Stockyard stacker-reclaimer management system based on digital twin

Abstract

The present invention relates to a material yard stacker and reclaimer management system based on digital twin, which belongs to the technical field of material yard management. The system includes a material yard stacker and reclaimer model building module, which is used to build a three-dimensional digital twin model of a target material yard, and to build a virtual environment corresponding to the three-dimensional digital twin model in a metaverse; an interactive operation module, which is used to monitor the operation behavior of operators in the virtual environment of the three-dimensional digital twin model in real time, and to feedback the operation training results of operators based on the operation behavior; a stacker and reclaimer simulation module, which is used to simulate the operation process of the virtual stacker and reclaimer based on different operating conditions of the virtual stacker and reclaimer, and output the target operation path and action coordination plan of the virtual stacker and reclaimer, so as to assist the operation of the real stacker and reclaimer according to the target operation path and action coordination plan. The present application has the effects of improving personnel skills and improving the operating efficiency and safety of material yard stacker and reclaimer.

Description

Technical Field

[0001] The present invention relates to the technical field of material yard management, and in particular to a material yard stacker-reclaimer management system based on digital twin. Background Art

[0002] With the rapid development of information technology, especially the breakthroughs in cutting-edge fields such as digital twins, metaverse and artificial intelligence, the fields of industrial manufacturing and engineering management are undergoing unprecedented changes. As an important part of industrial manufacturing and logistics, the management efficiency and safety of material yards are crucial to the overall operation of enterprises.

[0003] In the field of bulk material processing such as coal and ore, circular material yards are important places for material storage and transshipment. The efficient and safe operation of circular material yard stackers and reclaimers plays a vital role in improving the overall material handling efficiency.

[0004] However, the existing digital twin circular stockyard stacker-reclaimer management technology can construct a macro model during real-time simulation optimization, but it is still insufficient in terms of detailed optimization of the operation process and efficient allocation of resources, making it difficult to accurately guide actual production operations. Secondly, the immersive interactive potential contained in the metaverse technology has not yet been fully explored and applied to the practical skills training of operators, limiting the speed and effect of skill improvement. Furthermore, the application of advanced simulation technology in improving operation accuracy and optimizing operation paths is not yet in-depth, and it cannot effectively cope with the complex and changeable circular stockyard environment.

[0005] Therefore, there is an urgent need for a material yard stacker-reclaimer management technology that can achieve detailed optimization of the operating process, improvement of personnel skills, and improvement of the operating efficiency and safety of the material yard stacker-reclaimer. Summary of the invention

[0006] The technical problem to be solved by the present invention is to provide a material yard stacker-reclaimer management system based on digital twin, aiming to solve at least one of the above-mentioned technical problems.

[0007] The technical solution of the present invention to solve the above technical problems is as follows:

[0008] This application provides a material yard stacker-reclaimer management system based on digital twin, which adopts the following technical solutions:

[0009] A material yard stacker-reclaimer management system based on digital twin, comprising:

[0010] A model building module, used to build a three-dimensional digital twin model of a target material yard and a stacker-reclaimer in the target material yard, and to build a virtual environment corresponding to the three-dimensional digital twin model in the metaverse, wherein the three-dimensional digital twin model integrates the working logic, operating environment, operating conditions and operation data of the real stacker-reclaimer;

[0011] An interactive operation module, used to monitor the operation behavior information of the operator in the virtual environment of the three-dimensional digital twin model in real time, and to feed back the operation training results of the operator based on the operation behavior information;

[0012] A stacker-reclaimer simulation module is used to simulate the operation process of the virtual stacker-reclaimer based on different operation conditions and operation environments of the virtual stacker-reclaimer, and output a target operation path and an action coordination scheme of the virtual stacker-reclaimer, so as to assist the operation of the real stacker-reclaimer according to the target operation path and the action coordination scheme;

[0013] An equipment management module, used to predict equipment failures of a real stacker-reclaimer and generate a maintenance plan for the real stacker-reclaimer according to the prediction results;

[0014] The remote monitoring module is used to generate alarm information of the real stacker-reclaimer based on the operating data of the real stacker-reclaimer and preset alarm processing rules, and to display the operating data and alarm information of the real stacker-reclaimer in real time.

[0015] The beneficial effects of the present invention are as follows: by establishing a three-dimensional digital twin model of the target material yard and its internal stacker-reclaimer and constructing a virtual environment in the metaverse, high-precision model and environment simulation is achieved. The interactive operation module monitors the operation behavior in the virtual environment in real time, improves the operation training effect, and feeds back the training results of the operator, which not only reduces the training cost, but also significantly improves the operator's skill level and safety awareness. The stacker-reclaimer simulation module simulates different working conditions and environments, outputs optimized operation paths and action coordination plans, assists actual operations, reduces invalid operations and energy consumption, and improves work efficiency. The equipment management module predicts equipment failures and generates maintenance plans to improve maintenance efficiency. The remote monitoring module generates alarm information in real time and displays operation data to ensure safe and efficient equipment operation.

[0016] Based on the above technical solution, the present invention can also be improved as follows.

[0017] Furthermore, the stockyard stacker-reclaimer model building module includes:

[0018] A first acquisition submodule, used to acquire first geometric parameters, geographic information and environmental information of a real target material yard, and second geometric parameters of a stacker-reclaimer in the real target material yard;

[0019] The second acquisition submodule is used to acquire in real time the operating state, operating environment, operating conditions of the actual stacker-reclaimer and the material stacking density of each stacker-reclaiming area in the target material yard;

[0020] A physical model establishment and logic integration submodule, for establishing an initial model of the real target material yard and a stacker-reclaimer in the real target material yard according to the first geometric parameter, the geographic information, the environmental information, the second geometric parameter and the digital twin technology, and integrating the working logic of the real stacker-reclaimer into the initial model, wherein the initial model includes the mechanical characteristics, material properties and connection relationships between components of the real stacker-reclaimer;

[0021] An environmental factor simulation submodule, for establishing a virtual environment corresponding to the initial model based on the metaverse technology, simulating the operation process of the virtual stacker-reclaimer under different environments in the virtual environment, and updating the simulation parameters of the initial model;

[0022] a calibration submodule, for comparing the simulation parameters of the updated initial model with the actual operating data of the real target material yard and the real stacker-reclaimer, until the similarity between the simulation result and the actual operating data is greater than a set similarity threshold, and using the initial model corresponding to the similarity greater than the set similarity threshold as the three-dimensional digital twin model of the real target material yard and the stacker-reclaimer in the real target material yard;

[0023] The data synchronization submodule is used to integrate the operating status, operating environment and operating conditions of the real stacker and reclaimer and the material stacking density of each stacking and reclaiming area in the real target material yard into the three-dimensional digital twin model, so that the three-dimensional digital twin model can reflect the operating status, operating environment and operating conditions of the real stacker and reclaimer and the density of each stacking and reclaiming area in the real target material yard in real time.

[0024] The beneficial effect of adopting the above further scheme is that the material yard stacker-reclaimer model building module can establish a high-precision three-dimensional digital twin model by acquiring the geometric parameters and environmental information of the target material yard and stacker-reclaimer, and build a corresponding virtual environment in the metaverse. By obtaining the real operating status, operating environment and operating conditions of the stacker-reclaimer in real time, combined with the material stacking density, the model can be continuously updated and optimized to ensure that it is closely synchronized with the actual equipment operating status. The accuracy and reliability of the model are significantly improved, thereby improving the efficiency and safety of the stacker-reclaimer in actual operations.

