Decision optimization method for accurate coal bunker feeding

Abstract

The invention discloses a decision optimization method for accurate bunker feeding of a coal bunker. The method comprises the following steps: optimizing bunker feeding of a raw coal bunker according to an accurate bunker feeding strategy of the raw coal bunker; and optimizing the distribution of the commercial coal bunker according to the accurate distribution strategy of the commercial coal bunker. According to the decision-making optimization method for accurate bunker allocation of the coal bunker, different bunker allocation strategies are made for different coal bunker types, multi-factor and multi-aspect consideration is combined, automatic, intelligent and accurate bunker allocation of different coal bunkers is achieved, dynamic adjustment of coal bunker management can be achieved, bunker allocation efficiency and production benefits are improved, and the method is suitable for popularization and application. And the labor intensity of workers is reduced. Through accurate bunker distribution, coal waste caused by coal distribution errors and economic losses caused by quality fluctuation can be reduced, stable operation of a coal flow production line is guaranteed, the downstream loading and transporting requirements of the coal bunker are met, and economic benefits are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of mine production, and in particular to a decision-making optimization method for accurate allocation of coal bunkers. Background Art

[0002] Coal bunker refers to a place for temporary storage of coal at the bottom of a coal mine. In the process of coal mining, the safety management of coal bunkers has always been a matter of great concern. In recent years, with the continuous development of underground mechanization and intelligent construction, the production capacity of many coal mining areas has been greatly improved. Some coal mine underground transportation systems and equipment operation links cannot be coordinated, especially the management is not in place, which is prone to problems such as coal bunker blockage and bunker collapse. For example, the collapse of coal bunkers is mainly due to the backlog of a large amount of water-containing coal in the coal bunker. It is difficult for the coal feeder to control the coal release speed and amount when releasing coal, resulting in a large amount of coal and accumulated water in the coal bunker gushing out instantly. One of the main reasons for the collapse of coal bunkers is that the coal feeder cannot effectively control the amount of coal during the coal release process. In addition, in the production process of coal mines, coal bunkers are an important buffer link in coal flow production, and their management efficiency directly affects the production efficiency and transportation capacity of coal mines. Existing coal bunker management methods mostly rely on manual experience and static plans, and cannot achieve dynamic adjustment and optimization of bunker allocation, resulting in low loading efficiency and increased coal bunker management costs. Summary of the invention

[0003] In order to solve the technical problems existing in the prior art, the present invention provides a decision optimization method for accurate coal allocation in coal bunkers, which can realize efficient and accurate coal allocation management for raw coal bunkers and commercial coal bunkers.

[0004] The technical solution adopted by the present invention to solve its technical problem is: a decision optimization method for accurate allocation of coal bunkers, including: optimizing the allocation of raw coal bunkers according to the accurate allocation strategy of raw coal bunkers; optimizing the allocation of commercial coal bunkers according to the accurate allocation strategy of commercial coal bunkers.

[0005] Furthermore, the raw coal bunker precise allocation strategy includes:

[0006] Construct the objective function E;

[0007] Constructing constraints on the objective function E;

[0008] The objective function E is solved using a nonlinear programming model.

[0009] Furthermore, the constraints include: inventory safety constraints, non-negative constraints and upper warehouse belt conveyor capacity constraints.

[0010] Furthermore, the solution process of the nonlinear programming model includes:

[0011] Initialize parameter sets and decision variables;

[0012] Discretize the feasible domain;

[0013] Build decision-making models;

[0014] Deep search finds the optimal solution of the objective function E.

[0015] Furthermore, the objective function E represents the equilibrium index, C i represents the current amount of coal in the i-th raw coal bunker, i=1, 2, ..., N; Represents the average coal quantity of N raw coal bins; the optimization goal is to minimize the equilibrium index E.

[0016] Furthermore, the inventory safety constraint is expressed as: L i Indicates the lower limit of the safety stock of raw coal bunker, U i Represents the upper limit of the safety stock of the raw coal bunker, where: M represents the number of upper warehouse conveyor belts, j = 1, 2, ..., M; S i represents the initial coal quantity of the i-th raw coal bunker; x ji It represents the amount of coal distributed from the j-th upper bunker belt to the i-th raw coal bunker;

[0017] The non-negative constraint is expressed as:

[0018] The upper warehouse belt conveying capacity constraint is expressed as: P j Indicates the maximum coal transport capacity of the jth upper storage belt.

