Off-line quick detection management system and method for outsourcing coal

Abstract

The invention relates to an off-line fast detection management system and method for outsourcing coal, and the system comprises a sampling vehicle which is used for responding to a sampling task, generating a corresponding sampling path, and driving to a target area along the sampling path to execute a corresponding sampling action; the scheduling platform is used for generating a sampling task based on the outsourcing order, predicting the sampling efficiency of each sampling vehicle based on the sampling task and the state data of each sampling vehicle, and determining at least one target sampling vehicle based on the sampling efficiency so as to send the sampling task to the at least one target sampling vehicle; and the off-line rapid detection system is used for detecting the target sample to obtain a coal quality detection result. Therefore, the technical problems that in the prior art, coal quality detection links are many, the process is complex, the management difficulty is large, the labor cost is high, and then follow-up production is affected are solved.

Description

Technical Field

[0001] This application relates to the field of data management technology, and in particular to an offline rapid inspection management system and method for purchased coal. Background Technology

[0002] In related technologies, coal quality testing requires multiple and complex processes, including sampling, sample preparation, and analysis. Testing is time-consuming (over 24 hours) and involves numerous personnel, posing safety and ethical risks. In the sampling stage, bulk coal collection stations still rely primarily on manual sampling, which can only collect surface coal samples, failing to collect samples from deeper layers. Furthermore, manual sampling must strictly adhere to national standards, resulting in poor sample representativeness. Overall, management processes are inconsistent and operational procedures are fragmented.

[0003] Manual sampling is too labor-intensive and has a low degree of automation. In order to meet the daily unloading volume, it is necessary to rely on 24-hour operation to make up for the time shortage. However, the number of workers in 24-hour operation is large, the intensity is high, and the safety factor of night operation is low, which urgently needs to be improved. Summary of the Invention

[0004] This application provides an offline rapid testing management system and method for purchased coal to solve the technical problems in related technologies, such as the large number of coal quality testing links, complex processes, high management difficulty, high labor costs, and thus affecting subsequent production.

[0005] The first aspect of this application provides an offline rapid testing management system for purchased coal, comprising: a sampling vehicle, configured to generate a corresponding sampling path in response to a sampling task, and travel along the sampling path to a target area to perform corresponding sampling actions; a scheduling platform, configured to generate the sampling task based on the purchase order, predict the sampling efficiency of each sampling vehicle based on the sampling task and the status data of each sampling vehicle, and determine at least one target sampling vehicle based on the sampling efficiency, so as to send the sampling task to at least one target sampling vehicle; and an offline rapid testing system, configured to test the target sample and obtain coal quality test results.

[0006] Based on the above technical means, the embodiments of this application can generate sampling tasks according to external purchase orders through a scheduling platform, and schedule sampling vehicles in combination with the status of the sampling vehicles, so as to arrange target sampling vehicles for sample collection and transportation. Through the transfer of target sampling vehicles, it is convenient for the offline rapid testing system to test the samples, so as to realize intelligent management of the whole process, reduce manual intervention, and improve sampling efficiency and data accuracy.

[0007] Optionally, in one embodiment of this application, a first acquisition module is used to collect a target sample and acquire vibration data, temperature data, humidity data, and image data of the target sample during the sampling process to generate corresponding sampling data; a judgment module is used to combine the vibration data, temperature data, humidity data, and image data to determine whether the target sample meets the preset sampling qualification conditions and obtain a judgment result; and a sampling module is used to control the sampling vehicle to take a new target sample if the judgment result indicates that the target sample does not meet the preset sampling qualification conditions.

[0008] Based on the above technical means, the embodiments of this application can determine whether the sampling of the target sampling vehicle is qualified based on the sampling data of the sampling process, and resample if it is unqualified, so as to avoid unqualified samples flowing into the next process and speed up the inspection efficiency.

[0009] Optionally, in one embodiment of this application, it further includes: a verification platform, configured to, in response to the sampling task, identify the identification information of at least one of the target sampling vehicles, and, in combination with the identification information, the sampling task, and the personnel identification of the sampling personnel, verify at least one of the target sampling vehicles, obtain a verification result, and prohibit target sampling vehicles whose verification results do not meet the preset verification pass conditions from performing the sampling action.

[0010] Based on the above technical means, the embodiments of this application can achieve comprehensive verification through a verification platform to confirm that the target sampling vehicle is in the correct location and that the sampling action is performed by the correct operator, thereby avoiding sample confusion and causing the test results to not correspond to the samples.

[0011] Optionally, in one embodiment of this application, the offline rapid testing management system for purchased coal is a consortium blockchain architecture, which associates the sampling task, the sampling data, the judgment result, the coal quality test result, and the verification result, and stores them in the blockchain of the offline rapid testing management system for purchased coal.

[0012] Based on the above technical means, the embodiments of this application can utilize a consortium blockchain architecture to achieve effective data protection. Under the consortium blockchain architecture, when any data is modified, the sampling vehicle, verification platform, scheduling platform, and offline rapid testing system of the offline rapid testing management system for purchased coal need to be associated and verified to ensure data security.

