Intelligent Scheduling Method, Device and Medium for Integrated Mining, Loading and Transportation in Open-pit Mines

Abstract

The present application relates to the technical field of intelligent scheduling, and discloses an intelligent scheduling method, device and medium for integrated mining, hauling and loading in open-pit mines. The method includes: performing hierarchical decoupling processing on the operation efficiency indexes of the equipment group and the mining area exploitation planning data to obtain an energy-efficiency-oriented collaborative task sequence; performing swarm intelligence matching processing on the energy-efficiency-oriented collaborative task sequence and the spatio-temporal distribution data of the equipment group to obtain an integrated mining, hauling and loading resource allocation scheme; performing dynamic coordination processing on the integrated mining, hauling and loading resource allocation scheme and the road traffic constraint data to obtain an adaptive scheduling strategy for the equipment group; and performing closed-loop iterative processing on the adaptive scheduling strategy for the equipment group and the production process feedback data to obtain a collaborative optimization instruction for mining, hauling and loading. The present application solves the problems of fragmentation in the mining, hauling and loading links, insufficient energy consumption control, poor adaptability, etc. in traditional scheduling methods.

Description

Technical Field

[0001] This application relates to the field of intelligent scheduling, and particularly to an integrated intelligent scheduling method, device and medium for open-pit mine mining, loading and transportation. Background Art

[0002] The operation environment of open-pit mines is complex, and the production process involves multiple links such as mining, stripping, loading and transportation, which poses high requirements for equipment scheduling and management. At present, the scheduling and management of open-pit mines mainly rely on manual experience for decision-making, and use technical means such as GPS positioning and wireless communication to monitor and dispatch mining, loading and transportation equipment in real time. At the same time, some mines have begun to introduce computer-aided scheduling systems, which optimize the equipment scheduling by establishing mathematical models, and improve the production efficiency to a certain extent. With the development of technologies such as the Internet of Things and big data, the mine scheduling system is gradually developing towards intelligence and automation, and begins to try to use new technical means such as artificial intelligence to solve scheduling problems.

[0003] However, there are still some deficiencies in the existing open-pit mine scheduling methods: First, traditional scheduling methods often separate each link of mining, loading and transportation and optimize them separately, resulting in poor overall coordination effect; Second, the existing scheduling system lacks consideration of the energy consumption characteristics of equipment, and it is difficult to achieve overall consideration of energy efficiency and production efficiency; Third, the adaptability of scheduling strategies is not strong, and it is difficult to adjust in complex working conditions and emergencies; Finally, there is no effective closed-loop feedback mechanism, and the scheduling plan cannot be dynamically optimized according to the actual situation in the production process. These problems seriously restrict the production efficiency and economic benefits of open-pit mines. Summary of the Invention

[0004] This application provides an integrated intelligent scheduling method, device and medium for open-pit mine mining, loading and transportation, which is used to construct an integrated intelligent scheduling method based on energy efficiency orientation, realize the collaborative scheduling and dynamic optimization of equipment groups, and solve problems such as the separation of mining, loading and transportation links, insufficient energy consumption control and poor adaptability in traditional scheduling methods.

[0005] In a first aspect, the present application provides an integrated intelligent scheduling method for open-pit mining, transportation, and loading. The integrated intelligent scheduling method for open-pit mining, transportation, and loading includes: performing multi-source information fusion processing on the topographic and geomorphic feature data of the open-pit mining area and the real-time working condition data of the mining, transportation, and loading equipment group to obtain the collaborative operation scenario data of the mining area; performing intelligent feature extraction processing on the collaborative operation scenario data of the mining area and the energy consumption characteristic data of the mining, transportation, and loading equipment group to obtain the operation efficiency indicators of the equipment group; performing hierarchical decoupling processing on the operation efficiency indicators of the equipment group and the mining area mining plan data to obtain an energy-efficiency-oriented collaborative task sequence; performing swarm intelligence matching processing on the energy-efficiency-oriented collaborative task sequence and the spatio-temporal distribution data of the equipment group to obtain an integrated resource allocation plan for mining, transportation, and loading; performing dynamic coordination processing on the integrated resource allocation plan for mining, transportation, and loading and the road traffic constraint data to obtain an adaptive scheduling strategy for the equipment group; and performing closed-loop iterative processing on the adaptive scheduling strategy for the equipment group and the production process feedback data to obtain a collaborative optimization instruction for mining, transportation, and loading.

[0006] In a second aspect, the present application provides an integrated intelligent scheduling device for open-pit mining, transportation, and loading. The integrated intelligent scheduling device for open-pit mining, transportation, and loading includes:

[0007] A fusion module for performing multi-source information fusion processing on the topographic and geomorphic feature data of the open-pit mining area and the real-time working condition data of the mining, transportation, and loading equipment group to obtain the collaborative operation scenario data of the mining area;

[0008] An extraction module for performing intelligent feature extraction processing on the collaborative operation scenario data of the mining area and the energy consumption characteristic data of the mining, transportation, and loading equipment group to obtain the operation efficiency indicators of the equipment group;

[0009] A decoupling module for performing hierarchical decoupling processing on the operation efficiency indicators of the equipment group and the mining area mining plan data to obtain an energy-efficiency-oriented collaborative task sequence;

[0010] A matching module for performing swarm intelligence matching processing on the energy-efficiency-oriented collaborative task sequence and the spatio-temporal distribution data of the equipment group to obtain an integrated resource allocation plan for mining, transportation, and loading;

[0011] A coordination module for performing dynamic coordination processing on the integrated resource allocation plan for mining, transportation, and loading and the road traffic constraint data to obtain an adaptive scheduling strategy for the equipment group;

[0012] An iteration module for performing closed-loop iterative processing on the adaptive scheduling strategy for the equipment group and the production process feedback data to obtain a collaborative optimization instruction for mining, transportation, and loading.

[0013] In a third aspect of the present application, there is provided a computer-readable storage medium storing instructions which, when run on a computer, cause the computer to execute the above-mentioned integrated intelligent scheduling method for open-pit mining, transportation, and loading.

[0014] In the technical solution provided by this application, through multi-source information fusion processing of the topographic and geomorphic feature data of the open-pit mining area and the real-time working condition data of the mining, loading, and transportation equipment group, a comprehensive perception of the mining area's terrain features and equipment operating status is achieved, providing a reliable data basis for subsequent scheduling decisions. At the same time, intelligent feature extraction processing is carried out on the collaborative operation scenario data of the mining area and the energy consumption characteristic data of the mining, loading, and transportation equipment group, deeply excavating the energy consumption law during the equipment operation process, providing a basis for energy-saving optimization. Based on the hierarchical decoupling processing of the equipment group operation efficiency index and the mining area exploitation planning data, a reasonable decomposition and scientific organization of the mining, loading, and transportation operation tasks are achieved, effectively improving the feasibility of task execution. Through the group intelligent matching processing of the collaborative task sequence oriented to energy efficiency and the spatio-temporal distribution data of the equipment group, an optimal allocation of equipment resources is achieved, significantly improving the equipment utilization efficiency. Combining the dynamic coordination processing of the integrated mining, loading, and transportation resource allocation plan and the road passage constraint data, a flexible scheduling strategy adjustment mechanism is established, effectively coping with various uncertain factors during the production process. Finally, through the closed-loop iterative processing of the equipment group adaptive scheduling strategy and the production process feedback data, a complete closed-loop control system of optimization - execution - feedback - adjustment is formed, ensuring the continuous optimization of the scheduling plan and the stable operation of the production process. Through the organic combination of these technical features, the present invention not only improves the production efficiency and equipment utilization rate of the open-pit mining area, but also realizes the reduction of energy consumption and the saving of production costs, while enhancing the adaptability of the scheduling system to complex working conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0016] Figure 1 It is a schematic diagram of an embodiment of the integrated intelligent scheduling method for open-pit mining, loading, and transportation in the embodiments of this application;

[0017] Figure 2 It is a schematic diagram of an embodiment of the integrated intelligent scheduling device for open-pit mining, loading, and transportation in the embodiments of this application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0018] The embodiments of the present application provide an intelligent scheduling method, device, and medium for integrated mining, transportation, and loading in open-pit mines. The terms "first", "second", "third", "fourth", etc. (if any) in the specification, claims, and above-mentioned drawings of the present application are used to distinguish similar objects and do not necessarily need to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances so that the embodiments described here can be implemented in an order other than that illustrated or described here. In addition, the term "including" or "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or are inherent to these processes, methods, products, or devices.

