Control methods, devices, and readable storage media for unmanned mining equipment

Abstract

This application relates to a method, apparatus, and readable storage medium for controlling unmanned mining equipment. Based on actual operating data of the unmanned mining equipment at various times within a preset time period, basic simulation data of the unmanned mining equipment under different operating conditions is constructed. Constraints on the unmanned mining equipment are constructed based on the actual operating data and the basic simulation data. The method receives actual health curves and target fusion characteristics sent by the unmanned mining equipment at various times. Based on safety threshold constraints, fault level determination constraints, operation and maintenance resource scheduling constraints, and target fusion characteristics of core components, the operation and maintenance tasks of at least one core component of the unmanned mining equipment are determined. Based on the actual health curves and operation and maintenance tasks, the health status of the unmanned mining equipment is controlled. This application effectively reduces the probability of equipment fault misjudgment, reduces downtime losses in the mining area, and improves the precision and intelligence level of equipment operation and maintenance control.

Description

Technical Field

[0001] This application relates to the field of unmanned control technology, and in particular to a control method, device and readable storage medium for unmanned mining equipment. Background Technology

[0002] Open-pit mining is a crucial foundation for the secure and stable supply of energy and mineral resources in my country. The level of intelligent collaborative control of unmanned equipment in open-pit mines directly determines the overall mining efficiency, life-cycle operating cost control, and inherent safety management capabilities of the mine. Therefore, providing a unified health management system covering the entire lifecycle and an intelligent scheduling method for operation and maintenance resources to manage the health status of unmanned equipment in open-pit mines is a pressing technical problem that needs to be solved in this field. Summary of the Invention

[0003] Therefore, it is necessary to provide a management method, device, and readable storage medium for unmanned mining equipment that can be managed throughout its entire lifecycle, addressing the aforementioned technical problems.

[0004] Firstly, this application provides a method for controlling unmanned mining equipment, including:

[0005] Based on the actual operating data of the unmanned mining equipment at various times within a preset time period, basic simulation data of the unmanned mining equipment under different operating conditions is constructed.

[0006] Based on actual operational data and basic simulation data, constraints are constructed for unmanned mining equipment. These constraints include equipment dynamics operation constraints, safety threshold constraints for core components, health status assessment constraints, fault level determination constraints, and operation and maintenance resource scheduling constraints.

[0007] The system receives the actual health curve and target fusion features at each moment from the unmanned mining equipment. The actual health curve is obtained by correcting the initial health curve based on the standard health curve of the unmanned mining equipment. The initial health curve is determined by the unmanned mining equipment based on the target fusion features and the health assessment model. The target fusion features are obtained by fusing the features of each extracted actual operating data based on the equipment dynamics operation constraints. The health assessment model is determined based on the health status assessment constraints.

[0008] Based on the safety threshold constraints, fault level determination constraints, operation and maintenance resource scheduling constraints, and the fusion characteristics of each target, determine the operation and maintenance tasks of at least one core component in the unmanned mining equipment.

[0009] Based on actual health curves and operation and maintenance tasks, the health status of unmanned mining equipment is managed and controlled.

[0010] In one embodiment, based on the actual operating data of the unmanned mining equipment at various times within a preset time period, basic simulation data of the unmanned mining equipment under different operating conditions is constructed, including:

[0011] The parameters to be corrected in the virtual prototype model of the unmanned mining equipment are corrected based on the actual operating data to obtain the corrected virtual prototype model.

[0012] Using the corrected virtual prototype model, basic simulation data of unmanned mining equipment under different operating conditions are constructed.

[0013] In one embodiment, the target fusion feature includes: preprocessing the actual operating data of each core component at each time moment according to the equipment dynamics operation constraints of the unmanned mining equipment to obtain the preprocessed data of each core component at each time moment; extracting features from the preprocessed data of each core component at each time moment to obtain the features corresponding to each core component at each time moment; fusing the features of each core component at each time moment to obtain the initial fusion feature at each time moment; and performing dimensionality reduction processing on the initial fusion feature at each time moment.

[0014] In one embodiment, the initial health curve includes the initial health level at each time point. The initial health level is obtained by inputting the target fusion features of the unmanned mining equipment at each time point into the health assessment model and outputting the posterior probability corresponding to each preset health grading standard. The preset benchmark scores of each preset health grading standard are weighted and summed using the posterior probabilities corresponding to each preset health grading standard.

[0015] In one embodiment, based on the safety threshold constraints of the core components, the fault level determination constraints, the operation and maintenance resource scheduling constraints, and the fusion characteristics of each target, the operation and maintenance tasks of at least one core component in the unmanned mining equipment are determined, including:

[0016] Based on the safety threshold constraints of the core components, the fault level determination constraints, and the fusion characteristics of each target, determine the fault level of at least one core component.

[0017] Based on the fault level of at least one core component and the constraints of operation and maintenance resource scheduling, determine the operation and maintenance tasks of at least one core component.

[0018] In one embodiment, the fault level of at least one core component is determined based on the safety threshold constraints of the core component, the fault level determination constraints, and the fusion features of each target, including:

[0019] Based on the safety threshold constraints of the core components, the fusion features of each target are decoupled to obtain each abnormal feature;

[0020] By fitting the various abnormal features, the degradation trend of the target fault can be determined;

[0021] Target fault information is determined based on the target fault degradation trend and a preset mapping relationship; the target fault information includes the target fault and the target fault location corresponding to at least one core component; the preset mapping relationship is the relationship between the fault information and the fault degradation trend;

[0022] Based on the target fault information and fault level determination constraints corresponding to at least one core component, determine the fault level of at least one core component.

[0023] In one embodiment, at least one includes multiple components; based on the fault level of at least one core component and the scheduling constraints of operation and maintenance resources, the operation and maintenance tasks of at least one core component are determined, including:

[0024] The priority of the target faults corresponding to each core component is determined based on each fault level;

[0025] Based on the priority of the target faults corresponding to each core component and the constraints of operation and maintenance resource scheduling, determine the matching resources for each core component;

[0026] Maintenance tasks for each core component are generated based on the matching resources; preset buffer times are set between each maintenance task.

[0027] In one embodiment, the health status of unmanned mining equipment is managed based on actual health curves and maintenance tasks, including:

[0028] Obtain actual fault data during the execution of maintenance tasks;

[0029] Based on actual fault data and actual health curves, the constraints are optimized to obtain new constraints, which are then used to determine new actual health curves and new operation and maintenance tasks.

[0030] Based on the new actual health curve and new operation and maintenance tasks, the health status of unmanned mining equipment is managed and controlled.

[0031] Secondly, this application also provides a control device for unmanned mining equipment, comprising:

[0032] The first construction module is used to construct basic simulation data of unmanned mining equipment under different operating conditions based on the actual operating data of the unmanned mining equipment at each moment within a preset time period.

[0033] The second construction module is used to construct constraints for unmanned mining equipment based on actual operational data and basic simulation data. The constraints include equipment dynamics operation constraints, safety threshold constraints for core components, health status assessment constraints, fault level determination constraints, and operation and maintenance resource scheduling constraints.