[0013] Optionally, in one embodiment of this application, the scheduling platform includes: a second acquisition module for acquiring status data and historical task completion efficiency of each sampling vehicle; a third acquisition module for acquiring current environmental information; a prediction module for calculating the estimated sampling time and estimated resource consumption of each sampling vehicle based on the remaining sample capacity, location information, equipment operating status information, historical task completion efficiency, current environmental information, external purchase orders, and a pre-built scheduling prediction model in the status data; and a scheduling module for determining at least one target sampling vehicle based on the estimated sampling time and estimated resource consumption, and generating a sampling task for at least one target sampling vehicle.

[0014] Based on the above technical means, the embodiments of this application can combine the location information of the sampling vehicle, historical completion efficiency, and urgency of the sampling task to generate sampling tasks, so as to optimize sampling efficiency when there are multiple external purchase orders.

[0015] Optionally, in one embodiment of this application, the scheduling platform includes: an analysis module, configured to obtain the coal quality test results from the blockchain, analyze the coal quality test results to obtain analysis results, and use the analysis results to determine whether the target sample meets preset abnormal conditions. If the preset abnormal conditions are met, a verification signal is triggered to obtain the verification result of the target sample, and an audit report of the target sample is generated by combining the analysis results and / or the verification results, and the audit report is uploaded to the blockchain; a traceability module, configured to obtain the sampling tasks, sampling data, judgment results, and verification results of the target samples that meet the preset abnormal conditions from the blockchain, to determine whether the target samples that meet the preset abnormal conditions meet the preset sampling abnormal conditions, and if the preset sampling abnormal conditions are met, trace the sampling abnormal data to determine the fault source of the offline rapid testing management system for purchased coal; and a first optimization module, configured to obtain the sampling tasks, sampling data, judgment results, and verification results of the target samples that do not meet the preset abnormal conditions from the blockchain, to calculate the comprehensive sampling score of the target samples that do not meet the preset abnormal conditions, and use the comprehensive sampling score to optimize the scheduling prediction model.

[0016] Based on the above technical means, the embodiments of this application can analyze whether the target sample is abnormal through the scheduling platform, review the abnormal target sample, and trace whether the abnormality is caused by the sampling process; for normal target samples, a comprehensive sampling score can be calculated to optimize the scheduling prediction model through feedback optimization.

[0017] Optionally, in one embodiment of this application, the scheduling platform includes: a fourth acquisition module, which acquires the actual sampling time and actual resource consumption of at least one of the sampling vehicles in completing the sampling task; and a second optimization module, which optimizes the scheduling prediction model using the actual sampling time and actual resource consumption.

[0018] Based on the above technical means, the embodiments of this application optimize the scheduling of sampling vehicles through feedback optimization, thereby improving sampling efficiency.

[0019] A second aspect of this application provides an offline rapid testing management method for purchased coal, comprising the following steps: generating a sampling task based on a purchase order; predicting the sampling efficiency of each sampling vehicle based on the sampling task and the status data of each sampling vehicle; determining at least one target sampling vehicle based on the sampling efficiency; sending the sampling task to at least one target sampling vehicle; controlling at least one target sampling vehicle to respond to the sampling task, generating a corresponding sampling path, and traveling along the sampling path to a target area to perform corresponding sampling actions; and detecting the target sample to obtain coal quality test results.

[0020] A third aspect of this application 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 offline rapid inspection management method for purchased coal as described in the above embodiments.

[0021] A fourth aspect of this application provides a computer-readable storage medium storing computer instructions for causing the computer to execute the offline rapid inspection management method for purchased coal as described in the above embodiments.

[0022] A fifth aspect of this application provides a computer program product, including a computer program, which, when executed, is used to implement the above-described offline rapid inspection management method for purchased coal.

[0023] This application embodiment can generate sampling tasks based on purchased orders through a scheduling platform, and schedule sampling vehicles according to their status to arrange target sampling vehicles for sample collection and transportation. The transfer of target sampling vehicles facilitates the offline rapid testing system's inspection of samples, achieving intelligent management throughout the entire process, reducing manual intervention, and improving sampling efficiency and data accuracy. This solves the technical problems in related technologies where coal quality testing involves multiple and complex processes, resulting in high management difficulty, high labor costs, and consequently impacting subsequent production.

