A multi-objective optimization scheduling method, device, and computer equipment for mine mining equipment based on digital twins.

Abstract

This application applies to the field of mining technology, providing a method, apparatus, and computer device for multi-objective optimization scheduling of mining equipment based on digital twins. The method includes: acquiring mining operation parameters and mining equipment parameters, and inputting these parameters into a multi-objective optimization model to obtain a set of candidate scheduling schemes. For each candidate scheduling scheme, the scheme is input into a target simulation model constructed based on digital twin technology to obtain equipment operation data. Based on the equipment operation data corresponding to the multiple candidate scheduling schemes, a target scheduling scheme is determined from the set of candidate schemes. The target scheduling scheme is used for optimal scheduling of mining equipment during the mining operation. This application achieves scientific, efficient, and highly robust scheduling of mining equipment through a closed-loop combination of multi-objective optimization and digital twin simulation.

Description

Technical Field

[0001] This application relates to the field of mining technology, and in particular to a multi-objective optimization scheduling method, device and computer equipment for mining recovery equipment based on digital twins. Background Technology

[0002] With the continuous development of mining technology, the complexity of mining operations has increased significantly, and the scheduling of mining equipment such as drilling rigs, loaders, and mining trucks has become a key factor restricting the efficient operation of mines.

[0003] However, traditional equipment scheduling methods are usually based on human experience to schedule mining equipment, which can easily lead to problems such as information lag and poor coordination, thus affecting the operating efficiency of mining equipment. Summary of the Invention

[0004] In view of this, the embodiments of this application provide a multi-objective optimization scheduling method, device and computer equipment for mining recovery equipment based on digital twins, which can realize the accurate determination of scheduling schemes, thereby improving the operating efficiency of mining recovery equipment.

[0005] Firstly, this application provides a multi-objective optimization scheduling method for mine recovery equipment based on digital twins, including: Obtain the parameters of the mining operation and the mining equipment, and input these parameters into a multi-objective optimization model to obtain a set of candidate scheduling schemes; the set of candidate scheduling schemes includes multiple candidate scheduling schemes. For each candidate scheduling scheme, the candidate scheduling scheme is input into the target simulation model to obtain equipment operation data; Based on the equipment operation data corresponding to multiple candidate scheduling schemes, a target scheduling scheme is determined from the set of candidate scheduling schemes; the target scheduling scheme is used to optimally schedule the mining equipment during the mining operation.

[0006] Secondly, this application provides a multi-objective optimization scheduling device for mining equipment based on digital twins, comprising: The set determination unit is used to obtain the mining operation parameters and mining equipment parameters, and input the mining operation parameters and mining equipment parameters into the multi-objective optimization model to obtain a set of candidate scheduling schemes; wherein, the set of candidate scheduling schemes includes multiple candidate scheduling schemes; The data determination unit is used to input the candidate scheduling scheme into the target simulation model for each candidate scheduling scheme to obtain equipment operation data; The scheme determination unit is used to determine the target scheduling scheme from the set of candidate scheduling schemes based on the equipment operation data corresponding to multiple candidate scheduling schemes; wherein, the target scheduling scheme is used to perform optimal scheduling of mining equipment during the mining operation.

[0007] Thirdly, this application provides a storage medium on which a computer program is stored, which, when executed by a processor, implements the above-mentioned multi-objective optimization scheduling method for mining equipment based on digital twins.

[0008] Fourthly, this application provides a computer device, including a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor. When the processor executes the program, it implements the above-mentioned multi-objective optimization scheduling method for mining equipment based on digital twins.

[0009] By employing the above technical solutions, this application provides a multi-objective optimization scheduling method, apparatus, and computer equipment for mining equipment based on digital twins. This invention generates a set of candidate scheduling schemes by inputting mining operation parameters and mining equipment parameters into a multi-objective optimization model, covering the possibilities of optimal solutions under different working conditions. Then, it simulates each candidate scheduling scheme using a target simulation model to obtain accurate equipment operation data. Finally, based on this equipment operation data, it selects the optimal scheduling scheme from the candidate schemes. In this way, scientific and efficient scheduling of mining equipment can be achieved, reducing situations such as process waiting and equipment conflicts caused by unreasonable scheduling of mining equipment, optimizing the synergy of the mining operation process, ensuring the safe and stable operation of the mining process, and improving the operating efficiency of mining equipment.

[0010] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, specific embodiments of this application are given below. Attached Figure Description

[0011] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings: Figure 1 This paper shows a schematic diagram of the structure of a multi-objective optimization scheduling system for mining equipment provided in an embodiment of this application; Figure 2 This paper illustrates a flowchart of a multi-objective optimization scheduling method for mining equipment based on digital twins, as provided in an embodiment of this application. Figure 3This illustration shows a flowchart of a method for determining a set of candidate scheduling schemes according to an embodiment of this application; Figure 4 This illustration shows a flowchart of a target simulation model provided in an embodiment of this application; Figure 5 This paper illustrates a flowchart of another multi-objective optimization scheduling method for mine mining equipment based on digital twin, provided in an embodiment of this application. Figure 6 This paper illustrates a schematic diagram of a multi-objective optimization scheduling device for mining equipment based on digital twins, provided in an embodiment of this application. Figure 7 This paper presents a schematic diagram of another multi-objective optimization scheduling device for mining equipment based on digital twins, as provided in an embodiment of this application. Detailed Implementation

[0012] To facilitate the explanation of the embodiments of this application, some technical terms and technical means related to the embodiments of this application, as well as the application scenarios of the embodiments of this application, will be introduced first below.

[0013] In some cases, considering the complexity of working conditions in mining operations, the efficiency of mining operations can be ensured by rationally scheduling mining equipment, optimizing equipment operation sequence, running paths, and load distribution, thereby improving overall mining efficiency and guaranteeing the safe and stable operation of mining operations. Mining equipment refers to the mechanical equipment that directly participates in core processes such as ore extraction, transportation, and transshipment in underground or open-pit mining operations, and whose location dynamically changes with the progress of the operation. It is the core carrier of mining efficiency and safety. Examples of such mining equipment include rock drilling rigs, loaders, and mining trucks.

[0014] In one example, the scheduling method for the aforementioned mining equipment is typically based on manual experience. However, manual experience-based scheduling relies on the scheduler's subjective judgment and accumulated experience regarding the actual working conditions. In mining scenarios, equipment is widely distributed, work processes are closely linked, and the equipment is affected by dynamic factors such as roadway environment, equipment status, and ore reserves. Therefore, manual experience-based scheduling is prone to problems such as information lag and poor coordination, resulting in long equipment waiting times, frequent roadway congestion, and reduced equipment operating efficiency.

[0015] In another example, the scheduling method for the aforementioned mining equipment can also be based on a single-objective optimization model. That is, this method can only optimize the scheduling scheme for one objective, thus obtaining the optimal scheduling scheme under that objective. For example, this objective could be maximizing production efficiency or minimizing production costs. This not only makes it difficult to balance the multi-dimensional needs of mine production, but also, because single-objective optimization models are usually built based on preset fixed parameters and constraints, they fail to fully consider the dynamic uncertainties in real-world mine production scenarios, such as sudden equipment failures, changes in transportation route efficiency, and fluctuations in geological conditions at the mining site. This results in a disconnect between the optimal scheduling scheme output by the single-objective optimization model and the actual production scenario, easily leading to problems such as insufficient feasibility and large deviations between the actual and theoretical values ​​of the objective function, failing to meet the core requirements of reliable and practical scheduling schemes for mining operations.

[0016] Therefore, to ensure the reliability of the scheduling scheme and thus improve the operating efficiency of mining equipment, this application provides a multi-objective optimization scheduling method for mining equipment based on digital twins, applied to mining operation scenarios. In this method, mining operation parameters and mining equipment parameters are obtained and input into a multi-objective optimization model to obtain a set of candidate scheduling schemes. The set of candidate scheduling schemes includes multiple candidate scheduling schemes. Then, for each candidate scheduling scheme, it is input into a target simulation model to obtain equipment operating data. Finally, based on the equipment operating data corresponding to the multiple candidate scheduling schemes, a target scheduling scheme is determined from the set of candidate scheduling schemes. The target scheduling scheme is used for optimal scheduling of mining equipment during the mining operation process.