[0034] The receiving module is used to receive the actual health curve and target fusion features at each moment sent by the unmanned mining equipment. The actual health curve is obtained by the unmanned mining equipment by correcting the initial health curve according to the standard health curve of the unmanned mining equipment. The initial health curve is determined by the unmanned mining equipment based on the target fusion features and the health assessment model. The target fusion features are obtained by the unmanned mining equipment by fusing the features of each extracted actual operation data according to the equipment dynamics operation constraints. The health assessment model is determined based on the health status assessment constraints.

[0035] The determination module is used to determine the operation and maintenance tasks of at least one core component in the unmanned mining equipment based on the safety threshold constraints, fault level determination constraints, operation and maintenance resource scheduling constraints, and the fusion characteristics of each target.

[0036] The management and control module is used to manage the health status of unmanned mining equipment based on actual health curves and operation and maintenance tasks.

[0037] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the method steps provided in the first aspect.

[0038] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method steps provided in the first aspect.

[0039] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the method steps provided in the first aspect.

[0040] The aforementioned control method, device, and readable storage medium for unmanned mining equipment, based on actual operating data of the unmanned mining equipment at various times within a preset time period, constructs basic simulation data of the unmanned mining equipment under different operating conditions. Based on the actual operating data and basic simulation data, it constructs constraints for the unmanned mining equipment, receives actual health curves and target fusion characteristics at various times from the unmanned mining equipment, and determines the operation and maintenance tasks of at least one core component in the unmanned mining equipment based on safety threshold constraints, fault level determination constraints, operation and maintenance resource scheduling constraints, and target fusion characteristics. Based on the actual health curves and operation and maintenance tasks, it manages the unmanned mining equipment... The health status of unmanned mining equipment is managed and controlled. Constraints include equipment dynamics operation constraints, safety threshold constraints for core components, health status assessment constraints, fault level determination constraints, and maintenance resource scheduling constraints. The actual health curve is obtained by correcting the initial health curve based on the standard health curve of the unmanned mining equipment. The initial health curve is determined by the unmanned mining equipment based on the fusion characteristics of various targets and the health assessment model. The target fusion characteristics are obtained by fusing the characteristics of each extracted actual operating data based on the equipment dynamics operation constraints. The health assessment model is determined based on the health status assessment constraints. This application embodiment connects the entire process of simulation data construction, health assessment model determination, actual health curve solving, and maintenance task generation through constraints, unifying the judgment benchmark across all stages. By specifically correcting the initial health curve, data deviations are eliminated, improving the accuracy of actual health status judgment, and constructing a full lifecycle predictive health management system. This effectively reduces the probability of equipment fault misjudgment, reduces mine downtime losses, and improves the refinement and intelligence level of maintenance management of unmanned mining equipment. Attached Figure Description

[0041] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0042] Figure 1 This is an application environment diagram of a control method for unmanned mining equipment in one embodiment.

[0043] Figure 2 This is a flowchart illustrating a method for controlling unmanned mining equipment in one embodiment;

[0044] Figure 3 This is a flowchart illustrating a method for determining basic simulation data in one embodiment;

[0045] Figure 4 This is a flowchart illustrating a target fusion feature determination method in one embodiment;

[0046] Figure 5 This is a flowchart illustrating a fault level determination method in one embodiment;

[0047] Figure 6 This is a flowchart illustrating a method for determining operation and maintenance tasks in one embodiment;

[0048] Figure 7 This is a structural block diagram of a control device for unmanned mining equipment in one embodiment.

[0049] Figure 8 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0050] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0051] It should be noted that the terms "first," "second," etc., used in this application can be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "comprising" and "having," and any variations thereof, used in this application, are intended to cover non-exclusive inclusion. The term "multiple" used in this application refers to two or more. The term "and / or" used in this application refers to one of the embodiments, or any combination of multiple embodiments.

[0052] The control method for unmanned mining equipment provided in this application embodiment can be applied to, for example... Figure 1The application environment shown includes unmanned mining equipment 102 and cloud platform 104. Following the overall design scheme for unmanned equipment, various sensors are installed in core components of unmanned mining equipment 102, including its hydraulic system, working device, slewing mechanism, traveling mechanism, power system, and onboard electronic control system. These sensors utilize a pre-defined communication access protocol based on a dedicated industrial local area network for mining, adapting to the control units of the unmanned mining equipment. The control units are deployed at the nearest control node of the unmanned mining equipment, responsible for real-time preprocessing of multi-source sensor data, feature extraction, and health calculation. The operation and maintenance management platform on cloud platform 104 generates operation and maintenance tasks based on actual health curves and constraints. Finally, through on-site operation and maintenance interaction terminals, it provides mine R&D designers, equipment operation and maintenance managers, and production schedulers with functions such as synchronous health status monitoring, intelligent dispatching of operation and maintenance tasks, and visualized display of full lifecycle health decisions.

[0053] In one exemplary embodiment, such as Figure 2 As shown, a method for controlling unmanned mining equipment is provided, which can be applied to... Figure 1 The following explanation uses the cloud as an example, including S201 to S205. Among them:

[0054] S201, based on the actual operating data of the unmanned mining equipment at each moment within a preset time period, constructs basic simulation data of the unmanned mining equipment under different operating conditions.

[0055] Optionally, unmanned mining equipment can include: unmanned excavators for earthwork stripping, ore mining, and loading operations; unmanned mining dump trucks for long-distance transport of ore and slag; unmanned blasting drills for drilling holes in open-pit mines and pre-blasting construction; unmanned bulldozers for leveling mining sites, spreading ore piles, and trimming slopes; unmanned loaders for short-distance collection and loading of ore; and unmanned water sprinkler trucks for automatically watering and dust suppression on mining roads and maintaining road surfaces.

[0056] In this embodiment, based on the mining planning and production operation scenario, the actual operating data of the unmanned mining equipment at each moment within a preset time period is obtained. The parameters to be corrected in the virtual prototype model of the unmanned mining equipment are corrected according to the actual operating data to obtain the corrected virtual prototype model. The corrected virtual prototype model is then used to construct the basic simulation data of the unmanned mining equipment under different operating conditions.

[0057] In one possible implementation, the basic simulation data can be expanded by supplementing the data of uncollected operating points based on existing actual operating data through linear interpolation, piecewise polynomial fitting, and operating condition grid interpolation.

[0058] For example, unmanned mining equipment includes six major categories of core components: hydraulic system, working device, slewing mechanism, traveling mechanism, power system, and electrical control system.

[0059] Optionally, the basic simulation data can cover data such as pressure, flow, and temperature of the hydraulic system; data such as stress and attitude of the working device; vibration data of the slewing and traveling mechanisms; load operation data of the power system; current, voltage, and communication status of the electrical control system; and load characteristic data of core components under different coal seam and rock strata working conditions.

[0060] S202. Based on the actual operating data and the basic simulation data, construct the constraints for the unmanned mining equipment. The constraints include equipment dynamics operation constraints, safety threshold constraints for core components, health status assessment constraints, fault level determination constraints, and operation and maintenance resource scheduling constraints.