[0019] Furthermore, the parameter set includes: the number of raw coal bins N, the number of upper bin belts M, the initial coal quantity S of each raw coal bin i , the upper limit of safety stock constraint U i and the lower limit L i , the maximum coal conveying capacity P of each upper storage belt j ;

[0020] The decision variable is x ji .

[0021] Furthermore, the feasible domain is discretized, including:

[0022] Determine the decision variable x based on the inventory safety constraint and the upper warehouse belt conveyor capacity constraint ji The search scope is:

[0023]

[0024] Set the search step size to d ji, then the decision variable point in the feasible region can be expressed as:

[0025] n ji represents the decision variable x ji The number of discrete points in the feasible region;

[0026] For each decision variable x ji The search range is discretized into several points.

[0027] Further, a decision model is constructed according to a number of points obtained by the discretization process, wherein the decision model includes: an initial node, a number of layers, a branch node, and a terminal node;

[0028] The deep search process includes: initializing the search state, traversing layer by layer starting from the initial node; traversing the current layer, if the current layer is not the last layer, entering the next layer traversal, and the current node is used as the parent node of the next layer; if the current layer is the last layer, calculating the objective function E corresponding to the current terminal node; if the current objective function value is less than the known optimal solution, updating the optimal solution and the corresponding decision variable value combination; if all nodes of the current layer have been traversed and have not reached the initial node, backtracking to the previous layer, and continuing to traverse the untraversed nodes of the previous layer until the entire decision model is traversed or the convergence condition is reached.

[0029] Furthermore, the precise allocation strategy for commodity coal bunkers includes:

[0030] Real-time monitoring of the coal inventory Q of m commercial coal bunkers r , Coal inflow velocity V r_in and outflow velocity V r_out , r = 1, 2, ..., m; where Q r =H r ×A r ×ρ,H r represents the real-time coal position of the rth commercial coal bunker, A r represents the bottom area of ​​the rth commercial coal bunker, and ρ represents the density of the coal type;

[0031] According to the coal inventory Q r , Coal inflow velocity V r_in and outflow velocity V r_out Calculate the time T required to fill the commercial coal bunker full_r and the time required for emptying T empty_r ;

[0032] The commercial coal bunkers are allocated in order according to their weight priority.

[0033] Furthermore, the coal bunkers are allocated in order according to their weight priorities, including:

[0034] Determine the weight priority Y of the commercial coal bunker r =α×D r +β×I r +γ×W r , where Y r represents the weight priority of the rth commercial coal bunker, D r represents the inventory status of the rth commodity coal bunker, I r represents the waiting time of the loading vehicle in the loading channel where the rth commercial coal bunker is located, W r represents the number of shipping vehicles, α, β, γ represent weight coefficients;

[0035] Establish a warehouse allocation model based on the weight priority:

[0036] Sort the m commercial coal bunkers according to their weight priority from high to low to form a coal bunker list;

[0037] Traverse the coal bunker list one by one and perform the following steps for each commodity coal bunker:

[0038] Step a: Check the current coal quantity Q in the commercial coal bunker r (t) Whether the shipping demand Q is met order,r If the conditions are met, shipment will be carried out; if not, the next step will be executed;

[0039] Step b: Calculate the amount of coal required to be replenished ΔQ r =Q order,r -Q r (t);

[0040] Step c: Determine the amount of coal Q that can be allocated to the rth commercial coal bunker based on the conveying capacity of the belt conveyor and the needs of other commercial coal bunkers. alloc,r ;

[0041] Step d: By controlling the timing of the coal feeder under the bunker, the amount of coal Q allocated to the rth commercial coal bunker is alloc,r Load into the commodity coal bunker;

[0042] Step e: Update the coal quantity Q of the rth commercial coal bunker r (t+1)=Q r (t)+Q alloc,r ;

[0043] Step f: If there are any remaining shipping demands that have not been met, repeat steps ce until all shipping demands are met or the belt conveyor reaches its maximum conveying capacity.

