Coal quality supervision method and system based on big data and infrared measurement

Abstract

The invention provides a coal quality supervision method and system based on big data and infrared measurement. The method comprises the following steps: establishing and storing carriage size data and empty vehicle weight data of a coal transport vehicle to a database; after the vehicle is loaded with coal, scanning the coal pile in the carriage through an infrared three-dimensional scanner to obtain surface contour data of the coal pile; calculating the loading volume of the coal pile according to the carriage size data and the surface contour data of the coal pile; the total weight of the vehicles is obtained through the truck scale, and the net weight of the coal is calculated by combining the corresponding empty vehicle weight in the database; calculating the real-time density of the currently transported coal according to the net weight and the loading volume of the coal; calling a historical density weighted average value of the same batch of the current coal from a big data platform; and comparing the real-time density with the weighted average value of the historical density, and if the deviation exceeds a preset threshold value, triggering coal quality abnormity early warning. The efficiency and accuracy of coal quality supervision are effectively improved.

Description

Technical Field

[0001] This invention relates to the field of coal quality monitoring technology, and in particular to a coal quality monitoring method and system based on big data and infrared measurement. Background Technology

[0002] Coal, as a crucial energy source and industrial raw material, directly impacts combustion efficiency, pollutant emissions, and equipment safety. Effective coal quality monitoring during procurement, transportation, and acceptance at the plant is critical for ensuring fuel quality, controlling costs, and achieving compliant operation. Traditional coal quality monitoring methods primarily rely on manual sampling and laboratory testing. A typical process involves supervisors randomly selecting coal samples and sending them to a laboratory for industrial analysis, elemental analysis, and calorific value determination. While some automated sampling and online testing equipment has emerged in recent years to improve efficiency, it remains largely limited to fixed-point, contact-based measurements, failing to integrate with vehicle identification, transportation batches, and historical data. This lack of a comprehensive, data-driven, and intelligent monitoring system covering the entire transportation process is a significant challenge. Especially during transportation, effective technical means remain lacking for rapidly, non-contactly, and comprehensively identifying coal quality anomalies.

[0003] Therefore, there is an urgent need for a coal quality monitoring method that can be automated, real-time, and continuous, and can effectively prevent cheating, in order to improve the efficiency and accuracy of coal quality monitoring. Summary of the Invention

[0004] This invention provides a coal quality monitoring method and system based on big data and infrared measurement, which addresses the shortcomings of low automation level and poor monitoring efficiency and accuracy in coal quality monitoring.

[0005] On the one hand, this invention provides a coal quality monitoring method based on big data and infrared measurement, comprising: Establish and store data on the dimensions of coal transport vehicles and their empty weights in a database; After the coal is loaded into the vehicle, the coal pile inside the truck is scanned using an infrared 3D scanner to obtain the surface contour data of the coal pile. The loading volume of the coal pile is calculated based on the dimensions of the carriage and the surface contour data of the coal pile. The total weight of the vehicle is obtained by weighing it on a truck scale, and the net weight of the coal is calculated by combining it with the corresponding empty vehicle weight in the database. Calculate the real-time density of the coal being transported based on the net weight of the coal and the loading volume. Retrieve the historical density-weighted average value of the same batch of coal as the current batch from the big data platform; The real-time density is compared with the weighted average of the historical density. If the deviation exceeds a preset threshold, a coal quality anomaly warning is triggered.

[0006] According to the coal quality monitoring method based on big data and infrared measurement provided by the present invention, before establishing and storing the cargo box size data and empty vehicle weight data of coal transport vehicles into the database, the method further includes: Collect the length, width, and height dimensions of the inner walls of coal transport vehicles and store them in the database. An infrared calibration system is installed in the empty vehicle lane to scan the external dimensions of passing empty vehicles and obtain calibration scan data; The calibration scan data is compared with the record data in the database. If the error exceeds the set range, the coal transport vehicle is prohibited from entering the heavy vehicle inspection process.

[0007] According to the coal quality monitoring method based on big data and infrared measurement provided by the present invention, the calculation of the loading volume of the coal pile includes: The infrared 3D scanner is used to acquire 3D point cloud data of the coal pile surface; Based on the carriage size data filed in the database, reconstruct the interior space model of the carriage; By registering the three-dimensional point cloud data with the interior space model of the carriage, the actual volume occupied by the coal pile is calculated as the loading volume.

