Digital twin modeling method, device and equipment, storage medium and product

Abstract

The invention relates to the technical field of digital twinning, and discloses a digital twinning modeling method, device and equipment, a storage medium and a product, and the method comprises the steps: building a static environment model through selecting a corresponding processing technology based on the characteristics of a fixed facility and the characteristics of an operation machine, obtaining the point cloud data of a material pile through a multi-source sensor and a two-dimensional laser radar, and obtaining the point cloud data of the material pile; obtaining a virtual material pile irregular triangulation network model through a point-by-point insertion algorithm based on the material pile point cloud data, extracting material pile surface data from the virtual material pile irregular triangulation network model, and constructing a dynamic scene model based on the material pile surface data according to the material pile boundary and the material pile surface data; and a digital twin bulk cargo model is obtained by integrating the static environment model and the dynamic scene model. According to the invention, based on the fixed facility features, the operation machinery features and the two-dimensional laser radar, the static environment model and the dynamic scene model are integrated, so that the bulk cargo modeling data precision and the model real-time mapping stability are improved.

Description

Technical Field

[0001] The present application relates to the field of digital twin technology, and in particular to a digital twin modeling method, device, equipment, storage medium and product. Background Art

[0002] Container terminals have many large-scale equipment, harsh operating environment, and time-varying stockpile shapes. In the existing technology, although there are studies on digital operations, there are still many problems in establishing bulk cargo models for container terminals. For example, low data accuracy and poor stability affect unmanned and intelligent operation control. At the same time, the real-time connection and interaction emphasized by digital twins have not been well met in existing bulk cargo modeling. Summary of the invention

[0003] The main purpose of this application is to provide a digital twin modeling method, device, equipment, storage medium and product, aiming to solve the technical problems of low accuracy of bulk cargo modeling data and poor real-time mapping stability.

[0004] To achieve the above objectives, the present application proposes a digital twin modeling method, which includes:

[0005] Based on the characteristics of fixed facilities and operating machinery, a static environment model is constructed by selecting corresponding processing technologies;

[0006] Using a multi-source sensor and a two-dimensional laser radar to obtain material pile point cloud data, and based on the material pile point cloud data, obtaining a virtual material pile irregular triangulated network model through a point-by-point insertion algorithm;

[0007] Extracting material pile surface data from the virtual material pile irregular triangulated network model, and constructing a dynamic scene model based on the material pile surface data, according to the material pile boundary and the material pile surface data;

[0008] By integrating the static environment model and the dynamic scene model, a digital twin bulk cargo model is obtained.

[0009] In one embodiment, the step of acquiring material pile point cloud data using a multi-source sensor and a two-dimensional laser radar, and obtaining a virtual material pile irregular triangulated network model through a point-by-point insertion algorithm based on the material pile point cloud data includes:

[0010] The coordinate data of multiple locations on the surface of the pile are collected by using multi-source sensors and two-dimensional laser radar to obtain the point cloud data of the pile;

[0011] removing noise points from the material pile point cloud data, and updating the material pile point cloud data in real time through a data interface;

[0012] Calculating the three-dimensional coordinates of the pile of material pile point cloud data according to the relevant position information of the operating machinery;

[0013] Based on the world coordinate system of the static environment model and the local coordinate system of the working machine, the three-dimensional coordinates of the material pile are converted into the world coordinates of the material pile;

[0014] Based on the world coordinates of the material pile, the three-dimensional coordinates of the material pile are triangulated by a point-by-point insertion algorithm to obtain an irregular triangulated network model of a virtual material pile.

[0015] In one embodiment, the step of removing noise points from the material pile point cloud data and updating the material pile point cloud data in real time through a data interface includes:

[0016] Taking the bulk cargo repose angle and the theoretical size of the stockpile as boundary conditions, removing noise points of the stockpile point cloud data;

[0017] Data structures defining the surface of the stockpile;

[0018] The three-dimensional point cloud data of the surface of the pile is obtained in the form of a section, and the three-dimensional point cloud data is updated into the data structure through a data interface with the closest distance section as a strategic condition.

[0019] In one embodiment, the step of constructing a static environment model by selecting corresponding processing technologies based on fixed facility features and operating machinery features includes:

[0020] Based on the characteristics of fixed facilities, a fixed facility model is constructed by selecting corresponding processing technologies;

[0021] According to the spatial position and moving parts of the working machine characteristics, the working machine movement steps are decomposed to obtain the decomposition results;

[0022] Based on the constraint relationship of the decomposition result, a corresponding processing technology is selected to construct a hierarchical model of the operation machinery;

[0023] By integrating the fixed facility model and the operating machinery hierarchical model, a static environment model is obtained.

[0024] In one embodiment, after the step of obtaining a digital twin bulk cargo model by integrating the static environment model and the dynamic scene model, the method further includes:

[0025] By comparing the 2D LiDAR scanning data with the stockpile geometry data, the optimal installation plan for the 2D LiDAR is determined;

[0026] Based on the optimal installation solution, three-dimensional data of the stockpile surface is obtained, and combined with the digital twin bulk cargo model, a real-time bulk cargo twin model is generated according to the three-dimensional data of the stockpile surface;

[0027] By comparing the measured values ​​of the operating machinery with the twin values, the real-time bulk cargo twin model is initially verified in combination with the stockpile state on a large time scale;

[0028] By analyzing the reconstruction time and reconstruction delay of the real-time bulk cargo twin model, the real-time bulk cargo twin model is secondarily verified in combination with the operation machinery motion data;

[0029] The real-time bulk cargo twin model is optimized based on the primary verification and the secondary verification.

