Surface mine unmanned mine card scheduling method and system based on multi-objective optimization

Abstract

The invention discloses a multi-objective optimization-based surface mine unmanned mine card scheduling method and system, and relates to the technical field of smart mines, and the method comprises the steps: building a road network topological graph of a loading and unloading interval of a surface mine, constructing an unmanned mine card multi-objective optimization scheduling model, and carrying out the multi-objective optimization scheduling of the unmanned mine card. And solving the unmanned mine card multi-target optimization scheduling model to obtain a loading and unloading expected traffic flow matrix under various scheduling principles, thereby performing mine card real-time scheduling. According to the method, factors such as road conditions, road traffic flow saturability and real-time performance are considered, the queuing waiting time in an operation area is shortened, the mine operation efficiency and the equipment utilization rate are remarkably improved, and economic benefits are increased.

Description

Technical Field

[0001] The present invention relates to an open-pit mine unmanned mining truck scheduling method and system based on multi-objective optimization, belonging to the technical field of smart mines. Background Art

[0002] In recent years, with the continuous development of artificial intelligence, 5G technology and autonomous driving, construction machinery has also been continuously developing towards intelligence, and the mining field has also accelerated the pace of digitalization, intelligence and automation. In open-pit mine production, transportation costs basically account for more than 50% of the total cost. The traffic planning and dispatching plan of the transport trucks directly affect the production efficiency and economic benefits of the open-pit mine.

[0003] With the development of intelligent and unmanned open-pit mines, reasonable dispatching of unmanned trucks in open-pit mines can improve system operation efficiency and reduce transportation and labor costs. Traditional traffic flow planning and dispatching models are mostly single-objective, but open-pit mine truck dispatching is a typical MOP problem (multi-objective optimization problem). Transportation costs, output, and truck utilization all affect the production costs and benefits of mines. Most of the research on open-pit mine truck dispatching at home and abroad is still single-objective and fixed trucks and routes, with less consideration of real-time performance, while there are many factors that affect mine work efficiency.

[0004] In the field of unmanned driving in open-pit mines, how to reasonably optimize the dispatching plan of unmanned mine trucks has become an urgent problem to be solved in this field. It is also an important step for open-pit mines to move towards unmanned, large-scale and refined cost accounting. It is crucial to improving the mining efficiency of open-pit mines and the economic benefits of enterprises. Summary of the invention

[0005] The purpose of the present invention is to overcome the deficiencies in the prior art and to provide an open-pit mine unmanned mining truck scheduling method and system based on multi-objective optimization, which takes into account factors such as road conditions, road traffic saturation and real-time performance, reduces the waiting time in the operating area, significantly improves the mine operation efficiency and equipment utilization, and expands economic benefits.

[0006] To achieve the above object, the present invention is implemented by adopting the following technical solutions:

[0007] On the one hand, the present invention provides an open-pit mine unmanned mining truck scheduling method based on multi-objective optimization, comprising: Obtain road network diagram and working condition data of loading and unloading areas of open-pit mines; Obtaining an optimal path between loading and unloading areas according to the loading and unloading area road network diagram; According to the optimal path and the working condition data, a multi-objective optimization scheduling model for unmanned mining trucks is constructed with the optimization objectives of minimizing the total transportation cost of mining trucks and maximizing the output of loading areas; The unmanned mining trucks are dynamically scheduled in open-pit mines according to the multi-objective optimization scheduling model for unmanned mining trucks.

[0008] Further, acquiring the optimal path between the loading and unloading areas according to the loading and unloading area road network diagram includes: Constructing a road network topology map according to the loading and unloading area road network map; The Dijkstra algorithm is used according to the road network topology diagram to solve the optimal path between the loading and unloading areas.

[0009] Furthermore, the operating condition data include the average no-load speed of the mining truck, the average heavy-load speed of the mining truck, the fuel consumption per unit distance of the mining truck in the no-load state, the fuel consumption per unit distance of the mining truck in the heavy-load state, the heavy-load capacity of the mining truck, the production requirements and maximum working capacity of the loading and unloading area, the time required for loading and unloading in the loading and unloading area, the working hours per shift, the total number of mining trucks that have completed loading and unloading, and the number of mining trucks that are loading and unloading in real time.