[0025] Furthermore, the operation training result includes prompt information, correct operation behavior and evaluation information, and the interactive operation module includes:

[0026] A training mode selection submodule is used to obtain operation training content in response to a trigger action selected by an operator for an operation training mode; the operation training mode is a first training mode or a second training mode, the first training mode represents a mode in which the operator is trained according to a set operation sequence, the second training mode represents a mode in which the operator is trained according to a set operation sequence and randomly triggers a preset operation fault, the operation training content is a circular material yard three-dimensional layout operation, a stacker-reclaimer operation process or a fault scenario operation, and the fault scenario is an overheating of the stacker-reclaimer motor, a torn conveyor belt or a sensor failure;

[0027] A third acquisition submodule is used to obtain operation behavior information sent by the operator through a head-mounted device in the virtual environment of the three-dimensional digital twin model, wherein the operation behavior information includes operation nodes, operation gesture information, operation visual information, operation auditory information, action sequence and operation time, and the operation nodes represent nodes of the operation sequence in the operation training content;

[0028] a prompt submodule, for acquiring a target operation behavior based on the operation node, matching the operation behavior information with the target operation behavior, and if the similarity between the operation behavior information and the target operation behavior is less than a preset matching similarity threshold, generating prompt information corresponding to the similarity and displaying a correct operation behavior, wherein the prompt information is a handle vibration, an error message display or a voice prompt error message;

[0029] The evaluation submodule is used to input the operation training content and the operation behavior information into a preset neural network evaluation model for multi-dimensional evaluation to obtain evaluation information. The evaluation dimensions of the neural network evaluation model include operation speed, operation action accuracy and operation response time. The neural network evaluation model is trained based on historical operation behavior information with different operation speeds, operation action accuracy and operation response time.

[0030] The beneficial effect of adopting the above further scheme is that the interactive operation module significantly improves the operator's skill proficiency and emergency response ability by providing operation training based on a virtual reality environment. First, the training mode selection submodule provides the first training mode and the second training mode for different training needs, so that the operator can perform basic operation training or real operation drills including random fault triggering in a simulated environment, thereby improving the actual effect of operation training. The third acquisition submodule can capture the operator's operation behavior information in the virtual environment in real time, and realize comprehensive monitoring of operation details through the integration of multi-dimensional information such as handles, visual and auditory feedback. The prompt submodule performs similarity matching between the operator's operation and the preset target operation. For non-standard operation behaviors, it uses handle vibration, error message display or voice prompts to provide instant feedback to help the operator correct the error, thereby improving the standardization of operation. The evaluation submodule uses a neural network evaluation model to perform multi-dimensional evaluation of operation behavior, including operation speed, action accuracy, and response time, etc., and obtains evaluation results based on historical operation behavior information, further optimizing the quality of operation training.

[0031] Furthermore, the training mode selection submodule is also used for:

[0032] When the operator selects the second mode, obtaining the scoring information and the first operation frequency of each operation fault, the actual historical occurrence rate of each operation fault, the total historical operation times of each operation fault, and the operation difficulty of each operation fault of the operator within the first preset time period;

[0033] According to the scoring information of each of the operation faults by the operator within the first preset time period, a first weight is assigned to each of the operation faults;

[0034] According to the first operation frequency of each of the operation faults by the operator within the first preset time period, assigning a second weight to each of the operation faults;

[0035] assigning a third weight to each of the operation failures according to an actual historical occurrence rate of each of the operation failures;

[0036] Allocating a fourth weight to each of the operation faults according to the total number of historical operations of each of the operation faults;

[0037] According to the operational difficulty of each of the operational faults, assigning a fifth weight to each of the operational faults;

[0038] Determining a recommended value for each of the operational faults based on the first weight, the second weight, the third weight, the fourth weight, and the fifth weight of each of the operational faults;

[0039] Based on the recommended value of each of the operation faults, at least one of the operation faults that is randomly triggered in the operation training content and the number of times the operation fault is triggered are determined.

[0040] The beneficial effect of adopting the above further scheme is that the training mode selection submodule can comprehensively assign different weights according to the operator's operation fault scoring information, operation frequency, actual historical occurrence rate, total historical operation times and operation difficulty within the first preset time period, so as to determine the recommended value of each operation fault. Based on the recommended value, at least one operation fault and the corresponding triggering times are reasonably selected and randomly triggered, which improves the pertinence and flexibility of virtual training and enhances the operator's ability to handle complex faults. Through multi-dimensional evaluation and determination of recommended values, the operator's problems in the operation process can be accurately located, making the training more targeted and effective.

[0041] Furthermore, the stacker-reclaimer simulation module is specifically used for:

[0042] For any operating environment and operating condition of the virtual stacker-reclaimer, according to the set operation sequence, path selection mode and action coordination mode, the current simulation parameter combination of the virtual stacker-reclaimer is obtained, and the operating condition represents the operating conditions of the virtual stacker-reclaimer under different loads;

[0043] For any operating environment and operating condition of the virtual stacker-reclaimer, simulating the virtual stacker-reclaimer based on the current simulation parameter combination to obtain a simulation result;

[0044] For any operating environment and operating condition of the virtual stacker-reclaimer, based on a preset evaluation function and simulation results, the operating speed, operating accuracy, failure rate and operating energy consumption of the virtual stacker-reclaimer under the current parameter combination are evaluated to obtain an evaluation result;

[0045] For any operating environment and operating condition of the virtual stacker-reclaimer, based on the evaluation result and the preset genetic algorithm, the current parameter combination is adjusted, and the virtual stacker-reclaimer is simulated according to the adjusted parameter combination until the simulation time is reached, and the parameter combination with the fastest operating speed, the highest operating accuracy, the lowest failure rate and the lowest operating energy consumption is used as the target parameter combination;

[0046] For any operating environment and operating condition of the virtual stacker-reclaimer, based on the target parameter combination, the target operation path and action coordination plan of the virtual stacker-reclaimer under the operating environment and the operating condition are determined to assist the operation of the real stacker-reclaimer according to the target operation path and the action coordination plan.

[0047] The beneficial effect of adopting the above further scheme is that the stacker-reclaimer simulation module can optimize the operation sequence, path selection method and action coordination method through genetic algorithm for different working environments and working conditions, and obtain the best simulation parameter combination, thereby improving the operating speed and operating accuracy of the stacker-reclaimer and reducing the failure rate and operating energy consumption.

[0048] Furthermore, the device management module includes:

[0049] A fourth acquisition submodule is used to acquire the actual operation data, historical maintenance records and recommended maintenance cycles of various components of the stacker-reclaimer;

[0050] A prediction submodule, used for inputting the operation data of each component of the real stacker-reclaimer into a preset fault prediction model to obtain prediction results of each component of the real stacker-reclaimer, wherein the prediction results include service life and failure probability, and the preset fault prediction model is trained based on historical operation data;

[0051] The maintenance plan generation submodule is used to generate a maintenance plan based on the prediction results of the actual components of the stacker and reclaimer, historical maintenance information and the recommended maintenance cycle of the equipment manufacturer. The maintenance plan includes the maintenance sequence of the components, maintenance time, components to be replaced and maintenance steps.

[0052] The beneficial effects of adopting the above further scheme are: the equipment management module can obtain the operating data of each component of the stacker-reclaimer in real time, use the preset fault prediction model to predict the service life and failure probability of each component, and generate a maintenance plan including maintenance sequence, maintenance time, required replacement parts and maintenance steps based on the prediction results, historical maintenance information and the recommended maintenance cycle of the equipment manufacturer to avoid failures, thereby significantly improving the accuracy of equipment maintenance and equipment operation efficiency. Reduce the risk of equipment failure during operation and ensure production safety.

[0053] Furthermore, the maintenance plan generation submodule is specifically used for:

[0054] The component whose service life is less than the set service life or whose failure probability is greater than the set failure probability is taken as the target component;

[0055] Obtain maintenance time, parts to be replaced, maintenance steps, production impact, and parts inventory information for each target part;

[0056] Determine the health value of each target component based on the prediction results of each target component, historical maintenance information, the equipment manufacturer's recommended maintenance cycle, and the preset data fusion algorithm;

[0057] Generate an initial maintenance plan based on the health value of each target component, the maintenance time of each target component, and the components and maintenance steps to be replaced;

[0058] Based on a preset optimization algorithm, component inventory information and the production impact of each target component, the preliminary maintenance plan is optimized to obtain the real stacker-reclaimer maintenance plan in which the production cost meets the set cost threshold and the maintenance efficiency meets the set efficiency threshold.