[0019] For ease of understanding, the specific process of the embodiments of the present application is described below. Please refer to Figure 1 One embodiment of the intelligent scheduling method for integrated mining, transportation, and loading in open-pit mines in the embodiments of the present application includes:

[0020] Step S101: Perform multi-source information fusion processing on the topographic and geomorphic feature data of the open-pit mining area and the real-time working condition data of the mining, transportation, and loading equipment group to obtain the collaborative operation scenario data of the mining area;

[0021] Step S102: Perform intelligent feature extraction processing on the collaborative operation scenario data of the mining area and the energy consumption characteristic data of the mining, transportation, and loading equipment group to obtain the operation efficiency index of the equipment group;

[0022] Step S103: Perform hierarchical decoupling processing on the operation efficiency index of the equipment group and the mining area mining plan data to obtain an energy efficiency-oriented collaborative task sequence;

[0023] Step S104: Perform swarm intelligence matching processing on the energy efficiency-oriented collaborative task sequence and the spatio-temporal distribution data of the equipment group to obtain an integrated mining, transportation, and loading resource allocation plan;

[0024] Step S105: Perform dynamic coordination processing on the integrated mining, transportation, and loading resource allocation plan and the road traffic constraint data to obtain an adaptive scheduling strategy for the equipment group;

[0025] Step S106: Perform closed-loop iterative processing on the adaptive scheduling strategy of the equipment group and the production process feedback data to obtain an integrated mining, transportation, and loading collaborative optimization instruction.

[0026] It can be understood that the execution subject of the present application can be an intelligent scheduling device for integrated mining, transportation, and loading in open-pit mines, or a terminal or a server. Specifically, it is not limited here. The embodiments of the present application are described by taking the server as the execution subject as an example.

[0027] Specifically, the topographic and geomorphic feature data of the open-pit mining area and the real-time working condition data of the mining, loading, and transportation equipment group are processed. The topographic and geomorphic feature data includes information such as the terrain slope, regional elevation, and geological structure of the mining area, and the real-time working condition data of the mining, loading, and transportation equipment group includes real-time operation parameters such as the position, speed, and engine speed of the equipment. The operation-level data of the mining area is obtained through hierarchical and zonal processing, and then the boundary feature extraction is carried out to obtain the boundary point set of the operation area. After that, the passable area is determined using the boundary tracking algorithm. The spatial distribution characteristics of the equipment group are analyzed through density clustering processing, and the energy consumption status of the equipment is evaluated in combination with the engine working condition data. Finally, the collaborative operation scenario data of the mining area is formed. After obtaining the collaborative operation scenario data of the mining area, intelligent feature extraction is carried out in combination with the energy consumption characteristic data of the mining, loading, and transportation equipment group. First, the scenario data is classified by region to obtain the feature types of different operation areas, such as the excavation area, transportation area, unloading area, etc. The movement trajectories of the equipment group are analyzed through sequence pattern mining to identify typical operation modes. In combination with the instantaneous fuel consumption data of the equipment, the energy consumption change rate under different operation modes is calculated to establish the energy consumption gradient data. Multidimensional correlation analysis is carried out on parameters such as equipment load, engine speed, and hydraulic system pressure, and dimensionality reduction processing is carried out through principal component analysis. Finally, a comprehensive index reflecting the operation efficiency of the equipment is obtained. Based on the operation efficiency index of the equipment group, hierarchical decoupling processing is carried out in combination with the mining area exploitation planning data. The equipment is classified by energy efficiency level through hierarchical quantization, and the energy consumption interval threshold is determined. Spatial matching is carried out for the excavation working face to establish the corresponding relationship between the working face and the equipment energy consumption, and weighted calculation is carried out considering the transportation distance. The basic operation units are split according to the monthly mining plan, and the feasible task set is determined under the energy consumption constraint. Finally, spatio-temporal coordination is carried out to obtain the collaborative task sequence oriented to energy efficiency.

[0028] Group intelligent matching processing is carried out for the collaborative task sequence. First, the task constraint conditions are extracted and standardized. The distance matrix between the equipment and the tasks is calculated, and the scheduling cost is estimated. The Hungarian algorithm is used to optimize the task allocation. This algorithm realizes the optimal allocation of tasks by constructing the minimum weight matching of the bipartite graph. Conflict detection and time window adjustment are carried out for the initial allocation scheme to ensure the feasibility of task execution. Finally, a resource allocation scheme for integrated mining, loading, and transportation is formed. Based on the resource allocation scheme, dynamic coordination processing is carried out considering the road passage constraint. The movement time sequence of the equipment is analyzed, the intersection point position is predicted, and the safety distance is calculated in combination with the road bearing capacity. The road passage capacity is evaluated by time period, and a congestion warning mechanism is established. Peak-shifting scheduling is realized through time window adjustment, and dynamic correction is carried out according to the equipment trajectory deviation to form an adaptive scheduling strategy.

[0029] Finally, scheduling optimization is achieved through closed-loop iterative processing. Conduct timeliness analysis and progress monitoring on the implementation of the strategy, discover deviations by comparing real-time production data, and conduct attribution analysis. Identify typical deviation patterns, and put forward adjustment suggestions in combination with historical handling experience. Conduct scenario adaptation and feasibility verification, select the optimal instruction plan after multi-objective trade-off, and finally generate the collaborative optimization instruction for mining, hauling and loading.

[0030] Taking an open-pit mining area as an example, the area of this mining area is about 5 square kilometers, and there are 30 existing mining, hauling and loading equipment. Through multi-source information fusion processing, the mining area is divided into 8 operation levels, and 120 boundary feature points are identified. The distribution of the equipment group shows 3 main operation aggregation areas, and the average equipment energy consumption is 45L / h. Feature extraction analysis shows that the energy consumption difference under different regional operation modes reaches 30%, and there is an obvious correlation between load and energy consumption. During the task decoupling process, the monthly stripping volume of 2.4 million tons is decomposed into 2,400 basic operation units. The Hungarian algorithm is used for task matching, and the optimal scheduling plan calculated saves 15% energy consumption compared with the original scheduling plan. In the coordination of road traffic, 4 easily congested sections are identified, and the congestion time is reduced by 40% through dynamic adjustment. The closed-loop iterative optimization improves the operation efficiency of the mining, hauling and loading equipment by 20%, and the overall operation of the system is more stable and reliable.

[0031] In the embodiments of the present application, through multi-source information fusion processing of the topographic and geomorphic feature data of the open-pit mining area and the real-time working condition data of the mining, hauling and loading equipment group, a comprehensive perception of the mining area terrain features and equipment operation status is realized, providing a reliable data basis for subsequent scheduling decisions. At the same time, intelligent feature extraction processing is carried out on the collaborative operation scenario data of the mining area and the energy consumption characteristic data of the mining, hauling and loading equipment group, deeply excavating the energy consumption law in the equipment operation process, and providing a basis for energy-saving optimization. Based on the hierarchical decoupling processing of the operation efficiency index of the equipment group and the mining area exploitation planning data, a reasonable decomposition and scientific organization of the mining, hauling and loading operation tasks are realized, effectively improving the feasibility of task execution. Through the swarm intelligence matching processing of the collaborative task sequence oriented to energy efficiency and the spatio-temporal distribution data of the equipment group, an optimal allocation of equipment resources is realized, significantly improving the equipment utilization efficiency. Combining the dynamic coordination processing of the integrated resource allocation plan for mining, hauling and loading and the road traffic constraint data, a flexible scheduling strategy adjustment mechanism is established, effectively coping with various uncertain factors in the production process. Finally, through the closed-loop iterative processing of the adaptive scheduling strategy of the equipment group and the production process feedback data, a complete closed-loop control system of optimization - execution - feedback - adjustment is formed, ensuring the continuous optimization of the scheduling plan and the stable operation of the production process. Through the organic combination of these technical features, the present invention not only improves the production efficiency and equipment utilization rate of the open-pit mining area, but also realizes the reduction of energy consumption and the saving of production costs, while enhancing the adaptability of the scheduling system to complex working conditions.