[0010] Furthermore, the multi-objective optimization scheduling model for unmanned mining trucks with the optimization objectives of minimizing the total transportation cost of mining trucks and maximizing the output of loading areas is constructed according to the optimal path and the working condition data, including: Construct the objective function to minimize the total transportation cost of mining trucks :

[0011] in, represents the expected traffic flow matrix, , From the loading area To unloading area The number of heavy-load transport trucks, represents the unloading expected traffic matrix, , Indicates that the unloading area To the loading area The number of empty transport mining trucks, represents an overloaded distance matrix; , Indicates loading area To unloading area The sum of the edge weights of the optimal path, represents the unloaded distance matrix, , Indicates the unloading area To loading area The sum of the edge weights of the optimal path, is the number of loading areas in the open-pit mine, The number of unloading areas for open-pit mines; Indicates the fuel consumption per unit distance of the unmanned mining truck under heavy load. Indicates the fuel consumption per unit distance when the unmanned mining truck is unloaded; Constructing the objective function to maximize the loading area production :

[0012] in, Indicates the heavy load capacity of the mining card; According to the objective function of minimizing the total transportation cost of mining trucks and the objective function of maximizing the loading area production , build a multi-objective optimization scheduling model for unmanned mining trucks : .

[0013] Furthermore, the unmanned mining truck multi-objective optimization scheduling model takes the maximum output of the loading area, the maximum working capacity of the loading area, the minimum output plan of the unloading area, the maximum working capacity of the unloading area, the continuity of the traffic flow in the loading and unloading area, and the number of mining truck transport vehicles as positive integers as constraints; The expression of the constraint condition function of the maximum output of the loading area is: ; in, Indicates loading area Production requirements within the current shift; The expression of the constraint condition function of the maximum working capacity of the loading area is: ; in, Indicates the current shift working hours. Indicates loading area The time required to complete a load; The expression of the constraint condition function of the unloading area production plan is: ; in, Indicates the unloading area Production requirements within the current shift; The expression of the constraint condition function of the maximum working capacity of the unloading area is: ; in, Indicates the unloading area Maximum work capacity during the current shift; The expression of the constraint condition function of the vehicle flow continuity in the loading and unloading area is: ; The expression of the constraint condition function of the number of mining truck transport vehicles is: ; in, Represents a positive integer.

[0014] Furthermore, the dynamic scheduling of unmanned mining trucks in open-pit mines according to the unmanned mining truck multi-objective optimization scheduling model includes: The multi-objective optimization scheduling model of unmanned mining trucks is solved to obtain the loading expected traffic matrix under various scheduling principles. , Unloading expected traffic matrix ; The maximum number of operational mining trucks from the loading area to the unloading area is calculated based on the working condition data. , the maximum number of mining trucks that can be operated from the unloading area to the loading area ; During each shift, the production completion matrix from the loading area to the unloading area is calculated based on the working condition data. , Matrix of number of running mining trucks from loading area to unloading area , production completion matrix from unloading area to loading area , Matrix of the number of running mining trucks from the unloading area to the loading area ; According to the load expectation traffic matrix , Production completion matrix from loading area to unloading area , the maximum number of mining trucks that can be operated from the loading area to the unloading area , Matrix of number of running mining trucks from loading area to unloading area Get the real-time dispatching plan of mining trucks from loading area to unloading area; According to the unloading expected traffic matrix , production completion matrix from unloading area to loading area , the maximum number of mining trucks that can be operated from the unloading area to the loading area , Matrix of the number of running mining trucks from the unloading area to the loading area Obtain the real-time dispatch plan for mining trucks from the unloading area to the loading area.

[0015] Furthermore, the multi-objective optimization scheduling model of unmanned mining trucks is solved to obtain the loading expected vehicle flow matrix under various scheduling principles. , Unloading expected traffic matrix ,include: Leveraging NSGA- The multi-objective genetic optimization algorithm is used to solve the multi-objective optimization scheduling model of unmanned mining trucks and obtain a Pareto front consisting of multiple solutions. According to different scheduling principles, multiple Pareto solutions are solved by linear weighting to obtain the expected traffic matrix. , Unloading expected traffic matrix Among them, the scheduling principles include the principle of minimum cost, the principle of maximum output and the principle of balance.

[0016] Furthermore, the maximum number of mining trucks that can be operated from the loading area to the unloading area is a matrix By Loading area to The maximum number of mining trucks on the heavy-load route of each unloading area is used as an element, and the calculation expression of the element is: ; in, The maximum number of mining trucks that can be operated from the loading area to the unloading area is represented by Line The element of the column, i.e. Loading area to Maximum number of mining trucks on the heavy-load route of each unloading area, Indicates the average reload speed of the mining truck. Indicates The time required for an unloading zone to complete one unloading operation; The maximum number of mining trucks that can be operated from the unloading area to the loading area By Unloading area to The maximum number of mining trucks on the empty route of each loading area is used as an element, and the calculation expression of the element is: ; in, The maximum number of mining trucks that can be operated from the unloading area to the loading area is represented by Line The element of the column, i.e. Unloading area to Maximum number of mining trucks on the empty route of each loading area, Indicates the average no-load speed of the mining truck. Indicates The time required for a loading area to complete a load.

