A coal storage change monitoring method and system based on three-dimensional digital twinning

Abstract

The present application relates to the technical field of digital management, and a coal storage change monitoring method and system based on three-dimensional digital twinning, comprising: based on a pre-acquired coal storage time sequence and an initial coal storage yard acquired satellite image time sequence, one or more coal storage areas are identified using the satellite image time sequence, a regional coal storage type is acquired based on the coal storage area, a coal storage image set is acquired, a coal storage reconstruction model is acquired using the coal storage image set, the coal storage reconstruction model is divided based on the coal storage time sequence, a regional coal storage model set is obtained, a target calorific value influencing factor set is confirmed using the regional coal storage type, a calorific value equivalent database is confirmed, a target calorific value influencing parameter is acquired using the target calorific value influencing factor set and the regional coal storage model, a calorific value loss ratio is retrieved in the calorific value equivalent database using the target calorific value influencing parameter, and a coal storage equivalent model is constructed using the calorific value loss ratio. The present application can improve the accuracy of coal storage yard coal quantity change monitoring.

Description

Technical Field

[0001] This invention relates to the field of digital management technology, and in particular to a method and system for monitoring changes in coal reserves in coal storage yards based on three-dimensional digital twins. Background Technology

[0002] Coal, as one of my country's main energy sources, is widely used in various fields. If the coal stored in coal storage yards cannot be accurately assessed, it can lead to serious safety hazards. Therefore, accurately monitoring the coal reserves in coal storage yards is crucial for ensuring the safe and efficient operation of related facilities.

[0003] The methods used to monitor coal stored in coal storage yards largely rely on manual inventory and weighbridge methods.

[0004] Although the above methods can monitor the coal reserves in coal storage yards, they cannot update the coal reserves in the storage yards based on actual conditions during the monitoring process, and the monitoring results are inaccurate. Summary of the Invention

[0005] This invention provides a method for monitoring coal storage changes in coal storage yards based on three-dimensional digital twins and a computer-readable storage medium, the main purpose of which is to improve the accuracy of monitoring coal quantity changes in coal storage yards.

[0006] To achieve the above objectives, the present invention provides a method for monitoring coal reserve changes in a coal storage yard based on three-dimensional digital twins, comprising:

[0007] Receive a reserve monitoring instruction, and confirm the reserve monitoring environment based on the reserve monitoring instruction. The reserve monitoring environment includes the initial coal storage yard to be monitored and the reserve monitoring system. The reserve monitoring system includes an image acquisition unit, a parameter evaluation unit, a model reconstruction unit, and a result feedback unit.

[0008] Obtain the coal storage time series, and based on the coal storage time series and the initial coal storage yard, obtain satellite image time series. Use the satellite image time series to identify one or more coal storage areas, and perform the following operations on each of the one or more coal storage areas:

[0009] Based on the coal storage area, the regional coal storage type is obtained; based on the image acquisition unit and the coal storage area, a coal storage image set is obtained; and a coal storage reconstruction model is obtained using the model reconstruction unit and the coal storage image set.

[0010] Based on the coal storage time series, the coal storage reconstruction model is divided to obtain a set of regional coal storage models;

[0011] The set of factors influencing the target calorific value was identified by utilizing regional coal storage types, and the calorific value equivalent database was identified by utilizing regional coal storage types and parameter evaluation units.

[0012] For each regional coal storage model in the regional coal storage model set, the following operations are performed:

[0013] The target calorific value influencing parameters are obtained by using the target calorific value influencing factor set and regional coal storage model, and the calorific value loss ratio is retrieved from the calorific value equivalent database using the target calorific value influencing parameters.

[0014] A coal storage equivalent model is constructed using the calorific value loss ratio. The coal storage equivalent model and the coal storage reconstruction model are sent to the initiator of the storage monitoring command using the result feedback unit to realize the monitoring of coal storage.

[0015] Optionally, the step of using the satellite imagery to identify one or more coal storage areas in a time sequence includes:

[0016] Obtain an image segmentation model set for performing image segmentation on an image, wherein the image segmentation model set includes multiple image segmentation models;

[0017] For each satellite image in the satellite image time series, perform the following operations:

[0018] The satellite image is segmented using an image segmentation model set to obtain one or more initial segmented image sets. For each of the one or more initial segmented image sets, the following operations are performed:

[0019] Each initial segmented image in the initial segmented image set is mapped to a pre-constructed image coordinate system to obtain a mapped image;

[0020] The number of times each pixel is mapped in the mapped image is counted to obtain the reference mapping count;

[0021] Obtain the confidence score corresponding to each image segmentation model in the image segmentation model set to obtain a confidence score set, and calculate the minimum number of mappings based on the confidence score set;

[0022] The reference mapping count is compared with the minimum mapping count. If the reference mapping count is less than the minimum mapping count, the pixel is removed from the mapped image. The retained pixels are then summarized to obtain a filtered image. The region corresponding to the filtered image is taken as the recognition region. The recognition region corresponding to the last satellite image in the satellite image time series is taken as the coal storage region. The coal storage regions are summarized to obtain one or more coal storage regions.

[0023] Optionally, based on the coal storage time series, the coal storage reconstruction model is divided to obtain a regional coal storage model set, including:

[0024] Extract the coal storage time sequentially from the coal storage time series, and perform the following operations on each extracted coal storage time:

[0025] The current coal storage model is determined based on the coal storage time and satellite image time series.

[0026] The current coal storage model is iteratively updated to obtain an initial regional coal storage model. These initial regional coal storage models are then aggregated to obtain an initial regional coal storage model set. From this set, initial regional coal storage models are extracted sequentially, and the following operations are performed on each extracted model:

[0027] Obtain the coal storage volume of the initial regional coal storage model, compare the coal storage volume with a preset volume threshold, and if the coal storage volume is less than or equal to the volume threshold, then use the initial regional coal storage model to identify the set of neighboring coal storage models in the coal storage reconstruction model.

[0028] If the set of nearby coal storage models is not empty, then the following operation is performed on each nearby coal storage model in the set:

[0029] Calculate the absolute difference between the coal storage time corresponding to the initial regional coal storage model and the coal storage time corresponding to the adjacent coal storage model to obtain the absolute time difference value. Summarize the absolute time difference values ​​to obtain the absolute time difference value set.

[0030] Using the absolute time difference set, an initial coal storage model is identified in the set of adjacent coal storage models. The initial regional coal storage model is merged into the initial coal storage model to obtain an updated regional coal storage model. The updated regional coal storage model is used as the initial regional coal storage model. The step of obtaining the coal storage volume of the initial regional coal storage model is returned until the coal storage volume is greater than the volume threshold to obtain the regional coal storage model.

[0031] By summarizing the aforementioned regional coal storage models, a set of regional coal storage models is obtained.

[0032] Optionally, the step of identifying the set of factors influencing the target calorific value using regional coal storage types includes:

[0033] An initial factor set for assessing coal calorific value is obtained based on the regional coal storage type. The initial factor set includes multiple initial factors. The initial factors in the initial factor set are weighted using a pre-constructed principal component analysis method to obtain a set of weighted assessment values.

[0034] The weight evaluation values ​​in the weight evaluation value set are sorted in descending order to obtain the initial weight evaluation value sequence;

[0035] Using a preset initial extraction value, a target weight evaluation sequence is extracted from the initial weight evaluation value sequence, wherein the initial extraction value is 1, and the target weight evaluation sequence includes one or more target weight evaluation values, and the number of target weight evaluation values ​​is the same as the initial extraction value.

[0036] The one or more target weight evaluation values ​​are accumulated to obtain a comprehensive weight value, and the comprehensive weight value is compared with a preset weight evaluation threshold.

[0037] If the overall weight value is less than the weight evaluation threshold, then the initial extracted value is incremented by one to obtain an updated extracted value. The updated extracted value is then used as the initial extracted value, and the process of extracting the target weight evaluation sequence from the initial weight evaluation value sequence using the preset initial extracted value is repeated until the overall weight value is greater than or equal to the weight evaluation threshold.

[0038] If the comprehensive weight value is greater than or equal to the weight evaluation threshold, the target calorific value influencing factor set is identified in the initial factor set using the target weight evaluation sequence.

[0039] Optionally, the step of using the regional coal storage type and parameter evaluation unit to confirm the calorific value equivalent database includes:

[0040] The system confirms receipt of the parameter evaluation instruction from the parameter evaluation unit, parses the parameter evaluation instruction, and obtains a historical dataset. The historical dataset includes multiple historical data, including: historical coal type, historical coal storage parameters, and historical loss ratio.

