schematic diagram of an environment perception module of the present invention; Figure 3 This is a schematic diagram of a positioning and navigation module of the present invention; Figure 4 is a schematic diagram of a vehicle control module of the present invention; Figure 5 It is a schematic diagram of the communication interface module of the present invention. DETAILED DESCRIPTION

[0026] The following will be combined with the drawings in the specification of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0027] Please see attached Figure 1 The embodiment of the present invention provides an intelligent control system for unmanned driving of a mine electric locomotive, comprising: Environmental perception module, which is used to collect mine environmental information and generate real-time environmental models through multi-sensor fusion technology; The positioning and navigation module is connected to the environment perception module and is used for path planning and dynamic path optimization based on the real-time environment model; The vehicle control module is connected to the positioning navigation module and the environment perception module to control the operation of the electric locomotive and perform obstacle avoidance and dynamic adjustment operations; A communication interface module, which is connected to the environment perception module, the positioning navigation module and the vehicle control module, and is used to realize data transmission, remote operation and status monitoring; Specifically, the system adopts modular design, each module operates independently, and works together through communication interface modules to support function expansion and independent upgrades.

[0028] The environmental perception module is responsible for providing real-time data of the mine environment and providing the necessary input basis for other modules. Through devices such as lidar, cameras, ultrasonic sensors and inertial navigation units (IMUs), it collects three-dimensional structural information, obstacle distribution and vehicle posture in the environment.

[0029] Specifically, lidar is used to generate a three-dimensional point cloud model of the mine and identify tunnel walls and supporting structures; cameras collect image data to identify landmarks, path features and obstacle types in the mine; ultrasonic sensors detect close obstacles around the vehicle; and IMU provides the vehicle's acceleration and angular velocity information for posture correction and positioning.

[0030] As an option, the environment perception module uses the extended Kalman filter (EKF) algorithm to fuse multi-sensor data and generate a real-time environment model. In this implementation, the system performs state prediction and observation updates through the following formula:

[0031]

[0032] In this way, the fused environmental data provides high-precision input for path planning.

[0033] The positioning and navigation module completes path planning and dynamic optimization based on the three-dimensional environment model provided by the environmental perception module. As a possible implementation method, the positioning and navigation module uses a path search algorithm to find the optimal path in the weighted graph model of the mine. It should be noted that the path planning algorithm uses a weighted graph G=(V,E) to represent the mine terrain, where V is the set of path nodes, E is the set of path edges, and the weight of the edge represents the cost of the path. In optimal path planning, the goal is to minimize the path cost:

[0034] in, is a sequence of path points, is the path cost.

[0035] Specifically, after the path planning result is generated, the positioning and navigation module also optimizes the path in real time through dynamic planning. In one possible implementation, the optimization goal is to minimize the total path cost and the continuity error of the vehicle's running trajectory:

[0036] The vehicle control module receives path instructions from the positioning and navigation module, and implements dynamic obstacle avoidance and real-time adjustment of vehicle operation based on obstacle information from the environmental perception module.

[0037] Exemplarily, the obstacle avoidance control unit uses an artificial potential field method (APF) to calculate the direction of the resultant force between the vehicle, the target point, and the obstacle. As an implementation method, the potential field function includes an attractive potential field and a repulsive potential field:

[0038] In this way, the attractive potential field guides the vehicle to the target position, and its strength is proportional to the distance between the vehicle's current position and the target point position:

[0039] The repulsive potential field is used to prevent the vehicle from approaching an obstacle. When the distance between the vehicle and the obstacle is less than the predetermined safety distance, its force increases rapidly:

[0040] And in vehicle dynamic adjustment, model predictive control (MPC) further optimizes vehicle speed and direction. The objective function is:

[0041] In this way, through dynamic adjustments, the vehicle can follow the target path efficiently and safely.

[0042] The communication interface module runs through the operation of the above modules and is responsible for data transmission and remote operation. Specifically: The data transmission unit uses 5G or industrial wireless communication protocols to ensure that environmental perception data and path planning results can be shared to the remote monitoring platform in real time; The remote operation unit supports operators to adjust mission parameters or directly intervene in vehicle operation through the cloud control system.

[0043] In some embodiments, the communication interface module also transmits the operating status of the vehicle, including position, speed, and path information, through the status monitoring unit to ensure stable operation of the system without human intervention.