[0061] Optionally, constraints may include equipment dynamics operation constraints, core component safety threshold constraints, health status assessment constraints, fault level determination constraints, and operation and maintenance resource scheduling constraints. Among these, equipment dynamics operation constraints are the physical laws and performance limits that the motion and forces of unmanned mining equipment must satisfy, including mass, inertia, actuator torque / speed / acceleration limits, hydraulic system load-bearing capacity, ground-track / tire friction, structural resonance, and vibration stability. These constraints ensure that the actions of the unmanned mining equipment conform to Newtonian mechanics and do not exceed safe operating boundaries. Core component safety threshold constraints set a series of critical values ​​for safe operation parameters for core components, serving as constraints for fault early warning and scheduling control. Health status assessment constraints are the limitations, ethical norms, methodological boundaries, or institutional constraints faced when conducting health status assessments of unmanned mining equipment. Fault level determination constraints aim to address the inconsistency in judging the impact of faults from different perspectives by clarifying rules and unifying standards, providing a basis for subsequent emergency response and responsibility determination. Operation and maintenance resource scheduling constraints are the rules and restrictions that must be met when allocating and scheduling resources such as computing, storage, and manpower in an operation and maintenance scenario. These constraints are used to ensure the stable operation of core tasks and improve resource utilization. Through precise planning of these constraints, the boundary conditions for the healthy operation of the hydraulic system, working device, slewing mechanism, traveling mechanism, power system, and electrical control system, as well as the characteristic parameter matching thresholds and safe and stable operating ranges, are defined.

[0062] S203, Receive the actual health curve and target fusion features at each moment sent by the unmanned mining equipment; the actual health curve is obtained by the unmanned mining equipment by correcting the initial health curve according to the standard health curve of the unmanned mining equipment; the initial health curve is determined by the unmanned mining equipment based on the target fusion features and health assessment model; the target fusion features are obtained by the unmanned mining equipment by fusing the features of each extracted actual operation data according to the equipment dynamics operation constraints; the health assessment model is determined based on the health status assessment constraints.

[0063] In this embodiment of the application, the actual operating data of each core component at each time is preprocessed to obtain the preprocessed data of each core component at each time. Features are extracted from the preprocessed data of each core component at each time to obtain the features corresponding to each core component at each time. The features of each core component at each time are fused to obtain the initial fused features at each time. The initial fused features at each time are then subjected to dimensionality reduction processing to obtain the target fused features.

[0064] In one possible implementation, feature extraction can be performed directly on the actual operating data of each core component at each time point to obtain the features corresponding to each core component at each time point, thereby obtaining the target fusion features based on the features corresponding to each core component at each time point.

[0065] In another possible implementation, the initial fusion feature can be used as the target fusion feature.

[0066] In this embodiment, the standard health curve is an ideal health degradation reference curve obtained based on the design life and standard operating conditions, representing the expected trend of health degradation over time under normal deterioration. Since the initial health is affected by the variable loads of open-pit mines, impact conditions, and systematic errors in simulation models, it deviates from the actual aging degree of the equipment, requiring correction to obtain the actual health curve. The initial health curve calculated in real time is aligned with the reference value of the standard health curve at the same operating time point to determine the type of deviation between the initial health curve and the standard health curve, and then corresponding corrections are made based on the type of deviation. For example, when the deviation between the two is within the preset allowable deviation range, the initial health curve is shifted as a whole to compensate for small system offsets; when the degradation rate of the initial health curve deviates significantly from the theoretical decay rate of the standard health curve, the downward slope of the initial health curve is dynamically adjusted to match the actual aging and decay rate of the component; when the core component is overhauled and replaced, the initial health curve will have a cliff-like jump relative to the standard health curve. The new health of the core component after the overhaul and replacement is used as the new starting point of the initial health curve, and based on the decay slope obtained from multiple rounds of health assessment in the early stage, the degradation trend is continuously extended from the new starting point of the initial health curve.

[0067] S204. Based on the safety threshold constraints, fault level determination constraints, operation and maintenance resource scheduling constraints, and the fusion characteristics of each target, determine the operation and maintenance task of at least one core component in the unmanned mining equipment.

[0068] In this embodiment of the application, when determining the operation and maintenance task of at least one core component in an unmanned mining operation equipment based on the safety threshold constraints, fault level determination constraints, operation and maintenance resource scheduling constraints, and the fusion characteristics of each target, the fault level of at least one core component can be determined based on the safety threshold constraints, fault level determination constraints, and the fusion characteristics of each target. The operation and maintenance task of at least one core component can be determined based on the fault level of at least one core component and the operation and maintenance resource scheduling constraints.

[0069] In one possible implementation, accumulated information on harsh operating conditions such as long-term heavy loads, continuous operation, and high temperature and dust levels can be extracted from the target fusion features. This information is then combined with constraints on equipment dynamics, core component safety thresholds, and fault level determination to determine whether the accumulated information on harsh operating conditions exceeds limits. When the accumulated information on harsh operating conditions exceeds the limits, maintenance tasks are generated based on maintenance resource scheduling constraints. This changes the traditional maintenance approach of single-parameter acquisition, reactive post-event repair, and opaque health status. It enables online monitoring of all components, including hydraulic systems, working devices, slewing mechanisms, traveling mechanisms, power systems, and electrical control systems, as well as deep data fusion and precise quantification of health status. This significantly improves the manageability, controllability, and fault traceability of the core components of unmanned equipment.

[0070] S205 manages the health status of unmanned mining equipment based on actual health curves and maintenance tasks.

[0071] In this embodiment, the core components are repaired based on the operation and maintenance task, and the actual fault data during the execution of the operation and maintenance task is obtained. The constraints are optimized based on the actual fault data and the actual health curve to obtain new constraints. Based on the new constraints, a new actual health curve and a new operation and maintenance task are determined. Based on the new actual health curve and the new operation and maintenance task, the health status of the unmanned mining equipment is controlled.

[0072] In one possible implementation, the remaining service life of each core component can be calculated based on the actual health curve, and a lifespan warning threshold can be set in conjunction with health status assessment constraints and operation and maintenance resource scheduling constraints. Before the core component approaches the lifespan warning threshold, non-operational event windows can be planned in advance, and long-term health management of unmanned mining equipment can be achieved based on operation and maintenance tasks.