[0017] Furthermore, the output from the loading area to the unloading area completes the matrix From the loading area during the current shift To unloading area The total number of completed unloading mining trucks is used as an element; The matrix of the number of mining trucks running from the loading area to the unloading area From the loading area during the current shift To unloading area The number of mining trucks running in real time in the route is used as an element; The production matrix from the unloading area to the loading area is completed During the current shift, from the unloading area To loading area The total number of loaded mining trucks completed is used as the element composition; The matrix of the number of running mining trucks from the unloading area to the loading area During the current shift, from the unloading area To loading area The number of mining trucks running in real time in the route is used as an element.

[0018] Furthermore, the expected traffic matrix according to the loading , Production completion matrix from loading area to unloading area , the maximum number of mining trucks that can be operated from the loading area to the unloading area , Matrix of number of running mining trucks from loading area to unloading area Get the real-time dispatch plan of mining trucks from the loading area to the unloading area, including: According to the load expectation traffic matrix , Production completion matrix from loading area to unloading area Calculate the matrix , the matrix Middle The unloading area corresponding to the maximum value of the row is the unloading area with the highest priority, and the mining truck is dispatched to the unloading area with the highest priority; Matrix of the maximum number of operational mining trucks from the loading area to the unloading area , Matrix of number of running mining trucks from loading area to unloading area Calculate the matrix , judgment matrix Middle Line Is the column greater than 0? If it is greater than 0, it means that the traffic flow of the route is not saturated, and the mining truck is moved from the Loading area dispatched to unloading area; According to the unloading expected traffic flow matrix , production completion matrix from unloading area to loading area , the maximum number of mining trucks that can be operated from the unloading area to the loading area , Matrix of the number of running mining trucks from the unloading area to the loading area Get the real-time dispatching plan of mining trucks from the unloading area to the loading area, including: According to the unloading expected traffic matrix , production completion matrix from unloading area to loading area Calculate the matrix , the matrix Middle The loading area corresponding to the maximum value of the row is the loading area with the highest priority, and the mining truck is dispatched to the loading area with the highest priority; According to the matrix of the maximum number of mining trucks that can be operated from the unloading area to the loading area , Matrix of the number of running mining trucks from the unloading area to the loading area Calculate the matrix , judgment matrix Middle Line Is the column greater than 0? If it is greater than 0, it means that the traffic flow of the route is not saturated, and the mining truck is moved from the The unloading area is sent to A loading area.

[0019] On the other hand, the present invention also provides an open-pit mine unmanned mining truck dispatching system based on multi-objective optimization, comprising: A data acquisition module is configured to acquire a road network map and working condition data of a loading and unloading area of ​​an open-pit mine; A navigation optimization module is configured to obtain an optimal path between loading and unloading areas according to the loading and unloading area road network diagram; A data statistical analysis module is configured to construct a multi-objective optimization scheduling model for unmanned mining trucks with the optimization objectives of minimizing the total transportation cost of mining trucks and maximizing the output of loading areas according to the optimal path and the working condition data; The vehicle flow scheduling module is configured to perform dynamic scheduling of unmanned mining trucks in open-pit mines according to the unmanned mining truck multi-objective optimization scheduling model.

[0020] Compared with the prior art, the present invention has the following beneficial effects:

[0021] The present invention constructs and solves an unmanned mine truck scheduling model based on multi-objective optimization, and the open-pit mine production is transformed from manual scheduling to intelligent scheduling. Different scheduling methods based on the lowest cost, maximum output and balance principle are designed for the open-pit mine operation and scheduling center to choose. Under the premise of ensuring the mine production requirements and principles, the mine operation cost is reduced, and the development of intelligent, digital and unmanned mine technology is promoted.

[0022] The multi-objective optimization scheduling model for unmanned mining trucks proposed in the present invention is simple and easy to solve. The real-time scheduling takes the target production completion as the goal, takes the current vehicle flow saturation into consideration, takes the expected vehicle flow planning matrix as the basis, and takes into account the influence of system random factors in the mine operation process, such as line congestion, transportation distance, and the working capacity of loading and unloading equipment. It has stronger versatility and practicality, more reasonable vehicle dispatching results, better optimization effect, and can improve mine production efficiency.

