Power plant coal inventory intelligent prediction management system

Abstract

The invention relates to the technical field of inventory management, and discloses a power plant coal inventory intelligent prediction management system, which is characterized in that an acquisition construction module acquires historical inventory influence data and coal inventory, and constructs a coal inventory prediction analysis chain; the classification calculation module calculates historical average inventory influence data, classifies the historical inventory influence data and calculates historical coal influence factors; the factor calculation module calculates a first sub-coal inventory prediction factor and a second sub-coal inventory prediction factor according to the historical coal influence factor and the coal inventory; a construction calculation module constructs a coal inventory prediction set and calculates a comprehensive coal inventory prediction factor; the inventory prediction module judges whether the current coal inventory is managed or not according to the comprehensive coal inventory prediction factor, if yes, the amount of coal entering the warehouse is determined, intelligent prediction of the coal inventory is achieved, the coal prediction accuracy is improved, the inventory level is made to be matched with the actual demand, coal waste is avoided, and the stability and continuity of coal supply are ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of inventory management, and in particular to an intelligent forecasting and management system for coal inventory in a power plant. Background Art

[0002] Coal is a widely used fossil fuel, mainly composed of carbon, hydrogen, oxygen and small amounts of sulfur, nitrogen and other elements. It is formed by plant debris deep underground after a long period of geological action. The main types of coal include anthracite, lignite, bituminous coal and sub-bituminous coal, which are classified according to their carbon content and calorific value. In the modern energy management system, coal is the main fuel for thermal power plants, and its inventory management is crucial to ensure the stability and economic benefits of power supply.

[0003] Traditional coal inventory forecasting management relies on manual experience and quantitative allocation, lacking in-depth mining of big data and intelligent decision-making support. Due to the uncertainty of coal consumption and the complexity of the supply chain, traditional coal inventory management methods face many challenges. This management method often leads to a mismatch between inventory levels and actual demand, increases storage costs, and may even cause the risk of power supply interruptions. Summary of the invention

[0004] The embodiment of the present invention provides a power plant coal inventory intelligent prediction and management system to solve the technical problem in the prior art that the power plant coal inventory cannot be intelligently predicted, the coal prediction accuracy cannot be improved, and the inventory level does not match the actual demand.

[0005] In order to achieve the above object, the present invention provides a power plant coal inventory intelligent forecasting and management system, comprising: A collection and construction module is used to determine a coal warehouse to be predicted, collect multiple historical inventory impact data and coal inventory of the coal warehouse to be predicted at a preset time period as a collection frequency, and construct a coal inventory forecasting and analysis chain based on the historical inventory impact data and the coal inventory, wherein the coal inventory forecasting and analysis chain includes multiple forecasting and analysis nodes and connection chains, and each forecasting and analysis node corresponds to multiple historical inventory impact data and coal inventory; A classification calculation module, used to calculate the historical average inventory impact data corresponding to the multiple historical inventory impact data, classify the multiple historical inventory impact data of each forecast analysis node based on the historical average inventory impact data, and calculate the historical coal impact factor of each forecast analysis node based on the classification result; A factor calculation module, used for calculating the first sub-coal inventory prediction factor and the second sub-coal inventory prediction factor of the coal inventory prediction analysis chain according to all historical coal influencing factors and the coal inventory corresponding to each prediction analysis node; Constructing a calculation module, which is used to construct a plurality of coal inventory prediction sets based on the first sub-coal inventory prediction factor and the second sub-coal inventory prediction factor, and calculating a comprehensive coal inventory prediction factor of the coal inventory prediction analysis chain according to the coal inventory prediction sets; The inventory forecasting module is used to determine whether it is necessary to manage the current coal inventory of the coal warehouse to be predicted based on the comprehensive coal inventory forecasting factor, and if so, determine the amount of coal to be stored based on the comprehensive coal inventory forecasting factor.

[0006] Furthermore, the classification calculation module is used for: The classification calculation module is used to classify all historical inventory impact data that are smaller than the historical average inventory impact data in each forecast analysis node into a first classification data set; The classification calculation module is used to classify all historical inventory impact data equal to the historical average inventory impact data into a second classification data set; The classification calculation module is used to classify all historical inventory impact data greater than the historical average inventory impact data into a third classification data set; The classification calculation module is used to perform normalization processing on the first classification data set to obtain a corresponding first normalized data set; The classification calculation module is used to perform normalization processing on the second classification data set to obtain a corresponding second normalized data set; The classification calculation module is used to perform normalization processing on the third classification data set to obtain a corresponding third normalized data set; The classification calculation module is used to calculate a first classification calculation value and a second classification calculation value of the first normalized data set based on a preset calculation method; The classification calculation module is used to determine a data classification range according to the first classification calculation value and the second classification calculation value, wherein the data classification range includes a left boundary data value and a right boundary data value, and the left boundary data value is smaller than the right boundary data value; The classification calculation module is used to generate a first to-be-calculated mark for all normalized values ​​in the first normalized data set that are greater than the left boundary data value and less than the right boundary data value.