[0041] Regional datasets are extracted from historical datasets using regional coal storage types. These regional datasets include data from multiple regions, and the historical coal types corresponding to the regional datasets are the same as the regional coal storage types.

[0042] Perform the following operation on each region in the regional dataset:

[0043] By utilizing the set of factors influencing the target calorific value, regional influence parameters are extracted from regional data.

[0044] By correlating the regional impact parameters with historical loss ratios, the loss-impact parameters are obtained, as shown below:

[0045]

[0046] in, Indicates the loss-impact parameter. Indicates the historical loss percentage. These represent the first and second influencing parameters in the regional influence parameters, respectively. The total number of regional influence parameters is One influencing parameter, The first parameter in the regional influence parameters One influencing parameter;

[0047] By summarizing the aforementioned loss-impact parameters, a set of loss-impact parameters is obtained;

[0048] Using a preset verification ratio, a set of verification impact parameters is randomly extracted from the set of loss-impact parameters, and the complement of the set of verification impact parameters is taken from the set of loss-impact parameters to construct the set of impact parameters.

[0049] A calorific value equivalent database is constructed based on the verification of the influence parameter set and the construction of the influence parameter set.

[0050] Optionally, the step of constructing a calorific value equivalent database based on the verification of the influence parameter set and the construction of the influence parameter set includes:

[0051] Obtain a set of surface fitting models for fitting the surface. The set of surface fitting models includes multiple surface fitting models. Perform the following operation on each of the multiple surface fitting models:

[0052] An initial loss surface is constructed using a surface fitting model and a set of influence parameters. The surface loss ratio is extracted from the initial loss surface using the validation influence parameters in the validation influence parameter set. The absolute difference between the surface loss ratio and the historical loss ratio corresponding to the validation influence parameters is calculated to obtain the validation difference. The validation differences are then summarized and accumulated to obtain the model fitting difference.

[0053] The model fit difference is summarized to obtain a model fit difference set. The minimum model fit difference is extracted from the model fit difference set to obtain the evaluation difference. The evaluation difference is compared with a preset evaluation difference threshold. If the evaluation difference is greater than the evaluation difference threshold, the step of randomly extracting the verification influence parameter set from the loss-influence parameter set using a preset verification ratio is returned until the evaluation difference is less than or equal to the evaluation difference threshold.

[0054] When the evaluation difference is less than or equal to the evaluation difference threshold, the initial loss surface corresponding to the model fitting difference with the smallest model fitting difference in the model fitting difference set is used as the calorific value equivalent database.

[0055] Optionally, retrieving the calorific value loss ratio from the calorific value equivalent database using the target calorific value influence parameter includes:

[0056] The first loss ratio is retrieved from the calorific value equivalent database using the target calorific value influence parameter.

[0057] Cluster the target calorific value influencing parameters and the regional influencing parameters corresponding to the loss-influence parameter set to obtain one or more clustering parameter sets. Identify the target parameter set in one or more clustering parameter sets, where the target parameter set includes the target calorific value influencing parameters and multiple target regional influencing parameters.

[0058] For each of the multiple target region influence parameters, perform the following operation:

[0059] The parameter difference degree is calculated using the pre-constructed difference assessment formula, the target area influence parameter and the target calorific value influence parameter, and the parameter difference degree is summarized to obtain the parameter difference degree set;

[0060] The second loss ratio is calculated using the parameter difference set, and the weighted sum of the first loss ratio and the second loss ratio is calculated to obtain the calorific value loss ratio.

[0061] Optionally, the difference assessment relationship is as follows:

[0062]

[0063] in, Indicates the degree of difference in the parameters. Indicating the parameter affecting the target calorific value The weighted evaluation value corresponding to each thermal influence parameter. Indicating the first parameter in the target region's influence parameters One influencing parameter, Indicating the parameter affecting the target calorific value One thermally affected parameter.

[0064] Optionally, calculating the second loss ratio using the parameter difference set includes:

[0065]

[0066] in, Indicates the second loss ratio. The parameter difference set has a total The degree of difference of each parameter These represent the first parameter in the parameter difference set. The parameter difference and the parameter difference set The degree of difference of each parameter Indicates the first The historical loss ratio corresponding to the difference in each parameter.

[0067] To achieve the above objectives, the present invention also provides a coal storage yard coal reserve change monitoring system based on three-dimensional digital twin, comprising:

[0068] The coal storage environment confirmation module is used to receive the reserve monitoring command and confirm the reserve monitoring environment based on the reserve monitoring command. The reserve monitoring environment includes the initial coal storage yard to be monitored and the reserve monitoring system. The reserve monitoring system includes an image acquisition unit, a parameter evaluation unit, a model reconstruction unit and a result feedback unit.

[0069] An initial model is constructed to obtain the coal storage time series. Based on the coal storage time series and the initial coal storage yard, satellite image time series are obtained. One or more coal storage areas are identified using the satellite image time series. For each of the one or more coal storage areas, the following operations are performed:

[0070] Based on the coal storage area, the regional coal storage type is obtained; based on the image acquisition unit and the coal storage area, a coal storage image set is obtained; and a coal storage reconstruction model is obtained using the model reconstruction unit and the coal storage image set.

[0071] The model region division module is used to divide the coal storage reconstruction model based on the coal storage time series to obtain a set of regional coal storage models;

[0072] The coal storage equivalent acquisition module is used to identify the set of factors affecting the target calorific value using the regional coal storage type, and to identify the calorific value equivalent database using the regional coal storage type and parameter evaluation unit.

[0073] For each regional coal storage model in the regional coal storage model set, the following operations are performed:

[0074] The target calorific value influencing parameters are obtained by using the target calorific value influencing factor set and regional coal storage model, and the calorific value loss ratio is retrieved from the calorific value equivalent database using the target calorific value influencing parameters.

[0075] A coal storage equivalent model is constructed using the calorific value loss ratio. The coal storage equivalent model and the coal storage reconstruction model are sent to the initiator of the storage monitoring command using the result feedback unit to realize the monitoring of coal storage.

[0076] To address the above problems, the present invention also provides an electronic device, the electronic device comprising:

[0077] A memory for storing at least one instruction; and a processor for executing the instructions stored in the memory to implement the above-described method for monitoring changes in coal reserves in a coal storage yard based on three-dimensional digital twins.

[0078] To address the aforementioned problems, the present invention also provides a computer-readable storage medium storing at least one instruction, which is executed by a processor in an electronic device to implement the aforementioned method for monitoring coal reserve changes in coal storage yards based on three-dimensional digital twins.

[0079] To address the problems described in the background art, this invention obtains a coal storage time series. Based on the coal storage time series and the initial coal storage site, it acquires satellite image time series. Using the satellite image time series, it identifies one or more coal storage areas. For each of the one or more coal storage areas, the following operations are performed: the coal storage type of the area is obtained based on the coal storage area; a set of coal storage images is obtained based on the image acquisition unit and the coal storage area; and a coal storage reconstruction model is obtained using the model reconstruction unit and the coal storage image set. It is evident that this invention considers the possibility of inaccurate coal storage area acquisition using traditional measurement methods when acquiring coal storage areas. Therefore, it combines multiple image segmentation models to acquire coal storage areas to improve the accuracy of the acquired coal storage areas. Furthermore, identifying accurate coal storage areas and acquiring images within those areas improves the accuracy of the acquired images. An accurate three-dimensional model is constructed from the acquired images to obtain the coal storage reconstruction model. Based on the coal storage time series, the coal storage reconstruction model is divided to obtain a set of regional coal storage models. It is evident that this invention also considers the time period of coal stored in the coal storage area, and further combines different time... Dividing the model into segments improves the accuracy of subsequent coal equivalent assessments. A set of factors influencing the target calorific value is identified using regional coal storage types, and a calorific value equivalent database is established using regional coal storage types and parameter assessment units. For each regional coal storage model in the regional coal storage model set, the following operations are performed: Target calorific value influencing parameters are obtained using the target calorific value influencing factor set and the regional coal storage model; calorific value loss ratios are retrieved from the calorific value equivalent database using these parameters; a coal storage equivalent model is constructed using the calorific value loss ratios; and the result feedback unit is used to process the results. The coal storage equivalent model and the coal storage reconstruction model are sent to the initiating end of the storage monitoring command. This demonstrates that the present invention does not only consider the volume of coal stored in the coal storage yard, but also takes into account environmental parameters at different times, coal types, and locations during storage. This facilitates the optimization of local coal storage models within the coal storage reconstruction model. Consequently, the optimized coal storage reconstruction model includes the loss rate in calorific value equivalent of the local coal storage model. Furthermore, in this embodiment of the invention, the coal stored in the coal storage yard is extrapolated in time and space to improve the accuracy of the obtained assessed coal storage quantity. Therefore, the present invention can improve the accuracy of monitoring changes in coal quantity in coal storage yards. Attached Figure Description

[0080] Figure 1 A flowchart illustrating a method for monitoring coal storage changes in a coal storage yard based on three-dimensional digital twins, provided in an embodiment of the present invention.

