Coal warehouse inventory prediction method and device, electronic equipment and storage medium

Abstract

The present application relates to the technical field of inventory forecasting, and discloses a coal bunker inventory forecasting method and device, an electronic device and a storage medium, the method comprises the following steps: obtaining storage coal data corresponding to a target coal bunker, the storage coal data comprising height monitoring data and weight monitoring data of a coal pile in the target coal bunker, constructing a height probability density function of the coal pile according to the height monitoring data, and constructing a weight probability density function of the coal pile according to the weight monitoring data; fusing the height probability density function and the weight probability density function to construct an optimization model; taking the maximum fused probability density as an optimization target, solving the optimization model according to a preset constraint condition, and obtaining an output result; and forecasting the inventory of the target coal bunker according to the output result. The height monitoring data and the weight monitoring data of the coal pile are fused in a multi-signal fusion manner, thereby realizing accurate forecasting of the coal bunker inventory.

Description

Technical Field

[0001] This invention relates to the field of inventory forecasting technology, and in particular to a method, apparatus, electronic device, and storage medium for forecasting coal warehouse inventory. Background Technology

[0002] The coking industry currently faces problems such as overcapacity, excessive emissions, and low energy utilization, which severely restrict its development. Therefore, it is imperative to promote refined management and digital transformation of coking enterprises, including accurate forecasting of coal warehouse inventory.

[0003] In related technologies, some enterprises calculate coal warehouse inventory by accumulating the weight data from belt scales used for coal return and transportation. However, belt scales have inherent weighing errors during operation, and these errors accumulate over time, causing discrepancies between actual inventory and accumulated weight data. Other enterprises calculate coal volume and predict inventory by using the average height data from multiple level gauges and the cross-sectional area of ​​the coal bunker. However, the large cross-sectional area inside the coal bunker and the limited number of measurable points by level gauges, coupled with irregular coal pile shapes, result in significant discrepancies between the obtained average height data and the actual height, affecting the accurate estimation of coal warehouse inventory. Therefore, considering only a single signal data point in the coal bunker, such as belt scale data or level gauge data, yields coal warehouse inventory estimates with substantial errors. Summary of the Invention

[0004] To provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. This summary is not intended as a general commentary, nor is it intended to identify key / important components or describe the scope of protection of these embodiments, but rather as a prelude to the detailed description that follows.

[0005] In view of the shortcomings of the prior art described above, the present invention discloses a coal warehouse inventory prediction method, device, electronic device and storage medium to improve the accuracy of coal warehouse inventory prediction.

[0006] This invention provides a method for predicting coal warehouse inventory, comprising: acquiring coal storage data corresponding to a target coal warehouse, the coal storage data including height monitoring data and weight monitoring data of the coal pile in the target coal warehouse; constructing a height probability density function of the coal pile based on the height monitoring data, and constructing a weight probability density function of the coal pile based on the weight monitoring data; fusing the height probability density function and the weight probability density function to construct an optimization model; solving the optimization model according to preset constraints with the maximum fused probability density as the optimization objective to obtain an output result; and predicting the inventory of the target coal warehouse based on the output result.

[0007] Optionally, the height monitoring data includes current height data at the current moment and historical height data at at least one historical moment, and the weight monitoring data includes the cumulative amount of coal returned and the cumulative weight of coal transported at each moment; the height probability density function and the weight probability density function are fused to construct an optimization model, including: constructing a current height probability density function of the coal pile based on the current height data, and constructing at least one historical height probability density function of the coal pile based on at least one historical height data; constructing at least one weight probability density function based on multiple cumulative weights of returned coal and multiple cumulative weights of transported coal; and fusing the current height probability density function, at least one historical height probability density function, and at least one weight probability density function to obtain the optimization model.

[0008] Optionally, the current height data includes multiple current height values, and the historical height data includes multiple historical height values. Constructing a current height probability density function for the coal pile based on the current height data, and constructing at least one historical height probability density function for the coal pile based on at least one historical height data, includes: calculating the multiple current height values ​​to obtain a current height mean, and calculating the multiple historical height values ​​corresponding to each historical height data to obtain at least one historical height mean; calculating the current height standard deviation based on the multiple current height values ​​and the current height mean, and calculating the multiple historical height values ​​corresponding to each historical height data with the historical height mean to obtain at least one historical height standard deviation; constructing the current height probability density function based on the current height mean and the current height standard deviation, and constructing at least one historical height probability density function based on at least one historical height mean and the corresponding historical height standard deviation.

[0009] Optionally, constructing at least one weight probability density function based on multiple cumulative coal return weights and multiple cumulative coal transport weights includes: obtaining a preset first precision error corresponding to a coal return belt scale and a second precision error corresponding to a coal transport belt scale; sorting multiple cumulative coal return weights and multiple cumulative coal transport weights according to the order of each time, calculating the difference between adjacent cumulative coal return weights to obtain at least one coal return weight difference, and calculating the difference between adjacent cumulative coal transport weights to obtain at least one coal return weight difference; calculating at least one standard coal return weight difference based on the first precision error for at least one coal return weight difference, and calculating at least one standard coal transport weight difference based on the second precision error for at least one coal transport weight difference; constructing at least one coal return weight probability density function based on at least one coal return weight difference and the corresponding standard coal return weight difference, and constructing at least one coal transport weight probability density function based on at least one coal transport weight difference and the corresponding standard coal transport weight difference; convolving the coal transport weight probability density function and the coal return weight probability density function corresponding to each time point to obtain at least one weight probability density function.