[0007] Furthermore, the classification calculation module is used for: The classification calculation module is used to calculate the third classification calculation value and the fourth classification calculation value of the second normalized data set based on a preset calculation method; The classification calculation module is used to determine a second data classification range according to the third classification calculation value and the fourth classification calculation value, wherein the second data classification range includes a second left boundary data value and a second right boundary data value, and the second left boundary data value is smaller than the second right boundary data value; The classification calculation module is used to generate a second to-be-calculated mark for all normalized values ​​in the second normalized data set that are greater than the second left boundary data value and less than the second right boundary data value; The classification calculation module is used to calculate the fifth classification calculation value and the sixth classification calculation value of the third normalized data set based on a preset calculation method; The classification calculation module is used to determine a third data classification range according to the fifth classification calculation value and the sixth classification calculation value, wherein the third data classification range includes a third left boundary data value and a third right boundary data value, and the third left boundary data value is smaller than the third right boundary data value; The classification calculation module is used to generate a third to-be-calculated mark for all normalized values ​​in the third normalized data set that are greater than the third left boundary data value and less than the third right boundary data value; The classification calculation module is used to calculate the historical coal impact factor of each prediction analysis node according to the first mark to be calculated, the second mark to be calculated and the third mark to be calculated.

[0008] Furthermore, the classification calculation module is used for: The classification calculation module is used to configure a first calculation coefficient for the first mark to be calculated, configure a second calculation coefficient for the second mark to be calculated, and configure a third calculation coefficient for the third mark to be calculated; The classification calculation module is used to count the number of the first to-be-calculated marks, count the number of the second to-be-calculated marks, and count the number of the third to-be-calculated marks; The classification calculation module is used to calculate the historical coal impact factor of each prediction analysis node according to the following formula: ; Among them, d is the historical coal impact factor, e1 is the first calculation coefficient, e2 is the second calculation coefficient, e3 is the third calculation coefficient, f1 is the number of first marks to be calculated, f2 is the number of second marks to be calculated, f3 is the number of third marks to be calculated, and e1>e2>e3, e1>0, e2>0, e3>0.

[0009] Furthermore, the factor calculation module is used to: The factor calculation module is used to determine the first prediction analysis node and the adjacent prediction analysis nodes based on the acquisition order, and obtain the corresponding first coal inventory and the adjacent coal inventory; The factor calculation module is used to calculate the coal inventory difference between the first coal inventory and the adjacent coal inventory; The factor calculation module is used to determine the maximum coal inventory and the minimum coal inventory from all coal inventory, and calculate the second coal inventory difference between the maximum coal inventory and the minimum coal inventory; The factor calculation module is used to calculate the coal inventory ratio of the coal inventory difference and the second coal inventory difference; The factor calculation module is used to obtain the first historical coal impact factor corresponding to the first prediction and analysis node, and obtain the adjacent historical coal impact factors corresponding to the adjacent prediction and analysis nodes; The factor calculation module is used to calculate the factor difference between the first historical coal impact factor and the adjacent historical coal impact factor; The factor calculation module is used to determine the maximum historical coal impact factor and the minimum historical coal impact factor from all historical coal impact factors, and calculate the second factor difference between the maximum historical coal impact factor and the minimum historical coal impact factor; The factor calculation module is used to calculate the factor ratio of the factor difference and the second factor difference; The factor calculation module is used to calculate the product value of the factor ratio and the coal inventory ratio, and use it as the first sub-coal inventory prediction factor; The factor calculation module is used to process the remaining prediction analysis nodes to obtain a plurality of first sub-coal inventory prediction factors; The factor calculation module is used to calculate the mean of all first sub-coal inventory prediction factors and use it as the second sub-coal inventory prediction factor.

[0010] Furthermore, the construction calculation module is used to: The construction calculation module is used to divide all first sub-coal inventory prediction factors that are greater than the second sub-coal inventory prediction factor into an upper factor set; The construction calculation module is used to divide all first sub-coal inventory prediction factors that are less than or equal to the second sub-coal inventory prediction factor into a lower factor set; The construction calculation module is used to calculate the upper difference between each first sub-coal inventory prediction factor and the second sub-coal inventory prediction factor in the upper factor set, and generate an upper difference value set based on the principle of numerical size; The construction calculation module is used to calculate the lower difference between each first sub-coal inventory prediction factor and the second sub-coal inventory prediction factor in the lower factor set, and generate a lower difference value set based on the principle of numerical size; The construction calculation module is used to match the upper difference value set and the lower difference value set in pairs to obtain multiple coal inventory prediction sets.

