Coal supply dispatching optimization system and method based on machine learning

Abstract

The invention discloses a coal supply dispatching optimization system and method based on machine learning, and relates to the field of coal supply dispatching optimizing.A supply route is selected from the perspective of coal supply cost, so that the supply cost is minimum; according to the method, historical coal supply data are collected, a mapping equation between various types of coal supply cost influence factor data and the supply cost is constructed, a mapping tool is provided for subsequent continuous mapping calculation of the supply cost of each route, and then a selection basis is provided for selection of the route with the minimum supply cost at present; wherein for influence factor data which cannot be acquired in advance, historical data of the influence factor data are acquired, and then the influence factor data at future moments are predicted through a support vector machine model, so that subsequent mapping is facilitated; and different transportation modes are analyzed separately, so that the analysis accuracy is improved, and the accuracy of selecting the transportation route subsequently is improved.

Description

Technical Field

[0001] The present invention belongs to the field of coal supply and transportation optimization, and in particular, relates to a coal supply and transportation optimization system and method based on machine learning. Background Art

[0002] In the process of coal supply and transportation, the choice of supply and transportation routes is often involved; if the coal supply and transportation routes are unreasonable, it may lead to problems such as excessive transportation distance and mismatch of transportation methods, thereby significantly increasing transportation costs. In addition, unreasonable routes may cause coal to undergo unnecessary transfers or detours during transportation, increasing losses and waste during transportation, and indirectly increasing transportation costs. Summary of the invention

[0003] In response to the problems in the related technology, the present invention proposes a coal supply and transportation optimization system and method based on machine learning to overcome the above-mentioned technical problems existing in the existing related technology.

[0004] To solve the above technical problems, the present invention is achieved through the following technical solutions: The present invention is a coal supply and transportation optimization method based on machine learning, comprising the following steps: S1. Set several types of factors that affect the total cost of coal supply and transportation, and obtain a set of factors that affect the coal supply and transportation cost; S2. In conjunction with the type set of factors influencing coal supply and transportation costs, collect several sets of historical data on factors influencing coal supply and transportation costs, corresponding supply and transportation cost data, and coal transportation mode data, and construct a final set of coal supply and transportation cost mapping equations; S3. According to the type set of coal supply and transportation cost influencing factors, obtain the supply and transportation cost influencing factor data corresponding to each route from the current coal supply and transportation starting point to the current coal supply and transportation end point, and obtain the current to-be-forecasted supply and transportation cost influencing factor data matrix and the current non-forecasted supply and transportation cost influencing factor data matrix; S4. Use the final coal supply and transportation cost mapping equation set to map the current supply and transportation cost influencing factor data matrix to be predicted and the current non-predicted supply and transportation cost influencing factor data matrix to obtain the current supply and transportation cost data set; select the route for the current coal supply and transportation according to the current supply and transportation cost data set; This scheme selects the supply and transportation routes from the perspective of coal supply and transportation costs to minimize the supply and transportation costs. Among them, by collecting historical coal supply and transportation data, a mapping equation between various types of coal supply and transportation cost influencing factor data and supply and transportation costs is constructed, which provides a mapping tool for subsequent mapping calculations of the supply and transportation costs of each route, and thus provides a basis for selecting the route with the lowest current supply and transportation cost.

[0005] Preferably, the S1 comprises the following steps: S11. Set several types of factors that affect the total cost of coal supply and transportation to obtain a type set of factors that affect the coal supply and transportation cost; then set several types of coal transportation methods to obtain a type set of coal transportation methods; S12, setting the current coal supply and transportation starting point and the current coal supply and transportation destination; according to the coal transportation mode type set, obtaining route data of various types of transportation modes between the current coal supply and transportation starting point and the current coal supply and transportation destination, and obtaining a current transportation route data set; Each factor in the type set of factors affecting the cost of coal supply and transportation has a certain degree of influence on the cost of coal supply and transportation. By setting the type set of factors affecting the cost of coal supply and transportation, a collection basis is provided for the subsequent collection of historical coal supply and transportation data. Since different modes of transportation have different cost calculation methods, different modes of transportation are analyzed separately in this plan, which improves the accuracy of the analysis and thus improves the accuracy of the subsequent selection of transportation routes.