[0010] Optionally, the construction of the constraint conditions includes: sorting at least one historical height average and the current height average based on the order of each time, and calculating the difference between two adjacent different height averages to obtain the height difference of the coal pile between two adjacent time points; calculating the difference between each standard coal return weight difference and the corresponding standard coal transport weight difference to obtain the weight difference of the coal pile between two adjacent time points; establishing the correlation between the height difference and the weight difference between two adjacent time points; determining the current height maximum and current height minimum from multiple current height values, and determining the respective historical height maximum and historical height minimum from each historical height data; constructing the size relationship between the current height average, current height maximum, and current height minimum, and the size relationship between the historical height average, historical height maximum, and historical height minimum corresponding to each historical height data; and using each correlation relationship and each size relationship as the constraint conditions.

[0011] Optionally, establishing the correlation between the height difference and the weight difference between any two adjacent time points includes: obtaining the cross-sectional area corresponding to the target coal bunker and the density of the coal stored in the target coal bunker; constructing a weight function based on the coal surface height, the cross-sectional area, and the density; integrating the weight function with the coal pile height as a variable based on the average of two adjacent different heights to obtain the integral result; and obtaining the correlation based on the equality relationship between the integral result and the weight difference.

[0012] Optionally, the output results include height prediction values; predicting the inventory of the target coal bunker based on the output results includes: obtaining the cross-sectional area corresponding to the target coal bunker and the density of the coal type stored in the target coal bunker; constructing a weight function based on the coal surface height, the cross-sectional area, and the density; and integrating the weight function based on the height prediction value, using the coal pile height as a variable, to obtain the inventory of the target warehouse.

[0013] This invention provides a coal warehouse inventory prediction device, comprising: a construction module for acquiring coal storage data corresponding to a target coal warehouse, the coal storage data including height monitoring data and weight monitoring data of the coal pile in the target coal warehouse, constructing a height probability density function of the coal pile based on the height monitoring data, and constructing a weight probability density function of the coal pile based on the weight monitoring data; a fusion module for performing probability density fusion of the height probability density function and the weight probability density function to construct an optimization model; a solution module for solving the optimization model according to preset constraints with the maximum fused probability density as the optimization objective, and obtaining an output result; and a prediction module for predicting the inventory of the target coal warehouse based on the output result.

[0014] The present invention provides an electronic device, comprising: a processor and a memory; the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory to cause the electronic device to perform the above-described method.

[0015] The present invention provides a computer-readable storage medium having computer-readable instructions stored thereon, which, when executed by a computer's processor, cause the computer to perform the above-described method.

[0016] The beneficial effects of this invention are:

[0017] By acquiring height and weight monitoring data of coal piles in the target coal bunker, and constructing a height probability density function based on the height monitoring data and a weight probability density function based on the weight monitoring data, the probability density functions of the height and weight are then fused to build an optimization model. This optimization model integrates the height and weight data of the coal piles, constructing a multi-dimensional probability density function from a statistical analysis perspective. This transforms coal warehouse inventory prediction into model operation optimization. Furthermore, with the maximization of the fused probability density as the optimization objective, the optimization model is solved according to preset constraints. Under the condition that the fused probability function satisfies the constraints, the optimal output result is sought, thus ensuring the accuracy of the output result. Finally, based on the output result, the inventory of the target coal bunker is predicted, achieving accurate coal warehouse inventory prediction and providing a guarantee for the normal operation of the enterprise. Attached Figure Description

[0018] Figure 1 This is a flowchart illustrating a coal warehouse inventory prediction method in an embodiment of the present invention;

[0019] Figure 2 This is a flowchart illustrating another coal warehouse inventory prediction method in an embodiment of the present invention;

[0020] Figure 3 This is a schematic diagram of the structure of a coal warehouse inventory prediction device in an embodiment of the present invention;

[0021] Figure 4 This is a schematic diagram of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0022] The following specific examples illustrate the implementation of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that, unless otherwise specified, the following embodiments and sub-samples in the embodiments can be combined with each other.

[0023] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of the present invention. Therefore, the drawings only show the components related to the present invention and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0024] In the following description, numerous details are explored to provide a more thorough explanation of embodiments of the invention. However, it will be apparent to those skilled in the art that embodiments of the invention may be practiced without these specific details. In other embodiments, well-known structures and devices are shown in block diagram form rather than in detail to avoid obscuring embodiments of the invention.

[0025] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of this disclosure described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion.

[0026] Unless otherwise stated, the term "multiple" means two or more.

[0027] In this embodiment of the disclosure, the character " / " indicates that the objects before and after it are in an "or" relationship. For example, A / B means: A or B.

[0028] The term "and / or" describes an association between objects, indicating that three relationships can exist. For example, A and / or B means: A or B, or A and B.

[0029] Coal stored in the coal bunker is transported back to the bunker via conveyor equipment on top of the bunker; this process is called coal return. Simultaneously, the coal bunker also has conveyor equipment to remove coal; this process is called coal transport. Examples of conveyor equipment include coal conveyor corridors and coal conveyor bridges. Belt scales can be installed in the coal return and transport conveyor systems to obtain the weight of the returned and transported coal. It should be noted that the weight data from the belt scales is cumulative, and the total weight of coal in the bunker can be determined based on the weight data from both the return and transport belt scales.

[0030] In addition, the weight of coal in a coal bunker can also be obtained by installing level gauges in the bunker. This involves measuring the height of the coal pile using level gauges, and then calculating the weight by combining this with the cross-sectional area of ​​the bunker (i.e., the bottom area of ​​the coal pile) and the density of the coal. Generally, the cross-sectional area inside a coal bunker is large, and in cases where the coal surface is uneven, multiple level gauges are used to measure the coal surface at multiple points to obtain the average height for calculating the weight.