[0011] Furthermore, the construction calculation module is used to: The construction calculation module is used to calculate the comprehensive coal inventory prediction factor of the coal inventory prediction analysis chain according to the coal inventory prediction set; ; Among them, w is the comprehensive coal inventory forecast factor of the coal inventory forecast analysis chain, n is the number of coal inventory forecast sets, k1 i is the upper difference in the i-th coal inventory forecast set, k2 i is the lower difference value in the i-th coal inventory forecast set, For all The minimum value in For all The maximum value in g 2 For all The variance of .

[0012] Furthermore, the inventory forecasting module is used to: The inventory prediction module is used to determine whether it is necessary to manage the current coal inventory of the coal warehouse to be predicted according to the relationship between the comprehensive coal inventory prediction factor and the preset comprehensive coal inventory prediction factor; The inventory forecasting module is used to determine that it is not necessary to manage the current coal inventory of the coal warehouse to be forecasted when the comprehensive coal inventory forecasting factor is greater than or equal to the preset comprehensive coal inventory forecasting factor; The inventory forecasting module is used to determine that the current coal inventory of the coal warehouse to be forecasted needs to be managed when the comprehensive coal inventory forecasting factor is less than the preset comprehensive coal inventory forecasting factor.

[0013] Furthermore, the inventory forecasting module is used to: The inventory prediction module is used to calculate the comprehensive coal inventory prediction factor difference value between the preset comprehensive coal inventory prediction factor and the comprehensive coal inventory prediction factor; The inventory forecasting module is used to select a corresponding management coefficient according to the relationship between the comprehensive coal inventory forecasting factor difference value and a plurality of preset difference values; The inventory forecasting module is used to calculate the product value of the management coefficient and the current coal inventory and use it as the target coal inventory of the coal warehouse to be forecasted; The inventory prediction module is used to determine the amount of coal stored in the coal warehouse to be predicted based on the target coal inventory and the current coal inventory.

[0014] Compared with the prior art, the present invention has the following beneficial effects: The invention discloses an intelligent prediction and management system for coal inventory in a power plant. A collection and construction module collects historical inventory impact data and coal inventory quantity, and constructs a coal inventory prediction and analysis chain; a classification and calculation module calculates historical average inventory impact data, classifies historical inventory impact data, and calculates historical coal impact factors; a factor calculation module calculates a first sub-coal inventory prediction factor and a second sub-coal inventory prediction factor according to historical coal impact factors and coal inventory quantity; a construction and calculation module constructs a coal inventory prediction set, and calculates a comprehensive coal inventory prediction factor; an inventory prediction module determines whether to manage the current coal inventory quantity according to the comprehensive coal inventory prediction factor, and if so, determines the amount of coal entering the warehouse, thereby realizing intelligent prediction of coal inventory, improving the accuracy of coal prediction, and matching the inventory level with actual demand, thereby avoiding coal waste and ensuring the stability and continuity of coal supply. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings: Figure 1 A schematic diagram of the structure of an intelligent forecasting and management system for coal inventory in a power plant according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0016] The specific implementation of the present invention is further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0017] In the description of the present application, it should be understood that the terms "center", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0018] The terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0019] In the description of this application, 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 this application can be understood according to specific circumstances.

[0020] The following is a description of preferred embodiments of the present invention with reference to the accompanying drawings.

[0021] like Figure 1 As shown, an embodiment of the present invention discloses an intelligent prediction and management system for coal inventory in a power plant, comprising: A collection and construction module is used to determine a coal warehouse to be predicted, collect multiple historical inventory impact data and coal inventory of the coal warehouse to be predicted at a preset time period as a collection frequency, and construct a coal inventory forecasting and analysis chain based on the historical inventory impact data and the coal inventory, wherein the coal inventory forecasting and analysis chain includes multiple forecasting and analysis nodes and connection chains, and each forecasting and analysis node corresponds to multiple historical inventory impact data and coal inventory; A classification calculation module, used to calculate the historical average inventory impact data corresponding to the multiple historical inventory impact data, classify the multiple historical inventory impact data of each forecast analysis node based on the historical average inventory impact data, and calculate the historical coal impact factor of each forecast analysis node based on the classification result; A factor calculation module, used for calculating the first sub-coal inventory prediction factor and the second sub-coal inventory prediction factor of the coal inventory prediction analysis chain according to all historical coal influencing factors and the coal inventory corresponding to each prediction analysis node; Constructing a calculation module, which is used to construct a plurality of coal inventory prediction sets based on the first sub-coal inventory prediction factor and the second sub-coal inventory prediction factor, and calculating a comprehensive coal inventory prediction factor of the coal inventory prediction analysis chain according to the coal inventory prediction sets; The inventory forecasting module is used to determine whether it is necessary to manage the current coal inventory of the coal warehouse to be predicted based on the comprehensive coal inventory forecasting factor, and if so, determine the amount of coal to be stored based on the comprehensive coal inventory forecasting factor.