[0006] Preferably, S2 comprises the following steps: S21, in conjunction with the coal supply and transportation cost influencing factor type set and the coal transportation mode type set, collect several sets of historical coal supply and transportation cost influencing factor data, corresponding supply and transportation cost data, and coal transportation mode data, to obtain a historical coal supply and transportation cost influencing factor data matrix, a historical coal supply and transportation cost data set, and a historical coal transportation mode data set; S22, constructing a final coal supply and transportation cost mapping equation corresponding to each transportation mode according to the historical coal supply and transportation cost influencing factor data matrix, the historical coal supply and transportation cost data set, and the historical coal transportation mode data set to obtain a final coal supply and transportation cost mapping equation set; By collecting the data matrix of factors affecting historical coal supply and transportation costs, the historical coal supply and transportation cost data set, and the historical coal transportation mode data set, data support is provided for the subsequent construction of the final coal supply and transportation cost mapping equation set.

[0007] Preferably, the S22 comprises the following steps: S221. Constructing an initial coal supply and transportation cost mapping equation corresponding to each transportation mode in conjunction with the coal transportation mode type set to obtain an initial coal supply and transportation cost mapping equation set; S222, respectively substitute each row of data of the historical coal supply and transportation cost influencing factor data matrix into the corresponding initial coal supply and transportation cost mapping equation in the initial coal supply and transportation cost mapping equation set for mapping, and obtain the historical coal supply and transportation cost initial mapping data set; calculate the error value between the historical coal supply and transportation cost initial mapping data set and the coal supply and transportation cost data corresponding to the same transportation mode in the historical coal supply and transportation cost data set, and obtain the coal supply and transportation cost initial mapping error data set; S223, adjusting the initial coal supply and transportation cost mapping equation in the initial coal supply and transportation cost mapping equation set according to the coal supply and transportation cost initial mapping error data set; after the adjustment is completed, obtaining the final coal supply and transportation cost mapping equation set; By substituting the collected historical coal supply and transportation data into the constructed initial coal supply and transportation cost mapping equations for mapping, the mapping accuracy of the constructed initial coal supply and transportation cost mapping equations can be tested, and then the mapping equations whose mapping accuracy does not meet the requirements can be adjusted.

[0008] Preferably, in S223, the initial coal supply and transportation cost mapping equation in the initial coal supply and transportation cost mapping equation set is adjusted by using a honey badger optimization algorithm; The honey badger optimization algorithm simulates the foraging behavior of the honey badger, can conduct extensive exploration in the search space, has strong global search capabilities, and is not easily trapped in the local optimal solution; when approaching the optimal solution, the algorithm can converge quickly; and under different initial conditions and search environments, it can show good stability and can stably converge to the optimal solution or approximate optimal solution; based on the above advantages, the honey badger optimization algorithm is used in this scheme to adjust the constant coefficients of the initial coal supply and transportation cost mapping equation, thereby improving the adjustment accuracy and efficiency.

[0009] Preferably, the S223 comprises the following steps: S2231. Setting a coal supply and transportation cost mapping error threshold; S2232. When there is initial coal supply and transportation cost mapping error data greater than or equal to the coal supply and transportation cost mapping error threshold in the initial coal supply and transportation cost mapping error data set, the initial coal supply and transportation cost mapping equation corresponding to the initial coal supply and transportation cost mapping error data is recorded as the coal supply and transportation cost mapping equation to be adjusted, and the coal supply and transportation cost mapping equation to be adjusted is adjusted until there is no initial coal supply and transportation cost mapping error data greater than or equal to the coal supply and transportation cost mapping error threshold in the initial coal supply and transportation cost mapping error data set, and a final coal supply and transportation cost mapping equation set is obtained; otherwise, the initial coal supply and transportation cost mapping equation set is used as the final coal supply and transportation cost mapping equation set; By setting the coal supply and transportation cost mapping error threshold, a quantitative basis is provided for the subsequent determination of whether the mapping accuracy of the initial coal supply and transportation cost mapping equation meets the requirements.