[0017] In this embodiment, a set of candidate scheduling schemes is generated by inputting the mine mining operation parameters and mining equipment parameters into a multi-objective optimization model to cover the possibilities of optimal solutions under different working conditions. Then, the candidate scheduling schemes are simulated using a target simulation model to obtain accurate equipment operation data. Based on this equipment operation data, the optimal scheduling scheme is selected from the candidate schemes. This enables scientific and efficient scheduling of mine mining equipment, reducing situations such as process waiting and equipment conflicts caused by unreasonable scheduling of mining equipment, optimizing the synergy of the mine mining operation process, ensuring the safe and stable operation of the mine mining process, and improving the operating efficiency of the mining equipment.

[0018] The present application will be described in detail below with reference to the accompanying drawings and embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in the embodiments of the present application can be combined with each other.

[0019] like Figure 1 As shown in the figure, this application provides a multi-objective optimization scheduling system 100 for mining equipment, including: a model building module 110, a multi-objective optimization module 120, a simulation and measurement module 130, and a scheme determination module 140.

[0020] The aforementioned model construction module 110 is used to construct a multi-objective optimization model and an objective simulation model. The objective simulation model is used to verify the feasibility, rationality, and operational effectiveness of candidate scheduling schemes. The multi-objective optimization model includes a first objective optimization function and a second objective optimization function. The first objective optimization function aims to maximize the operating efficiency of the mining equipment, and the second objective optimization function aims to minimize the operating cost of the mining equipment. In other words, the optimization objectives of the multi-objective optimization model include maximizing the operating efficiency of the mining equipment and minimizing its operating cost. In some embodiments of this application, the multi-objective optimization model can be constructed based on the Fast and Elitist Non-dominated Sorting Genetic Algorithm II (NSGA-II). In other embodiments, the multi-objective optimization model can also be constructed based on multi-objective optimization algorithms such as NSGA-III, MOEA / D, and MOPSO.

[0021] The aforementioned multi-objective optimization module 120 is used to input the acquired mine recovery operation parameters and mine recovery equipment parameters into the aforementioned multi-objective optimization model, thereby obtaining a set of candidate scheduling schemes that balance operation efficiency and operation cost. The aforementioned simulation and testing module 130 is used to input each candidate scheduling scheme included in the candidate scheduling scheme set into the aforementioned target simulation model, thereby obtaining equipment operation data including equipment spatial coordination and temporal linkage. The equipment operation data may include operation data and equipment operation data recorded at preset time intervals. Operation data includes at least equipment location, equipment status, mine recovery output, and mine recovery cost. Equipment operation data includes at least equipment waiting time, road congestion frequency, and equipment idle rate.

[0022] The aforementioned scheme determination module 140 is used to determine the target scheduling scheme from the candidate scheduling scheme set based on the equipment operation data output by the target simulation model. The target scheduling scheme is used to optimally schedule the mining equipment during the mining operation. In other words, scheduling the mining equipment through this target scheduling scheme can reduce situations such as process waiting and equipment conflicts caused by unreasonable scheduling of mining equipment, optimize the coordination of the mining operation process, ensure the safe and stable operation of the mining process, and improve the operating efficiency of the mining equipment.

[0023] In some embodiments, such as Figure 1 As shown, when the model building module 110 constructs a multi-objective optimization model and a target simulation model, step a can be executed to send the multi-objective optimization model to the multi-objective optimization module 120, so that the multi-objective optimization module 120 can use the multi-objective optimization model to output a set of candidate scheduling schemes. Simultaneously, step b can be executed to send the target simulation model to the simulation and testing module 130, so that the simulation and testing module 130 can use the target simulation model to output the equipment operation data corresponding to each candidate scheduling scheme.

[0024] Upon receiving the multi-objective optimization model from the model building module 110, the multi-objective optimization module 120 inputs the acquired mine recovery operation parameters and mine recovery equipment parameters into the multi-objective optimization model to obtain a set of candidate scheduling schemes. Then, the multi-objective optimization module 120 can execute step c, sending the set of candidate scheduling schemes to the simulation and testing module 130. Upon receiving the set of candidate scheduling schemes from the multi-objective optimization module 120, the simulation and testing module 130 inputs each of the candidate scheduling schemes into the target simulation model, thereby obtaining the equipment operation data corresponding to each candidate scheduling scheme. Then, the simulation and testing module 130 can execute step d, sending the equipment operation data corresponding to each candidate scheduling scheme to the scheme determination module 140. Upon receiving the equipment operation data corresponding to each candidate scheduling scheme from the simulation and testing module 130, the scheme determination module 140 can determine the target scheduling scheme from the set of candidate scheduling schemes based on this data.

[0025] Simultaneously, the scheme determination module 140 can also calculate the deviation ratio between the mine recovery output and the theoretical output included in the equipment operation data, and the deviation ratio between the mine recovery cost and the theoretical cost included in the equipment operation data. Subsequently, if the deviation ratio between the mine recovery output and the theoretical output is not within the first deviation ratio range, and / or the deviation ratio between the mine recovery cost and the theoretical cost is not within the second deviation ratio range, the scheme determination module 140 can adjust the model parameters and constraints of the multi-objective optimization model. Then, the scheme determination module 140 can execute step e, sending the adjusted multi-objective optimization model to the multi-objective optimization module 120.

[0026] Furthermore, this embodiment provides a multi-objective optimization scheduling method for mine recovery equipment based on digital twins, such as... Figure 2 As shown, the method includes: S101: Obtain the mining operation parameters and mining equipment parameters, and input the mining operation parameters and mining equipment parameters into the multi-objective optimization model to obtain a set of candidate scheduling schemes.

[0027] The mining operation parameters may include information on mining stope units, transport routes, and mining operations. Stope unit information may include the number of stope units, the amount of ore in each unit, and the ore's bulking coefficient. Transport route information may include the number of transport roadways in the mine, the maximum speed of the mining equipment in each transport roadway, and the maximum speed of the mining equipment when traversing sections with a gradient higher than a preset value. Mining operation information may include the operating period of the mining equipment and the maintenance duration for each operation. In some embodiments of this application, the number of stope units is 12, the amount of ore in each unit is 27,000 tons, and the ore's bulking coefficient is 1.5. There are 5 transport roadways. The maximum travel speed of the mining equipment in each transport roadway is 8 kilometers per hour (km / h). In other words, the normal travel speed of the mining equipment in each transport roadway should be less than or equal to 8 km / h. The maximum travel speed of the mining equipment when traversing sections with an angle greater than 10 degrees (°) is 5 km / h. The operating hours of the mining equipment are 8:00-16:00, and the maintenance time for a single operation is 30 minutes (min).

[0028] Accordingly, the parameters for mining equipment can include the number of each functional device, operating costs, troubleshooting time, working capacity, and the slowest connection time between different functional devices. Functional devices can include drilling rigs, loaders, mining trucks, and other similar equipment. For example, if the functional device is a drilling rig, the number of units can be 3, the operating cost can be 320 yuan / hour, the troubleshooting time is 45 minutes, and the drilling efficiency is 2.5 meters / minute (m / min). If the functional device is a loader, the number of units can be 4, the operating cost can be 280 yuan / hour, the troubleshooting time is 30 minutes, and the loading capacity is 4.5 cubic meters / load. If the functional device is a mining truck, the number of units can be 6, the operating cost can be 450 yuan / hour, the troubleshooting time is 60 minutes, and the load capacity is 42 tons / truck. The slowest connection time between the drilling rig and the loader is 20 minutes, and the slowest connection time between the loader and the mining truck is 15 minutes.

[0029] In some cases, the above-mentioned mining operation parameters and mining equipment parameters can be determined based on the operation parameters and equipment parameters under actual working conditions.

[0030] Furthermore, after obtaining the aforementioned mine recovery operation parameters and mine recovery equipment parameters, these parameters can be input into a multi-objective optimization model to obtain a set of candidate scheduling schemes. The multi-objective optimization model is constructed based on the Fast and Elitist Non-dominated Sorting Genetic Algorithm II (NSGA-II) algorithm. The NSGA-II algorithm is used to find a Pareto optimal solution that considers all optimization objectives under multiple conflicting optimization objectives. A Pareto optimal solution can also be called a non-dominated solution. In some embodiments of this application, the optimization objective can be maximizing the operating efficiency of the mine recovery equipment, minimizing the operating cost of the mine recovery equipment, etc.