[0024] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0025] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein: Figure 1 This is a schematic diagram of an offline rapid testing management system for purchased coal provided according to an embodiment of this application; Figure 2 This is a flowchart of an offline rapid testing management system for purchased coal provided according to an embodiment of this application; Figure 3 This is a flowchart illustrating intelligent scheduling and path optimization according to an embodiment of this application; Figure 4 This is a schematic diagram of a multimodal recognition and blockchain evidence storage process according to an embodiment of this application; Figure 5 This is a schematic diagram of the edge intelligent sampling and quality feedback process according to an embodiment of this application; Figure 6 This is a schematic diagram of the offline rapid inspection and review push process according to an embodiment of this application; Figure 7 This is a schematic diagram of a digital twin simulation and prediction process according to an embodiment of this application; Figure 8 This is a flowchart illustrating an offline rapid testing management method for purchased coal according to an embodiment of this application; Figure 9 This is a schematic diagram of the structure of an electronic device provided according to an embodiment of this application. Detailed Implementation

[0026] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0027] The following description, with reference to the accompanying drawings, describes an offline rapid testing management system and method for purchased coal according to embodiments of this application. Addressing the technical problems mentioned in the background art, such as the numerous and complex coal quality testing steps, high management difficulty, and high labor costs that affect subsequent production, this application provides an offline rapid testing management system for purchased coal. In this system, a scheduling platform can generate sampling tasks based on purchase orders, and schedule sampling vehicles according to their status. This allows for the arrangement of target sampling vehicles for sample collection and transportation. The transfer of target sampling vehicles facilitates the offline rapid testing system's inspection of samples, achieving intelligent management throughout the entire process, reducing manual intervention, and improving sampling efficiency and data accuracy. Thus, it solves the technical problems in related technologies where the numerous and complex coal quality testing steps, high management difficulty, and high labor costs affect subsequent production.

[0028] Understandably, as the main energy source in the energy structure, coal quality testing is crucial for ensuring energy security, optimizing resource allocation, and achieving fair trade. Traditional quality testing processes for purchased coal typically include multiple steps such as sampling, sample preparation, and testing. These steps are not only time-consuming, but the sampling process also generally relies on manual operation, resulting in problems such as insufficient sample representativeness, low efficiency, high safety risks, and low data reliability.

[0029] In related technologies, sampling often relies on manual fixed-point or surface sampling, making it difficult to obtain deep coal samples, resulting in a serious lack of representativeness. The sampling process depends on manual experience, has a low degree of standardization, and is highly susceptible to human error, affecting the impartiality and accuracy of test results. From sampling and sample preparation to testing, the process is cumbersome, fragmented, and has a long testing cycle, failing to meet the demands of modern coal logistics for efficient unloading and rapid settlement. This severely restricts logistics efficiency and capital turnover. Furthermore, data from sampling, transportation, and testing rely heavily on manual recording and entry, making it prone to data tampering, omissions, or falsification. The lack of effective anti-counterfeiting and traceability mechanisms during data flow makes it difficult to achieve transparent supervision throughout the entire process, posing significant risks of corruption. Moreover, the dispatching of sampling vehicles relies heavily on manual experience or simple rules, lacking comprehensive optimization based on multi-dimensional information such as vehicle status, road conditions, and task priorities. This leads to high vehicle empty-running rates, slow task response, frequent route conflicts, low overall resource utilization efficiency, and a low overall level of intelligence.

[0030] To address the aforementioned technical issues, the offline rapid inspection management system for purchased coal in this application embodiment can achieve automated quality inspection and scheduling of purchased coal, thereby improving overall resource utilization efficiency.

[0031] Specifically, Figure 1 This is a schematic diagram of the structure of an offline rapid testing management system for purchased coal provided in an embodiment of this application.

[0032] like Figure 1As shown, the offline rapid testing management system 10 for purchased coal includes: a sampling vehicle 100, a dispatching platform 200, and an offline rapid testing system 300.

[0033] Specifically, the sampling vehicle 100 is used to generate a corresponding sampling path in response to the sampling task, and travel along the sampling path to the target area to perform the corresponding sampling action.

[0034] In actual operation, after receiving a sampling task, the sampling vehicle 100 proceeds to the designated station to complete the sampling operation based on the station, date, and train number fields indicated in the task. The upper-level terminal of the sampling vehicle 100 can monitor the sampling process in real time and record key parameters such as sampling depth, sampling point distribution, and sample quality.

[0035] Optionally, in one embodiment of this application, the sampling vehicle 100 includes: a first acquisition module, a judgment module, and a sampling module.

[0036] The first acquisition module is used to collect the target sample and acquire vibration data, temperature data, humidity data and image data of the target sample during the sampling process to generate corresponding sampling data.

[0037] The judgment module is used to combine vibration data, temperature data, humidity data and image data to determine whether the target sample meets the preset sampling qualification conditions and obtain the judgment result.

[0038] The sampling module is used to control the sampling vehicle to take new target samples if the judgment result does not meet the preset sampling qualification conditions.

[0039] This application embodiment can utilize edge computing and sensor fusion to fuse vibration, temperature, humidity and image sensor data during the sampling process, and judge whether the sampling quality is qualified in real time based on a preset quality assessment model. If it is determined to be unqualified, a resampling instruction is immediately triggered, and the abnormal event and processing process are recorded in the blockchain.

[0040] For example, the sampling vehicle 100 can be equipped with edge computing devices to collect and analyze sampling depth, sampling volume, coal sample temperature, and humidity data in real time. If the sampling deviation exceeds a preset threshold, a resampling process will be automatically triggered. The resampling process includes deviation cause analysis, sampling parameter adjustment, and sampling location repositioning.