[0044] The beneficial effect of the present invention is that the decision-making optimization method for accurate coal bunker allocation of the present invention formulates different allocation strategies for different coal bunker types, combines multiple factors and multiple aspects of consideration, realizes the automation, intelligence and precision of different coal bunker allocation, can realize the dynamic adjustment of coal bunker management, improves allocation efficiency and production benefits, and reduces the labor intensity of manual labor. Through accurate allocation, it is possible to reduce the economic losses caused by coal waste and quality fluctuations due to coal allocation errors, ensure the stable operation of the coal flow production line, meet the downstream shipping needs of the coal bunker, and improve economic benefits. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The present invention is further described below in conjunction with the accompanying drawings and embodiments.

[0046] Figure 1 It is a flow chart of the decision-making optimization method for accurate coal bunker allocation of the present invention.

[0047] Figure 2 It is a flow chart of the raw coal bunker precise allocation strategy of the present invention.

[0048] Figure 3 It is a flow chart of the accurate bunker allocation strategy for commercial coal bunkers of the present invention. DETAILED DESCRIPTION

[0049] The present invention will now be described in further detail with reference to the accompanying drawings. These drawings are simplified schematic diagrams, which only illustrate the basic structure of the present invention in a schematic manner, and therefore only show the components related to the present invention.

[0050] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. In addition, features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, unless otherwise specified, "multiple" means two or more.

[0051] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0052] like Figures 1 to 3 As shown, the decision-making optimization method for accurate coal bunker allocation of the present invention includes: optimizing the allocation of raw coal bunker according to the accurate allocation strategy of raw coal bunker; optimizing the allocation of commercial coal bunker according to the accurate allocation strategy of commercial coal bunker. Raw coal bunker refers to a storage bin for granular materials such as raw coal and coal slime. Raw coal refers to coal that is mined from underground and only visible gangue is selected without any processing. Commercial coal bunker refers to a storage bin for storing coal sold as a commodity. Therefore, different allocation strategies should be adopted for the allocation of raw coal bunker and commercial coal bunker.

[0053] The characteristics of raw coal bunkers are that they are large in size, store a large amount of coal, and store the same type of coal in each raw coal bunker. Therefore, the balance between the raw coal bunkers needs to be considered when allocating the bunkers. Specifically, the precise allocation strategy for raw coal bunkers includes: constructing the objective function E; constructing constraints on the objective function E; and solving the objective function E using a nonlinear programming model. Constraints include: inventory safety constraints, non-negative constraints, and upper warehouse belt conveyor capacity constraints. The solution process of the nonlinear programming model includes: initializing parameter sets and decision variables; discretizing the feasible domain; constructing a decision model; and deep search to find the optimal solution to the objective function E.

[0054] Objective Function E represents the equilibrium index, C i represents the current amount of coal in the i-th raw coal bunker, i=1, 2, ..., N; Represents the average coal quantity of N raw coal bins; the optimization goal is to minimize the equilibrium index E.

[0055] The inventory safety constraint is expressed as: L i Indicates the lower limit of the safety stock of raw coal bunker, U i Represents the upper limit of the safety stock of the raw coal bunker, where: M represents the number of upper warehouse conveyor belts, j = 1, 2, ..., M; S i represents the initial coal quantity of the i-th raw coal bunker; x ji represents the amount of coal distributed from the j-th upper storage belt to the i-th raw coal bunker. The non-negative constraint is expressed as: That is, the amount of coal x distributed from the upper bunker belt to each raw coal bunkerji Must be non-negative. The upper warehouse belt conveyor capacity constraint is expressed as: P j It represents the maximum coal transport capacity of the j-th upper storage belt. Each upper storage belt has a maximum coal transport capacity. Therefore, the sum of the coal quantities allocated to each raw coal bunker cannot exceed the maximum coal transport capacity of the upper storage belt, otherwise a safety accident may occur. By setting constraints, the safety of bunker distribution control can be improved.

[0056] The solution process of the nonlinear programming model is as follows:

[0057] (1) Initialize parameter set and decision variables

[0058] The parameter set includes: the number of raw coal bins N, the number of upper bin belts M, the initial coal quantity S of each raw coal bin i , the upper limit of the safety stock constraint U i and the lower limit L i , the maximum coal conveying capacity P of each upper storage belt j The decision variable is x ji .