[0010] Preferably, S3 comprises the following steps: S31. Classify the types of coal supply and transportation cost influencing factors in the coal supply and transportation cost influencing factor type set to obtain a non-predicted supply and transportation cost influencing factor type set and a to-be-predicted supply and transportation cost influencing factor type set; obtain the non-predicted supply and transportation cost influencing factor data corresponding to each route in the process from the current coal supply and transportation starting point to the current coal supply and transportation end point in combination with the non-predicted supply and transportation cost influencing factor type set and the current transportation route data set to obtain the current non-predicted supply and transportation cost influencing factor data matrix; S32. Before the start of coal supply and transportation, in conjunction with the set of types of factors affecting the supply and transportation cost to be predicted and the current transportation route data set, collect the data of factors affecting the supply and transportation cost to be predicted at several historical time points of each route to obtain a data matrix set of factors affecting the supply and transportation cost to be predicted in history; set several time points in the process from the current coal supply and transportation starting point to the current coal supply and transportation end point to obtain a current supply and transportation time point set; predict the data of factors affecting the supply and transportation cost to be predicted at multiple time points of each route corresponding to each current supply and transportation time point according to the set of factors affecting the supply and transportation cost to be predicted and calculate the average value to obtain a data matrix of factors affecting the supply and transportation cost to be predicted in history; Preferably, in S32, the support vector machine model is used to predict the data of the factors affecting the supply and transportation costs to be predicted at multiple time points of each route corresponding to each current supply and transportation time point; Since some factors affecting the supply and transportation cost can be obtained before transportation, while other factors cannot be collected in advance, this solution handles these two types of factors separately. The support vector machine (SVM) model can construct an excellent hyperplane in a high-dimensional feature space, thereby achieving effective classification of high-dimensional data; when constructing a classifier, the decision boundary is selected by maximizing the interval, so that the model has good generalization ability on unseen data; it is relatively robust to noise data, that is, it is less sensitive to outliers and noise points. This is because the classification decision boundary of the SVM is determined by the support vector, and the support vector is usually the sample point closest to the classification boundary, so the outlier has less impact on the decision boundary, making the model more robust; based on the above advantages of the support vector machine model, for the influencing factors that cannot be collected in advance, by collecting their historical data, the influencing factor data at future moments is predicted through the support vector machine model for subsequent mapping.

[0011] Preferably, S4 comprises the following steps: S41, in conjunction with the final coal supply and transportation cost mapping equation set, input each row of data combination in the current non-predicted supply and transportation cost influencing factor data matrix and the current to-be-predicted supply and transportation cost influencing factor data matrix into the corresponding final coal supply and transportation cost mapping equation for mapping, to obtain the current supply and transportation cost data set; S42: Select the current transportation route data corresponding to the minimum supply and transportation cost data in the current supply and transportation cost data set as the selected route for the current transportation.

[0012] The coal supply and transportation optimization system based on machine learning includes a coal supply and transportation cost influencing factor setting module, a current transportation route data collection module, a historical coal supply and transportation data collection module, a coal supply and transportation cost mapping equation construction module, a current coal supply and transportation cost influencing factor data acquisition module, a current supply and transportation cost mapping module and a final supply and transportation route selection module.

[0013] The present invention has the following beneficial effects: 1. The present invention selects the supply and transportation routes from the perspective of coal supply and transportation costs to minimize the supply and transportation costs; wherein, by collecting historical coal supply and transportation data, mapping equations between various types of coal supply and transportation cost influencing factor data and supply and transportation costs are constructed, providing a mapping tool for subsequent continued mapping calculations of the supply and transportation costs of each route, and thus providing a selection basis for selecting the route with the lowest current supply and transportation costs; wherein, for the influencing factor data that cannot be collected in advance, the historical data is collected, and then the influencing factor data at future moments is predicted through a support vector machine model for subsequent mapping.

[0014] 2. In the present invention, different modes of transportation are analyzed separately in this solution, which improves the accuracy of the analysis and further improves the accuracy of the subsequent selection of transportation routes.

[0015] 3. In the present invention, by substituting the collected historical coal supply and transportation data into the constructed initial coal supply and transportation cost mapping equations for mapping, the mapping accuracy of the constructed initial coal supply and transportation cost mapping equations can be detected, and then the mapping equations whose mapping accuracy does not meet the requirements can be adjusted; wherein, the honey badger optimization algorithm is used to adjust the constant coefficients of the initial coal supply and transportation cost mapping equation, thereby improving the adjustment accuracy and efficiency.

[0016] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the invention, the drawings required for describing the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0018] Figure 1 This is a module schematic diagram of a coal supply and transportation optimization system based on machine learning according to the present invention; Figure 2 It is a flow chart of the coal supply and transportation optimization method based on machine learning of the present invention. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the invention to clearly and completely describe the technical solutions in the embodiments of the invention. Obviously, the described embodiments are only part of the embodiments of the invention, not all of the embodiments. Based on the embodiments in the invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the invention.