[0044] Please see attached Figure 2 , the environment perception module includes: A variety of sensors, including lidar, ultrasonic sensors, cameras and inertial navigation units, to collect data about the mine environment; Mine environment data includes but is not limited to obstacle information, mine operating equipment status, personnel distribution information, ventilation and gas distribution, temperature and humidity information, and lighting and visibility; The data fusion unit fuses the sensor data through extended Kalman filtering. The filtering process includes: The state prediction stage predicts the vehicle state based on the known system dynamic model; The observation update phase updates the state based on the measured data and satisfies the following formula:

[0045]

[0046] in, is the state vector, is the control input, is the observed value, and for noise; The environmental model generated by the environmental perception module includes a three-dimensional map and obstacle distribution information. The resolution of the map can be dynamically adjusted according to the needs of mine operations.

[0047] Specifically, in this embodiment, the environment perception module includes the following parts: First, a sensor component. As an exemplary implementation, the sensor configuration in the environment perception module is as follows: LiDAR: Used to scan the three-dimensional structure of mine tunnels, generate point cloud data, and identify the spatial positions of tunnel walls, supporting structures, and obstacles.

[0048] Camera: used to collect mine images, identify ground signs, path features, and types of obstacles (such as mine equipment, pedestrians, etc.).

[0049] Ultrasonic sensor: used to detect the position and distance of close-range obstacles, suitable for safe distance perception around the vehicle.

[0050] Inertial Navigation Unit (IMU): Provides vehicle attitude information by measuring acceleration and angular velocity, providing a basis for estimation and compensation of motion state.

[0051] Specifically, the data collection frequency and resolution of different sensors can be adjusted according to the actual situation of the mine. For example, the scanning frequency of the lidar can be set to 10Hz for dynamic perception of moving obstacles; the image resolution of the camera can be optimized according to the lighting conditions to improve the accuracy of visual recognition.

[0052] The second is the data fusion unit. In order to eliminate the noise and error in the single sensor data, the environmental perception module uses the extended Kalman filter (EKF) algorithm to realize the fusion processing of multi-sensor data.

[0053] Status prediction: Predict the state at the next moment based on the vehicle's motion model:

[0054] in, is the state vector at the current moment, including position, velocity, and acceleration, is the control input at the previous moment, is the motion model of the system, which is used to describe the running characteristics of the vehicle on the mine track. is the process noise, which represents the uncertainty of the model.

[0055] Observation Update: Update the system status using the sensor's measurement data:

[0056] In a possible implementation, the data fusion unit aligns the sampled data of each sensor through a time synchronization mechanism and inputs the data into a fusion algorithm, thereby generating a consistent environment model.

[0057] Meanwhile, in some embodiments, the three-dimensional environment model generated by the environment perception module includes the following contents: 3D structural information of the tunnel: shape, width, height, slope and branch structure of the tunnel; The location and attributes of obstacles: including the spatial coordinates, size, shape and motion state of obstacles; Dynamic environmental data: such as pedestrian distribution, movement trajectory of mining equipment, etc.

[0058] As an option, the generated environment model can be represented by gridding and output in the form of an occupancy grid map for input to the path planning module. In a dynamic and complex mine environment, the environment perception module can update the environment model in real time to ensure the overall operation safety of the system.

[0059] Furthermore, in some implementations, the environmental perception module combines historical environmental data for dynamic optimization. For example, using the probability map method, the environmental data from multiple runs is fused to generate a three-dimensional map with higher confidence. This method can effectively reduce sensor errors and further improve the robustness of the perception module.

[0060] It should be noted that the design of this module supports scalability. For example, according to the specific application requirements of the mine, gas sensors can be added to monitor the concentration of harmful gases in the mine; or thermal imaging equipment can be added to identify heat sources or hidden danger areas.

[0061] Through the above description, it can be understood that the environment perception module realizes high-precision perception and real-time modeling of the mine environment through multi-sensor collaboration and data fusion technology, ensuring the operational safety and adaptability of the system. Combined with specific formulas and algorithms, those skilled in the art can reproduce the functions of the environment perception module based on the disclosure of the present invention.

[0062] Please see attached Figure 3 , the positioning and navigation module includes: A path planning unit, which uses a graph search algorithm to generate the optimal path from the starting point to the target point based on the mine terrain data; Mine topographic data includes, but is not limited to: condition of walls and support structures, fixtures and tracks; The dynamic path optimization unit optimizes the path cost by dynamic programming method. The goal is to minimize the total path cost of the vehicle from the starting point to the end point, where the path cost is determined by the combined influence of the current position and control input, expressed as:

[0063] in, represents the path cost, is the penalty factor, represents the path continuity error; The positioning and navigation module supports dynamic learning of path planning and obstacle avoidance algorithms, and optimizes algorithm performance through historical data of mine operations.