[0030] In one embodiment, after the step of obtaining a digital twin bulk cargo model by integrating the static environment model and the dynamic scene model, the method further includes:

[0031] By integrating the external environment perception system, the intelligent decision-making system and the real-time monitoring system, the digital twin bulk cargo model is updated in real time;

[0032] Determine the best stacking and unloading point by evaluating the utilization rate of operating machinery and the stockpile status of the material pile.

[0033] In addition, to achieve the above objectives, the present application also proposes a digital twin modeling device, which includes:

[0034] Static model building module, used to build a static environment model by selecting corresponding processing technology based on the characteristics of fixed facilities and operating machinery;

[0035] A triangulated network model building module is used to obtain material pile point cloud data using a multi-source sensor and a two-dimensional laser radar, and obtain a virtual material pile irregular triangulated network model through a point-by-point insertion algorithm based on the material pile point cloud data;

[0036] A dynamic model building module, used to extract material pile surface data from the virtual material pile irregular triangulated network model, and build a dynamic scene model based on the material pile surface data, according to the material pile boundary and the material pile surface data;

[0037] The digital twin model building module is used to obtain a digital twin bulk cargo model by integrating the static environment model and the dynamic scene model.

[0038] In addition, to achieve the above-mentioned objectives, the present application also proposes a digital twin modeling device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, and the computer program is configured to implement the steps of the digital twin modeling method described above.

[0039] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the digital twin modeling method described above are implemented.

[0040] In addition, to achieve the above-mentioned objectives, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the digital twin modeling method described above.

[0041] The technical solution proposed in this application is based on the characteristics of fixed facilities and operating machinery, and constructs a static environment model by selecting corresponding processing technologies. It uses multi-source sensors and two-dimensional laser radars to obtain stockpile point cloud data, and based on the stockpile point cloud data, obtains a virtual stockpile irregular triangulated network model through a point-by-point insertion algorithm, extracts the stockpile surface data from the virtual stockpile irregular triangulated network model, and based on the stockpile surface data, constructs a dynamic scene model according to the stockpile boundary and the stockpile surface data, and obtains a digital twin bulk cargo model by integrating the static environment model and the dynamic scene model. Since this application is based on the characteristics of fixed facilities, operating machinery and two-dimensional laser radars, and integrates the static environment model with the dynamic scene model, it improves the data accuracy of bulk cargo modeling and the stability of real-time mapping of the model. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0043] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0044] Figure 1 A flowchart of the first embodiment of the digital twin modeling method of the present application is provided;

[0045] Figure 2 A schematic diagram of the process flow provided for the second embodiment of the digital twin modeling method of the present application;

[0046] Figure 3 A schematic diagram of the process flow provided for the third embodiment of the digital twin modeling method of the present application;

[0047] Figure 4 This is a schematic diagram of the module structure of the digital twin modeling device of the embodiment of the present application;

[0048] Figure 5This is a schematic diagram of the device structure of the hardware operating environment involved in the digital twin modeling method in the embodiment of the present application.

[0049] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0050] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0051] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0052] Container terminals have many large-scale equipment, harsh operating environment, and time-varying stockpile shapes. In the existing technology, although there are studies on digital operations, there are still many problems in establishing bulk cargo models for container terminals. For example, low data accuracy and poor stability affect unmanned and intelligent operation control. At the same time, the real-time connection and interaction emphasized by digital twins have not been well met in existing bulk cargo modeling.

[0053] Therefore, in order to overcome the above-mentioned defects, the present application provides a solution based on the characteristics of fixed facilities, operating machinery characteristics and two-dimensional lidar, by integrating static environment models with dynamic scene models, thereby improving the data accuracy of bulk cargo modeling and the real-time mapping stability of the model.

[0054] It should be noted that the execution subject of each embodiment of the present application may be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, a digital twin modeling device, etc. The following embodiments are described below taking a digital twin modeling device as an example.

[0055] Based on this, the embodiment of the present application provides a digital twin modeling method, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the digital twin modeling method of the present application.

[0056] In this embodiment, the digital twin modeling method includes steps S10 to S40:

[0057] Step S10, based on the fixed facility characteristics and the operating machinery characteristics, a static environment model is constructed by selecting corresponding processing technologies.

[0058] It can be understood that port facilities used for loading, unloading and transshipment of bulk cargo (such as coal, ore, etc.) are called container terminals, which are places with clear boundaries that can accommodate the complete container loading and unloading operation process, including water areas such as harbors, anchorages, port channels, berths, as well as land areas such as freight stations, yards, dock fronts, office and living areas.

[0059] It should be noted that fixed facilities in container terminals refer to equipment or buildings that are fixed and not easy to move in container terminals, such as warehouse buildings, conveyor belt systems, lighting facilities, safety facilities, etc. Operating machinery refers to movable mechanical equipment used for cargo loading, unloading, handling, stacking, etc. in container terminals, such as forklifts, cranes, loaders, and conveyor trucks.

[0060] When constructing a static environment model, the fixed facility characteristics to be considered may include geometric shape and size, location and layout, material and attributes, etc., and the operating machinery characteristics may include spatial position and motion trajectory, moving parts and working principles, etc.

[0061] In view of these characteristics, 3D modeling technology or simulation technology can be selected for simulation and analysis, such as using texture mapping (such as simplified building modeling), billboard technology (such as tree modeling), external references (such as a large number of repeated facilities) and other processing technologies to optimize the model structure.

[0062] Step S20, using a multi-source sensor and a two-dimensional laser radar to obtain material pile point cloud data, and based on the material pile point cloud data, obtaining a virtual material pile irregular triangulated network model through a point-by-point insertion algorithm.