[0031] However, belt scales have errors during operation, and these errors accumulate over time. Level gauges can only measure a limited number of points, and the coal pile height is inaccurate. All of these factors contribute to discrepancies between actual and predicted inventory. Since coal warehouse inventory plays a crucial role in the overcapacity and energy utilization of the coking industry, accurate prediction of coal warehouse inventory is extremely important.

[0032] Please see Figure 1 This disclosure provides a method for predicting coal warehouse inventory, including:

[0033] Step S101: Obtain the coal storage data corresponding to the target coal bunker. The coal storage data includes the height monitoring data and weight monitoring data of the coal pile in the target coal bunker. Construct the height probability density function of the coal pile based on the height monitoring data, and construct the weight probability density function of the coal pile based on the weight monitoring data.

[0034] Among them, height monitoring data can be obtained through level gauges, weight monitoring data can be obtained through coal return and coal conveyor belt scales, and coal storage data also includes coal quality data and coal unit price data in addition to height monitoring data and weight monitoring data.

[0035] Step S102: Perform probability density fusion on the height probability density function and the weight probability density function to construct an optimized model.

[0036] Step S103: With the maximum fusion probability density as the optimization objective, the optimization model is solved according to the preset constraints to obtain the output results.

[0037] Step S104: Predict the inventory of the target coal bunker based on the output results.

[0038] The coal warehouse inventory prediction method provided in this disclosure acquires height and weight monitoring data of the coal pile in the target coal warehouse. A height probability density function is constructed based on the height monitoring data, and a weight probability density function is constructed based on the weight monitoring data. The height and weight probability density functions are then fused to construct an optimization model. This optimization model integrates the height and weight data of the coal pile, constructing a multi-dimensional probability density function from a statistical analysis perspective. This transforms coal warehouse inventory prediction into model operation optimization. Furthermore, with the maximum fused probability density as the optimization objective, the optimization model is solved according to preset constraints. Under the condition that the fused probability function satisfies the constraints, the optimal output result is sought, thus ensuring the accuracy of the output result. Finally, the inventory of the target coal warehouse is predicted based on the output result, achieving accurate coal warehouse inventory prediction and providing a guarantee for the normal operation of the enterprise.

[0039] Optionally, the height monitoring data includes the current height data at the current moment and historical height data at at least one historical moment, and the weight monitoring data includes the cumulative amount of coal returned and the cumulative weight of coal transported at each moment; the height probability density function and the weight probability density function are fused to construct an optimization model, including: constructing the current height probability density function of the coal pile based on the current height data, and constructing at least one historical height probability density function of the coal pile based on at least one historical height data; constructing at least one weight probability density function based on multiple cumulative weights of returned coal and multiple cumulative weights of transported coal; and fusing the current height probability density function, at least one historical height probability density function, and at least one weight probability density function to obtain the optimization model.

[0040] In one embodiment, a height probability density function can be constructed based solely on the height monitoring data of the coal pile at the current moment, and a weight probability density function can be constructed based on the cumulative amount of coal returned and the cumulative weight of coal transported at the current moment. Then, probability density fusion and model solving are performed. However, considering that data from a single point in time is not representative, and that significant errors in the data at the current moment cannot be avoided, the probability density functions are constructed and fused using height and weight monitoring data from multiple points in time. This increases the accuracy of the optimized model's output.

[0041] It should be noted that at least one historical moment can be any one or more moments before the current moment, including the starting moment of the entire coal storage system. In the case where only a height probability density function is constructed based on the height monitoring data of the coal pile at the current moment, and a weight probability density function is constructed based on the cumulative quantity of coal returned and the cumulative weight of coal transported at the current moment, the historical moment is assumed to be the starting moment. In this case, the difference between the cumulative quantity of coal returned and the cumulative weight of coal transported can be considered as the coal storage inventory.

[0042] It should also be noted that the probability density function in the embodiments of this application can use the density function corresponding to a continuous probability distribution such as Gaussian distribution or exponential distribution.

[0043] Optionally, the current height data includes multiple current height values, and the historical height data includes multiple historical height values. Constructing a current height probability density function for the coal pile based on the current height data, and constructing at least one historical height probability density function for the coal pile based on at least one historical height data, includes: calculating the average current height for multiple current height values, and calculating the average historical height for each historical height data to obtain at least one historical height average; calculating the standard deviation of the current height based on multiple current height values ​​and the average current height, and calculating the standard deviation of the historical height for each historical height data to obtain at least one historical height standard deviation; constructing a current height probability density function based on the average current height and the standard deviation of the current height, and constructing at least one historical height probability density function based on the average historical height and the corresponding historical height standard deviation.

[0044] In one embodiment, the current height probability density function refers to the probability density function corresponding to the average coal pile height at the current moment, and the historical height probability density function refers to the probability density function corresponding to the average coal pile height at historical moments. Furthermore, the multiple current height values ​​in the current height data are obtained through monitoring by multiple level gauges, and the multiple historical height values ​​in the historical height data are also obtained through monitoring by multiple level gauges. By establishing the height probability density function based on the average coal pile height at each moment, the predicted height value in the output of the optimized model includes the predicted value of the current average height and the predicted value of the historical average height.

