Fuel metering method for a coal yard and system therefor

Abstract

The present application relates to the technical field of coal yard fuel metering, and relates to a coal yard fuel metering method and system, the method comprising: acquiring real-time information collected by a first unmanned aerial vehicle, the real-time information comprising the positions of obstacles, dust concentration and wind speed information; establishing a three-dimensional risk map according to the real-time information collected by the unmanned aerial vehicle; dividing the three-dimensional risk map to obtain a plurality of sub-three-dimensional risk maps; matching the sub-three-dimensional risk maps to be detected by a second unmanned aerial vehicle using an auction algorithm to obtain a matching result; determining the type of a corresponding fuel pile according to the matching result to obtain type information; planning a scanning track for the second unmanned aerial vehicle to scan the fuel pile according to the type information, and calculating the weight of the fuel pile according to point cloud data collected by scanning. The present application does not require vehicles to transport fuel to a weightometer for metering, and realizes fast, accurate and contactless metering of large coal yard fuel piles.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of coal yard fuel metering, in particular to a coal yard fuel metering method and system. BACKGROUND

[0002] Under the current technical system, the static weighing method is commonly used for fuel pile metering in the coal yard. The operation principle of this method is relatively simple, which mainly uses the ground scale to implement twice weighing operation on the transport vehicle. The first time is to weigh the empty vehicle to obtain the weight data of the empty vehicle, and the second time is to weigh the vehicle after loading fuel to the full load state. Finally, the weight value of the transported fuel can be obtained by calculating the difference between the two weighing data. However, this seemingly simple metering method has the significant disadvantage of extremely low efficiency when applied to large coal yards. As a place for storing a large number of fuel piles, large coal yards have a large number of daily fuel transport vehicles. If the static weighing method is used, each transport vehicle needs to go through the series of processes of empty vehicle weighing, loading, and full load weighing, which undoubtedly consumes a lot of time. Moreover, during the entire weighing process, a dedicated person needs to be arranged to operate the ground scale, record data, and guide the vehicle, which undoubtedly wastes a lot of manpower. At the same time, the purchase, maintenance, and occupation of the ground scale device require a considerable amount of funds, and the material cost is also considerable. SUMMARY

[0003] The present application aims to provide a coal yard fuel metering method and system to improve the above problems.

[0004] To achieve the above-mentioned purpose, the present application provides the following technical solutions:

[0005] On the one hand, the present application provides a coal yard fuel metering method, which comprises:

[0006] acquiring real-time information collected by a first unmanned aerial vehicle, the real-time information including the position of obstacles, dust concentration, and wind speed information;

[0007] establishing a three-dimensional risk map according to the real-time information collected by the unmanned aerial vehicle, the three-dimensional risk map including all fuel piles that need to be weighed in the coal yard;

[0008] dividing the three-dimensional risk map to obtain a plurality of sub-three-dimensional risk maps;

[0009] matching the sub-three-dimensional risk map to be detected by a second unmanned aerial vehicle using an auction algorithm to obtain a matching result;

[0010] determining the type of the corresponding fuel pile according to the matching result to obtain type information;

[0011] The type information is used for planning a scanning track of the fuel pile by the second unmanned aerial vehicle, and the weight of the fuel pile is calculated according to point cloud data collected by scanning.

[0012] In a second aspect, the embodiments of the present application provide a fuel metering system for a coal yard, and the system comprises:

[0013] The acquisition module is configured to acquire real-time information collected by the first unmanned aerial vehicle, wherein the real-time information comprises position information of an obstacle, dust concentration and wind speed information;

[0014] The first processing module is configured to establish a three-dimensional risk map according to the real-time information collected by the unmanned aerial vehicle, wherein the three-dimensional risk map comprises all fuel piles in the coal yard that need to be weighed;

[0015] The second processing module is configured to divide the three-dimensional risk map to obtain a plurality of sub-three-dimensional risk maps;

[0016] The third processing module is configured to match the sub-three-dimensional risk map to be detected by the second unmanned aerial vehicle by using an auction algorithm to obtain a matching result;

[0017] The fourth processing module is configured to determine the type of the corresponding fuel pile according to the matching result to obtain type information;

[0018] The fifth processing module is configured to plan a scanning track of the fuel pile by the second unmanned aerial vehicle according to the type information, and calculate the weight of the fuel pile according to point cloud data collected by scanning.