[0059] The beneficial effect of adopting the above further scheme is that the maintenance plan generation module can comprehensively judge the actual health status of the equipment through the data fusion algorithm based on various information sources such as historical maintenance records, real-time data of equipment operation status, prediction results output by the prediction analysis module, and recommended maintenance cycles provided by equipment manufacturers, and automatically generate a preliminary maintenance plan. This function significantly improves the pertinence and accuracy of the maintenance plan, ensuring that maintenance work is more timely and effective. At the same time, the optimization algorithm comprehensively considers maintenance costs, the impact of downtime on production or operations, component inventory, and the real-time operating status of the equipment, and further optimizes the preliminary maintenance plan. The generated final maintenance plan contains detailed operating steps, which effectively improves the efficiency of maintenance work and the availability of equipment, and reduces unplanned downtime.

[0060] Furthermore, the remote monitoring module is specifically used for:

[0061] For each component of the real stacker-reclaimer, compare the temperature of the component with a set temperature threshold corresponding to the component, and if the temperature exceeds the set temperature threshold, determine that the real stacker-reclaimer has a first abnormality;

[0062] For each component of the real stacker-reclaimer, the humidity of the component is compared with a set humidity threshold corresponding to the component, and if the humidity exceeds the set humidity threshold, it is determined that the real stacker-reclaimer has a second abnormality;

[0063] For each component of the real stacker-reclaimer, the pressure of the component is compared with a set pressure threshold corresponding to the component, and if the pressure exceeds the set pressure threshold, it is determined that the real stacker-reclaimer has a third abnormality;

[0064] For each component of the real stacker-reclaimer, a vibration value of the component is compared with a set vibration threshold value corresponding to the component, and if the vibration value exceeds the set vibration threshold value, it is determined that the real stacker-reclaimer has a fourth abnormality;

[0065] For each component of the real stacker-reclaimer, the displacement of the component is compared with a set displacement threshold corresponding to the component, and if the displacement is greater than the set displacement threshold, it is determined that the real stacker-reclaimer has a fifth abnormality;

[0066] Based on the first abnormality, the second abnormality, the third abnormality, the fourth abnormality and the fifth abnormality, alarm information of the real stacker and reclaimer is generated, and operating data and alarm information of the real stacker and reclaimer are displayed in real time.

[0067] The beneficial effect of adopting the above further scheme is that the remote monitoring module can timely discover and determine the abnormal state by comparing the temperature, humidity, pressure, vibration value and displacement of each component of the stacker and reclaimer with its corresponding threshold value in real time, thereby generating alarm information and displaying the operating data and alarm information of the stacker and reclaimer in real time, thereby improving the monitoring accuracy and abnormal response speed of the system.

[0068] Furthermore, the remote monitoring module is also used for:

[0069] Obtaining material stacking density change information, material type, and stacking and reclaiming plan and operation data of the real stacker and reclaimer in the current time period in each stacker and reclaimer area in the real target material yard, wherein the stacker and reclaimer plan includes the target operation path and action coordination scheme of the real stacker and reclaimer;

[0070] Inputting the material stacking density change information of each stacking and reclaiming area, the stacking and reclaiming plan and the operating data into a preset energy efficiency evaluation model to obtain the operating energy consumption of each stacking and reclaiming area and the actual operating efficiency of the stacker and reclaimer;

[0071] Determining a first priority value for each of the stacking and reclaiming areas based on the operating energy consumption of each of the stacking and reclaiming areas;

[0072] Determining a second priority value for each of the stacking and reclaiming areas based on the material stacking density of each of the stacking and reclaiming areas;

[0073] Determining a third priority value for each of the stacking and reclaiming areas based on a material type of each of the stacking and reclaiming areas;

[0074] Determining the priority of each of the stacking and reclaiming areas based on the first priority value, the second priority value and the third priority value of each of the stacking and reclaiming areas;

[0075] Based on the priority of each of the stacking and reclaiming areas and a preset path adjustment strategy, adjusting the stacking and reclaiming path of the real stacker and reclaimer in the next time period;

[0076] Based on the priority of the stacking and reclaiming area and the operation efficiency, the target stacking and reclaiming speed of the real stacker and reclaimer in the next time period is adjusted.

[0077] The beneficial effect of adopting the above further scheme is that the remote monitoring module can obtain the material stacking density change information, material type, and stacking and reclaiming plan and operation data of each stacking and reclaiming area in the target material yard in the current time period, and obtain the operating energy consumption of each stacking and reclaiming area and the operating efficiency of the stacker and reclaimer through the energy efficiency evaluation model. By comprehensively considering multiple factors such as material stacking density, material type, and operating energy consumption, the priority of each stacking and reclaiming area is determined. This priority sorting helps the stacker and reclaimer to arrange the operation sequence more reasonably and reduce invalid movement and waiting time. By optimizing the operation path and speed of the stacker and reclaimer, unnecessary energy consumption losses can be reduced, thereby reducing operating costs.

[0078] Furthermore, the second acquisition submodule includes:

[0079] A plurality of temperature sensors, for detecting the temperature of various components of the stacker-reclaimer, and sending the temperature of all components to corresponding edge computing devices;

[0080] A plurality of humidity sensors, used for detecting the humidity of various components of the stacker-reclaimer, and sending the humidity of all components to corresponding edge computing devices;

[0081] A plurality of pressure sensors, used to detect the pressure of various components of the stacker-reclaimer and send the pressure of all components to the corresponding edge computing device;

[0082] A plurality of vibration sensors, used for detecting the vibration values ​​of various components of the stacker-reclaimer, and sending the vibration values ​​of all components to corresponding edge computing devices;

[0083] A plurality of displacement sensors, used for detecting the displacement of various components of the stacker-reclaimer, and sending the displacement of all components to corresponding edge computing devices;

[0084] An environment collection unit, used to collect the environmental parameters of the real target material yard, wherein the environmental parameters include temperature, humidity, wind speed, wind direction, light intensity and visibility;

[0085] A stacker-reclaimer load detection unit, used to detect the actual load condition of the stacker-reclaimer and obtain the actual operating condition of the stacker-reclaimer;

[0086] A plurality of material stacking density acquisition units, used to measure the material stacking density of each stacking and reclaiming area of ​​the real target material yard;

[0087] Multiple edge computing devices are used to preprocess the temperatures, humidity, pressures, vibration values, displacements, operating conditions, environmental parameters of the real target material yard, and material stacking densities in each stacking and reclaiming area of ​​the real target material yard, and upload the preprocessed data to the three-dimensional digital twin model of the real stacker and reclaimer.

[0088] The beneficial effect of adopting the above further scheme is that multiple temperature sensors, humidity sensors, pressure sensors, vibration sensors and displacement sensors respectively detect the temperature, humidity, pressure, vibration value and displacement of each component of the stacker and reclaimer, and send the detection data to the corresponding edge computing device. After the edge computing device pre-processes the data, it uploads it to the three-dimensional digital twin model to achieve real-time monitoring and precise control of the stacker and reclaimer's operating status, improving the system's response speed and data processing efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0089] Figure 1 A module block diagram of a material yard stacker-reclaimer management system based on digital twin provided by the present invention. DETAILED DESCRIPTION

[0090] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0091] In addition, the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article, unless otherwise specified, generally means that the associated objects before and after are in an "or" relationship.