[0045] Taking the Gaussian distribution as an example, suppose we establish an altitude probability density function using altitude monitoring data from the current time and a historical time. Let the historical time be denoted as time T1, the current time as time T2, the multiple historical altitude data points at time T1 as altitude data set HT1, and the multiple current altitude data points at time T2 as altitude data set HT2. Then the historical altitude probability density function corresponding to time T1 is:

[0046]

[0047] Where f(h1) represents the historical altitude probability density function at time T1; h1 represents the mean altitude at time T1, as an unknown variable; HM T1 Let σ1 represent the mean of the altitude dataset HT1; σ1 represent the standard deviation of the altitude dataset HT1. The probability density function for the current altitude at time T2 is:

[0048]

[0049] Where f(h2) represents the probability density function of the current altitude at time T2; h2 represents the mean altitude at time T2, as an unknown variable; HM T2 σ² represents the mean of the altitude dataset HT2; σ² represents the standard deviation of the altitude dataset HT2.

[0050] It should be noted that, from a statistical analysis perspective, the average height of the coal pile in the coal bunker satisfies a Gaussian probability density function, with its mean being the average of multiple level gauge data and its variance being the variance of multiple level gauge data; from an empirical analysis perspective, the actual height distribution can be expressed as a specific probability distribution model according to experience, and the model can be selected based on the actual situation.

[0051] Optionally, at least one weight probability density function is constructed based on multiple cumulative coal return weights and multiple cumulative coal transport weights, including: obtaining a preset first precision error corresponding to the coal return belt scale and a second precision error corresponding to the coal transport belt scale; sorting the multiple cumulative coal return weights and multiple cumulative coal transport weights according to the order of each time, calculating the difference between adjacent cumulative coal return weights to obtain at least one coal return weight difference, and calculating the difference between adjacent cumulative coal transport weights to obtain at least one coal return weight difference; calculating at least one standard coal return weight difference based on the first precision error, and calculating at least one standard coal transport weight difference based on the second precision error; constructing at least one coal return weight probability density function based on at least one coal return weight difference and the corresponding standard coal return weight difference, and constructing at least one coal transport weight probability density function based on at least one coal transport weight difference and the corresponding standard coal transport weight difference; convolving the coal transport weight probability density function and the coal return weight probability density function corresponding to each time point to obtain at least one weight probability density function.

[0052] In this embodiment, the first precision error and the second precision error are set based on experience, and can be specific proportional coefficients, error formulas, etc. The difference in coal return weight and the first precision error between two time points are calculated, as well as the difference in coal transport weight and the second precision error between two time points. In this way, the actual difference in coal return weight and the actual difference in coal transport weight between two time points can be obtained, eliminating the problem of inaccurate coal return weight and coal transport weight caused by belt scale operation error.

[0053] It should be noted that the weight probability density function refers to the probability density function of the net coal weight entering the coal bunker between two time points. It is obtained by convolving the return coal weight probability density function corresponding to the difference in return coal weight between the two time points and the transportation coal weight probability density function corresponding to the difference in transportation coal weight.

[0054] Continuing with the Gaussian distribution example, let's assume we establish a weight probability density function using weight monitoring data from the current time and a historical time. Here, the current time is the same as the current period in the exemplary description of the height probability density function above, and the historical time is also the same. Therefore, let's denote the historical time as time T1 and the current time as time T2. Then, the coal return weight probability density function between time T1 and T2 is:

[0055]

[0056] Where, f(w) o ) represents the probability density function of coal weight during time intervals T1-T2; w o The weight of the returned coal between time points T1 and T2 is represented as an unknown variable; WO represents the difference in the weight of the returned coal corresponding to the conveyor belt scale between time points T1 and T2; σ wo This represents the difference in standard coal weight between the coal return belt scale and time T1-T2.

[0057] The formula for calculating the standard return coal weight difference is:

[0058] σ wo =WO×e o Equation (4)

[0059] Where, σ wo WO represents the difference in standard coal weight between the T1 and T2 time points corresponding to the return coal belt scales; e represents the difference in return coal weight between the T1 and T2 time points corresponding to the return coal belt scales. o This indicates the first accuracy error corresponding to the coal return belt scale.

[0060] The probability density function of coal weight during time intervals T1-T2 is:

[0061]

[0062] Where, f(w) i) represents the probability density function of coal transport weight during time intervals T1-T2; w i The weight of coal transported between time points T1 and T2 is represented as an unknown variable; WI represents the difference in coal transport weight corresponding to the conveyor scale between time points T1 and T2; σ wo This represents the difference in standard coal transport weight between time points T1 and T2 corresponding to the belt scale.

[0063] The formula for calculating the standard coal transport weight difference is:

[0064] σ wi =WI×e i Equation (6)

[0065] Where, σ wi The difference in standard coal transport weight between time points T1 and T2 is represented by WI; e represents the difference in standard coal transport weight between time points T1 and T2. i This indicates the second precision error corresponding to the coal conveyor belt scale.

[0066] It should be noted that, from a statistical analysis perspective, the weight of coal transported and returned within a coal bunker over a period of time satisfies a Gaussian probability density function, with its mean being the incremental data of the belt scale (i.e., the difference in the weight of coal transported between two time points), and its variance being the belt scale increment × belt scale error. From an empirical analysis perspective, the actual weight distribution can be expressed as a specific probability distribution model based on experience, and the appropriate model can be selected according to the actual situation.

[0067] The weight probability density function corresponding to the net weight of coal entering the coal bunker between time points T1 and T2 is:

[0068] f(Δw 12 )=f(w i )*f(w o Equation (7)

[0069] That is, f(w) i ) and f(w o The convolution function of ).

[0070] At this point, the fusion probability function is:

[0071] F 12 = f(h1)×f(h2)×f(Δw) 12 Equation (8)

[0072] The optimization objective is max(F) 12 ).