[0031] The aforementioned candidate scheduling scheme set may include multiple candidate scheduling schemes. In some embodiments of this application, the number of candidate scheduling schemes may be preset according to actual needs. For example, the number of candidate scheduling schemes may be 20, 30, etc., and is not specifically limited. In other embodiments of this application, the number of candidate scheduling schemes may not be limited, that is, the candidate scheduling scheme set may include any number of candidate scheduling schemes.

[0032] In some cases, the aforementioned multi-objective optimization model can also be constructed based on multi-objective optimization algorithms such as NSGA-Ⅲ, MOEA / D, and MOPSO.

[0033] In one implementation, such as Figure 3 As shown, the process of determining the above-mentioned set of candidate scheduling schemes may specifically include: S201 generates an initial scheduling scheme set based on the mining operation parameters and mining equipment parameters.

[0034] The number of schemes included in the initial scheduling scheme set is preset according to actual needs. In some embodiments of this application, the number of schemes included in the initial scheduling scheme set can be 100, that is, the initial scheduling scheme set can include 100 initial scheduling schemes. In other embodiments, the number of schemes included in the initial scheduling scheme set can be 150, 200, etc., and there is no specific limitation.

[0035] S202, according to the optimization objective corresponding to the multi-objective optimization model, the initial scheduling scheme set includes multiple initial scheduling schemes, which are hierarchically divided to obtain multiple scheduling scheme groups.

[0036] Specifically, after generating the aforementioned initial scheduling scheme set, the multiple initial scheduling schemes included in the initial scheduling scheme set can be divided into non-dominated hierarchical groups according to the optimization objectives corresponding to the multi-objective optimization model. The multi-objective optimization model can include a first objective optimization function and a second objective optimization function. The first objective optimization function aims to maximize the operating efficiency of the mining equipment, and the second objective optimization function aims to minimize the operating cost of the mining equipment. In other words, the optimization objectives corresponding to the multi-objective optimization model include maximizing the operating efficiency of the mining equipment and minimizing the operating cost of the mining equipment.

[0037] In some cases, for each initial scheduling scheme in the initial scheduling scheme set, the initial scheduling scheme is input into a first objective optimization function to obtain the corresponding job efficiency. Then, the initial scheduling scheme is input into a second objective optimization function to obtain the corresponding job cost. Afterwards, based on the job efficiency and job cost corresponding to the multiple initial scheduling schemes, the multiple initial scheduling schemes are hierarchically divided to obtain multiple scheduling scheme groups. It can be understood that the higher the level of the scheduling scheme group, the higher the quality of the initial scheduling schemes within the scheduling scheme group. That is, if a scheduling scheme group is at the first front, it means that the initial scheduling schemes within that scheduling scheme group are Pareto optimal solutions within the initial scheduling scheme set.

[0038] In one implementation, the first objective optimization function described above can be represented by the following expression: Expression 1; in, The job efficiency corresponding to the initial scheduling scheme; The total ore output of all mining units within a single operation; This refers to the total operating time of the mining equipment. For example, this total operating time can be the sum of the operating times of 3 drilling rigs, 4 loaders, and 6 mining trucks.

[0039] In another implementation, the second objective function described above can be represented by the following expression: Expression 2; in, This represents the job cost corresponding to the initial scheduling scheme; The total operating cost of mining equipment in a single operation; The total ore output of all mining units within a single operation; The operating costs of the rock drilling rig; This refers to the total operating time of the rock drilling rig. For the operating costs of the loader; This refers to the total operating time of the loader; Operating costs for mining trucks; This represents the total operating time of the mining truck.

[0040] In some cases, the aforementioned multi-objective optimization model may also include multiple constraints, such as work sequence constraints, equipment quantity constraints, roadway transportation constraints, and work duration constraints. The work sequence constraint requires each mining unit to follow the work flow of drilling first, then loading, and finally transporting, and prohibits premature entry into the next work process. Equipment quantity constraints may include a maximum of one drilling rig and two loaders per mining unit, a maximum of three mining trucks in the same transport roadway, and the number of each functional piece of equipment must not exceed the actual configuration of the functional equipment, i.e., it must not exceed the number of equipment included in the aforementioned mine recovery equipment parameters. Roadway transportation constraints may include mining truck speeds meeting roadway slope requirements, a safe distance of at least 5 meters between vehicles at avoidance points, and prohibition of reverse driving. Work duration constraints may include a continuous working time of no more than 4 hours for each mine recovery equipment, and a cumulative working time for a single operation not exceeding 7 hours. It should be understood that the cumulative working time for a single operation does not include the maintenance time for that single operation.

[0041] S203, For each scheduling scheme group, calculate the congestion degree of each initial scheduling scheme included in the scheduling scheme group to obtain the congestion degree of each initial scheduling scheme.

[0042] Specifically, after obtaining the aforementioned multiple scheduling scheme groups, the congestion degree of each initial scheduling scheme included in each group is calculated to obtain the congestion degree of the initial scheduling scheme. The congestion degree measures the sparseness of the initial scheduling schemes within the objective optimization space, representing the distance between the initial scheduling scheme and its neighboring scheduling schemes. The objective optimization space is a multi-dimensional function space composed of the optimization objectives corresponding to the multi-objective optimization model.

[0043] It's understandable that a higher crowding level for an initial scheduling scheme indicates fewer surrounding schemes, meaning a more even distribution of the initial scheduling schemes within the target optimization space. Conversely, a lower crowding level indicates more surrounding schemes, meaning a more chaotic distribution of the initial scheduling schemes within the target optimization space. In other words, calculating the crowding level of each initial scheduling scheme reduces the likelihood of all high-quality scheduling schemes within the initial scheme set residing in the same region, ensuring diversity of high-quality scheduling schemes and providing the necessary conditions for accurately determining the candidate scheduling scheme set.

[0044] S204. Determine a new set of initial scheduling schemes based on the congestion of multiple initial scheduling schemes in the initial scheduling scheme set.

[0045] Specifically, after obtaining the congestion levels of each of the above initial scheduling schemes, a new set of initial scheduling schemes can be determined based on the congestion levels of each initial scheduling scheme.

[0046] In one implementation, a preset number of initial scheduling schemes with the highest congestion in the initial scheduling scheme set can be used as the parent scheduling scheme set. The preset number can be pre-set according to actual needs; for example, it could be 20. Then, a genetic operation is performed on the parent scheduling scheme set to obtain a child scheduling scheme set. This genetic operation can include crossover and / or mutation operations. The number of schemes in the child scheduling scheme set is the same as the number of schemes in the parent scheduling scheme set. Finally, the child scheduling scheme set and the parent scheduling scheme set are combined to form a new initial scheduling scheme set.

[0047] Optionally, when the genetic operations include crossover and mutation operations, the parent scheduling scheme set can be subjected to a crossover operation according to the crossover probability. Upon detection that the crossover operation on the parent scheduling scheme set is complete, a mutation operation is performed on the parent scheduling scheme set according to the mutation probability to obtain the child scheduling scheme set. The crossover and mutation probabilities can be preset according to actual needs, or adjusted based on the deviation ratio between the mine's recovered output and theoretical output, and the deviation ratio between the mine's recovered cost and theoretical cost; there are no specific limitations. For example, the crossover probability can be 0.8, and the mutation probability can be 0.04.

[0048] S205, determine whether the number of iterations of the multi-objective optimization model has reached the preset number of iterations.

[0049] Specifically, after obtaining the new initial scheduling scheme set, it can be determined whether the number of iterations of the multi-objective optimization model has reached the preset number of iterations. The preset number of iterations can be pre-set according to actual needs. For example, the preset number of iterations can be 300, 200, etc., without specific limitations.

[0050] In some embodiments, if the number of iterations of the multi-objective optimization model reaches a preset number of iterations, it indicates that the multi-objective optimization model is in a convergent state. Therefore, to reduce unnecessary resource waste, a new initial scheduling scheme set can be directly determined as the candidate scheduling scheme set. However, if the number of iterations of the multi-objective optimization model does not reach the preset number of iterations, it indicates that the multi-objective optimization model is not in a convergent state and the scheduling scheme still needs to be optimized. Therefore, to improve the accuracy of candidate scheduling scheme determination, the process can return to step S202 above until the number of iterations of the multi-objective optimization model reaches the preset number of iterations.