[0022] In this embodiment, the preset time period can be set to 8 hours, 10 hours or 12 hours, etc., and can be adjusted according to actual conditions.

[0023] In this embodiment, the historical inventory impact data includes historical demand frequency, historical order quantity, historical coal consumption, historical coal consumption rate, etc.

[0024] In this embodiment, the connection chain is used to connect the prediction analysis nodes.

[0025] The beneficial effects of the above technical solution are: the present invention realizes intelligent prediction of coal inventory, improves the accuracy of coal prediction, and matches the inventory level with actual demand, which can not only avoid coal waste, but also ensure the stability and continuity of coal supply.

[0026] In some embodiments of the present application, the classification calculation module is used to: The classification calculation module is used to classify all historical inventory impact data that are smaller than the historical average inventory impact data in each forecast analysis node into a first classification data set; The classification calculation module is used to classify all historical inventory impact data equal to the historical average inventory impact data into a second classification data set; The classification calculation module is used to classify all historical inventory impact data greater than the historical average inventory impact data into a third classification data set; The classification calculation module is used to perform normalization processing on the first classification data set to obtain a corresponding first normalized data set; The classification calculation module is used to perform normalization processing on the second classification data set to obtain a corresponding second normalized data set; The classification calculation module is used to perform normalization processing on the third classification data set to obtain a corresponding third normalized data set; The classification calculation module is used to calculate a first classification calculation value and a second classification calculation value of the first normalized data set based on a preset calculation method; The classification calculation module is used to determine a data classification range according to the first classification calculation value and the second classification calculation value, wherein the data classification range includes a left boundary data value and a right boundary data value, and the left boundary data value is smaller than the right boundary data value; The classification calculation module is used to generate a first to-be-calculated mark for all normalized values ​​in the first normalized data set that are greater than the left boundary data value and less than the right boundary data value.

[0027] In this embodiment, if the historical inventory impact data is the historical order quantity, the historical average order quantity of the historical order quantities corresponding to all the forecast analysis nodes is calculated.

[0028] In this embodiment, the normalization processing method is the Min-Max normalization method, so that the result value is mapped to between [0, 1]. The specific normalization process is complicated and mature, and will not be introduced in detail here.

[0029] In this embodiment, the preset calculation method is to calculate the mean and the standard deviation, that is, the first category calculation value is the mean, and the second category calculation value is the standard deviation.

[0030] In this embodiment, when determining the data classification range according to the first classification calculation value and the second classification calculation value, the data classification range is calculated according to the following formula: ; Among them, L1 is the left boundary value, p1 is the mean, q1 is the calculation factor corresponding to the mean, r1 is the standard deviation, q2 is the calculation factor corresponding to the standard deviation, and q1+q2=1, q1>q2.

[0031] ; Among them, L2 is the right boundary value.

[0032] In this embodiment, the data classification range is determined according to the calculated left boundary value and right boundary value.

[0033] The beneficial effect of the above technical solution is: the present invention generates a first mark to be calculated for all normalized values ​​in the first normalized data set that are greater than the left boundary data value and less than the right boundary data value, thereby laying the foundation for calculating the historical coal impact factor of each prediction and analysis node and ensuring the calculation accuracy of the historical coal impact factor.

[0034] In some embodiments of the present application, the classification calculation module is used to: The classification calculation module is used to calculate the third classification calculation value and the fourth classification calculation value of the second normalized data set based on a preset calculation method; The classification calculation module is used to determine a second data classification range according to the third classification calculation value and the fourth classification calculation value, wherein the second data classification range includes a second left boundary data value and a second right boundary data value, and the second left boundary data value is smaller than the second right boundary data value; The classification calculation module is used to generate a second to-be-calculated mark for all normalized values ​​in the second normalized data set that are greater than the second left boundary data value and less than the second right boundary data value; The classification calculation module is used to calculate the fifth classification calculation value and the sixth classification calculation value of the third normalized data set based on a preset calculation method; The classification calculation module is used to determine a third data classification range according to the fifth classification calculation value and the sixth classification calculation value, wherein the third data classification range includes a third left boundary data value and a third right boundary data value, and the third left boundary data value is smaller than the third right boundary data value; The classification calculation module is used to generate a third to-be-calculated mark for all normalized values ​​in the third normalized data set that are greater than the third left boundary data value and less than the third right boundary data value; The classification calculation module is used to calculate the historical coal impact factor of each prediction analysis node according to the first mark to be calculated, the second mark to be calculated and the third mark to be calculated.

[0035] In this embodiment, as described above, the third category calculation value here is the mean, the fourth category calculation value is the standard deviation, the fifth category calculation value is the mean, and the sixth category calculation value is the standard deviation.