[0092] Figure 1 The module block diagram of a digital twin-based material yard stacker and reclaimer management system 100 provided by the present invention. Figure 1 As shown, the system includes:

[0093] A model building module 101 is used to build a three-dimensional digital twin model of a target material yard and a stacker-reclaimer in the target material yard, and to build a virtual environment corresponding to the three-dimensional digital twin model in the metaverse, wherein the three-dimensional digital twin model integrates the working logic, operating environment, operating conditions and operation data of the real stacker-reclaimer;

[0094] An interactive operation module 102 is used to monitor the operation behavior information of the operator in the virtual environment of the three-dimensional digital twin model in real time, and to feed back the operation training result of the operator based on the operation behavior information;

[0095] The stacker-reclaimer simulation module 103 is used to simulate the operation process of the virtual stacker-reclaimer based on different operation conditions and operation environments of the virtual stacker-reclaimer, and output the target operation path and action coordination scheme of the virtual stacker-reclaimer, so as to assist the operation of the real stacker-reclaimer according to the target operation path and the action coordination scheme;

[0096] The equipment management module 104 is used to predict the equipment failure of the real stacker-reclaimer and generate a maintenance plan for the real stacker-reclaimer according to the prediction result;

[0097] The remote monitoring module 105 is used to generate alarm information of the real stacker-reclaimer based on the operation data of the real stacker-reclaimer and preset alarm processing rules, and to display the operation data and alarm information of the real stacker-reclaimer in real time.

[0098] In the embodiment of the present application, the operating condition represents the operating condition of the actual stacker-reclaimer at different loads, and the operating condition of the stacker-reclaimer includes but is not limited to full load, half load and no load.

[0099] The present invention achieves high-precision model and environment simulation by establishing a three-dimensional digital twin model of the target material yard and its internal stacker and reclaimer and constructing a virtual environment in the metaverse. The interactive operation module 102 monitors the operation behavior in the virtual environment in real time, improves the operation training effect, and feeds back the training results of the operator, which not only reduces the training cost, but also significantly improves the operator's skill level and safety awareness. The stacker and reclaimer simulation module 103 simulates different working conditions and environments, outputs optimized operation paths and action coordination plans, assists actual operations, reduces invalid operations and energy consumption, and improves work efficiency. The equipment management module 104 predicts equipment failures and generates maintenance plans, thereby improving maintenance efficiency. The remote monitoring module 105 generates alarm information in real time and displays operation data to ensure safe and efficient equipment operation.

[0100] As an optional implementation of the embodiment of the present application, the stockyard stacker-reclaimer model building module 101 includes:

[0101] A first acquisition submodule, used to acquire first geometric parameters, geographic information and environmental information of a real target material yard, and second geometric parameters of a stacker-reclaimer in the real target material yard;

[0102] The second acquisition submodule is used to acquire in real time the operating state, operating environment, operating conditions of the actual stacker-reclaimer and the material stacking density of each stacker-reclaiming area in the target material yard;

[0103] A physical model establishment and logic integration submodule, for establishing an initial model of the real target material yard and a stacker-reclaimer in the real target material yard according to the first geometric parameter, the geographic information, the environmental information, the second geometric parameter and the digital twin technology, and integrating the working logic of the real stacker-reclaimer into the initial model, wherein the initial model includes the mechanical characteristics, material properties and connection relationships between components of the real stacker-reclaimer;

[0104] An environmental factor simulation submodule, for establishing a virtual environment corresponding to the initial model based on the metaverse technology, simulating the operation process of the virtual stacker-reclaimer under different environments in the virtual environment, and updating the simulation parameters of the initial model;

[0105] a calibration submodule, for comparing the simulation parameters of the updated initial model with the actual operating data of the real target material yard and the real stacker-reclaimer, until the similarity between the simulation result and the actual operating data is greater than a set similarity threshold, and using the initial model corresponding to the similarity greater than the set similarity threshold as the three-dimensional digital twin model of the real target material yard and the stacker-reclaimer in the real target material yard;

[0106] The data synchronization submodule is used to integrate the operating status, operating environment and operating conditions of the real stacker and reclaimer and the material stacking density of each stacking and reclaiming area in the real target material yard into the three-dimensional digital twin model, so that the three-dimensional digital twin model can reflect the operating status, operating environment and operating conditions of the real stacker and reclaimer and the density of each stacking and reclaiming area in the real target material yard in real time.

[0107] In the above implementation, the first acquisition submodule integrates a CAD drawing import unit, a geographic information system (GIS) integration unit, a mechanical analysis unit, a material property database, an environmental parameter input unit, and the like.

[0108] Among them, the CAD drawing import unit is used to import high-precision CAD drawings using software such as AutoCAD to ensure that the geometric parameters of the model are consistent with the actual equipment. The geographic information system (GIS) integration unit is used to integrate the geographical location and environmental information of the target material yard through geographic information systems such as ArcGIS. The mechanical analysis unit is used to perform mechanical property analysis using software such as ANSYS Mechanical to ensure the accuracy of the mechanical parameters of the three-dimensional digital twin model of the stacker and reclaimer. The material property database integrates the commonly used material property database of the stacker and reclaimer. The environmental parameter input unit is used to input the topography, soil type, climate characteristics and vegetation coverage of the target material yard.

[0109] The second acquisition submodule includes:

[0110] A plurality of temperature sensors, for detecting the temperature of various components of the stacker-reclaimer, and sending the temperature of all components to corresponding edge computing devices;

[0111] A plurality of humidity sensors, used for detecting the humidity of various components of the stacker-reclaimer, and sending the humidity of all components to corresponding edge computing devices;

[0112] A plurality of pressure sensors, used to detect the pressure of various components of the stacker-reclaimer and send the pressure of all components to the corresponding edge computing device;

[0113] A plurality of vibration sensors, used for detecting the vibration values ​​of various components of the stacker-reclaimer, and sending the vibration values ​​of all components to corresponding edge computing devices;

[0114] A plurality of displacement sensors, used for detecting the displacement of various components of the stacker-reclaimer, and sending the displacement of all components to corresponding edge computing devices;

[0115] An environment collection unit, used to collect the environmental parameters of the real target material yard, wherein the environmental parameters include temperature, humidity, wind speed, wind direction, light intensity and visibility;

[0116] A stacker-reclaimer load detection unit, used to detect the actual load condition of the stacker-reclaimer and obtain the actual operating condition of the stacker-reclaimer;

[0117] A plurality of material stacking density acquisition units, used to measure the material stacking density of each stacking and reclaiming area of ​​the real target material yard;

[0118] Multiple edge computing devices are used to preprocess the temperatures, humidity, pressures, vibration values, displacements, operating conditions, environmental parameters of the real target material yard, and material stacking densities in each stacking and reclaiming area of ​​the real target material yard, and upload the preprocessed data to the three-dimensional digital twin model of the real stacker and reclaimer.

[0119] Among them, the temperature sensor adopts the XYZ-123 model, the humidity sensor adopts the ABC-456 model, the vibration sensor adopts the DEF-789 model, the displacement sensor adopts the GHI-012 model, etc.

[0120] In the above implementation, the physical model establishment and logic integration submodule constructs a 1:1 scale virtual environment according to the CAD drawings of the actual target material yard, including key components such as the stacker-reclaimer, the stacker-reclaimer area and the conveyor belt.

[0121] In the virtual environment of the environmental factor simulation submodule, different weather conditions (such as rain, snow, wind, etc.), lighting conditions, time changes, etc. are set to simulate the operation process of the stacker-reclaimer in different environments, including stacking, retrieving, moving, and avoiding obstacles. Afterwards, the parameters of the initial model are adjusted according to the simulation results, such as adjusting the mechanical properties to adapt to different material densities and optimizing the control strategy to improve operating efficiency.

[0122] The calibration submodule compares the simulation results with the actual operation data, including operating status, operating efficiency, energy consumption, failure rate and other indicators. The similarity between the simulation results and the actual operation data is calculated using a similarity algorithm. If the similarity is lower than the set threshold, the physical model establishment and logic integration submodule or the environmental factor simulation submodule is returned to make adjustments until the similarity meets the requirements. The initial model corresponding to the similarity greater than the set similarity threshold is used as the three-dimensional digital twin model of the real target material yard and the stacker-reclaimer in the real target material yard.

[0123] The material yard stacker-reclaimer model building module 101 can establish a high-precision three-dimensional digital twin model by acquiring the geometric parameters and environmental information of the real target material yard and the real stacker-reclaimer, and build a corresponding virtual environment in the metaverse. By acquiring the real operating status, operating environment and operating conditions of the stacker-reclaimer in real time, combined with the material stacking density, the model can be continuously updated and optimized to ensure that it is closely synchronized with the actual equipment operating status. The accuracy and reliability of the model are significantly improved, thereby improving the efficiency and safety of the stacker-reclaimer in actual operations.

