A method and device for managing coal quality data in a thermal power plant

Abstract

The application discloses a kind of thermal power plant coal quality data whole-process management method and device, belong to energy management and intelligent power plant technical field.The unified object identifier system is established, and only identification is allocated for coal source, batch, equipment and coal quality data, to realize the whole-link association of fuel full life cycle data;Rely on coal information management, coal yard management and coal flow monitoring module, dynamic acquisition and closed loop circulation procurement, inventory, environment and multi-source data such as transportation;Build data automatic check and early warning mechanism, based on the comparison and analysis of fast detection and laboratory data to identify abnormal, linkage intelligent diagnosis function to coal yard spontaneous combustion risk and coal flow anomaly are early warned;Fusion multi-source data constructs coal quality knowledge graph, establishes the correlation network of coal source-coal variety-chemical characteristics-burning performance, provides dynamic data support for coal blending optimization and combustion prediction model.The application realizes the through management and intelligent analysis of coal quality data, and improves the fine and early warning capability of fuel management.

Description

Technical Field

[0001] This invention relates to the field of energy management and smart power plant technology, and in particular to a method, apparatus, equipment and storage medium for full-process management of coal quality data in thermal power plants. Background Technology

[0002] In the fuel management system of thermal power plants, the comprehensive collection, accurate processing, and efficient management of coal quality data are the core foundation for ensuring the safe and stable operation of the unit, improving combustion economy, and meeting environmental emission requirements. Coal quality data runs through the entire process of fuel procurement, delivery, storage, blending, and combustion, and its accuracy and availability are directly related to the power plant's cost control, operation optimization, and risk management level.

[0003] However, existing methods and systems for coal quality data management in thermal power plants have significant limitations and cannot meet the demands of modern, refined management. Firstly, at the data level, coal quality-related information is characterized by its wide range of sources, heterogeneous formats, and frequent updates, encompassing supplier coal delivery information, laboratory test reports, manual records from the coal yard, and online monitoring data. Currently, most management systems only use independent business forms or basic databases for recording, with inconsistent data definitions between modules and a lack of a unified identification system and association rules, resulting in severe "information silos." Data is fragmented at the stages of entry, storage, and transportation, failing to form a complete fuel lifecycle data link, making batch traceability difficult and hindering the achievement of end-to-end tracking and accountability from coal source to the furnace.

[0004] Secondly, at the system functionality level, existing solutions mostly focus on basic data entry and storage, providing only simple CRUD operations, resulting in low levels of intelligence. A particularly prominent problem is the lack of a data consistency verification mechanism: there are often discrepancies in timeliness and accuracy between the online rapid coal quality testing systems commonly deployed in power plants and laboratory analysis results. Current systems lack automated data comparison, deviation analysis, and anomaly detection functions, failing to promptly detect data inconsistencies or measurement equipment malfunctions, thus introducing uncertainties and risks into subsequent coal blending and combustion calculations.

[0005] Furthermore, in terms of data application and value mining, existing systems place data management at the level of recording and storage, lacking in-depth correlation analysis and knowledge construction capabilities. A valid correlation model has not been established between massive amounts of historical coal quality data, corresponding boiler operating parameters, and environmental indicators, thus failing to fully activate the data's value. The system cannot support the mining of long-term patterns between coal quality changes and combustion performance, slagging tendency, and pollutant generation, nor can it proactively warn of coal yard storage safety (such as the risk of spontaneous combustion in coal piles) or abnormalities in the coal conveying process based on multi-source information fusion. This makes management decisions still highly dependent on human experience, unable to provide dynamic and forward-looking data-driven support for coal blending optimization, combustion adjustment, and procurement strategy formulation.

[0006] In summary, current coal quality management systems in thermal power plants are essentially still in a rudimentary stage of data digitization, exhibiting significant shortcomings in data connectivity, consistency, intelligence, and serviceability. The core deficiency lies in the failure to construct an integrated platform covering the entire fuel process, enabling automatic data verification and closed-loop management, and possessing in-depth analytical capabilities. This results in the system only being able to perform basic recording functions, falling far short of the advanced goal of comprehensively optimizing production safety, environmental performance, and economic efficiency through data-driven approaches. Therefore, a comprehensive coal quality data management solution that can systematically address these deficiencies is urgently needed. Summary of the Invention

[0007] The present invention aims to at least partially solve one of the technical problems in the related art.