[0073] In the aforementioned management and control method for unmanned mining equipment, based on the actual operating data of the unmanned mining equipment at various times within a preset time period, basic simulation data of the unmanned mining equipment under different operating conditions is constructed. Constraints on the unmanned mining equipment are constructed based on the actual operating data and the basic simulation data. The method receives the actual health curve and target fusion characteristics sent by the unmanned mining equipment at various times. Based on the safety threshold constraints, fault level determination constraints, operation and maintenance resource scheduling constraints, and target fusion characteristics of the core components, the operation and maintenance tasks of at least one core component in the unmanned mining equipment are determined. Based on the actual health curve and the operation and maintenance tasks, the unmanned mining equipment is managed... The health status of the equipment is managed and controlled. Constraints include equipment dynamics operation constraints, safety threshold constraints for core components, health status assessment constraints, fault level determination constraints, and maintenance resource scheduling constraints. The actual health curve is obtained by correcting the initial health curve based on the standard health curve of the unmanned mining equipment. The initial health curve is determined by the unmanned mining equipment based on the fusion characteristics of various targets and the health assessment model. The target fusion characteristics are obtained by fusing the characteristics of each extracted actual operating data based on the equipment dynamics operation constraints. The health assessment model is determined based on the health status assessment constraints. This application embodiment connects the entire process of simulation data construction, health assessment model determination, actual health curve solving, and maintenance task generation through constraints, unifying the judgment benchmark across all stages. By specifically correcting the initial health curve, data deviations are eliminated, improving the accuracy of actual health status judgment, constructing a full lifecycle predictive health management system, effectively reducing the probability of equipment fault misjudgment, reducing mine downtime losses, and improving the refinement and intelligence level of maintenance management of unmanned mining equipment.

[0074] Figure 3 This is a flowchart illustrating a method for determining basic simulation data in one embodiment, as shown below. Figure 3 As shown, this application embodiment relates to a possible implementation method for constructing basic simulation data of unmanned mining equipment under different operating conditions based on the actual operating data of the unmanned mining equipment at various times within a preset time period, including the following steps:

[0075] S301, based on the actual operating data, the parameters to be corrected in the virtual prototype model of the unmanned mining equipment are corrected to obtain the corrected virtual prototype model.

[0076] In this embodiment, the unmanned mining equipment is modified from the main body of manned mining equipment. A virtual prototype model of the unmanned mining equipment is built based on digital twin technology. The parameters in the virtual prototype model are divided into intrinsic parameters that do not need adjustment and differential parameters that must be corrected (i.e., parameters to be corrected). The intrinsic parameters that do not need correction mainly involve the main structural dimensions, component mass, moment of inertia, and basic dimensions of hydraulic cylinders in the virtual prototype model. The differential parameters that must be corrected include sensor parameters, control execution parameters, operating environment parameters, and safety redundancy parameters. For example, the digital twin system uses a built-in mechanical-hydraulic coupling virtual prototype, which is the core carrier for the entire digital twin simulation calculation. Mechanical-hydraulic coupling can simultaneously simulate the mechanical structural motion characteristics and hydraulic transmission system working characteristics of the unmanned mining equipment. The whole machine geometric model is completed using SolidWorks, and a multidisciplinary dynamic simulation model is built in conjunction with ADAMS and AMESim. A visualization engine is used to achieve virtual-real data linkage.

[0077] When correcting differentiated parameters, the parameters to be corrected are determined based on the degree of automation of the unmanned mining equipment. For example, the degree of automation might involve drive-by-wire modification, replacement of hydraulic components, or the addition of an automatic driving system. If the automation level is only drive-by-wire modification, the original parameters of the hydraulic system are retained, and only the response delay and gain parameters of the electro-hydraulic conversion stage are corrected. If the automation level involves replacing hydraulic components, only the displacement and pressure response parameters of the newly replaced hydraulic components are calibrated, while other parameters are directly used. If the automation level involves adding an automatic driving system, only the sensor installation location and noise model parameters need to be added, without modifying the core parameters. Optionally, the least squares method can be used to construct the data residual function, and the particle swarm optimization algorithm can be combined to iteratively correct the parameters to be corrected, resulting in a corrected virtual prototype model.

[0078] When calibrating the parameters to be calibrated, static calibration is performed first: fix the unmanned mining equipment in multiple postures, compare the joint angles output by the sensors with the actual joint angles, and calibrate the sensor zero bias and installation position deviation. No-load dynamic testing: allow the unmanned mining equipment to complete 3-5 typical boom / stick swing movements, collect joint angle and cylinder pressure data to calibrate control gain, joint friction, and valve response parameters. Typical operating scenario testing: select a specific operating scenario, perform 3-5 standard movements to measure torque and resistance, and calibrate soil cutting parameters.

[0079] S302 uses the corrected virtual prototype model to construct basic simulation data for unmanned mining equipment under different operating conditions.

[0080] In this embodiment, a virtual prototype model, calibrated and corrected based on actual operational data, is used to divide different operating conditions, including different action combinations, different load levels, different soil environments, different component deterioration degrees, and various fault coupling conditions. Control commands, load parameters, and component performance degradation coefficients corresponding to each operating condition are configured in batches to drive the corrected virtual prototype in electromechanical-hydraulic joint simulation. During the simulation process, multi-dimensional time-series output data from the hydraulic system, working device, slewing mechanism, traveling mechanism, power system, and onboard electronic control system are simultaneously collected and stored according to operating conditions, components, and runtime, resulting in basic simulation data for different operating conditions of the unmanned mining equipment.

[0081] In this embodiment, the parameters to be corrected in the virtual prototype model of the unmanned mining equipment are corrected based on actual operating data to obtain a corrected virtual prototype model. Using this corrected virtual prototype model, basic simulation data for the unmanned mining equipment under different operating conditions is constructed. This embodiment generates a large amount of basic simulation data under different operating conditions through the corrected virtual prototype model, ensuring that the basic simulation data highly matches the actual mining conditions. This provides a precise quantitative simulation benchmark and preliminary planning constraints for subsequent status monitoring, fault early warning, and dynamic scheduling of operation and maintenance resources for the unmanned mining equipment.

[0082] Figure 4 This is a flowchart illustrating a target fusion feature determination method in one embodiment, such as... Figure 4 As shown, this application embodiment relates to a possible implementation of how to fuse the features of extracted actual operating data to obtain the target fused features at each time point. This method is applied to... Figure 1 The unmanned mining equipment includes the following steps:

[0083] S401, based on the equipment dynamics operation constraints, preprocess the actual operating data of each core component at each moment to obtain the preprocessed data of each core component at each moment.

[0084] In this embodiment of the application, the preprocessing of actual operating data can be a standardized preprocessing based on the equipment dynamics operating constraints, such as outlier removal, missing data completion, normalization, and time alignment.

[0085] S402, extract features from the preprocessed data of each core component at each time step to obtain the features corresponding to each core component at each time step.

[0086] In the embodiments of this application, feature extraction is performed on the preprocessed data of each core component at each time point, which may involve extracting time-domain features, frequency-domain features, time-frequency features, etc. from the preprocessed data.

[0087] In one possible implementation, preprocessed data can be input into a feature extraction model to obtain the features corresponding to each core component at each time step.

[0088] S403, fuses the features of each core component at each time step to obtain the initial fused features at each time step.

[0089] S404 performs dimensionality reduction on the initial fusion features at each time step to obtain the fusion features of each target.

[0090] In this embodiment, cross-component feature fusion is achieved through a Convolutional Neural Network (CNN) combined with a Transformer self-attention mechanism. Principal Component Analysis (PCA) is used for dimensionality reduction to obtain low-dimensional target fusion features. For example, the input signal sequentially passes through three one-dimensional convolutional modules to complete local temporal feature mining, with convolutional output channels of 16, 32, and 64 respectively. The convolutional output features are fed into a single-layer Transformer encoder with an embedding dimension of 64 and a 4-head multi-head self-attention mechanism. The encoding result is then global average pooled and mapped through a fully connected layer to obtain 32-dimensional target fusion features. A dynamic adjustment mechanism for attention weights is used to enhance the feature proportion of highly sensitive parameters under different operating conditions.