[0124] As an optional implementation of the embodiment of the present application, the operation training result includes prompt information, correct operation behavior and evaluation information, and the interactive operation module 102 includes:

[0125] A training mode selection submodule is used to obtain operation training content in response to a trigger action selected by an operator for an operation training mode; the operation training mode is a first training mode or a second training mode, the first training mode represents a mode in which the operator is trained according to a set operation sequence, the second training mode represents a mode in which the operator is trained according to a set operation sequence and randomly triggers a preset operation fault, the operation training content is a circular material yard three-dimensional layout operation, a stacker-reclaimer operation process or a fault scenario operation, and the fault scenario is an overheating of the stacker-reclaimer motor, a torn conveyor belt or a sensor failure;

[0126] A third acquisition submodule is used to obtain operation behavior information sent by the operator through a head-mounted device in the virtual environment of the three-dimensional digital twin model, wherein the operation behavior information includes operation nodes, operation gesture information, operation visual information, operation auditory information, action sequence and operation time, and the operation nodes represent nodes of the operation sequence in the operation training content;

[0127] a prompt submodule, for acquiring a target operation behavior based on the operation node, matching the operation behavior information with the target operation behavior, and if the similarity between the operation behavior information and the target operation behavior is less than a preset matching similarity threshold, generating prompt information corresponding to the similarity and displaying a correct operation behavior, wherein the prompt information is a handle vibration, an error message display or a voice prompt error message;

[0128] The evaluation submodule is used to input the operation training content and the operation behavior information into a preset neural network evaluation model for multi-dimensional evaluation to obtain evaluation information. The evaluation dimensions of the neural network evaluation model include operation speed, operation action accuracy and operation response time. The neural network evaluation model is trained based on historical operation behavior information with different operation speeds, operation action accuracy and operation response time.

[0129] In the above implementation, when the operator needs to be trained, first, start and load the three-dimensional digital twin model of the circular material yard, and set the simulation parameters through the Metaverse platform. For example, the lighting conditions are daytime, the wind speed is 5m / s, and the temperature range is -5°C to 40°C to simulate the working environment under different climatic conditions.

[0130] Afterwards, the operator selects a training mode through the touch screen or voice command. For example, select the "first training mode", that is, training according to the set standard operating procedures; or select the "second training mode", which randomly triggers preset fault scenarios in the standard process and requires completion within a limited time.

[0131] The training mode selection submodule loads the corresponding operation training content from the database according to the operator's selection. For example, if "circular material yard three-dimensional layout operation" is selected, the operation guidance and simulation scenes related to the circular material yard layout adjustment are loaded.

[0132] After that, the operator wears the VR headset to enter the virtual environment. The operator needs to complete the operation of the virtual stacker and reclaimer in the order of the operation training content, such as completing the start, run, stop and other processes of the virtual stacker and reclaimer. The third acquisition submodule captures the operator's operation behavior information through the built-in sensors of the headset (such as cameras, microphones, accelerometers, etc.), including gesture information (such as finger pointing, holding), visual information (such as gaze point), auditory information (such as verbal commands), action sequence and operation time.

[0133] The prompt submodule analyzes the operator's behavior in real time according to the current operation node (such as "start the stacker and reclaimer") and compares it with the target operation behavior. If the similarity is lower than the preset threshold (such as 80%), the corresponding prompt information is generated.

[0134] In the embodiment of the present application, the interactive operation module 102 has three built-in fault scenario operations, namely motor overheating, conveyor belt tearing, and sensor failure. A random trigger probability is set for each fault scenario, which are set to 15%, 25%, and 10%, respectively. The trigger probability of each fault scenario can also be randomly triggered, but is not limited to this.

[0135] In the above implementation, the training mode selection submodule is further used for:

[0136] When the operator selects the second mode, obtaining the scoring information and the first operation frequency of each operation fault, the actual historical occurrence rate of each operation fault, the total historical operation times of each operation fault, and the operation difficulty of each operation fault of the operator within the first preset time period;

[0137] According to the scoring information of each of the operation faults by the operator within the first preset time period, a first weight is assigned to each of the operation faults;

[0138] According to the first operation frequency of each of the operation faults by the operator within the first preset time period, assigning a second weight to each of the operation faults;

[0139] assigning a third weight to each of the operation failures according to an actual historical occurrence rate of each of the operation failures;

[0140] Allocating a fourth weight to each of the operation faults according to the total number of historical operations of each of the operation faults;

[0141] According to the operational difficulty of each of the operational faults, assigning a fifth weight to each of the operational faults;

[0142] Determining a recommended value for each of the operational faults based on the first weight, the second weight, the third weight, the fourth weight, and the fifth weight of each of the operational faults;

[0143] Based on the recommended value of each of the operation faults, at least one of the operation faults that is randomly triggered in the operation training content and the number of times the operation fault is triggered are determined.

[0144] In the above implementation, a sixth weight may be assigned to each of the operation faults according to the second operation frequency of each of the operation faults by the operator within the second preset time period, and a recommended value of each of the operation faults may be determined based on the first weight, the second weight, the third weight, the fourth weight, the fifth weight and the sixth weight of each of the operation faults. This is not limited thereto.

[0145] The training mode selection submodule can comprehensively assign different weights according to the operator's operation fault score information, operation frequency, actual historical occurrence rate, total historical operation times and operation difficulty within the first preset time period, so as to determine the recommended value of each operation fault. Based on the recommended value, at least one operation fault and the corresponding triggering times are reasonably selected and randomly triggered, which improves the pertinence and flexibility of virtual training and enhances the operator's ability to handle complex faults.

[0146] As an optional implementation of the embodiment of the present application, the stacker-reclaimer simulation module 103 is specifically used for:

[0147] For any operating environment and operating condition of the virtual stacker-reclaimer, according to the set operation sequence, path selection mode and action coordination mode, the current simulation parameter combination of the virtual stacker-reclaimer is obtained, and the operating condition represents the operating conditions of the virtual stacker-reclaimer under different loads;

[0148] For any operating environment and operating condition of the virtual stacker-reclaimer, simulating the virtual stacker-reclaimer based on the current simulation parameter combination to obtain a simulation result;

[0149] For any operating environment and operating condition of the virtual stacker-reclaimer, based on a preset evaluation function and simulation results, the operating speed, operating accuracy, failure rate and operating energy consumption of the virtual stacker-reclaimer under the current parameter combination are evaluated to obtain an evaluation result;

[0150] For any operating environment and operating condition of the virtual stacker-reclaimer, based on the evaluation result and the preset genetic algorithm, the current parameter combination is adjusted, and the virtual stacker-reclaimer is simulated according to the adjusted parameter combination until the simulation time is reached, and the parameter combination with the fastest operating speed, the highest operating accuracy, the lowest failure rate and the lowest operating energy consumption is used as the target parameter combination;

[0151] For any operating environment and operating condition of the virtual stacker-reclaimer, based on the target parameter combination, the target operation path and action coordination plan of the virtual stacker-reclaimer under the operating environment and the operating condition are determined to assist the operation of the real stacker-reclaimer according to the target operation path and the action coordination plan.

[0152] In the embodiment of the present application, different working conditions and working environments are set to simulate the virtual assembly and operation path of the stacker and reclaimer. The parameters adjusted in each simulation include: the set operation sequence is to adjust 5 schemes in sequence, the path selection method is to adjust the path angle by ±5° on the previous path, and the action coordination method is to delay by ±0.2s, such as the boom lifting speed time delay of 0.2 seconds. The 5 schemes are pre-set according to the actual situation, such as stacking first and then taking, stacking and taking at the same time, etc.

[0153] Use the simulation module to simulate based on the current parameter combination. For example, simulate the medium load condition under the condition of 10-meter-high cargo pile and light wind.