[0059] (2) Discretization of the feasible domain

[0060] First, the decision variable x is determined according to the inventory safety constraint and the upper warehouse belt conveyor capacity constraint. ji For the inventory safety constraint, the current coal quantity C of the i-th raw coal bin i Should be between the upper limit U i and the lower limit L i The current coal quantity C i The initial coal quantity S i and the amount of coal distributed from the upper storage belt, so the decision variable x ji The lower limit is Upper limit is It should be noted that due to the distribution amount x of other upper storage belts k to the i-th raw coal bin ki may not yet be determined, so the decision variable x ji The upper and lower limits of may be dynamically changing. However, when discretizing, we can temporarily assume that the distribution amount x of other upper storage belts to the i-th raw coal bin is ki is known or set to a fixed value (e.g. 0) to ensure that the discretization process can proceed. For the upper warehouse belt conveying capacity constraint, for the jth upper warehouse belt, the sum of the coal volume allocated to each raw coal bin cannot exceed its own maximum conveying coal volume P j , this Yushu condition directly restricts the decision variable x ji The upper limit is Similarly, due to the allocation of x to other raw coal bin g jgIt may not be determined yet, and this upper limit may also change dynamically. When discretizing, it is temporarily assumed that the allocation of other raw coal bins is known or takes a fixed value (for example, 0). Therefore, the decision variable x ji The search scope is set to:

[0061]

[0062] Secondly, set the search step size to d ji , then the decision variable point in the feasible region can be expressed as:

[0063] n ji represents the decision variable x ji The number of discrete points in the feasible region. The search step size d ji The size of directly affects the accuracy and amount of calculation of subsequent search results. If the search step is too small, the calculation accuracy will be improved but the amount of calculation will increase; if the search step is too large, the calculation accuracy will be reduced but the amount of calculation will be reduced. Therefore, the size of the search step can be set appropriately according to the characteristics of the actual processing situation. Decision variable x ji The number of discrete points n in the feasible region ji It can be calculated based on the search range and the search step size. The starting value can be the lower limit of the search range or a value close to the lower limit to ensure that no point in the feasible region is missed.

[0064] Third, after determining the search range and search step, the range of each decision variable can be discretized into several points. These points are used to build the decision model and are traversed during the depth search.

[0065] Let's take a simple example to illustrate the discretization process. Assuming the search range of the decision variable is 0 to 1, the search step is 0.1, and the starting value is 0, then the discretization points are 0, 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1. The purpose of discretization is to facilitate the subsequent search for the optimal solution.

[0066] The process of building a decision model is:

[0067] Create an empty decision model and set the initial node, which represents the initial state of all decision variables, that is, all x jiThe initial value of is 0. Then, determine the total number of decision variables N×M according to the actual situation, where N represents the number of raw coal bins and M represents the number of upper bin belts. Arrange all decision variables according to the number of raw coal bins and upper bin belts to determine the number of layers of the decision model. Each layer contains a decision variable. According to the number of discrete points obtained by discretization, create a corresponding number of branch nodes in the current layer. Each branch node represents a possible value of the decision variable. Connect all branch nodes in the current layer. Then, after all decision variables have been assigned to the corresponding layers, generate the terminal node. Each terminal node represents a complete set of decision variable value combinations for a decision variable.

[0068] After the decision model is constructed, a deep search can be performed to find the optimal solution of the objective function. Compared with other decision models, the structure of the decision model of the present invention can clearly display the decision path and rules in the warehouse allocation process, so that coal bunker managers can quickly understand the warehouse allocation logic and improve the transparency and accuracy of the decision. The decision model can process numerical data and categorical features without the need for complex preprocessing, which is of great advantage for the diverse types of coal and quality standards in coal bunkers. In addition, the decision model of the present invention is easy to construct and easy to implement and apply for coal bunker management companies. In actual use, multiple decision models can also be combined and applied to further improve the accuracy of warehouse allocation decisions.