[0008] According to the coal quality monitoring method based on big data and infrared measurement provided by the present invention, the step of retrieving the historical density-weighted average value of the same batch of coal as the current coal from the big data platform includes: Based on the current mining site information and batch number, extract the density records of all historical transportations of the same batch from the big data platform; The historical density data is weighted based on the time distance, and the dynamically updated weighted average density is calculated as the historical density weighted average. A density deviation threshold based on statistical analysis is set, the real-time density is compared with the weighted average density, and the coal quality anomaly warning is triggered based on the comparison result.

[0009] The coal quality monitoring method based on big data and infrared measurement provided by the present invention further includes: Record information on all coal transport vehicles that trigger coal quality anomaly warnings and subsequent manual test results; The density deviation threshold is dynamically adjusted based on the consistency between the manual test results and the system's early warning judgment. The weights of the weighted average density are updated based on the new data, so that the weighted average of the historical density is adaptively optimized.

[0010] According to the coal quality monitoring method based on big data and infrared measurement provided by the present invention, the step of comparing the calibration scan data with the record data in the database includes: If the error between the calibration scan data and the filing data is within a first preset range, a calibration prompt is generated and the filing data is automatically suggested to be corrected. If the error exceeds the second preset range, a structural anomaly alarm will be triggered, and the coal transport vehicle will be forced to exit the current inspection process until re-registration is completed.

[0011] According to the coal quality monitoring method based on big data and infrared measurement provided by the present invention, the step of calculating the net weight of coal by combining the corresponding empty vehicle weight in the database includes: The system automatically associates coal transport vehicles with corresponding data by identifying their license plate numbers and / or reading the RFID electronic tags installed on them.

[0012] According to the coal quality monitoring method based on big data and infrared measurement provided by the present invention, after triggering the coal quality anomaly warning, the method further includes: Output audible and visual alarm signals, and mark the corresponding coal transport vehicle information as abnormal on the monitoring interface; Supervisory personnel were instructed to manually sample and test the coal carried by the coal transport vehicles corresponding to the aforementioned abnormal conditions. The final coal quality data obtained from manual testing is entered into the system and stored in association with the real-time density data calculated in this study, forming a closed-loop feedback record.

[0013] According to the present invention, a coal quality monitoring method based on big data and infrared measurement is provided. The big data platform includes multiple logically related data sub-databases to support the operation of the method. The data sub-databases include at least: The vehicle archive is used to store the registered dimensions, empty vehicle weight, and calibration history of the coal transport vehicles. The transportation transaction database is used to store information on mining sites, batches, weights, volumes, and calculated densities by vehicle number. Density benchmark library is used to store and dynamically update density statistical benchmark values ​​by mining location and batch dimensions; An alarm log library is used to record all warning events and subsequent processing results.

[0014] Secondly, the present invention provides a coal quality monitoring system based on big data and infrared measurement, comprising: A module is established to create and store data on the dimensions of coal truck bodies and the weight of empty trucks into a database. The scanning module is used to scan the coal pile inside the truck bed with an infrared 3D scanner after the coal is loaded into the vehicle, and to obtain the surface contour data of the coal pile. The calculation module is used to calculate the loading volume of the coal pile based on the dimensions of the truck bed and the surface contour data of the coal pile; obtain the total weight of the vehicle through a weighbridge and calculate the net weight of the coal by combining it with the corresponding empty truck weight in the database; and calculate the real-time density of the coal being transported based on the net weight of the coal and the loading volume. The early warning module is used to retrieve the historical density-weighted average value of the same batch of coal as the current coal from the big data platform; compare the real-time density with the historical density-weighted average value, and if the deviation exceeds a preset threshold, trigger an early warning of coal quality anomalies.

[0015] Thirdly, the present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the coal quality monitoring method based on big data and infrared measurement as described above.

[0016] Fourthly, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the coal quality monitoring method based on big data and infrared measurement as described above.

[0017] Fifthly, the present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the coal quality monitoring method based on big data and infrared measurement as described above.