[0032] In a specific embodiment, the process of executing step S101 may specifically include the following steps:

[0033] (1) Perform hierarchical and zonal processing on the topographic and geomorphic feature data of the open-pit mining area to obtain the mining area operation level data, and perform boundary feature extraction processing on the mining area operation level data to obtain the operation area boundary point set;

[0034] (2) Perform regional connectivity analysis processing on the operation area boundary point set to obtain the passable area data for the mining and haulage equipment, and perform contour extraction processing on the passable area data through the boundary tracking algorithm to obtain the mining area passable range data;

[0035] (3) Perform spatio-temporal correlation processing on the position data and speed data of the mining and haulage equipment group to obtain the dynamic distribution data of the equipment group, and perform density clustering processing on the dynamic distribution data of the equipment group to obtain the operation aggregation area data of the equipment group;

[0036] (4) Perform correlation analysis processing on the operation aggregation area data of the equipment group and the engine speed data of the equipment to obtain the working condition characteristic data of the equipment group, and perform energy consumption assessment processing on the working condition characteristic data of the equipment group to obtain the energy consumption status data of the equipment group;

[0037] (5) Perform regional division processing on the mining area passable range data and the energy consumption status data of the equipment group to obtain the energy consumption zone data, and perform grade division processing on the energy consumption zone data to obtain the zone energy consumption grade data;

[0038] (6) Perform frequency statistics processing on the zone energy consumption grade data and the historical operation records to obtain the regional operation frequency data, and perform weight calculation processing on the regional operation frequency data to obtain the regional operation intensity data;

[0039] (7) Perform matching and correlation processing on the regional operation intensity data and the real-time equipment status data to obtain the mining area collaborative operation scenario data.

[0040] Specifically, the processing of the topographic and geomorphic feature data of the open-pit mining area first involves layering and zoning, which is carried out based on the elevation data of the mining area. The topographic and geomorphic feature data includes information such as the slope, altitude, and geological structure of the mining area. By analyzing these data, the mining area is divided into different operation levels. Each operation level represents a specific mining platform with similar topographic features and operating conditions. After obtaining the operation level data of the mining area, boundary feature extraction is performed on each level to identify the key boundary points of the operation area. These boundary points form the boundary point set of the operation area, which is used to describe the spatial scope of each operation area. After obtaining the boundary point set of the operation area, regional connectivity analysis is required to determine the passable areas for the mining, loading, and transportation equipment. Connectivity analysis identifies the areas where the equipment can pass by judging the relationship between adjacent boundary points. The boundary tracking algorithm is an important method for extracting the regional contour. The algorithm starts from a starting boundary point and sequentially searches for adjacent boundary points according to specific rules, finally forming a complete regional contour. By processing the passable area data with the boundary tracking algorithm, accurate passable range data of the mining area is obtained. For the management of the mining, loading, and transportation equipment group, spatio-temporal correlation processing of the position data and speed data of the equipment is required. The position data comes from the GPS positioning system, and the speed data comes from the driving records of the equipment. Spatio-temporal correlation processing corresponds the position and speed information in the time dimension to form the dynamic distribution data of the equipment group. Density clustering processing is a density-based clustering analysis method. By analyzing the distribution density of the equipment in space, the operation aggregation areas of the equipment group are identified. The correlation analysis between the operation aggregation area data of the equipment group and the engine speed data of the equipment aims to evaluate the working state of the equipment. The engine speed data reflects the load condition of the equipment. Through correlation analysis, the working condition characteristic data of the equipment group is obtained. The working conditions characteristics include indicators such as the engine load rate, running time, and idle time. Energy consumption assessment is performed on the working condition characteristic data to calculate parameters such as the fuel consumption per unit time and the energy utilization efficiency, thereby obtaining the energy consumption state data of the equipment group.

[0041] The combination of the passable range data of the mining area and the energy consumption state data of the equipment group forms energy consumption zoning data through regional division processing. Regional division takes into account the impact of factors such as road slope and road surface conditions on energy consumption. Grade division is performed on the energy consumption zoning data. The area is divided into different grades according to the energy consumption level per unit distance to obtain the zoned energy consumption grade data. Frequency statistics are performed on the zoned energy consumption grade data in combination with historical operation records to analyze the operation frequencies of each area. Frequency statistics includes information such as the number of equipment passes and operation duration. Through statistics, the regional operation frequency data is obtained. Weight calculation is performed on the operation frequency data, considering factors such as operation type, equipment type, and operation time, to determine the operation intensity weights of each area and obtain the regional operation intensity data.

[0042] Finally, the regional operation intensity data is matched and associated with the real-time device status data. The real-time device status data includes information such as device location, working status, and remaining fuel. Through matching and association, the corresponding relationship between the regional operation intensity and the device status is established, and finally, the complete data of the collaborative operation scenario in the mining area is formed.

[0043] Taking an open-pit mine as an example, the area of this mining area is 4 square kilometers, and the vertical height difference is 300 meters. Through hierarchical and zonal processing, the mining area is divided into 12 operation levels, with a height difference of 25 meters for each level. Feature extraction of the boundary identifies an average of 80 boundary feature points for each level. Regional connectivity analysis determines 10 main transportation channels, and the boundary tracking algorithm outlines a passage range with a total length of 15 kilometers. The mining area is equipped with 20 mining, loading, and transportation devices. Through density clustering analysis, 3 main operation aggregation areas are identified, which are located in the mining area, loading area, and unloading area respectively. The engine speed data of the devices shows that the average speed on the uphill section is 1800 rpm, and the energy consumption is about 50 L / h; the average speed on the flat section is 1500 rpm, and the energy consumption is about 35 L / h. The energy consumption area is divided into 5 levels, among which the first-level area (slope less than 3%) has the lowest energy consumption, and the fifth-level area (slope greater than 15%) has the highest energy consumption. Historical operation records show that the average daily passing frequency of the main road is 200 times, and the average daily passing frequency of the branch road is 50 times. Weight calculation takes into account the operation type (mining and loading weight 1.5, transportation weight 1.0) and time period factors (peak period weight 1.2, off-peak period weight 1.0).

[0044] In a specific embodiment, the process of executing step S102 may specifically include the following steps:

[0045] (1) Perform regional classification processing on the data of the collaborative operation scenario in the mining area to obtain the data of the set of scenario feature types, and perform statistical aggregation processing on the data of the set of scenario feature types to obtain the data of the regional operation mode.

[0046] (2) Perform spatio-temporal association processing on the data of the regional operation mode and the GPS trajectory data of the device group to obtain the data of the movement characteristics of the device group, and perform frequent pattern extraction processing on the data of the movement characteristics of the device group through sequence pattern mining to obtain the data of the typical operation sequence.

[0047] (3) Perform temporal matching processing on the data of the typical operation sequence and the instantaneous fuel consumption data of the device group to obtain the corresponding data of the operation energy consumption, and perform change rate calculation processing on the corresponding data of the operation energy consumption to obtain the energy consumption gradient data of the device group.

[0048] (4) Perform multi-dimensional association processing on the energy consumption gradient data of the device group and the device load data to obtain the energy consumption per unit load data, and perform outlier detection processing on the energy consumption per unit load data to obtain the data of the energy consumption threshold interval.

[0049] (5) Analyze and process the response characteristics of the energy consumption threshold interval data and the equipment engine speed data to obtain the equipment power response data, and perform feature dimensionality reduction processing on the equipment power response data through principal component analysis to obtain the key feature factor data;

[0050] (6) Conduct combined analysis and processing on the key feature factor data and the equipment hydraulic system pressure data to obtain the equipment comprehensive performance data, and perform quantitative scoring processing on the equipment comprehensive performance data to obtain the equipment group operation efficiency index.

[0051] Specifically, the processing of the mining area collaborative operation scenario data starts from regional classification. The mining area is mainly divided into different types such as the excavation operation area, the loading operation area, the transportation channel area, and the unloading operation area. The regional classification processing is based on the terrain features, equipment distribution, and operation characteristics in the scenario data, and the scenario feature type set data is obtained through the clustering analysis method. Perform statistical aggregation processing on the scenario feature type set data, analyze the characteristics such as the area ratio, equipment distribution density, and operation frequency of each type of area, so as to obtain the regional operation mode data. Conduct spatio-temporal correlation analysis on the regional operation mode data and the equipment group GPS trajectory data. The GPS trajectory data records information such as the position, speed, and direction of the equipment. The spatio-temporal correlation processing analyzes the movement characteristics of the equipment in different regions by matching the equipment trajectory points with the regional operation mode. Sequence pattern mining is a data mining method specifically used to discover frequently occurring patterns in data sequences. Process the equipment group movement characteristic data through the sequence pattern mining technology, identify the typical movement paths and operation sequences of the equipment group between different regions, and form the typical operation sequence data.