[0069] The process of deep search is:

[0070] First, initialize the search state, that is, create a data structure to record the current search position of each decision variable. Set the current search layer to the layer where the initial node is located (i.e., the first layer). Then, start traversing layer by layer from the initial node. Traverse each branch node of the current layer and check whether the value of the current branch node meets the constraint conditions. If it does, proceed to the next step; otherwise, continue to traverse the next branch node of the current layer. After traversing the current layer, if the current layer is not the last layer, continue to traverse the next layer, and use the current node as the parent node of the next layer to traverse the branch nodes of the next layer; if the current layer is the last layer, it means that all decision variables have been assigned values, and calculate the objective function value corresponding to the current terminal node. If the calculated objective function value is less than the known optimal solution, update the optimal solution and the corresponding decision variable value combination. If all nodes of the current layer have been traversed and have not reached the initial node, go back to the previous layer and continue to traverse the untraversed nodes of the previous layer until the entire decision model is traversed or the convergence condition is reached (for example, the convergence condition is that the maximum number of iterations is reached or the optimal solution has not changed significantly within a certain number of iterations). According to the optimal solution of the objective function found through search and the corresponding combination of decision variable values, each raw coal bin is allocated.

[0071] Below, a simple example is used to illustrate the solution process of the entire nonlinear programming model.

[0072] Assuming that the number of raw coal bins is 2 and the number of upper bin belts is 2, four decision variables can be generated: x 11 、x 12 、x 21 、x 22 .x 11 represents the amount of coal distributed from upper bunker belt 1 to raw coal bunker 1, x 12 It represents the amount of coal distributed from upper bunker belt 1 to raw coal bunker 2, x 21 It represents the amount of coal distributed from upper storage belt 2 to raw coal storage 1, x 22 It represents the amount of coal allocated to the raw coal bunker 2 by the upper storage belt 2. The decision model has four layers. Assuming that the search range of the four decision variables is discretized to obtain 5, 6, 7, and 8 value points respectively, then according to the number of discretized value points, a corresponding number of branch nodes are created in the corresponding layer. Finally, create a terminal node, and each terminal node represents a set of four decision variable value combinations. When searching, start the search from the initial node, traverse the branch nodes in the first layer in turn, and judge whether the current value point meets all the constraints. If it does, enter the second layer; if it does not meet the constraints, continue to traverse the next branch node in the first layer; and so on, until all four layers are searched. Calculate the objective function corresponding to the current terminal node, find the optimal solution of the objective function and the decision variable value combination corresponding to the optimal solution. That is, finally obtain x 11 、x 12 、x 21 、x 22 The optimal value of .

[0073] The types of coal stored in commercial coal bunkers are different. Therefore, when allocating coal, it is necessary to focus on the coordination between coal quantity and loading to ensure that different commercial coal bunkers can meet loading needs.

[0074] Specifically, the precise allocation strategy for commodity coal bunkers includes: real-time monitoring of the coal inventory Q of m commodity coal bunkers r (Unit: tons), coal inflow velocity V r_in (tons / second) and outflow velocity V r_out (tons / second), r = 1, 2, ..., m; where Q r =H r ×A r ×ρ,H r represents the real-time coal position of the rth commercial coal bunker (unit: m), A r Represents the bottom area of ​​the rth commercial coal bunker (unit: m 2 ), ρ represents the density of coal (unit: Kg / m 3 ). According to the coal inventory Qr , Coal inflow velocity V r_in and outflow velocity V r_out Calculate the time T required to fill the commercial coal bunker full_r and the time required for emptying T empty_r .in, Q max_r Indicates the maximum capacity of the rth commercial coal bunker. The bunkers are allocated in order according to their weight priority.

[0075] Specifically, the coal bunkers are allocated in order according to their weight priorities, including:

[0076] Determine the weight priority Y of the commercial coal bunker r =α×D r +β×I r +γ×W r , where Y r represents the weight priority of the rth commercial coal bunker, D r represents the inventory status of the rth commodity coal bunker, I r represents the waiting time of the loading vehicle in the loading channel where the rth commercial coal bunker is located, W r It represents the number of shipping vehicles, and α, β, and γ represent weight coefficients (adjusted according to actual conditions through the comprehensive management and control platform).