[0008] To address this, this invention proposes a method for full-process management of coal quality data in thermal power plants. This method establishes a unified object identifier system to achieve end-to-end association of fuel lifecycle data; utilizes the collaborative operation of coal arrival information management, coal yard management, and coal flow monitoring modules to form a closed-loop acquisition and dynamic flow of coal quality data; constructs a consistency verification and intelligent early warning mechanism based on automatic comparison of rapid detection and laboratory data to proactively diagnose data anomalies and safety risks; and integrates multi-source data to construct a coal quality knowledge graph, establishing a network linking coal source characteristics to combustion performance, providing dynamic data support for coal blending optimization and combustion prediction models. This achieves consistent management, full-process traceability, and intelligent application of coal quality data.

[0009] Another objective of this invention is to provide a device for managing the entire process of coal quality data in thermal power plants.

[0010] The third objective of this invention is to provide a computer device.

[0011] A fourth objective of this invention is to provide a non-transitory computer-readable storage medium.

[0012] To achieve the above objectives, this invention proposes a method for full-process management of coal quality data in thermal power plants, comprising: S1. Establish a unified object identifier system to assign unique identifiers to coal source, batch, equipment and coal quality data, and realize the full-link association of fuel life cycle data; S2 collects and transfers coal quality data, records procurement, testing and transportation data through the coal arrival information management module, dynamically updates inventory and environmental parameters through the coal yard management module, and then monitors the transportation status and coal quality changes in real time through the coal flow monitoring module, forming a closed-loop data management system. S3 verifies data consistency and triggers an alert. It automatically compares rapid test data with laboratory data to identify anomalies, generates a deviation report by combining contract comparison analysis, and links with intelligent diagnostic functions to issue early warnings for coal yard spontaneous combustion risk points and coal flow anomalies. S4 constructs a coal quality knowledge graph and realizes algorithm linkage. Through the coal quality database module, it integrates multi-source data and establishes a correlation network of coal source, coal type, chemical characteristics and combustion performance, providing dynamic data support for coal blending optimization and combustion prediction models.

[0013] The method for full-process management of coal quality data in thermal power plants according to an embodiment of the present invention may also have the following additional technical features: In one embodiment of the present invention, establishing a unified object identifier system includes: S11 generates a coal source OID based on coal source location, transportation method and supplier information, and ensures that the identifier cannot be tampered with through a hash algorithm; S12 uses blockchain technology to distribute the storage of coal source OIDs, enabling anti-counterfeiting verification for cross-module data traceability.

[0014] In one embodiment of the present invention, collecting and transferring coal quality data includes: S21 uses digital twin technology to build a three-dimensional visualization model of the coal yard and updates coal pile distribution and inventory data in real time. S22 uses a multi-parameter vector model to perform similarity matching on coal quality characteristics and generates a list of recommended alternative coal types.

[0015] In one embodiment of the present invention, verifying data consistency and triggering an alert includes: S31, calculate the deviation rate between rapid test data and laboratory data; S32: When the deviation rate exceeds the preset threshold, a deviation report containing the supplier name, batch number, and abnormal indicators will be automatically generated.

[0016] In one embodiment of the present invention, constructing a coal quality knowledge graph and implementing algorithmic linkage includes: S41, based on historical coal arrival data and coal yard stockpiling records, and establish a coal quality prediction model; S42 constructs a four-layer relational network by combining coal source, coal type, chemical properties, and combustion performance data to achieve topological analysis of non-obvious features.

[0017] In one embodiment of the present invention, it further includes: S5 uses a dynamic correlation evaluation algorithm for combustion efficiency to analyze the real-time relationship between coal flow fluctuations and boiler combustion efficiency, and generates combustion optimization suggestions. S6, based on the coal flow data and equipment status information collected by the coal flow monitoring module, calls the expert system to generate anomaly handling plans and pushes them to the control terminal.

[0018] To achieve the above objectives, another aspect of the present invention provides a device for full-process management of coal quality data in thermal power plants, comprising: The unified object identifier management module is used to establish a unified object identifier system, assign unique identifiers to coal source, batch, equipment and coal quality data, and realize the full-link association of fuel life cycle data; The coal quality data acquisition and transfer module is used to collect and transfer coal quality data. The coal arrival information management module records procurement, testing and transportation data, the coal yard management module dynamically updates inventory and environmental parameters, and the coal flow monitoring module monitors the transportation status and coal quality changes in real time, forming a closed-loop data management system. The data consistency verification and early warning module is used to verify data consistency and trigger early warnings. It identifies anomalies based on the automatic comparison between rapid test data and laboratory data, generates deviation reports by combining contract comparison analysis, and links with intelligent diagnostic functions to provide early warnings for coal yard spontaneous combustion risk points and coal flow anomalies. The coal quality knowledge graph construction and algorithm linkage module is used to construct a coal quality knowledge graph and realize algorithm linkage. Through the coal quality database module, it integrates multi-source data and establishes a correlation network of coal source, coal type, chemical characteristics and combustion performance, providing dynamic data support for coal blending optimization and combustion prediction models.