[0073] Similarly, when acquiring altitude and weight monitoring data at n time points (where the nth time point is the current time point + (n-1) times are historical times), the constructed fusion probability function is:

[0074] F 1n =f(h1)×f(Δw) 12 )×f(h2)×f(Δw 23 )×f(h3)×…×f(h n-1 )×f(Δw (n-1)n )×f(h n Equation (9)

[0075] The optimization objective is max(F) 1n ).

[0076] In one embodiment, the constraints of the optimization model include the relationship between the mean height, maximum height, and minimum height corresponding to the height data set at each time point (current time + historical time), and the relationship between the difference in coal pile height and the difference in coal pile weight between every two adjacent time points.

[0077] Optionally, the construction of constraints includes: sorting at least one historical height average and the current height average based on the order of each time point, and calculating the difference between two adjacent different height averages to obtain the height difference of the coal pile between two adjacent time points; calculating the difference between each standard return coal weight difference and the corresponding standard transport coal weight difference to obtain the weight difference of the coal pile between two adjacent time points; establishing the correlation between the height difference and weight difference between two adjacent time points; determining the current height maximum and current height minimum from multiple current height values, and determining the respective historical height maximum and historical height minimum from each historical height data; constructing the size relationship between the current height average, current height maximum, and current height minimum, as well as the size relationship between the historical height average, historical height maximum, and historical height minimum corresponding to each historical height data; and using each correlation relationship and each size relationship as a constraint condition.

[0078] In this embodiment, continuing to use times T1 and T2 as examples, the relationship between the mean height, maximum height, and minimum height of the height data set corresponding to each time point (current time + historical time) is constrained as follows:

[0079] min(HT1)≤h1≤max(HT1) Formula (10)

[0080] min(HT2)≤h2≤max(HT2) Equation (11)

[0081] Wherein, min(HT1) represents the minimum value in the altitude data set HT1 composed of multiple historical altitude data at time T1; h1 represents the mean value in the altitude data set HT1; max(HT1) represents the maximum value in the altitude data set HT1; min(HT2) represents the minimum value in the altitude data set HT2 composed of multiple current altitude data at time T2; h2 represents the mean value in the altitude data set HT2; and max(HT2) represents the maximum value in the altitude data set HT2.

[0082] Optionally, a correlation between the height difference and weight difference between any two adjacent time points can be established, including: obtaining the cross-sectional area of ​​the target coal bunker and the density of the coal stored in the target coal bunker; constructing a weight function based on the coal surface height, cross-sectional area, and density; integrating the weight function with the coal pile height as a variable based on the average of two adjacent different heights to obtain the integral result; and obtaining the correlation based on the equality relationship between the integral result and the weight difference.

[0083] In this embodiment, the weight function is:

[0084] W = S × D × h (Equation 12)

[0085] Where W represents the weight of the coal pile; S represents the cross-sectional area; D represents the density; and h represents the height of the coal pile.

[0086] Continuing with the example of times T1 and T2, we establish the correlation between the height difference and weight difference of the coal pile between T1 and T2. Using the height of the coal pile as the variable, we integrate the weight function based on the average heights at times T1 and T2. The integral result equals the weight difference of the coal pile between T1 and T2. Therefore, the correlation is as follows:

[0087]

[0088] Where S represents the cross-sectional area; D represents the density; Δw 12 h1 represents the weight difference of the coal pile between times T1 and T2; h2 represents the average height of the coal pile at time T1; h3 represents the average height of the coal pile at time T2.

[0089] Additionally, Δw 12 The difference is calculated based on the difference between the standard coal return weight at times T1 and T2 and the corresponding difference between the standard coal transport weight at times T1 and T2. The difference may be positive or negative.

[0090] Furthermore, when acquiring altitude and weight monitoring data at n time points (the nth time point being the current time point + (n-1) times point being historical times), the constraints of the constructed fusion probability function (see equation (9)) include:

[0091] min(HT1)≤h1≤max(HT1)

[0092] min(HT2)≤h2≤max(HT2)

[0093] ...

[0094] min(HTn)≤h n ≤max(HTn)

[0095]

[0096]

[0097] ...

[0098]

[0099] That is, the relationship between the mean height, maximum height and minimum height of the height monitoring dataset at each time point, and the correlation between the height difference and weight difference between two adjacent time points.

[0100] In this embodiment, the output includes the predicted height at each time point and the predicted weight difference between every two time points. Taking times T1 and T2 as an example, the output would be h1, h2, and Δw. 12 .

[0101] It should be noted that when T1 is the starting time and T2 is the current time, h1 can be considered to be 0, then Δw 12 This represents the inventory level of the target coal bunker. At this point, h2 represents the current height of the coal pile. Alternatively, the inventory level of the target coal bunker can be calculated based on h2, cross-sectional area, and density.

[0102] Furthermore, at n time points (where the nth time point is the current time point + (n-1) times point is a historical time point), the output results are h1, h2...h n Δw 12 Δw 23 …Δw (n-1)n At this point, it can be determined based on h. n Calculate the current inventory level in the target coal bunker. Depending on specific needs, the inventory level at corresponding historical moments can also be calculated based on h1, h2, etc. Additionally, Δw can be used... 12 Δw 23 …Δw (n-1)n The positive and negative values ​​of these parameters are used to determine the coal transportation and return situation for each period, in order to guide the rational planning of the coal storage system.

[0103] Optionally, the output includes a height prediction value; based on the output, the inventory of the target coal bunker is predicted, including: obtaining the cross-sectional area of ​​the target coal bunker and the density of the coal stored in the target coal bunker; constructing a weight function based on the coal surface height, cross-sectional area, and density; and integrating the weight function based on the height prediction value with the coal pile height as a variable to obtain the inventory of the target warehouse.