[0023] The present invention proposes a real-time scheduling method with production completion as the goal and taking into account the current vehicle flow saturation. It is based on the expected vehicle flow planning matrix and takes into account the system random factors, line congestion, transportation distance, and the working capacity and idleness of loading and unloading equipment during mine operation. The vehicle dispatching and scheduling method is more universal and practical, and the vehicle dispatching and scheduling results are more in line with the mine production environment, which can effectively improve the utilization rate of mining trucks, loading and unloading equipment and the overall work efficiency of mines. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 It is a flow chart of an open-pit mine unmanned mining truck scheduling method based on multi-objective optimization in an embodiment of the present invention;

[0025] Figure 2 It is a schematic structural diagram of a road network topology diagram of an open-pit mine loading and unloading area of ​​an open-pit mine unmanned mining truck scheduling method based on multi-objective optimization in an embodiment of the present invention;

[0026] Figure 3 The present invention is a schematic diagram of the traffic scheduling process from the loading area to the unloading area of ​​an open-pit mine unmanned mining truck scheduling method based on multi-objective optimization in an embodiment of the present invention. DETAILED DESCRIPTION

[0027] The present invention will be further described below in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present invention, and cannot be used to limit the protection scope of the present invention. Example 1

[0028] like Figure 1 As shown, an embodiment of the present invention provides a method for dispatching open-pit unmanned mine trucks based on multi-objective optimization, comprising the following steps:

[0029] First, the road network map and working condition data of the open-pit mine loading and unloading area are obtained. The road network map contains accessible paths and accessible path information. The accessible path information includes the road status of each section, such as path length, slope, and road surface conditions.

[0030] The road network topology is established with the path nodes as vertices, such as Figure 2 As shown in Figure 1, the road network topology graph includes information such as the weight of the topological edge and the location of the loading and unloading area. The calculation expression of the weight of the topological edge is: ; in, represents the topological edge weight, represents the path length of the road segment. Indicates the road condition influencing factor of the road section, generally taken as The worse the road condition or the greater the slope, the greater the value of the influencing factor.

[0031] The road network topology is used as input, and the optimal path between loading and unloading areas is obtained after being processed by the Dijkstra algorithm. The Dijkstra algorithm is the most typical graph theory algorithm used to solve the problem of finding the shortest path.

[0032] Next, a multi-objective optimization scheduling model for unmanned mining trucks was constructed based on the working condition data. The working condition data included the average empty speed of mining trucks, the average heavy-load speed of mining trucks, the unit distance fuel consumption of mining trucks in empty state, the unit distance fuel consumption of mining trucks in heavy-load state, the heavy-load capacity of mining trucks, the production requirements and maximum working capacity of the loading and unloading area, the time required for loading and unloading in the loading and unloading area, the working time of each shift, the total number of mining trucks loaded and unloaded, and the number of mining trucks loaded and unloaded in real time.

[0033] When the number of mining trucks is fixed, the open-pit mine mainly considers cost and output when planning traffic flow, that is, spending the least cost in the hope of obtaining the greatest benefit. However, these two optimization goals are conflicting. Therefore, the unmanned mining truck multi-objective optimization scheduling model in this embodiment takes the maximum output of the loading area, the maximum working capacity of the loading area, the minimum output plan of the unloading area, the maximum working capacity of the unloading area, the traffic continuity of the loading and unloading area, and the number of mining truck transport vehicles as positive integers as constraints. Specifically:

[0034] Assume that the open-pit mine has loading area, The objective function expression for minimizing the total transportation cost of mining trucks is: ; in, represents the objective function of minimizing the total transportation cost of mining trucks, represents the expected traffic flow matrix, , From the loading area To unloading area The number of heavy-load transport trucks, represents the unloading expected traffic matrix, , Indicates that the unloading area To the loading area The number of empty transport mining trucks, represents an overloaded distance matrix; , Indicates loading area To unloading area The sum of the edge weights of the optimal path, represents the unloaded distance matrix, , Indicates the unloading area To loading area The sum of the edge weights of the optimal path of the loading and unloading area can be known from the road network topology diagram.

[0035] Indicates the fuel consumption per unit distance of the unmanned mining truck under heavy load. Indicates the fuel consumption per unit distance when the unmanned mining truck is unloaded. It means to sum all elements of the matrix. Represents the multiplication of corresponding elements of matrices.