[0018] The coal quality supervision method and system based on big data and infrared measurement provided by this invention includes: establishing and storing the dimensions of the coal truck bed and the empty weight data of coal transport vehicles in a database; after the coal is loaded into the vehicle, scanning the coal pile inside the truck bed with an infrared 3D scanner to obtain the surface contour data of the coal pile; calculating the loading volume of the coal pile based on the dimensions of the truck bed and the surface contour data of the coal pile; obtaining the total weight of the vehicle through a weighbridge and calculating the net weight of the coal by combining it with the corresponding empty weight in the database; calculating the real-time density of the coal being transported based on the net weight and loading volume; retrieving the historical density weighted average of the same batch of coal from the big data platform; comparing the real-time density with the historical density weighted average, and triggering a coal quality anomaly warning if the deviation exceeds a preset threshold; automatically calculating the coal density through infrared scanning and weighing data, and intelligently comparing it with the historical density of the same batch in the big data platform, thereby realizing real-time, non-contact, and automated supervision of the coal quality of each truckload, avoiding the bias and lag of manual sampling, improving the efficiency and accuracy of supervision, and being applicable to anti-cheating and quality control throughout the entire coal transportation process, thus improving the efficiency and accuracy of supervision. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0020] Figure 1 This is a flowchart illustrating the coal quality monitoring method based on big data and infrared measurement provided in this embodiment; Figure 2 This is a schematic diagram of the coal quality monitoring system based on big data and infrared measurement provided in this embodiment; Figure 3 This is a schematic diagram of the structure of the electronic device provided in this embodiment. Detailed Implementation

[0021] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this 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 this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0022] Figure 1 This is a flowchart illustrating the coal quality monitoring method based on big data and infrared measurement provided in this embodiment.

[0023] like Figure 1 As shown in the figure, this embodiment provides a coal quality supervision method based on big data and infrared measurement. It creatively uses density, a key physical indicator, as a proxy variable for coal quality supervision, aiming to solve problems such as low efficiency, insufficient sampling representativeness, and high risk of human interference in traditional coal quality supervision. This achieves automated, intelligent, and contactless quality supervision throughout the entire coal transportation process. The method mainly includes the following steps: 101. Establish and store the dimensions of the coal truck body and the weight of the empty truck in the database.

[0024] Specifically, staff use precision measuring tools to collect core dimensional data of coal transport vehicles, such as the length and width of the inner walls of the cargo compartment, and the height from the floor to the top of the sideboards. They also record the vehicle's license plate number and cargo compartment identification number, temporarily linking and storing this information in a database to form a preliminary basic vehicle information structure. An infrared calibration system has been deployed in the empty vehicle lane for coal transport vehicles entering the plant area. When an empty vehicle awaiting registration passes through this lane, the system automatically performs a 360-degree scan, collecting the external dimensions of the cargo compartment, the total length of the vehicle, and accurately identifying the internal structure of the cargo compartment to obtain complete calibration scan data.

[0025] The system compares the real-time collected calibration scan data with the temporarily stored car body dimensions in the database item by item. If the error is within the first preset range (e.g., 10mm-30mm), the system generates a calibration prompt, automatically suggesting that staff correct the temporarily stored car body dimensions to ensure initial data accuracy. If the error exceeds the second preset range (e.g., 30mm), the system immediately triggers a structural anomaly alarm, forcing the coal transport vehicle to exit the current process and prohibiting it from entering the subsequent heavy vehicle inspection stage. The system requires the carrier to investigate the risk of vehicle deformation or cheating modifications, and to resubmit the basic data after completing the precision measurement.

[0026] Empty trucks that have passed infrared calibration are slowly driven across a high-standard truck scale. The scale automatically and accurately weighs the empty truck, ensuring accurate weight data. The calibrated and confirmed dimensions of the truck bed (length, width, height) and empty truck weight are uniquely linked to the vehicle's license plate number, truck identification number, and calibration record. Following a one-vehicle-one-file principle, this data is officially stored in the vehicle archive of the big data platform, forming an unalterable digital registration file for the vehicle. The database allows staff to query and verify vehicle registration data, and corrections are only permitted after a minor discrepancy is discovered during subsequent empty truck calibrations, ensuring dynamic data accuracy.

[0027] By establishing a complete process of data collection, calibration, comparison, correction / prohibition, and storage, an accurate vehicle size database and empty vehicle weight benchmark database are created. This eliminates the risk of vehicle data distortion at the source and provides core benchmark data for subsequent coal pile volume calculation and coal net weight calculation, which is the fundamental guarantee for the accuracy of the entire supervision process.

[0028] 102. After the vehicle is loaded with coal, the coal pile inside the truck bed is scanned using an infrared 3D scanner to obtain the surface contour data of the coal pile.