[0019] In a third aspect, the embodiments of the present application provide a fuel metering device for a coal yard, and the device comprises a memory and a processor. The memory is configured to store a computer program; and the processor is configured to execute the computer program to implement the steps of the fuel metering method for the coal yard.

[0020] In a fourth aspect, the embodiments of the present application provide a readable storage medium, and the readable storage medium stores a computer program. When the computer program is executed by a processor, the steps of the fuel metering method for the coal yard are implemented.

[0021] The present application has the following beneficial effects:

[0022] The present application divides the three-dimensional risk map after constructing the three-dimensional risk map by using the real-time information collected by the first unmanned aerial vehicle, obtains a plurality of sub-three-dimensional risk maps, matches the second unmanned aerial vehicle and the sub-three-dimensional risk map by using an auction algorithm, allocates a corresponding area to each second unmanned aerial vehicle for detection, makes the multiple unmanned aerial vehicles work cooperatively, improves the metering efficiency in a large coal yard, determines the scanning track according to the type of the fuel pile, avoids the existence of a scanning blind area, improves the quality of the collected point cloud data, and thus improves the fuel metering precision.

[0023] Other features and advantages of the invention will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing embodiments of the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description and the accompanying drawings. Attached Figure Description

[0024] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0025] Figure 1 This is a schematic diagram of the fuel metering method for a coal yard as described in an embodiment of the present invention.

[0026] Figure 2 This is a schematic diagram of the fuel metering system structure of the coal yard described in an embodiment of the present invention.

[0027] Figure 3 This is a schematic diagram of the fuel metering equipment in the coal yard as described in an embodiment of the present invention.

[0028] The diagram is labeled as follows: 800, fuel metering equipment in the coal yard; 801, processor; 802, memory; 803, multimedia component; 804, I / O interface; 805, communication component; 901, acquisition module; 902, first processing module; 903, second processing module; 904, third processing module; 905, fourth processing module; 906, fifth processing module. Detailed Implementation

[0029] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0030] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this invention, terms such as "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0031] Example 1:

[0032] This embodiment provides a fuel metering method for a coal yard. It can be understood that this embodiment can set up a scenario, such as a scenario in a large coal yard where all fuel piles in the coal yard are metered.

[0033] See Figure 1 The figure shows that the method includes steps S1, S2, S3, S4, S5, and S6, which specifically include:

[0034] Step S1: Obtain real-time information collected by the first UAV, including the location of obstacles, dust concentration, and wind speed information;

[0035] In this step, sensors are deployed at various key locations in the coal yard, such as lidar to obtain the location of obstacles, dust concentration sensors to monitor dust concentration, and wind speed sensors to measure wind speed.

[0036] Step S2: Establish a three-dimensional risk map based on the real-time information collected by the UAV. The three-dimensional risk map includes all fuel piles in the coal yard that need to be weighed.

[0037] In this step, a basic 3D model of the coal yard is constructed using lidar scanning technology, presenting the overall layout of the coal yard, the outline of the coal piles, and the terrain undulations. The collected real-time information is then quantitatively evaluated, specifically by classifying dust concentration into different levels, set at 0-50 mg / m³. 3 For low risk, 51-100 mg / m² 3 Medium risk, 100mg / m 3 The above are high-risk areas, assigned numerical values ​​of 1, 2, and 3 respectively. Wind speed is also classified similarly: 0-3 m / s is low-risk, 3.1-6 m / s is medium-risk, and above 6.1 m / s is high-risk, corresponding to numerical values ​​of 1, 2, and 3. Risk factors are transformed into actionable quantitative indicators, which are then mapped to corresponding coordinate points in the 3D basic model. The risk level is displayed intuitively using colors, such as green for low-risk areas, yellow for medium-risk areas, and red for high-risk areas.