[0064] Specifically, the positioning and navigation module is an important component of the unmanned intelligent control system of the mine electric locomotive of the present invention. Its function is to use the three-dimensional environmental model and vehicle status information provided by the environmental perception module to complete path planning and dynamic path optimization to ensure that the electric locomotive can reach the target position safely and efficiently in a complex mine environment. It should be noted that this module can not only process the static characteristics of the mine environment (such as tunnel structure and fixed obstacles), but also dynamically adapt to the real-time changing environment (such as moving obstacles or path blocking), thereby ensuring the smooth operation of the electric locomotive.

[0065] In a specific embodiment of the present invention, the positioning and navigation module works in coordination with the path planning unit and the dynamic path optimization unit. The path planning unit uses a weighted graph model to describe the mine terrain information, and models the tunnel nodes and their connection relationships as a graph structure G=(V,E), where V represents the path node set, E represents the path connection set, and the weight of each path edge E is Represents a slave node To Node The cost of the route, such as the length of the route, the slope, or the difficulty of passing. In path planning, the system uses a graph search algorithm to minimize the total cost of the path and calculate the optimal path from the starting point to the end point. The optimization goal of path planning can be expressed as:

[0066] in, is the path node sequence, is the cost function of the path edge.

[0067] It should be noted that the path planning result provides a global path for the initial operation of the vehicle, but due to the dynamic changes in the mine environment, the path may become unavailable due to temporary obstacles or the movement of operating equipment. Therefore, the positioning and navigation module further adjusts the path in real time through the dynamic path optimization unit. In some embodiments, the dynamic path optimization unit recalculates the local optimization scheme of the current path through a dynamic programming method to minimize the comprehensive operation cost of the vehicle. The optimization objective function is:

[0068] in, represents the path cost of the current time step, represents the path continuity constraint, is the penalty factor for path smoothness, The motion model of the vehicle.

[0069] As a possible implementation method, the dynamic path optimization unit adopts a hierarchical optimization strategy: when the global path remains unchanged, the local path is adjusted first to avoid new obstacles; if the global path is completely unfeasible due to an emergency, the path planning unit is re-called to generate a new global path. This hierarchical optimization method can effectively reduce the amount of calculation and improve the system response speed.

[0070] In some embodiments, the positioning and navigation module also supports dynamic learning and historical optimization of path planning. For example, the system can record environmental data and path execution results of multiple runs, generate an experience library, and optimize the parameters of the path planning model through a machine learning algorithm. It should be noted that this optimization method based on historical data can significantly improve the efficiency and adaptability of path planning, especially when the mine environment structure is complex and operations change frequently.

[0071] The positioning and navigation module can also update the path in real time in combination with the dynamic obstacle information provided by the environmental perception module. For example, when a moving obstacle is detected ahead, the system will adjust the vehicle's path point sequence according to the speed and direction of the obstacle to avoid a collision. In addition, the positioning and navigation module can also cooperate with the communication interface module to transmit the path planning results to the remote monitoring system in real time for the operator to view and manually intervene when necessary.

[0072] Through the above method, the positioning and navigation module realizes the organic combination of global path planning and local path optimization, and can meet the requirements of the mine environment for the navigation accuracy and flexibility of the unmanned electric locomotive. Combined with the above formulas and technical details, those skilled in the art can realize the design and application of the positioning and navigation module based on the disclosure of the present invention.

[0073] Please see attached Figure 4 , the vehicle control module includes: An obstacle avoidance control unit generates an obstacle avoidance path by calculating the attraction and repulsion between the vehicle's running target and the obstacle, wherein: The attraction forces the vehicle to approach the target point, and its force is proportional to the distance between the vehicle's current position and the target point; The repulsive force keeps the vehicle away from obstacles. Its strength is inversely proportional to the distance between the vehicle and the obstacle. When the distance is less than the safe range, the repulsive force increases rapidly, as shown in the following:

[0074] in, is the total potential field function, is the attractive potential field function, is the repulsive potential field function, the attractive potential field and the repulsive potential field are defined as:

[0075]

[0076] in, is the target point position, is the obstacle position, is the proportionality coefficient of the attractive potential field, is the proportionality coefficient of the repulsive potential field, is the range of the repulsive potential field, indicating the safe distance of obstacles, is the Euclidean distance between the vehicle’s current position and the target point’s position, is the Euclidean distance between the vehicle’s current position and the obstacle’s position; A dynamic adjustment unit that optimizes vehicle operating parameters in real time based on a prediction model so that the vehicle's operating trajectory conforms to the target path while meeting stability and energy consumption optimization requirements; The dynamic adjustment unit in the vehicle control module is able to coordinate multiple optimization objectives, including maximizing operating efficiency and minimizing energy consumption.