[0052] In the time series matching process of the typical operation sequence data and the equipment group instantaneous fuel consumption data, associate the fuel consumption data corresponding to each operation sequence segment to obtain the energy consumption characteristics of different operation types and paths. The fuel consumption data comes from the real-time monitoring of the equipment fuel sensor and records the fuel consumption per unit time. By calculating the fuel consumption change rate between adjacent time points, obtain the equipment group energy consumption gradient data, which reflects the dynamic characteristics of energy consumption changing with operation type and road conditions. Conduct multi-dimensional correlation analysis on the equipment group energy consumption gradient data and the equipment load data. The load data includes the equipment self-weight and the weight of the loaded goods. By calculating the energy consumption level per unit load under different operation conditions, obtain the energy consumption per unit load data. Adopt outlier detection methods, such as the 3σ criterion or the box plot method, to identify abnormal energy consumption data points and determine a reasonable energy consumption change range, so as to obtain the energy consumption threshold interval data.

[0053] The response characteristic analysis of the energy consumption threshold interval data and the equipment engine speed data mainly focuses on the corresponding relationship between the engine working conditions and the energy consumption. The engine speed data reflects the power output state of the equipment. Combining with the previously obtained energy consumption data, the energy consumption change characteristics at different speeds are analyzed to obtain the equipment power response data. Principal component analysis is a dimensionality reduction method that performs an orthogonal transformation on high-dimensional data to retain the main characteristic information. Principal component analysis is performed on the equipment power response data to extract key characteristic factors, reduce the data dimension, and obtain the key characteristic factor data. The combined analysis of the key characteristic factor data and the equipment hydraulic system pressure data focuses on examining the comprehensive working performance of the equipment. The hydraulic system pressure data reflects the load state of the equipment actuator and is closely related to the power output and energy consumption. By analyzing the correlation between various indicators, a performance evaluation system is established, and finally the equipment comprehensive performance data is obtained. The comprehensive performance data is quantitatively scored to form a standardized equipment group operation efficiency index.

[0054] Taking the actual application of an open-pit mine as an example, the total area of the mining area is 6 square kilometers, with 3 excavation faces, 2 loading areas, and 4 unloading platforms. Statistical analysis shows that the excavation area accounts for 30%, the loading area accounts for 15%, the transportation channel accounts for 40%, and the unloading area accounts for 15%. GPS trajectory analysis shows the daily operation trajectories of 15 mining trucks. Through sequence pattern mining, 4 typical operation paths are found: the mining-loading-transporting-unloading cyclic operation accounts for 65%, the short-distance shuttle transportation accounts for 20%, the mining-loading combined operation accounts for 10%, and the maintenance and rescue operation accounts for 5%. Time series matching analysis shows that under the condition of an average load of 40 tons, the no-load uphill energy consumption is 45 L / h, the full-load uphill energy consumption is 75 L / h, the no-load energy consumption on the flat section is 25 L / h, and the full-load is 45 L / h. Outlier detection eliminates the energy consumption data points outside the normal range and determines the energy consumption threshold interval under each working condition. The engine response characteristic analysis shows that when the speed is in the range of 1200 - 1800 rpm, the energy consumption and the speed show a linear relationship, and the energy consumption rises sharply after exceeding 1800 rpm. Principal component analysis reduces the original 12 performance indicators to 4 key characteristic factors, and these factors can explain 85% of the data variance. Finally, the equipment group operation efficiency index is obtained through comprehensive scoring. The scoring range is 0 - 100, where above 90 points is excellent, 80 - 90 points is good, 70 - 80 points is qualified, and below 70 points requires optimization and improvement.

[0055] In a specific embodiment, the process of executing step S103 may specifically include the following steps:

[0056] (1) Perform hierarchical quantization processing on the equipment group operation efficiency index to obtain equipment energy efficiency classification data, and perform threshold segmentation processing on the equipment energy efficiency classification data to obtain equipment operating energy consumption interval data;

[0057] (2) Perform spatial matching processing on the equipment operation energy consumption interval data and the mining face layout data to obtain the energy consumption mapping data of the working face equipment, and perform hierarchical clustering processing on the energy consumption mapping data of the working face equipment to obtain the energy consumption level data of the loading operation;

[0058] (3) Perform weighted calculation processing on the energy consumption level data of the loading operation and the transportation route distance data to obtain the transportation energy consumption weight data, and perform segmented cumulative processing on the transportation energy consumption weight data to obtain the segmented transportation cost data;

[0059] (4) Perform task decomposition processing on the segmented transportation cost data and the monthly mining plan data of the mining area to obtain the basic operation unit data, and perform energy consumption constraint processing on the basic operation unit data to obtain the energy efficiency feasible task set;

[0060] (5) Perform boundary constraint processing on the energy efficiency feasible task set and the equipment operation range data to obtain the task space distribution data, and perform time sequence sorting processing on the task space distribution data to obtain the initial task time sequence data;

[0061] (6) Perform matching and optimization processing on the initial task time sequence data and the equipment energy efficiency level data to obtain the task-equipment corresponding data, and perform space-time coordination processing on the task-equipment corresponding data to obtain the collaborative task sequence oriented to energy efficiency.

[0062] Specifically, the hierarchical quantization processing of the equipment group operation efficiency index involves converting continuous efficiency indexes into discrete level data. The equipment energy efficiency classification data is obtained by dividing different energy efficiency level intervals, and then threshold segmentation processing is performed on the equipment energy efficiency classification data to determine the energy consumption range corresponding to each level, so as to obtain the equipment operation energy consumption interval data. In the process of spatial matching between the equipment operation energy consumption interval data and the mining face layout data, the energy consumption characteristics of the equipment are associated with the spatial position of the mining face. Spatial matching calculates the energy consumption level of the equipment at different mining face positions to obtain the energy consumption mapping data of the working face equipment. Hierarchical clustering is a bottom-up clustering method that gradually merges mining faces according to energy consumption similarity to form the energy consumption level data of the loading operation.

[0063] For the weighted calculation of the energy consumption level data of the loading operation and the transportation route distance data, a segmented transportation cost calculation formula is introduced:

[0064] ;

[0065] Among them, is the total transportation cost, is the number of transportation sections, is the plane transportation energy consumption coefficient of the i-th section, is the transportation distance of the i-th section, is the load coefficient of the i-th section, is the vertical transportation energy consumption coefficient of the i-th section, is the elevation difference of the i-th section, is the slope correction coefficient of the i-th section, is the road condition weight coefficient of the i-th section.

[0066] The transportation energy consumption weight data is calculated through this formula, and the transportation energy consumption weight data is cumulatively segmented to obtain the segmented transportation cost data. The segmented transportation cost data is combined with the monthly mining plan data of the mining area for task decomposition, splitting the large-scale mining task into basic operation units to obtain the basic operation unit data. Energy consumption constraint processing is performed on the basic operation unit data, and the operation plans with excessive energy consumption are eliminated to obtain the energy efficiency feasible task set.

[0067] The boundary constraint processing of the energy efficiency feasible task set and the equipment operation range data mainly considers the operation radius and area limitations of the equipment. The spatial distribution characteristics of the tasks are determined through boundary constraints to obtain the task spatial distribution data. The task spatial distribution data is sorted in chronological order to form the initial task time series data. Matching and optimization processing are performed on the initial task time series data and the equipment energy efficiency level data. According to the task requirements and equipment performance characteristics, the most suitable equipment is selected to execute the corresponding tasks to obtain the task-equipment corresponding data. Finally, through space-time coordination processing, it is ensured that there is no conflict in the operations between multiple equipment, forming a collaborative task sequence oriented to energy efficiency.