[0020] Embodiment 1 See also Figure 2 , this embodiment is a coal supply and transportation optimization method based on machine learning, comprising the following steps: S1. Set several types of factors that affect the total cost of coal supply and transportation, and obtain a set of factors that affect the coal supply and transportation cost; The S1 comprises the following steps: S11. Set several types of factors that affect the total cost of coal supply and transportation to obtain a set of factors affecting coal supply and transportation cost; the set of factors affecting coal supply and transportation cost includes transportation distance, transportation volume, oil price, weather factors, etc.; then set several types of coal transportation modes to obtain a set of coal transportation mode types; the set of coal transportation mode types includes railway transportation mode, road transportation mode, water transportation mode, etc.; S12, setting the current coal supply and transportation starting point and the current coal supply and transportation destination; according to the coal transportation mode type set, obtaining route data of various types of transportation modes between the current coal supply and transportation starting point and the current coal supply and transportation destination, and obtaining a current transportation route data set; S2. In conjunction with the type set of factors influencing coal supply and transportation costs, collect several sets of historical data on factors influencing coal supply and transportation costs, corresponding supply and transportation cost data, and coal transportation mode data, and construct a final set of coal supply and transportation cost mapping equations; The S2 comprises the following steps: S21, in conjunction with the coal supply and transportation cost influencing factor type set and the coal transportation mode type set, collect several sets of historical coal supply and transportation cost influencing factor data, corresponding supply and transportation cost data, and coal transportation mode data to obtain a historical coal supply and transportation cost influencing factor data matrix a 1. Historical coal supply and transportation cost dataset and historical coal transportation mode dataset ; a 3i Indicates the collected i The coal transportation mode data of historical coal supply and transportation is collected. Indicates the total number of groups of historical coal supply and transportation data collected; a 1 is as follows, ; in, a 1ij Indicates the collected i The first time the group carried out coal supply and transportation j Types of data on factors affecting supply and transportation costs, Indicates the total number of factors affecting coal supply and transportation cost; S22, constructing a final coal supply and transportation cost mapping equation corresponding to each transportation mode according to the historical coal supply and transportation cost influencing factor data matrix, the historical coal supply and transportation cost data set, and the historical coal transportation mode data set to obtain a final coal supply and transportation cost mapping equation set; The S22 comprises the following steps: S221, in conjunction with the coal transportation mode type set, construct an initial coal supply and transportation cost mapping equation corresponding to each transportation mode to obtain an initial coal supply and transportation cost mapping equation set , Indicates the setting i The initial coal supply and transportation cost mapping equation corresponding to the types of transportation modes is: b Indicates the total number of coal transportation modes set; as follows, ; In the formula, for The dependent variable represents the coal supply and transportation cost data; express The mapping method refers to The combination relationship of each independent variable, such as multiplication, addition, exponential relationship and inverse relationship; for No. j The independent variable represents j Data on factors affecting coal supply and transportation costs of various types; S222, each row of data of the historical coal supply and transportation cost influencing factor data matrix is ​​substituted into the initial coal supply and transportation cost mapping equation corresponding to the initial coal supply and transportation cost mapping equation set for mapping, so as to obtain the initial mapping data set of the historical coal supply and transportation cost , It means that the first i Substituting the row data into the initial coal supply and transportation cost mapping equation corresponding to the initial coal supply and transportation cost mapping equation set to obtain mapping data; calculating the error value between the historical coal supply and transportation cost initial mapping data set and the coal supply and transportation cost data corresponding to the same transportation mode in the historical coal supply and transportation cost data set, to obtain the coal supply and transportation cost initial mapping error data set; S223, adjusting the initial coal supply and transportation cost mapping equation in the initial coal supply and transportation cost mapping equation set according to the coal supply and transportation cost initial mapping error data set; after the adjustment is completed, obtaining the final coal supply and transportation cost mapping equation set; In S223, the initial coal supply and transportation cost mapping equation in the initial coal supply and transportation cost mapping equation set is adjusted using the honey badger optimization algorithm; The S223 comprises the following steps: S2231. Setting a coal supply and transportation cost mapping error threshold; S2232. When there is initial coal supply and transportation cost mapping error data greater than or equal to the coal supply and transportation cost mapping error threshold in the initial coal supply and transportation cost mapping error data set, the initial coal supply and transportation cost mapping equation corresponding to the initial coal supply and transportation cost mapping error data is recorded as the coal supply and transportation cost mapping equation to be adjusted, and the coal supply and transportation cost mapping equation to be adjusted is adjusted until there is no initial coal supply and transportation cost mapping error data greater than or equal to the coal supply and transportation cost mapping error threshold in the initial coal supply and transportation cost mapping error data set, and a final coal supply and transportation cost mapping equation set is obtained; otherwise, the initial coal supply and transportation cost mapping equation set is used as the final coal supply and transportation cost mapping equation set; S3. According to the type set of coal supply and transportation cost influencing factors, obtain the supply and transportation cost influencing factor data corresponding to each route from the current coal supply and transportation starting point to the current coal supply and transportation end point, and obtain the current to-be-forecasted supply and transportation cost influencing factor data matrix and the current non-forecasted supply and transportation cost influencing factor data matrix; The S3 comprises the following steps: S31. Divide the types of coal supply and transportation cost influencing factors in the coal supply and transportation cost influencing factor type set to obtain a non-predicted supply and transportation cost influencing factor type set and a to-be-predicted supply and transportation cost influencing factor type set; cooperate with the non-predicted supply and transportation cost influencing factor type set and the current transportation route data set to obtain the non-predicted supply and transportation cost influencing factor data corresponding to each route in the process from the current coal supply and transportation starting point to the current coal supply and transportation destination, and obtain the current non-predicted supply and transportation cost influencing factor data matrix; the non-predicted supply and transportation cost influencing factor type set includes transportation distance and transportation volume, etc.; the to-be-predicted supply and transportation cost influencing factor type set includes precipitation, etc.; S32. Before the start of coal supply and transportation, in conjunction with the set of types of factors affecting the supply and transportation cost to be predicted and the current transportation route data set, collect the data of factors affecting the supply and transportation cost to be predicted at several historical time points of each route to obtain a data matrix set of factors affecting the supply and transportation cost to be predicted in history; set several time points in the process from the current coal supply and transportation starting point to the current coal supply and transportation end point to obtain a current supply and transportation time point set; predict the data of factors affecting the supply and transportation cost to be predicted at multiple time points of each route corresponding to each current supply and transportation time point according to the set of factors affecting the supply and transportation cost to be predicted and calculate the average value to obtain a data matrix of factors affecting the supply and transportation cost to be predicted in history; Preferably, in S32, the support vector machine model is used to predict the data of the factors affecting the supply and transportation costs to be predicted at multiple time points of each route corresponding to each current supply and transportation time point; S4. Use the final coal supply and transportation cost mapping equation set to map the current supply and transportation cost influencing factor data matrix to be predicted and the current non-predicted supply and transportation cost influencing factor data matrix to obtain the current supply and transportation cost data set; select the route for the current coal supply and transportation according to the current supply and transportation cost data set; The S4 comprises the following steps: S41, in conjunction with the final coal supply and transportation cost mapping equation set, input each row of data combination in the current non-predicted supply and transportation cost influencing factor data matrix and the current to-be-predicted supply and transportation cost influencing factor data matrix into the corresponding final coal supply and transportation cost mapping equation for mapping, to obtain the current supply and transportation cost data set; S42: Select the current transportation route data corresponding to the minimum supply and transportation cost data in the current supply and transportation cost data set as the selected route for the current transportation.