[0104] As one possible implementation, the height prediction value here is the height prediction value at the current time, where the weight function is shown in equation (12). If we continue to take T1 and T2 as examples, the height prediction value is h2. Taking the coal pile height as a variable, the integral formula for integrating the weight function based on the height prediction value is:

[0105]

[0106] This means obtaining the inventory of the target coal bunker at time T2.

[0107] In one possible embodiment, with the goal of maximizing the fusion probability density, the optimization model is solved according to preset constraints, including: setting the population size, gene encoding method, selection, crossover, and mutation strategies, and termination conditions for the optimization algorithm; randomly generating a set of solutions, each of which includes the average height at multiple time points and the weight difference between every two time points; calculating the fitness value of each solution, where a higher fitness value indicates a solution closer to the optimal solution; performing a selection operation based on the fitness value, selecting target solutions with fitness values ​​higher than a first preset threshold to enter the next generation; performing crossover and mutation operations on the target solutions to generate new solutions; determining whether the new solutions meet the preset constraints, and if not, correcting or discarding them; forming a new generation of population with the new solutions after selection, crossover, mutation, and constraint checks, and repeating the above process until a preset termination condition is reached, such as the maximum number of iterations or the fitness value of the optimal solution reaching a second preset threshold, at which point the output solution is the optimal solution, where the average height at multiple time points and the weight difference between every two time points maximize the fusion probability density.

[0108] It should be noted that the embodiments of this application do not limit the solution method of the optimization model. The solution method can be genetic algorithm, particle swarm optimization algorithm, simulated annealing algorithm, etc.

[0109] In one exemplary embodiment, please refer to Figure 2 , Figure 2 This is a flowchart illustrating another coal warehouse inventory prediction method in an embodiment of the present invention. Figure 2 As shown, the entire process of the coal warehouse inventory prediction method corresponding to times T1 and T2 includes at least the following steps:

[0110] Step S201: Input the height dataset HT1 corresponding to multiple level gauges at time T1, the height dataset HT2 corresponding to multiple level gauges at time T2, the coal transport weight WI between time T1 and time T2, and the coal return weight WO between time T1 and time T2.

[0111] Step S202: Establish the probability density function f(h1) of the actual height of the coal pile in the coal bunker at time T1, the probability density function f(h2) of the actual height of the coal pile in the coal bunker at time T2, and the probability density function f(w) of the coal transport weight WI between times T1 and T2. i The probability density function f(w) is the weight of coal returned from the coal bunker between time T1 and T2. o );

[0112] Step S203: Construct an expression relating the height changes of h1 at time T1 and h2 at time T2 to the net weight of coal entering the silo, i.e., (h2-h1)×S×D=went (went is the aforementioned Δw) 12 And construct the probability density function of the net coal input weight between time T1 and T2, i.e., f(went) = f(w i )*f(w o f(went) is the same as f(Δw) mentioned above. 12 );

[0113] Step S204: Establish an optimization model with the maximum fusion probability as the objective function, i.e., max(f(went)×f(h1)×f(h2));

[0114] Step S205: Use the actual estimated limits (i.e., height size relationship) and the above relationship expression as constraints;

[0115] Step S206: Solve using a genetic algorithm;

[0116] In step S207, output h1, h2, and went, and then calculate the inventory quantity based on h2.

[0117] The coal warehouse inventory prediction method provided in this disclosure involves acquiring height and weight monitoring data of the coal pile in the target coal warehouse. A height probability density function is constructed based on the height monitoring data, and a weight probability density function is constructed based on the weight monitoring data. The height and weight probability density functions are then fused to construct an optimization model. The optimization objective is to maximize the fused probability density. The model is solved according to preset constraints to find the optimal output result. The inventory of the target coal warehouse is then predicted based on the output result.

[0118] First, it integrates the height and weight data of coal piles and constructs a multi-dimensional probability density function from a statistical analysis perspective. That is, it constructs a unified objective function for the corresponding data of height and weight signals, transforming coal warehouse inventory prediction into the operation and optimization of the model, thus ensuring the accuracy of coal warehouse inventory prediction.

[0119] Second, based on actual forecasting experience, reasonable constraints are preset. Under the condition that the fusion probability function meets the constraints, the optimal output result is sought, which ensures the accuracy of the output result and realizes accurate prediction of coal warehouse inventory, thus providing a guarantee for the normal operation of enterprises.

[0120] Combination Figure 3 As shown in the figure, this disclosure provides a coal warehouse inventory prediction device, which includes at least a construction module 301, a fusion module 302, a solution module 303, and a prediction module 304, as detailed below:

[0121] The construction module 301 is used to obtain the coal storage data corresponding to the target coal bunker. The coal storage data includes the height monitoring data and weight monitoring data of the coal pile in the target coal bunker. The height probability density function of the coal pile is constructed based on the height monitoring data, and the weight probability density function of the coal pile is constructed based on the weight monitoring data.

[0122] The fusion module 302 is used to perform probability density fusion on the height probability density function and the weight probability density function to build an optimization model;

[0123] The solver module 303 is used to solve the optimization model with the maximum fusion probability density as the optimization objective and according to the preset constraints to obtain the output results;

[0124] The prediction module 304 is used to predict the inventory of the target coal bunker based on the output results.