[0077] Specifically, the vehicle control module is the core execution module in the unmanned intelligent control system of the mine electric locomotive of the present invention. Its function is to generate specific vehicle operation control instructions based on the path planning results provided by the positioning navigation module and the real-time environmental information of the environmental perception module, including speed adjustment, direction control, and dynamic obstacle avoidance operations, so as to achieve the smooth operation of the electric locomotive in a complex mine environment. It should be noted that the module combines dynamic obstacle avoidance logic and real-time adjustment strategy, and can adapt to dynamic environmental changes and various emergencies in the mine, thereby ensuring the safety and stability of vehicle operation.

[0078] In a specific embodiment of the present invention, the vehicle control module is composed of an obstacle avoidance control unit and a dynamic adjustment unit. The obstacle avoidance control unit generates a dynamic obstacle avoidance path by calculating the potential field between the vehicle and the target point and the obstacle. As an exemplary implementation, an artificial potential field method is used for obstacle avoidance calculation. The potential field function includes an attractive potential field and a repulsive potential field, and its total potential field can be expressed as:

[0079] Among them, the attractive potential field Used to guide the vehicle to the target position, the expression is:

[0080] The repulsive field It is used to prevent the vehicle from approaching obstacles. Its intensity increases sharply as the distance between the vehicle and the obstacle decreases. Its expression is:

[0081] In this way, by calculating the combined force of the attractive potential field and the repulsive potential field, the system can dynamically adjust the vehicle's driving direction to avoid obstacles and move toward the target point. It should be noted that in order to avoid falling into a local minimum, the obstacle avoidance control unit combines a random perturbation algorithm and a local path optimization strategy to further improve the obstacle avoidance capability.

[0082] The dynamic adjustment unit is responsible for optimizing the vehicle's motion parameters in real time to ensure that the vehicle maintains smooth operation while following the path. In some embodiments, the dynamic adjustment unit uses a model predictive control algorithm to predict the operation trajectory in the next several time steps based on the current vehicle state and path planning results, and optimize the control input. The optimization objective function is:

[0083] in, Indicates that the vehicle is The state of each time step, including position, velocity and direction, Indicates that the vehicle is The control input for each time step is is the deviation between the vehicle’s current position and the target path point, It is the cost of control input, which is used to balance control stability and response speed.

[0084] In actual operation, the dynamic adjustment unit adjusts the speed and direction of the vehicle in real time according to the results predicted by the model. For example, when the vehicle needs to pass a sharp turn or a steep slope, the dynamic adjustment unit will reduce the vehicle speed and increase the steering angle to ensure safety.

[0085] In some embodiments, the vehicle control module also combines the dynamic obstacle information provided by the environmental perception module to further optimize the obstacle avoidance path and motion parameters. For example, when a moving obstacle (such as a person or equipment) is detected in front, the system will dynamically adjust the speed and direction of the vehicle to avoid potential collisions. It should be noted that when the vehicle control module executes the control instructions, it will adapt in combination with the physical constraints of the vehicle (such as maximum acceleration, minimum turning radius, etc.) to ensure that the actual operation effect is consistent with the planning objectives.

[0086] In addition, the vehicle control module cooperates with the communication interface module to support remote operation and monitoring. In some implementation scenarios, the operator can manually adjust the vehicle's motion parameters through the remote monitoring system, such as directly intervening in vehicle operation under complex working conditions.

[0087] In this way, the vehicle control module realizes an organic combination of obstacle avoidance control and dynamic adjustment, and can adapt to the complexity and dynamic changes of the mine environment. In combination with the above formulas and technical details, those skilled in the art can design and implement the functions of the vehicle control module based on the disclosure of the present invention.