[0041] Understandably, although the sampling vehicle 100 can respond to sampling tasks and travel along the planned path of the sampling task, unexpected situations may occur during sampling and transportation. For example, if the sampling data of the sampling vehicle 100 that performed the previous sampling task is judged to be unqualified, it needs to be resampled, which will affect the sampling vehicle 100 for the next sampling task. Since resampling may not have been included as part of the path planning when the sampling task is generated, the sampling vehicle 100 also has adaptive path planning capabilities.

[0042] In this embodiment of the application, the sampling vehicle 100 can detect the actions of other sampling vehicles 100 in the vicinity when performing sampling tasks, so as to avoid path collisions, and perform avoidance actions and other actions in the area around the planned path where self-adjustment is allowed.

[0043] The scheduling platform 200 is used to generate sampling tasks based on external purchase orders, predict the sampling efficiency of each sampling vehicle 100 based on the sampling tasks and the status data of each sampling vehicle 100, and determine at least one target sampling vehicle 100 based on the sampling efficiency, so as to send the sampling tasks to at least one target sampling vehicle 100.

[0044] The dispatch platform 200 can generate sampling tasks based on the input sampling requirements or purchase orders. Specifically, it determines the arrival time, placement area, and content to be tested for the purchased coal based on the purchase order, generates corresponding sampling tasks, and determines the urgency of sampling based on the usage requirements of the purchased coal, thereby further revising the sampling tasks to determine the target sampling vehicle 100.

[0045] Optionally, in one embodiment of this application, the scheduling platform 200 includes: a second acquisition module, a third acquisition module, a prediction module, and a scheduling module.

[0046] The second acquisition module is used to acquire the status data and historical task completion efficiency of each sampling vehicle.

[0047] The third acquisition module is used to acquire current environment information.

[0048] The prediction module is used to calculate the estimated sampling time and estimated resource consumption of each sampling vehicle based on the remaining sample capacity, location information, equipment operating status information, historical task completion efficiency, current environmental information, purchase orders and pre-built scheduling prediction models in the status data. The scheduling module is used to determine at least one target sampling vehicle based on the estimated sampling time and estimated resource consumption, and to generate a sampling task for at least one target sampling vehicle.

[0049] In actual implementation, the embodiments of this application can acquire multi-dimensional data, such as the vehicle location of the sampling vehicle 100, equipment status, task urgency, weather and road conditions, remaining sample capacity of the vehicle, historical task completion efficiency, and platform congestion.

[0050] This study utilizes an LSTM fusion network structure and reinforcement learning algorithms with the objective functions of maximizing sampling efficiency, minimizing path cost, and maximizing sampling quality compliance rate. A digital twin simulation is used to model the sampling process, constructing a scheduling prediction model to predict sampling time and resource consumption. The digital twin model integrates 3D geographic information, equipment models, and real-time sensor data to achieve full-element dynamic simulation of the sampling vehicle's operating status, sampling operation process, and rapid detection feedback. It can also pre-generate emergency plans for scenarios such as equipment failure, extreme weather, and abnormal traffic congestion. This enables visualized simulation of the sampling process and prediction of resource consumption. Furthermore, a two-way data closed loop continuously optimizes the scheduling strategy and emergency response mechanism, improving the overall resilience and intelligence of the system.

[0051] Understandably, due to potential unforeseen circumstances during the sampling process, in addition to the sampling vehicle 100 automatically avoiding obstacles, the scheduling platform 200 can also perform macro-level planning and adjustments. For example, reinforcement learning algorithms can be used to optimize the scheduling and path planning of the sampling vehicle 100 in real time, detect path conflicts in real time and make dynamic adjustments, and combine edge computing to evaluate vehicle status and sampling quality in real time, thus achieving closed-loop task completion. This enables intelligent collaboration between task generation and path optimization, and, combined with real-time conflict detection and dynamic adjustments, significantly shortens the sampling cycle and improves vehicle utilization and task completion rate.

[0052] Optionally, in one embodiment of this application, the scheduling platform 200 includes: a third acquisition module and a second optimization module.

[0053] The third acquisition module acquires the actual sampling time and actual resource consumption of at least one sampling vehicle to complete the sampling task.

[0054] The second optimization module is used to optimize the scheduling prediction model using actual sampling time and actual resource consumption.

[0055] In this application embodiment, the digital twin simulation in the scheduling prediction model is a two-way closed-loop feedback. Specifically, the digital twin model receives actual sampled data to update the model, and the simulation prediction results are used to generate an initial scheduling scheme. At the same time, execution data and conflict events, i.e., actual sampling time and actual resource consumption, are fed back to the digital twin model in real time for iterative optimization of simulation accuracy and prediction strategy.

[0056] The offline rapid testing system 300 is used to test target samples and obtain coal quality test results.

[0057] As one possible implementation method, the offline rapid testing system 300 of this application embodiment can automatically receive target samples and perform testing. The test results are filtered by review rules. If there are any abnormalities, manual review is triggered. Finally, a review report is generated and encrypted and pushed to relevant parties.