[0081] Figure 2 A functional block diagram of a coal storage yard coal reserve change monitoring system based on three-dimensional digital twin provided in an embodiment of the present invention;

[0082] Figure 3 This is a schematic diagram of the structure of an electronic device for implementing the method for monitoring coal reserve changes in a coal storage yard based on three-dimensional digital twins, as provided in an embodiment of the present invention.

[0083] Explanation of reference numerals in the attached figures:

[0084] 10. Electronic device; 11. Processor; 12. Memory; 13. Bus.

[0085] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0086] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0087] This application provides a method for monitoring changes in coal reserves in a coal storage yard based on three-dimensional digital twins. The executing entity of this method includes, but is not limited to, at least one electronic device that can be configured to execute the method provided in this application, such as a server or a terminal. In other words, the method can be executed by software or hardware installed on a terminal device or a server device, and the software may be a blockchain platform. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster.

[0088] Reference Figure 1 The diagram shown is a flowchart illustrating a method for monitoring coal reserve changes in a coal storage yard based on three-dimensional digital twins, according to an embodiment of the present invention. In this embodiment, the method for monitoring coal reserve changes in a coal storage yard based on three-dimensional digital twins includes:

[0089] S1. Receive a reserve monitoring instruction and confirm the reserve monitoring environment based on the reserve monitoring instruction. The reserve monitoring environment includes the initial coal storage yard to be monitored and the reserve monitoring system. The reserve monitoring system includes an image acquisition unit, a parameter evaluation unit, a model reconstruction unit, and a result feedback unit.

[0090] It should be explained that the reserve monitoring command is issued by the coal reserve assessment personnel of the coal storage yard to assess the coal reserves in the coal storage yard. The reserve monitoring system refers to the mini-program and APP used to assess the coal reserves in the coal storage yard. The reserve monitoring system includes an image acquisition unit, a parameter assessment unit, a model reconstruction unit, and a result feedback unit. For the specific application of the units, please refer to the following embodiments.

[0091] Furthermore, when monitoring the coal storage capacity of a coal yard, dynamic monitoring of the coal storage capacity is more difficult than static monitoring. Therefore, the main purpose of this invention is to improve the accuracy and intelligence of monitoring changes in the coal storage capacity of a coal yard.

[0092] For example, in order to dynamically assess the coal storage capacity of the coal storage yard so that coal can be dispatched in a timely manner when the coal storage capacity is insufficient, the coal storage assessment personnel issue the storage monitoring instruction and confirm the storage monitoring system.

[0093] S2. Obtain the coal storage time series, and based on the coal storage time series and the initial coal storage yard, obtain the satellite image time series, and use the satellite image time series to identify one or more coal storage areas.

[0094] It should be explained that the coal storage time series refers to the sequence of coal storage times, where coal storage time refers to the time when the stored coal quantity changes each time. The satellite image time series refers to the sequence obtained by sorting the acquired satellite images of the initial coal storage yard in chronological order after the coal storage time series has been used.

[0095] Furthermore, the step of using the satellite imagery to identify one or more coal storage areas in a time sequence includes:

[0096] Obtain an image segmentation model set for performing image segmentation on an image, wherein the image segmentation model set includes multiple image segmentation models;

[0097] For each satellite image in the time series, perform the following operations:

[0098] The satellite image is segmented using an image segmentation model set to obtain one or more initial segmented image sets. For each of the one or more initial segmented image sets, the following operations are performed:

[0099] Each initial segmented image in the initial segmented image set is mapped to a pre-constructed image coordinate system to obtain a mapped image;

[0100] The number of times each pixel is mapped in the mapped image is counted to obtain the reference mapping count;

[0101] Obtain the confidence score corresponding to each image segmentation model in the image segmentation model set to obtain a confidence score set, and calculate the minimum number of mappings based on the confidence score set;

[0102] The reference mapping count is compared with the minimum mapping count. If the reference mapping count is less than the minimum mapping count, the pixel is removed from the mapped image. The retained pixels are then summarized to obtain a filtered image. The region corresponding to the filtered image is taken as the recognition region. The recognition region corresponding to the last satellite image in the satellite image time series is taken as the coal storage region. The coal storage regions are summarized to obtain one or more coal storage regions.

[0103] It should be explained that an image segmentation model refers to an algorithm or model capable of segmenting images. Optionally, a pre-trained neural network model can be used as the image segmentation model; other techniques can achieve the same effect, which will not be elaborated further here. The initial segmented image refers to the image in the satellite image that includes the area where coal is stored in the coal storage site, segmented using the image segmentation model. Generally, different types of coal may be stored in the same coal storage site; therefore, using a set of image segmentation models can segment the satellite image into one or more initial segmented image sets, and the regions corresponding to the initial segmented image sets are the same region.

[0104] Understandably, mapping the initial segmented image to an image coordinate system yields the union of the satellite image segmentations performed by each of the multiple image segmentation models—the mapped image. Confidence level refers to the numerical value used to express whether an image segmentation model can correctly segment the image. For example, if a pre-trained neural network model is used as the image segmentation model, the confidence level of the neural network model can be considered as its accuracy during validation. The image coordinate system is existing technology and will not be elaborated upon here.

[0105] It should be understood that calculating the minimum number of mappings based on the confidence set includes:

[0106] The confidence scores in the confidence score set are sorted in ascending order to obtain a confidence score sequence. Using the preset extraction value, a target confidence score sequence is extracted from the confidence score sequence. The target confidence score sequence includes one or more target confidence scores, and the number of target confidence scores is the extraction value, which is 1.

[0107] The overall confidence level is calculated based on the one or more target confidence levels, using the following formula:

[0108]

[0109] in, Indicates the overall confidence level. This indicates the extracted value. Represents the first of one or more target confidence scores. Confidence level of each target;

[0110] The overall confidence level is compared with a preset confidence threshold. If the overall confidence level is greater than or equal to the confidence threshold, the extracted value is taken as the minimum number of mappings.

[0111] Otherwise, increment the extracted value by one to obtain an optimized extracted value. Using the optimized extracted value as the extracted value, return to the step of extracting the target confidence sequence from the confidence sequence using the preset extracted value, until the minimum number of mappings is obtained.

[0112] Furthermore, the minimum number of mappings refers to the minimum number of times a pixel is mapped while ensuring reliability. For example, if the confidence level of each image segmentation model in the image segmentation model set is greater than the confidence threshold, then the region corresponding to the initial segmented image divided by any image segmentation model is considered to be the coal storage region. The confidence threshold is a value set manually to evaluate the reliability of pixels in the initial segmented image. Optionally, the confidence threshold is set to 99%. The purpose of obtaining the coal storage region is to improve the subsequent scheme for collecting coal storage regions and to distinguish different coal storage regions. For example, if a drone equipped with a camera is used to collect images of the coal storage region, and a model is built solely based on the collected images, it is possible that due to unclear division of the coal storage region, different coal storage regions may be mistakenly constructed as a single local region.

[0113] S3. Obtain the regional coal storage type based on the coal storage area, obtain a coal storage image set based on the image acquisition unit and the coal storage area, and obtain a coal storage reconstruction model using the model reconstruction unit and the coal storage image set.

[0114] It should be explained that regional coal storage type refers to the type of coal stored in the coal storage area. Examples include thermal coal, coking coal, and gas coal. The coal storage image set refers to the collection of images taken in the coal storage area to represent the amount of coal stored there. It should also be explained that the model reconstruction unit is a unit capable of constructing a three-dimensional model based on the coal storage images in the image set. The technology of constructing a three-dimensional model from the acquired images is existing technology and will not be elaborated upon here. The method for obtaining the coal storage reconstruction model is as follows: whenever the amount of coal stored in the coal storage yard changes, a three-dimensional model of the coal stored in the coal storage yard is constructed and updated, resulting in a three-dimensional model of the coal stored in the coal storage yard at the current time. Optionally, a drone equipped with a camera can be used as the image acquisition unit; other technologies can achieve the same effect and will not be elaborated upon here.