[0091] When fusing the features of each core component at different times, adaptive weight coefficients are configured for parameters that are highly sensitive to the aging of unmanned mining equipment, such as vibration and oil pressure. When the proportion of such high-weight monitoring parameters increases and the health degradation rate of unmanned mining equipment accelerates, the health status assessment update cycle is dynamically shortened. Under harsh mining conditions such as nighttime, rain, snow, and fog, the weight proportion of key parameters such as vibration and oil pressure is adaptively increased to enhance the sensitivity of deterioration feature identification.

[0092] In this embodiment, the actual operating data of each core component at each time moment is preprocessed according to the equipment dynamics operation constraints to obtain preprocessed data of each core component at each time moment. Feature extraction is performed on the preprocessed data of each core component at each time moment to obtain the corresponding features of each core component at each time moment. The features of each core component at each time moment are fused to obtain the initial fused features at each time moment. The initial fused features at each time moment are then subjected to dimensionality reduction processing to obtain the target fused features. This application unifies and evaluates multi-dimensional data, avoiding the problems of distorted single monitoring data and conflicting multi-source monitoring information leading to misjudgment of health status and disordered early warning, achieving complete multi-dimensional monitoring of all components and efficient feature fusion, ensuring stable and accurate determination of equipment health level.

[0093] In an exemplary embodiment, the initial health curve of the unmanned mining equipment is determined based on the target fusion features and the health assessment model, including: for the target fusion features at each time point, inputting the target fusion features into the health assessment model and outputting the posterior probability corresponding to each preset health grading standard; using the posterior probability corresponding to each preset health grading standard, performing weighted summation on the preset benchmark scores of each preset health grading standard to obtain the initial health level curve; the initial health curve includes the initial health level at each time point.

[0094] In this embodiment, for each time point, the dimensionality-reduced target fusion features are input into a Dirichlet Hidden Markov Model (DMM). Combined with a Bayesian inference algorithm, the posterior probability of each preset health level for the unmanned mining equipment is calculated based on a preset five-level health grading standard. A quantified health score ranging from 0 to 100 is obtained by weighting the posterior probabilities of each preset health level, and the corresponding initial health level is matched based on the health score. For example, the preset five-level health grading standard is: Level 1 Healthy (90–100); Level 2 Good (80–89); Level 3 Slight Deterioration (60–79); Level 4 Moderate Deterioration (40–59); Level 5 Severe Failure (0–39). The baseline scores corresponding to each preset five-level health grading standard are 96, 86, 71, 51, and 21. The target fusion features are input into the health assessment model to obtain the posterior probabilities of each level: Level 1 Healthy: 5%, Level 2 Good: 12%, Level 3 Slight Deterioration: 73%, Level 4 Moderate Deterioration: 9%, Level 5 Severe Failure: 1%. The posterior probabilities of each level are used to weight and sum the preset benchmark scores to obtain a quantitative health score of 71.75. Based on the above preset five-level health grading standard, the initial health level is determined to be Level 3 Slight Deterioration. For example, this scheme uses a five-state Dirichlet Hidden Markov Model to conduct quantitative assessment of equipment health. Five health levels are set to correspond to the five levels of equipment health to severe failure. Based on the aging characteristics of unmanned mining equipment, corresponding Dirichlet hyperparameters are configured. The dimensionality-reduced target features are used as observation variables. For each health level, two sets of Gaussian functions are used to characterize the normal fluctuation range of the feature data under that state. The cloud uses a Bayesian inference algorithm to iteratively solve the Gaussian function based on basic simulation data and actual operating data, thereby obtaining the posterior probabilities of each preset health level.

[0095] In this embodiment, the target fusion features at each time point are input into the health assessment model, and the posterior probabilities corresponding to each preset health grading standard are output. Using the posterior probabilities corresponding to each preset health grading standard, the preset benchmark scores of each preset health grading standard are weighted and summed to obtain the initial health level curve. This embodiment unifies and collaboratively integrates data from different core components to form a standardized health status assessment logic of perception, fusion, assessment, and health level grading. This eliminates the problems of misjudgment of health status and disordered early warning caused by single data misjudgment and multi-source information conflict from the source, achieving complete monitoring dimensions across all components, efficient data fusion, and stable and reliable health level determination.

[0096] In an exemplary embodiment, the operation and maintenance task of at least one core component in the unmanned mining equipment is determined based on the safety threshold constraints, fault level determination constraints, operation and maintenance resource scheduling constraints, and the fusion characteristics of each target. This includes: determining the fault level of at least one core component based on the safety threshold constraints, fault level determination constraints, and the fusion characteristics of each target; and determining the operation and maintenance task of at least one core component based on the fault level of at least one core component and the operation and maintenance resource scheduling constraints.

[0097] In this embodiment, the fusion features of each target are decoupled based on the safety threshold constraints of the core components to obtain each abnormal feature. Each abnormal feature is fitted to determine the target fault degradation trend. Based on the target fault degradation trend and a preset mapping relationship, target fault information is determined. Based on the target fault information corresponding to at least one core component and fault level determination constraints, the fault level of at least one core component is determined. When multiple fault levels are included, the priority of the target fault corresponding to each core component is determined based on each fault level. Based on the priority of the target fault corresponding to each core component and the operation and maintenance resource scheduling constraints, matching resources for each core component are determined. Operation and maintenance tasks for each core component are generated based on each matching resource. When multiple target faults are included, but the target fault levels are consistent, matching resources for each core component can be determined based on the target fault generation time, in addition to the operation and maintenance resource scheduling constraints. When only one target fault is included, the operation and maintenance task for that core component is determined directly based on the operation and maintenance resource scheduling constraints.

[0098] In this embodiment, the fault level of at least one core component is determined based on the safety threshold constraints, fault level determination constraints, and fusion characteristics of each target. The maintenance task of at least one core component is then determined based on its fault level and maintenance resource scheduling constraints. This application automatically generates maintenance tasks for different fault levels based on these constraints, achieving intelligent resource allocation and closed-loop process integration. It eliminates the need for manual experience-based task assignment and offline coordination, significantly shortening fault response time, improving maintenance efficiency, and reducing overall maintenance costs.

[0099] Figure 5 This is a flowchart illustrating a fault level determination method in one embodiment, such as... Figure 5 As shown, this application embodiment relates to a possible implementation of how to determine the fault level of at least one core component based on the safety threshold constraints of the core component, the fault level determination constraints, and the fusion features of each target, including the following steps:

[0100] S501, based on the safety threshold constraints of the core components, decouples the fusion features of each target to obtain each abnormal feature.