[0058] Understandably, to ensure the timeliness of data transmission, in this embodiment, the scheduling platform 200, sampling vehicle 100, and offline rapid testing system 300 can adopt a communication architecture that combines 5G and edge computing to achieve low-latency transmission of sampling data, detection results, and scheduling instructions, with an end-to-end transmission latency of less than 100ms. This ensures low-latency and highly reliable data transmission.

[0059] Optionally, in one embodiment of this application, the offline rapid testing management system 10 for purchased coal further includes a verification platform.

[0060] The verification platform is used to respond to the sampling task, identify the identification information of at least one target sampling vehicle, and verify at least one target sampling vehicle by combining the identification information, the sampling task and the personnel identification of the sampling personnel, obtain the verification result, and prohibit the target sampling vehicle whose verification result does not meet the preset verification pass conditions from performing the sampling action.

[0061] The verification platform can be a station of the sampling vehicle 100 or a detection point along the path of the sampling vehicle 100.

[0062] The verification platform can identify the unique device code (identification information) of the sampling vehicle 100 through RFID, verify the identity of the operator (personnel identification) through facial recognition, and compare the sampling scene with the designated station for the task through image recognition. Sampling operation can only be started after all three verifications are passed. This ensures the uniqueness and legality of the sampling subject, vehicle, and scene, and achieves tamper-proof and traceable data throughout the entire process, effectively preventing human fraud and data falsification.

[0063] Optionally, in one embodiment of this application, the offline rapid testing management system 10 for purchased coal is a consortium blockchain architecture, which associates sampling tasks, sampling data, judgment results, coal quality test results and verification results, and stores them in the blockchain of the offline rapid testing management system 10 for purchased coal.

[0064] In this embodiment, the blockchain of the offline rapid testing management system 10 for purchased coal adopts a consortium blockchain architecture. Participating nodes include a scheduling platform 200, a sampling vehicle 100, an offline rapid testing system 300, and a verification platform. Each piece of sampling data, vehicle trajectory, and test result generates a unique hash value and stores it in association. Data modification requires consensus verification from at least three nodes. This consortium blockchain consensus mechanism ensures efficient data sharing while achieving multi-party collaborative supervision and secure evidence storage.

[0065] For example, when performing a sampling task, the verification platform integrates image recognition, RFID, and facial recognition technologies during the sampling process of the sampling vehicle 100. After the verification is passed, a unique identity is generated, and the verification data is packaged to generate a blockchain hash and stored on the blockchain. The offline rapid testing system 300 uploads and stores the generated coal quality test results to the blockchain in real time. After the sampling vehicle 100 analyzes whether the sampling quality is qualified in real time through edge computing, it can trigger a resampling command if the quality is unqualified, and record the abnormal event and processing process in the blockchain.

[0066] The high-security data in blockchain can effectively ensure the accuracy of data and the effectiveness of optimization in subsequent processes such as comprehensive scoring and scheduling optimization.

[0067] Optionally, in one embodiment of this application, the scheduling platform 200 includes: an analysis module, a tracing module, and a first optimization module.

[0068] The analysis module is used to obtain coal quality test results from the blockchain, analyze the coal quality test results, obtain analysis results, and use the analysis results to determine whether the target sample meets the preset abnormal conditions. If the preset abnormal conditions are met, a verification signal is triggered to obtain the verification results of the target sample. The verification report of the target sample is generated by combining the analysis results and / or the verification results, and the verification report is uploaded to the blockchain.

[0069] The traceability module is used to obtain the sampling task, sampling data, judgment result and verification result of the target sample that meets the preset abnormal conditions from the blockchain, so as to determine whether the target sample that meets the preset abnormal conditions meets the preset sampling abnormal conditions, and if the preset sampling abnormal conditions are met, trace the sampling abnormal data to determine the fault source of the offline rapid inspection management system 10 for purchased coal.

[0070] The first optimization module is used to obtain the sampling tasks, sampling data, judgment results and verification results of target samples that do not meet the preset abnormal conditions from the blockchain, so as to calculate the comprehensive sampling score of the target samples that do not meet the preset abnormal conditions, and use the comprehensive sampling score to optimize the scheduling prediction model.

[0071] Based on the blockchain, the scheduling platform 200 in this embodiment can also perform numerical range verification, historical trend comparison and outlier detection on coal quality test results according to the built-in audit rule engine. If the result is abnormal, the manual review process is automatically triggered. After the audit is approved, an encrypted audit report is generated and pushed to relevant parties such as procurement, quality inspection and finance through 5G network security. All data in the process (sampling, testing and audit) is stored in the consortium blockchain in real time, and each piece of data generates a unique hash value to support full traceability.

[0072] For the target samples that fail to pass, internal traceability can be performed first to determine whether the quality inspection failure is due to non-standard internal sampling. By comparing the sampling data of historical batches of purchased coal in the blockchain, it can be determined whether there is a data deviation in a certain link. If the deviation is too large, it is determined that there is a problem in that link, which is the source of failure of the offline rapid inspection management system 10 for purchased coal.