[0029] Specifically, after the coal is loaded, the vehicle enters the heavy vehicle inspection lane, where non-contact scanning acquires the coal pile's outline information. The coal truck smoothly drives into the designated scanning area of ​​the heavy vehicle inspection lane and stops as prompted by the system. A high-precision infrared 3D scanner is deployed on the roof of the truck in this lane, and the scanner is capable of penetrating interference such as dust generated during coal transportation. The infrared 3D scanner is activated to perform a comprehensive and rapid scan of the coal pile inside the truck. By capturing the three-dimensional spatial coordinate information of the coal pile surface, the scanner generates high-density 3D point cloud data of the coal pile surface, which fully reflects the outline shape of the coal pile. The scanned 3D point cloud data of the coal pile surface, i.e., the coal pile surface outline data, is transmitted in real time to the big data platform, and after being associated with the vehicle's identity information, it is temporarily stored in the transportation transaction database.

[0030] By acquiring coal pile contours in a non-contact and non-intrusive manner, the safety risks and pollution problems caused by manual contact with coal are avoided, while ensuring the integrity and accuracy of the contour data, providing a high-quality data source for subsequent volume calculations.

[0031] 103. Calculate the loading volume of the coal pile based on the dimensions of the car body and the surface contour data of the coal pile.

[0032] Specifically, based on the vehicle identification results, the calibrated and confirmed dimensions of the vehicle's cargo compartment's inner wall (length, width, and height) are retrieved from the vehicle database. A 3D modeling algorithm is then used to reconstruct a 3D model of the cargo compartment's interior space, clearly defining the effective loading area and automatically deducting non-loading spaces such as the reinforcing ribs on the inner wall. A professional registration algorithm precisely aligns the 3D point cloud data of the coal pile surface with the reconstructed 3D model of the cargo compartment's interior space, ensuring the coal pile's outline data is fully mapped into the cargo compartment's spatial coordinate system. Through space occupancy analysis, the actual volume occupied by the coal pile within the cargo compartment's interior space is calculated, representing the loading volume of the coal being transported. This volume data, linked to vehicle information and scanning time, is then formally stored in the transportation transaction database.

[0033] This method effectively solves the problem that traditional volume measurement cannot handle irregular coal piles, and realizes automated and accurate volume calculation, avoiding the problems of low efficiency and large errors caused by manual estimation or contact measurement.

[0034] 104. Obtain the total weight of the vehicle using a weighbridge, and calculate the net weight of the coal by combining it with the corresponding empty vehicle weight in the database.

[0035] Specifically, after a coal-loaded vehicle leaves the scanning area, it slowly passes through a high-standard truck scale. The scale automatically and accurately measures and records the vehicle's total weight, and the measurement data is uploaded to a big data platform in real time. The vehicle's license plate number is automatically identified by a camera installed next to the scale, or by reading information from a pre-installed RFID tag on the vehicle. This uniquely associates the vehicle being weighed with the registered data in the vehicle database, ensuring error-free data matching. Based on the association result, the system automatically retrieves the calibrated empty vehicle weight data from the vehicle database and performs the calculation using a built-in automated program: Net Coal Weight = Total Weight Measured by the Scale - Empty Vehicle Weight Retrieved from the Database. The calculated net coal weight data is then linked with vehicle information, total weight data, weighing time, etc., and stored in the transportation transaction database, forming a complete weight data chain.

[0036] By automating the collection and calculation of weight data, eliminating the need for human intervention, errors and cheating during manual recording and calculation are avoided, ensuring the authenticity and reliability of coal net weight data.

[0037] 105. Calculate the real-time density of the coal being transported based on its net weight and loading volume.

[0038] Specifically, the system automatically retrieves the net weight and loading volume data of the coal being transported from the transportation transaction database, ensuring the uniqueness and accuracy of the data. Following the fixed formula of real-time coal density = net weight / loading volume, the system automatically performs calculations to quickly obtain the real-time density value of the coal. This calculated real-time density data is then comprehensively correlated with the vehicle's identification information, transportation mine information, batch number, net weight data, and volume data, and stored together in the transportation transaction database, providing a complete basis for subsequent data comparisons.

[0039] By transforming abstract coal quality indicators into quantifiable and directly comparable densities, it provides a core basis for judging coal quality anomalies, and the calculation process is automated, leaving no room for human intervention.