[0068] Taking an open-pit mine as an example, this mining area is equipped with 20 mining, loading and transportation equipment. Through the quantification of efficiency indicators, the equipment is divided into three energy efficiency levels: A, B, and C, and the corresponding energy consumption ranges are 30 - 40 L / h, 40 - 50 L / h, and 50 - 60 L / h respectively. There are 4 excavation faces in the mining area. Through spatial matching and hierarchical clustering analysis, the excavation faces are divided into 2 energy consumption levels: the first-level excavation face (average energy consumption 35 L / h) and the second-level excavation face (average energy consumption 45 L / h). The total length of the transportation route is 15 kilometers and is divided into 8 sections. The transportation cost of each section is calculated through the above formula. Taking the first section as an example: the horizontal distance is 1.2 kilometers ( = 1.2), the elevation difference is 50 meters ( = 50), the full load coefficient is 1.5 ( = 1.5), the slope correction coefficient is 1.2 ( = 1.2), the road condition weight is 1.1 ( = 1.1), and the transportation cost of this section is calculated.

[0069] The monthly mining plan is 3 million tons, which is decomposed into 2,000 basic operation units, with an average of 1,500 tons per unit. After considering the energy consumption constraint, 1,800 feasible tasks are screened out. The operation range of the equipment is limited within a radius of 2 kilometers. Through boundary constraints and time sequence sorting, an 8-hour shift operation plan is formed. The final matching result shows that Class A equipment is mainly assigned to long-distance transportation tasks, Class B equipment performs medium-distance transportation, and Class C equipment is responsible for short-distance transportation, thus achieving the optimal energy efficiency in collaborative operations.

[0070] In a specific embodiment, the process of executing step S104 may specifically include the following steps:

[0071] (1) Perform pre-demand extraction processing on the collaborative task sequence oriented to energy efficiency to obtain task constraint condition data, and perform normalization processing on the task constraint condition data to obtain normalized constraint index data;

[0072] (2) Perform distance calculation processing on the normalized constraint index data and the real-time position data of the equipment group to obtain equipment task distance matrix data, and perform energy consumption estimation processing on the equipment task distance matrix data to obtain equipment scheduling cost data;

[0073] (3) Perform fitness calculation processing on the equipment scheduling cost data and the equipment operation capacity data to obtain equipment task matching degree data, and perform optimal allocation processing on the equipment task matching degree data through the Hungarian algorithm to obtain initial allocation scheme data;

[0074] (4) Perform conflict detection processing on the initial allocation scheme data and the historical operation record data to obtain task conflict point set data, and perform time window adjustment processing on the task conflict point set data to obtain feasible scheduling time sequence data;

[0075] (5) Perform dynamic balance processing on the feasible scheduling time sequence data and the energy consumption status data of the equipment group to obtain equipment load allocation data, and perform working face collaboration processing on the equipment load allocation data to obtain an integrated mining, transportation, and loading resource allocation scheme.

[0076] Specifically, in the integrated intelligent scheduling method for open-pit mining, loading, and transportation, the pre-demand extraction and processing is a process of constraint analysis for the energy-efficient collaborative task sequence. The task constraint condition data includes multiple aspects such as time constraints (task start time, completion deadline), space constraints (operation area range, equipment driving route), and resource constraints (equipment type requirements, personnel configuration requirements), etc. The standardization process converts different types of constraint conditions into indicators with a unified dimension, forming standardized constraint index data, which provides a basis for subsequent matching calculations. The distance calculation processing between the standardized constraint index data and the real-time position data of the equipment group uses the Euclidean distance calculation method. Calculate the actual distance between each piece of equipment and each task point, and construct the equipment-task distance matrix data. The energy consumption estimation processing is based on the distance matrix, combined with factors such as road slope and road conditions, to calculate the energy required to complete each task, and obtain the equipment scheduling cost data.

[0077] In the process of calculating the fitness between the equipment scheduling cost data and the equipment operation capacity data, factors such as the rated load, operation efficiency, and energy consumption level of the equipment are comprehensively considered to calculate the adaptation degree of each piece of equipment to perform various tasks, and obtain the equipment-task matching degree data. The Hungarian algorithm is a classic algorithm for solving the task assignment problem. Through iterative optimization, it finds the allocation scheme with the minimum total cost based on the equipment-task matching degree data and generates the initial allocation scheme data. When performing conflict detection processing on the initial allocation scheme data and the historical operation record data, it mainly checks for conflict situations of the equipment in the spatial and temporal dimensions. By analyzing the driving routes and operation timings of the equipment, find the task points with intersections and overlaps, and form the task conflict point set data. The time window adjustment processing is to arrange the conflict tasks at different times, adjust the execution timings of the tasks, and generate the feasible scheduling timings data.

[0078] The dynamic balance processing between the feasible scheduling timings data and the equipment group energy consumption status data focuses on the balance of equipment loads. According to the current energy consumption level and remaining operation capacity of the equipment, reallocate the tasks to obtain the equipment load allocation data. The working face coordination processing makes overall arrangements for the mining and loading operations and transportation operations to ensure smooth connection of each link, and finally forms the integrated resource allocation scheme for mining, loading, and transportation.

[0079] Taking an open-pit mine as an example, the mining area has 25 mining, loading and hauling equipment, including 5 excavators, 8 loaders and 12 mining trucks. Through pre-demand extraction, it is determined that 300 operation units need to be executed for the mining task of 300,000 tons per day. The time window for each operation unit is 2 hours, and the operation area is restricted within the range of 2,000 meters × 1,500 meters. The normalized constraint index converts the time window into a 0-1 standard score, and the space constraint is converted into a relative distance ratio. The distance calculation process constructs a 25×300 distance matrix, and each cell represents the distance from a specific piece of equipment to a task point. For example, the distance from Mining Truck No. 1 to Task Point A1 is 1.2 kilometers, and the energy consumption estimation shows that 25 liters of fuel are required to complete this task. The equipment operation capacity data shows that the rated load of this truck is 90 tons, the average operation efficiency is 300 tons / hour, and the energy consumption level is 40 liters / hour.

[0080] Through the iterative optimization of the Hungarian algorithm, the initial allocation plan shows that 12 mining trucks are respectively responsible for 20-30 transportation tasks. Conflict detection finds that there are intersections in three sections, two of which are near the loading points and one is on the main transportation road. By adjusting the time window, the conflict task interval is set to 15 minutes, effectively avoiding equipment congestion. The dynamic balance processing results show that through task reallocation, the load difference of each piece of equipment is controlled within 10%. The final integrated mining, loading and hauling resource allocation plan realizes the close cooperation of the three links of mining, loading and hauling. The excavation rhythm of the excavator matches the loading capacity of the loader, and the turnover of the transportation vehicles is highly coordinated with the loading operation. The overall operation efficiency is increased by 25%, and the equipment utilization rate reaches more than 85%.

[0081] In a specific embodiment, the process of executing step S105 may specifically include the following steps:

[0082] (1) Conduct time series analysis on the integrated mining, loading and hauling resource allocation plan to obtain equipment movement time series data, and conduct cross-detection on the equipment movement time series data to obtain equipment intersection prediction data;

[0083] (2) Conduct safety distance calculation on the equipment intersection prediction data and road bearing capacity data to obtain minimum safety spacing data, and conduct traffic capacity analysis on the minimum safety spacing data and road width data to obtain road traffic capacity data;

[0084] (3) Conduct status evaluation on the road traffic capacity data and real-time road condition monitoring data to obtain road traffic level data, and conduct sub-period statistics on the road traffic level data to obtain road congestion warning data;

[0085] (4) Adjust the time window of the road congestion warning data and the equipment group scheduling sequence data to obtain the off-peak scheduling plan data, and perform collaborative optimization processing on the off-peak scheduling plan data and the equipment energy consumption status data to obtain the road resource allocation data;

[0086] (5) Conduct deviation analysis on the road resource allocation data and the equipment operation trajectory data to obtain the trajectory correction parameter data, and perform comprehensive decision-making on the trajectory correction parameter data and the current job status data to obtain the equipment group adaptive scheduling strategy.