[0063] It should be noted that a multi-source sensor refers to a sensor that has multiple measurement channels and capabilities at the same time. It can collect information data of multiple environmental parameters, including but not limited to sound, image, temperature, humidity, pressure, speed, direction and other parameters, and can perceive and detect targets from multiple angles and directions.

[0064] A 2D laser radar is a sensor that continuously rotates to emit laser beams in all directions and receives the reflected lasers to measure the distance. It can detect the distances of various obstacles around the horizontal plane where the radar is located. Compared with laser ranging sensors, the detection range of a 2D laser radar is a plane, not a line, so its return value is an array containing the distance information of multiple points in the horizontal plane.

[0065] A stockpile refers to a pile of bulk cargo in a container terminal. Its shape and size will change with factors such as loading and unloading operations.

[0066] Multi-source sensor fusion technology is used in combination with two-dimensional laser radar and other equipment to collect point cloud data of material piles. Point cloud data is a set of coordinate data of a large number of discrete points obtained by laser radar and other equipment, which is used to represent information such as the surface shape of the object.

[0067] In addition, it should be noted that the point-by-point insertion algorithm is a common method for constructing a triangulated network model. It starts with an initial triangular mesh, then inserts points in the point cloud data one by one, and connects these points to the existing mesh according to certain rules to form new triangles.

[0068] The virtual material pile irregular triangulated network model is a digital elevation model based on the triangulated irregular network (TIN). It uses a series of interconnected triangles to fit and represent the three-dimensional form of the material pile or other irregular surfaces. The shape and size of these triangles depend on the location and density of the sampling points on the actual material pile surface, so that it can accurately reflect the complex terrain and characteristics of the material pile.

[0069] Exemplarily, the steps of constructing the irregular triangulated network model of the virtual stockpile may be: taking the stockpile point cloud data as input, initializing an empty triangular mesh, inserting the points in the point cloud data one by one, and constructing the triangulated network model according to the point-by-point insertion algorithm. When inserting each point, ensure that the newly formed triangle meets the Delaunay triangulation algorithm criteria to maintain the accuracy and stability of the model.

[0070] Step S30, extracting the pile surface data from the virtual pile irregular triangulated network model, and constructing a dynamic scene model based on the pile surface data, according to the pile boundary and the pile surface data.

[0071] It is understandable that the already constructed virtual material pile irregular triangulated network model is loaded and the material pile surface data is extracted therefrom, which may include information such as the vertex coordinates and normal vector of each triangle.

[0072] It should be understood that, according to actual needs or given boundary information, the boundary range of the stockpile may be a polygonal area, which is used to limit the construction range of the dynamic scene model.

[0073] Exemplarily, the stockpile boundary estimation process may be: determining the important parameters (length, width, height) for stockpile boundary estimation, clarifying the influence of width on the operating range of bucket wheel excavator, the relationship between height and bucket wheel excavator arm pitch angle and stockpile width, and the situation where length has little influence on loading and unloading operations when the layout of container terminal is known, and taking the maximum values ​​in the three directions of the stockpile as the theoretical size for subsequent data processing boundary value conditions.

[0074] Based on the extracted material pile surface data and material pile boundaries, the material pile surface is reconstructed, and dynamic elements are added to the reconstructed three-dimensional surface, such as the loading, unloading, and moving processes of the material pile. This can be achieved through animation, physics engine and other technologies to simulate the dynamic changes of the material pile in the actual scene.

[0075] Step S40, obtaining a digital twin bulk cargo model by integrating the static environment model and the dynamic scene model.

[0076] It should be noted that digital twin is a concept that combines a physical entity with its digital representation, reflecting and simulating real-world objects, processes or systems in real time by combining sensor data, simulation models and real-time analysis.

[0077] It should be understood that first, a suitable technical platform needs to be selected to integrate the static environment model and the dynamic scene model, which can be a dedicated digital twin platform, a geographic information system (GIS) platform or simulation software. If the data formats of the static environment model and the dynamic scene model are different, data format conversion is required to ensure that they can be integrated on the same platform.

[0078] Exemplarily, the process of obtaining a digital twin bulk cargo model may be: first, the data of the static environment model and the dynamic scene model are fused, which may involve the superposition of spatial data, synchronization of temporal data, etc. The fused data is verified to ensure the accuracy and consistency of the data, which may include checking the integrity, correctness, redundancy, etc. of the data.

[0079] Then, the static environment model and the dynamic scene model are aligned in space and time, and the interaction between the static environment model and the dynamic scene model is realized, which may include the update of the static model by the dynamic model, the constraint of the dynamic model by the static model, etc.

[0080] Finally, the integrated model is optimized, verified, and tested to improve the model's operating efficiency and accuracy, which may include reducing data redundancy, optimizing algorithms, increasing rendering speed, testing running speed, response time, resource usage, etc.

[0081] In addition, it should be noted that the digital twin bulk cargo model framework design: builds a digital twin structure framework including physical layer, data layer, virtual layer, and application layer.

[0082] Among them, the physical layer: as the data source, includes port static facilities (such as buildings, street lights, communication towers, etc.), operating facilities (such as loaders, unloaders, belt conveyors, bucket wheel excavators, etc.) and container terminals. Multi-source sensors are deployed on ships and loading and unloading equipment to collect physical data, and lidar scans the stockpile model. The data is transmitted to the data layer in a variety of ways.

[0083] Data layer: Integrate data from different data sources, perform format conversion, cleaning, missing value processing, normalization and other operations, and then load them into the target data model. Establish database management and modeling for preprocessed data, implement data mapping, and provide real-time updates and feedback for the digital twin model through data interfaces.