[0038] Step S3: Divide the three-dimensional risk map to obtain several sub-three-dimensional risk maps;

[0039] Step S4: Use the auction algorithm to match the sub-3D risk map to be detected by the second UAV to obtain the matching result;

[0040] In this step, since the large coal yard covers a large area, using a single drone requires multiple recharges to complete the metering of the entire large coal yard, which reduces the efficiency of the operation. Therefore, the three-dimensional risk map is divided, and multiple drones work together. Each drone is assigned a corresponding sub-three-dimensional risk map for detection, which effectively improves the metering efficiency of fuel piles in large coal yards.

[0041] Step S4 further includes steps S41, S42, and S43, which specifically include:

[0042] Step S41: Obtain the attribute information of each second UAV, including location information, battery information and sensor type;

[0043] Step S42: Determine the bidding price of each second UAV based on the attribute information of each second UAV, and obtain the bidding price information;

[0044] In this step, the specific calculation process for the auction price information is as follows:

[0045]

[0046] In the above formula, B represents the auction price, P represents the remaining battery power of the second drone, D represents the distance to the target, and M represents the sensor matching degree. The highest bidder wins the mission, ensuring load balancing and optimal resource matching.

[0047] Step S43: Match the sub-3D risk map of each drone to be detected based on the auction price information.

[0048] Following step S43, the system further includes steps S44, S45, S46, S47, and S48, which specifically include:

[0049] Step S44: Obtain obstacle type information;

[0050] In this step, the obstacle type information includes vehicles and fixed equipment in the coal yard.

[0051] Step S45: Determine the repulsion coefficient of the obstacle based on the obstacle type information;

[0052] Step S46: Generate a repulsive field around the obstacle according to the repulsive force coefficient of the obstacle;

[0053] In this step, the formula for calculating the repulsive force is:

[0054]

[0055] In the above formula, F1 represents the repulsive force, d and d0 represent the distance between the second UAV and the repulsive field and the radius of influence of the repulsive force, respectively, and K1 represents the repulsive force coefficient, which will be adjusted according to the type of obstacle (the repulsive force coefficient of vehicles is greater than that of fixed equipment).

[0056] Step S47: Generate a gravitational field at the corresponding fuel pile location in the sub-3D risk map;

[0057] In this step, the formula for calculating gravity is:

[0058] F2=K2·d goal

[0059] In the above formula, F2 represents gravity, K2 represents the gravitational coefficient, and d goal This indicates the distance to the target point, which in this invention is the fuel pile.

[0060] Step S48: Plan the flight path of the second UAV based on the repulsive field and the gravitational field.

[0061] In this embodiment, multiple second UAVs work collaboratively, and given the large volume of vehicles entering and exiting a large coal yard, it is necessary for the second UAVs to effectively avoid obstacles. This invention constructs a dynamic potential energy field to effectively model and represent the environmental information surrounding the UAVs. By considering factors such as the position, shape, and size of obstacles, a virtual force field environment is constructed for the UAVs. The UAVs can then make obstacle avoidance decisions in real time based on the potential field conditions at their current location. For example, if a working vehicle suddenly appears in the coal yard, it will generate a new repulsive force area in the potential field. The UAVs can sense this change and adjust their flight path in time to avoid the vehicle, thereby achieving local real-time obstacle avoidance and preventing interference with metering operations.

[0062] Step S5: Determine the type of the corresponding fuel stack based on the matching result to obtain type information;

[0063] In this step, after the second UAV is matched, the second UAV can determine the type of fuel pile by performing an initial scan of the fuel pile's height.