[0036] The objective function expression for maximizing the loading area output is: ; in, represents the objective function of maximizing the loading area production, Indicates the heavy load capacity of the mining card.

[0037] According to the objective function of minimizing the total transportation cost of mining trucks and the objective function of maximizing the loading area production , build a multi-objective optimization scheduling model for unmanned mining trucks : .

[0038] The loading area needs to have a maximum production constraint, that is, the total loading volume of the loading area per shift has a certain production requirement, so the expression of the constraint function of the maximum production of the loading area is: ; in, Indicates loading area Production requirements within the current shift.

[0039] The loading area needs to have a maximum working capacity constraint, that is, within a shift, due to the working capacity limitations of equipment such as excavators or electric shovels, the maximum number of vehicles loaded in each loading area is limited within a shift. The expression of the constraint condition function of the maximum working capacity of the loading area is: ; in, Indicates the current shift time. Indicates loading area The time required to complete a load;

[0040] In scenarios such as unloading areas such as crushing stations, production plan constraints are required, that is, each unloading area must complete a certain unloading volume requirement within each shift. The expression of the constraint condition function of the unloading area production plan is: ; in, Indicates the unloading area Production requirements within the current shift;

[0041] The unloading area needs to have a maximum working capacity constraint, that is, within a shift, since the unloading equipment such as the crushing station has a working capacity limit, each unloading area has a maximum working capacity limit within a shift. The expression of the constraint condition function of the maximum working capacity of the unloading area is: ; in, Indicates the unloading area Maximum work capacity during the current shift;

[0042] The vehicle flow continuity constraint of the loading and unloading area, that is, the number of vehicles loaded from the loading area to a certain unloading area should be equal to the number of vehicles loaded from the unloading area to the loading area. The expression of the vehicle flow continuity constraint function of the loading and unloading area is: .

[0043] The number of mining trucks transported should be a positive integer, that is, the matrix , All elements in are positive integers, and the constraint function expression of the number of mining truck transport vehicles is: ; in, Represents a positive integer.

[0044] Leveraging NSGA- The multi-objective genetic optimization algorithm solves the constructed multi-objective optimization scheduling model for unmanned mining trucks and obtains a Pareto frontier consisting of multiple solutions. There are three scheduling principles to choose from in the system front-end interface: the principle of minimum cost, the principle of maximum output, and the principle of equilibrium. Different scheduling principles are solved by multiple Pareto solutions through linear weighting. Each shift can select the appropriate scheduling principle according to the production requirements of the mine, and finally obtain the loading expected vehicle flow matrix. , Unloading expected traffic matrix , used for real-time scheduling.

[0045] In the actual production process of the mine, it is necessary to consider the production completion, road congestion and fault conditions, the working capacity and idle status of the electric shovel and excavator in the loading area, and to achieve the expected traffic flow planning results as much as possible. Real-time dispatch of open-pit mine trucks means sending vehicles to a specific loading area or unloading area.

[0046] According to the open-pit mine working data, the maximum number of operational mining trucks from the loading area to the unloading area is calculated. , the maximum number of mining trucks that can be operated from the unloading area to the loading area .

[0047] Matrix of the maximum number of mining trucks that can be operated from the loading area to the unloading area By Loading area to The maximum number of mining trucks on the heavy-load route of each unloading area is used as an element, and the calculation expression of the element is:

[0048] in, The maximum number of mining trucks that can be operated from the loading area to the unloading area is represented by Line The element of the column, i.e. Loading area to Maximum number of mining trucks on the heavy-load route of each unloading area, Indicates the average reload speed of the mining truck. Indicates The time required for an unloading zone to complete an unloading operation.

[0049] Matrix of the maximum number of mining trucks that can be operated from the unloading area to the loading area By Unloading area to The maximum number of mining trucks on the empty route of each loading area is used as an element, and the calculation expression of the element is:

[0050] in, The maximum number of mining trucks that can be operated from the unloading area to the loading area is represented by Line The element of the column, i.e. Unloading area to Maximum number of mining trucks on the empty route of each loading area, Indicates the average no-load speed of the mining truck. Indicates The time required for a loading area to complete a load.

[0051] During each shift, the production completion matrix from the loading area to the unloading area is calculated based on the open-pit mine work data. , Matrix of number of running mining trucks from loading area to unloading area , production completion matrix from unloading area to loading area , Matrix of the number of running mining trucks from the unloading area to the loading area .