[0115] S4. Based on the coal storage time series, the coal storage reconstruction model is divided to obtain a regional coal storage model set.

[0116] It should be explained that, based on the coal storage time series, the coal storage reconstruction model is divided to obtain a regional coal storage model set, including:

[0117] Extract the coal storage time sequentially from the coal storage time series, and perform the following operations on each extracted coal storage time:

[0118] The current coal storage model is determined based on the coal storage time and satellite image time series.

[0119] The current coal storage model is iteratively updated to obtain an initial regional coal storage model. These initial regional coal storage models are then aggregated to obtain an initial regional coal storage model set. From this set, initial regional coal storage models are extracted sequentially, and the following operations are performed on each extracted model:

[0120] Obtain the coal storage volume of the initial regional coal storage model, compare the coal storage volume with a preset volume threshold, and if the coal storage volume is less than or equal to the volume threshold, then use the initial regional coal storage model to identify the set of neighboring coal storage models in the coal storage reconstruction model.

[0121] If the set of nearby coal storage models is not empty, then the following operation is performed on each nearby coal storage model in the set:

[0122] Calculate the absolute difference between the coal storage time corresponding to the initial regional coal storage model and the coal storage time corresponding to the adjacent coal storage model to obtain the absolute time difference value. Summarize the absolute time difference values ​​to obtain the absolute time difference value set.

[0123] Using the absolute time difference set, an initial coal storage model is identified in the set of adjacent coal storage models. The initial regional coal storage model is merged into the initial coal storage model to obtain an updated regional coal storage model. The updated regional coal storage model is used as the initial regional coal storage model. The step of obtaining the coal storage volume of the initial regional coal storage model is returned until the coal storage volume is greater than the volume threshold to obtain the regional coal storage model.

[0124] By summarizing the aforementioned regional coal storage models, a set of regional coal storage models is obtained.

[0125] Furthermore, the current coal storage model refers to the model of the amount of coal stored under each coal storage time. Here, the current coal storage model is used to represent the model under each coal storage time. Iteratively updating the current coal storage model means updating the amount of coal stored under each coal storage time to obtain a local area model that expresses different changes over time. Here, the local area model is used to express the model when the amount of coal stored in the coal storage yard changes each time. For example, if coal needs to be transported out of the coal storage yard, the current coal storage model should be smaller. When the coal corresponding to the current coal storage model needs to be transferred, the current coal storage model remains unchanged after the transfer, only its position changes. The coal storage volume refers to the volume corresponding to the initial regional coal storage model. For example, when the initial regional coal storage model is constructed using SolidWorks software, the coal storage volume can be read from the software. Optionally, iterative updates of the initial regional coal storage model can be achieved by combining video streaming with a machine learning model. Other technologies can achieve the same effect, which will not be elaborated here.

[0126] For example, if there are three coal storage times in the coal storage time series, then three current coal storage models can be identified using the coal storage times and satellite image time series. Each current coal storage model represents the amount of coal stored in the storage location at a given coal storage time, and the model corresponding to the third coal storage time is the model at the current time. Since different models only express the volume at a given coal storage time, it is necessary to iteratively update the current coal storage models to obtain the changes in the amount of coal stored at different locations at different time points. This initial regional coal storage model is used to represent the coal at different locations and time points. The initial regional coal storage model differs from the current coal storage model in that the current coal storage model expresses the overall situation of the initial regional coal storage model, while the initial regional coal storage model constitutes a local situation of the current coal storage model.

[0127] It should be clarified that the gaps between coals during coal stockpiling are not considered in the embodiments of this invention. Therefore, the embodiments of this invention are only applicable to scenarios where gaps between coals are not considered or can be ignored. For example, coal is crushed before being stored in a coal storage yard to store it as smaller particles. The adjacent coal storage model set refers to the set of coal storage models that are geographically adjacent to the initial regional coal storage model. Identifying the initial merged coal storage model in the adjacent coal storage model set using the absolute time difference set means taking the adjacent coal storage model corresponding to the smallest absolute time difference in the absolute time difference set as the initial merged coal storage model, and the volume corresponding to the adjacent coal storage model is greater than the coal storage volume. Merging the initial regional coal storage model into the initial merged coal storage model to obtain the updated regional coal storage model means constructing the initial regional coal storage model and the initial merged coal storage model into the same model.

[0128] For example, if there is only one coal storage area in a coal storage yard, but coal is stored three times in this area, then considering the initial coal stored in the coal storage area, when constructing a coal storage model in this area, the coal storage model consists of four local models. The first local model is the initial coal stored in the coal storage area, and the second, third, and fourth local models correspond to the coal stored in each of the three times. If the volume of the initially stored coal is less than a volume threshold, the initially stored coal is adjacent to the second local model, and the volume corresponding to the second local model is greater than the volume of the initially stored coal, then the initially stored coal is merged into the second local model to obtain the updated regional coal storage model. The parameters of the merged initial stored coal in subsequent calculations are based on the parameters corresponding to the second local model. At this time, there are three local models in the updated regional coal storage model.

[0129] It should be explained that the purpose of merging the initial regional models in the initial regional model set is to reduce the complexity of the models in order to improve the intelligence of monitoring the amount of coal stored in the coal storage yard.

[0130] S5. Use regional coal storage types to identify the set of factors affecting the target calorific value, and use regional coal storage types and parameter evaluation units to identify the calorific value equivalent database.

[0131] Understandably, the set of factors influencing the target calorific value identified by utilizing regional coal storage types includes:

[0132] An initial factor set for assessing coal calorific value is obtained based on the regional coal storage type. The initial factor set includes multiple initial factors. The initial factors in the initial factor set are weighted using a pre-constructed principal component analysis method to obtain a set of weighted assessment values.

[0133] The weight evaluation values ​​in the weight evaluation value set are sorted in descending order to obtain the initial weight evaluation value sequence;

[0134] Using a preset initial extraction value, a target weight evaluation sequence is extracted from the initial weight evaluation value sequence, wherein the initial extraction value is 1, and the target weight evaluation sequence includes one or more target weight evaluation values, and the number of target weight evaluation values ​​is the same as the initial extraction value.

[0135] The one or more target weight evaluation values ​​are accumulated to obtain a comprehensive weight value, and the comprehensive weight value is compared with a preset weight evaluation threshold.

[0136] If the overall weight value is less than the weight evaluation threshold, then the initial extracted value is incremented by one to obtain an updated extracted value. The updated extracted value is then used as the initial extracted value, and the process of extracting the target weight evaluation sequence from the initial weight evaluation value sequence using the preset initial extracted value is repeated until the overall weight value is greater than or equal to the weight evaluation threshold.

[0137] If the comprehensive weight value is greater than or equal to the weight evaluation threshold, the target calorific value influencing factor set is identified in the initial factor set using the target weight evaluation sequence.

[0138] Furthermore, the initial factors refer to factors that may affect the calorific value of regional coal storage types, such as ambient temperature, ambient humidity, sunlight, and air volume. Using a pre-constructed principal component analysis (PCA) method to assess the weights of the initial factors in the initial factor set refers to using PCA to obtain the weight corresponding to each initial factor in the initial factor set. This weight value represents the weight of its impact on the calorific value of the coal. The technique of using PCA to assess the weights of the initial factors in the initial factor set is existing technology and will not be elaborated further here. The calorific value of coal refers to the heat generated when a unit mass of coal is completely burned. When the comprehensive weight value is greater than or equal to the weight assessment threshold, it indicates that one or more initial factors corresponding to the comprehensive weight value are the main factors affecting the calorific value loss of the coal. The target calorific value influencing factor set refers to one or more initial factors corresponding to the target weight assessment value in the target weight assessment sequence.

[0139] It should be understood that the calorific value equivalent database confirmed by the regional coal storage type and parameter evaluation unit includes:

[0140] The system confirms receipt of the parameter evaluation instruction from the parameter evaluation unit, parses the parameter evaluation instruction, and obtains a historical dataset. The historical dataset includes multiple historical data, including: historical coal type, historical coal storage parameters, and historical loss ratio.