[0088] Please see attached Figure 5 , the communication interface module includes: Data transmission unit, which uses wireless communication technologies, including 5G and industrial protocols, to ensure real-time transmission of environmental data and vehicle operation data; Remote operation unit, which can remotely issue task instructions through cloud server; The status monitoring unit is used to transmit the vehicle position, speed, running path and obstacle information to the remote monitoring platform in real time; The communication interface module supports task priority scheduling, which can automatically allocate computing resources according to the urgency of the task and give priority to key task instructions.

[0089] Specifically, the communication interface module is an important component of the unmanned intelligent control system of the mine electric locomotive of the present invention, and its main function is to realize real-time data transmission, remote operation and monitoring of system status. Through the communication interface module, the environmental perception module, the positioning navigation module and the vehicle control module can carry out efficient data interaction to ensure the coordinated operation of the entire system. At the same time, the module also supports communication with the remote monitoring platform, providing the necessary technical means for monitoring and scheduling in mine operations. It should be noted that due to the characteristics of the mine environment being closed in space and severe signal attenuation, the stability and real-time performance of data transmission are fully considered in the design of the communication interface module.

[0090] In a specific embodiment of the present invention, the communication interface module includes a data transmission unit, a remote operation unit and a status monitoring unit. Among them, the data transmission unit is responsible for the data interaction between the modules within the system, and uploads the data to the remote monitoring platform through wireless communication technology. As an exemplary implementation method, the data transmission unit adopts 5G communication technology or industrial wireless protocol to achieve low-latency and high-bandwidth data transmission. For example, the three-dimensional environment model generated by the environmental perception module, the path planning results output by the positioning and navigation module, and the operating instructions of the vehicle control module are all shared in real time through the data transmission unit. In addition, in some embodiments, the data transmission unit also supports data compression and encryption functions to reduce bandwidth occupancy while ensuring data integrity and security.

[0091] The remote operation unit provides operators with direct control over the unmanned driving system. In some special scenarios, operators can directly issue control instructions or adjust task parameters through the remote operation unit. For example, when a path is blocked or equipment fails in a mine, the remote operation unit can temporarily take over the operation of the vehicle control module and command the vehicle to detour or stop running. It should be noted that the remote operation unit and the various functional modules within the system have a strict authority management mechanism to ensure that the operator's instructions will not cause unnecessary interference to the overall operation of the system.

[0092] The state monitoring unit is used to monitor the operating status and environmental perception information of the vehicle in real time, and upload the relevant data to the remote monitoring platform. Specifically, the data information collected by the state monitoring unit includes but is not limited to the vehicle's position, speed, operating trajectory, and path planning status. In addition, the dynamic obstacle information provided by the environmental perception module will also be uploaded to the remote platform through the state monitoring unit so that the operator can understand the real-time environmental conditions in the mine. In some embodiments, the state monitoring unit also supports the storage and analysis of historical operating data. For example, the system can record the vehicle's operating trajectory and path execution deviation, and optimize future path planning and vehicle control strategies by analyzing these data.

[0093] It is important to understand that the design of the communication interface module not only ensures the coordination between the modules within the system, but also provides operators with the ability to monitor and intervene in real time. For example, in actual operation, when the vehicle control module issues an obstacle avoidance command, the command and its execution results will be fed back to the remote monitoring platform through the communication interface module, and the operator can view the vehicle's obstacle avoidance trajectory and current operating status in real time. If obstacle avoidance fails or path planning cannot solve the problem, the operator can adjust the vehicle's motion parameters through the remote operation unit or directly choose to take over manually.

[0094] As an extension, the communication interface module can also be combined with multi-channel redundant communication technology to improve the reliability of data transmission. For example, in the case of severe signal attenuation or failure of a single communication channel, the system can switch to a backup communication channel to ensure the continuity of data transmission. In addition, the communication interface module also supports the task priority scheduling mechanism. When there are multiple unmanned devices running simultaneously in the mine, the system will dynamically allocate communication bandwidth and computing resources according to the urgency of the task to ensure the priority execution of critical tasks.

[0095] In the above manner, the communication interface module realizes the functions of data transmission, remote operation and status monitoring, can adapt to the special needs in the mine environment, and ensure the efficient operation and safety of the system. Combined with the above technical details and implementation schemes, those skilled in the art can realize the design and application of the communication interface module based on the disclosure of the present invention.