[0051] S206, the new initial scheduling scheme set is determined as the candidate scheduling scheme set.

[0052] Specifically, after determining that the number of iterations of the aforementioned multi-objective optimization model has reached the preset number of iterations, the new initial set of scheduling schemes is directly determined as the candidate scheduling scheme set. This reduces unnecessary intermediate processing and redundant calculations, making the multi-objective optimization process simpler and more efficient. While ensuring that the optimization results meet scheduling requirements, it shortens the model's running time, improves the overall response speed and stability of scheduling decisions, and facilitates the rapid acquisition of reliable candidate scheduling schemes in complex scheduling scenarios.

[0053] It is understood that the aforementioned set of candidate scheduling schemes may include candidate scheduling schemes corresponding to different objective optimization scenarios. Here, the objective optimization scenario is used to characterize the degree of optimization of the corresponding optimization objective of the aforementioned multi-objective optimization model. In other words, the set of candidate scheduling schemes may include candidate scheduling schemes with "high efficiency and high cost," "medium efficiency and medium cost," and "low efficiency and low cost."

[0054] For example, as shown in Table 1, taking the above candidate scheduling scheme set including three candidate scheduling schemes as an example, Scheme 3 is a candidate scheduling scheme of "high efficiency-high cost", Scheme 8 is a candidate scheduling scheme of "medium efficiency-medium cost", and Scheme 15 is a candidate scheduling scheme of "low efficiency-low cost". Among them, the total ore output per shift of Scheme 3 is 8200 tons, the operating cost per ton of ore is 16.8 yuan, the total operating time of the drilling rig is 19.5 hours, the total operating time of the loader is 26.2 hours, and the total operating time of the mining truck is 38.8 hours. The total ore output per shift of Scheme 8 is 7600 tons, the operating cost per ton of ore is 15.2 yuan, the total operating time of the drilling rig is 17.8 hours, the total operating time of the loader is 24.5 hours, and the total operating time of the mining truck is 35.6 hours. Scheme 15 has a total single-shift ore output of 7,000 tons, an operating cost of 14.1 yuan per ton of ore, a total operating time of 16.2 hours for the rock drilling rig, a total operating time of 22.8 hours for the loader, and a total operating time of 32.4 hours for the mining truck.

[0055] Table 1 Summary of Job Information for Candidate Scheduling Schemes

[0056] S102, for each candidate scheduling scheme, input the candidate scheduling scheme into the target simulation model to obtain equipment operation data.

[0057] Specifically, after obtaining the aforementioned set of candidate scheduling schemes, each candidate scheduling scheme can be input into the target simulation model to obtain the equipment operation data corresponding to each candidate scheduling scheme. The target simulation model is used to verify the feasibility, rationality, and operational effectiveness of the candidate scheduling schemes.

[0058] In some cases, the aforementioned equipment operation data may include work data and equipment operation data recorded at preset time intervals. The preset time intervals can be pre-set according to actual conditions. For example, the preset time interval could be 30 seconds, 1 minute, etc., with no specific limitation. Work data includes at least equipment location, equipment status, mine recovery output, and mine recovery cost. Equipment operation data includes at least equipment waiting time, number of road congestion incidents, and equipment idle time rate.

[0059] Optionally, the candidate scheduling schemes mentioned above are converted according to a preset data format. The preset data format can be JSON data format. Then, the candidate scheduling schemes conforming to the preset data format are input into the target simulation model to obtain equipment operation data. The simulation period of the target simulation model is the same as the operating time period of the mining equipment included in the above mining operation parameters, that is, the simulation period is 8 hours, and 12:00-12:30 is the maintenance period for a single operation. Simultaneously, the time step of the target simulation model is 1 minute / step to ensure precise simulation of the operation sequence and equipment movement.

[0060] In one implementation, such as Figure 4 As shown, the construction process of the above-mentioned target simulation model may specifically include: S301, acquire model building data and preprocess the model building data. The model building data may include static data and dynamic data.

[0061] The aforementioned static data may include 3D mine data, equipment parameter data, stope layout data, and transportation route data. The 3D mine data may include a roadway topographic map, with elevation and dimensional errors within a preset range. For example, this roadway topographic map could be a 1:200 scale map, with a preset elevation error range of -0.2 to 0.2 meters and a preset dimensional error range of -3 to 3 millimeters. Equipment parameter data may include the geometric dimensions, rated power, operating costs, fault handling time, maximum travel speed, braking distance, and fuel consumption rate of various functional equipment. Stope layout data may include drawings showing the division of various stope units within the mine, mining sequence, working face dimensions, drill hole layout, ore loosening coefficient, and safety distance requirements for loading operations. It is understood that this static data may originate from mine equipment ledgers, manufacturer technical manuals, and geographic information systems.

[0062] In some cases, the aforementioned dynamic data refers to the operational data of IoT devices collected over a preset time period. These IoT devices can be Ultra Wide Band (UWB) positioning base stations or sensors located underground in mines. The preset time period can be pre-set according to actual needs. For example, the preset time period can be 3 months, 4 months, etc., with no specific limitation.

[0063] Specifically, dynamic data can include equipment location, equipment status, equipment operating time, equipment traffic efficiency, and fault handling time. The positioning accuracy of the equipment location must be within a preset positioning error range. For example, this preset positioning error range could be -0.5 to 0.5 m. Equipment status can be in operating state, standby state, or fault state. Equipment traffic efficiency can be the average travel speed of mining equipment in the main roadway, the average waiting time of mining equipment at intersections of avoidance points, etc.

[0064] Accordingly, after obtaining the aforementioned model construction data, preprocessing can be performed on this data. Preprocessing may include at least one of the following: data cleaning, standardization, and correlation integration. Data cleaning refers to deleting abnormal data collected by IoT devices. For example, deleting instantaneous speeds of devices exceeding twice their rated speed. Standardization refers to converting device locations to a unified mine coordinate system. Correlation integration refers to establishing spatial relationships from the mining unit to the mining equipment to the transportation route. For example, this spatial relationship could be that mining unit 3 corresponds to transportation route 2, and transportation route 2 only allows the passage of loaders and mining trucks.

[0065] S302, Construct an initial simulation model based on the preprocessed static data.

[0066] Specifically, after the data preprocessing for the aforementioned model construction is completed, an initial simulation model can be constructed based on the preprocessed static data. This initial simulation model may include a working environment model and a 3D model of the equipment. This initial simulation model is constructed using 3D modeling software and is based on digital twin technology. Digital twin technology constructs a dynamic digital mirror image of a physical entity in virtual space, achieving perception, prediction, and optimization of the physical entity's entire lifecycle through real-time data synchronization, simulation analysis, and closed-loop control. In some embodiments of this application, the 3D modeling software can be Blender software. In other embodiments, the 3D modeling software can also be 3ds Max software, C4D software, etc., without specific limitations.

[0067] In some cases, the construction process of the aforementioned operational environment model may specifically include: reconstructing the mine topography based on the 3D mine data included in the aforementioned static data, and setting the width of the main haulage roadway to 5m and the maximum slope to 12°. Simultaneously, based on the 3D mine data, three avoidance points are set, located at K1+200m, K2+500m, and K3+800m respectively, and the geometry of the unloading points concentrated in the underground crushing station is configured, along with the actual rock material matching the texture of the roadway inner wall. The 3D coordinates of the underground crushing station are: horizontal X = 32500m, vertical Y = 18600m, and depth Z = -520m. Then, based on the stope layout data included in the aforementioned static data, 12 stope units within the mine are set, and the mining sequence of each stope unit is marked. Each stope unit has a length of 40m, a width of 25m, and a height of 18m.

[0068] In other cases, the construction process of the aforementioned 3D equipment model may specifically include: constructing 3D models of equipment such as rock drilling rigs, loaders, and mining trucks at a 1:1 scale, based on the equipment parameter data included in the static data. These 3D models include movable parts such as the operator's cab and working devices. For example, the working devices may include a drilling arm, bucket, and truck body. It should be noted that the geometrical dimensional errors between the 3D equipment model and the functional equipment are within a preset dimensional error range, which can be -2 to 2 mm. Simultaneously, it is ensured that the appearance and structure of the 3D equipment model are consistent with the actual functional equipment.