[0019] In one embodiment of the present invention, it further includes: The combustion efficiency dynamic correlation evaluation module is used to analyze the real-time relationship between coal flow fluctuations and boiler combustion efficiency through the combustion efficiency dynamic correlation evaluation algorithm, and generate combustion optimization suggestions. The anomaly handling plan generation module is used to generate anomaly handling plans based on the coal flow data and equipment status information collected by the coal flow monitoring module, and then push them to the control terminal.

[0020] This invention discloses a method and apparatus for full-process management of coal quality data in thermal power plants. It establishes a unified object identifier system based on blockchain anti-counterfeiting verification to achieve data association throughout the fuel lifecycle, and utilizes digital twin technology and a multi-parameter vector model to achieve closed-loop acquisition and intelligent matching of coal quality data. An automatic verification and early warning mechanism is constructed based on the deviation rate threshold of rapid testing and laboratory data, linking with intelligent diagnostic functions to achieve real-time early warning of data anomalies and the risk of spontaneous combustion in the coal yard. By constructing a four-layer association knowledge graph of coal source-coal type-chemical characteristics-combustion performance, and introducing a dynamic combustion efficiency evaluation algorithm and expert system, dynamic data support and anomaly handling solutions are provided for coal blending optimization and combustion prediction models. This effectively solves the problems of extensive management and delayed decision-making caused by data fragmentation, missing verification, and insufficient association in existing technologies. It achieves integrated full-process management from data acquisition, consistency verification, intelligent early warning to in-depth analysis, significantly improving the consistency, traceability, and application value of coal quality data, and enhancing the comprehensive efficiency and engineering practicality of the fuel management system in terms of safety, environmental protection, and economic optimization.

[0021] To achieve the above objectives, a third aspect of this application provides a computer device, including a processor and a memory; wherein the processor reads executable program code stored in the memory to run a program corresponding to the executable program code, for implementing a full-process management method for coal quality data in thermal power plants as described in the first aspect embodiment.

[0022] To achieve the above objectives, the fourth aspect of this application proposes a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements a full-process management method for coal quality data in a thermal power plant as described in the first aspect embodiment.

[0023] Additional aspects and advantages of the invention 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 the invention. Attached Figure Description

[0024] The above and / or additional aspects and advantages of the present invention 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 flowchart of a method for full-process management of coal quality data in a thermal power plant according to an embodiment of the present invention; Figure 2 This is an architecture diagram of a full-process management system for coal quality data in a thermal power plant according to an embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of a coal quality data full-process management device for thermal power plants according to an embodiment of the present invention; Figure 4 It is a computer device according to an embodiment of the present invention. Detailed Implementation

[0025] It should be noted that, unless otherwise specified, the embodiments and features described in the present invention can be combined with each other. The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0026] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0027] The following description, with reference to the accompanying drawings, describes a method, apparatus, device, and storage medium for the collaborative prediction of multi-level health status and lifespan of a battery pack according to embodiments of the present invention.

[0028] The core idea of ​​this invention is to construct a unified object identifier system covering the entire process of "coal source-batch-equipment-data," and integrate blockchain anti-counterfeiting and digital twin technologies to establish a data space topology and real-time dynamic mapping. Based on this, a multi-module collaborative acquisition and closed-loop flow mechanism is adopted to achieve automatic aggregation and dynamic updating of multi-source data from coal arrival information, coal yard inventory to coal flow status. Furthermore, a consistency verification model is established through automatic comparison of rapid testing and laboratory data, and intelligent diagnosis is triggered based on deviation thresholds to achieve proactive early warning of data anomalies and risks such as spontaneous combustion in the coal yard. Finally, a multi-layered knowledge graph of coal source-coal type-chemical characteristics-combustion performance is constructed, forming a deep linkage with coal blending optimization and combustion prediction models through multi-parameter vector matching and dynamic combustion efficiency evaluation algorithms. This method transforms the traditional isolated, passive, and shallow data recording mode into a full-process data governance system based on unified identification, closed-loop management, intelligent verification, and knowledge-driven approaches. This significantly improves the consistency, traceability, and intelligent application level of coal quality data in thermal power plants, effectively supporting the comprehensive optimization of fuel management in terms of safety, environmental protection, and economy.