[0036] In some embodiments of the present application, the classification calculation module is used to: The classification calculation module is used to configure a first calculation coefficient for the first mark to be calculated, configure a second calculation coefficient for the second mark to be calculated, and configure a third calculation coefficient for the third mark to be calculated; The classification calculation module is used to count the number of the first to-be-calculated marks, count the number of the second to-be-calculated marks, and count the number of the third to-be-calculated marks; The classification calculation module is used to calculate the historical coal impact factor of each prediction analysis node according to the following formula: ; Among them, d is the historical coal impact factor, e1 is the first calculation coefficient, e2 is the second calculation coefficient, e3 is the third calculation coefficient, f1 is the number of first marks to be calculated, f2 is the number of second marks to be calculated, f3 is the number of third marks to be calculated, and e1>e2>e3, e1>0, e2>0, e3>0.

[0037] The beneficial effect of the above technical solution is: the historical coal impact factor of each prediction and analysis node is calculated according to the first mark to be calculated, the second mark to be calculated and the third mark to be calculated, which ensures the calculation accuracy and intelligence of the historical coal impact factor, avoids the errors caused by human participation, and provides reliable data support for coal inventory forecasting.

[0038] In some embodiments of the present application, the factor calculation module is used to: The factor calculation module is used to determine the first prediction analysis node and the adjacent prediction analysis nodes based on the acquisition order, and obtain the corresponding first coal inventory and the adjacent coal inventory; The factor calculation module is used to calculate the coal inventory difference between the first coal inventory and the adjacent coal inventory; The factor calculation module is used to determine the maximum coal inventory and the minimum coal inventory from all coal inventory, and calculate the second coal inventory difference between the maximum coal inventory and the minimum coal inventory; The factor calculation module is used to calculate the coal inventory ratio of the coal inventory difference and the second coal inventory difference; The factor calculation module is used to obtain the first historical coal impact factor corresponding to the first prediction and analysis node, and obtain the adjacent historical coal impact factors corresponding to the adjacent prediction and analysis nodes; The factor calculation module is used to calculate the factor difference between the first historical coal impact factor and the adjacent historical coal impact factor; The factor calculation module is used to determine the maximum historical coal impact factor and the minimum historical coal impact factor from all historical coal impact factors, and calculate the second factor difference between the maximum historical coal impact factor and the minimum historical coal impact factor; The factor calculation module is used to calculate the factor ratio of the factor difference and the second factor difference; The factor calculation module is used to calculate the product value of the factor ratio and the coal inventory ratio, and use it as the first sub-coal inventory prediction factor; The factor calculation module is used to process the remaining prediction analysis nodes to obtain a plurality of first sub-coal inventory prediction factors; The factor calculation module is used to calculate the mean of all first sub-coal inventory prediction factors and use it as the second sub-coal inventory prediction factor.

[0039] In this embodiment, the collection order is the above-mentioned forecast collection frequency, and the first forecast analysis node is the first collected historical inventory impact data.

[0040] In this embodiment, when processing the remaining prediction and analysis nodes, the third prediction and analysis node and the fourth prediction and analysis node are obtained, and the first sub-coal inventory prediction factor is calculated. The remaining prediction and analysis nodes are processed in the same way. If there is a single prediction and analysis node, this single prediction and analysis node is deleted.

[0041] The beneficial effect of the above technical solution is that the present invention can provide a prediction basis for the prediction of coal inventory and ensure the prediction accuracy by calculating the first sub-coal inventory prediction factor and the second sub-coal inventory prediction factor.

[0042] In some embodiments of the present application, the construction calculation module is used to: The construction calculation module is used to divide all first sub-coal inventory prediction factors that are greater than the second sub-coal inventory prediction factor into an upper factor set; The construction calculation module is used to divide all first sub-coal inventory prediction factors that are less than or equal to the second sub-coal inventory prediction factor into a lower factor set; The construction calculation module is used to calculate the upper difference between each first sub-coal inventory prediction factor and the second sub-coal inventory prediction factor in the upper factor set, and generate an upper difference value set based on the principle of numerical size; The construction calculation module is used to calculate the lower difference between each first sub-coal inventory prediction factor and the second sub-coal inventory prediction factor in the lower factor set, and generate a lower difference value set based on the principle of numerical size; The construction calculation module is used to match the upper difference value set and the lower difference value set in pairs to obtain multiple coal inventory prediction sets.

[0043] In this embodiment, the head upper difference in the upper difference set is the largest upper difference, the tail upper difference is the smallest upper difference, and the head lower difference in the lower difference set is the largest lower difference, and the tail lower difference is the smallest lower difference.

[0044] The beneficial effect of the above technical solution is: the present invention matches the upper difference set and the lower difference set in pairs to obtain multiple coal inventory prediction sets, realizes the accurate division of the first sub-coal inventory prediction factor, and lays the foundation for the calculation of the comprehensive coal inventory prediction factor.