[0077] A warehouse allocation model is established based on weight priority. The goal of this warehouse allocation model is to maximize the demand for high-priority commodity coal bunkers while minimizing the waiting time for low-priority commodity coal bunkers. The specific process is as follows:

[0078] Sort the m commercial coal bunkers according to their weight priority from high to low to form a coal bunker list;

[0079] Traverse the coal bunker list one by one and perform the following steps for each commodity coal bunker:

[0080] Step a: Check the current coal quantity Q in the commercial coal bunker r (t) Whether the shipping demand Q is met order,r If it is satisfied, shipment will be carried out; if not, proceed to the next step.

[0081] Step b: Calculate the amount of coal required to be replenished ΔQ r =Q order,r -Q r (t).

[0082] Step c: Determine the amount of coal Q that can be allocated to the rth commercial coal bunker based on the conveying capacity of the belt conveyor and the needs of other commercial coal bunkers. alloc,r ; Among them, C conveyor Indicates the maximum conveying capacity of the belt conveyor, Nhigh_prio Indicates the number of other commercial coal bunkers with a priority higher than or equal to the rth commercial coal bunker.

[0083] Step d: By controlling the timing of the coal feeder under the bunker, the amount of coal Q allocated to the rth commercial coal bunker is alloc,r Load into the commodity coal bunker.

[0084] Step e: Update the coal quantity Q of the rth commercial coal bunker r (t+1)=Q r (t)+Q alloc,r .

[0085] Step f: If there are any remaining shipping demands that have not been met, repeat steps ce until all shipping demands are met or the belt conveyor reaches its maximum conveying capacity.

[0086] In summary, the decision-making optimization method for accurate coal bunker allocation of the present invention has formulated different allocation strategies for different coal bunker types, combined with multiple factors and multi-faceted considerations, to achieve automation, intelligence and precision of different coal bunker allocation, and can achieve dynamic adjustment of coal bunker management, improve allocation efficiency and production benefits, and reduce manual labor intensity. Through accurate allocation, it is possible to reduce the economic losses caused by coal waste and quality fluctuations due to coal allocation errors, ensure the stable operation of the coal flow production line, meet the downstream shipping needs of the coal bunker, and improve economic benefits.

[0087] Based on the above ideal embodiments of the present invention, the relevant staff can make various changes and modifications without departing from the technical concept of the present invention through the above description. The technical scope of the present invention is not limited to the contents of the specification, but must be determined according to the scope of the claims.

Claims

1. A decision optimization method for accurate coal bunker allocation, characterized in that: include: Optimize the raw coal bunker allocation according to the raw coal bunker precise allocation strategy; The allocation of commercial coal bunkers is optimized according to the precise allocation strategy of commercial coal bunkers.

2. The decision optimization method for accurate coal bunker allocation according to claim 1 is characterized in that: The precise allocation strategy for raw coal bunkers includes: Construct the objective function E; Constructing constraints on the objective function E; The objective function E is solved using a nonlinear programming model.

3. The decision optimization method for accurate coal bunker allocation according to claim 2 is characterized in that: The constraints include: inventory safety constraints, non-negative constraints and upper warehouse belt conveyor capacity constraints.

4. The decision optimization method for accurate coal bunker allocation according to claim 3 is characterized in that: The solution process of the nonlinear programming model includes: Initialize parameter sets and decision variables; Discretize the feasible domain; Build decision-making models; Deep search finds the optimal solution of the objective function E.

5. The decision-making optimization method for accurate coal bunker allocation according to claim 4 is characterized in that: The objective function E represents the equilibrium index, C i represents the current amount of coal in the i-th raw coal bunker, i=1, 2, ..., N; Represents the average coal quantity of N raw coal bins; the optimization goal is to minimize the equilibrium index E.

6. The decision-making optimization method for accurate coal bunker allocation according to claim 5 is characterized in that: The inventory safety constraint is expressed as: L i ≤C i ≤U i , L i Indicates the lower limit of the safety stock of raw coal bunker, U i Represents the upper limit of the safety stock of the raw coal bunker, where: M represents the number of upper warehouse conveyor belts, j = 1, 2, ..., M; S i represents the initial coal quantity of the i-th raw coal bunker; x ji It represents the amount of coal distributed from the j-th upper bunker belt to the i-th raw coal bunker; The non-negative constraint is expressed as: ji ≥0, The upper warehouse belt conveying capacity constraint is expressed as: P j Indicates the maximum coal transport capacity of the jth upper storage belt.