[0073] For the target samples that pass the test, the embodiments of this application can perform a comprehensive score calculation. For example, the analytic hierarchy process can be used to comprehensively score the sampling process data, rapid test results and historical data. The score results serve as the basis for subsequent task scheduling and optimization of the sampling vehicle 100.

[0074] Combination Figures 2 to 7 As shown, the working principle of the offline rapid inspection management system for purchased coal in this application is explained in detail using an embodiment.

[0075] like Figure 2 As shown, embodiments of this application may include the following steps: Step S1: Intelligent generation and dynamic distribution of sampling tasks. This embodiment of the application can generate optimal sampling tasks based on multi-dimensional data using a deep learning model and distribute them via blockchain encryption; the multi-dimensional data includes vehicle location, equipment status, task urgency, weather and road conditions, remaining sample capacity of the vehicle, historical task completion efficiency, and platform congestion.

[0076] The scheduling platform 200 uses a deep learning model based on LSTM and attention mechanism to extract features and perform temporal modeling on the above multidimensional data, and outputs the optimal sampling task sequence. After the task is generated, it is sent to the edge computing terminal of the target sampling vehicle through blockchain encryption. The blockchain encryption adopts an asymmetric encryption algorithm to ensure the integrity and immutability of the task instructions.

[0077] Step S2, sampling vehicle 100 scheduling and route optimization. For example... Figure 3 As shown, the embodiments of this application can use reinforcement learning algorithms to optimize vehicle scheduling and path planning in real time, detect path conflicts in real time and make dynamic adjustments, and combine edge computing to evaluate vehicle status and sampling quality in real time, so as to achieve task closed-loop completion.

[0078] After receiving the sampling task, the scheduling platform 200 uses a reinforcement learning algorithm based on deep deterministic policy gradient to schedule and plan the sampling vehicle 100. The algorithm takes maximizing sampling efficiency, minimizing path cost, and maximizing the sampling quality compliance rate as a multi-objective optimization function. It receives vehicle location updates, road condition changes, and task queue changes in real time and dynamically adjusts the path within milliseconds. If a path conflict is detected (such as vehicle merging or road congestion), the system automatically triggers a conflict resolution strategy and replans the path. At the same time, the edge computing terminal collects vehicle status data (such as vehicle speed, fuel consumption, and equipment voltage) and preliminary sampling quality assessment data in real time, forming a "scheduling-execution-feedback" task closed loop.

[0079] Step S3, multimodal identity verification and anti-cheating sampling. For example... Figure 4 As shown, the sampling process integrates image recognition, RFID, and facial recognition technologies. After verification, a unique identity is generated, and the verification data is packaged to generate a blockchain hash and stored on the blockchain.

[0080] After the target sampling vehicle 100 arrives at the designated platform, a multimodal identity verification process is initiated. First, the unique device code of the sampling vehicle is read via RFID. Second, the driver's facial image is captured by the onboard camera and matched in real time with a pre-set personnel information database. Finally, the platform scene is captured by a panoramic camera and compared with the platform image specified in the task. If all three verifications pass, the system generates a unique identity identifier containing a timestamp, vehicle ID, and personnel ID, and packages the verification process data into a blockchain hash value, which is then uploaded to the consortium blockchain node for storage in real time. Failure of any verification triggers an alarm and suspends the sampling process.

[0081] Step S4, edge intelligent sampling and quality feedback. For example... Figure 5 As shown, the sampling vehicle 100 can be equipped with edge computing devices to collect and analyze sampling depth, sampling volume, coal sample temperature and humidity data in real time. If the sampling deviation exceeds the preset threshold, the resampling process will be automatically triggered.

[0082] During sampling, the edge computing terminal collects and processes data from multiple sensors in real time: vibration sensors monitor the stability of the sampling arm, temperature and humidity sensors monitor the condition of the coal sample, high-definition cameras capture images of the sampling points, and the edge device has a built-in lightweight quality assessment model that analyzes sampling depth, sampling volume, and physical properties of the coal sample in real time. If a sampling deviation is detected to exceed a preset threshold (such as insufficient depth or uneven sample distribution), a resampling process is automatically triggered. Resampling includes deviation cause analysis, adaptive adjustment of sampling parameters (such as adding sampling points or adjusting sampling depth), and repositioning of the sampling location. All sampling events and adjustment records are uploaded to the blockchain for evidence storage in real time.

[0083] Step S5: Offline rapid inspection and data blockchain storage. For example... Figure 6 As shown, the offline rapid testing system 300 can automatically receive samples and perform tests. The test results are filtered according to the review rules. If there are any abnormalities, manual review is triggered. Finally, a review report is generated and encrypted and pushed to the relevant parties. All data is uploaded in real time and stored in the blockchain.