[0141] Regional datasets are extracted from historical datasets using regional coal storage types. These regional datasets include data from multiple regions, and the historical coal types corresponding to the regional datasets are the same as the regional coal storage types.

[0142] Perform the following operation on each region in the regional dataset:

[0143] By utilizing the set of factors influencing the target calorific value, regional influence parameters are extracted from regional data.

[0144] By correlating the regional impact parameters with historical loss ratios, the loss-impact parameters are obtained, as shown below:

[0145]

[0146] in, Indicates the loss-impact parameter. Indicates the historical loss percentage. These represent the first and second influencing parameters in the regional influence parameters, respectively. The total number of regional influence parameters is One influencing parameter, The first parameter in the regional influence parameters One influencing parameter;

[0147] By summarizing the aforementioned loss-impact parameters, a set of loss-impact parameters is obtained;

[0148] Using a preset verification ratio, a set of verification impact parameters is randomly extracted from the set of loss-impact parameters, and the complement of the set of verification impact parameters is taken from the set of loss-impact parameters to construct the set of impact parameters.

[0149] A calorific value equivalent database is constructed based on the verification of the influence parameter set and the construction of the influence parameter set.

[0150] It should be understood that the historical data refers to data stored in other coal storage sites that can be used as a reference. The definition of historical coal type is the same as that of regional coal storage type, and will not be repeated here. Historical coal storage parameters include, but are not limited to, coal storage time, storage temperature, and storage humidity. Historical loss ratio refers to the proportion of coal calorific value loss. For example, if the calorific value of coal decreases by 30% after a period of storage, then the historical loss ratio is 30%. The technology for obtaining coal calorific value is existing technology and will not be repeated here. The influence parameters in the regional influence parameters correspond one-to-one with the target calorific value influence factors in the target calorific value influence factor set. The verification ratio is a preset ratio, optionally set to 10%. For example, if there are 100 loss-influence parameters in the loss-influence parameter set, and the verification ratio is 10%, then 10 loss-influence parameters are randomly extracted from the loss-influence parameter set using the verification ratio as the verification influence parameter set, and the remaining 90 loss-influence parameters are used to construct the influence parameter set.

[0151] Furthermore, the step of constructing a calorific value equivalent database based on the verification of the influence parameter set and the construction of the influence parameter set includes:

[0152] Obtain a set of surface fitting models for fitting the surface. The set of surface fitting models includes multiple surface fitting models. Perform the following operation on each of the multiple surface fitting models:

[0153] An initial loss surface is constructed using a surface fitting model and a set of influence parameters. The surface loss ratio is extracted from the initial loss surface using the validation influence parameters in the validation influence parameter set. The absolute difference between the surface loss ratio and the historical loss ratio corresponding to the validation influence parameters is calculated to obtain the validation difference. The validation differences are then summarized and accumulated to obtain the model fitting difference.

[0154] The model fit difference is summarized to obtain a model fit difference set. The minimum model fit difference is extracted from the model fit difference set to obtain the evaluation difference. The evaluation difference is compared with a preset evaluation difference threshold. If the evaluation difference is greater than the evaluation difference threshold, the step of randomly extracting the verification influence parameter set from the loss-influence parameter set using a preset verification ratio is returned until the evaluation difference is less than or equal to the evaluation difference threshold.

[0155] When the evaluation difference is less than or equal to the evaluation difference threshold, the initial loss surface corresponding to the model fitting difference with the smallest model fitting difference in the model fitting difference set is used as the calorific value equivalent database.

[0156] It should be explained that a surface fitting model refers to a model used to construct a surface with the loss ratio as the dependent variable and the remaining parameters as independent variables. For example, a neural network model can be used as a surface fitting model. The initial loss surface refers to the surface constructed with the historical loss ratio as the dependent variable and the influencing parameters as independent variables. Generally, the shape of the initial loss surface is related to the dimension of the influencing parameters; when the influencing parameters are one-dimensional, the initial loss surface is a curve.

[0157] Furthermore, extracting the surface damage ratio from the initial damage surface using the validation influence parameters in the validation influence parameter set refers to identifying the dependent variable in the initial damage surface using the influence parameters in the validation influence parameter set as the independent variable. Here, the dependent variable is the surface damage ratio. Summarizing and accumulating the validation differences refers to summing the validation differences to obtain a validation difference set, and then accumulating the validation differences in the validation difference set to obtain the simulation fit difference degree.

[0158] It is easy to understand that since the verification influence parameter set is obtained by random extraction in the embodiments of the present invention, the constructed surface may be distorted. Therefore, in the embodiments of the present invention, the constructed surface is verified by setting an evaluation difference threshold to improve the accuracy of the constructed calorific value equivalent database.

[0159] S6. Obtain the target calorific value influencing parameters using the target calorific value influencing factor set and regional coal storage model, and retrieve the calorific value loss ratio from the calorific value equivalent database using the target calorific value influencing parameters.

[0160] Understandably, retrieving the calorific value loss ratio from the calorific value equivalent database using the target calorific value influence parameter includes:

[0161] The first loss ratio is retrieved from the calorific value equivalent database using the target calorific value influence parameter.

[0162] Cluster the target calorific value influencing parameters and the regional influencing parameters corresponding to the loss-influence parameter set to obtain one or more clustering parameter sets. Identify the target parameter set in one or more clustering parameter sets, where the target parameter set includes the target calorific value influencing parameters and multiple target regional influencing parameters.

[0163] For each of the multiple target region influence parameters, perform the following operation:

[0164] The parameter difference degree is calculated using the pre-constructed difference assessment formula, the target area influence parameter and the target calorific value influence parameter, and the parameter difference degree is summarized to obtain the parameter difference degree set;

[0165] The second loss ratio is calculated using the parameter difference set, and the weighted sum of the first loss ratio and the second loss ratio is calculated to obtain the calorific value loss ratio.

[0166] It should be explained that obtaining the target calorific value influencing parameters using the target calorific value influencing factor set and the regional coal storage model refers to obtaining the coal influencing parameters corresponding to the regional coal storage model using the target calorific value influencing factor set. Here, the influencing parameters are the target calorific value influencing parameters. Optionally, by setting the detection frequency, coal in different regions can be detected, and the average of the detected parameters can be taken as the influencing parameters of the coal in that region. Other techniques can achieve the same effect, which will not be elaborated here.

[0167] It is understood that the method of retrieving the first loss ratio from the calorific value equivalent database using the target calorific value influence parameter is the same as the method of extracting the surface loss ratio from the initial loss surface using the verification influence parameter set, and will not be elaborated here. Optionally, the k-means clustering algorithm is used to cluster the target calorific value influence parameter and the regional influence parameters corresponding to the loss-influence parameters in the loss-influence parameter set to obtain one or more clusters. The parameters contained in each cluster constitute the clustering parameter set, and the clustering parameter set including the target calorific value influence parameter is the target parameter set.

[0168] Furthermore, the difference assessment relationship is as follows:

[0169]

[0170] in, Indicates the degree of difference in the parameters. Indicating the parameter affecting the target calorific value The weighted evaluation value corresponding to each thermal influence parameter. Indicating the first parameter in the target region's influence parameters One influencing parameter, Indicating the parameter affecting the target calorific value One thermally affected parameter.

[0171] It should be explained that the difference assessment formula is only used to calculate the distance between different parameters. Therefore, in the calculation process, only numerical values ​​are substituted in.

[0172] It should be explained that the calculation of the second loss ratio using the parameter difference set includes:

[0173]

[0174] in, Indicates the second loss ratio. The parameter difference set has a total The degree of difference of each parameter These represent the first parameter in the parameter difference set. The parameter difference and the parameter difference set The degree of difference of each parameter Indicates the first The historical loss ratio corresponding to the difference in each parameter.

[0175] Furthermore, in this embodiment of the invention, the weight corresponding to the historical loss ratio that is closer to the target calorific value influence parameter is set to a larger weight, so as to improve the accuracy of calculating the second loss ratio in this embodiment of the invention.

[0176] S7. Construct a coal storage equivalent model using the calorific value loss ratio, and send the coal storage equivalent model and the coal storage reconstruction model to the initiator of the storage monitoring command using the result feedback unit to realize the monitoring of coal storage.