[0052] Production completion matrix from loading area to unloading area From the loading area during the current shift To unloading area The total number of completed unloaded mining trucks is used as an element.

[0053] Matrix of number of running mining trucks from loading area to unloading area From the loading area during the current shift To unloading area The number of mining trucks running in real time in the route is used as an element.

[0054] Production completion matrix from unloading area to loading area During the current shift, from the unloading area To loading area The total number of loaded mining trucks completed is used as an element.

[0055] Matrix of the number of running mining trucks from the unloading area to the loading area During the current shift, from the unloading area To loading area The number of mining trucks running in real time in the route is used as an element.

[0056] Finally, in real-time scheduling, unmanned mining truck scheduling can be completed based on production completion and vehicle flow, combined with Figure 3 , when the mine is stuck in the loading area When the expected traffic flow matrix is ​​loaded , Production completion matrix from loading area to unloading area Calculate the matrix ,matrix Middle The unloading area corresponding to the maximum value of the row is the unloading area with the highest priority, and the mining truck is dispatched to the unloading area with the highest priority.

[0057] Matrix of the maximum number of operational mining trucks from the loading area to the unloading area , Matrix of number of running mining trucks from loading area to unloading area Calculate the matrix , judgment matrix Middle Line Is the column greater than 0? If it is greater than 0, it means that the traffic flow of the route is not saturated, and the mining truck is moved from the Loading area dispatched to Unloading area.

[0058] Similarly, when the mine is stuck in the unloading area When, according to the unloading expected traffic matrix , production completion matrix from unloading area to loading area Calculate the matrix ,matrix Middle The loading area corresponding to the maximum value of the row is the loading area with the highest priority, and the mining truck is dispatched to the loading area with the highest priority.

[0059] According to the matrix of the maximum number of mining trucks that can be operated from the unloading area to the loading area , Matrix of the number of running mining trucks from the unloading area to the loading area Calculate the matrix , judgment matrix Middle Line Is the column greater than 0? If it is greater than 0, it means that the traffic flow of the route is not saturated, and the mining truck is moved from the The unloading area is sent to A loading area. Example 2

[0060] Based on Example 1, this embodiment provides an open-pit mine unmanned mining truck scheduling system based on multi-objective optimization, including: A data acquisition module is configured to acquire a road network map and working condition data of a loading and unloading area of ​​an open-pit mine; A navigation optimization module is configured to obtain an optimal path between loading and unloading areas according to the loading and unloading area road network diagram; A data statistical analysis module is configured to construct a multi-objective optimization scheduling model for unmanned mining trucks with the optimization objectives of minimizing the total transportation cost of mining trucks and maximizing the output of loading areas according to the optimal path and the working condition data; The vehicle flow scheduling module is configured to perform dynamic scheduling of unmanned mining trucks in open-pit mines according to the unmanned mining truck multi-objective optimization scheduling model.

[0061] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for dispatching unmanned mining trucks in open-pit mines based on multi-objective optimization, characterized in that: include: Obtain road network diagram and working condition data of loading and unloading areas of open-pit mines; Obtaining an optimal path between loading and unloading areas according to the loading and unloading area road network diagram; According to the optimal path and the working condition data, a multi-objective optimization scheduling model for unmanned mining trucks is constructed with the optimization objectives of minimizing the total transportation cost of mining trucks and maximizing the output of loading areas; The unmanned mining trucks are dynamically scheduled in open-pit mines according to the multi-objective optimization scheduling model for unmanned mining trucks.

2. The method for dispatching unmanned mining trucks in open-pit mines based on multi-objective optimization according to claim 1 is characterized in that: The acquiring of the optimal path between the loading and unloading areas according to the loading and unloading area road network diagram comprises: Constructing a road network topology map according to the loading and unloading area road network map; The Dijkstra algorithm is used according to the road network topology diagram to solve the optimal path between the loading and unloading areas.

3. The method for dispatching unmanned mining trucks in open-pit mines based on multi-objective optimization according to claim 1 is characterized in that: The operating condition data include the average no-load speed of the mining truck, the average heavy-load speed of the mining truck, the fuel consumption per unit distance of the mining truck in the no-load state, the fuel consumption per unit distance of the mining truck in the heavy-load state, the heavy-load capacity of the mining truck, the production requirements and maximum working capacity of the loading and unloading area, the time required for loading and unloading in the loading and unloading area, the working hours per shift, the total number of mining trucks that have completed loading and unloading, and the number of mining trucks that are loading and unloading in real time.