[0040] 106. Retrieve the historical density-weighted average value of the same batch of coal as the current coal from the big data platform.

[0041] Specifically, based on the mine location information and batch number in the current transportation record, the source attribute of the current coal is clarified to ensure the relevance of the comparison benchmark. From the transportation transaction database of the big data platform, all historical transportation density records of the same mine location and batch as the current coal are accurately extracted, i.e., real-time density data of all trains prior to this batch. A weighted average algorithm is used to process the extracted historical density data, assigning different weights based on time proximity, with higher weights for recent transportation density data (e.g., data from the last 3 days has a higher weight than data from 1 month ago). An automatically calculated, dynamically updated weighted average density is obtained, which is the historical density weighted average. The calculated historical density weighted average is stored in the density benchmark database of the big data platform. This database also stores statistical information such as the sample size and standard deviation of density data for each batch of coal, providing a reference for threshold setting. Based on statistical analysis methods, combined with the standard deviation and fluctuation range of the coal density for this batch, a reasonable preset density deviation threshold (e.g., ±3%) is set to provide a judgment standard for subsequent comparisons.

[0042] By using dynamically updated weighted average density as the comparison benchmark, rather than a fixed standard value, it can accurately reflect the slight natural fluctuations in the source of coal, avoiding misjudgments caused by normal fluctuations in the quality of coal at the source. At the same time, relying on the collaboration of multiple sub-databases of the big data platform, it ensures that the benchmark data retrieval is efficient and accurate.

[0043] 107. Compare the real-time density with the weighted average of historical densities. If the deviation exceeds the preset threshold, trigger a coal quality anomaly warning.

[0044] Specifically, the current real-time density of coal is compared with the weighted average of historical densities in real time, and the deviation between the two is calculated: Deviation = |Real-time density - Weighted average of historical density| / Weighted average of historical density × 100%) If the deviation value is within the preset threshold range, the quality of the transported coal is determined to be normal, the system does not trigger an early warning, and sends a normal coal quality notification to the monitoring terminal, allowing the vehicle to proceed with the subsequent unloading or plant entry process. If the deviation value exceeds the preset threshold, the coal quality is determined to be at risk of abnormality, and the system immediately activates the coal quality abnormality early warning mechanism. Simultaneously, the audible and visual alarm device is triggered, emitting a continuous alarm sound and flashing lights. At the same time, the information of the coal transport vehicle, including license plate number, batch number, real-time density, historical density weighted average, and deviation value, is prominently displayed on the monitoring interface as an abnormal status, facilitating quick location by supervisors.

[0045] The monitoring terminal sends verification task prompts to supervisors, guiding them to manually sample the coal carried by the abnormal vehicle and send it to the laboratory for core quality tests such as industrial analysis, elemental analysis, and calorific value determination. The final coal quality data obtained from the manual tests is entered into the system and comprehensively linked and stored with the real-time density data, early warning records, vehicle information, and transportation information to form a complete closed-loop feedback record, which is then stored in the alarm log database.

[0046] For each new batch of coal from the same mine, the system automatically recalculates the historical density-weighted average for that batch and updates it in the density benchmark database, ensuring that the benchmark density promptly reflects subtle natural fluctuations in the coal's origin. Based on the consistency between manual testing results stored in the alarm log database and the system's early warning judgments, preset thresholds are dynamically adjusted. For example, if multiple system warnings occur despite passing tests, the threshold is considered too strict, and the system automatically relaxes it appropriately; conversely, if no warning is issued but tests fail, the threshold is considered too lenient, and the system automatically tightens it appropriately. Based on the effectiveness analysis of historical data, the weighting rules for historical density data are continuously optimized to ensure that recent data and high-quality data without anomalies play a greater role in the weighted average calculation. By responding quickly and verifying accurately to abnormal situations, substandard coal is prevented from flowing into subsequent stages. At the same time, through closed-loop feedback and adaptive optimization, a virtuous cycle of data accumulation, benchmark optimization, and accurate judgment is formed. The longer the system runs, the higher the accuracy of coal quality judgment. All data is classified and stored in four sub-databases, forming a complete traceability chain to ensure the compliance and seriousness of the supervision process.