[0177] Furthermore, the coal storage equivalent model includes the calorific value loss rate of coal corresponding to each local coal storage area. This allows coal storage assessment personnel to promptly query the calorific value loss rate of coal corresponding to different coal storage areas, facilitating decision-making based on the coal storage equivalent model. The difference between the coal storage equivalent model and the coal storage reconstruction model lies in the following: the coal storage reconstruction model represents the amount of coal stored in different batches, with its total volume representing the volume of coal stored at the current storage site. The coal storage equivalent model, in addition to representing volume, also identifies the coal loss rate for different areas. Optionally, the coal loss rate for different areas can be identified in text form; other technologies can achieve the same effect, which will not be elaborated upon here.

[0178] To address the problems described in the background art, this invention obtains a coal storage time series. Based on the coal storage time series and the initial coal storage site, it acquires satellite image time series. Using the satellite image time series, it identifies one or more coal storage areas. For each of the one or more coal storage areas, the following operations are performed: the coal storage type of the area is obtained based on the coal storage area; a set of coal storage images is obtained based on the image acquisition unit and the coal storage area; and a coal storage reconstruction model is obtained using the model reconstruction unit and the coal storage image set. It is evident that this invention considers the possibility of inaccurate coal storage area acquisition using traditional measurement methods when acquiring coal storage areas. Therefore, it combines multiple image segmentation models to acquire coal storage areas to improve the accuracy of the acquired coal storage areas. Furthermore, identifying accurate coal storage areas and acquiring images within those areas improves the accuracy of the acquired images. An accurate three-dimensional model is constructed from the acquired images to obtain the coal storage reconstruction model. Based on the coal storage time series, the coal storage reconstruction model is divided to obtain a set of regional coal storage models. It is evident that this invention also considers the time period of coal stored in the coal storage area, and further combines different time... Dividing the model into segments improves the accuracy of subsequent coal equivalent assessments. A set of factors influencing the target calorific value is identified using regional coal storage types, and a calorific value equivalent database is established using regional coal storage types and parameter assessment units. For each regional coal storage model in the regional coal storage model set, the following operations are performed: Target calorific value influencing parameters are obtained using the target calorific value influencing factor set and the regional coal storage model; calorific value loss ratios are retrieved from the calorific value equivalent database using these parameters; a coal storage equivalent model is constructed using the calorific value loss ratios; and the result feedback unit is used to process the results. The coal storage equivalent model and the coal storage reconstruction model are sent to the initiating end of the storage monitoring command. This demonstrates that the present invention does not only consider the volume of coal stored in the coal storage yard, but also takes into account environmental parameters at different times, coal types, and locations during storage. This facilitates the optimization of local coal storage models within the coal storage reconstruction model. Consequently, the optimized coal storage reconstruction model includes the loss rate in calorific value equivalent of the local coal storage model. Furthermore, in this embodiment of the invention, the coal stored in the coal storage yard is extrapolated in time and space to improve the accuracy of the obtained assessed coal storage quantity. Therefore, the present invention can improve the accuracy of monitoring changes in coal quantity in coal storage yards.

[0179] like Figure 2 The diagram shown is a functional block diagram of a coal storage yard coal reserve change monitoring system based on three-dimensional digital twin provided in an embodiment of the present invention.

[0180] The coal storage yard coal reserve change monitoring system 100 based on three-dimensional digital twins described in this invention can be installed in an electronic device. Depending on the functions implemented, the coal storage yard coal reserve change monitoring system 100 may include a coal storage environment confirmation module 101, an initial model construction module 102, a model area division module 103, and a coal storage equivalent acquisition module 104. The module described in this invention can also be called a unit, which refers to a series of computer program segments that can be executed by the processor of an electronic device and can perform a fixed function, and is stored in the memory of the electronic device.

[0181] The coal storage environment confirmation module 101 is used to receive the reserve monitoring instruction and confirm the reserve monitoring environment based on the reserve monitoring instruction. The reserve monitoring environment includes the initial coal storage yard to be monitored and the reserve monitoring system. The reserve monitoring system includes an image acquisition unit, a parameter evaluation unit, a model reconstruction unit and a result feedback unit.

[0182] The initial model construction model 102 is used to obtain the coal storage time series. Based on the coal storage time series and the initial coal storage yard, satellite image time series are obtained. One or more coal storage areas are identified using the satellite image time series. For each of the one or more coal storage areas, the following operations are performed:

[0183] Based on the coal storage area, the regional coal storage type is obtained; based on the image acquisition unit and the coal storage area, a coal storage image set is obtained; and a coal storage reconstruction model is obtained using the model reconstruction unit and the coal storage image set.

[0184] The model region division module 103 is used to divide the coal storage reconstruction model based on the coal storage time series to obtain a set of regional coal storage models.

[0185] The coal storage equivalent acquisition module 104 is used to identify the target calorific value influencing factor set using the regional coal storage type, and to identify the calorific value equivalent database using the regional coal storage type and parameter evaluation unit.

[0186] For each regional coal storage model in the regional coal storage model set, the following operations are performed:

[0187] The target calorific value influencing parameters are obtained by using the target calorific value influencing factor set and regional coal storage model, and the calorific value loss ratio is retrieved from the calorific value equivalent database using the target calorific value influencing parameters.

[0188] A coal storage equivalent model is constructed using the calorific value loss ratio. The coal storage equivalent model and the coal storage reconstruction model are sent to the initiator of the storage monitoring command using the result feedback unit to realize the monitoring of coal storage.

[0189] In detail, the modules in the coal storage yard coal reserve change monitoring system 100 based on three-dimensional digital twins described in this embodiment of the invention adopt the same approach as described above when in use. Figure 1 The method described above uses the same technical means as the three-dimensional digital twin-based coal storage yard coal reserve change monitoring method, and can produce the same technical effect, so it will not be repeated here.

[0190] like Figure 3 The diagram shown is a structural schematic of an electronic device for implementing a method for monitoring coal storage changes in a coal storage yard based on three-dimensional digital twins, according to an embodiment of the present invention.

[0191] The electronic device 1 may include a processor 10, a memory 11 and a bus 12, and may also include a computer program stored in the memory 11 and capable of running on the processor 10, such as a method program for monitoring coal storage changes in coal storage yards based on three-dimensional digital twins.

[0192] The memory 11 includes at least one type of readable storage medium, such as flash memory, portable hard drive, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of the electronic device 1, such as the portable hard drive of the electronic device 1. In other embodiments, the memory 11 can be an external storage device of the electronic device 1, such as a plug-in portable hard drive, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the electronic device 1. Furthermore, the memory 11 includes both internal storage units and external storage devices of the electronic device 1. The memory 11 can be used not only to store application software and various types of data installed on the electronic device 1, such as the code of a coal storage yard coal reserve change monitoring method program based on three-dimensional digital twins, but also to temporarily store data that has been output or will be output.

[0193] In some embodiments, the processor 10 may be composed of integrated circuits, such as a single packaged integrated circuit or multiple integrated circuits with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 10 is the control unit of the electronic device, connecting various components of the entire electronic device through various interfaces and lines. It executes programs or modules stored in the memory 11 (e.g., a method for monitoring coal reserve changes in a coal storage yard based on three-dimensional digital twins), and calls data stored in the memory 11 to perform various functions of the electronic device 1 and process data.

[0194] The bus 12 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus 12 can be divided into an address bus, a data bus, a control bus, etc. The bus 12 is configured to realize the connection and communication between the memory 11 and at least one processor 10, etc.

[0195] Figure 3 Only electronic devices with components are shown; it will be understood by those skilled in the art that... Figure 3 The structure shown does not constitute a limitation on the electronic device 1, and may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0196] For example, although not shown, the electronic device 1 may also include a power supply (such as a battery) to power the various components. Preferably, the power supply can be logically connected to the at least one processor 10 through a power management system, thereby enabling functions such as charging management, discharging management, and power consumption management through the power management system. The power supply may also include one or more DC or AC power supplies, recharging systems, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device 1 may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be described in detail here.

[0197] Furthermore, the electronic device 1 may also include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a Wi-Fi interface, a Bluetooth interface, etc.), which is typically used to establish communication connections between the electronic device 1 and other electronic devices.

[0198] Optionally, the electronic device 1 may further include a user interface, which may be a display, an input unit (such as a keyboard), and optionally, a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen, etc. The display may also be appropriately referred to as a screen or display unit, used to display information processed in the electronic device 1 and to display a visual user interface.

