Mine loading vehicle weighing automatic metering system and method based on light field technology

Abstract

The invention belongs to the technical field of logistics management, and particularly relates to a mine loading vehicle weighing automatic metering system and method based on a light field technology, and the system comprises a light field intelligent detection device, a weighing system, a loading vehicle, and a blocking control system. Three-dimensional data of a vehicle are collected through a light field camera array, the volume and weight of the material are calculated in real time in combination with a deep learning algorithm, and high-precision load metering is achieved through dual verification with wagon balance data. And a self-adaptive grid algorithm and density deviation detection are adopted, so that theft or overload behaviors can be effectively identified. The system can still operate stably in a dust concentration environment, the volume metering precision reaches + / -0.8%, the weight verification error is smaller than or equal to + / -1%, the mine weighing efficiency and safety are remarkably improved, and manual intervention is reduced.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of mine logistics management, and particularly relates to a mine loading vehicle weighing automatic measurement system and method based on light field technology. BACKGROUND

[0002] In the process of mine production, accurate measurement of material transportation is the core link of logistics management. The traditional weighing method relies on manual operation, which has the problems of low efficiency (single time consumption > 3 minutes), high human error rate (± 5%-8%), and easy to be disturbed by subjective factors.

[0003] After searching, it is found that the patent with publication number CN119648101A discloses a factory transportation vehicle unloading real-time monitoring system, which includes: through automatic identification combined with manual intervention, realizing full-process closed-loop management, generating a transportation scheduling scheme containing license plate, driver, time and goods details according to the order, after the vehicle loads according to the plan and drives into the loading area outlet, the system automatically captures vehicle information and compares with the scheduling data, and if the matching is successful, it is released to the unloading area; if the first captured information is missing or incorrect, the vehicle needs to exit and be verified again, and if it fails twice, manual investigation is triggered, and after correction, it reenters the verification process. After arriving at the unloading area, the system captures and verifies the scheduling information again, and if the matching is successful, it can unload and mark the task as completed; if the identification is abnormal, it needs to be repeated or handled manually, ensuring that all errors are corrected in the closed loop. This method improves the accuracy, real-time performance and abnormal response efficiency of factory logistics through multi-node verification in the three stages of loading, transportation and unloading, combined with automatic identification and manual backup mechanism. However, the core defect of this system is that it relies on two-dimensional image recognition technology for material monitoring, which lacks three-dimensional space information acquisition capability, making it impossible to establish an accurate material volume estimation model. The physical correlation between two-dimensional plane data and material weight is difficult to effectively fit through algorithm. More seriously, this technical architecture lacks a mechanism to identify material density anomalies - when high-density materials are replaced by low-density substances (such as sand and straw) during transportation, the system can only identify surface image changes and cannot perform substantive verification through the density-volume relationship model. This technical defect has caused many monitoring loopholes and disputes over the value difference. The patent with publication number CN117606595A discloses an unattended load cell weighing system and method based on intelligent weighing algorithm, which is similar to patent CN119648101A, and only has a single source of weight information acquisition, which cannot solve the problem of human tampering with weighing equipment measurement data.

[0004] To solve the above problems, the present application provides a mine loading vehicle weighing automatic measurement system based on light field technology, which realizes three-dimensional point cloud reconstruction accuracy ±2mm in a dusty environment by using a light field camera, and establishes an abnormal detection mechanism based on the comparison between the algorithm and the load cell data, to solve the problem of human theft of minerals during the weighing of mine loading vehicles. SUMMARY