[0125] The coal warehouse inventory prediction device provided in this embodiment acquires height and weight monitoring data of the coal pile in the target coal warehouse. It constructs a height probability density function based on the height monitoring data and a weight probability density function based on the weight monitoring data. Then, it fuses the height and weight probability density functions to build an optimization model. This optimization model integrates the height and weight data of the coal pile, constructing a multi-dimensional probability density function from a statistical analysis perspective. This transforms coal warehouse inventory prediction into model operation optimization. Furthermore, it aims to maximize the fused probability density and solves the optimization model according to preset constraints. Under the condition that the fused probability function satisfies the constraints, it seeks the optimal output result, thus ensuring the accuracy of the output result. Finally, it predicts the inventory of the target coal warehouse based on the output result, achieving accurate coal warehouse inventory prediction and providing a guarantee for the normal operation of enterprises.

[0126] Figure 4 A schematic diagram of a computer system suitable for implementing the embodiments of this application is shown. It should be noted that... Figure 4 The computer system 400 of the electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0127] like Figure 4 As shown, the computer system 400 includes a Central Processing Unit (CPU) 401, which can perform various appropriate actions and processes, such as executing the methods described in the above embodiments, based on programs stored in Read-Only Memory (ROM) 402 or programs loaded from Storage Unit 408 into Random Access Memory (RAM) 403. The RAM 403 also stores various programs and data required for system operation. The CPU 401, ROM 402, and RAM 403 are interconnected via a bus 404. An Input / Output (I / O) interface 405 is also connected to the bus 404.

[0128] The following components are connected to I / O interface 405: an input section 406 including a keyboard, mouse, etc.; an output section 407 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 408 including a hard disk, etc.; and a communication section 409 including a network interface card such as a LAN (Local Area Network) card, modem, etc. The communication section 409 performs communication processing via a network such as the Internet. A drive 410 is also connected to I / O interface 405 as needed. A removable medium 411, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 410 as needed so that computer programs read from it can be installed into storage section 408 as needed.

[0129] Specifically, according to embodiments of this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program including a computer program for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 409, and / or installed from removable medium 411. When the computer program is executed by central processing unit (CPU) 401, it performs various functions defined in the system of this application.

[0130] It should be noted that the computer-readable medium shown in the embodiments of this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying a computer-readable computer program. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The computer program contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to wireless, wired, etc., or any suitable combination thereof.

[0131] The electronic device disclosed in this embodiment includes a processor, a memory, a transceiver, and a communication interface. The memory and the communication interface are connected to the processor and the transceiver and complete communication between them. The memory is used to store computer programs, the communication interface is used to perform communication, and the processor and the transceiver are used to run the computer programs, so that the electronic device performs the various steps of the above method.

[0132] In this embodiment, the memory may include random access memory (RAM) and may also include non-volatile memory, such as at least one disk storage device.

[0133] The processors mentioned above can be general-purpose processors, including central processing units (CPUs), graphics processing units (GPUs), network processors (NPs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0134] The foregoing description and accompanying drawings fully illustrate embodiments of this disclosure to enable those skilled in the art to practice them. Other embodiments may include structural, logical, electrical, procedural, and other changes. The embodiments represent only possible variations. Individual components and functions are optional unless explicitly required, and the order of operation may vary. Parts and subsamples of some embodiments may be included in or replace parts and subsamples of other embodiments. Moreover, the terminology used in this application is for describing embodiments only and is not intended to limit the claims. As used in the description of embodiments and claims, the singular forms “a,” “an,” and “the” are intended to equally include the plural forms unless the context clearly indicates otherwise. Similarly, the term “and / or” as used herein means including one or more of the associated listed items and all possible combinations thereof. Additionally, when used in this application, the term "comprise" and its variations "comprises" and / or "comprising" refer to the presence of stated subsamples, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other subsamples, wholes, steps, operations, elements, components, and / or groups thereof. Without further limitations, an element defined by the phrase "comprising a..." does not exclude the presence of other identical elements in the process, method, or apparatus that includes the element. In this document, each embodiment may focus on the differences from other embodiments, and similar or identical parts between embodiments can be referred to mutually. For methods, products, etc., disclosed in the embodiments, if they correspond to the method section disclosed in the embodiments, the relevant parts can be referred to the description of the method section.

[0135] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the embodiments of this disclosure. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0136] The methods and products (including but not limited to devices and equipment) disclosed in the embodiments herein can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For instance, the division of units may be merely a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some sub-samples may be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection of devices or units may be electrical, mechanical, or other forms. Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the units may be selected to implement this embodiment according to actual needs. Furthermore, the functional units in the embodiments of this disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0137] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to embodiments of the present disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than that shown in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. In the descriptions corresponding to the flowcharts and block diagrams in the accompanying drawings, the operations or steps corresponding to different blocks may also occur in a different order than disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. Each block in a block diagram and / or flowchart, and combinations of blocks in a block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

Claims

1. A method for predicting coal warehouse inventory, characterized in that, The method includes: Obtain coal storage data corresponding to the target coal bunker. The coal storage data includes height monitoring data and weight monitoring data of the coal pile in the target coal bunker. Construct a height probability density function of the coal pile based on the height monitoring data, and construct a weight probability density function of the coal pile based on the weight monitoring data. The height monitoring data includes the current height data at the current moment and historical height data at at least one historical moment. The weight monitoring data includes the cumulative weight of coal returned and the cumulative weight of coal transported at each moment. The probability density functions of height and weight are fused to construct an optimization model. Specifically, the following steps are taken: First, a current height probability density function for the coal pile is constructed based on the current height data; second, at least one historical height probability density function for the coal pile is constructed based on at least one historical height data. Third, at least one return coal weight probability density function is constructed based on at least one return coal weight difference and its corresponding standard return coal weight difference; fourth, at least one transport coal weight probability density function is constructed based on at least one transport coal weight difference and its corresponding standard transport coal weight difference. The transport coal weight probability density function and the return coal weight probability density function corresponding to a given time are convolved to obtain at least one weight probability density function. Finally, the current height probability density function, at least one historical height probability density function, and at least one weight probability density function are fused to obtain the optimized model. With the fusion probability density as the optimization objective, the optimization model is solved according to the preset constraints to obtain the output result; The inventory of the target coal bunker is predicted based on the output results.