4. The method for dispatching unmanned mining trucks in open-pit mines based on multi-objective optimization according to claim 1 is characterized in that: The multi-objective optimization scheduling model for unmanned mining trucks is constructed based on the optimal path and the working condition data with the optimization objectives of minimizing the total transportation cost of mining trucks and maximizing the output of loading areas, including: Construct the objective function to minimize the total transportation cost of mining trucks : ； in, represents the loading expected traffic flow matrix, , From the loading area To the unloading area The number of heavy-load transport mining trucks, represents the unloading expected traffic matrix, , Indicates that the unloading area To the loading area The number of empty transport mining trucks, represents an overloaded distance matrix; , Indicates loading area To unloading area The sum of the edge weights of the optimal path, represents the unloaded distance matrix, , Indicates the unloading area To loading area The sum of the edge weights of the optimal path, is the number of loading areas in the open-pit mine, The number of unloading areas for open-pit mines; Indicates the fuel consumption per unit distance of the unmanned mining truck under heavy load. Indicates the fuel consumption per unit distance when the unmanned mining truck is unloaded; Constructing the objective function to maximize the loading area production : ； in, Indicates the heavy load capacity of the mining card; According to the objective function of minimizing the total transportation cost of mining trucks and the objective function of maximizing the loading area production , build a multi-objective optimization scheduling model for unmanned mining trucks : 。 5. The method for dispatching unmanned mining trucks in open-pit mines based on multi-objective optimization according to claim 4 is characterized in that: The unmanned mining truck multi-objective optimization scheduling model takes the maximum output of the loading area, the maximum working capacity of the loading area, the minimum output plan of the unloading area, the maximum working capacity of the unloading area, the continuity of the traffic flow in the loading and unloading area, and the number of mining truck transport vehicles as positive integers as constraints; The expression of the constraint condition function of the maximum output of the loading area is: ； in, Indicates loading area Production requirements within the current shift; The expression of the constraint condition function of the maximum working capacity of the loading area is: ； in, Indicates the current shift working hours. Indicates loading area The time required to complete a load; The expression of the constraint condition function of the unloading area production plan is: ； in, Indicates the unloading area Production requirements within the current shift; The expression of the constraint condition function of the maximum working capacity of the unloading area is: ； in, Indicates the unloading area Maximum work capacity during the current shift; The expression of the constraint condition function of the vehicle flow continuity in the loading and unloading area is: ； The expression of the constraint condition function of the number of mining truck transport vehicles is: ； in, Represents a positive integer.

6. The method for dispatching unmanned mining trucks in open-pit mines based on multi-objective optimization according to claim 1 is characterized in that: The method of dynamically scheduling unmanned mining trucks in open-pit mines according to the unmanned mining truck multi-objective optimization scheduling model includes: The multi-objective optimization scheduling model of unmanned mining trucks is solved to obtain the loading expected traffic matrix under various scheduling principles. , Unloading expected traffic matrix ; The maximum number of operational mining trucks from the loading area to the unloading area is calculated based on the working condition data. , the maximum number of mining trucks that can be operated from the unloading area to the loading area ; During each shift, the production completion matrix from the loading area to the unloading area is calculated based on the working condition data. , Matrix of number of running mining trucks from loading area to unloading area , production completion matrix from unloading area to loading area , Matrix of the number of running mining trucks from the unloading area to the loading area ; According to the load expectation traffic matrix , Production completion matrix from loading area to unloading area , the maximum number of mining trucks that can be operated from the loading area to the unloading area , Matrix of number of running mining trucks from loading area to unloading area Get the real-time dispatching plan of mining trucks from loading area to unloading area; According to the unloading expected traffic matrix , production completion matrix from unloading area to loading area , the maximum number of mining trucks that can be operated from the unloading area to the loading area , Matrix of the number of running mining trucks from the unloading area to the loading area Obtain the real-time dispatch plan for mining trucks from the unloading area to the loading area.

7. The method for dispatching unmanned mining trucks in open-pit mines based on multi-objective optimization according to claim 6 is characterized in that: The multi-objective optimization scheduling model of unmanned mining trucks is solved to obtain the loading expected vehicle flow matrix under various scheduling principles. , Unloading expected traffic matrix ,include: Leveraging NSGA- The multi-objective genetic optimization algorithm is used to solve the multi-objective optimization scheduling model of unmanned mining trucks and obtain a Pareto front consisting of multiple solutions. According to different scheduling principles, multiple Pareto solutions are solved by linear weighting to obtain the expected traffic matrix. , Unloading expected traffic matrix Among them, the scheduling principles include the principle of minimum cost, the principle of maximum output and the principle of balance.