[0005] The present application aims to provide a mine loading vehicle weighing automatic measurement system and method based on light field technology, which realizes the automation and intelligentization of material weighing through light field technology, improves the weighing efficiency and accuracy, reduces human error, and effectively prevents illegal activities such as stealing materials; The light field intelligent detection device is installed on the top of the weighing area shed frame, used for real-time collection of three-dimensional light field data of the carriage shape and material distribution of the mine loading vehicle, and calculation of the material volume and weight through a deep learning algorithm. The light field intelligent detection device comprises a light field collection module, an intelligent analysis and decision module, a data storage module, a communication module and an alarm module. The weighbridge weighing system is arranged in the upper weighing area and the lower weighing area, comprising a data acquisition unit, a weighbridge sensor and a signal transceiver, used for obtaining vehicle load data through the difference between two weighing values. The loading vehicle is used for transporting ore materials. The blocking control system comprises a blocking rod, a transmission device and a signal transceiver, used for receiving instructions and controlling the vehicle to drive away from the weighing area. The light field intelligent detection device reconstructs the three-dimensional model of the carriage through point cloud data, calculates the weight in combination with the material density, and compares the weight data with the weight data of the weighbridge weighing system, to realize double verification of the load. All modules communicate through a switch and an optical fiber network to complete data interaction and control instruction transmission.

[0006] Further, the light field collection module comprises a 5x5 array of high-resolution light field cameras to collect four-dimensional light field data at a refresh rate of 60Hz , covering an area of 8m x 6m x 4m, with a spatial resolution of ±2mm; Further, the image processing unit is used for denoising, enhancing and segmenting the light field data to extract the carriage contour and material surface features; Further, the deep learning recognition unit recognizes the license plate number, vehicle model and material type based on a convolutional neural network; Further, the volume calculation unit uses an adaptive octree grid algorithm to calculate the material volume in real time ; Further, the density checking unit matches the preset density according to the material type , if the measured density and deviation exceeds ±10%, it is determined to be abnormal.

[0007] Further, the alarm module comprises an audible and visual alarm and a visual interface, when overload, abnormal density or license plate information is detected, the alarm is triggered and the data flow is frozen, and the abnormal data is stored in the edge server.

[0008] Further, the wagon balance sensor adopts a strain gauge type pressure sensor, the measurement accuracy is ±0.1%, the range is 0-100 tons, and the signal sampling frequency is 100Hz.

[0009] Further, the barrier control system adjusts the lifting speed of the barrier rod through a PID controller, the response time is ≤0.5s, and the positioning accuracy is ±1mm.

[0010] An automatic measurement and identification method for loading vehicle weighing based on light field technology, according to the automatic measurement system for loading vehicle weighing based on light field technology, characterized in that it comprises the following steps: S1. Vehicle entry detection When the vehicle enters the weighing area, the light field intelligent detection device is activated, and the panoramic light field data of the vehicle is collected; Call the deep learning algorithm to identify the license plate and vehicle type, and match the database to obtain the vehicle parameter template; S2. Empty load reference modeling: The wagon balance system collects empty vehicle data ; The light field intelligent detection device scans the empty vehicle compartment to generate an empty load three-dimensional model , and sends a signal to lift the rod and release; S3. Heavy vehicle load measurement: After the vehicle is loaded with ore, it drives into the lower weighing area, and the wagon balance system collects the total weight ; Synchronously scan the heavy vehicle compartment to generate point cloud data, calculate the loading volume and weight ; Check , if the difference is too large, an alarm will be triggered; S4. Data closed loop and output: Generate a digital measurement certificate, including timestamp, license plate number, material type, volume and weight data; When abnormal working conditions occur, store the original point cloud and analysis report to the edge server; S5. Vehicle departure control: After the check is passed, the barrier rod is lifted, the vehicle state is updated to "has been measured", and the vehicle drives away from the weighing area.