[0047] The method described in this embodiment can produce the following beneficial effects: Fully automated: From vehicle data collection, calibration, and registration to coal pile scanning, weight collection, density calculation, data comparison, early warning triggering, and system optimization, the entire process requires no manual intervention, significantly improving the efficiency of coal quality supervision and solving the problem of low efficiency in traditional manual supervision.

[0048] Non-contact inspection: Volume measurement is achieved through an infrared 3D scanner deployed on the roof of the vehicle, which adapts to the complex environment of coal transportation and avoids the safety risks and pollution problems caused by manual contact.

[0049] Outstanding anti-cheating capabilities: Through empty vehicle infrared calibration to eliminate vehicle deformation and modification cheating, automatic identity association to avoid data matching cheating, and full data traceability and tamper-proof design to prevent manual data tampering, a comprehensive anti-cheating system is built.

[0050] Accurate and reliable judgment: Based on the dynamically updated historical density-weighted average as a benchmark, combined with statistical thresholds and closed-loop optimization mechanisms, it solves the problem of insufficient representativeness of traditional manual sampling and significantly reduces the coal quality misjudgment rate.

[0051] Full traceability: Relying on the vehicle archive, transportation transaction database, density benchmark database, and alarm log database of the big data platform, all operation data, calibration records, early warning information, and test results are fully traceable and can be checked at any time, improving the modernization level of fuel management.

[0052] Figure 2 This is a schematic diagram of the coal quality monitoring system based on big data and infrared measurement provided in this embodiment.

[0053] like Figure 2 As shown in the figure, this embodiment provides a coal quality monitoring system based on big data and infrared measurement, including: Module 201 is established to create and store the dimensions of the coal truck body and the weight of the empty truck into the database; The scanning module 202 is used to scan the coal pile inside the truck bed with an infrared 3D scanner after the coal is loaded into the vehicle, and to obtain the surface contour data of the coal pile. The calculation module 203 is used to calculate the loading volume of the coal pile based on the dimensions of the truck bed and the surface contour data of the coal pile; to obtain the total weight of the vehicle through the truck scale and to calculate the net weight of the coal by combining it with the corresponding empty truck weight in the database; and to calculate the real-time density of the coal being transported based on the net weight of the coal and the loading volume. The early warning module 204 is used to retrieve the historical density-weighted average value of the same batch of coal from the big data platform; compare the real-time density with the historical density-weighted average value, and if the deviation exceeds the preset threshold, trigger an early warning of coal quality anomalies.

[0054] Figure 3 This is a schematic diagram of the structure of the electronic device provided in this embodiment.

[0055] like Figure 3As shown, the electronic device may include a processor 301, a communication interface 302, a memory 303, and a communication bus 304. The processor 301, communication interface 302, and memory 303 communicate with each other via the communication bus 304. The processor 301 can call logical instructions stored in the memory 303 to execute a coal quality monitoring method based on big data and infrared measurement.

[0056] Furthermore, the logical instructions in the aforementioned memory 303 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, essentially, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0057] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer is able to execute the coal quality monitoring method based on big data and infrared measurement provided by the above methods.

[0058] In another aspect, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to perform the coal quality monitoring method based on big data and infrared measurement provided by the above methods.

[0059] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0060] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0061] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A coal quality monitoring method based on big data and infrared measurement, characterized in that, include: Establish and store data on the dimensions of coal transport vehicles and their empty weights in a database; After the coal is loaded into the vehicle, the coal pile inside the truck is scanned using an infrared 3D scanner to obtain the surface contour data of the coal pile. The loading volume of the coal pile is calculated based on the dimensions of the carriage and the surface contour data of the coal pile. The total weight of the vehicle is obtained by weighing it on a truck scale, and the net weight of the coal is calculated by combining it with the corresponding empty vehicle weight in the database. Calculate the real-time density of the coal being transported based on the net weight of the coal and the loading volume. Retrieve the historical density-weighted average value of the same batch of coal as the current batch from the big data platform; The real-time density is compared with the weighted average of the historical density. If the deviation exceeds a preset threshold, a coal quality anomaly warning is triggered.

2. The coal quality monitoring method based on big data and infrared measurement according to claim 1, characterized in that, Before establishing and storing the cargo box size data and empty vehicle weight data of coal transport vehicles into the database, the following steps are also included: Collect the length, width, and height dimensions of the inner walls of coal transport vehicles and store them in the database. An infrared calibration system is installed in the empty vehicle lane to scan the external dimensions of passing empty vehicles and obtain calibration scan data; The calibration scan data is compared with the record data in the database. If the error exceeds the set range, the coal transport vehicle is prohibited from entering the heavy vehicle inspection process.

