An Adaptive Update Method for Intelligent Chassis Model of Unmanned Mining Based on DT

Abstract

This invention belongs to the field of coal mine transportation auxiliary technology, aiming to solve the problems of long testing time, high cost, and high safety risks associated with actual environment testing methods. It provides a digital twin-based adaptive update method for an unmanned intelligent mine chassis model, including the following steps: acquiring environmental data around the vehicle and constructing a 3D environmental map of the underground coal mine transportation roadway based on the environmental data; acquiring vehicle status data and constructing a whole vehicle mechanism model based on the vehicle status data; constructing a digital twin model based on the 3D environmental map and the whole vehicle mechanism model, and performing joint simulation; and improving the operation control strategy for the vehicle's physical entity based on the simulation results. This invention uses digital twin technology to construct an unmanned intelligent mine chassis testing and simulation platform. This method efficiently and accurately verifies the effectiveness of unmanned driving algorithms and the reliability of drive-by-wire chassis structure design and high response.

Description

Technical Field

[0001] This invention belongs to the field of coal mine transportation auxiliary technology, specifically relating to a method for adaptive updating of an unmanned mine intelligent chassis model based on DT (Digital Transmission Technology). Background Technology

[0002] Currently, mine transportation systems are gradually moving towards unmanned operation. As the main means of transporting materials other than coal and personnel in underground coal mine production, the mine auxiliary transportation system is a crucial link in the entire coal production system. Its technical level and operational efficiency directly affect the achievement of the goal of reducing manpower and increasing efficiency in coal mine production. At present, traditional mine auxiliary transportation mainly relies on driver operation and manual dispatching, with low automation and backward information technology, making it prone to safety accidents; at the same time, it mainly uses mechanical and hydraulic transmission, which has low transmission efficiency and poor reliability.

[0003] Due to the harsh underground environment and the fact that coal transportation is a high-risk industry, on the one hand, if the path planning of the unmanned driving system is unreasonable, it will cause serious coal mine accidents. Therefore, it is essential to ensure the safety and reliability of the unmanned driving system. On the other hand, since the unmanned driving system is designed based on the characteristics of a drive-by-wire chassis, the drive-by-wire characteristics of the steering system, braking system, and transmission system of the unmanned mine intelligent chassis must highly meet the linear requirements of the unmanned driving system. If the unmanned mine intelligent chassis has an abnormal state, it will also pose a safety hazard.

[0004] Current autonomous driving systems and drive-by-wire chassis performance testing requires extensive training and experimentation in relevant real-world physical scenarios to obtain suitable structural design parameters and decision-making control algorithms. This approach demands significant debugging time and costs, and also carries certain safety risks, hindering rapid product development. Summary of the Invention

[0005] In order to solve at least one of the above-mentioned technical problems in the prior art, the present invention provides a method for adaptive updating of unmanned mine intelligent chassis model based on DT.

[0006] This invention employs the following technical solution: an adaptive update method for an unmanned mine intelligent chassis model based on DT (Digital Transmission Technology), comprising the following steps: acquiring environmental data around the vehicle, and constructing a three-dimensional environmental map of the underground transportation roadway in the coal mine based on the environmental data; acquiring vehicle status data, and constructing a whole vehicle mechanism model based on the vehicle status data; the whole vehicle mechanism model includes a mechanical subsystem module, a decision-making subsystem module, and a control subsystem module; constructing a digital twin model based on the three-dimensional environmental map and the whole vehicle mechanism model, and performing joint simulation; and improving the operation control strategy for the physical entity of the vehicle based on the simulation results.

[0007] Preferably, the environmental data includes fused perception data obtained by combining lidar, combined inertial navigation and RGB-D front camera. The lidar is used to collect point cloud data, the combined inertial navigation is used to measure the acceleration and angular velocity of objects using accelerometers and gyroscopes, and obtain velocity and position information through integration, and the RGB-D front camera is used to classify and identify traffic signs and traffic light status to obtain traffic signal information.