[0064] Step S6: Plan the scanning trajectory of the second UAV to scan the fuel pile according to the type information, and calculate the weight of the fuel pile according to the point cloud data collected by the scan.

[0065] Step S6 further includes steps S61, S62, and S63, which specifically include:

[0066] Step S61: When the type information is a tall fuel pile, obtain the surface slope information of the fuel pile, wherein the tall fuel pile is a fuel pile with a height greater than a height threshold.

[0067] Step S62: Determine whether the surface slope information of the fuel pile is greater than the angle threshold, and obtain the determination result;

[0068] In this step, the angle threshold is set to 45°.

[0069] Step S63: Plan the scanning trajectory of the fuel pile based on the judgment result.

[0070] In this step, for tall fuel piles, the scanning trajectory is unfolded starting from the top of the coal pile according to the Archimedes spiral equation to ensure that there are no blind spots at the top of the coal pile. When the slope of the coal pile surface is greater than 45°, the number of scanning circles is increased, that is, the pitch is reduced, to prevent the loss of data on the side of the coal pile, ensure the integrity of the scanning data, thereby improving the quality of point cloud data and ensuring measurement accuracy.

[0071] Understandably, when the surface slope information of the fuel pile is less than the angle threshold, a parallel flight path mode is adopted, covering the coal pile surface in an "S" shaped path. The flight path spacing is calculated based on the lidar field of view, specifically:

[0072]

[0073] In the above formula, X represents the flight path spacing, H represents the flight altitude of the second UAV, and θ represents the field of view of the lidar. By reasonably calculating the flight path spacing, effective coverage scanning of low coal piles can be achieved.

[0074] In this embodiment, different scanning strategies are adopted to adapt to coal piles of different shapes, which can effectively improve the efficiency, safety and scanning quality of UAVs in coal yard operations, thereby further improving measurement accuracy.

[0075] Step S6 further includes steps S64, S65, S66, S67, and S68, which specifically include:

[0076] Step S64: Obtain a multispectral image of the fuel stack;

[0077] Step S65: Extract features from the multispectral image of the fuel pile to obtain multispectral texture features;

[0078] In this step, there are no restrictions on the method of feature extraction from the multispectral image.

[0079] Step S66: Segment the fuel pile according to the multispectral texture features and point cloud data to obtain the segmented fuel pile;

[0080] Understandably, point cloud data needs to be preprocessed before it can be used. This includes: firstly, noise reduction, which removes outliers by statistical filtering (removing point clouds with a mean distance greater than 3σ); then, registration, which stitches together the point clouds of multiple drones into a complete coal yard model based on the NDT algorithm. After preprocessing the point cloud data, the processed point cloud data and multispectral texture features are sent to the segmentation model. An attention mechanism layer is added to the network structure to enhance the extraction of coal pile boundary features and output the fuel pile ID to which each point belongs. This invention combines spectral texture features to segment contiguous fuel piles to improve the accuracy of establishing a three-dimensional density field. It should be noted that the segmentation model selected is the PointNet++ model.

[0081] Step S67: Establish a three-dimensional density field based on the segmented fuel pile;

[0082] Step S67 further includes steps S671, S672, S673, S674, and S675, which specifically include:

[0083] Step S671: Obtain the multispectral image corresponding to the segmented fuel pile;

[0084] Step S672: Send the multispectral image corresponding to the segmented fuel pile to the partial least squares regression model to obtain ash content information;

[0085] In this step, a partial least squares regression model can be used to establish a mapping relationship between multispectral images and actual ash content, thereby enabling the rapid acquisition of ash content information based on the mapping relationship.

[0086] Step S673: Obtain the moisture content information corresponding to the segmented fuel pile;

[0087] Step S674: Calculate the density information based on the moisture content information, the ash content information, and the fuel pile reference density;

[0088] In this step, the density information is calculated as follows:

[0089] ρ=ρ0×(1-αM)×(1-βN)

[0090] In the above formula, ρ represents density information, ρ0 represents the fuel pile reference density, α and β are empirical correction coefficients, M represents moisture content information, N represents ash content information, and ρ0 can be obtained from a historical database.