[0084] Virtual layer: Use 3D visualization technology to present virtual port information and build a high-quality digital twin model of the terminal from four dimensions: geometry, physics, behavior, and rules. The geometric model describes the intuitive features of the terminal elements such as the appearance; the physical model adds physical properties and operating parameters; the behavioral model simulates the dynamic behavior of the entity; and the rule model describes the system operation rules and constraints.

[0085] Application layer: Integrates external environment perception system, intelligent decision-making system and real-time monitoring system, simulates the movement of container terminal equipment and stockpile changes, monitors weather and dust concentration, evaluates equipment utilization and stockpile status, provides intelligent decision-making and optimal stacking and unloading points, provides accurate information for decision makers, and supports fault diagnosis and maintenance.

[0086] It should be understood that the functions of each layer are clear and interrelated, forming an organic whole from data collection (physical layer), integration processing (data layer), model building and presentation (virtual layer) to application services (application layer), which comprehensively covers all aspects of digital twin modeling and application of bulk container terminals, and provides a systematic solution for the intelligent management of bulk terminals.

[0087] This embodiment is based on the characteristics of fixed facilities and operating machinery, and constructs a static environment model by selecting corresponding processing technologies, uses multi-source sensors and two-dimensional laser radars to obtain stockpile point cloud data, and based on the stockpile point cloud data, obtains a virtual stockpile irregular triangulated network model through a point-by-point insertion algorithm, extracts the stockpile surface data from the virtual stockpile irregular triangulated network model, and based on the stockpile surface data, constructs a dynamic scene model according to the stockpile boundary and the stockpile surface data, and obtains a digital twin bulk cargo model by integrating the static environment model and the dynamic scene model. Since this application is based on the characteristics of fixed facilities, operating machinery and two-dimensional laser radars, and integrates the static environment model with the dynamic scene model, the accuracy of the container terminal modeling data and the stability of the real-time mapping of the model are improved.

[0088] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. Figure 2 , the step S20 may include steps S201 to S205:

[0089] Step S201, by using a multi-source sensor and a two-dimensional laser radar to collect coordinate data of multiple locations on the surface of the pile, to obtain the pile point cloud data.

[0090] It should be noted that, considering the impact of various factors on data collection accuracy, it is necessary to evaluate factors such as lighting and dust interference when determining the installation position of the two-dimensional laser radar to ensure that the measurement range covers the operating area, the installation position is high and calibration verification is performed. However, in actual operations, it is limited by factors such as the repose angle of bulk cargo and the structural stability of the bucket wheel excavator. The maximum height of the two-dimensional laser radar is limited and it is easily interfered with to produce noise points. It is necessary to determine a reasonable installation position to balance the data acquisition range and accuracy requirements.

[0091] It should be understood that the multi-source sensor needs to be installed in a suitable position, such as on the cantilever of the stacker and reclaimer, and the sensor needs to be started to collect data on the surface of the pile. The two-dimensional laser radar needs to be installed in a suitable position, such as the front end of the cantilever of the stacker and reclaimer, and the two-dimensional laser radar needs to be started to scan the surface of the pile and record the scanned point cloud data in real time. Then, the data collected by the multi-source sensor and the point cloud data collected by the two-dimensional laser radar are fused, which may require the use of data fusion algorithms and technologies to ensure that the coordinate data of multiple pile surfaces from different sources can accurately and consistently represent the shape and characteristics of the pile surface.

[0092] Step S202, removing noise points from the material pile point cloud data, and updating the material pile point cloud data in real time through a data interface.

[0093] It should be noted that noise points are usually caused by sensor errors, environmental interference or mismatch in the data fusion process. They may appear as isolated points, outliers or points that are obviously inconsistent with other points. Statistical methods, distance thresholds, neighborhood analysis and other techniques can be used to identify noise points.

[0094] For example, the distance from each point to its nearest neighbor is calculated, and if the distance exceeds a certain threshold, it may be regarded as a noise point.

[0095] In order to improve the accuracy and reliability of the stockpile point cloud data, the step S202 may further include:

[0096] Taking the bulk cargo repose angle and the theoretical size of the stockpile as boundary conditions, removing noise points of the stockpile point cloud data;

[0097] Data structures defining the surface of the stockpile;

[0098] The three-dimensional point cloud data of the surface of the pile is obtained in the form of a section, and the three-dimensional point cloud data is updated into the data structure through a data interface with the closest distance section as a strategic condition.

[0099] It should be noted that the angle of repose, also known as the angle of repose, refers to the angle between the slope of the pile and the horizontal plane when the bulk cargo is naturally stacked. It is an important physical characteristic parameter of bulk cargo. The theoretical size of the pile is the geometric size of the pile that is pre-set based on factors such as material type, container terminal design, and loading and unloading equipment.

[0100] By using the bulk cargo repose angle as a constraint, point cloud data that obviously exceeds the natural stacking angle can be eliminated. Combined with the theoretical size of the stockpile, the range of the point cloud data can be further limited to ensure that only valid data within the theoretical size range is retained.

[0101] It is understandable that, according to the complexity of the pile surface and the requirements of subsequent applications, a suitable data structure (such as point cloud array, triangular mesh, height map, etc.) is selected to store and represent the pile point cloud data. According to the geometric shape of the pile and the requirements of subsequent applications, a suitable cross-sectional direction (such as horizontal, vertical or oblique) is selected to obtain the three-dimensional point cloud data of the pile surface. Use a slicing algorithm or a plane clipping algorithm to extract the point cloud data on the cross section.