[0087] Specifically, the time series analysis of the integrated mining, loading and transportation resource allocation plan is the primary link. This processing converts the scheduling tasks of the equipment into time series, records the expected positions and motion states of each equipment at different times, and thus obtains the equipment movement time series data. By performing cross-detection on the equipment movement time series data, analyzing the spatio-temporal intersection points of the running trajectories of different equipment, predicting the meeting time and position of the equipment during operation, and generating equipment meeting prediction data. The equipment meeting prediction data is combined with the road bearing capacity data for safety distance calculation. The road bearing capacity data includes information such as road surface strength, road surface width, and slope. According to the braking performance of the equipment, road conditions, and driving speed, the safe stopping distance is calculated to form the minimum safety distance data. Perform traffic capacity analysis on the minimum safety distance data and the road width data, consider the vehicle meeting conditions of the equipment under the road width limit, and calculate the road traffic capacity data, which represents the maximum number of equipment that can pass through the road per unit time.

[0088] In the process of state evaluation of the road traffic capacity data and the real-time road condition monitoring data, comprehensively analyze the road traffic state, including factors such as road surface conditions, weather impacts, and equipment density, to obtain the road traffic level data. Conduct sub-period statistical processing on the road traffic level data, analyze the variation law of traffic pressure in different periods, and form the road congestion warning data. Adjust the time window of the road congestion warning data and the equipment group scheduling sequence data to avoid traffic congestion by adjusting the equipment operation time. Perform collaborative optimization on the adjusted off-peak scheduling plan data and the equipment energy consumption status data to calculate the road resource allocation data. The road resource allocation is calculated by the following formula:

[0089] ;

[0090] where RD is the road resource allocation index, is the number of road segments, m is the number of equipment, is the traffic weight of the i-th road segment, is the speed coefficient of the j-th equipment, is the period correction coefficient, is the road condition impact factor, is the energy consumption weight of the i-th section of the road, is the energy consumption coefficient of the j-th device. is the time period energy consumption correction coefficient, is the occupation time ratio of device j on road section i.

[0091] Deviation analysis is performed on the road resource allocation data and the device operation trajectory data to calculate the deviation between the actual operation trajectory and the planned path, and trajectory correction parameter data is generated. Comprehensive decision-making processing is carried out on the trajectory correction parameter data and the current job status data, and the scheduling strategy is dynamically adjusted according to factors such as job progress and device status, and finally an adaptive scheduling strategy for the device group is formed.

[0092] Taking the actual application of an open-pit mine as an example, there are 35 mining, loading and transportation devices in this mining area, and the total length of the transportation road is 18 kilometers. The time series analysis shows that each device runs 12 trips per shift on average, and 86 potential intersection points are identified through cross-checking. The safety distance calculation shows that on the main road (gradient 8%, road surface width 12 meters), heavy-load vehicles need to maintain a safety distance of more than 50 meters, and empty-load vehicles need to maintain a safety distance of more than 35 meters. The analysis result of the road traffic capacity shows that the maximum traffic volume per hour on the main road is 60 vehicle trips, and that on the secondary road is 40 vehicle trips. The road condition monitoring data is divided into three states: sunny day (traffic level A), light rain (traffic level B), and heavy rain (traffic level C). Statistics show that the traffic peak hours are from 9 to 11 am and from 3 to 5 pm, and the congestion risk increases by 50%.

[0093] Through time window adjustment, the 30 devices originally scheduled in the same time period are dispersed into 3 time periods, with 10 devices in each time period, reducing the probability of traffic congestion. The energy consumption data shows that after avoiding the congested sections, the average fuel consumption of the devices is reduced from 45L / h to 38L / h. The trajectory deviation analysis finds that the average deviation between the actual operation trajectory and the planned path is within the range of 3 - 5 meters. According to this deviation characteristic, the scheduling paths of the subsequent devices are dynamically adjusted, improving the overall transportation efficiency by 20%.

[0094] In a specific embodiment, the process of executing step S106 may specifically include the following steps:

[0095] (1) Perform timeliness analysis on the adaptive scheduling strategy of the device group to obtain the strategy execution time limit data, and perform segmented monitoring on the strategy execution time limit data to obtain the scheduling execution progress data;

[0096] (2) Perform difference comparison on the scheduling execution progress data and the real-time production data to obtain the production deviation index data, and perform attribution analysis on the production deviation index data to obtain the deviation cause data;

[0097] (3) Perform pattern recognition processing on the deviation cause data and equipment operation record data to obtain typical deviation pattern data, and perform correlation analysis processing on the typical deviation pattern data and historical disposal plan data to obtain strategy adjustment recommendation data;

[0098] (4) Perform scenario adaptation processing on the strategy adjustment recommendation data and the current equipment status data to obtain corrected control parameter data, and perform regional coordination processing on the corrected control parameter data to obtain equipment group regulation instruction data;

[0099] (5) Perform feasibility verification processing on the equipment group regulation instruction data and the operation environment constraint data to obtain instruction reliability evaluation data, and perform multi-objective trade-off processing on the instruction reliability evaluation data to obtain alternative instruction plan data;

[0100] (6) Perform matching degree calculation processing on the alternative instruction plan data and the production target data to obtain instruction optimization result data, and perform spatio-temporal consistency processing on the instruction optimization result data to obtain the coordinated optimization instruction for mining, hauling and loading.

[0101] Specifically, perform timeliness analysis processing on the equipment group adaptive scheduling strategy, and pay attention to the execution time window and key nodes of the strategy. The timeliness analysis is based on the task urgency, equipment operation cycle time and production plan requirements to form strategy execution time limit data. Perform segmented monitoring on the strategy execution time limit data, divide the entire execution cycle into multiple time segments, record the task completion situation in each time segment to obtain scheduling execution progress data. In the process of differential comparison processing between the scheduling execution progress data and the real-time production data, calculate the deviation value in the production process by comparing indicators such as planned output and actual output, planned time and actual time, etc., to form production deviation index data. Perform attribution analysis on the production deviation index data, and find the reasons for the deviation from multiple dimensions such as equipment performance, road conditions, and weather conditions to obtain deviation cause data.

[0102] The pattern recognition processing of the deviation cause data and the equipment operation record data adopts the clustering analysis method, classify similar deviation patterns, extract common features to form typical deviation pattern data. Perform correlation analysis on the typical deviation pattern data and the historical disposal plan data, find effective treatment measures taken in similar deviation situations in history, and generate strategy adjustment recommendation data. The scenario adaptation processing of the strategy adjustment recommendation data and the current equipment status data mainly considers factors such as the real-time working conditions of the equipment, remaining energy, and operation environment to ensure the executability of the adjustment recommendation in the current scenario, and obtain corrected control parameter data. Perform regional coordination processing on the corrected control parameter data to ensure the coordination of scheduling instructions between each operation area, and form equipment group regulation instruction data.

[0103] During the feasibility verification process of the equipment group control instruction data and the operation environment constraint data, check whether the scheduling instructions meet the constraint conditions such as safety distance, road conditions, and equipment capabilities, and generate instruction reliability evaluation data. Conduct multi-objective trade-offs on the instruction reliability evaluation data, and on the basis of ensuring multiple objectives such as production efficiency, energy utilization, and equipment life, form alternative instruction plan data. Calculate the matching degree between the alternative instruction plan data and the production target data, evaluate the satisfaction degree of each plan with respect to the production target, and obtain the instruction optimization result data. Conduct spatio-temporal consistency processing on the instruction optimization result data to ensure the coordination and unity of scheduling instructions in different regions and different time periods, and finally generate the collaborative optimization instruction for mining, loading, and transportation.

[0104] Taking the actual application of an open-pit mine as an example, this mining area is equipped with 45 mining, loading, and transportation equipment, and the daily production plan is 500,000 tons. The timeliness analysis divides the 8-hour work shift into 16 30-minute time segments, and sets the production target of 31,250 tons for each time segment. The segmented monitoring shows that in the third time segment in the morning, the actual production is 28,000 tons, resulting in a negative deviation of 3,250 tons. The difference comparison analysis finds that the running time of 2 transport vehicles in this time period exceeds the expectation, with an average increase of 4 minutes per trip. The attribution analysis shows that the main reason is that the road surface of a specific section is slippery, resulting in a reduction in vehicle speed. The pattern recognition process extracts 5 typical deviation patterns from the recent 300 deviation records, and the transportation delay caused by road conditions accounts for 35%. The historical disposal plan shows that through a combination of measures such as temporary diversion and adjustment of the loading volume, similar situations can be effectively alleviated.