[0084] After sampling, the sampling vehicle 100 proceeds to the offline rapid testing system 300. The offline rapid testing system 300 automatically identifies the sample identity via QR code, and the sample handover is completed by the automatic sample receiving device. The near-infrared spectroscopy detection module completes the detection of key indicators such as calorific value, ash content, and sulfur content of the coal sample within 5-10 minutes. The detection data is encrypted and uploaded to the dispatch platform 200 in real time. The dispatch platform 200 has a built-in audit rule engine to perform numerical range verification, historical trend comparison, and outlier detection on the test results. If the results are abnormal, the system 10 automatically triggers the manual review process. After the review is approved, an encrypted audit report is generated and pushed to relevant parties such as procurement, quality inspection, and finance through the 5G network security. All data in the entire process (sampling, testing, and auditing) is stored in the consortium blockchain in real time, and each piece of data generates a unique hash value, supporting full traceability.

[0085] Step S6: Process simulation and optimization based on digital twins. For example... Figure 7 As shown, a digital twin model of the station is constructed to simulate and predict the entire sampling process. The simulation results are fed back to the scheduling platform 200 to provide support for scheduling decisions and task strategy updates.

[0086] In this embodiment, the platform digital twin model integrates 3D geographic information, equipment 3D models, real-time sensor data, and historical operation data to achieve full-element dynamic simulation of the sampling vehicle 100's operating trajectory, equipment operation actions, sample flow paths, and rapid test result feedback. The digital twin engine and the scheduling platform 200 form a two-way closed-loop linkage: the twin model receives actual sampling data and continuously calibrates the model's accuracy; simultaneously, simulation prediction results (such as task completion time, equipment failure probability, and energy consumption trends) are fed back to the scheduling system to generate initial scheduling plans and emergency strategies. For abnormal scenarios such as extreme weather, equipment failure, and traffic congestion, the digital twin system can perform simulations in advance and pre-generate emergency sampling plans. When the actual system detects an abnormal threshold being triggered, the corresponding emergency plan is automatically activated, achieving intelligent fault tolerance and adaptive optimization.

[0087] The offline rapid testing management system for purchased coal proposed in this application can generate sampling tasks based on purchase orders through a scheduling platform. This, combined with the status of the sampling vehicles, allows for the scheduling of target sampling vehicles for sample collection and transportation. The transfer of these target sampling vehicles facilitates the offline rapid testing system's inspection of the samples, achieving intelligent management throughout the entire process, reducing manual intervention, and improving sampling efficiency and data accuracy. This solves the technical problems in related technologies where coal quality testing involves multiple and complex processes, resulting in high management difficulty, high labor costs, and consequently impacting subsequent production.

[0088] Next, referring to the accompanying drawings, a method for offline rapid testing and management of purchased coal proposed according to an embodiment of this application is described.

[0089] Figure 8 This is a flowchart of an offline rapid testing management method for purchased coal according to an embodiment of this application.

[0090] like Figure 8 As shown, the offline rapid testing management method for purchased coal includes the following steps: In step S801, a sampling task is generated based on the purchase order. Based on the sampling task and the status data of each sampling vehicle, the sampling efficiency of each sampling vehicle is predicted. Based on the sampling efficiency, at least one target sampling vehicle is determined so that the sampling task is sent to at least one target sampling vehicle.

[0091] In step S802, at least one target sampling vehicle is controlled to respond to the sampling task, generate a corresponding sampling path, and travel along the sampling path to the target area to perform the corresponding sampling action; In step S803, the target sample is tested to obtain the coal quality test results.

[0092] It should be noted that the explanation of the aforementioned embodiment of the offline rapid inspection management system for purchased coal also applies to the offline rapid inspection management method for purchased coal in this embodiment, and will not be repeated here.

[0093] The offline rapid testing management method for purchased coal proposed in this application can generate sampling tasks based on purchase orders through a scheduling platform. This, combined with the status of the sampling vehicles, allows for the scheduling of target sampling vehicles for sample collection and transportation. The transfer of these target sampling vehicles facilitates the offline rapid testing system's inspection of the samples, achieving intelligent management throughout the entire process, reducing manual intervention, and improving sampling efficiency and data accuracy. This solves the technical problems in related technologies where coal quality testing involves multiple and complex processes, resulting in high management difficulty, high labor costs, and consequently impacting subsequent production.

[0094] Figure 9 A schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device may include: The memory 901, the processor 902, and the computer program stored on the memory 901 and capable of running on the processor 902.

[0095] When processor 902 executes the program, it implements the offline rapid inspection management method for purchased coal provided in the above embodiments.

[0096] Furthermore, electronic devices also include: Communication interface 903 is used for communication between memory 901 and processor 902.

[0097] The memory 901 is used to store computer programs that can run on the processor 902.

[0098] The memory 901 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0099] If the memory 901, processor 902, and communication interface 903 are implemented independently, then the communication interface 903, memory 901, and processor 902 can be interconnected via a bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of representation, Figure 9 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0100] Optionally, in a specific implementation, if the memory 901, processor 902, and communication interface 903 are integrated on a single chip, then the memory 901, processor 902, and communication interface 903 can communicate with each other through an internal interface.