[0008] Preferably, the mechanical subsystem module is a vehicle dynamics model built on Simulink / Simscape, including the vehicle dimensions and shape, driving system, power transmission system, braking system, and steering system. The vehicle dimensions and shape include parameter settings for vehicle body information and aerodynamics, the driving system includes parameter configurations for tires and suspension, and the power transmission system includes parameter settings for the transmission and differential. The vehicle's mass, inertia matrix, and friction coefficient are set in Simulink / Simscape.

[0009] Preferably, based on a recursive least squares algorithm with a forgetting factor, the vehicle state data collected in real time from sensors and encoders is used for iterative optimization to achieve online adaptive updating and parameter synchronization of the physical parameter values ​​of tire lateral stiffness of the whole vehicle mechanism model.

[0010] Preferably, both the decision-making subsystem module and the control subsystem module are built based on MATLAB / Simulink software. The decision-making subsystem module includes normal driving state, StopToEnd state, RiskLevelA state, RiskLevelB state, QuitStateOne state, QuitStateTwo state, and parking state. The control subsystem module is built based on the decision-making subsystem module and constructs corresponding control strategies based on different risk levels and vehicle states. The Simulink / Simscape mechanism model and the MATLAB / Simulink decision control module are jointly simulated through the built-in energy conversion and transmission module.

[0011] Preferably, a global map of underground transportation roadways in a coal mine is constructed based on point cloud data and the Gazebo physics simulation platform. Simultaneously, in the Gazebo physics simulation environment, a three-dimensional environment map is generated by adding vehicles, workers, lighting, dust, water mist, and obstacles. The map is continuously updated using point cloud data obtained from real-time scanning of the new environment by LiDAR. Based on MATLAB / Simulink, Simulink / Simscape, and Gazebo, a final co-simulation platform is constructed, integrating the Ray-Col collision detection method and the Multi-PPO algorithm to perform predictive simulation of the entire vehicle. The operation control strategy of the vehicle's physical entity is updated based on the simulation results.

[0012] Preferably, the input variables of the digital twin model are braking pressure and steering angle, and the output parameters include vehicle speed, body roll angle, pitch angle and yaw rate.

[0013] Preferably, the digital twin model includes a physical data module, a digital twin space, a physical space, a virtual-real interaction mapping space, and a twin data module; wherein the physical space includes the physical entity of the unmanned mining intelligent chassis vehicle, the lidar, RGB-D front camera, combined inertial navigation system and its actual working environment arranged on the vehicle, the core component is a wheeled drive-by-wire intelligent chassis, the physical data module includes environmental data and vehicle status data, the digital twin space is the core part of the digital twin model, including a three-dimensional environment map and a vehicle mechanism model, the virtual-real interaction mapping space monitors the vehicle's movement process in real time through one-dimensional data, two-dimensional charts and three-dimensional models, and the twin data module includes twin data obtained based on simulation.

[0014] Preferably, virtual debugging is performed based on a digital twin model. Based on the obtained twin data, decision feedback for the unmanned intelligent mining chassis is achieved, forming a closed-loop mapping mechanism. Its five-dimensional expression is shown in the formula:

[0015] DV DT =(PDV,VDV,DVDTD,DVSS,CN)

[0016] Among them, DV DT The framework represents the digital twin framework of the unmanned intelligent mining chassis. PDV represents the physical space of the unmanned intelligent mining chassis, VDV represents the digital twin space of the unmanned intelligent mining chassis, DVDTD represents the twin data obtained from the simulation of the digital twin model, DVSS represents the virtual-physical interaction mapping space, and CN represents connection.

[0017] Compared with the prior art, the beneficial effects of the present invention are:

[0018] This invention proposes to use digital twin technology to construct a test simulation platform for unmanned intelligent mining chassis. It constructs a complex mechatronics model of unmanned intelligent mining chassis with multiple domains, multiple variables, multiple parameters, multiple couplings, and nonlinearity. This solves the problems that most current modeling still stays at the stage of single model construction, making it difficult to achieve coupled modeling of multiple domains and low model simulation accuracy.