[0011] Compared with the prior art, the present application has the following advantages and technical effects: Firstly, the system has high degree of automation, significantly reduces manual intervention, reduces human error, improves weighing efficiency, and is particularly suitable for high-frequency mine transportation scenarios, which can effectively cope with the weighing demand of a large number of vehicles; secondly, the system uses light field-IMU fusion perception technology combined with deep learning algorithm, reduces the vehicle stability judgment error to 1 / 8 of the traditional scheme, and realizes load measurement through three-dimensional difference algorithm, with a relative error of ≤0.7%, which significantly improves the accuracy and reliability of vehicle and material identification, and effectively solves the limitations of traditional two-dimensional image recognition technology; in addition, the system is based on the four-layer architecture of "perception-modeling-computing-verification", realizes full closed-loop control of the measurement process, and the single measurement cycle is <90 seconds, which is more than 50% shorter than the industry standard, can monitor and analyze the weighing data in real time, and compare the scanning results with the weighing data to find abnormal situations such as material stealing behavior in time, improve the safety and reliability of mine management, and provide strong technical support for mine enterprises; the system also has strong environmental adaptability and can work stably in complex mine environment, unaffected by environmental factors such as light and dust, ensuring the reliability and stability of the system; in terms of data management, the system builds an audit chain through blockchain distributed storage technology to ensure that the measurement data is traceable and tamper-proof throughout the process, while supporting data query, statistics and analysis to provide decision support for mine management, and through the communication module, the system shares data with external systems such as mine production management system and financial system for collaborative management, improving the overall management level of the mine; in terms of safety, the system has an automatic alarm function that can send an alarm signal in time when an abnormal situation is detected, reminding the staff to handle it, avoiding potential safety hazards and ensuring the safe and stable operation of mine production; in terms of preventing illegal behavior, the system can effectively identify material stealing behavior through intelligent comparison of high-precision scanning results and weighing data, protecting the legal rights and interests of enterprises and providing strong technical support for mine enterprises; in addition, the present application simplifies the weighing process, reduces operating costs, improves economic efficiency, and has significant economic advantages; finally, the present application promotes the intelligent construction of mines and improves the overall technical level of the industry, leading the mine industry to develop in the direction of intelligence and automation, and has broad application prospects and important industry significance. BRIEF DESCRIPTION OF DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed in the embodiments. Obviously, the drawings described below are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor: Fig. 1 Flowchart of the mine vehicle weighing automatic measurement system and method based on light field technology of the present application; Fig. 2 The system architecture of the present application is shown in the figure; Fig. 3 The operation flowchart of the present application is shown in the figure; DETAILED DESCRIPTION

[0013] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0014] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the present application will be further described in detail below with reference to the drawings and specific embodiments.

[0015] With reference to Figs. 1 to 3 The embodiment discloses a mine loading vehicle weighing automatic metering system and method based on light field technology, which comprises: a light field intelligent detection device installed on the top of a shed frame, which collects the material form and volume in the mine loading vehicle based on deep learning, calculates the weight, and sends signals to a weighbridge weighing system and a blocking control system. The weight data obtained by the weighbridge weighing system is compared, and signals are sent to the blocking control system to guide the vehicle to drive away from the weighing area. All signals are controlled through a switch and an optical fiber. The light field intelligent detection device comprises a light field acquisition module, a graphic processing module, an intelligent analysis and decision module, a data storage module, a communication module and an alarm module. The weighbridge weighing system is used for collecting the weight of the vehicle and is placed at the weighing-in place and the weighing-out place respectively. The load data is obtained by the difference between the two weighing. The weighbridge weighing system comprises a data acquisition unit, a weighbridge sensor and a signal transceiver. The blocking control system is used for receiving signals and guiding the vehicle to start and stop, and comprises a blocking signal transceiver, a blocking rod and a transmission device. Two systems are respectively arranged at the weighing-in place and the weighing-out place to identify the material information, so that the mine material weighing automatic metering and identification are quickly realized.

[0016] In the application example of mine material weighing, the mine material weighing automatic metering and identification system and method based on light field technology realize automatic and intelligent operation through the following process: Firstly, when a material transport vehicle enters the first weighing area, the light field intelligent detection device installed on the shed frame moves quickly, the light field information in the shed frame is collected through the light field acquisition module, the obtained information is converted into signals through the graphic processing module, the vehicle head contour and the vehicle body are identified based on the intelligent analysis and decision module, it is confirmed that the signal of the vehicle entering the field is received, and the whole process is 5s.

[0017] Secondly, the system automatically obtains the relevant information of the vehicle from the mine information collection system and performs matching confirmation, including the license plate number (such as "Beijing A12345") and the vehicle type (such as "heavy semi-trailer truck").

[0018] Then, the system determines whether the vehicle has stopped stably through the light field device and the load cell sensor installed in the weighing area to ensure the accuracy and safety of the scanning process; the vehicle is determined to be in a stable state by continuously scanning the edge profile of the vehicle compartment, if the pixel displacement of adjacent two frames is <5 pixels, and the sensor monitors the vehicle vibration frequency with an amplitude <0.1 mm / s² for 5 seconds; if the vehicle is not stable, the system will prompt the driver to adjust again.