8. The method for dispatching unmanned mining trucks in open-pit mines based on multi-objective optimization according to claim 6 is characterized in that: The maximum number of mining trucks that can be operated from the loading area to the unloading area By Loading area to The maximum number of mining trucks on the heavy-load route of each unloading area is used as an element, and the calculation expression of the element is: ； in, The maximum number of mining trucks that can be operated from the loading area to the unloading area is represented by Line The element of the column, Loading area to Maximum number of mining trucks on the heavy-load route of each unloading area, Indicates the average reload speed of the mining truck. Indicates The time required for an unloading zone to complete one unloading operation; The maximum number of mining trucks that can be operated from the unloading area to the loading area By Unloading area to The maximum number of mining trucks on the empty route of each loading area is used as an element, and the calculation expression of the element is: ； in, The maximum number of mining trucks that can be operated from the unloading area to the loading area is represented by Line The element of the column, i.e. Unloading area to Maximum number of mining trucks on the empty route of each loading area, Indicates the average no-load speed of the mining truck. Indicates The time required for a loading area to complete a load.

9. The method for dispatching unmanned mining trucks in open-pit mines based on multi-objective optimization according to claim 6 is characterized in that: The production matrix from the loading area to the unloading area is completed From the loading area during the current shift To the unloading area The total number of completed unloading mining trucks is used as an element; The matrix of the number of mining trucks running from the loading area to the unloading area From the loading area during the current shift To the unloading area The number of mining trucks running in real time in the route is used as an element; The production matrix from the unloading area to the loading area is completed During the current shift, from the unloading area To loading area The total number of loaded mining trucks completed is used as the element composition; The matrix of the number of running mining trucks from the unloading area to the loading area During the current shift, from the unloading area To loading area The number of mining trucks running in real time in the route is used as an element.

10. The method for dispatching unmanned mining trucks in open-pit mines based on multi-objective optimization according to claim 6, characterized in that: According to the loading expected traffic flow matrix , Production completion matrix from loading area to unloading area , the maximum number of mining trucks that can be operated from the loading area to the unloading area , Matrix of number of running mining trucks from loading area to unloading area Get the real-time dispatch plan of mining trucks from the loading area to the unloading area, including: According to the load expectation traffic matrix , Production completion matrix from loading area to unloading area Calculate the matrix , the matrix Middle The unloading area corresponding to the maximum value of the row is the unloading area with the highest priority, and the mining truck is dispatched to the unloading area with the highest priority; Matrix of the maximum number of operational mining trucks from the loading area to the unloading area , Matrix of number of running mining trucks from loading area to unloading area Calculate the matrix , judgment matrix Middle Line Is the column greater than 0? If it is greater than 0, it means that the traffic flow of the route is not saturated, and the mining truck is moved from the Loading area dispatched to unloading area; According to the unloading expected traffic flow matrix , production completion matrix from unloading area to loading area , the maximum number of mining trucks that can be operated from the unloading area to the loading area , Matrix of the number of running mining trucks from the unloading area to the loading area Get the real-time dispatching plan of mining trucks from the unloading area to the loading area, including: According to the unloading expected traffic matrix , production completion matrix from unloading area to loading area Calculate the matrix , the matrix Middle The loading area corresponding to the maximum value of the row is the loading area with the highest priority, and the mining truck is dispatched to the loading area with the highest priority; According to the matrix of the maximum number of mining trucks that can be operated from the unloading area to the loading area , Matrix of the number of running mining trucks from the unloading area to the loading area Calculate the matrix , judgment matrix Middle Line Is the column greater than 0? If it is greater than 0, it means that the traffic flow of the route is not saturated, and the mining truck is moved from the The unloading area is sent to A loading area.

11. An open-pit mine unmanned truck dispatching system based on multi-objective optimization, characterized in that: include: A data acquisition module is configured to acquire a road network map and working condition data of a loading and unloading area of ​​an open-pit mine; A navigation optimization module is configured to obtain an optimal path between loading and unloading areas according to the loading and unloading area road network diagram; A data statistical analysis module is configured to construct a multi-objective optimization scheduling model for unmanned mining trucks with the optimization objectives of minimizing the total transportation cost of mining trucks and maximizing the output of loading areas according to the optimal path and the working condition data; The vehicle flow scheduling module is configured to perform dynamic scheduling of unmanned mining trucks in open-pit mines according to the unmanned mining truck multi-objective optimization scheduling model.

Images