[0101] In this embodiment, based on equipment dynamics constraints and safety threshold constraints, short-term instantaneous fluctuations can be filtered out from the fusion features of each target, and persistent fluctuation features can be extracted as anomalous features. Alternatively, based on filtering out short-term instantaneous fluctuations and extracting persistent fluctuation features from the fusion features of each target according to equipment dynamics constraints and safety threshold constraints, high-frequency impact noise and low-frequency aging drift components in the fusion features of each target can be separated by frequency domain transformation, retaining the slowly varying offset components as anomalous features.

[0102] S502, fits each abnormal feature to determine the target fault degradation trend.

[0103] In this embodiment, each abnormal feature after decoupling is fitted and modeled. Based on the fitting results, the variation law of abnormal features with the cumulative running time of the equipment is characterized, and the performance degradation evolution curve is solved to determine the target fault degradation trend.

[0104] S503, determine the target fault information based on the target fault degradation trend and the preset mapping relationship; the target fault information includes the target fault and the target fault location corresponding to at least one core component; the preset mapping relationship is the relationship between the fault information and the fault degradation trend.

[0105] In this embodiment, a mapping relationship between fault information and fault degradation trends is pre-established. The target fault degradation trend is used to search within the mapping relationship to obtain the corresponding target fault information. The target fault location can pinpoint the core component where the target fault occurs, and the target fault can reveal the specific fault type occurring in the core component.

[0106] S504, determine the fault level of at least one core component based on the target fault and fault level determination constraints corresponding to at least one core component.

[0107] In this embodiment, the severity of degradation can be quantified and matched based on the target failure degradation trend and the failure level determination constraints to determine the failure level of the corresponding core component. For example, different relationships between failure degradation trends and failure levels can be set in the failure level determination constraints. A slight health decline state triggers a warning, a general performance degradation state triggers a warning, a severe abnormal state triggers a warning, and an emergency failure risk triggers a shutdown warning. By dynamically balancing the warning logic and response strategies of each component, the operational risks such as unplanned downtime and expanded equipment damage caused by false alarms, missed alarms, and delayed alarms can be effectively eliminated. This enables early detection, early identification, and early warning of failures in the core components of the unmanned excavator, and ensures controllable health status throughout its entire life cycle.

[0108] In this embodiment, the fusion features of each target are decoupled according to the safety threshold constraints of the core components to obtain each abnormal feature. Each abnormal feature is then fitted to determine the target fault degradation trend. Based on the target fault degradation trend and a preset mapping relationship, the target fault information is determined. Finally, based on the target fault and fault level determination constraints corresponding to at least one core component, the fault level of at least one core component is determined. This embodiment effectively solves industry problems such as the difficulty in identifying early, weak faults in core components and the difficulty in distinguishing coupled faults. It achieves early fault location, early risk warning, and predictable lifespan, significantly reducing the number of sudden unplanned downtimes, the probability of equipment damage, and on-site operational safety hazards, thereby improving the reliability of unmanned continuous operation.

[0109] Figure 6 This is a flowchart illustrating a method for determining operation and maintenance tasks in one embodiment, such as... Figure 6 As shown, this application embodiment relates to a possible implementation of how to determine the operation and maintenance tasks of at least one core component based on the fault level of at least one core component and the constraints of operation and maintenance resource scheduling, including the following steps:

[0110] S601 determines the priority of the target faults corresponding to each core component based on each fault level.

[0111] S602 determines the matching resources for each core component based on the priority of the target faults corresponding to each core component and the scheduling constraints of operation and maintenance resources.

[0112] S603 generates maintenance tasks for each core component based on each matching resource; preset buffer durations are set between each maintenance task.

[0113] In this embodiment, target faults are first prioritized according to their fault severity. Then, based on the existing scheduling constraints of maintenance resources such as repair personnel, spare parts, and workstations, resources with faster response times are matched to the highest priority target fault. Maintenance tasks for each core component are generated based on the matched resources. Simultaneously, differentiated buffer durations are set for maintenance tasks corresponding to different priorities, and flexible window durations are reserved in the maintenance sequence planning to handle unexpected situations such as maintenance timeouts, spare parts delays, and new faults, preventing a single maintenance task delay from causing a chain reaction of disruptions to the entire scheduling plan. The differentiated buffer durations for maintenance tasks corresponding to different priorities are pre-set in the maintenance resource scheduling constraints.

[0114] When a high-risk fault task is added during the operation and maintenance task scheduling process, a gradual timing fine-tuning strategy is adopted. This involves only slightly delaying low- and medium-priority operation and maintenance work orders, without interrupting ongoing maintenance operations or completely overturning the existing scheduling plan. This ensures timely handling of high-risk faults while avoiding idle and wasted operation and maintenance resources. For example, if there are three target faults with different priority levels, where target fault 1 has a higher priority than target fault 2, and target fault 2 has a higher priority than target fault 3, and operation and maintenance tasks for each of these three target faults are generated, and if, based on operation and maintenance task 1, there are target faults 4 and 5, where target fault 4 has a higher priority than target fault 2, and target fault 5 has a lower priority than target fault 3, then the operation and maintenance task for target fault 4 will be executed after operation and maintenance task 1 is completed. During the transition between fault warning and operation and maintenance resource scheduling, priority adjustments are made gradually and tasks are smoothly connected. This completes the adaptation and debugging of operation and maintenance resource scheduling, ensuring reasonable assignment, efficient scheduling, and smooth execution.

[0115] In this embodiment, the priority of the target fault corresponding to each core component is determined according to each fault level. Based on the priority of the target fault corresponding to each core component and the constraints of operation and maintenance resource scheduling, the matching resources for each core component are determined. Operation and maintenance tasks for each core component are then generated based on the matching resources. This embodiment, by setting a buffer time between operation and maintenance tasks, ensures that high-risk faults are not delayed and resources are not wasted. It eliminates the problems of low operation and maintenance efficiency caused by operation and maintenance command conflicts, resource contention, and response delays. It achieves seamless logical connection and smooth transition between fault warning, operation and maintenance decision-making, resource scheduling, and maintenance execution, ensuring continuous and stable overall machine health management and operation and maintenance scheduling status.

[0116] In one exemplary embodiment, the health status of unmanned mining equipment is managed based on actual health curves and maintenance tasks, including: acquiring actual fault data during the execution of maintenance tasks; optimizing constraints based on actual fault data and actual health curves to obtain new constraints, and determining new actual health curves and new maintenance tasks based on the new constraints; and managing the health status of unmanned mining equipment based on the new actual health curves and new maintenance tasks.

[0117] In this embodiment, after each maintenance task is completed, the parameters in the health status assessment constraints, fault level determination constraints, and maintenance resource scheduling constraints are updated using actual fault data from the task execution process. The effect is verified after each fine-tuning, and this process is repeated. The parameters in the health status assessment constraints include: weights of each monitoring parameter, health level classification thresholds, and the degradation slope of the standard health curve; the parameters in the fault level determination constraints include: anomaly identification thresholds, dynamic early warning level triggering conditions, and degradation rate determination thresholds; the parameters in the maintenance resource scheduling constraints include: maintenance priority determination criteria, buffer durations for different priorities, and resource matching degree calculation weights.

[0118] Furthermore, the parameters of the aforementioned models can be adjusted: the attention weights for multi-source feature fusion and the prior probabilities of the health assessment model.