[0021] Embodiment 2 See also Figure 1, this embodiment discloses a coal supply and transportation optimization system based on machine learning, the system can implement the method of the above embodiment, including a coal supply and transportation cost influencing factor setting module, a current transportation route data collection module, a historical coal supply and transportation data collection module, a coal supply and transportation cost mapping equation construction module, a current coal supply and transportation cost influencing factor data acquisition module, a current supply and transportation cost mapping module and a final supply and transportation route selection module; The coal supply and transportation cost influencing factor setting module is used to set several types of factors that affect the total cost of coal supply and transportation, and obtain a set of coal supply and transportation cost influencing factor types; The current transportation route data acquisition module is used to obtain route data of various types of transportation modes between the current coal supply and transportation starting point and the current coal supply and transportation end point, and obtain a current transportation route data set; The historical coal supply and transportation data collection module is used to cooperate with the coal supply and transportation cost influencing factor type set to collect several groups of historical coal supply and transportation cost influencing factor data, corresponding supply and transportation cost data and coal transportation mode data, and obtain the historical coal supply and transportation cost influencing factor data matrix, the historical coal supply and transportation cost data set and the historical coal transportation mode data set; The coal supply and transportation cost mapping equation construction module is used to construct a final coal supply and transportation cost mapping equation set using a historical coal supply and transportation cost influencing factor data matrix, a historical coal supply and transportation cost data set, and a historical coal transportation mode data set; The current coal supply and transportation cost influencing factor data acquisition module is used to obtain the supply and transportation cost influencing factor data corresponding to each route from the current coal supply and transportation starting point to the current coal supply and transportation end point according to the coal supply and transportation cost influencing factor type set, and obtain the current to-be-predicted supply and transportation cost influencing factor data matrix and the current non-predicted supply and transportation cost influencing factor data matrix; The current supply and transportation cost mapping module is used to map the current supply and transportation cost influencing factor data matrix to be predicted and the current non-predicted supply and transportation cost influencing factor data matrix using the final coal supply and transportation cost mapping equation set to obtain a current supply and transportation cost data set; The final supply and transportation route selection module is used to select a route corresponding to the current coal supply and transportation according to the current supply and transportation cost data set.