[0102] Defining "closest distance section" as the condition of the update strategy means that when updating the data structure, the point cloud data with the closest distance to the current section will be given priority, that is, according to the closest distance section strategy, the extracted point cloud data will be compared and updated with the existing data in the data structure.

[0103] Step S203, calculating the three-dimensional coordinates of the material pile of the material pile point cloud data according to the relevant position information of the working machine.

[0104] It should be understood that the location information collected from sensors (such as GPS, laser rangefinder, radar, etc.) installed on the operating machinery (such as stackers, loaders, etc.) may include the longitude, latitude, altitude, orientation, etc. of the machinery. The preliminary position of the pile is calculated based on the location information of the machinery and the positional relationship of the pile relative to the machinery (for example, through a pre-set offset or through real-time sensor measurement). Using the location of the operating machinery as a reference point, combined with the point cloud data on the surface of the pile, the three-dimensional coordinates of each point in the pile are calculated, which may require the use of some geometric transformation and coordinate conversion methods, such as translation, rotation, etc.

[0105] Step S204: based on the world coordinate system of the static environment model and the local coordinate system of the working machine, convert the three-dimensional coordinates of the material pile into the world coordinates of the material pile.

[0106] It should be noted that the world coordinate system is a standard mathematical model used to describe the position of a point in three-dimensional space. In this coordinate system, the position of each point can be uniquely determined by three coordinate values ​​(x, y, z). Static environment models usually have a global world coordinate system to describe the position relationship of the entire material yard or work area. The operating machine has a local coordinate system to describe the position and posture of the machine itself.

[0107] It should be understood that the calculated three-dimensional coordinates of the stockpile are converted from the local coordinate system to the world coordinate system according to the conversion relationship between the local coordinate system of the working machine and the world coordinate system (eg, a conversion matrix obtained through a calibration process).

[0108] Step S205 , based on the world coordinates of the material pile, triangulate the three-dimensional coordinates of the material pile by a point-by-point insertion algorithm to obtain an irregular triangulated network model of a virtual material pile.

[0109] Taking the world coordinates of the material pile as the input point set and applying the point-by-point insertion algorithm for triangulation, we can obtain a mesh model composed of triangles, namely the irregular triangulated network model of the virtual material pile. This model can accurately describe the geometric shape and surface features of the material pile and can be used for subsequent volume calculation, shape analysis, visualization and other applications.

[0110] This embodiment uses multi-source sensors and two-dimensional laser radar to collect surface coordinate data of the material pile, obtains point cloud data of the material pile and preprocesses and updates it, calculates the three-dimensional coordinates of the material pile according to the position information of the operating machinery, and converts it into coordinates in the world coordinate system, and uses a point-by-point insertion algorithm to triangulate the three-dimensional coordinates of the material pile to generate an irregular triangulated network model of a virtual material pile, which can truly reflect the actual shape and size of the material pile, improves the accuracy and completeness of the point cloud data, and ensures the reliability and real-time performance of the model.

[0111] In the second embodiment, step S10 may include:

[0112] Based on the characteristics of fixed facilities, a fixed facility model is constructed by selecting corresponding processing technologies;

[0113] According to the spatial position and moving parts of the working machine characteristics, the working machine movement steps are decomposed to obtain the decomposition results;

[0114] Based on the constraint relationship of the decomposition result, a corresponding processing technology is selected to construct a hierarchical model of the operation machinery;

[0115] By integrating the fixed facility model and the operating machinery hierarchical model, a static environment model is obtained.

[0116] It is understandable that, according to the characteristics of fixed facilities, the fixed facility model can be constructed using technologies such as Computer Aided Design (CAD), GIS, and Building Information Modeling (BIM).

[0117] Then, the structure of the operating machine is analyzed in detail to understand the spatial position relationship and movement mode of its various components. According to the workflow and operation requirements of the operating machine, its movement steps are decomposed. Each step contains a specific movement trajectory and action, and the starting position, end position, movement path and required time of each step can be recorded.

[0118] It should be understood that based on the above information, the constraint relationship between each motion step is analyzed, such as sequence, spatial position restrictions, motion speed restrictions, etc., to ensure that each step in the model can be simulated and emulated according to the actual workflow and constraint conditions. Based on the constraint relationship of the decomposition results, the corresponding processing technology is selected to construct the operation machinery hierarchical model.

[0119] For example, taking a bucket wheel excavator as an example, the three-dimensional shape of its surface remains unchanged during operation, but the spatial position and moving parts need to be adjusted. Its motion is decomposed into four steps: trolley travel, slewing mechanism rotation, wheel arm pitching motion, and bucket wheel rotation and material collection operation, and the hierarchical structure of the bucket wheel excavator digital model is planned based on the constraint relationship between each decomposed motion.

[0120] This embodiment constructs a fixed facility model based on the fixed facility characteristics, decomposes the operating machinery movement steps according to the spatial position and moving parts of the operating machinery characteristics, and then constructs an operating machinery hierarchical model. The fixed facility model and the operating machinery hierarchical model are integrated to form a complete static environment model, which can accurately present the physical layout of the bulk container terminal and the actual status of the operating machinery, provide a basis for the upgrade of the bulk container terminal model, and improve the intelligence level of the bulk container terminal.

[0121] Based on the first embodiment of the present application, in the third embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. Figure 3 After step S40, steps S411 to S415 may also be included:

[0122] Step S411, determining the optimal installation plan of the two-dimensional laser radar by comparing the two-dimensional laser radar scanning data and the material pile geometric data.