[0069] S303: Based on the preprocessed dynamic data, a physics engine with equipment kinematics simulation and environmental interaction simulation is established, and the equipment operation logic is designed.

[0070] Specifically, after the data preprocessing for the aforementioned model construction is completed, a physics engine capable of simulating equipment kinematics and environmental interactions can be established based on the preprocessed dynamic data. In some embodiments of this application, the physics engine can be the Chaos physics engine of Unreal Engine 5.2. The Chaos physics engine is a built-in physics engine of Unreal Engine (UE), used to construct the underground working environment to achieve high-fidelity simulation of the motion of functional equipment and the interaction between the equipment and the tunnel environment. In other embodiments, the physics engine can also be Unity's NVIDIA PhysX physics engine, CryEngine physics system, etc., without specific limitations.

[0071] In some cases, the configuration process for the kinematic simulation of the aforementioned equipment may specifically include: setting the rotation angle of the drilling arm in the drilling rig to -90° to 90°, the lifting speed of the bucket in the loader to 0.8 m / s, and the driving acceleration of the mining truck to 0.5 m / s². 2 The braking deceleration is 1.2 m / s². 2 It should be noted that the settings parameters configured in the equipment kinematics simulation are matched with the actual motion laws of each functional device.

[0072] In other cases, the configuration process for the aforementioned environmental interaction simulation may specifically include: setting the friction coefficient of the roadway surface to 0.35, the equipment collision detection rules, and the collision force threshold during the ore loading process to 50 kN. The equipment collision detection rules may include a minimum safe distance of 2m for equipment of the same type and a minimum safe distance of 1.5m for equipment of different types.

[0073] In some cases, the aforementioned equipment operation logic may include configuring equipment operation procedures, "first-come, first-served" rules for avoidance points, and backup replacement rules for faulty equipment. The equipment operation procedure may follow a sequence of drilling, loading, transporting, and unloading. Specifically, after the drilling rig completes 40 minutes of drilling work per stope, the loader enters the stope unit and loads the ore drilled by the drilling rig into mining trucks. While the loader is loading the mining trucks, the trucks travel along a preset transport route to the unloading point and unload the ore. The loader can complete three loads to fill the mining trucks, with each load lasting 3 minutes. The unloading time for the mining trucks is 4 minutes.

[0074] The aforementioned "first-come, first-served" rule for avoidance points means that mining trucks must travel on the same transport route according to this rule, waiting for the equipment ahead to pass before entering the mining unit at the avoidance point, thereby reducing roadway congestion. The aforementioned backup replacement rule for faulty equipment means that when a mining machine malfunctions, a backup machine is automatically dispatched to take over. For example, if a loader malfunctions, the nearest standby loader is prioritized for dispatch.

[0075] S304 integrates the physics engine into the initial simulation model and configures the device operation logic in the initial simulation model with the integrated physics engine to obtain the target simulation model.

[0076] Specifically, after the aforementioned physics engine is established, it can be integrated into the initial simulation model. Equipment operation logic is then configured within this integrated model to obtain the target simulation model. In this way, by combining dynamic data to establish a physics engine capable of simulating equipment kinematics and environmental interactions, and by designing targeted equipment operation logic, the motion state of the equipment and its interactive behaviors during operation are realistically reproduced. Integrating the physics engine and equipment operation logic into the initial simulation model ultimately forms a complete target simulation model. This significantly improves the realism, real-time performance, and reliability of the simulation system, reduces insufficient granularity during modeling, optimizes the spatial coordination of equipment and processes, and reduces equipment waiting time and the probability of roadway conflicts. This provides more accurate and efficient technical support for mine recovery operation environment simulation, equipment operation analysis, and safety verification.

[0077] Furthermore, after obtaining the target simulation model, the candidate scheduling schemes can be input into the target simulation model to obtain equipment operation data.

[0078] S103, Based on the equipment operation data corresponding to multiple candidate scheduling schemes, determine the target scheduling scheme from the set of candidate scheduling schemes.

[0079] The aforementioned target scheduling scheme is used to optimally schedule mining equipment during the mining operation. In other words, by scheduling mining equipment through this target scheduling scheme, it is possible to reduce situations such as process waiting and equipment conflicts caused by unreasonable scheduling of mining equipment, optimize the coordination of the mining operation process, ensure the safe and stable operation of the mining process, and improve the operating efficiency of mining equipment.

[0080] In some embodiments, when the aforementioned equipment operation data includes mine recovery output and mine recovery cost, the actual historical data of the mine corresponding to the target simulation model is obtained. The actual historical data may include the average output per shift and the average cost per ton within a preset time period. The average output per shift refers to the average output completed by the mine recovery equipment in one mining operation. The average cost per ton refers to the average cost incurred by the mine recovery equipment in transporting one ton of ore. The preset time period can be pre-set according to actual conditions. For example, the preset time period can be 3 months, 4 months, 6 months, etc., and is not specifically limited.

[0081] Furthermore, based on the average output per shift within the preset time period, the increase ratio of mine recovery output corresponding to each candidate scheduling scheme is calculated, and based on the average cost per ton within the preset time period, the decrease ratio of mine recovery cost corresponding to each candidate scheduling scheme is calculated. The increase ratio of mine recovery output can be obtained by dividing the difference between mine recovery output and average output per shift by the average output per shift. The decrease ratio of mine recovery cost can be obtained by dividing the difference between mine recovery cost and average cost per ton by the average cost per ton. Then, based on the increase ratio of mine recovery output and the decrease ratio of mine recovery cost corresponding to each candidate scheduling scheme, a target scheduling scheme is determined from the set of candidate scheduling schemes. The target scheduling scheme is the candidate scheduling scheme that achieves the optimal balance between mine recovery output and mine recovery cost.

[0082] In some cases, the candidate scheduling scheme with the highest increase ratio and decrease ratio is selected as the target scheduling scheme from the set of candidate scheduling schemes. Alternatively, if the increase ratio has a first weight and the decrease ratio has a second weight, the increase ratio of mine recovery output and the decrease ratio of mine recovery cost corresponding to each candidate scheduling scheme are weighted and summed to obtain a comprehensive score for each candidate scheduling scheme, and the candidate scheduling scheme with the highest comprehensive score in the set of candidate scheduling schemes is selected as the target scheduling scheme.

[0083] For example, continuing with the aforementioned candidate scheduling scheme set including three candidate scheduling schemes, with an average single-shift output of 6800 tons and an average cost per ton of 18.5 yuan, Scheme 3 corresponds to an 18.3% increase in mine output and a 7.5% decrease in mine cost. Scheme 8 corresponds to a 10.6% increase in mine output and a 17.3% decrease in mine cost. Scheme 15 corresponds to a 2.6% increase in mine output and a 23.2% decrease in mine cost. It can be seen that Scheme 8 achieves the best balance between mine output and mine cost. Therefore, Scheme 8 can be considered the target scheduling scheme.

[0084] In other embodiments, when the aforementioned equipment operation data includes equipment waiting time and road congestion frequency, the actual waiting time and actual congestion frequency of the mining equipment are obtained. The actual waiting time refers to the accumulated waiting time of the mining equipment during a single mining operation in the mine corresponding to the target simulation model. The actual congestion frequency refers to the accumulated number of times the mining equipment experiences congestion during a single mining operation in the mine corresponding to the target simulation model. For example, the actual waiting time could be 1.2 hours per shift, and the actual congestion frequency could be 3-4 times per shift.

[0085] Furthermore, based on the actual waiting time, the reduction ratio of equipment waiting time for each candidate scheduling scheme is calculated, and based on the actual number of congestion events, the reduction ratio of road congestion events for each candidate scheduling scheme is calculated. The reduction ratio of equipment waiting time can be obtained by dividing the difference between the equipment waiting time and the actual waiting time by the actual waiting time. The reduction ratio of road congestion events can be obtained by dividing the difference between the number of road congestion events and the actual number of congestion events by the actual number of congestion events. Then, the candidate scheduling scheme with the highest reduction ratio of both equipment waiting time and road congestion events is selected as the target scheduling scheme.