[0022] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0023] The preferred embodiments of the invention disclosed above are only used to help explain the invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the invention, so that those skilled in the art can understand and use the invention well.

Claims

1. A coal supply and transportation optimization method based on machine learning, characterized in that: The following steps are involved: S1. Set several types of factors that affect the total cost of coal supply and transportation, and obtain a set of factors that affect the coal supply and transportation cost; S2. In conjunction with the type set of factors influencing coal supply and transportation costs, collect several sets of historical data on factors influencing coal supply and transportation costs, corresponding supply and transportation cost data, and coal transportation mode data, and construct a final set of coal supply and transportation cost mapping equations; S3. According to the type set of coal supply and transportation cost influencing factors, obtain the supply and transportation cost influencing factor data corresponding to each route from the current coal supply and transportation starting point to the current coal supply and transportation end point, and obtain the current to-be-forecasted supply and transportation cost influencing factor data matrix and the current non-forecasted supply and transportation cost influencing factor data matrix; S4. Use the final coal supply and transportation cost mapping equation set to map the current supply and transportation cost influencing factor data matrix to be predicted and the current non-predicted supply and transportation cost influencing factor data matrix to obtain the current supply and transportation cost data set; select the route for the current coal supply and transportation according to the current supply and transportation cost data set.

2. The coal supply and transportation optimization method based on machine learning according to claim 1 is characterized in that: The S1 comprises the following steps: S11. Set several types of factors that affect the total cost of coal supply and transportation to obtain a type set of factors that affect the coal supply and transportation cost; then set several types of coal transportation methods to obtain a type set of coal transportation methods; S12. Set the current coal supply and transportation starting point and the current coal supply and transportation destination; according to the coal transportation mode type set, obtain the route data of various types of transportation modes between the current coal supply and transportation starting point and the current coal supply and transportation destination to obtain the current transportation route data set.

3. The coal supply and transportation optimization method based on machine learning according to claim 2 is characterized in that: The S2 comprises the following steps: S21, in conjunction with the coal supply and transportation cost influencing factor type set and the coal transportation mode type set, collect several sets of historical coal supply and transportation cost influencing factor data, corresponding supply and transportation cost data, and coal transportation mode data, to obtain a historical coal supply and transportation cost influencing factor data matrix, a historical coal supply and transportation cost data set, and a historical coal transportation mode data set; S22. Construct a final coal supply and transportation cost mapping equation corresponding to each transportation mode according to the historical coal supply and transportation cost influencing factor data matrix, the historical coal supply and transportation cost data set, and the historical coal transportation mode data set to obtain a final coal supply and transportation cost mapping equation set.