[0123] It should be noted that when the two-dimensional laser radar obtains the point cloud data of the material pile, it is affected by many factors (such as operating machinery and vibration, obstacle surface reflectivity, environmental climate, material composition of different types of cargo piles, and the parameters of the two-dimensional laser radar itself), and the measurement accuracy is difficult to guarantee. In actual operations, the determination of the installation position of the laser radar is more complicated. It is necessary to consider covering the operating area, avoiding obstructions and blind spots to ensure detection accuracy and completeness, and taking into account its height to obtain a wider field of view and a longer detection distance. At the same time, it is also necessary to consider the impact of factors such as the operating conditions of the bulk terminal and the structural stability of the operating machinery on its measurement results.

[0124] It is understandable that the scanning data of the 2D LiDAR in different installation positions and directions is obtained, and the geometric data of the stockpile, including shape, size, height, etc., is collected. The LiDAR scanning data is compared with the stockpile geometric data to evaluate the integrity and accuracy of the scanning data. Based on the comparison results, the LiDAR installation scheme with the highest scanning data quality, the most comprehensive coverage, and the smallest blind area is selected.

[0125] Step S412, obtaining three-dimensional data of the material pile surface based on the optimal installation solution, combining the digital twin bulk cargo model, and generating a real-time bulk cargo twin model according to the three-dimensional data of the material pile surface.

[0126] It should be understood that the 2D LiDAR under the optimal installation scheme is used for continuous scanning to obtain the 3D point cloud data of the stockpile surface. Then, the digital twin bulk cargo model is combined with the real-time data to construct a real-time bulk cargo twin model.

[0127] Step S413, by comparing the actual measured value of the operating machinery with the twin value, the real-time bulk cargo twin model is initially verified in combination with the stockpile state on a large time scale.

[0128] It should be noted that the state of a pile of materials on a large time scale refers to the overall state or characteristics of the pile of materials over a longer period of time (such as days, weeks, months or longer). These states or characteristics are usually closely related to the physical properties, chemical properties, storage conditions and external environmental factors of the pile of materials.

[0129] The total station can be used to measure the actual values ​​of the operating machinery (such as loaders, stackers and reclaimers) during the operation process, including position, speed, posture, etc., and record the state changes of the stockpile over a large time scale (such as days, weeks, and months), such as height changes, shape changes, etc. The actual values ​​of the operating machinery are compared with the corresponding values ​​in the twin model to evaluate the accuracy of the model. Combined with the changes in the stockpile state, analyze whether the model can accurately reflect the actual state of the stockpile.

[0130] Step S414: performing secondary verification on the real-time bulk cargo twin model by analyzing the reconstruction time and reconstruction delay of the real-time bulk cargo twin model in combination with the operation machinery motion data.

[0131] It should be noted that the reconstruction time refers to the total time required from the start of the reconstruction process of the real-time bulk cargo twin model to the completion of the reconstruction and reaching a usable state, including the time for the operation of operating machinery, radar scanning, data transmission, point cloud 3D reconstruction, etc. The length of the reconstruction time directly reflects the response speed of the model in dealing with changes in the container terminal. The reconstruction delay only refers to the time consumed for point cloud 3D reconstruction. The size of the reconstruction delay directly affects the real-time performance and accuracy of the model.

[0132] Monitor the reconstruction time and delay of the real-time bulk cargo twin model, evaluate the real-time performance of the model, and analyze whether there are bottlenecks or delays in the reconstruction process. In addition, compare the motion data of the operating machinery with the motion data in the twin model to verify whether the model can accurately simulate the motion behavior of the operating machinery.

[0133] Step S415: optimizing the real-time bulk cargo twin model according to the primary verification and the secondary verification.

[0134] It is understandable that, based on the results of the primary and secondary verifications, the optimization of the real-time bulk cargo twin model may include adjusting the model's parameters, algorithms, and data processing procedures.

[0135] This embodiment accurately determines the laser radar installation plan by comparing the two-dimensional laser radar scanning data with the stockpile geometry data. Based on this plan, the three-dimensional data of the stockpile surface is collected, and the data is used to generate a real-time digital twin model of bulk cargo. The model is initially verified by comparing the measured values ​​of the operating machinery with the twin values ​​and analyzing the stockpile status on a large time scale. Furthermore, the model is secondarily verified by analyzing the reconstruction time, reconstruction delay and operating machinery motion data of the model, thereby ensuring that the digital twin model can accurately reflect the actual situation of the container terminal, improving the accuracy and reliability of the digital twin model, and providing strong support for the optimized management and decision-making of bulk cargo.

[0136] In the third embodiment, after step S40, the following steps may also be included:

[0137] By integrating the external environment perception system, the intelligent decision-making system and the real-time monitoring system, the digital twin bulk cargo model is updated in real time;

[0138] Determine the best stacking and unloading point by evaluating the utilization rate of operating machinery and the stockpile status of the material pile.

[0139] It should be understood that the integrated external environment perception system may include the deployment of monitoring equipment such as sensors and cameras to collect real-time external environmental data of the container terminal, such as weather, temperature, humidity, etc. Using the Internet of Things technology, the collected data is transmitted to the data processing center in real time.

[0140] The integrated intelligent decision-making system can be based on the collected external environmental data and internal data of the container terminal (such as material type, inventory, etc.), and use artificial intelligence technologies such as machine learning and deep learning to analyze and predict. According to the analysis results, the intelligent decision-making system generates optimized container terminal management strategies, such as adjusting the stacking method and optimizing the material retrieval path.

[0141] The integrated real-time monitoring system can be a real-time monitoring system that monitors the operating status of the container terminal, including the location, status, and work efficiency of the operating machinery. At the same time, the monitoring system is also responsible for updating the digital twin model in real time to ensure that the model is consistent with the actual status of the container terminal.