[0154] Afterwards, when the simulation is finished, the evaluation results are calculated according to the preset evaluation function. For example, operation speed = the inverse of the time required to complete the task, operation accuracy = the deviation between the actual position and the target position, failure rate = the number of failures in the simulation / total simulation time, and operation energy consumption = total energy consumption in the simulation.

[0155] Afterwards, based on the evaluation results, the genetic algorithm is used to adjust the current parameter combination. The genetic algorithm generates new parameter combinations through operations such as selection (retaining excellent individuals), crossover (exchanging some genes of different individuals), and mutation (randomly changing some genes of individuals).

[0156] Repeat the simulation and evaluation process until the preset simulation time is reached or the convergence condition is met or the set number of iterations is reached. The convergence condition is that the evaluation results of multiple generations have not reached the set change trend. Finally, select the target operation path and action coordination plan corresponding to the target parameter combination under the operating environment and the operating condition.

[0157] The stacker-reclaimer simulation module 103 optimizes the operation sequence, path selection method and action coordination method through genetic algorithms for different working environments and working conditions to obtain the best simulation parameter combination, thereby improving the operating speed and operating accuracy of the real stacker-reclaimer and reducing the failure rate and operating energy consumption.

[0158] As an optional implementation of the embodiment of the present application, the device management module 104 includes:

[0159] A fourth acquisition submodule is used to acquire the actual operation data, historical maintenance records and recommended maintenance cycles of various components of the stacker-reclaimer;

[0160] A prediction submodule, used for inputting the operation data of each component of the real stacker-reclaimer into a preset fault prediction model to obtain prediction results of each component of the real stacker-reclaimer, wherein the prediction results include service life and failure probability, and the preset fault prediction model is trained based on historical operation data;

[0161] The maintenance plan generation submodule is used to generate a maintenance plan based on the prediction results of the actual components of the stacker and reclaimer, historical maintenance information and the recommended maintenance cycle of the equipment manufacturer. The maintenance plan includes the maintenance sequence of the components, maintenance time, components to be replaced and maintenance steps.

[0162] In the above implementation, the maintenance plan generation submodule is specifically used for:

[0163] The component whose service life is less than the set service life or whose failure probability is greater than the set failure probability is taken as the target component;

[0164] Obtain maintenance time, parts to be replaced, maintenance steps, production impact, and parts inventory information for each target part;

[0165] Based on the prediction results of each target component, historical maintenance information, the recommended maintenance cycle of the equipment manufacturer and the preset data fusion algorithm, the health value of each target component is determined. The health value is a quantitative indicator used to reflect the risk level of the component.

[0166] Generate an initial maintenance plan based on the health value of each target component, the maintenance time of each target component, the components to be replaced, and the maintenance steps; the target components with smaller health values ​​are maintained first;

[0167] Based on a preset optimization algorithm, component inventory information and the production impact of each target component, the preliminary maintenance plan is optimized to obtain the real stacker-reclaimer maintenance plan in which the production cost meets the set cost threshold and the maintenance efficiency meets the set efficiency threshold.

[0168] In the embodiment of the present application, the preset optimization algorithm may be a multi-objective optimization algorithm, a linear programming algorithm, etc.

[0169] The optimization algorithm comprehensively considers maintenance costs, the impact of downtime on production or operations, parts inventory, and the real-time operating status of the equipment, and further optimizes the preliminary maintenance plan. The generated final maintenance plan contains detailed operation steps, which effectively improves the efficiency of maintenance work and equipment availability, and reduces unplanned downtime.

[0170] Optionally, each component may be classified according to its importance, and different failure probability thresholds may be set according to different classifications. For example, a smaller failure probability threshold may be set for more important components, and a larger failure probability threshold may be set for components with less impact.

[0171] As an optional implementation of the embodiment of the present application, the remote monitoring module 105 is specifically used for:

[0172] For each component of the real stacker-reclaimer, compare the temperature of the component with a set temperature threshold corresponding to the component, and if the temperature exceeds the set temperature threshold, determine that the real stacker-reclaimer has a first abnormality;

[0173] For each component of the real stacker-reclaimer, the humidity of the component is compared with a set humidity threshold corresponding to the component, and if the humidity exceeds the set humidity threshold, it is determined that the real stacker-reclaimer has a second abnormality;

[0174] For each component of the real stacker-reclaimer, the pressure of the component is compared with a set pressure threshold corresponding to the component, and if the pressure exceeds the set pressure threshold, it is determined that the real stacker-reclaimer has a third abnormality;

[0175] For each component of the real stacker-reclaimer, a vibration value of the component is compared with a set vibration threshold value corresponding to the component, and if the vibration value exceeds the set vibration threshold value, it is determined that the real stacker-reclaimer has a fourth abnormality;

[0176] For each component of the real stacker-reclaimer, the displacement of the component is compared with a set displacement threshold corresponding to the component, and if the displacement is greater than the set displacement threshold, it is determined that the real stacker-reclaimer has a fifth abnormality;

[0177] Based on the first abnormality, the second abnormality, the third abnormality, the fourth abnormality and the fifth abnormality, alarm information of the real stacker and reclaimer is generated, and operating data and alarm information of the real stacker and reclaimer are displayed in real time.

[0178] The remote monitoring module 105 can detect and determine abnormal conditions in a timely manner by comparing the temperature, humidity, pressure, vibration value and displacement of each component of the stacker and reclaimer with its corresponding threshold value in real time, thereby generating alarm information and displaying the operating data and alarm information of the stacker and reclaimer in real time, thereby improving the system's monitoring accuracy and abnormal response speed.

[0179] Furthermore, the remote monitoring module 105 is also used for:

[0180] Obtaining material stacking density change information, material type, and stacking and reclaiming plan and operation data of the real stacker and reclaimer in the current time period in each stacker and reclaimer area in the real target material yard, wherein the stacker and reclaimer plan includes the target operation path and action coordination scheme of the real stacker and reclaimer;

[0181] Inputting the material stacking density change information of each stacking and reclaiming area, the stacking and reclaiming plan and the operating data into a preset energy efficiency evaluation model to obtain the operating energy consumption of each stacking and reclaiming area and the actual operating efficiency of the stacker and reclaimer;

[0182] Determining a first priority value for each of the stacking and reclaiming areas based on the operating energy consumption of each of the stacking and reclaiming areas;

[0183] Determining a second priority value for each of the stacking and reclaiming areas based on the material stacking density of each of the stacking and reclaiming areas;

[0184] Determining a third priority value for each of the stacking and reclaiming areas based on a material type of each of the stacking and reclaiming areas;

[0185] Determining the priority of each of the stacking and reclaiming areas based on the first priority value, the second priority value and the third priority value of each of the stacking and reclaiming areas;

[0186] Based on the priority of each of the stacking and reclaiming areas and a preset path adjustment strategy, adjusting the stacking and reclaiming path of the real stacker and reclaimer in the next time period;

[0187] Based on the priority of the stacking and reclaiming area and the operation efficiency, the target stacking and reclaiming speed of the real stacker and reclaimer in the next time period is adjusted.

[0188] In the embodiment of the present application, the operating parameters are automatically adjusted once every 30 minutes, such as optimizing the stacking speed, path selection, etc., to maximize the operating efficiency.

[0189] The preset energy efficiency evaluation model is based on historical data, machine learning algorithms (such as TensorFlow or PyTorch) or expert system training, and can evaluate the operating energy consumption of each stacker and reclaimer area and the operating efficiency of the stacker and reclaimer.

[0190] In the embodiment of the present application, the first priority value is calculated based on the energy consumption of each stacking and reclaiming area. Areas with higher energy consumption have lower priority values, and high energy consumption tasks are moved to low power consumption periods for execution, thereby minimizing energy consumption.

[0191] Determine a second priority value based on the bulk density of the material. Areas with higher density may need to be treated first to avoid excessive accumulation or safety hazards.

[0192] The third priority value is determined based on the material type. Some materials may have a higher priority (such as perishable and high-value materials) and need to be processed first. Finally, the final priority of each stacking and reclaiming area is determined by combining the three priority values.