[0199] The program for monitoring coal storage changes in a coal storage yard based on three-dimensional digital twins, stored in the memory 11 of the electronic device 1, is a combination of multiple instructions. When run in the processor 10, it can achieve the following:

[0200] Receive a reserve monitoring instruction, and confirm the reserve monitoring environment based on the reserve monitoring instruction. The reserve monitoring environment includes the initial coal storage yard to be monitored and the reserve monitoring system. The reserve monitoring system includes an image acquisition unit, a parameter evaluation unit, a model reconstruction unit, and a result feedback unit.

[0201] Obtain the coal storage time series, and based on the coal storage time series and the initial coal storage yard, obtain satellite image time series. Use the satellite image time series to identify one or more coal storage areas, and perform the following operations on each of the one or more coal storage areas:

[0202] Based on the coal storage area, the regional coal storage type is obtained; based on the image acquisition unit and the coal storage area, a coal storage image set is obtained; and a coal storage reconstruction model is obtained using the model reconstruction unit and the coal storage image set.

[0203] Based on the coal storage time series, the coal storage reconstruction model is divided to obtain a set of regional coal storage models;

[0204] The set of factors influencing the target calorific value was identified by utilizing regional coal storage types, and the calorific value equivalent database was identified by utilizing regional coal storage types and parameter evaluation units.

[0205] For each regional coal storage model in the regional coal storage model set, the following operations are performed:

[0206] The target calorific value influencing parameters are obtained by using the target calorific value influencing factor set and regional coal storage model, and the calorific value loss ratio is retrieved from the calorific value equivalent database using the target calorific value influencing parameters.

[0207] A coal storage equivalent model is constructed using the calorific value loss ratio. The coal storage equivalent model and the coal storage reconstruction model are sent to the initiator of the storage monitoring command using the result feedback unit to realize the monitoring of coal storage.

[0208] Specifically, the processor 10's implementation method for the above instructions can be found in [reference needed]. Figures 1 to 3 The descriptions of the relevant steps in the corresponding embodiments are not repeated here.

[0209] Furthermore, if the modules / units integrated in the electronic device 1 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium may include: any entity or system capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, or a read-only memory (ROM).

[0210] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor of an electronic device, can perform the following:

[0211] Receive a reserve monitoring instruction, and confirm the reserve monitoring environment based on the reserve monitoring instruction. The reserve monitoring environment includes the initial coal storage yard to be monitored and the reserve monitoring system. The reserve monitoring system includes an image acquisition unit, a parameter evaluation unit, a model reconstruction unit, and a result feedback unit.

[0212] Obtain the coal storage time series, and based on the coal storage time series and the initial coal storage yard, obtain satellite image time series. Use the satellite image time series to identify one or more coal storage areas, and perform the following operations on each of the one or more coal storage areas:

[0213] Based on the coal storage area, the regional coal storage type is obtained; based on the image acquisition unit and the coal storage area, a coal storage image set is obtained; and a coal storage reconstruction model is obtained using the model reconstruction unit and the coal storage image set.

[0214] Based on the coal storage time series, the coal storage reconstruction model is divided to obtain a set of regional coal storage models;

[0215] The set of factors influencing the target calorific value was identified by utilizing regional coal storage types, and the calorific value equivalent database was identified by utilizing regional coal storage types and parameter evaluation units.

[0216] For each regional coal storage model in the regional coal storage model set, the following operations are performed:

[0217] The target calorific value influencing parameters are obtained by using the target calorific value influencing factor set and regional coal storage model, and the calorific value loss ratio is retrieved from the calorific value equivalent database using the target calorific value influencing parameters.

[0218] A coal storage equivalent model is constructed using the calorific value loss ratio. The coal storage equivalent model and the coal storage reconstruction model are sent to the initiator of the storage monitoring command using the result feedback unit to realize the monitoring of coal storage.

[0219] In the embodiments provided by this invention, it should be understood that the disclosed devices, systems, and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative, and actual implementations may have other classification methods.