[0086] In one example, taking the actual waiting time of 1.2 hours per shift as an example, the equipment waiting time corresponding to Scheme 8 is 42 minutes per shift. Specifically, the waiting time for the rock drilling rig is 8 minutes, the waiting time for the loader is 15 minutes, and the waiting time for the mining truck is 19 minutes. Then, based on the equipment waiting time corresponding to Scheme 8 and the actual waiting time, the reduction ratio of the equipment waiting time corresponding to Scheme 8 is determined to be 41.7%. It can be understood that by calculating the reduction ratio of equipment waiting time, the optimized planning of the transportation route and the coordinated scheduling of avoidance points can be verified.

[0087] In another example, taking the actual number of congestion events as 4 times per shift as an example, Scheme 8 corresponds to a road congestion event of 1 minute per shift. For instance, this road congestion event occurs at the K2+500m avoidance point and lasts for 5 minutes. Then, based on the road congestion event corresponding to Scheme 8 and the actual number of congestion events, the reduction ratio of equipment waiting time corresponding to Scheme 8 is determined to be 75%. It can be understood that by calculating the reduction ratio of equipment waiting time, the effectiveness of the above constraints can be verified.

[0088] In some cases, it may be sufficient to obtain only the actual waiting time of the aforementioned mining equipment. Then, based on the actual waiting time, the reduction ratio of the equipment waiting time for each candidate scheduling scheme is calculated. Finally, the candidate scheduling scheme with the highest reduction ratio of equipment waiting time in the candidate scheduling scheme set is selected as the target scheduling scheme.

[0089] In other cases, only the actual number of congestion incidents at the aforementioned mining equipment can be obtained. Then, based on the actual congestion incidents, the reduction ratio of road congestion incidents for each candidate scheduling scheme is calculated. Finally, the candidate scheduling scheme with the highest reduction ratio of road congestion incidents in the candidate scheduling scheme set is selected as the target scheduling scheme.

[0090] Accordingly, before determining the aforementioned target scheduling scheme, abnormal scenarios such as sudden equipment failures can be simulated. Then, in the event of an abnormal scenario, the abnormal single-shift mining output and abnormal single-shift mining cost are calculated. Next, based on the single-shift mining output, the reduction ratio of the abnormal single-shift mining output is calculated, and based on the single-shift mining cost, the increase ratio of the abnormal single-shift mining cost is calculated. Specifically, the reduction ratio of the abnormal single-shift mining output can be obtained by dividing the difference between the abnormal single-shift mining output and the normal single-shift mining output by the normal single-shift mining output. Similarly, the increase ratio of the abnormal single-shift mining cost can be obtained by dividing the difference between the abnormal single-shift mining cost and the normal single-shift mining cost by the normal single-shift mining cost.

[0091] Furthermore, if the reduction ratio of abnormal single-shift recovery output is within a preset reduction ratio range, and the increase ratio of abnormal single-shift recovery cost is within a preset increase ratio range, it indicates that the candidate scheduling scheme has strong fault adaptability. Therefore, this candidate scheduling scheme can be used as the target scheduling scheme. The preset reduction ratio range and preset increase ratio range can be preset according to actual conditions. The preset reduction ratio range and preset increase ratio range can be the same or different, and are not specifically limited. In this embodiment, both the preset reduction ratio range and the preset increase ratio range are -5% to 5%.

[0092] For example, in Scheme 8 above, a scenario is simulated where a mining truck suddenly breaks down at 10:00 AM, causing a two-hour work stoppage. Upon detecting the sudden breakdown, a standby mining truck is called in within 15 minutes to take over the task, and the single-shift mine recovery output is calculated to be 7280 tons, with a single-shift mine recovery cost of 15.8 yuan / ton. Based on the single-shift mine recovery output in Scheme 8, the reduction ratio of the abnormal single-shift recovery output is calculated to be 3.2%, and based on the single-shift mine recovery cost in Scheme 8, the increase ratio of the abnormal single-shift recovery cost is calculated to be 3.3%. That is, both the reduction ratio of the abnormal single-shift recovery output and the increase ratio of the abnormal single-shift recovery cost are within -5% to 5%. Therefore, Scheme 8 can be used as the target scheduling scheme.

[0093] In one implementation, after obtaining the aforementioned equipment operating data, the deviation ratio between the mine's recovered output and the theoretical output, as well as the deviation ratio between the mine's recovered cost and the theoretical cost, included in the equipment operating data, can be calculated first. Then, based on the deviation ratios between the mine's recovered output and the theoretical output, and the deviation ratios between the mine's recovered cost and the theoretical cost, the robustness of the multi-objective optimization model and its applicability to actual working conditions are verified, thereby ensuring the accuracy of the candidate scheduling scheme set output. Specifically, the verification process of the multi-objective optimization model may include, for example... Figure 5 S104~S107 shown: S104, calculate the ratio of the deviation between the mine's recovered output and the theoretical output, and the ratio of the deviation between the mine's recovered cost and the theoretical cost.

[0094] The theoretical output and theoretical cost are determined based on the target optimization scenario corresponding to the candidate scheduling scheme. In other words, the theoretical output and theoretical cost are different under different target optimization scenarios.

[0095] S105, determine whether the deviation ratio between the mine's recovered output and the theoretical output is within the first deviation ratio range.

[0096] Specifically, after calculating the deviation ratio between the mined output and the theoretical output, it can be determined whether this deviation ratio falls within a first deviation ratio range. This first deviation ratio range can be preset based on actual conditions. For example, it could be -2% to 2%.

[0097] In some embodiments, if the ratio of the deviation between the mined output and the theoretical output is within the first deviation ratio range, it indicates that the deviation between the mined output and the theoretical output is small, meaning the output accuracy of the multi-objective optimization model is high. Therefore, step S106 can be executed to further verify the robustness of the multi-objective optimization model. Conversely, if the ratio of the deviation between the mined output and the theoretical output is not within the first deviation ratio range, it indicates that the deviation between the mined output and the theoretical output is large, meaning the output accuracy of the multi-objective optimization model is low. Therefore, step S107 can be executed to readjust the model parameters and constraints of the multi-objective optimization model.

[0098] S106, determine whether the deviation ratio between the mining cost and the theoretical cost is within the second deviation ratio range.

[0099] Specifically, after determining that the deviation ratio between the mine's recovered output and the theoretical output falls within the first deviation ratio range, it can be further determined whether the deviation ratio between the mine's recovered cost and the theoretical cost falls within the second deviation ratio range. The second deviation ratio range can be preset according to actual conditions. This second deviation ratio range can be the same as or different from the first deviation ratio range; no specific limitation is made. In this embodiment, the second deviation ratio range and the first deviation ratio range are the same, both ranging from -2% to 2%.

[0100] In some embodiments, if the ratio of the deviation between the mining recovery cost and the theoretical cost is within the second deviation ratio range, it indicates that the deviation between the mining recovery cost and the theoretical cost is small, meaning the output accuracy of the multi-objective optimization model is high. Therefore, step S103 can be executed to determine the optimal target scheduling scheme. Conversely, if the ratio of the deviation between the mining recovery cost and the theoretical cost is not within the second deviation ratio range, it indicates that the deviation between the mining recovery cost and the theoretical cost is large, meaning the output accuracy of the multi-objective optimization model is low. Therefore, step S107 can be executed to readjust the model parameters and constraints of the multi-objective optimization model.

[0101] It should be noted that the execution order of the above-mentioned production deviation judgment process and cost deviation judgment process is not limited. That is to say, the production deviation judgment process and the cost deviation judgment process can be executed simultaneously or in a preset execution order. For example, step S105 can be executed first, followed by step S106. Another example is that step S106 can be executed first, followed by step S105. Yet another example is that steps S105 and S106 can be executed simultaneously.

[0102] S107, Adjust the model parameters and constraints of the multi-objective optimization model.

[0103] Specifically, after determining that the ratio of the deviation between the mine's recovered output and the theoretical output is not within the first deviation ratio range, and / or the ratio of the deviation between the mine's recovered cost and the theoretical cost is not within the second deviation ratio range, the model parameters and constraints of the multi-objective optimization model can be adjusted. This allows for a quantitative evaluation of the scheduling scheme's effectiveness, making the optimization results more closely reflect the actual production situation of the mine, effectively improving the accuracy, rationality, and applicability of the scheduling scheme, and contributing to enhanced production control precision and cost control effectiveness.