3. The coal quality monitoring method based on big data and infrared measurement according to claim 1, characterized in that, The calculation of the loading volume of the coal pile includes: The infrared 3D scanner is used to acquire 3D point cloud data of the coal pile surface; Based on the carriage size data filed in the database, reconstruct the interior space model of the carriage; By registering the three-dimensional point cloud data with the interior space model of the carriage, the actual volume occupied by the coal pile is calculated as the loading volume.

4. The coal quality monitoring method based on big data and infrared measurement according to claim 1, characterized in that, The process of retrieving the historical density-weighted average value of the same batch of coal from the big data platform includes: Based on the current mining site information and batch number, extract the density records of all historical transportations of the same batch from the big data platform; The historical density data is weighted based on the time distance, and the dynamically updated weighted average density is calculated as the historical density weighted average. A density deviation threshold based on statistical analysis is set, the real-time density is compared with the weighted average density, and the coal quality anomaly warning is triggered based on the comparison result.

5. The coal quality monitoring method based on big data and infrared measurement according to claim 4, characterized in that, Also includes: Record information on all coal transport vehicles that trigger coal quality anomaly warnings and subsequent manual test results; The density deviation threshold is dynamically adjusted based on the consistency between the manual test results and the system's early warning judgment. The weights of the weighted average density are updated based on the new data, so that the weighted average of the historical density is adaptively optimized.

6. The coal quality monitoring method based on big data and infrared measurement according to claim 2, characterized in that, The step of comparing the calibration scan data with the record data in the database includes: If the error between the calibration scan data and the filing data is within a first preset range, a calibration prompt is generated and the filing data is automatically suggested to be corrected. If the error exceeds the second preset range, a structural anomaly alarm will be triggered, and the coal transport vehicle will be forced to exit the current inspection process until re-registration is completed.

7. The coal quality monitoring method based on big data and infrared measurement according to claim 1, characterized in that, The calculation of the net weight of coal, based on the corresponding empty vehicle weights in the database, includes: The system automatically associates coal transport vehicles with corresponding data by identifying their license plate numbers and / or reading the RFID electronic tags installed on them.

8. The coal quality monitoring method based on big data and infrared measurement according to claim 1, characterized in that, After triggering the coal quality anomaly warning, the following are also included: Output audible and visual alarm signals, and mark the corresponding coal transport vehicle information as abnormal on the monitoring interface; Supervisory personnel were instructed to manually sample and test the coal carried by the coal transport vehicles corresponding to the aforementioned abnormal conditions. The final coal quality data obtained from manual testing is entered into the system and stored in association with the real-time density data calculated in this study, forming a closed-loop feedback record.

9. The coal quality monitoring method based on big data and infrared measurement according to any one of claims 1-8, characterized in that, The big data platform comprises multiple logically related data sub-databases to support the operation of the method. Each data sub-database includes at least: The vehicle archive is used to store the registered dimensions, empty vehicle weight, and calibration history of the coal transport vehicles. The transportation transaction database is used to store information on mining sites, batches, weights, volumes, and calculated densities by vehicle number. Density benchmark library is used to store and dynamically update density statistical benchmark values ​​by mining location and batch dimensions; An alarm log library is used to record all warning events and subsequent processing results.

10. A coal quality monitoring system based on big data and infrared measurement, characterized in that, include: A module is established to create and store data on the dimensions of coal truck bodies and the weight of empty trucks into a database. The scanning module is used to scan the coal pile inside the truck bed with an infrared 3D scanner after the coal is loaded into the vehicle, and to obtain the surface contour data of the coal pile. The calculation module is used to calculate the loading volume of the coal pile based on the dimensions of the truck bed and the surface contour data of the coal pile; obtain the total weight of the vehicle through a weighbridge and calculate the net weight of the coal by combining it with the corresponding empty truck weight in the database; and calculate the real-time density of the coal being transported based on the net weight of the coal and the loading volume. The early warning module is used to retrieve the historical density-weighted average value of the same batch of coal as the current coal from the big data platform; compare the real-time density with the historical density-weighted average value, and if the deviation exceeds a preset threshold, trigger an early warning of coal quality anomalies.

Images