[0220] The modules described as separate components may or may not be physically separate. The components shown as modules 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 modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0221] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0222] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0223] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A coal storage change monitoring method for a coal yard based on a three-dimensional digital twin, characterized by, The method comprises: receiving a stockpile monitoring instruction, and confirming a stockpile monitoring environment based on the stockpile monitoring instruction, wherein the stockpile monitoring environment comprises an initial coal storage yard to be monitored and a stockpile monitoring system, and the stockpile monitoring system comprises an image acquisition unit, a parameter evaluation unit, a model reconstruction unit and a result feedback unit; acquiring a coal quantity storage time sequence, acquiring a satellite image time sequence based on the coal quantity storage time sequence and the initial coal storage yard, and identifying one or more coal storage areas by using the satellite image time sequence, wherein the following operations are performed on each of the one or more coal storage areas: acquiring a regional coal storage type based on the coal storage area, acquiring a coal storage image set based on the image acquisition unit and the coal storage area, and acquiring a coal storage reconstruction model by using the model reconstruction unit and the coal storage image set; dividing the coal storage reconstruction model based on the coal quantity storage time sequence to obtain a regional coal storage model set; confirming a target calorific value influencing factor set by using the regional coal storage type, and confirming a calorific value equivalent database by using the regional coal storage type and the parameter evaluation unit; the following operations are performed on each of the regional coal storage models in the regional coal storage model set: acquiring a target calorific value influencing parameter by using the target calorific value influencing factor set and the regional coal storage model, and searching for a calorific value loss ratio in the calorific value equivalent database by using the target calorific value influencing parameter; constructing a coal equivalent model by using the calorific value loss ratio, and sending the coal equivalent model and the coal storage reconstruction model to an initiating end of the stockpile monitoring instruction by using the result feedback unit to realize monitoring of the coal stockpile. 2.The coal reserve change monitoring method based on three-dimensional digital twinning of a coal storage yard according to claim 1, wherein, The identification of the one or more coal storage areas by using the satellite image time sequence comprises: acquiring an image segmentation model set for realizing image segmentation of an image, wherein the image segmentation model set comprises a plurality of image segmentation models; the following operations are performed on each of the satellite images in the satellite image time sequence: segmenting the satellite image by using the image segmentation model set to obtain one or more initial segmentation image sets, and the following operations are performed on each of the initial segmentation image sets in the one or more initial segmentation image sets: mapping each of the initial segmentation images in the initial segmentation image set to a pre-constructed image coordinate system to obtain a mapping image; counting the number of times that each pixel point is mapped in the mapping image to obtain a reference mapping number; acquiring a confidence degree corresponding to each of the image segmentation models in the image segmentation model set to obtain a confidence degree set, and calculating a minimum mapping number based on the confidence degree set; comparing the reference mapping number with the minimum mapping number, and if the reference mapping number is less than the minimum mapping number, eliminating the pixel point in the mapping image, and collecting the remaining pixel points to obtain a screening image, taking a region corresponding to the screening image as the identified region, taking an identified region corresponding to a last satellite image in the satellite image time sequence as the coal storage area, and collecting the coal storage areas to obtain the one or more coal storage areas. 3.The coal reserve change monitoring method based on three-dimensional digital twinning of a coal storage yard according to claim 2, characterized in that, The division of the coal storage reconstruction model based on the coal quantity storage time sequence to obtain the regional coal storage model set comprises: The coal storage time is sequentially extracted in the coal storage time sequence, and the following operations are performed on the extracted coal storage time: According to the coal storage time and the satellite image time sequence, the current coal storage model is confirmed; The current coal storage model is iteratively updated to obtain an initial regional coal storage model, and the initial regional coal storage models are aggregated to obtain an initial regional coal storage model set. The initial regional coal storage model is sequentially extracted in the initial regional coal storage model set, and the following operations are performed on the extracted initial regional coal storage model: The coal storage volume of the initial regional coal storage model is obtained, and the coal storage volume is compared with a preset volume threshold. If the coal storage volume is less than or equal to the volume threshold, the initial regional coal storage model is used to identify a nearby coal storage model set in the coal storage reconstruction model; If the nearby coal storage model set is not empty, the following operations are performed on each nearby coal storage model in the nearby coal storage model set: The absolute difference between the coal storage time corresponding to the initial regional coal storage model and the coal storage time corresponding to the nearby coal storage model is calculated to obtain an absolute time difference value. The absolute time difference values are aggregated to obtain an absolute time difference value set; Using the absolute time difference value set, an initial merged coal storage model is identified in the nearby coal storage model set. The initial regional coal storage model is merged into the initial merged coal storage model to obtain an updated regional coal storage model. The updated regional coal storage model is used as the initial regional coal storage model, and the step of obtaining the coal storage volume of the initial regional coal storage model is returned until the coal storage volume is greater than the volume threshold, and the regional coal storage model is obtained; The regional coal storage models are aggregated to obtain a regional coal storage model set. 4.The coal reserve change monitoring method based on three-dimensional digital twinning of a coal storage yard according to claim 3, characterized in that, The target heat value influencing factor set is confirmed based on the regional coal storage type, including: Based on the regional coal storage type, an initial factor set for evaluating the heat of coal is obtained. The initial factor set includes multiple initial factors. The initial factors in the initial factor set are evaluated for weight using a pre-constructed principal component analysis method to obtain a weight evaluation value set; The weight evaluation values in the weight evaluation value set are sorted in descending order to obtain an initial weight evaluation value sequence; Using a preset initial extraction value, a target weight evaluation sequence is extracted from the initial weight evaluation value sequence. The initial extraction value is 1, and the target weight evaluation sequence includes one or more target weight evaluation values. The number of target weight evaluation values is the same as the initial extraction value. The one or more target weight evaluation values are accumulated to obtain a comprehensive weight value, and the comprehensive weight value is compared with a preset weight evaluation threshold; If the comprehensive weight value is less than the weight evaluation threshold, the initial extraction value is incremented by one to obtain an updated extraction value. The updated extraction value is used as the initial extraction value, and the step of extracting the target weight evaluation sequence from the initial weight evaluation value sequence using the preset initial extraction value is returned until the comprehensive weight value is greater than or equal to the weight evaluation threshold; If the comprehensive weight value is greater than or equal to the weight evaluation threshold, the target heat value influencing factor set is identified in the initial factor set using the target weight evaluation sequence. 5.The coal reserve change monitoring method based on three-dimensional digital twinning of a coal storage yard according to claim 4, wherein The utilization area coal storage type and parameter evaluation unit confirms a heat value equivalent database, including: Confirming receiving a parameter evaluation instruction from the parameter evaluation unit, analyzing the parameter evaluation instruction, and obtaining a historical data set, wherein the historical data set includes a plurality of historical data, and the historical data includes historical coal types, historical coal storage parameters, and historical loss ratios; Using the regional coal storage type, a regional data set is extracted from the historical data set, wherein the regional data set includes a plurality of regional data, and the historical coal type corresponding to the regional data set is the same as the regional coal storage type; For each regional data in the regional data set, the following operations are performed: Using the target heat value influence factor set, the regional influence parameter is extracted from the regional data; Correlate the regional influence parameter with the historical loss ratio to obtain the loss-influence parameter, wherein the loss-influence parameter is as follows: ， in, Indicates the loss-impact parameter. Indicates the historical loss percentage. These represent the first and second influencing parameters in the regional influence parameters, respectively. The total number of regional influence parameters is indicated. One influencing parameter, The first parameter in the regional influence parameters One influencing parameter; Summarize the loss-influence parameter to obtain a loss-influence parameter set; Using a preset verification ratio, a verification influence parameter set is randomly extracted from the loss-influence parameter set, and the complement of the verification influence parameter set in the loss-influence parameter set is taken as a construction influence parameter set; Based on the verification influence parameter set and the construction influence parameter set, a heat value equivalent database is constructed. 6.The coal reserve change monitoring method based on three-dimensional digital twinning of a coal storage yard according to claim 5, wherein, The heat value equivalent database is constructed based on the verification influence parameter set and the construction influence parameter set, including: Obtain a surface fitting model set for fitting a surface, wherein the surface fitting model set includes a plurality of surface fitting models, and for each surface fitting model in the plurality of surface fitting models, the following operations are performed: Using the surface fitting model and the construction influence parameter set, an initial loss surface is constructed, and using the verification influence parameter in the verification influence parameter set, a surface loss ratio is extracted from the initial loss surface, the absolute difference between the surface loss ratio and the historical loss ratio corresponding to the verification influence parameter is calculated, and a verification difference is obtained. Summarize and accumulate the verification difference to obtain a model fitting difference degree; Summarize the model fitting difference degree to obtain a model fitting difference degree set, and extract the smallest model fitting difference degree from the model fitting difference degree set to obtain an evaluation difference degree. Compare the evaluation difference degree with a preset evaluation difference threshold value, if the evaluation difference degree is greater than the evaluation difference threshold value, return to the step of randomly extracting the verification influence parameter set from the loss-influence parameter set using the preset verification ratio, until the evaluation difference degree is less than or equal to the evaluation difference threshold value; When the evaluation difference degree is less than or equal to the evaluation difference threshold value, the initial loss surface corresponding to the smallest model fitting difference degree in the model fitting difference degree set is taken as the heat value equivalent database. 7.The coal reserve change monitoring method based on three-dimensional digital twinning of a coal storage yard according to claim 6, wherein, The target heat value influence parameter is used to retrieve a heat value loss ratio in the heat value equivalent database, including: Using the target heat value influence parameter, a first loss ratio is retrieved in the heat value equivalent database; Clustering the target heat value influence parameter and the regional influence parameter corresponding to the loss-influence parameter in the loss-influence parameter set to obtain one or more cluster parameter sets, and identifying a target parameter set in the one or more cluster parameter sets, wherein the target parameter set includes the target heat value influence parameter and a plurality of target regional influence parameters; The following operations are performed on each of the plurality of target area influence parameters: A pre-constructed difference evaluation relationship, a target area influence parameter, and a target heat value influence parameter are used to calculate a parameter difference degree, and the parameter difference degrees are aggregated to obtain a parameter difference degree set; The parameter difference degree set is used to calculate a second loss ratio, and a weighted sum of the first loss ratio and the second loss ratio is calculated to obtain a heat value loss ratio. 8.The coal reserve change monitoring method based on three-dimensional digital twinning of a coal storage yard according to claim 7, wherein, The difference evaluation relationship is as follows: ， wherein, represents the parameter difference degree, represents a weight evaluation value corresponding to the th thermal influence parameter in the target thermal value influence parameter, represents the th influence parameter in the target area influence parameter, represents the th thermal influence parameter in the target thermal value influence parameter. 9.The coal reserve change monitoring method based on three-dimensional digital twinning of a coal storage yard according to claim 8, wherein The parameter difference degree set is used to calculate a second loss ratio, The system comprises: ， in, Indicates the second loss ratio. The total number of parameters in the set of differences The degree of difference of each parameter These represent the first parameter in the parameter difference set. The parameter difference and the parameter difference set The degree of difference of each parameter Indicates the first The historical loss ratio corresponding to the difference in each parameter.

10. A coal storage change monitoring system for a coal yard based on a three-dimensional digital twin, characterized by, The coal storage environment confirmation module is configured to receive a storage monitoring instruction and confirm a storage monitoring environment based on the storage monitoring instruction, wherein the storage monitoring environment includes an initial coal storage yard to be monitored and a storage monitoring system, and the storage monitoring system includes an image acquisition unit, a parameter evaluation unit, a model reconstruction unit, and a result feedback unit. The initial model construction module is configured to obtain a coal quantity storage time sequence, obtain a satellite image time sequence based on the coal quantity storage time sequence and the initial coal storage yard, and identify one or more coal storage areas using the satellite image time sequence, and perform the following operations on each of the one or more coal storage areas: Based on the coal storage area, a regional coal storage type is obtained, a coal storage image set is obtained based on the image acquisition unit and the coal storage area, and a coal storage reconstruction model is obtained using the model reconstruction unit and the coal storage image set. The model area division module is configured to divide the coal storage reconstruction model based on the coal quantity storage time sequence to obtain a set of regional coal storage models. The coal storage equivalent obtaining module is configured to confirm a target heat value influence factor set using the regional coal storage type, and confirm a heat value equivalent database using the regional coal storage type and the parameter evaluation unit. The following operations are performed on each of the set of regional coal storage models: A target heat value influence parameter is obtained using the set of target heat value influence factors and the regional coal storage model, and a heat value loss ratio is retrieved in the heat value equivalent database using the target heat value influence parameter. The coal storage equivalent model is constructed using the heat value loss ratio, and the coal storage equivalent model and the coal storage reconstruction model are sent to the initiator of the storage monitoring instruction using the result feedback unit to realize monitoring of the coal reserves. ​

Images