[0105] During the scenario adaptation process, considering the current equipment status (15 transport vehicles are in the best working condition) and the characteristics of the operation area (the bearing capacity of the alternative road is sufficient), the control parameters for adjusting the transportation route are generated. The regional coordination process ensures the balance of the vehicle flow after the diversion, and the equipment group control instruction requires 8 vehicles to use the alternative route. The feasibility verification shows that the new route meets the safety requirements but will increase the energy consumption by 5%. After multi-objective trade-offs, three alternative plans are formed: complete diversion, partial diversion, and maintaining the original route but reducing the loading volume. Through the matching degree calculation, the complete diversion plan has the highest satisfaction degree with respect to the production target, and finally this plan is selected as the optimization instruction. After implementing this plan, the production in the subsequent time segments reaches 32,000 tons, successfully making up for the previous deviation.

[0106] The above describes the integrated intelligent scheduling method for open-pit mine mining, loading, and transportation in the embodiments of the present application. Next, the integrated intelligent scheduling device for open-pit mine mining, loading, and transportation in the embodiments of the present application will be described. Please refer to Figure 2 , an embodiment of the integrated intelligent scheduling device for open-pit mine mining, loading, and transportation in the embodiments of the present application includes:

[0107] The fusion module 201 is used to perform multi-source information fusion processing on the topographic and geomorphic feature data of the open-pit mining area and the real-time working condition data of the mining, loading, and transportation equipment group to obtain the collaborative operation scenario data of the mining area;

[0108] The extraction module 202 is used to perform intelligent feature extraction processing on the collaborative operation scenario data of the mining area and the energy consumption characteristic data of the mining, loading, and transportation equipment group to obtain the operation efficiency index of the equipment group;

[0109] The decoupling module 203 is used to perform hierarchical decoupling processing on the operation efficiency index of the equipment group and the mining area exploitation planning data to obtain the collaborative task sequence oriented to energy efficiency;

[0110] The matching module 204 is used to perform swarm intelligence matching processing on the collaborative task sequence oriented to energy efficiency and the spatio-temporal distribution data of the equipment group to obtain the integrated mining, loading, and transportation resource allocation plan;

[0111] The coordination module 205 is used to perform dynamic coordination processing on the integrated mining, loading, and transportation resource allocation plan and the road traffic constraint data to obtain the adaptive scheduling strategy of the equipment group;

[0112] The iteration module 206 is used to perform closed-loop iteration processing on the adaptive scheduling strategy of the equipment group and the production process feedback data to obtain the collaborative optimization instruction for mining, loading, and transportation.

[0113] Through the collaborative cooperation of the above-mentioned various components, through the multi-source information fusion processing of the topographic and geomorphic feature data of the open-pit mining area and the real-time working condition data of the mining, loading, and transportation equipment group, a comprehensive perception of the mining area's topographic features and equipment operating status is achieved, providing a reliable data basis for subsequent scheduling decisions. At the same time, intelligent feature extraction processing is carried out on the collaborative operation scenario data of the mining area and the energy consumption characteristic data of the mining, loading, and transportation equipment group, deeply excavating the energy consumption law during the equipment operation process, providing a basis for energy-saving optimization. Based on the hierarchical decoupling processing of the equipment group operation efficiency index and the mining area exploitation planning data, a reasonable decomposition and scientific organization of the mining, loading, and transportation operation tasks are realized, effectively improving the feasibility of task execution. Through the swarm intelligence matching processing of the collaborative task sequence oriented to energy efficiency and the spatio-temporal distribution data of the equipment group, an optimized allocation of equipment resources is achieved, significantly improving the equipment utilization efficiency. Combining the dynamic coordination processing of the integrated mining, loading, and transportation resource allocation scheme and the road traffic constraint data, a flexible scheduling strategy adjustment mechanism is established, effectively coping with various uncertain factors during the production process. Finally, through the closed-loop iterative processing of the equipment group adaptive scheduling strategy and the production process feedback data, a complete closed-loop control system of optimization - execution - feedback - adjustment is formed, ensuring the continuous optimization of the scheduling scheme and the stable operation of the production process. Through the organic combination of these technical features, the present invention not only improves the production efficiency and equipment utilization rate of the open-pit mining area, but also realizes the reduction of energy consumption and the saving of production costs, while enhancing the adaptability of the scheduling system to complex working conditions.

[0114] This application also provides a computer-readable storage medium, which can be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. Instructions are stored in the computer-readable storage medium. When the instructions run on a computer, the computer is made to execute the steps of the intelligent scheduling method for integrated mining, loading, and transportation in an open-pit mine.

[0115] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described system, system, and unit can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0116] When the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to enable a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of this application. The foregoing storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs.

[0117] As described above, the above embodiments are only used to illustrate the technical solutions of this application and are not intended to limit them; although this application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of various embodiments of this application.

Claims

1. An integrated intelligent dispatching method for open-pit mining, loading and transportation, characterized in that: The open-pit mine integrated intelligent scheduling method comprises: Multi-source information fusion processing is performed on the topographic and geomorphic feature data of the open-pit mine area and the real-time working condition data of the mining and loading equipment group to obtain the collaborative operation scene data of the mine area; Perform intelligent feature extraction and processing on the mining area collaborative operation scene data and the energy consumption characteristic data of the mining and loading equipment group to obtain the equipment group operation efficiency index; Performing hierarchical decoupling processing on the equipment group operation efficiency index and the mining area mining planning data to obtain a collaborative task sequence oriented to energy efficiency; Performing group intelligent matching processing on the energy efficiency-oriented collaborative task sequence and the spatiotemporal distribution data of the equipment group to obtain a resource allocation plan for integrated procurement, loading and transportation; Dynamically coordinate the integrated resource allocation plan for procurement, loading and transportation and the road traffic constraint data to obtain an adaptive scheduling strategy for the equipment group; The adaptive scheduling strategy of the equipment group and the feedback data of the production process are processed in a closed loop to obtain the coordinated optimization instructions of procurement, loading and transportation.

2. The open-pit mine mining, loading and transportation integrated intelligent scheduling method according to claim 1 is characterized in that: The multi-source information fusion processing of the topographic and geomorphic feature data of the open-pit mine area and the real-time working condition data of the mining and loading equipment group is performed to obtain the mining area collaborative operation scene data, including: Performing layered and partitioned processing on the topographic and geomorphic feature data of the open-pit mine area to obtain mining area operation level data, and performing boundary feature extraction processing on the mining area operation level data to obtain an operation area boundary point set; Performing regional connectivity analysis on the boundary point set of the operation area to obtain data on the passable area for mining and loading equipment, and performing contour extraction on the passable area data through a boundary tracking algorithm to obtain data on the mine area passable range; Performing spatiotemporal correlation processing on the location data and speed data of the collection and transportation equipment group to obtain dynamic distribution data of the equipment group, and performing density clustering processing on the dynamic distribution data of the equipment group to obtain operation cluster area data of the equipment group; Performing correlation analysis on the equipment group operation cluster area data and the equipment engine speed data to obtain equipment group working condition characteristic data, and performing energy consumption evaluation on the equipment group working condition characteristic data to obtain equipment group energy consumption status data; Performing regional division processing on the mine area traffic range data and the equipment group energy consumption status data to obtain energy consumption partition data, and performing grade division processing on the energy consumption partition data to obtain grade data of partition energy consumption; Performing frequency statistics processing on the partition energy consumption level data and historical operation records to obtain regional operation frequency data, and performing weight calculation processing on the regional operation frequency data to obtain regional operation intensity data; The regional operation intensity data and real-time equipment status data are matched and associated to obtain mining area collaborative operation scene data.