[0119] This application's embodiments acquire actual fault data during the execution of maintenance tasks; optimize constraints based on actual fault data and actual health curves to obtain new constraints; determine new actual health curves and new maintenance tasks based on these new constraints; and manage the health status of unmanned mining equipment based on these new actual health curves and maintenance tasks. This application adopts a full-process closed-loop iterative optimization and management logic. Through automatic iterative optimization of health assessment, fault early warning, and resource scheduling strategies after the loop is closed, the management adaptation effect is continuously optimized, forming a complete closed-loop health management process. This achieves optimal synergy among multiple objectives: monitoring accuracy, early warning effectiveness, maintenance timeliness, and maintenance economy, adapting to the long-term unmanned, highly reliable, and highly efficient stable operation requirements of unmanned equipment under complex and variable working conditions in open-pit mines.

[0120] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0121] Based on the same inventive concept, this application also provides a control device for unmanned mining equipment to implement the control method for the aforementioned unmanned mining equipment. The solution provided by this device is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the control device for unmanned mining equipment provided below can be found in the limitations of the control method for unmanned mining equipment described above, and will not be repeated here.

[0122] In one exemplary embodiment, such as Figure 7 As shown, a control device for unmanned mining equipment is provided, comprising: a first construction module 11, a second construction module 12, a receiving module 13, a determining module 14, and a control module 15, wherein:

[0123] The first construction module 11 is used to construct basic simulation data of the unmanned mining equipment under different operating conditions based on the actual operating data of the unmanned mining equipment at each moment within a preset time period.

[0124] The second construction module 12 is used to construct the constraints of the unmanned mining equipment based on the actual operation data and the basic simulation data. The constraints include equipment dynamic operation constraints, safety threshold constraints of core components, health status assessment constraints, fault level determination constraints, and operation and maintenance resource scheduling constraints.

[0125] The receiving module 13 is used to receive the actual health curve and target fusion features at each moment sent by the unmanned mining equipment. The actual health curve is obtained by the unmanned mining equipment by correcting the initial health curve according to the standard health curve of the unmanned mining equipment. The initial health curve is determined by the unmanned mining equipment based on the target fusion features and the health assessment model. The target fusion features are obtained by the unmanned mining equipment by fusing the features of each extracted actual operation data according to the equipment dynamics operation constraints. The health assessment model is determined based on the health status assessment constraints.

[0126] The determination module 14 is used to determine the operation and maintenance tasks of at least one core component in the unmanned mining equipment based on the safety threshold constraints, fault level determination constraints, operation and maintenance resource scheduling constraints, and the fusion characteristics of each target.

[0127] The control module 15 is used to control the health status of unmanned mining equipment based on actual health curves and operation and maintenance tasks.

[0128] In an exemplary embodiment, the first construction module 11 is specifically used to correct the parameters to be corrected in the virtual prototype model of the unmanned mining equipment according to the actual operating data, so as to obtain the corrected virtual prototype model; and to use the corrected virtual prototype model to construct the basic simulation data of the unmanned mining equipment under different operating conditions.

[0129] In an exemplary embodiment, the target fusion feature includes: preprocessing the actual operating data of each core component at each time moment according to the equipment dynamics operation constraints of the unmanned mining equipment to obtain preprocessed data of each core component at each time moment; extracting features from the preprocessed data of each core component at each time moment to obtain features corresponding to each core component at each time moment; fusing the features of each core component at each time moment to obtain the initial fusion feature at each time moment; and performing dimensionality reduction processing on the initial fusion feature at each time moment.

[0130] In an exemplary embodiment, the initial health curve includes the initial health level at each time point. The initial health level is obtained by inputting the target fusion features of the unmanned mining equipment at each time point into the health assessment model and outputting the posterior probability corresponding to each preset health grading standard. The preset benchmark scores of each preset health grading standard are weighted and summed using the posterior probabilities corresponding to each preset health grading standard.

[0131] In an exemplary embodiment, the determining module 14 is configured to determine the fault level of at least one core component based on the security threshold constraints, fault level determination constraints, and fusion characteristics of each target; and to determine the operation and maintenance tasks of at least one core component based on the fault level of at least one core component and operation and maintenance resource scheduling constraints.

[0132] In an exemplary embodiment, the determining module 14 is configured to decouple the fusion features of each target according to the safety threshold constraints of the core components to obtain each abnormal feature; fit each abnormal feature to determine the target fault degradation trend; determine the target fault information according to the target fault degradation trend and the preset mapping relationship; the target fault information includes the target fault and the target fault location corresponding to at least one core component; the preset mapping relationship is the relationship between the fault information and the fault degradation trend; and determine the fault level of at least one core component according to the target fault information corresponding to at least one core component and the fault level determination constraints.

[0133] In an exemplary embodiment, the determining module 14 is configured to determine the priority of the target fault corresponding to each core component according to each fault level; determine the matching resources for each core component according to the priority of the target fault corresponding to each core component and the operation and maintenance resource scheduling constraints; generate operation and maintenance tasks for each core component according to each matching resource; and set a preset buffer time between each operation and maintenance task.

[0134] In an exemplary embodiment, the control module 14 is used to acquire actual fault data during the execution of operation and maintenance tasks; optimize the constraints based on the actual fault data and the actual health curve to obtain new constraints, so as to determine a new actual health curve and a new operation and maintenance task based on the new constraints; and control the health status of the unmanned mining equipment based on the new actual health curve and the new operation and maintenance task.

[0135] The various modules in the control device of the aforementioned unmanned mining equipment can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0136] In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 8As shown, the computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores relevant data for the management and control of unmanned mining equipment. The I / O interfaces are used for information exchange between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a management and control method for unmanned mining equipment.

[0137] Those skilled in the art will understand that Figure 8 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0138] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of any of the above method embodiments.

[0139] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the above method embodiments.

[0140] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of any of the above method embodiments.

[0141] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0142] Those skilled in the art will understand that all or part of the processes in the methods of 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, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory 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, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0143] 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 application.

[0144] 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 method for managing and controlling mine unmanned operation equipment, characterized by, The method comprises: Based on the actual operation data of the mine unmanned operation equipment at each time within a preset time length, the basic simulation data of the mine unmanned operation equipment under different operation conditions is constructed; According to each actual operation data and each basic simulation data, the constraint condition of the mine unmanned operation equipment is constructed; The constraint condition includes equipment dynamics operation constraint condition, safety threshold constraint condition of core component, health state evaluation constraint condition, fault level judgment constraint condition and operation and maintenance resource scheduling constraint condition; Receive the actual health curve and the target fusion feature at each time sent by the mine unmanned operation equipment; The actual health curve is obtained by correcting the initial health curve of the mine unmanned operation equipment according to the standard health curve of the mine unmanned operation equipment, the initial health curve is determined by the mine unmanned operation equipment according to each target fusion feature and health evaluation model, and the target fusion feature is obtained by fusing the features of each actual operation data extracted by the mine unmanned operation equipment according to the equipment dynamics operation constraint condition; The health evaluation model is determined based on the health state evaluation constraint condition; According to the safety threshold constraint condition of the core component, the fault level judgment constraint condition, the operation and maintenance resource scheduling constraint condition and each target fusion feature, the operation and maintenance task of at least one core component in the mine unmanned operation equipment is determined; Based on the actual health curve and the operation and maintenance task, the health condition of the mine unmanned operation equipment is controlled.