[0045] In some embodiments of the present application, the construction calculation module is used to: The construction calculation module is used to calculate the comprehensive coal inventory prediction factor of the coal inventory prediction analysis chain according to the coal inventory prediction set; ; Among them, w is the comprehensive coal inventory forecast factor of the coal inventory forecast analysis chain, n is the number of coal inventory forecast sets, k1i is the upper difference in the i-th coal inventory forecast set, k2 i is the lower difference value in the i-th coal inventory forecast set, For all The minimum value in For all The maximum value in g 2 For all The variance of .

[0046] In some embodiments of the present application, the inventory forecasting module is used to: The inventory prediction module is used to determine whether it is necessary to manage the current coal inventory of the coal warehouse to be predicted according to the relationship between the comprehensive coal inventory prediction factor and the preset comprehensive coal inventory prediction factor; The inventory forecasting module is used to determine that it is not necessary to manage the current coal inventory of the coal warehouse to be forecasted when the comprehensive coal inventory forecasting factor is greater than or equal to the preset comprehensive coal inventory forecasting factor; The inventory forecasting module is used to determine that the current coal inventory of the coal warehouse to be forecasted needs to be managed when the comprehensive coal inventory forecasting factor is less than the preset comprehensive coal inventory forecasting factor.

[0047] In this embodiment, the preset comprehensive coal inventory prediction factor is derived based on historical data and is predicted and determined by combining time series analysis and machine learning algorithms. It is preferably 8.5 here and can be adjusted according to actual conditions.

[0048] The beneficial effect of the above technical solution is: the present invention determines whether it is necessary to manage the current coal inventory of the coal warehouse to be predicted based on the relationship between the comprehensive coal inventory prediction factor and the preset comprehensive coal inventory prediction factor, thereby realizing accurate and convenient coal inventory prediction, avoiding the judgment errors existing in manual participation, and avoiding the subjective judgment caused by manual experience.

[0049] In some embodiments of the present application, the inventory forecasting module is used to: The inventory prediction module is used to calculate the comprehensive coal inventory prediction factor difference value between the preset comprehensive coal inventory prediction factor and the comprehensive coal inventory prediction factor; The inventory forecasting module is used to select a corresponding management coefficient according to the relationship between the comprehensive coal inventory forecasting factor difference value and a plurality of preset difference values; The inventory forecasting module is used to calculate the product value of the management coefficient and the current coal inventory and use it as the target coal inventory of the coal warehouse to be forecasted; The inventory prediction module is used to determine the amount of coal stored in the coal warehouse to be predicted based on the target coal inventory and the current coal inventory.

[0050] In this embodiment, the comprehensive coal inventory prediction factor difference value = the preset comprehensive coal inventory prediction factor - the comprehensive coal inventory prediction factor, that is, the difference between the two.

[0051] In this embodiment, the preset difference value includes a first preset difference value and a second preset difference value, and the first preset difference value is preferably 4.5, and the second preset difference value is preferably 6.5.

[0052] In this embodiment, the management coefficient includes a first preset management coefficient, a second preset management coefficient and a third preset management coefficient, and the first preset management coefficient is preferably 1.15, the second preset management coefficient is preferably 1.25, and the third preset management coefficient is preferably 1.35.

[0053] In this embodiment, when the difference value of the comprehensive coal inventory prediction factor is less than the first preset difference value, the first preset management coefficient is selected; when the difference value of the comprehensive coal inventory prediction factor is greater than or equal to the first preset difference value and less than the second preset difference value, the second preset management coefficient is selected; when the difference value of the comprehensive coal inventory prediction factor is greater than or equal to the second preset difference value, the third preset management coefficient is selected.

[0054] In this embodiment, the target coal inventory cannot exceed the maximum coal storage capacity of the coal warehouse to be predicted.

[0055] In this embodiment, the difference between the target coal inventory and the current coal inventory is calculated, that is, the coal inventory of the coal warehouse to be predicted is obtained.

[0056] The beneficial effects of the above technical solution are: realizing intelligent prediction of coal inventory, improving the accuracy of coal prediction, and matching inventory levels with actual demand, which can not only avoid coal waste but also ensure the stability and continuity of coal supply.

[0057] In the description of the above embodiments, specific features, structures, materials or characteristics may be combined in a suitable manner in any one or more embodiments or examples.

[0058] Although the present invention has been described above with reference to the embodiments, various modifications may be made thereto and parts thereof may be replaced with equivalents without departing from the scope of the present invention. In particular, as long as there is no structural conflict, the various features in the embodiments disclosed by the present invention may be used in combination with each other in any manner, and the fact that these combinations are not fully described in this specification is only for the sake of omitting space and saving resources.