[0193] After that, the new target operation path is determined according to the priority of each stacker and reclaimer area and the preset path adjustment strategy. Materials in high-priority areas are processed first, while considering the efficiency and safety of the path. The preset path adjustment strategy is to optimize the path based on the current position of the stacker, the position of each stacker and reclaimer area, the position of obstacles in the path, the correlation between the stacker and reclaimer areas, and the genetic algorithm, and finally determine the stacker and reclaimer path in the next time period.

[0194] Finally, based on the priority and operating efficiency of the stacking and reclaiming area, the target stacking and reclaiming speed of the actual stacker and reclaimer in the next time period is adjusted. For areas with high priority and low operating efficiency, the stacking and reclaiming speed can be appropriately increased; for areas with low priority or areas that are close to completing their tasks, the speed can be reduced to save energy.

[0195] The remote monitoring module 105 is also used to regularly generate optimization reports to demonstrate efficiency improvement, energy saving and maintenance effects for management decision support. In the embodiment of the present application, an optimization report is generated once a week. The report will list in detail the changes in the stacker-reclaimer operating efficiency, including the specific efficiency improvement percentage, the comparison diagram before and after the operation process optimization, the comparative analysis before and after the adjustment of key operating parameters (such as stacking speed, path selection, etc.), and the specific reduction in equipment energy consumption after parameter adjustment.

[0196] The remote monitoring module 105 is used to obtain the material stacking density change information, material type, and stacking and reclaiming plan and operation data of each stacking and reclaiming area in the target material yard in the current time period, and the energy consumption of each stacking and reclaiming area and the operating efficiency of the stacking and reclaiming machine are obtained through the energy efficiency evaluation model. By comprehensively considering multiple factors such as material stacking density, material type, and operating energy consumption, the priority of each stacking and reclaiming area is determined. This priority sorting helps the stacker and reclaimer to arrange the operation sequence more reasonably and reduce invalid movement and waiting time. By optimizing the operation path and speed of the stacker and reclaimer, unnecessary energy consumption losses can be reduced, thereby reducing operating costs.

[0197] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0198] The terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not expressly listed, or also includes elements inherent to such process, method, article, or apparatus.

[0199] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of application involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the aforementioned application concept. For example, the above features are replaced with (but not limited to) technical features with similar functions applied in the present application.

Claims

1. A digital twin-based stacker-reclaimer management system, characterized in that: include: A model building module, used to build a three-dimensional digital twin model of a target material yard and a stacker-reclaimer in the target material yard, and to build a virtual environment corresponding to the three-dimensional digital twin model in the metaverse, wherein the three-dimensional digital twin model integrates the working logic, operating environment, operating conditions and operation data of the real stacker-reclaimer; An interactive operation module, used to monitor the operation behavior information of the operator in the virtual environment of the three-dimensional digital twin model in real time, and to feed back the operation training results of the operator based on the operation behavior information; A stacker-reclaimer simulation module is used to simulate the operation process of the virtual stacker-reclaimer based on different operation conditions and operation environments of the virtual stacker-reclaimer, and output a target operation path and an action coordination scheme of the virtual stacker-reclaimer, so as to assist the operation of the real stacker-reclaimer according to the target operation path and the action coordination scheme; An equipment management module, used to predict equipment failures of a real stacker-reclaimer and generate a maintenance plan for the real stacker-reclaimer according to the prediction results; A remote monitoring module, for generating alarm information of the real stacker-reclaimer based on the operation data of the real stacker-reclaimer and preset alarm processing rules, and displaying the operation data and alarm information of the real stacker-reclaimer in real time; The operation training result includes prompt information, correct operation behavior and evaluation information. The interactive operation module includes: A training mode selection submodule is used to obtain operation training content in response to a trigger action selected by an operator for an operation training mode; the operation training mode is a first training mode or a second training mode, the first training mode represents a mode in which the operator is trained according to a set operation sequence, the second training mode represents a mode in which the operator is trained according to a set operation sequence and randomly triggers a preset operation fault, the operation training content is a circular material yard three-dimensional layout operation, a stacker-reclaimer operation process or a fault scenario operation, and the fault scenario is an overheating of the stacker-reclaimer motor, a torn conveyor belt or a sensor failure; A third acquisition submodule is used to obtain the operation behavior information sent by the operator through the head-mounted device in the virtual environment of the three-dimensional digital twin model, wherein the operation behavior information includes operation nodes, operation gesture information, operation visual information, operation auditory information, action sequence and operation time, and the operation node represents the node of the operation sequence in the operation training content; a prompt submodule, for acquiring a target operation behavior based on the operation node, matching the operation behavior information with the target operation behavior, and if the similarity between the operation behavior information and the target operation behavior is less than a preset matching similarity threshold, generating prompt information corresponding to the similarity and displaying a correct operation behavior, wherein the prompt information is a handle vibration, an error message display or a voice prompt error message; The evaluation submodule is used to input the operation training content and the operation behavior information into a preset neural network evaluation model for multi-dimensional evaluation to obtain evaluation information. The evaluation dimensions of the neural network evaluation model include operation speed, operation action accuracy and operation response time. The neural network evaluation model is trained based on historical operation behavior information with different operation speeds, operation action accuracy and operation response time.

2. A digital twin-based stockyard stacker-reclaimer management system according to claim 1, characterized in that: The stockyard stacker-reclaimer model building module includes: A first acquisition submodule, used to acquire first geometric parameters, geographic information and environmental information of a real target material yard, and second geometric parameters of a stacker-reclaimer in the real target material yard; The second acquisition submodule is used to acquire in real time the operating state, operating environment, operating conditions of the actual stacker-reclaimer and the material stacking density of each stacker-reclaiming area in the target material yard; A physical model establishment and logic integration submodule, for establishing an initial model of the real target material yard and a stacker-reclaimer in the real target material yard according to the first geometric parameter, the geographic information, the environmental information, the second geometric parameter and the digital twin technology, and integrating the working logic of the real stacker-reclaimer into the initial model, wherein the initial model includes the mechanical characteristics, material properties and connection relationships between components of the real stacker-reclaimer; An environmental factor simulation submodule, for establishing a virtual environment corresponding to the initial model based on the metaverse technology, simulating the operation process of the virtual stacker-reclaimer under different environments in the virtual environment, and updating the simulation parameters of the initial model; a calibration submodule, for comparing the simulation parameters of the updated initial model with the actual operating data of the real target material yard and the real stacker-reclaimer, until the similarity between the simulation result and the actual operating data is greater than a set similarity threshold, and using the initial model corresponding to the similarity greater than the set similarity threshold as the three-dimensional digital twin model of the real target material yard and the stacker-reclaimer in the real target material yard; The data synchronization submodule is used to integrate the operating status, operating environment and operating conditions of the real stacker and reclaimer and the material stacking density of each stacking and reclaiming area in the real target material yard into the three-dimensional digital twin model, so that the three-dimensional digital twin model can reflect the operating status, operating environment and operating conditions of the real stacker and reclaimer and the density of each stacking and reclaiming area in the real target material yard in real time.

3. A digital twin-based stockyard stacker-reclaimer management system according to claim 1, characterized in that: The training mode selection submodule is further used for: When the operator selects the second mode, obtaining the scoring information and the first operation frequency of each operation fault, the actual historical occurrence rate of each operation fault, the total historical operation times of each operation fault, and the operation difficulty of each operation fault of the operator within the first preset time period; According to the scoring information of each of the operation faults by the operator within the first preset time period, a first weight is assigned to each of the operation faults; According to the first operation frequency of each of the operation faults by the operator within the first preset time period, assigning a second weight to each of the operation faults; assigning a third weight to each of the operation failures according to an actual historical occurrence rate of each of the operation failures; Allocating a fourth weight to each of the operation faults according to the total number of historical operations of each of the operation faults; According to the operational difficulty of each of the operational faults, assigning a fifth weight to each of the operational faults; Determining a recommended value for each of the operational faults based on the first weight, the second weight, the third weight, the fourth weight, and the fifth weight of each of the operational faults; Based on the recommended value of each of the operation faults, at least one of the operation faults that is randomly triggered in the operation training content and the number of times the operation fault is triggered are determined.