[0091] Step S675: Establish a three-dimensional density field based on the density information.

[0092] In this step, a three-dimensional density field is generated based on the Kriging algorithm. The technique of generating a three-dimensional density field using the Kriging algorithm is well known to those skilled in the art, so it will not be described in detail here.

[0093] Step S68: Calculate the weight of the fuel pile based on the three-dimensional density field.

[0094] Understandably, before calculating the weight of the fuel stack using a three-dimensional density field, actual sampling is used to calibrate and correct the three-dimensional density field, thereby improving the accuracy of the weight calculation. The specific process is as follows: calculate the confidence level of each point in the three-dimensional density field to obtain confidence level information; map the confidence level information onto the three-dimensional space of the fuel stack to generate a density field confidence map; use a Monte Carlo sampling algorithm to filter the sampling points in the density field confidence map to obtain a filtering result, which includes at least three sampling points, with sampling locations including the surface layer, middle layer, and core layer; and use an acoustic probe to analyze the filtered results. The sampling points included in the result are sampled to obtain the sample density; the three-dimensional density field is corrected according to the sample density to obtain the corrected three-dimensional density field. The acoustic probe is mounted on the robot, which can plan a collision-free path using the A* algorithm based on the generated three-dimensional risk map and real-time obstacle information, ensuring that the robot can safely and efficiently reach the target coal pile and realize the automation of the entire flow field. It should be noted that the Kalman filter fusion method is used to compare the measured density with the density in the previous three-dimensional density field, thereby updating the density field model parameters. The specific process is as follows:

[0095] ρ new =ρ old +K(ρ m -ρ)

[0096] In the above formula, ρ new and ρ old Let ρ represent the density of the current iteration and the density of the previous iteration, respectively. K represents the Kalman gain, which can be dynamically adjusted based on historical errors to continuously optimize the density field model. m ρ represents the measured sample density, and ρ represents the density in the three-dimensional density field. By continuously iterating the model, the accuracy of the generated density is improved, thereby generating a corrected three-dimensional density field, making the measurement of the fuel pile more accurate.

[0097] Following step S6, the system further includes steps S7, S8, S9, and S10, which specifically include:

[0098] Step S7: Obtain environmental parameters and fuel stack attribute parameters;

[0099] Step S8: Obtain a preset weathering loss model, which is used to predict weight loss at future times.

[0100] In this step, the preset weathering loss model includes a physical model and a machine learning model, wherein the physical model is:

[0101]

[0102] In the above formula, k(T) represents the oxidation rate at temperature T, A represents the pre-exponential factor, which reflects the probability of effective collisions between molecules per unit time; E represents the activation energy; R represents the gas constant; γ represents the humidity correction factor; and L represents the humidity.

[0103] The machine learning model employs an LSTM (Long Short-Term Memory) network to capture complex nonlinear relationships. Input features include CHMI (Cumulative Temperature and Humidity Index), wind speed, coal type code, storage time, and initial density. The output is the density decay rate over the next 7 or 30 days. It should be noted that CHMI represents the Cumulative Temperature and Humidity Index, which comprehensively reflects the long-term impact of temperature and humidity on fuel weathering. The weathering loss model is constructed by fusing the physical model and the machine learning model, specifically as follows:

[0104] Δρ=ω·Δρ 物理 +(1-ω)·Δρ LSTM

[0105] In the above formula, Δρ represents the density decay rate output by the weathering loss model. 物理 Δρ represents the density decay rate output by the physical model. LSTM ω represents the density decay rate of the machine learning model output, and ω represents the weight parameter, which is adjusted according to the stability of the environment. When the environment is stable, the value of ω is biased towards the physical model; when the environment changes abruptly, the value is biased towards the machine learning model.