[0142] The optimization strategy generated by the intelligent decision-making system is applied to the digital twin model for simulation verification. Based on the simulation results, necessary adjustments and optimizations are made to the model to ensure its accuracy and reliability.

[0143] Collect and analyze the operating data of operating machinery, such as operating time, downtime, failure rate, etc., calculate the utilization rate of operating machinery, and evaluate its work efficiency and performance. Use digital twin models and real-time monitoring systems to obtain the real-time storage status of the material pile, including pile height, pile shape, material type, etc. Perform stability analysis on the material pile to assess whether there are safety hazards such as collapse and landslide.

[0144] Taking into account the utilization rate of the operating machinery and the stockpile status of the material pile, the intelligent decision-making system is used to determine the best stacking and unloading point to ensure that the stacking and unloading point can maximize the working efficiency of the operating machinery while ensuring the stability and safety of the material pile.

[0145] This embodiment integrates the external environment perception system, intelligent decision-making system and real-time monitoring system to update the digital twin bulk cargo model in real time, and accurately determine the best stacking and unloading point based on the evaluation of the utilization rate of operating machinery and the stockpile status, thereby improving the operational efficiency of bulk container terminals and ensuring that container terminal resources are reasonably allocated and efficiently utilized. At the same time, through real-time monitoring and intelligent decision-making, the uncertainty caused by human operation is reduced, and the safety and stability of the operation process are enhanced.

[0146] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the digital twin modeling method of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0147] This application also provides a digital twin modeling device, please refer to Figure 4 , the digital twin modeling device comprises:

[0148] The static model building module 10 is used to build a static environment model by selecting corresponding processing technology based on the fixed facility characteristics and the operating machinery characteristics;

[0149] A triangulated network model building module 20 is used to obtain material pile point cloud data using a multi-source sensor and a two-dimensional laser radar, and obtain a virtual material pile irregular triangulated network model through a point-by-point insertion algorithm based on the material pile point cloud data;

[0150] A dynamic model building module 30 is used to extract the pile surface data from the virtual pile irregular triangulated network model, and build a dynamic scene model based on the pile surface data, the pile boundary and the pile surface data;

[0151] The digital twin model construction module 40 is used to obtain a digital twin bulk cargo model by integrating the static environment model and the dynamic scene model.

[0152] The digital twin modeling device provided in this application adopts the digital twin modeling method in the above embodiment, which can solve the technical problems of low precision of bulk cargo modeling data and poor stability of real-time mapping. Compared with the prior art, the beneficial effects of the digital twin modeling device provided in this application are the same as the beneficial effects of the digital twin modeling method provided in the above embodiment, and the other technical features in the digital twin modeling device are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0153] The present application provides a digital twin modeling device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the digital twin modeling method in the above-mentioned embodiment one.

[0154] Reference below Figure 5, which shows a schematic diagram of the structure of a digital twin modeling device suitable for implementing the embodiment of the present application. The digital twin modeling device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Desctions: tablet computers), PMPs (Portable Media Players: portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 5 The digital twin modeling device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0155] like Figure 5 As shown, the digital twin modeling device may include a processing device 1001 (such as a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the digital twin modeling device are also stored. The processing device 1001, ROM1002 and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the digital twin modeling device to communicate wirelessly or wired with other devices to exchange data. Although the figure shows a digital twin modeling device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or provided instead.

[0156] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0157] The digital twin modeling device provided by this application adopts the digital twin modeling method in the above embodiment, which can solve the technical problems of low precision of bulk cargo modeling data and poor stability of real-time mapping. Compared with the prior art, the beneficial effects of the digital twin modeling device provided by this application are the same as the beneficial effects of the digital twin modeling method provided by the above embodiment, and the other technical features in the digital twin modeling device are the same as the features disclosed in the previous embodiment method, which will not be repeated here.

[0158] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0159] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0160] The present application provides a computer-readable storage medium having computer-readable program instructions (i.e., computer programs) stored thereon, and the computer-readable program instructions are used to execute the digital twin modeling method in the above-mentioned embodiment.

[0161] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0162] The above-mentioned computer-readable storage medium may be included in the digital twin modeling device; or it may exist independently without being assembled into the digital twin modeling device.

[0163] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the digital twin modeling device, the digital twin modeling device: based on the characteristics of fixed facilities and operating machinery, constructs a static environment model by selecting corresponding processing technologies, uses multi-source sensors and two-dimensional lidar to obtain material pile point cloud data, and based on the material pile point cloud data, obtains a virtual material pile irregular triangulated network model through a point-by-point insertion algorithm, extracts the material pile surface data from the virtual material pile irregular triangulated network model, and based on the material pile surface data, constructs a dynamic scene model according to the material pile boundary and the material pile surface data, and obtains a digital twin bulk cargo model by integrating the static environment model and the dynamic scene model.

[0164] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0165] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0166] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0167] The readable storage medium provided in this application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned digital twin modeling method, and can solve the technical problems of low precision of bulk cargo modeling data and poor stability of real-time mapping. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as the beneficial effects of the digital twin modeling method provided in the above-mentioned embodiment, and will not be repeated here.

[0168] The present application also provides a computer program product, including a computer program, which implements the steps of the digital twin modeling method as described above when executed by a processor.

[0169] The computer program product provided by this application can solve the technical problems of low data accuracy of bulk cargo modeling and poor stability of real-time mapping. Compared with the prior art, the beneficial effects of the computer program product provided by this application are the same as the beneficial effects of the digital twin modeling method provided by the above embodiment, which will not be repeated here.