[0019] This invention integrates a digital twin model of an unmanned intelligent mining chassis coupled with a LiDAR SLAM 3D reconstruction image to form a virtual testing environment. Furthermore, it integrates autonomous collision detection, local obstacle avoidance, and global path planning algorithms to verify the effectiveness of the unmanned driving algorithm and the reliability of the drive-by-wire chassis structure design and high response. This solves the problems of long testing time, high cost, and high safety risks associated with current real-world testing methods, and is conducive to the rapid iteration and development of the product in the later stages. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a flowchart illustrating the construction process of the unmanned intelligent mine chassis digital twin system of the present invention;

[0022] Figure 2 This invention relates to the framework of a digital twin testing system for an unmanned intelligent chassis in a mine.

[0023] Figure 3 This is a structural diagram of the vehicle mechanism model of the present invention. Detailed Implementation

[0024] The technical solutions of the embodiments of the present invention will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other implementation methods obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0025] It should be noted that the structures, proportions, sizes, etc., shown in the accompanying drawings of this specification are only for the purpose of assisting those skilled in the art in understanding and reading the content disclosed in the specification, and are not intended to limit the conditions under which the present invention can be implemented. Therefore, they have no substantial technical significance. Any modifications to the structure, changes in the proportional relationships, or adjustments to the size, without affecting the effects and objectives that the present invention can produce, should fall within the scope of the technical content disclosed in the present invention. It should be noted that in this specification, relational terms such as "first" and "second" are only used to distinguish one entity from several other entities, and do not necessarily require or imply any actual relationship or order between these entities.

[0026] This invention provides an embodiment:

[0027] like Figures 1 to 3 As shown, an adaptive update method for an unmanned mine intelligent chassis model based on DT (Digital Transmission Technology) includes the following steps: acquiring environmental data around the vehicle and constructing a three-dimensional environmental map of the underground transportation roadway in the coal mine based on the environmental data; acquiring vehicle state data and constructing a whole vehicle mechanism model based on the vehicle state data; the whole vehicle mechanism model includes a mechanical subsystem module, a decision subsystem module, and a control subsystem module; constructing a digital twin model based on the three-dimensional environmental map and the whole vehicle mechanism model, and performing joint simulation; and improving the operation control strategy for the physical entity of the vehicle based on the simulation results.

[0028] In this embodiment, the testing framework for the digital twin model includes a physical data module, a digital twin space, a physical space, a virtual-real interaction mapping space, and a twin data module.

[0029] The physical space includes the physical entity of the unmanned intelligent mining chassis vehicle, the lidar, RGB-D front camera, combined inertial navigation system and its actual working environment. The core component is the wheeled drive-by-wire intelligent chassis, which is both a driving device and a load-bearing structure, and also integrates various unit modules with autonomous driving functions.

[0030] The physical data module includes environmental data and vehicle status data. The environmental data includes fused perception data obtained from a combination of LiDAR, integrated inertial navigation, and an RGB-D front camera. The LiDAR uses a 128-line long-range LiDAR with a maximum detection range of 200m, a wavelength of 865nm, a vertical field of view of 45°, a horizontal field of view of 360°, and a scanning frequency of 20Hz. It is mainly responsible for collecting a large amount of point cloud data. The integrated inertial navigation system includes GNSS and IMU, which use accelerometers and gyroscopes to measure the acceleration and angular velocity of objects. Through integration, it obtains velocity and position information to achieve accurate navigation and positioning. The RGB-D front camera is mainly responsible for classifying and recognizing traffic signs and traffic light status to obtain traffic signal information.

[0031] Environmental data obtained through the fusion perception of LiDAR, combined inertial navigation, and RGB-D front camera can be divided into two main categories based on their application: The first category is used for mapping and localization testing. By combining SLAM (Simultaneous Localization and Mapping) mapping algorithms and UWB (Ultra-Wideband) technology, a multimodal data-driven fusion localization strategy is formed, which can build an environmental map in real time and determine its own absolute coordinates, thereby improving the accuracy and robustness of unmanned intelligent mining chassis in underground environmental localization; The second category is used for perception testing, responsible for perceiving the traffic environment near the vehicle, such as pedestrians and vehicles.