[0059] Those skilled in the art can understand that the above are only preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions recorded in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An intelligent forecasting and management system for coal inventory in a power plant, characterized in that: include: A collection and construction module is used to determine a coal warehouse to be predicted, collect multiple historical inventory impact data and coal inventory of the coal warehouse to be predicted at a preset time period as a collection frequency, and construct a coal inventory forecasting and analysis chain based on the historical inventory impact data and the coal inventory, wherein the coal inventory forecasting and analysis chain includes multiple forecasting and analysis nodes and connection chains, and each forecasting and analysis node corresponds to multiple historical inventory impact data and coal inventory; A classification calculation module, used to calculate the historical average inventory impact data corresponding to the multiple historical inventory impact data, classify the multiple historical inventory impact data of each forecast analysis node based on the historical average inventory impact data, and calculate the historical coal impact factor of each forecast analysis node based on the classification result; A factor calculation module, used for calculating the first sub-coal inventory prediction factor and the second sub-coal inventory prediction factor of the coal inventory prediction analysis chain according to all historical coal influencing factors and the coal inventory corresponding to each prediction analysis node; Constructing a calculation module, which is used to construct a plurality of coal inventory prediction sets based on the first sub-coal inventory prediction factor and the second sub-coal inventory prediction factor, and calculating a comprehensive coal inventory prediction factor of the coal inventory prediction analysis chain according to the coal inventory prediction sets; The inventory forecasting module is used to determine whether it is necessary to manage the current coal inventory of the coal warehouse to be predicted based on the comprehensive coal inventory forecasting factor, and if so, determine the amount of coal to be stored based on the comprehensive coal inventory forecasting factor.

2. The intelligent forecasting and management system for coal inventory in power plants according to claim 1 is characterized in that: The classification calculation module is used for: The classification calculation module is used to classify all historical inventory impact data that are smaller than the historical average inventory impact data in each forecast analysis node into a first classification data set; The classification calculation module is used to classify all historical inventory impact data equal to the historical average inventory impact data into a second classification data set; The classification calculation module is used to classify all historical inventory impact data greater than the historical average inventory impact data into a third classification data set; The classification calculation module is used to perform normalization processing on the first classification data set to obtain a corresponding first normalized data set; The classification calculation module is used to perform normalization processing on the second classification data set to obtain a corresponding second normalized data set; The classification calculation module is used to perform normalization processing on the third classification data set to obtain a corresponding third normalized data set; The classification calculation module is used to calculate a first classification calculation value and a second classification calculation value of the first normalized data set based on a preset calculation method; The classification calculation module is used to determine a data classification range according to the first classification calculation value and the second classification calculation value, wherein the data classification range includes a left boundary data value and a right boundary data value, and the left boundary data value is smaller than the right boundary data value; The classification calculation module is used to generate a first to-be-calculated mark for all normalized values ​​in the first normalized data set that are greater than the left boundary data value and less than the right boundary data value.

3. The intelligent forecasting and management system for coal inventory in power plants according to claim 2 is characterized in that: The classification calculation module is used for: The classification calculation module is used to calculate the third classification calculation value and the fourth classification calculation value of the second normalized data set based on a preset calculation method; The classification calculation module is used to determine a second data classification range according to the third classification calculation value and the fourth classification calculation value, wherein the second data classification range includes a second left boundary data value and a second right boundary data value, and the second left boundary data value is smaller than the second right boundary data value; The classification calculation module is used to generate a second to-be-calculated mark for all normalized values ​​in the second normalized data set that are greater than the second left boundary data value and less than the second right boundary data value; The classification calculation module is used to calculate the fifth classification calculation value and the sixth classification calculation value of the third normalized data set based on a preset calculation method; The classification calculation module is used to determine a third data classification range according to the fifth classification calculation value and the sixth classification calculation value, wherein the third data classification range includes a third left boundary data value and a third right boundary data value, and the third left boundary data value is smaller than the third right boundary data value; The classification calculation module is used to generate a third to-be-calculated mark for all normalized values ​​in the third normalized data set that are greater than the third left boundary data value and less than the third right boundary data value; The classification calculation module is used to calculate the historical coal impact factor of each prediction analysis node according to the first mark to be calculated, the second mark to be calculated and the third mark to be calculated.

4. The power plant coal inventory intelligent forecasting and management system according to claim 3 is characterized in that: The classification calculation module is used for: The classification calculation module is used to configure a first calculation coefficient for the first mark to be calculated, configure a second calculation coefficient for the second mark to be calculated, and configure a third calculation coefficient for the third mark to be calculated; The classification calculation module is used to count the number of the first to-be-calculated marks, count the number of the second to-be-calculated marks, and count the number of the third to-be-calculated marks; The classification calculation module is used to calculate the historical coal impact factor of each prediction analysis node according to the following formula: ； Among them, d is the historical coal impact factor, e1 is the first calculation coefficient, e2 is the second calculation coefficient, e3 is the third calculation coefficient, f1 is the number of first marks to be calculated, f2 is the number of second marks to be calculated, f3 is the number of third marks to be calculated, and e1>e2>e3, e1>0, e2>0, e3>0.