[0170] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or directly / indirectly applied in other related technical fields, are included in the patent protection scope of the present application.

Claims

1. A digital twin modeling method, characterized in that: The method comprises the following steps: Based on the characteristics of fixed facilities and operating machinery, a static environment model is constructed by selecting corresponding processing technologies; Using a multi-source sensor and a two-dimensional laser radar to obtain material pile point cloud data, and based on the material pile point cloud data, obtaining a virtual material pile irregular triangulated network model through a point-by-point insertion algorithm; Extracting material pile surface data from the virtual material pile irregular triangulated network model, and constructing a dynamic scene model based on the material pile surface data, according to the material pile boundary and the material pile surface data; By integrating the static environment model and the dynamic scene model, a digital twin bulk cargo model is obtained.

2. The digital twin modeling method according to claim 1, characterized in that: The step of using a multi-source sensor and a two-dimensional laser radar to obtain the stockpile point cloud data, and obtaining a virtual stockpile irregular triangulated network model through a point-by-point insertion algorithm based on the stockpile point cloud data includes: The coordinate data of multiple locations on the surface of the pile are collected by using multi-source sensors and two-dimensional laser radar to obtain the point cloud data of the pile; removing noise points from the material pile point cloud data, and updating the material pile point cloud data in real time through a data interface; Calculating the three-dimensional coordinates of the pile of material pile point cloud data according to the relevant position information of the operating machinery; Based on the world coordinate system of the static environment model and the local coordinate system of the working machine, the three-dimensional coordinates of the material pile are converted into the world coordinates of the material pile; Based on the world coordinates of the material pile, the three-dimensional coordinates of the material pile are triangulated by a point-by-point insertion algorithm to obtain an irregular triangulated network model of a virtual material pile.

3. The digital twin modeling method according to claim 2, characterized in that: The step of removing noise points from the material pile point cloud data and updating the material pile point cloud data in real time through a data interface includes: Taking the bulk cargo repose angle and the theoretical size of the stockpile as boundary conditions, removing noise points of the stockpile point cloud data; Data structures defining the surface of the stockpile; The three-dimensional point cloud data of the surface of the pile is obtained in the form of a section, and the three-dimensional point cloud data is updated into the data structure through a data interface with the closest distance section as a strategic condition.

4. The digital twin modeling method according to any one of claims 1 to 3, characterized in that: The step of constructing a static environment model by selecting corresponding processing technologies based on the fixed facility characteristics and the operating machinery characteristics includes: Based on the characteristics of fixed facilities, a fixed facility model is constructed by selecting corresponding processing technologies; According to the spatial position and moving parts of the working machine characteristics, the working machine movement steps are decomposed to obtain the decomposition results; Based on the constraint relationship of the decomposition result, a corresponding processing technology is selected to construct a hierarchical model of the operation machinery; By integrating the fixed facility model and the operating machinery hierarchical model, a static environment model is obtained.

5. The digital twin modeling method according to any one of claims 1 to 3, characterized in that: After the step of obtaining a digital twin bulk cargo model by integrating the static environment model and the dynamic scene model, the method further includes: By comparing the 2D LiDAR scanning data with the stockpile geometry data, the optimal installation plan for the 2D LiDAR is determined; Based on the optimal installation solution, three-dimensional data of the stockpile surface is obtained, and combined with the digital twin bulk cargo model, a real-time bulk cargo twin model is generated according to the three-dimensional data of the stockpile surface; By comparing the measured values ​​of the operating machinery with the twin values, the real-time bulk cargo twin model is initially verified in combination with the stockpile state on a large time scale; By analyzing the reconstruction time and reconstruction delay of the real-time bulk cargo twin model, the real-time bulk cargo twin model is secondarily verified in combination with the operation machinery motion data; The real-time bulk cargo twin model is optimized based on the primary verification and the secondary verification.

6. The digital twin modeling method according to any one of claims 1 to 3, characterized in that: After the step of obtaining a digital twin bulk cargo model by integrating the static environment model and the dynamic scene model, the method further includes: By integrating the external environment perception system, the intelligent decision-making system and the real-time monitoring system, the digital twin bulk cargo model is updated in real time; Determine the best stacking and unloading point by evaluating the utilization rate of operating machinery and the stockpile status of the material pile.

7. A digital twin modeling device, characterized in that: The digital twin modeling device comprises: Static model building module, used to build a static environment model by selecting corresponding processing technology based on the characteristics of fixed facilities and operating machinery; A triangulated network model building module is used to obtain material pile point cloud data using a multi-source sensor and a two-dimensional laser radar, and obtain a virtual material pile irregular triangulated network model through a point-by-point insertion algorithm based on the material pile point cloud data; A dynamic model building module, used to extract material pile surface data from the virtual material pile irregular triangulated network model, and build a dynamic scene model based on the material pile surface data, according to the material pile boundary and the material pile surface data; The digital twin model building module is used to obtain a digital twin bulk cargo model by integrating the static environment model and the dynamic scene model.

8. A digital twin modeling device, characterized in that: The digital twin modeling device includes: a memory, a processor, and a digital twin modeling program stored in the memory and executable on the processor. When the digital twin modeling program is executed by the processor, the digital twin modeling method according to any one of claims 1 to 6 is implemented.

9. A storage medium, characterized in that: A digital twin modeling program is stored on the storage medium, and when the digital twin modeling program is executed by the processor, the digital twin modeling method according to any one of claims 1 to 6 is implemented.

10. A computer program product, characterized in that The computer program product includes a digital twin modeling program, which, when executed by a processor, implements the digital twin modeling method as described in any one of claims 1 to 6.

Images