[0106] Understandably, when training the weathering loss model, at least one year of historical coal yard monitoring data is used, which covers the weathering conditions of different seasons and different coal types. At the same time, accelerated aging data from the laboratory is used to simulate the coal aging process under different conditions through a constant temperature and humidity chamber to enrich the training data.

[0107] Step S9: Send the environmental parameters and the fuel pile attribute parameters to the preset weathering loss model to obtain the prediction results;

[0108] In this step, environmental parameters are collected hourly, and the coal pile morphology data is updated daily using fuel pile attribute parameters obtained through drone scanning. Based on the input data, the weight loss curve for future moments is output, thereby predicting the future weight loss of the coal pile.

[0109] Step S10: Calculate the fuel pile weight at future times based on the prediction results.

[0110] In this embodiment, since the weight and quality decrease due to factors such as weathering during storage, accurate prediction of weathering loss allows for real-time and precise monitoring of the actual fuel stockpile inventory. This avoids inventory data deviations caused by inaccurate calculation of weathering loss, enabling managers to have a clear understanding of the actual usable resources in the coal yard. This allows for the rational arrangement of production plans and resource allocation, preventing production disruptions due to insufficient inventory or resource waste caused by inventory buildup.

[0111] Example 2:

[0112] like Figure 2 As shown, this embodiment provides a fuel metering system for a coal yard. The system includes an acquisition module 901, a first processing module 902, a second processing module 903, a third processing module 904, a fourth processing module 905, and a fifth processing module 906, specifically including:

[0113] The acquisition module 901 is used to acquire real-time information collected by the first UAV, including the location of obstacles, dust concentration, and wind speed information;

[0114] The first processing module 902 is used to build a three-dimensional risk map based on the real-time information collected by the UAV. The three-dimensional risk map includes all fuel piles in the coal yard that need to be weighed.

[0115] The second processing module 903 is used to divide the three-dimensional risk map to obtain several sub-three-dimensional risk maps;

[0116] The third processing module 904 is used to match the sub-3D risk map to be detected by the second UAV using an auction algorithm to obtain the matching result;

[0117] The fourth processing module 905 is used to determine the type of the corresponding fuel stack based on the matching result and obtain type information;

[0118] The fifth processing module 906 is used to plan the scanning trajectory of the second UAV to scan the fuel pile according to the type information, and to calculate the weight of the fuel pile according to the point cloud data collected by the scan.

[0119] In one specific embodiment of this disclosure, the third processing module further includes a first acquisition unit, a first processing unit, and a second processing unit, specifically comprising:

[0120] The first acquisition unit is used to acquire attribute information of each second UAV, including location information, power information and sensor type;

[0121] The first processing unit is used to determine the bidding price of each second UAV based on the attribute information of each second UAV, and obtain the bidding price information;

[0122] The second processing unit is used to match the sub-3D risk map to be detected for each UAV based on the auction price information.

[0123] In one specific embodiment of this disclosure, the second processing unit is followed by a third processing unit, a fourth processing unit, a fifth processing unit, a sixth processing unit, and a seventh processing unit, specifically including:

[0124] The third processing unit is used to obtain obstacle type information;

[0125] The fourth processing unit is used to determine the repulsion coefficient of the obstacle based on the type information of the obstacle;

[0126] The fifth processing unit is used to generate a repulsive field around the obstacle based on the repulsive force coefficient of the obstacle;

[0127] The sixth processing unit is used to generate a gravitational field at the corresponding fuel pile in the sub-3D risk map;

[0128] The seventh processing unit is used to plan the flight path of the second UAV based on the repulsive field and the gravitational field.

[0129] It should be noted that the specific methods by which each module performs operations in the system described in the above embodiments have been described in detail in the embodiments related to the method, and will not be elaborated here.