[0101] The processor 902 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0102] This embodiment also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described offline rapid inspection management method for purchased coal.

[0103] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the offline rapid inspection management method for purchased coal provided in this embodiment of the invention.

[0104] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0105] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0106] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0107] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0108] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0109] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0110] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0111] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. An offline rapid inspection and management system for purchased coal, characterized in that, include: A sampling vehicle is used to generate a corresponding sampling path in response to a sampling task, and travel along the sampling path to the target area to perform the corresponding sampling action; The scheduling platform is used to generate the sampling task based on the purchased order, predict the sampling efficiency of each sampling vehicle based on the sampling task and the status data of each sampling vehicle, and determine at least one target sampling vehicle based on the sampling efficiency, so as to send the sampling task to at least one target sampling vehicle. An offline rapid testing system is used to test the target sample and obtain coal quality test results.

2. The system according to claim 1, characterized in that, The sampling vehicle includes: The first acquisition module is used to collect target samples and acquire vibration data, temperature data, humidity data and image data of the target samples during the sampling process, so as to generate corresponding sampling data. The judgment module is used to combine the vibration data, the temperature data, the humidity data and the image data to determine whether the target sample meets the preset sampling qualification conditions, and to obtain the judgment result; The sampling module is used to control the sampling vehicle to take a new target sample if the judgment result does not meet the preset sampling qualification conditions.

3. The system according to claim 2, characterized in that, Also includes: A verification platform is used to respond to the sampling task, identify the identification information of at least one of the target sampling vehicles, and verify at least one of the target sampling vehicles by combining the identification information, the sampling task, and the personnel identification of the sampling personnel, to obtain a verification result, and to prohibit the target sampling vehicle whose verification result does not meet the preset verification pass condition from performing the sampling action.

4. The system according to claim 3, characterized in that, The offline rapid testing management system for purchased coal adopts a consortium blockchain architecture to associate the sampling task, the sampling data, the judgment result, the coal quality test result, and the verification result, and store them in the blockchain of the offline rapid testing management system for purchased coal.

5. The system according to claim 4, characterized in that, The scheduling platform includes: The second acquisition module is used to acquire the status data and historical task completion efficiency of each sampling vehicle; The third acquisition module is used to acquire current environment information; The prediction module is used to calculate the estimated sampling time and estimated resource consumption of each sampling vehicle based on the remaining sample capacity, location information, equipment operating status information, historical task completion efficiency, current environmental information, external purchase orders and pre-built scheduling prediction model in the status data. The scheduling module is used to determine at least one target sampling vehicle based on the estimated sampling time and the estimated resource consumption, and to generate a sampling task for at least one target sampling vehicle.

6. The system according to claim 4, characterized in that, The scheduling platform includes: An analysis module is used to obtain the coal quality test results from the blockchain, analyze the coal quality test results, obtain analysis results, and use the analysis results to determine whether the target sample meets the preset abnormal conditions. If the preset abnormal conditions are met, a review signal is triggered to obtain the review result of the target sample. The review report of the target sample is generated by combining the analysis results and / or the review results, and the review report is uploaded to the blockchain. The traceability module is used to obtain the sampling task, sampling data, judgment result and verification result of the target sample that meets the preset abnormal conditions from the blockchain, so as to determine whether the target sample that meets the preset abnormal conditions meets the preset sampling abnormal conditions, and if the preset sampling abnormal conditions are met, trace the sampling abnormal data to determine the source of the fault in the offline rapid testing management system of the purchased coal. The first optimization module is used to obtain the sampling task, sampling data, judgment result and verification result of the target sample that does not meet the preset abnormal conditions from the blockchain, so as to calculate the comprehensive sampling score of the target sample that does not meet the preset abnormal conditions, and optimize the scheduling prediction model using the comprehensive sampling score.

7. The system according to claim 4, characterized in that, The scheduling platform includes: The fourth acquisition module acquires the actual sampling time and actual resource consumption of at least one of the sampling vehicles in completing the sampling task; The second optimization module is used to optimize the scheduling prediction model using the actual sampling time and actual resource consumption.

8. An offline rapid testing management method for purchased coal, characterized in that, An offline rapid testing management system for purchased coal as described in any one of claims 1-7, wherein the method comprises the following steps: A sampling task is generated based on the purchase order. Based on the sampling task and the status data of each sampling vehicle, the sampling efficiency of each sampling vehicle is predicted. Based on the sampling efficiency, at least one target sampling vehicle is determined so that the sampling task is sent to at least one target sampling vehicle. Control at least one of the target sampling vehicles to respond to the sampling task, generate a corresponding sampling path, and travel along the sampling path to the target area to perform the corresponding sampling action; The target sample was tested to obtain coal quality test results.

9. An electronic device, characterized in that, include: The system includes 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 offline rapid inspection management method for purchased coal as described in claim 8.

10. A computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to execute the offline rapid inspection management method for purchased coal as described in claim 8.

Images