[0032] Vehicle status data is collected through various sensors, such as encoders, speed sensors, temperature sensors, and pressure sensors, comprehensively gathering data on the unmanned intelligent mining chassis during operation. This data also includes drive signals such as steering angle and braking pressure. After processing and cleaning, the collected historical and real-time data is transmitted via a high-speed industrial Ethernet LAN bus and a system-safe CAN bus and stored in a multi-dimensional database, facilitating subsequent mapping of the data to a digital twin model.

[0033] The digital twin space is the core component of the digital twin model, including a 3D environment map and a vehicle mechanism model. The mechanical subsystem module is a visualized 3D dynamic model constructed based on the geometry of the unmanned intelligent mining chassis and the constraints of its components. The mechanical subsystem module is a vehicle dynamic model built on Simulink / Simscape, including the vehicle dimensions and shape, driving system, powertrain system, braking system, and steering system. The vehicle dimensions and shape include parameter settings for vehicle body information and aerodynamics. The driving system includes parameter configurations for tires and suspension. The powertrain system includes parameter settings for the engine, clutch, transmission, and differential. The vehicle's mass, inertia matrix, and friction coefficient are set in Simulink / Simscape to further improve the model's accuracy.

[0034] Meanwhile, considering that the mechanical components of the unmanned mining intelligent chassis will change in performance due to wear during long-term actual operation, and the physical parameters of the system will also change, a static model cannot accurately reflect its actual operating conditions, and the error between simulation accuracy and actual operating results will gradually increase. Therefore, based on a recursive least squares algorithm with a forgetting factor, iterative optimization is performed using vehicle state data collected in real time from sensors and encoders to achieve online adaptive updating and parameter synchronization of the tire lateral stiffness physical parameter values ​​in the whole vehicle mechanism model. Through the adaptive updating of the unmanned mining intelligent chassis, the model can better adapt to different operating and environmental conditions and improve the simulation accuracy of the model.

[0035] Both the decision-making subsystem and the control subsystem are built using MATLAB / Simulink software. The decision-making subsystem, based on a finite state machine, formulates prevention and control decisions and path planning for various risks during vehicle operation. The decision-making subsystem includes states such as normal driving, StopToEnd, RiskLevelA, RiskLevelB, QuitStateOne, QuitStateTwo, and parking. The control subsystem, built upon the decision-making subsystem, constructs corresponding control strategies based on different risk levels and vehicle states, thereby achieving smooth and safe braking and stopping of the unmanned intelligent mining chassis when facing collision risks. The Simulink / Simscape mechanism model and the MATLAB / Simulink control and decision-making module are jointly simulated using the built-in energy conversion and transmission module.

[0036] Based on point cloud data and the Gazebo physics simulation platform, a global map of underground coal mine transport roadways is constructed. Simultaneously, within the Gazebo physics simulation environment, a 3D environment map is generated by adding vehicles, workers, lighting, dust, water mist, and obstacles to meet the actual underground scenario. This further verifies the stability, sensitivity, and reliability of the unmanned driving system in obstacle avoidance and emergency handling. This method not only establishes a high-precision prior map of underground coal mine roadways but also utilizes point cloud data obtained from real-time scanning of new environments using lidar to continuously update the map, ensuring that the digital twin model has adaptive update capabilities.

[0037] Based on MATLAB / Simulink, Simulink / Simscape, and Gazebo, a final co-simulation platform was built, integrating the Ray-Col collision detection method and the Multi-PPO algorithm. Through simulation, predictive estimation of various motion states of the vehicle under autonomous driving system was performed to obtain twin data. Based on the twin data, the control strategy of the physical entity and the autonomous driving algorithm were further improved.