[0130] Example 3:

[0131] Corresponding to the above method embodiments, this embodiment also provides a fuel metering device for a coal yard. The fuel metering device for a coal yard described below and the fuel metering method for a coal yard described above can be referred to in correspondence.

[0132] Figure 3 This is a block diagram illustrating a fuel metering device 800 for a coal yard according to an exemplary embodiment. Figure 3 As shown, the fuel metering device 800 of the coal yard may include: a processor 801 and a memory 802. The fuel metering device 800 of the coal yard may also include one or more of a multimedia component 803, an I / O interface 804, and a communication component 805.

[0133] The processor 801 controls the overall operation of the fuel metering device 800 in the coal yard to complete all or part of the steps in the aforementioned fuel metering method for the coal yard. The memory 802 stores various types of data to support the operation of the fuel metering device 800 in the coal yard. This data may include, for example, instructions for any application or method operating on the fuel metering device 800 in the coal yard, as well as application-related data such as contact data, sent and received messages, images, audio, video, etc. The memory 802 can be implemented using any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The multimedia component 803 may include a screen and an audio component. The screen may be, for example, a touchscreen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals may be further stored in the memory 802 or transmitted via the communication component 805. The audio component also includes at least one speaker for outputting audio signals. I / O interface 804 provides an interface between processor 801 and other interface modules, such as keyboards, mice, and buttons. These buttons can be virtual or physical. Communication component 805 is used for wired or wireless communication between the fuel metering device 800 and other devices in the coal yard. Wireless communication includes, for example, Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, or 4G, or a combination thereof. Therefore, the corresponding communication component 805 may include a Wi-Fi module, a Bluetooth module, and an NFC module.

[0134] In an exemplary embodiment, the fuel metering device 800 of the coal yard may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above-described fuel metering method for the coal yard.

[0135] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, which, when executed by a processor, implement the steps of the above-described coal yard fuel metering method. For example, the computer-readable storage medium may be the memory 802 including the program instructions, which may be executed by the processor 801 of the coal yard fuel metering device 800 to complete the above-described coal yard fuel metering method.

[0136] Example 4:

[0137] Corresponding to the above method embodiments, this embodiment also provides a readable storage medium. The readable storage medium described below can be referred to in conjunction with the fuel metering method for a coal yard described above.

[0138] A readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the fuel metering method for a coal yard as described in the above method embodiments.

[0139] The readable storage medium can specifically be a USB flash drive, external hard drive, read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk, or any other readable storage medium capable of storing program code.

[0140] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

[0141] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A fuel metering method for a coal yard, characterized in that, include: The system acquires real-time information collected by the first drone, including the location of obstacles, dust concentration, and wind speed information. A three-dimensional risk map is established based on the real-time information collected by the UAV. The three-dimensional risk map includes all fuel piles in the coal yard that need to be weighed. The three-dimensional risk map is divided into several sub-three-dimensional risk maps; The auction algorithm is used to match the sub-3D risk map to be detected by the second UAV to obtain the matching results; Based on the matching results, the type of the corresponding fuel stack is determined, and type information is obtained; Based on the type information, a scanning trajectory for the second UAV to scan the fuel pile is planned, and the weight of the fuel pile is calculated based on the point cloud data collected by the scan.

2. The fuel metering method for a coal yard according to claim 1, characterized in that, The auction algorithm is used to match the sub-3D risk map to be detected by the second UAV, including: Acquire the attribute information of each second UAV, including location information, battery information, and sensor type; The bidding price for each second drone is determined based on its attribute information, thus obtaining the bidding price information; The sub-3D risk map for each drone to be detected is matched based on the auction price information.

3. The fuel metering method for a coal yard according to claim 2, characterized in that, After matching the sub-3D risk map to be detected for each drone based on the auction price information, the process also includes: Obtain information about the type of obstacle; Determine the repulsion coefficient of the obstacle based on the type information of the obstacle; A repulsive field is generated around the obstacle based on the repulsive force coefficient of the obstacle; Generate a gravitational field at the corresponding fuel pile in the sub-3D risk map; The flight path of the second UAV is planned based on the repulsive field and the gravitational field.