[0096] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent control system for unmanned mine electric locomotive, characterized in that: include: Environmental perception module, which is used to collect mine environmental information and generate real-time environmental models through multi-sensor fusion technology; A positioning and navigation module, which is connected to the environment perception module and is used for performing path planning and dynamic path optimization according to a real-time environment model; A vehicle control module, which is connected to the positioning navigation module and the environment perception module, and is used to control the operation of the electric locomotive and perform obstacle avoidance and dynamic adjustment operations; The communication interface module is connected with the environment perception module, the positioning navigation module and the vehicle control module to realize data transmission, remote operation and status monitoring.

2. The intelligent control system for unmanned mine electric locomotive according to claim 1 is characterized in that: The environment perception module comprises: A variety of sensors, including lidar, ultrasonic sensors, cameras and inertial navigation units, to collect data about the mine environment; The mine environment data includes but is not limited to obstacle information, mine operating equipment status, personnel distribution information, ventilation and gas distribution, temperature and humidity information, and light and visibility; The data fusion unit fuses the sensor data through extended Kalman filtering. The filtering process includes: The state prediction stage predicts the vehicle state based on the known system dynamic model; The observation update phase updates the state based on the measured data and satisfies the following formula: in, is the state vector, is the control input, is the observed value, and For noise.

3. The intelligent control system for unmanned mine electric locomotive according to claim 1 is characterized in that: The positioning and navigation module includes: A path planning unit, which uses a graph search algorithm to generate the optimal path from the starting point to the target point based on the mine terrain data; The mine topographic data includes, but is not limited to: walls and support structures, fixtures and track conditions; The dynamic path optimization unit optimizes the path cost by dynamic programming method. The goal is to minimize the total path cost of the vehicle from the starting point to the end point, where the path cost is determined by the combined influence of the current position and control input, expressed as: in, represents the path cost, is the penalty factor, Represents the path continuity error.

4. The intelligent control system for unmanned mine electric locomotive according to claim 1 is characterized in that: The vehicle control module comprises: An obstacle avoidance control unit generates an obstacle avoidance path by calculating the attraction and repulsion between the vehicle's running target and the obstacle, wherein: The attraction forces the vehicle to approach the target point, and its force is proportional to the distance between the vehicle's current position and the target point; The repulsive force keeps the vehicle away from obstacles. Its strength is inversely proportional to the distance between the vehicle and the obstacle. When the distance is less than the safe range, the repulsive force increases rapidly, as shown in the following: in, is the total potential field function, is the attractive potential field function, is the repulsive potential field function, the attractive potential field and the repulsive potential field are defined as: in, is the target point position, is the obstacle position, is the proportionality coefficient of the attractive potential field, is the proportionality coefficient of the repulsive potential field, is the range of the repulsive potential field, indicating the safe distance of obstacles, is the Euclidean distance between the vehicle’s current position and the target point’s position, is the Euclidean distance between the vehicle’s current position and the obstacle’s position; The dynamic adjustment unit optimizes the vehicle operating parameters in real time based on the prediction model so that the vehicle's operating trajectory conforms to the target path while meeting the requirements of stability and energy consumption optimization.

5. The intelligent control system for unmanned mine electric locomotive according to claim 1 is characterized in that: The communication interface module comprises: Data transmission unit, which uses wireless communication technologies, including 5G and industrial protocols, to ensure real-time transmission of environmental data and vehicle operation data; Remote operation unit, which can remotely issue task instructions through cloud servers; The status monitoring unit is used to transmit the vehicle position, speed, running path and obstacle information to the remote monitoring platform in real time.

6. The intelligent control system for unmanned mine electric locomotive according to claim 1 is characterized in that: The environmental model generated by the environmental perception module includes a three-dimensional map and obstacle distribution information, and the resolution of the map can be dynamically adjusted according to the needs of mine operations.

7. The intelligent control system for unmanned mine electric locomotive according to claim 1 is characterized in that: The positioning and navigation module supports dynamic learning of path planning and obstacle avoidance algorithms, and optimizes algorithm performance through historical data of mine operations.

8. The intelligent control system for unmanned mine electric locomotive according to claim 1 is characterized in that: The dynamic adjustment unit in the vehicle control module is capable of coordinating multiple optimization objectives, including maximizing operating efficiency and minimizing energy consumption.

9. The intelligent control system for unmanned mine electric locomotive according to claim 1, characterized in that: The communication interface module supports task priority scheduling, can automatically allocate computing resources according to the urgency of the task, and give priority to processing key task instructions.

10. The intelligent control system for unmanned mine electric locomotive according to claim 1, characterized in that: The system adopts modular design, each module operates independently and works together through the communication interface module to support function expansion and independent upgrade.

Images