[0019] Next, the empty vehicle is scanned using the light field acquisition module to obtain the volume data of the vehicle compartment. Assuming that the ground load weighing system obtains the total vehicle weight of 10 tons, the system sends the data to the light field intelligent detection device through the communication module, and the data storage module stores the data obtained by the ground load weighing system this time; assuming that the light field intelligent detection device analyzes the scanning result and obtains the material volume in the empty vehicle compartment as 0 cubic meters, the analysis result this time is also recorded in the data storage module; Subsequently, the system associates the empty vehicle volume data and the empty vehicle weight data obtained by the light field intelligent detection device and the ground load weighing system with the license plate number "Beijing A12345" of the vehicle, records the relevant data, including the time such as "January 11, 2025 13:30", the license plate number such as "Beijing A12345", the ore category such as "iron concentrate", the initial material volume as "0 m³", and the initial material weight as "0 tons", and sends them to the database through the communication module for subsequent query and comparison, and marks the vehicle as "unmeasured in the field"; When the vehicle completes the material loading and is ready to pass through the second weighing area, the system receives the signal of the vehicle entering the field again through the light field intelligent detection device installed on the shed.

[0020] The material load weighing automatic measurement and recognition system based on light field technology matches the license plate number "Beijing A12345" of the vehicle again to confirm the vehicle entering the field.

[0021] The system determines whether the vehicle has stopped stably again through the light field device and the load cell sensor installed in the weighing area to ensure the accuracy and safety of the scanning process; the vehicle is determined to be in a stable state by continuously scanning the edge profile of the vehicle compartment, if the pixel displacement of adjacent two frames is <5 pixels, and the sensor monitors the vehicle vibration frequency with an amplitude <0.1 mm / s² for 5 seconds; if the vehicle is not stable, the system will prompt the driver to adjust again.

[0022] The vehicle loaded with materials is scanned by the light field acquisition module, and the volume data of the materials in the carriage are obtained by the graphic processing module. Assuming that the intelligent analysis and decision module analyzes that the volume of the ore in the carriage is 8 cubic meters, and the density of the ore is 2.5 tons / cubic meter, the weight of the loaded materials is calculated as 20 tons; At the same time, the whole vehicle and material data obtained by the weighbridge weighing system through the data acquisition unit and the weighbridge sensor weighing is 25 tons, and the weighing data is sent to the light field intelligent detection device. The material weight of 20 tons obtained by the intelligent analysis and decision module is compared with the material weight of 15 tons obtained by the weighbridge weighing system. At this time, they are not consistent, indicating that there is an abnormal situation, the weighbridge system may be operated by someone, and there is a situation of stealing ore. The alarm module performs abnormal situation alarm. The light field intelligent detection device sends a signal to the barrier, and the barrier keeps the state of blocking the vehicle after receiving the signal. At the same time, the vehicle is marked as “has been metered, exists abnormality, and is waiting for verification”.

[0023] Finally, the system sends the analysis result to the database, including the time “January 11, 2025 13:40”, the license plate number “Beijing A12345”, the ore category “iron concentrate powder”, the material volume “8m³” and the material weight “abnormality”, and displays it in real time on the data platform. At this time, the barrier control system barrier rod is always in the blocking state, the relevant personnel go to the scene according to the alarm signal, confirm the existence of the stealing situation, mark the information corresponding to the license plate in the system, handle it, change the correct weight data “20 tons” in the system, then send a release signal to the system, mark “has been metered, exists abnormality, has been verified”, and store it in the archives, open the barrier, and the vehicle leaves.