[0038] The virtual-real interactive mapping space monitors vehicle movement in real time through one-dimensional data, two-dimensional charts, and three-dimensional models, enhancing the immersiveness and accuracy of monitoring during the operation of the unmanned intelligent mining chassis. The status monitoring function can quickly locate problems during the operation of the unmanned intelligent mining chassis, and the virtual debugging function of the digital twin model can predict potential future problems, allowing for pre-adjustment of model parameters to maintain optimal working condition. This not only reduces troubleshooting time and shortens the resolution process but also improves the safety of the unmanned intelligent mining chassis during operation and reduces maintenance costs.

[0039] Virtual debugging is performed based on a digital twin model. Using the obtained twin data, decision feedback for the unmanned intelligent mining chassis is achieved, forming a closed-loop mapping mechanism. Its five-dimensional expression is shown in the formula:

[0040] DV DT =(PDV,VDV,DVDTD,DVSS,CN)

[0041] Among them, DV DT This represents the digital twin framework for an unmanned intelligent mining chassis. PDV represents the physical space of the unmanned intelligent mining chassis, VDV represents the digital twin space, DVDTD represents the twin data obtained from the digital twin model simulation, DVSS represents the virtual-physical interaction mapping space, and CN represents connectivity. The input variables of the digital twin model are braking pressure and steering angle, and the output parameters include vehicle speed, body roll angle, pitch angle, and yaw rate.

[0042] Specific implementation plan:

[0043] Multi-source perception information collected by various sensors, including LiDAR, RGB-D front camera, and vehicle-mounted terminal, is transmitted in real time to the digital twin space via communication modules, including Ethernet LAN bus and system security CAN bus. Within this space, a mechanistic model of the unmanned intelligent mining chassis and a high-precision 3D reconstructed map are constructed, while real-time updates of the subsequent models are also implemented.

[0044] In the virtual digital twin space, Simulink / Simscape was used to model the overall dynamics of the unmanned intelligent mining chassis from five aspects: overall vehicle shape, transmission system, braking system, steering system, and driving system, providing an accurate reference for subsequent simulation and control algorithms.

[0045] To achieve global path planning for unmanned intelligent mining chassis, the PPO algorithm was improved in MATLAB / Simulink based on Markov decision process theory and within the Critic-Actor learning framework. By utilizing a reward and punishment mechanism, the algorithm was made capable of decision-making. This enabled the compilation of an autonomous global path planning algorithm for the digital twin model of the unmanned intelligent mining chassis, thus equipping the vehicle with decision-making capabilities.

[0046] A digital twin model of an unmanned intelligent mine chassis, coupling multiple fields of electromechanical control, was constructed in MATLAB / Simulink. The model takes braking pressure and steering angle as input variables and outputs key parameters including vehicle speed, roll angle, pitch angle, and yaw rate. The input variables are real-time drive signals collected by sensors, enabling real-time simulation of the digital twin model.

[0047] Furthermore, using the Gazebo physics simulation platform and combining a high-precision digital 3D map, the driving conditions of vehicles in a real underground coal mine environment were simulated, and obstacles such as vehicles and people were added. On the one hand, the feasibility and stability of the Ray-Col collision detection method and the Multi-PPO algorithm were verified through simulation. On the other hand, the reliability of each subsystem, such as drive, steering and braking, as well as the response accuracy of the control strategy were verified during operation.

[0048] By using predictive simulation results from digital twin models to improve the unmanned intelligent chassis for mining, the vehicle can reach its optimal state during actual operation, greatly improving its reliability. This also solves the problems of long testing times, high costs, and high safety risks associated with actual vehicle testing in open underground coal mine environments.