[0104] For example, as shown in Table 2, continuing with the example of the above candidate scheduling scheme set including three candidate scheduling schemes, Scheme 3 has a single-shift mine recovery output of 8050 tons, a single-shift mine recovery cost of 17.1 yuan, a deviation ratio between the mine recovery output and the theoretical output of -1.8%, and a deviation ratio between the mine recovery cost and the theoretical cost of +1.8%. Scheme 8 has a single-shift mine recovery output of 7520 tons, a single-shift mine recovery cost of 15.3 yuan, a deviation ratio between the mine recovery output and the theoretical output of -1.1%, and a deviation ratio between the mine recovery cost and the theoretical cost of +0.7%. Scheme 15 has a single-shift mine recovery output of 6980 tons, a single-shift mine recovery cost of 14.2 yuan, a deviation ratio between the mine recovery output and the theoretical output of -0.3%, and a deviation ratio between the mine recovery cost and the theoretical cost of +0.7%.

[0105] Table 2. Record of Deviation of Operational Indicators for Candidate Scheduling Schemes

[0106] As can be seen, the deviation ratios of all candidate scheduling schemes included in Table 2 are within the deviation ratio range, specifically -2% to 2%. This indicates that the calculation accuracy of the target simulation model is high, meaning that the target simulation model can accurately reflect the implementation effect of the candidate scheduling schemes. Therefore, there is no need to adjust the model parameters and constraints of the multi-objective optimization model again.

[0107] In some cases, after obtaining the aforementioned equipment operating data, it may be possible to calculate only the deviation ratio between the mine's recovered output and the theoretical output. That is, if the deviation ratio between the mine's recovered output and the theoretical output is not within the first deviation ratio range, the model parameters and constraints of the multi-objective optimization model can be directly adjusted. Alternatively, it may be possible to calculate only the deviation ratio between the mine's recovered cost and the theoretical cost. That is, if the deviation ratio between the mine's recovered cost and the theoretical cost is not within the second deviation ratio range, the model parameters and constraints of the multi-objective optimization model can be directly adjusted.

[0108] It should be noted that the execution order of the verification process of the multi-objective optimization model and the determination process of the target scheduling scheme is not limited. That is, the verification process of the multi-objective optimization model and the determination process of the target scheduling scheme can be executed simultaneously or in a preset order. For example, steps S104 to S107 can be executed first, followed by step S103. Alternatively, step S103 can be executed first, followed by steps S104 to S107. Yet another example is that steps S104 to S107 and S103 can be executed simultaneously.

[0109] Furthermore, as Figure 2 In terms of specific implementation, this application provides a multi-objective optimization scheduling device for mine recovery equipment based on digital twins, such as... Figure 6 As shown, the device includes: a set determination unit 401, a data determination unit 402, and a scheme determination unit 403.

[0110] The set determination unit 401 is used to acquire the mining operation parameters and mining equipment parameters, and input the mining operation parameters and mining equipment parameters into the multi-objective optimization model to obtain a set of candidate scheduling schemes; wherein, the set of candidate scheduling schemes includes multiple candidate scheduling schemes; The data determination unit 402 is used to input the candidate scheduling scheme into the target simulation model for each candidate scheduling scheme to obtain equipment operation data; The scheme determination unit 403 is used to determine the target scheduling scheme from the candidate scheduling scheme set based on the equipment operation data corresponding to multiple candidate scheduling schemes; wherein, the target scheduling scheme is used to perform optimal scheduling of mining equipment during the mining operation.

[0111] Furthermore, in one possible implementation of this embodiment, such as Figure 6 As shown, the set determination unit 401 is also used to generate an initial scheduling scheme set based on the mining operation parameters and the mining equipment parameters; The process involves repeatedly dividing the initial scheduling schemes into multiple groups based on the optimization objectives corresponding to the multi-objective optimization model. For each scheduling scheme group, the congestion degree of each initial scheduling scheme included in the scheduling scheme group is calculated to obtain the congestion degree of each initial scheduling scheme. Based on the congestion of multiple initial scheduling schemes in the initial scheduling scheme set, a new initial scheduling scheme set is determined until the number of iterations of the multi-objective optimization model reaches the preset number of iterations. The new initial scheduling scheme set is then determined as the candidate scheduling scheme set.

[0112] Furthermore, in one possible implementation of this embodiment, such as Figure 6 As shown, the set determination unit 401 is also used to take the preset number of initial scheduling schemes with the highest congestion in the initial scheduling scheme set as the parent scheduling scheme set. Genetic operations are performed on the set of parent scheduling schemes to obtain the set of offspring scheduling schemes; the genetic operations include crossover and / or mutation operations. Combine the set of child scheduling schemes and the set of parent scheduling schemes to form a new initial scheduling scheme set.

[0113] Furthermore, in one possible implementation of this embodiment, such as Figure 6 As shown, the set determination unit 401 is also used to input the initial scheduling scheme into the first objective optimization function for each initial scheduling scheme included in the initial scheduling scheme set, so as to obtain the job efficiency corresponding to the initial scheduling scheme; The initial scheduling scheme is input into the second objective optimization function to obtain the job cost corresponding to the initial scheduling scheme; Based on the corresponding job efficiency and job cost of multiple initial scheduling schemes, the multiple initial scheduling schemes are hierarchically divided to obtain multiple scheduling scheme groups.

[0114] Furthermore, in one possible implementation of this embodiment, such as Figure 6 As shown, the data determination unit 402 is also used to calculate the deviation ratio between the mine recovery output and the theoretical output, and the deviation ratio between the mine recovery cost and the theoretical cost; wherein, the theoretical output and theoretical cost are determined based on the target optimization scenario corresponding to the candidate scheduling scheme; If the ratio of the deviation between the mine's recovered output and the theoretical output is not within the first deviation ratio range, and / or if the ratio of the deviation between the mine's recovered cost and the theoretical cost is not within the second deviation ratio range, adjust the model parameters and constraints of the multi-objective optimization model.

[0115] Furthermore, in one possible implementation of this embodiment, such as Figure 6 As shown, the scheme determination unit 403 is also used to obtain the real historical data of the mine corresponding to the target simulation model; wherein, the real historical data includes the average single-shift output and the average single-ton cost within a preset time period. The average single-shift output refers to the average output completed by the mining equipment in one mining operation, and the average single-ton cost refers to the average cost consumed by the mining equipment to transport out one ton of ore. Based on the average output per shift within the preset time period, calculate the increase ratio of mine recovery output corresponding to each candidate scheduling scheme, and based on the average cost per ton within the preset time period, calculate the decrease ratio of mine recovery cost corresponding to each candidate scheduling scheme. Based on the ratio of increase in mine production and the ratio of decrease in mine cost corresponding to each candidate scheduling scheme, a target scheduling scheme is determined from the set of candidate scheduling schemes; wherein, the target scheduling scheme is the candidate scheduling scheme that can achieve the optimal balance between mine production and mine cost.

[0116] Furthermore, in one possible implementation of this embodiment, such as Figure 6As shown, the scheme determination unit 403 is also used to obtain the actual waiting time and actual congestion number of the mining equipment; wherein, the actual waiting time refers to the accumulated waiting time of the mining equipment in the mine corresponding to the target simulation model for one mining operation, and the actual congestion number refers to the accumulated congestion number of the mining equipment in the mine corresponding to the target simulation model for one mining operation. Based on the actual waiting time, calculate the reduction ratio of the equipment waiting time corresponding to each candidate scheduling scheme, and based on the actual number of congestion events, calculate the reduction ratio of the number of road congestion events corresponding to each candidate scheduling scheme. The candidate scheduling scheme with the highest reduction ratio of equipment waiting time and the highest reduction ratio of road congestion frequency in the candidate scheduling scheme set is selected as the target scheduling scheme.

[0117] Furthermore, in one possible implementation of this embodiment, such as Figure 7 As shown, the multi-objective optimization scheduling device for mining equipment based on digital twins also includes a model building unit 400.

[0118] The model building unit 400 is used to acquire model building data and preprocess the model building data; the model building data includes static data and dynamic data. Based on the preprocessed static data, an initial simulation model is constructed; Based on the preprocessed dynamic data, a physics engine with equipment kinematics simulation and environmental interaction simulation is established, and the equipment operation logic is designed. The physics engine is integrated into the initial simulation model, and the device operation logic is configured in the initial simulation model with the integrated physics engine to obtain the target simulation model.