Claims

1. An automatic weighing system for ore loading vehicles based on light field technology, characterized in that, include: The intelligent light field detection device is installed on the top of the weighing area rack to collect three-dimensional light field data of the shape of the cargo compartment and the distribution of materials in real time, and calculates the volume and weight of the materials through deep learning algorithms. The intelligent light field detection device includes a light field acquisition module, an intelligent analysis and decision-making module, a data storage module, a communication module and an alarm module. The weighbridge weighing system is set up in the upper and lower weighbridge areas, including a data acquisition unit, weighbridge sensors and signal transceivers, and is used to obtain vehicle load data by the difference between two weighings. Loading vehicles used for transporting ore materials; The barrier control system includes a barrier bar, a transmission device, and a signal transceiver, used to receive instructions and control the vehicle to leave the weighing area; The light field intelligent detection device reconstructs a three-dimensional model of the carriage using point cloud data, calculates the weight by combining it with the material density, and compares it with the weight data of the weighbridge system to achieve dual verification of the load. The light field acquisition module, intelligent analysis and decision-making module, data storage module, communication module, and alarm module communicate through a switch and fiber optic network to complete data interaction and control command transmission.

2. The automatic weighing system for ore loading vehicles based on light field technology according to claim 1, characterized in that, The light field acquisition module includes a 5×5 array of high-resolution light field cameras, which acquire four-dimensional light field data at a refresh rate of 60Hz. The coverage area is 8m×6m×4m, with a spatial resolution of ±2mm.

3. The automatic weighing system for ore loading vehicles based on light field technology according to claim 1, characterized in that, The intelligent analysis and decision-making module includes: The image processing unit is used to perform noise reduction, enhancement, and segmentation operations on the light field data, and to extract the outline of the carriage and the surface features of the materials. The deep learning recognition unit identifies license plate numbers, vehicle models, and material types based on convolutional neural networks. The volume calculation unit uses an adaptive octree grid algorithm to calculate the material volume in real time. ; The density verification unit matches a preset density based on the material type. If the actual density and If the deviation exceeds ±10%, it is considered abnormal. For the weight of the loaded vehicle, This refers to the weight of an empty vehicle when weighed.

4. The automatic weighing system for ore loading vehicles based on light field technology according to claim 3, characterized in that, The volume calculation unit is implemented through the following steps: Constructing a 3D geometric model of the carriage High-density point cloud data is generated based on back projection transformation; The material volume is calculated using a hierarchical integration strategy, with the grid resolution adaptively adjusted to a minimum of 5cm×5cm×5cm. Volume calculation error ≤ ±0.8%, single calculation time ≤ 5ms.

5. The automatic weighing system for ore loading vehicles based on light field technology according to claim 1, characterized in that, The alarm module includes an audible and visual alarm, which alerts the driver of the offending vehicle by sounding and visual alarms when overloading, abnormal density, or inconsistent license plate information is detected.

6. The automatic weighing system for ore loading vehicles based on light field technology according to claim 1, characterized in that, The weighbridge sensor adopts a conventional strain gauge pressure sensor design.

7. The automatic weighing system for ore loading vehicles based on light field technology according to claim 1, characterized in that, The barrier control system adjusts the lifting speed of the barrier arm through a PID controller, with a response time of ≤0.5s and a positioning accuracy of ±1mm.

8. An automatic weighing method for ore loading vehicles based on light field technology, based on the system described in any one of claims 1-7, characterized in that, Includes the following steps: S1. Vehicle entry inspection When a vehicle enters the weighing area, the intelligent light field detection device is activated to collect panoramic light field data of the vehicle. The system uses deep learning algorithms to identify license plates and vehicle models, and then matches them with a database to obtain vehicle parameter templates. S2. Unloaded baseline modeling: Weighbridge weighing system collects empty vehicle data ; The light field intelligent detection device scans empty carriages and generates empty 3D models. And send a signal to raise the barrier and allow passage; S3. Load capacity measurement for heavy vehicles: After the vehicle is loaded with ore, it enters the weighbridge area, where the weighbridge system collects the total weight. ; Simultaneously scan the loaded car body to generate point cloud data and calculate the loading volume. and weight ; check If the error exceeds the limit, an alarm will be triggered. S4. Data Closure and Output: Generate digital measurement vouchers, including timestamps, license plate numbers, material types, volume, and weight data; In case of abnormal operating conditions, store the original point cloud and analysis report to the edge server; S5. Vehicle Departure Control: After the verification is passed, the barrier is raised, the vehicle status is updated to "measured", and the vehicle leaves the weighing area.

Images