[0049] The above description is merely a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for adaptive updating of an unmanned mine intelligent chassis model based on DT (Data Technology), characterized in that, Includes the following steps: Acquire environmental data around the vehicle and construct a three-dimensional environmental map of the underground transportation roadway in the coal mine based on the environmental data; Acquire vehicle status data and construct a vehicle mechanism model based on the vehicle status data; the vehicle mechanism model includes a mechanical subsystem module, a decision-making subsystem module, and a control subsystem module. A digital twin model is constructed based on a 3D environment map and a vehicle mechanism model, and joint simulation is performed. The input variables of the digital twin model are braking pressure and steering angle, and the output parameters include vehicle speed, body roll angle, pitch angle, and yaw rate. The digital twin model includes a physical data module, a digital twin space, a physical space, a virtual-real interaction mapping space, and a twin data module. The physical space includes the physical entity of the unmanned mining intelligent chassis, the lidar, RGB-D front camera, combined inertial navigation system, and its actual working environment. The core component is the wheeled drive-by-wire intelligent chassis. The physical data module includes environmental data and vehicle status data. The digital twin space is the core part of the digital twin model, including a 3D environment map and a vehicle mechanism model. The virtual-real interaction mapping space monitors the vehicle's motion process in real time through one-dimensional data, two-dimensional charts, and three-dimensional models. The twin data module includes twin data obtained from simulation. Improve the operation control strategy for the physical entity of the vehicle based on simulation results; Virtual debugging is performed based on a digital twin model. Using the obtained twin data, decision feedback for the unmanned intelligent mining chassis is achieved, forming a closed-loop mapping mechanism. Its five-dimensional expression is shown in the formula: in, This represents a digital twin framework for an intelligent chassis in unmanned mining operations. This indicates the physical space of the unmanned mining intelligent chassis. This indicates the digital twin space of the intelligent chassis for unmanned mining operations. This represents the twin data obtained from the simulation of the digital twin model. Represents the virtual-real interaction mapping space. Indicates a connection.

2. The adaptive update method for an unmanned mine intelligent chassis model based on DT according to claim 1, characterized in that: Environmental data includes fused perception data obtained from a combination of LiDAR, integrated inertial navigation, and RGB-D front camera. LiDAR is used to collect point cloud data, integrated inertial navigation is used to measure the acceleration and angular velocity of objects using accelerometers and gyroscopes, and velocity and position information are obtained through integration, and RGB-D front camera is used to classify and identify traffic signs and traffic light status to obtain traffic signal information.

3. The adaptive update method for an unmanned mine intelligent chassis model based on DT according to claim 1, characterized in that: The mechanical subsystem module is a vehicle dynamics model built on Simulink / Simscape, including the overall vehicle dimensions and shape, driving system, powertrain system, braking system, and steering system. The overall vehicle dimensions and shape include the parameter settings for vehicle body information and aerodynamics, the driving system includes the parameter configuration for tires and suspension, and the powertrain system includes the parameter settings for the transmission and differential. The vehicle's mass, inertia matrix, and friction coefficient are set in Simulink / Simscape.

4. The adaptive update method for an unmanned mine intelligent chassis model based on DT according to claim 3, characterized in that: Based on a recursive least squares algorithm with a forgetting factor, the system uses real-time vehicle state data collected from sensors and encoders to perform iterative optimization, thereby achieving online adaptive updating and parameter synchronization of tire lateral stiffness values ​​in the whole vehicle mechanism model.

5. The adaptive update method for an unmanned mine intelligent chassis model based on DT according to claim 3, characterized in that: Both the decision-making subsystem module and the control subsystem module are built based on MATLAB / Simulink software. The decision-making subsystem module includes normal driving state, StopToEnd state, RiskLevelA state, RiskLevelB state, QuitStateOne state, QuitStateTwo state, and parking state. The control subsystem module is built upon the decision subsystem module, and corresponding control strategies are constructed based on different risk levels and vehicle status.

6. The adaptive update method for an unmanned mine intelligent chassis model based on DT according to claim 5, characterized in that: Based on point cloud data and the Gazebo physics simulation platform, a global map of underground transportation roadways in coal mines is constructed. At the same time, in the Gazebo physics simulation environment, a three-dimensional environment map is generated by adding vehicles, workers, lighting, dust, water mist and obstacles. The map is continuously updated by using point cloud data obtained from real-time scanning of the new environment by LiDAR. Based on MATLAB / Simulink, Simulink / Simscape, and Gazebo, a final co-simulation platform was built, and the Ray-Col collision detection method and Multi-PPO algorithm were integrated to perform predictive simulation of the whole vehicle. Based on the simulation results, the operation control strategy of the vehicle's physical entity was updated.

Images