3. The open-pit mine mining, loading and transportation integrated intelligent scheduling method according to claim 1 is characterized in that: The intelligent feature extraction and processing of the mining area collaborative operation scene data and the energy consumption characteristic data of the mining and loading equipment group is performed to obtain the equipment group operation efficiency index, including: Performing regional classification processing on the mining area collaborative operation scene data to obtain scene feature type set data, and performing statistical aggregation processing on the scene feature type set data to obtain regional operation mode data; Performing spatiotemporal correlation processing on the regional operation mode data and the equipment group GPS trajectory data to obtain equipment group motion feature data, and performing frequent pattern extraction processing on the equipment group motion feature data through sequence pattern mining to obtain typical operation sequence data; Performing time series matching processing on the typical operation sequence data and the instantaneous fuel consumption data of the equipment group to obtain operation energy consumption corresponding data, and performing change rate calculation processing on the operation energy consumption corresponding data to obtain equipment group energy consumption gradient data; Perform multi-dimensional correlation processing on the energy consumption gradient data of the equipment group and the equipment load data to obtain unit load energy consumption data, and perform outlier detection processing on the unit load energy consumption data to obtain energy consumption threshold interval data; Performing response characteristic analysis on the energy consumption threshold interval data and the equipment engine speed data to obtain equipment power response data, and performing feature dimension reduction processing on the equipment power response data through principal component analysis to obtain key characteristic factor data; The key characteristic factor data and the equipment hydraulic system pressure data are combined and analyzed to obtain equipment comprehensive performance data, and the equipment comprehensive performance data is quantitatively scored to obtain equipment group operation efficiency indicators.

4. The open-pit mine mining, loading and transportation integrated intelligent scheduling method according to claim 1 is characterized in that: The hierarchical decoupling of the equipment group operation efficiency index and the mining area mining planning data is performed to obtain a collaborative task sequence oriented to energy efficiency, including: Performing grade quantification processing on the equipment group operation efficiency indicators to obtain equipment energy efficiency grading data, and performing threshold segmentation processing on the equipment energy efficiency grading data to obtain equipment operation energy consumption interval data; Performing spatial matching processing on the equipment operation energy consumption interval data and the mining working face layout data to obtain working face equipment energy consumption mapping data, and performing hierarchical clustering processing on the working face equipment energy consumption mapping data to obtain mining and loading operation energy consumption level data; Performing weighted calculation processing on the energy consumption level data of the collection and loading operation and the transportation route distance data to obtain transportation energy consumption weight data, and performing segmented accumulation processing on the transportation energy consumption weight data to obtain segmented transportation cost data; Performing task decomposition processing on the segmented transportation cost data and the monthly mining plan data of the mining area to obtain basic operation unit data, and performing energy consumption constraint processing on the basic operation unit data to obtain an energy-efficient feasible task set; Performing boundary constraint processing on the energy efficiency feasible task set and equipment operation range data to obtain task space distribution data, and performing time series sorting processing on the task space distribution data to obtain initial task time series data; The initial task timing data and the equipment energy efficiency level data are matched and optimized to obtain task equipment corresponding data, and the task equipment corresponding data are coordinated in time and space to obtain a collaborative task sequence oriented to energy efficiency.

5. The open-pit mine mining, loading and transportation integrated intelligent scheduling method according to claim 1 is characterized in that: The energy efficiency-oriented collaborative task sequence and the equipment group spatiotemporal distribution data are subjected to group intelligent matching processing to obtain a procurement, loading and transportation integrated resource allocation plan, including: Performing pre-requirement extraction processing on the energy efficiency-oriented collaborative task sequence to obtain task constraint condition data, and performing standardization processing on the task constraint condition data to obtain normalized constraint indicator data; Performing distance calculation processing on the normalized constraint index data and the real-time location data of the equipment group to obtain equipment task distance matrix data, and performing energy consumption estimation processing on the equipment task distance matrix data to obtain equipment scheduling cost data; Performing fitness calculation processing on the equipment scheduling cost data and the equipment operation capacity data to obtain equipment task matching data, and performing optimal allocation processing on the equipment task matching data through the Hungarian algorithm to obtain initial allocation plan data; Performing conflict detection processing on the initial allocation plan data and the historical operation record data to obtain task conflict point set data, and performing time window adjustment processing on the task conflict point set data to obtain feasible scheduling time series data; The feasible scheduling time series data and the energy consumption status data of the equipment group are dynamically balanced to obtain equipment load distribution data, and the equipment load distribution data is collaboratively processed on the working surface to obtain an integrated resource allocation plan for procurement, loading and transportation.

6. The open-pit mine mining, loading and transportation integrated intelligent scheduling method according to claim 1 is characterized in that: The method of dynamically coordinating the integrated resource allocation scheme for procurement, loading and transportation and the road traffic constraint data to obtain an adaptive scheduling strategy for the equipment group includes: Performing time series analysis on the integrated procurement, loading and transportation resource allocation plan to obtain equipment movement time series data, and performing cross detection on the equipment movement time series data to obtain equipment intersection prediction data; Performing safety distance calculation processing on the equipment intersection prediction data and the road bearing capacity data to obtain minimum safety distance data, and performing traffic capacity analysis processing on the minimum safety distance data and the road width data to obtain road traffic capacity data; Performing status evaluation processing on the road traffic capacity data and the real-time road condition monitoring data to obtain road traffic grade data, and performing time-division statistical processing on the road traffic grade data to obtain road congestion warning data; Performing time window adjustment processing on the road congestion warning data and the equipment group scheduling sequence data to obtain peak-shifting scheduling plan data, and performing collaborative optimization processing on the peak-shifting scheduling plan data and the equipment energy consumption status data to obtain road resource allocation data; Deviation analysis is performed on the road resource allocation data and the equipment operation trajectory data to obtain trajectory correction parameter data, and comprehensive decision processing is performed on the trajectory correction parameter data and the current operation status data to obtain an equipment group adaptive scheduling strategy.

7. The open-pit mine mining, loading and transportation integrated intelligent scheduling method according to claim 1 is characterized in that: The closed-loop iterative processing of the equipment group adaptive scheduling strategy and the production process feedback data to obtain procurement, loading and transportation collaborative optimization instructions includes: Performing timeliness analysis on the adaptive scheduling strategy of the equipment group to obtain strategy execution time limit data, and performing segmented monitoring on the strategy execution time limit data to obtain scheduling execution progress data; Performing difference comparison processing on the scheduling execution progress data and the real-time production data to obtain production deviation index data, and performing attribution analysis processing on the production deviation index data to obtain deviation cause data; Performing pattern recognition processing on the deviation cause data and the equipment operation record data to obtain typical deviation pattern data, and performing correlation analysis processing on the typical deviation pattern data and the historical disposal plan data to obtain strategy adjustment suggestion data; Performing scene adaptation processing on the strategy adjustment suggestion data and the current device status data to obtain corrected control parameter data, and performing regional collaborative processing on the corrected control parameter data to obtain device group control instruction data; Performing feasibility verification processing on the equipment group control instruction data and the operating environment constraint data to obtain instruction reliability evaluation data, and performing multi-objective trade-off processing on the instruction reliability evaluation data to obtain alternative instruction solution data; The matching degree of the alternative instruction scheme data and the production target data is calculated and processed to obtain instruction optimization result data, and the instruction optimization result data is processed for time and space consistency to obtain procurement, loading and transportation collaborative optimization instructions.

8. An open-pit mine mining and loading integrated intelligent dispatching device, used to implement the open-pit mine mining and loading integrated intelligent dispatching method as described in any one of claims 1 to 7, characterized in that: The open-pit mine mining, loading and transportation integrated intelligent dispatching device comprises: The fusion module is used to perform multi-source information fusion processing on the topographic and geomorphic feature data of the open-pit mine area and the real-time working condition data of the mining and loading equipment group to obtain the collaborative operation scene data of the mine area; An extraction module is used to perform intelligent feature extraction processing on the mining area collaborative operation scene data and the energy consumption characteristic data of the mining and loading equipment group to obtain the equipment group operation efficiency index; A decoupling module is used to perform hierarchical decoupling processing on the equipment group operation efficiency index and the mining area mining planning data to obtain a collaborative task sequence oriented to energy efficiency; A matching module, used to perform group intelligent matching processing on the energy efficiency-oriented collaborative task sequence and the spatiotemporal distribution data of the equipment group to obtain a resource allocation plan for integrated procurement, loading and transportation; A coordination module is used to dynamically coordinate the integrated resource allocation scheme for procurement, loading and transportation and the road traffic constraint data to obtain an adaptive scheduling strategy for the equipment group; The iteration module is used to perform closed-loop iterative processing on the adaptive scheduling strategy of the equipment group and the feedback data of the production process to obtain the procurement, loading and transportation collaborative optimization instructions.

9. A computer-readable storage medium having instructions stored thereon, characterized in that: When the instructions are executed by the processor, the open-pit mine mining, loading and transportation integrated intelligent scheduling method as described in any one of claims 1-7 is implemented.

Images