4. The fuel metering method for a coal yard according to claim 1, characterized in that, Based on the type information, plan the scanning trajectory of the second UAV to scan the fuel pile, including: When the type information is a tall fuel pile, the surface slope information of the fuel pile is obtained. The tall fuel pile is a fuel pile with a height greater than a height threshold. Determine whether the surface slope information of the fuel pile is greater than an angle threshold, and obtain the determination result; The scanning trajectory of the fuel pile is planned based on the judgment results.

5. The fuel metering method for a coal yard according to claim 1, characterized in that, The weight of the fuel stack is calculated based on the point cloud data collected by scanning, including: Acquire multispectral images of the fuel stack; Feature extraction is performed on the multispectral image of the fuel pile to obtain multispectral texture features; The fuel pile is segmented based on the multispectral texture features and point cloud data to obtain the segmented fuel pile; A three-dimensional density field is established based on the segmented fuel pile; The weight of the fuel stack is calculated based on the three-dimensional density field.

6. The fuel metering method for a coal yard according to claim 5, characterized in that, Establishing a three-dimensional density field based on the segmented fuel pile includes: Obtain the multispectral image corresponding to the segmented fuel stack; The segmented multispectral image of the fuel stack is sent to a partial least squares regression model to obtain ash content information. Obtain the moisture content information corresponding to the segmented fuel stack; Density information is obtained by calculating based on the moisture content information, the ash content information, and the fuel pile reference density. A three-dimensional density field is established based on the density information.

7. The fuel metering method for a coal yard according to claim 1, characterized in that, After calculating the weight of the fuel stack based on the point cloud data collected by scanning, the following is included: Obtain environmental parameters and fuel stack attribute parameters; Obtain a preset weathering loss model, which is used to predict weight loss at future times; The environmental parameters and the fuel pile attribute parameters are sent to a preset weathering loss model to obtain the prediction results; The fuel stack weight at future times is calculated based on the predicted results.

8. A fuel metering system for a coal yard, characterized in that, include: The acquisition module is used to acquire real-time information collected by the first UAV, including the location of obstacles, dust concentration, and wind speed information; The first processing module is used to build a three-dimensional risk map based on the real-time information collected by the UAV. The three-dimensional risk map includes all fuel piles in the coal yard that need to be weighed. The second processing module is used to divide the three-dimensional risk map into several sub-three-dimensional risk maps; The third processing module is used to match the sub-3D risk map to be detected by the second UAV using an auction algorithm to obtain the matching result; The fourth processing module is used to determine the type of the corresponding fuel stack based on the matching result and obtain type information; The fifth processing module is used to plan the scanning trajectory of the second UAV to scan the fuel pile according to the type information, and to calculate the weight of the fuel pile according to the point cloud data collected by the scan.

9. The fuel metering system for a coal yard according to claim 8, characterized in that, The third processing module includes: The first acquisition unit is used to acquire attribute information of each second UAV, including location information, power information and sensor type; The first processing unit is used to determine the bidding price of each second UAV based on the attribute information of each second UAV, and obtain the bidding price information; The second processing unit is used to match the sub-3D risk map to be detected for each UAV based on the auction price information.

10. The fuel metering system for a coal yard according to claim 9, characterized in that, Following the second processing unit, it further includes: The third processing unit is used to obtain obstacle type information; The fourth processing unit is used to determine the repulsion coefficient of the obstacle based on the type information of the obstacle; The fifth processing unit is used to generate a repulsive field around the obstacle based on the repulsive force coefficient of the obstacle; The sixth processing unit is used to generate a gravitational field at the corresponding fuel pile in the sub-3D risk map; The seventh processing unit is used to plan the flight path of the second UAV based on the repulsive field and the gravitational field.

Images