4. The digital twin-based stockyard stacker-reclaimer management system according to claim 1, characterized in that: The stacker-reclaimer simulation module is specifically used for: For any operating environment and operating condition of the virtual stacker-reclaimer, according to the set operation sequence, path selection mode and action coordination mode, the current simulation parameter combination of the virtual stacker-reclaimer is obtained, and the operating condition represents the operating conditions of the virtual stacker-reclaimer under different loads; For any operating environment and operating condition of the virtual stacker-reclaimer, simulating the virtual stacker-reclaimer based on the current simulation parameter combination to obtain a simulation result; For any operating environment and operating condition of the virtual stacker-reclaimer, based on a preset evaluation function and simulation results, the operating speed, operating accuracy, failure rate and operating energy consumption of the virtual stacker-reclaimer under the current parameter combination are evaluated to obtain an evaluation result; For any operating environment and operating condition of the virtual stacker-reclaimer, based on the evaluation result and the preset genetic algorithm, the current parameter combination is adjusted, and the virtual stacker-reclaimer is simulated according to the adjusted parameter combination until the simulation time is reached, and the parameter combination with the fastest operating speed, the highest operating accuracy, the lowest failure rate and the lowest operating energy consumption is used as the target parameter combination; For any operating environment and operating condition of the virtual stacker-reclaimer, based on the target parameter combination, the target operation path and action coordination plan of the virtual stacker-reclaimer under the operating environment and the operating condition are determined to assist the operation of the real stacker-reclaimer according to the target operation path and the action coordination plan.

5. The digital twin-based stockyard stacker-reclaimer management system according to claim 1, characterized in that: The device management module includes: A fourth acquisition submodule is used to acquire the actual operation data, historical maintenance records and recommended maintenance cycles of various components of the stacker-reclaimer; A prediction submodule, used for inputting the operation data of each component of the real stacker-reclaimer into a preset fault prediction model to obtain prediction results of each component of the real stacker-reclaimer, wherein the prediction results include service life and failure probability, and the preset fault prediction model is trained based on historical operation data; The maintenance plan generation submodule is used to generate a maintenance plan based on the prediction results of the actual components of the stacker and reclaimer, historical maintenance information and the recommended maintenance cycle of the equipment manufacturer. The maintenance plan includes the maintenance sequence of the components, maintenance time, components to be replaced and maintenance steps.

6. A digital twin-based stockyard stacker-reclaimer management system according to claim 5, characterized in that: The maintenance plan generation submodule is specifically used for: The component whose service life is less than the set service life or whose failure probability is greater than the set failure probability is taken as the target component; Obtain maintenance time, parts to be replaced, maintenance steps, production impact, and parts inventory information for each target part; Based on the prediction results of each target component, historical maintenance information, the recommended maintenance cycle of the equipment manufacturer and a preset data fusion algorithm, the health value of each target component is determined, and the health value represents the risk level of the target component; Generate an initial maintenance plan based on the health value of each target component, the maintenance time of each target component, and the components and maintenance steps to be replaced; Based on a preset optimization algorithm, component inventory information and the production impact of each target component, the preliminary maintenance plan is optimized to obtain the real stacker-reclaimer maintenance plan in which the production cost meets the set cost threshold and the maintenance efficiency meets the set efficiency threshold.

7. The digital twin-based stockyard stacker-reclaimer management system according to claim 1, characterized in that: The remote monitoring module is specifically used for: For each component of the real stacker-reclaimer, compare the temperature of the component with a set temperature threshold corresponding to the component, and if the temperature exceeds the set temperature threshold, determine that the real stacker-reclaimer has a first abnormality; For each component of the real stacker-reclaimer, the humidity of the component is compared with a set humidity threshold corresponding to the component, and if the humidity exceeds the set humidity threshold, it is determined that the real stacker-reclaimer has a second abnormality; For each component of the real stacker-reclaimer, the pressure of the component is compared with a set pressure threshold corresponding to the component, and if the pressure exceeds the set pressure threshold, it is determined that the real stacker-reclaimer has a third abnormality; For each component of the real stacker-reclaimer, a vibration value of the component is compared with a set vibration threshold value corresponding to the component, and if the vibration value exceeds the set vibration threshold value, it is determined that the real stacker-reclaimer has a fourth abnormality; For each component of the real stacker-reclaimer, the displacement of the component is compared with a set displacement threshold corresponding to the component, and if the displacement is greater than the set displacement threshold, it is determined that the real stacker-reclaimer has a fifth abnormality; Based on the first abnormality, the second abnormality, the third abnormality, the fourth abnormality and the fifth abnormality, alarm information of the real stacker and reclaimer is generated, and operating data and alarm information of the real stacker and reclaimer are displayed in real time.

8. The digital twin-based stockyard stacker-reclaimer management system according to claim 4, characterized in that: The remote monitoring module is also used for: Obtaining material stacking density change information, material type, and stacking and reclaiming plan and operation data of the real stacker and reclaimer in the current time period in each stacker and reclaimer area in the real target material yard, wherein the stacker and reclaimer plan includes the target operation path and action coordination scheme of the real stacker and reclaimer; Inputting the material stacking density change information of each stacking and reclaiming area, the stacking and reclaiming plan and the operating data into a preset energy efficiency evaluation model to obtain the operating energy consumption of each stacking and reclaiming area and the actual operating efficiency of the stacker and reclaimer; Determining a first priority value for each of the stacking and reclaiming areas based on the operating energy consumption of each of the stacking and reclaiming areas; Determining a second priority value for each of the stacking and reclaiming areas based on the material stacking density of each of the stacking and reclaiming areas; Determining a third priority value for each of the stacking and reclaiming areas based on a material type of each of the stacking and reclaiming areas; Determining the priority of each of the stacking and reclaiming areas based on the first priority value, the second priority value and the third priority value of each of the stacking and reclaiming areas; Based on the priority of each of the stacking and reclaiming areas and a preset path adjustment strategy, adjusting the stacking and reclaiming path of the real stacker and reclaimer in the next time period; Based on the priority of the stacking and reclaiming area and the operation efficiency, the target stacking and reclaiming speed of the real stacker and reclaimer in the next time period is adjusted.

9. The digital twin-based stockyard stacker-reclaimer management system according to claim 2, characterized in that: The second acquisition submodule includes: A plurality of temperature sensors, used for detecting the temperature of each component of the real stacker-reclaimer, and sending the temperature of all components to the corresponding edge computing device; A plurality of humidity sensors, used for detecting the humidity of various components of the real stacker-reclaimer, and sending the humidity of all components to the corresponding edge computing device; A plurality of pressure sensors, used for detecting the pressure of various components of the real stacker-reclaimer, and sending the pressure of all components to the corresponding edge computing device; A plurality of vibration sensors, used for detecting vibration values ​​of various components of the real stacker and reclaimer, and sending the vibration values ​​of all components to corresponding edge computing devices; A plurality of displacement sensors, used for detecting the displacement of various components of the real stacker-reclaimer, and sending the displacement of all components to the corresponding edge computing device; An environment collection unit, used to collect the environmental parameters of the real target material yard, wherein the environmental parameters include temperature, humidity, wind speed, wind direction, light intensity and visibility; A stacker-reclaimer load detection unit, used to detect the actual load condition of the stacker-reclaimer and obtain the actual operating condition of the stacker-reclaimer; A plurality of material stacking density acquisition units, used to measure the material stacking density of each stacking and reclaiming area of ​​the real target material yard; Multiple edge computing devices are used to preprocess the temperatures, humidity, pressures, vibration values, displacements, operating conditions, environmental parameters of the real target material yard, and material stacking densities in each stacking and reclaiming area of ​​the real target material yard, and upload the preprocessed data to the three-dimensional digital twin model of the real stacker and reclaimer.

Images