5. The power plant coal inventory intelligent forecasting and management system according to claim 1 is characterized in that: The factor calculation module is used for: The factor calculation module is used to determine the first prediction analysis node and the adjacent prediction analysis nodes based on the acquisition order, and obtain the corresponding first coal inventory and the adjacent coal inventory; The factor calculation module is used to calculate the coal inventory difference between the first coal inventory and the adjacent coal inventory; The factor calculation module is used to determine the maximum coal inventory and the minimum coal inventory from all coal inventory, and calculate the second coal inventory difference between the maximum coal inventory and the minimum coal inventory; The factor calculation module is used to calculate the coal inventory ratio of the coal inventory difference and the second coal inventory difference; The factor calculation module is used to obtain the first historical coal impact factor corresponding to the first prediction and analysis node, and obtain the adjacent historical coal impact factors corresponding to the adjacent prediction and analysis nodes; The factor calculation module is used to calculate the factor difference between the first historical coal impact factor and the adjacent historical coal impact factor; The factor calculation module is used to determine the maximum historical coal impact factor and the minimum historical coal impact factor from all historical coal impact factors, and calculate the second factor difference between the maximum historical coal impact factor and the minimum historical coal impact factor; The factor calculation module is used to calculate the factor ratio of the factor difference and the second factor difference; The factor calculation module is used to calculate the product value of the factor ratio and the coal inventory ratio, and use it as the first sub-coal inventory prediction factor; The factor calculation module is used to process the remaining prediction analysis nodes to obtain a plurality of first sub-coal inventory prediction factors; The factor calculation module is used to calculate the mean of all first sub-coal inventory prediction factors and use it as the second sub-coal inventory prediction factor.

6. The power plant coal inventory intelligent forecasting and management system according to claim 1 is characterized in that: The construction calculation module is used to: The construction calculation module is used to divide all first sub-coal inventory prediction factors that are greater than the second sub-coal inventory prediction factor into an upper factor set; The construction calculation module is used to divide all first sub-coal inventory prediction factors that are less than or equal to the second sub-coal inventory prediction factor into a lower factor set; The construction calculation module is used to calculate the upper difference between each first sub-coal inventory prediction factor and the second sub-coal inventory prediction factor in the upper factor set, and generate an upper difference value set based on the principle of numerical size; The construction calculation module is used to calculate the lower difference between each first sub-coal inventory prediction factor and the second sub-coal inventory prediction factor in the lower factor set, and generate a lower difference value set based on the principle of numerical size; The construction calculation module is used to match the upper difference value set and the lower difference value set in pairs to obtain multiple coal inventory prediction sets.

7. The power plant coal inventory intelligent forecasting and management system according to claim 6 is characterized in that: The construction calculation module is used to: The construction calculation module is used to calculate the comprehensive coal inventory prediction factor of the coal inventory prediction analysis chain according to the coal inventory prediction set; ； Among them, w is the comprehensive coal inventory forecast factor of the coal inventory forecast analysis chain, n is the number of coal inventory forecast sets, k1 i is the upper difference in the i-th coal inventory forecast set, k2 i is the lower difference value in the i-th coal inventory forecast set, For all The minimum value in For all The maximum value in g 2 For all The variance of .

8. The power plant coal inventory intelligent forecasting and management system according to claim 1, characterized in that: The inventory forecasting module is used to: The inventory prediction module is used to determine whether it is necessary to manage the current coal inventory of the coal warehouse to be predicted according to the relationship between the comprehensive coal inventory prediction factor and the preset comprehensive coal inventory prediction factor; The inventory forecasting module is used to determine that it is not necessary to manage the current coal inventory of the coal warehouse to be forecasted when the comprehensive coal inventory forecasting factor is greater than or equal to the preset comprehensive coal inventory forecasting factor; The inventory forecasting module is used to determine that the current coal inventory of the coal warehouse to be forecasted needs to be managed when the comprehensive coal inventory forecasting factor is less than the preset comprehensive coal inventory forecasting factor.

9. The intelligent forecasting and management system for coal inventory in power plants according to claim 8, characterized in that: The inventory forecasting module is used to: The inventory prediction module is used to calculate the comprehensive coal inventory prediction factor difference value between the preset comprehensive coal inventory prediction factor and the comprehensive coal inventory prediction factor; The inventory forecasting module is used to select a corresponding management coefficient according to the relationship between the comprehensive coal inventory forecasting factor difference value and a plurality of preset difference values; The inventory forecasting module is used to calculate the product value of the management coefficient and the current coal inventory and use it as the target coal inventory of the coal warehouse to be forecasted; The inventory prediction module is used to determine the amount of coal entering the coal warehouse to be predicted based on the target coal inventory and the current coal inventory.

Images