2. The method of claim 1, wherein, The basic simulation data of the mine unmanned operation equipment under different operation conditions is constructed based on the actual operation data of the mine unmanned operation equipment at each time within a preset time length, which comprises: According to each actual operation data, the to be corrected parameters in the virtual prototype model of the mine unmanned operation equipment are corrected to obtain the corrected virtual prototype model; Using the corrected virtual prototype model, the basic simulation data of the mine unmanned operation equipment under different operation conditions is constructed.

3. The method of claim 1, wherein, The target fusion feature comprises: the actual operation data of each core component at each time is preprocessed by the mine unmanned operation equipment according to the equipment dynamics operation constraint condition to obtain the preprocessing data of each core component at each time; The features of each core component at each time are extracted to obtain the corresponding features of each core component at each time; The features of each core component at each time are fused to obtain the initial fusion feature at each time; The initial fusion feature at each time is obtained by dimension reduction processing.

4. The method of claim 1, wherein, The initial health curve includes the initial health level at each time, and the initial health level is obtained by inputting the target fusion feature into the health evaluation model and outputting the posterior probability corresponding to each preset health classification standard. The preset reference points of each preset health classification standard are weighted and summed by using the posterior probability corresponding to each preset health classification standard.

5. The method of claim 1, wherein, The operation and maintenance task of at least one core component in the mine unmanned operation equipment is determined according to the safety threshold constraint condition, the fault level judgment constraint condition, the operation and maintenance resource scheduling constraint condition and each target fusion feature of the core component, and the operation and maintenance task of at least one core component in the mine unmanned operation equipment is determined according to the safety threshold constraint condition, the fault level judgment constraint condition, the operation and maintenance resource scheduling constraint condition and each target fusion feature of the core component, and the operation and maintenance task of at least one core component in the mine unmanned operation equipment is determined according to the safety threshold constraint condition, the fault level judgment constraint condition, the operation and maintenance resource scheduling constraint condition and each target fusion feature of the core component, and the operation and maintenance task of at least one core component in the mine unmanned operation equipment is determined according to the safety threshold constraint condition, the fault level judgment constraint condition, the operation and maintenance resource scheduling constraint condition and each target fusion feature of the core component, and the operation and maintenance task of at least one core component in the mine unmanned operation equipment is determined according to the safety threshold constraint condition, the fault level judgment constraint condition, the operation and maintenance resource scheduling constraint condition and each target fusion feature of the core component, and the operation and maintenance task of at least one core component in the mine unmanned operation equipment is determined according to the safety threshold constraint condition, the fault level judgment constraint condition, the operation and maintenance resource scheduling constraint condition and each target fusion feature of the core component, and the operation and maintenance task of at least one core component in the mine unmanned operation equipment is determined according to the safety threshold constraint condition, the fault level judgment constraint condition, the operation and maintenance resource scheduling constraint condition and each target fusion feature of the core component, and the operation and maintenance task of at least one core component in the mine unmanned operation equipment is determined according to the safety threshold constraint condition, the fault level judgment constraint condition, the operation and maintenance resource scheduling constraint condition and each target fusion feature of the core component, and the operation and maintenance task of at least one core component in the mine unmanned operation equipment is determined according to the safety threshold constraint condition, the fault level judgment constraint condition, the operation and maintenance resource scheduling constraint condition and each target fusion feature of the core component, and the operation and maintenance task of at least one core component in the mine unmanned operation equipment is determined according to the safety threshold constraint condition, the fault level judgment constraint condition, and each target fusion feature of the core component. The fault level of the at least one core component is determined according to the safety threshold constraint condition, the fault level judgment constraint condition and each target fusion feature of the core component. The operation and maintenance task of the at least one core component is determined according to the fault level of the at least one core component and the operation and maintenance resource scheduling constraint condition.

6. The method of claim 5, wherein, The fault level of the at least one core component is determined according to the safety threshold constraint of the core component, the fault level judgment constraint condition and each target fusion feature. Each abnormal feature is obtained by decoupling each target fusion feature according to the safety threshold constraint condition of the core component; Each target fault degradation trend is determined by fitting each abnormal feature; Target fault information corresponding to the at least one core component is determined according to the target fault degradation trend and a preset mapping relationship; the target fault information includes target fault and target fault position corresponding to the at least one core component; the preset mapping relationship is the relationship between fault information and fault degradation trend; The fault level of the at least one core component is determined according to the target fault information corresponding to the at least one core component and the fault level judgment constraint condition.

7. The method of claim 6, wherein, At least one includes a plurality; the operation and maintenance task of the at least one core component is determined according to the fault level of each core component and the operation and maintenance resource scheduling constraint condition. The priority of target fault corresponding to each core component is determined according to each fault level; The matching resource of each core component is determined according to the priority of target fault corresponding to each core component and the operation and maintenance resource scheduling constraint condition; The operation and maintenance task of each core component is generated according to each matching resource; a preset buffer time length is set between each operation and maintenance task.

8. The method of claim 1, wherein, The health condition of the mine unmanned operation equipment is controlled based on the actual health curve and the operation and maintenance task, including: Actual fault data in the operation and maintenance task execution process is obtained; The constraint condition is optimized according to the actual fault data and the actual health curve to obtain a new constraint condition, so as to determine a new actual health curve and a new operation and maintenance task based on the new constraint condition; The health condition of the mine unmanned operation equipment is controlled based on the new actual health curve and the new operation and maintenance task.

9. A management and control device of mine unmanned operation equipment, characterized by, The device includes: A first construction module is configured to construct basic simulation data of the mine unmanned operation equipment under different operation conditions based on actual operation data of the mine unmanned operation equipment at each time within a preset time length; A second construction module is configured to construct constraint conditions of the mine unmanned operation equipment according to each actual operation data and each basic simulation data; the constraint conditions include equipment dynamics operation constraint conditions, safety threshold constraint conditions of core components, health state evaluation constraint conditions, fault level judgment constraint conditions and operation and maintenance resource scheduling constraint conditions; The receiving module is used to receive the actual health curve and target fusion features at each moment sent by the unmanned mining equipment; it is used to correct the initial health curve according to the standard health curve of the unmanned mining equipment, wherein the initial health curve is determined by the unmanned mining equipment based on the target fusion features and the health assessment model, and the target fusion features are obtained by fusing the features of each extracted actual operation data according to the equipment dynamics operation constraints; the health assessment model is determined based on the health status assessment constraints. The determination module is used to determine the operation and maintenance task of at least one core component in the unmanned mining equipment based on the safety threshold constraints, fault level determination constraints, operation and maintenance resource scheduling constraints, and the fusion characteristics of each target. The control module is used to control the health status of the unmanned mining equipment based on the actual health curve and the operation and maintenance tasks.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method described in any one of claims 1-8.

Images