4. The coal supply and transportation optimization method based on machine learning according to claim 3 is characterized in that: The S22 comprises the following steps: S221. Constructing an initial coal supply and transportation cost mapping equation corresponding to each transportation mode in conjunction with the coal transportation mode type set to obtain an initial coal supply and transportation cost mapping equation set; S222, substitute each row of data of the historical coal supply and transportation cost influencing factor data matrix into the corresponding initial coal supply and transportation cost mapping equation in the initial coal supply and transportation cost mapping equation set for mapping, and obtain the historical coal supply and transportation cost initial mapping data set; calculate the error value between the historical coal supply and transportation cost initial mapping data set and the coal supply and transportation cost data corresponding to the same transportation mode in the historical coal supply and transportation cost data set, and obtain the coal supply and transportation cost initial mapping error data set; S223. Adjust the initial coal supply and transportation cost mapping equation in the initial coal supply and transportation cost mapping equation set according to the coal supply and transportation cost initial mapping error data set; after the adjustment is completed, obtain the final coal supply and transportation cost mapping equation set.

5. The coal supply and transportation optimization method based on machine learning according to claim 4 is characterized in that: In S223, the initial coal supply and transportation cost mapping equation in the initial coal supply and transportation cost mapping equation set is adjusted using the honey badger optimization algorithm.

6. The coal supply and transportation optimization method based on machine learning according to claim 5 is characterized in that: The S223 comprises the following steps: S2231. Setting a coal supply and transportation cost mapping error threshold; S2232. When there is initial coal supply and transportation cost mapping error data greater than or equal to the coal supply and transportation cost mapping error threshold in the initial coal supply and transportation cost mapping error data set, the initial coal supply and transportation cost mapping equation corresponding to the initial coal supply and transportation cost mapping error data is recorded as the coal supply and transportation cost mapping equation to be adjusted, and the coal supply and transportation cost mapping equation to be adjusted is adjusted until there is no initial coal supply and transportation cost mapping error data greater than or equal to the coal supply and transportation cost mapping error threshold in the initial coal supply and transportation cost mapping error data set, and the final coal supply and transportation cost mapping equation set is obtained; otherwise, the initial coal supply and transportation cost mapping equation set is used as the final coal supply and transportation cost mapping equation set.

7. The coal supply and transportation optimization method based on machine learning according to claim 6 is characterized in that: The S3 comprises the following steps: S31. Classify the types of coal supply and transportation cost influencing factors in the coal supply and transportation cost influencing factor type set to obtain a non-predicted supply and transportation cost influencing factor type set and a to-be-predicted supply and transportation cost influencing factor type set; obtain the non-predicted supply and transportation cost influencing factor data corresponding to each route in the process from the current coal supply and transportation starting point to the current coal supply and transportation end point in combination with the non-predicted supply and transportation cost influencing factor type set and the current transportation route data set to obtain the current non-predicted supply and transportation cost influencing factor data matrix; S32. Before the start of coal supply and transportation, in conjunction with the set of types of supply and transportation cost influencing factors to be predicted and the current transportation route data set, collect the data of supply and transportation cost influencing factors to be predicted at several historical time points of each route to obtain a data matrix set of historical supply and transportation cost influencing factors to be predicted; set several time points in the process from the current coal supply and transportation starting point to the current coal supply and transportation end point to obtain a current supply and transportation time point set; predict the data of supply and transportation cost influencing factors to be predicted at multiple time points of each route corresponding to each current supply and transportation time point according to the set of historical supply and transportation cost influencing factors data matrix set and the current supply and transportation time point set, and calculate the average value to obtain a data matrix of current supply and transportation cost influencing factors to be predicted.

8. The coal supply and transportation optimization method based on machine learning according to claim 7 is characterized in that: In S32, a support vector machine model is used to predict the data of factors affecting the supply and transportation costs to be predicted at multiple time points of each route corresponding to each current supply and transportation time point.

9. The coal supply and transportation optimization method based on machine learning according to claim 8 is characterized in that: The S4 comprises the following steps: S41, in conjunction with the final coal supply and transportation cost mapping equation set, input each row of data combination in the current non-predicted supply and transportation cost influencing factor data matrix and the current to-be-predicted supply and transportation cost influencing factor data matrix into the corresponding final coal supply and transportation cost mapping equation for mapping, to obtain the current supply and transportation cost data set; S42: Select the current transportation route data corresponding to the minimum supply and transportation cost data in the current supply and transportation cost data set as the selected route for the current transportation.

10. A system for implementing the coal supply and transportation optimization method based on machine learning as described in any one of claims 1 to 9.

Images