7. The decision optimization method for accurate coal bunker allocation according to claim 6 is characterized in that: The parameter set includes: the number of raw coal bins N, the number of upper bin belts M, the initial coal quantity S of each raw coal bin i , the upper limit of the safety stock constraint U i and the lower limit L i , the maximum coal conveying capacity P of each upper storage belt j ; The decision variable is x ji .

8. The decision optimization method for accurate coal bunker allocation according to claim 7 is characterized in that: Discretize the feasible domain, including: Determine the decision variable x based on the inventory safety constraint and the upper warehouse belt conveyor capacity constraint ji The search scope is: Set the search step size to d ji , then the decision variable point in the feasible region can be expressed as: n ji represents the decision variable x ji The number of discrete points in the feasible region; For each decision variable x ji The search range is discretized into several points.

9. The decision optimization method for accurate coal bunker allocation according to claim 8, characterized in that: Constructing a decision model based on a number of points obtained through discretization, wherein the decision model includes: an initial node, a number of layers, a branch node, and a terminal node; The deep search process includes: initializing the search state, traversing layer by layer starting from the initial node; traversing the current layer, if the current layer is not the last layer, entering the next layer traversal, and the current node is used as the parent node of the next layer; if the current layer is the last layer, calculating the objective function E corresponding to the current terminal node; if the current objective function value is less than the known optimal solution, updating the optimal solution and the corresponding decision variable value combination; if all nodes of the current layer have been traversed and have not reached the initial node, backtracking to the previous layer, and continuing to traverse the untraversed nodes of the previous layer until the entire decision model is traversed or the convergence condition is reached.

10. The decision optimization method for accurate coal bunker allocation according to claim 1, characterized in that: The precise allocation strategy for commodity coal bunkers includes: Real-time monitoring of the coal inventory Q of m commercial coal bunkers r , Coal inflow velocity V r_in and outflow velocity V r_out , r = 1, 2, ..., m; where Q r =H r ×A r ×ρ,H r represents the real-time coal position of the rth commercial coal bunker, A r represents the bottom area of ​​the rth commercial coal bunker, and ρ represents the density of the coal type; According to the coal inventory Q r , Coal inflow velocity V r_in and outflow velocity V r_out Calculate the time T required to fill the commercial coal bunker full_r and the time required for emptying T empty_r ; The commercial coal bunkers are allocated in order according to their weight priority.

11. The decision optimization method for accurate coal bunker allocation according to claim 10, characterized in that: The warehouses are allocated in sequence according to the weight priority of the commodity coal warehouses, including: Determine the weight priority Y of the commercial coal bunker r =α×D r +β×I r +γ×W r , where Y r represents the weight priority of the rth commercial coal bunker, D r represents the inventory status of the rth commodity coal bunker, I r represents the waiting time of the loading vehicle in the loading channel where the rth commercial coal bunker is located, W r represents the number of shipping vehicles, α, β, γ represent weight coefficients; Establish a warehouse allocation model based on the weight priority: Sort the m commercial coal bunkers according to their weight priority from high to low to form a coal bunker list; Traverse the coal bunker list one by one and perform the following steps for each commodity coal bunker: Step a: Check the current coal quantity Q in the commercial coal bunker r (t) Whether the shipping demand Q is met order,r If the conditions are met, shipment will be carried out; if not, the next step will be executed; Step b: Calculate the amount of coal required to be replenished ΔQ r =Q order,r -Q r (t); Step c: Determine the amount of coal Q that can be allocated to the rth commercial coal bunker based on the conveying capacity of the belt conveyor and the needs of other commercial coal bunkers. alloc,r ; Step d: By controlling the timing of the coal feeder under the bunker, the amount of coal Q allocated to the rth commercial coal bunker is alloc,r Load into the commodity coal bunker; Step e: Update the coal quantity Q of the rth commercial coal bunker r (t+1)=Q r (t)+Q alloc,r ; Step f: If there are any remaining shipping demands that have not been met, repeat steps ce until all shipping demands are met or the belt conveyor reaches its maximum conveying capacity.

Images