[0119] It should be noted that other corresponding descriptions of the functional units involved in the scheduling scheme determination device for mining equipment provided in this application embodiment can be found in the following references. Figures 2 to 5 The corresponding descriptions in the method will not be repeated here.

[0120] This application also provides a computer device, specifically a personal computer, server, network device, etc. The computer device includes a bus, processor, memory, and communication interface, and may also include input / output interfaces and a display device. The processor of the computer device provides computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The database of the computer device stores location information. The network interface of the computer device is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements the steps in the various method embodiments.

[0121] Those skilled in the art will understand that the structure of the computer device described above is only a partial structure related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. A specific computer device may include more or fewer components, or combine certain components, or have different component arrangements.

[0122] In one embodiment, a computer-readable storage medium is provided, which may be non-volatile or volatile, having stored thereon a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0123] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0124] It should be noted that the user personal information involved in the embodiments of this application is all authorized (with the knowledge and consent) by the relevant parties or fully authorized by all parties, and the executing entity can obtain it through various legal and compliant means. The collection, storage, use, processing, transmission, provision, and disclosure of the information, data, and signals involved all comply with the relevant laws and regulations of the relevant countries and regions, and do not violate public order and good morals. It should be noted that if any software tools or components other than those of this company appear in the embodiments of this application, they are merely illustrative examples and do not represent actual use.

[0125] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, graphics processors, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0126] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0127] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A multi-objective optimization scheduling method for mining equipment based on digital twins, characterized in that, include: Obtain the mining operation parameters and mining equipment parameters, and input the mining operation parameters and mining equipment parameters into a multi-objective optimization model to obtain a set of candidate scheduling schemes; wherein, the set of candidate scheduling schemes includes multiple candidate scheduling schemes; For each candidate scheduling scheme, the candidate scheduling scheme is input into the target simulation model to obtain equipment operation data; Based on the equipment operation data corresponding to the multiple candidate scheduling schemes, a target scheduling scheme is determined from the set of candidate scheduling schemes; wherein, the target scheduling scheme is used to optimally schedule the mining equipment during the mining operation.

2. The method according to claim 1, characterized in that, The step of inputting the mine mining operation parameters and the mine mining equipment parameters into a multi-objective optimization model to obtain a set of candidate scheduling schemes includes: Based on the mining operation parameters and the mining equipment parameters, an initial scheduling scheme set is generated; The process is repeated to hierarchically divide the initial scheduling schemes included in the initial scheduling scheme set according to the optimization objectives corresponding to the multi-objective optimization model, thereby obtaining multiple scheduling scheme groups. For each scheduling scheme group, the congestion degree of each initial scheduling scheme included in the scheduling scheme group is calculated to obtain the congestion degree of each initial scheduling scheme. Based on the congestion of multiple initial scheduling schemes in the initial scheduling scheme set, a new initial scheduling scheme set is determined until the number of iterations of the multi-objective optimization model reaches a preset number of iterations, and the new initial scheduling scheme set is determined as the candidate scheduling scheme set.

3. The method according to claim 2, characterized in that, The step of determining a new set of initial scheduling schemes based on the congestion of multiple initial scheduling schemes in the initial scheduling scheme set includes: The initial scheduling schemes with the highest congestion among the initial scheduling scheme sets are used as the parent scheduling scheme set. Genetic operations are performed on the set of parent scheduling schemes to obtain a set of offspring scheduling schemes; wherein, the genetic operations include crossover and / or mutation operations; The set of child scheduling schemes and the set of parent scheduling schemes are combined to form the new initial scheduling scheme set.

4. The method according to claim 2, characterized in that, The multi-objective optimization model includes a first objective optimization function and a second objective optimization function. The first objective optimization function is used to maximize the operating efficiency of the mining equipment, and the second objective optimization function is used to minimize the operating cost of the mining equipment. The initial scheduling schemes in the initial scheduling scheme set are hierarchically divided according to the optimization objectives corresponding to the multi-objective optimization model, resulting in multiple scheduling scheme groups, including: For each initial scheduling scheme included in the initial scheduling scheme set, the initial scheduling scheme is input into the first objective optimization function to obtain the job efficiency corresponding to the initial scheduling scheme; The initial scheduling scheme is input into the second objective optimization function to obtain the job cost corresponding to the initial scheduling scheme; Based on the job efficiency and job cost corresponding to the multiple initial scheduling schemes, the multiple initial scheduling schemes are hierarchically divided to obtain the multiple scheduling scheme groups.

5. The method according to any one of claims 1-4, characterized in that, When the equipment operating data includes mine production output and mine operating costs, after inputting the candidate scheduling scheme into the target simulation model to obtain the equipment operating data, the method further includes: Calculate the deviation ratio between the mine's recovered output and the theoretical output, and the deviation ratio between the mine's recovered cost and the theoretical cost; wherein, the theoretical output and the theoretical cost are determined based on the target optimization scenario corresponding to the candidate scheduling scheme; If the ratio of the deviation between the mine's recovered output and the theoretical output is not within the first deviation ratio range, and / or if the ratio of the deviation between the mine's recovered cost and the theoretical cost is not within the second deviation ratio range, the model parameters and constraints of the multi-objective optimization model shall be adjusted.

6. The method according to claim 5, characterized in that, The step of determining the target scheduling scheme from the set of candidate scheduling schemes based on the equipment operation data corresponding to the multiple candidate scheduling schemes includes: Obtain the real historical data of the mine corresponding to the target simulation model; wherein, the real historical data includes the average output per shift and the average cost per ton within a preset time period; Based on the average output per shift within the preset time period, calculate the increase ratio of mine recovery output corresponding to each candidate scheduling scheme, and based on the average cost per ton within the preset time period, calculate the decrease ratio of mine recovery cost corresponding to each candidate scheduling scheme. Based on the ratio of increase in mine production corresponding to each candidate scheduling scheme and the ratio of decrease in mine production cost corresponding to each candidate scheduling scheme, the target scheduling scheme is determined from the set of candidate scheduling schemes; wherein, the target scheduling scheme is the candidate scheduling scheme that can achieve the optimal balance between mine production and mine production cost.

7. The method according to any one of claims 1-4, characterized in that, When the equipment operation data includes equipment waiting time and road congestion frequency, the step of determining the target scheduling scheme from the candidate scheduling scheme set based on the equipment operation data corresponding to the multiple candidate scheduling schemes includes: Obtain the actual waiting time and actual number of congestions for the mining equipment; Based on the actual waiting time, calculate the reduction ratio of the equipment waiting time corresponding to each candidate scheduling scheme, and based on the actual number of congestion events, calculate the reduction ratio of the number of road congestion events corresponding to each candidate scheduling scheme. The candidate scheduling scheme with the highest ratio of reduction in equipment waiting time and reduction in road congestion frequency in the candidate scheduling scheme set is selected as the target scheduling scheme.

8. The method according to any one of claims 1-4, characterized in that, The method further includes: Acquire model building data and preprocess the model building data; wherein the model building data includes static data and dynamic data; Based on the preprocessed static data, an initial simulation model is constructed; Based on the preprocessed dynamic data, a physics engine with equipment kinematics simulation and environmental interaction simulation is established, and the equipment operation logic is designed. The physics engine is integrated into the initial simulation model, and the device operation logic is configured in the initial simulation model with the integrated physics engine to obtain the target simulation model.

9. A multi-objective optimization scheduling device for mining equipment based on digital twins, characterized in that, include: A set determination unit is used to acquire mining operation parameters and mining equipment parameters, and input the mining operation parameters and mining equipment parameters into a multi-objective optimization model to obtain a set of candidate scheduling schemes; wherein, the set of candidate scheduling schemes includes multiple candidate scheduling schemes; The data determination unit is used to input the candidate scheduling scheme into the target simulation model for each candidate scheduling scheme to obtain equipment operation data; The scheme determination unit is used to determine the target scheduling scheme from the set of candidate scheduling schemes based on the equipment operation data corresponding to the multiple candidate scheduling schemes respectively; wherein, the target scheduling scheme is used to perform optimal scheduling of mining equipment during the mining operation.

10. A computer device, comprising a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method of any one of claims 1 to 8.

Images