2. The method according to claim 1, characterized in that, The current altitude data includes multiple current altitude values, and the historical altitude data includes multiple historical altitude values; Constructing a current height probability density function of the coal pile based on the current height data, and constructing at least one historical height probability density function of the coal pile based on at least one historical height data, including: The average current height is obtained by calculating multiple current height values, and at least one average historical height is obtained by calculating multiple historical height values ​​corresponding to each historical height data. The standard deviation of the current height is obtained by calculating multiple current height values ​​and the average current height, and at least one historical height standard deviation is obtained by calculating multiple historical height values ​​corresponding to each historical height data and the average historical height. The current altitude probability density function is constructed based on the current altitude mean and the current altitude standard deviation, and at least one historical altitude probability density function is constructed based on at least one historical altitude mean and the corresponding historical altitude standard deviation.

3. The method according to claim 2, characterized in that, The methods for determining the standard return coal weight difference and the standard transport coal weight difference include: Obtain the preset first precision error corresponding to the coal return belt scale and the second precision error corresponding to the coal conveying belt scale; Based on the order of each time point, the cumulative weights of multiple coal returns and multiple cumulative weights of multiple coal transports are sorted, the difference between adjacent cumulative weights of coal returns is calculated to obtain at least one difference in coal return weight, and the difference between adjacent cumulative weights of coal transport is calculated to obtain at least one difference in coal transport weight. The weight difference of at least one of the returned coals is calculated based on the first accuracy error to obtain at least one standard returned coal weight difference, and the weight difference of at least one of the transported coals is calculated based on the second accuracy error to obtain at least one standard transported coal weight difference.

4. The method according to claim 3, characterized in that, The construction of the constraints includes: Based on the order of each moment, at least one of the historical height averages and the current height averages are sorted, and the difference between two adjacent different height averages is calculated to obtain the height difference of the coal pile between each two adjacent moments. Calculate the difference between each standard return coal weight difference and the corresponding standard transport coal weight difference to obtain the weight difference of the coal pile between two adjacent time points; Establish the correlation between the height difference and the weight difference between any two adjacent time points; The maximum and minimum current height values ​​are determined from a plurality of the current height values, and the maximum and minimum historical height values ​​are determined from each of the historical height data. Construct the relationship between the current average height, the current maximum height, and the current minimum height, as well as the relationship between the historical average height, the historical maximum height, and the historical minimum height for each historical height data point; Each of the aforementioned relationships and each of the aforementioned size relationships shall be used as the constraint condition.

5. The method according to claim 4, characterized in that, Establishing the correlation between the height difference and the weight difference between any two adjacent time points includes: Obtain the cross-sectional area of ​​the target coal bunker and the density of the coal stored in the target coal bunker; A weight function is constructed based on the coal pile height, the cross-sectional area, and the density. Using the height of the coal pile as a variable, the weight function is integrated based on the average of two adjacent different heights to obtain the integral result; The correlation is obtained based on the equality relationship between the integral result and the weight difference.

6. The method according to any one of claims 1 to 5, characterized in that, The output includes a height prediction value; Based on the output results, the inventory of the target coal bunker is predicted, including: Obtain the cross-sectional area of ​​the target coal bunker and the density of the coal stored in the target coal bunker; A weight function is constructed based on the coal pile height, the cross-sectional area, and the density. Using the height of the coal pile as a variable, the weight function is integrated based on the predicted height value to obtain the inventory of the target coal bunker.

7. A coal warehouse inventory prediction device, characterized in that, The device includes: A construction module is used to acquire coal storage data corresponding to the target coal bunker. The coal storage data includes height monitoring data and weight monitoring data of the coal pile in the target coal bunker. A height probability density function of the coal pile is constructed based on the height monitoring data, and a weight probability density function of the coal pile is constructed based on the weight monitoring data. The height monitoring data includes the current height data at the current moment and historical height data at at least one historical moment. The weight monitoring data includes the cumulative weight of coal returned and the cumulative weight of coal transported at each moment. A fusion module is used to fuse the height probability density function and the weight probability density function to construct an optimization model. Specifically, it constructs a current height probability density function for the coal pile based on the current height data, and at least one historical height probability density function for the coal pile based on at least one historical height data point; it constructs at least one return coal weight probability density function based on at least one return coal weight difference and its corresponding standard return coal weight difference, and at least one transport coal weight probability density function based on at least one transport coal weight difference and its corresponding standard transport coal weight difference; it convolves the transport coal weight probability density function and the return coal weight probability density function corresponding to a given time point to obtain at least one weight probability density function; and it fuses the current height probability density function, at least one historical height probability density function, and at least one weight probability density function to obtain the optimization model. The solution module is used to solve the optimization model with the maximum fusion probability density as the optimization objective and according to the preset constraints to obtain the output results; The prediction module is used to predict the inventory of the target coal bunker based on the output results.

8. An electronic device, characterized in that, include: Processor and memory; The memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory to cause the electronic device to perform the method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, It stores computer-readable instructions that, when executed by the computer's processor, cause the computer to perform the method of any one of claims 1 to 6.

Images