[0029] Example 1 To achieve the above invention, embodiments of the present invention provide a method for collaborative prediction of multi-level health status and lifespan of a battery pack, such as... Figure 1 As shown, it includes: S1. Establish a unified object identifier system to assign unique identifiers to coal source, batch, equipment and coal quality data, and realize the full-link association of fuel life cycle data.

[0030] Specifically, the technical implementation principle of this step is based on the standardized design of object identifiers (OIDs) and a distributed data management mechanism. By assigning unique and tamper-proof OIDs to each entity in the fuel lifecycle (such as coal source, batch, equipment, test data, etc.), cross-module and cross-system data association and consistency assurance are achieved.

[0031] Specifically, the system adopts the OID structure defined by the ISO / IEC 8824 standard to construct a multi-level identification system. For example, the coal source OID can be represented as `1.3.6.1.4.1.12345.2.1.1`, where the prefix `1.3.6.1.4.1` is the standard enterprise root node, `12345` is the unique identifier for the power plant enterprise, and `2.1.1` is the coal source subclass identifier. Each batch, equipment, and coal quality data generates a unique OID according to a similar structure, ensuring unique identification and traceability within the system.

[0032] Furthermore, the system supports configurable OID lengths of 16 to 32 bits and allows for custom prefix and subclass encoding rules. During the data acquisition phase, entities are automatically bound to OIDs via RFID, QR codes, or API interfaces to ensure the accuracy of the data source. Simultaneously, the system supports OID mapping mechanisms with external systems such as ERP and SCADA to achieve cross-system data synchronization.

[0033] Specifically, this OID system is widely used in coal arrival registration, coal yard scheduling, coal flow monitoring, and combustion optimization. For example, in the coal yard module, the system uses OIDs to associate coal pile location, coal type characteristics, and equipment status, enabling dynamic updates of the digital twin model. In the coal quality database, OIDs serve as primary key indexes, supporting rapid retrieval of multi-parameter vector models and matching of similar coal types.

[0034] Specifically, by establishing a unified OID system, the traceability and consistency of fuel data throughout its entire lifecycle have been achieved, solving problems such as data silos and information conflicts in traditional systems. This provides a solid data foundation for subsequent intelligent coal blending, combustion optimization, and risk warning, significantly improving the level of intelligence and decision-making efficiency of fuel management in thermal power plants.

[0035] Furthermore, S1 includes: S11 generates a coal source OID based on the coal source location, transportation method, and supplier information, and ensures that the identifier cannot be tampered with through a hash algorithm.

[0036] Specifically, this step aims to establish a unique and traceable data identification system for each batch of coal entering the plant, thereby achieving the uniqueness, consistency, and tamper-proof nature of fuel data in the system.

[0037] Specifically, this step first extracts metadata from the fuel procurement system, including coal source location (such as mine name, latitude and longitude coordinates), transportation mode (such as road, rail, waterway, etc.), and supplier information (such as supplier number, qualification certification, and historical performance records). This data is then standardized and encapsulated using a predefined data structure to form a tuple containing key attributes. ,in Indicates the coal source area. Indicates the mode of transportation. As a unique identifier for the supplier, This is the batch number. This tuple is used as input, and a fixed-length hash value is generated using a hash algorithm (such as SHA-256). This hash value serves as the unique OID (Object Identifier) ​​for that batch of coal. .

[0038] Furthermore, the output length of the hash algorithm is typically 256 bits (32 bytes) to ensure the uniqueness and collision resistance of the identifier. The system may optionally employ a timestamp and a random salt to further enhance the unpredictability and security of the OID. ,in This is the current timestamp. This indicates an XOR operation. Furthermore, the system supports digital signatures for OIDs to ensure their integrity and source credibility during subsequent data transfer.

[0039] Specifically, this step is widely applied in business processes such as fuel procurement, coal quality tracking, and supplier evaluation in thermal power plants. For example, in coal quality anomaly detection, if the test results of a batch of coal deviate significantly from historical records, the system can quickly locate the source and transportation route of that batch of coal through OID, assisting in responsibility tracing and risk control. Simultaneously, OID can also serve as the primary key in the coal quality database module, used to link coal characteristics, combustion performance, and equipment operation data, supporting subsequent coal blending optimization and combustion prediction models.

[0040] Specifically, this step, through standardized data input and hash algorithm processing, effectively solves problems such as chaotic coal quality data sources, identifier conflicts, and data tampering in traditional systems. The uniqueness and immutability of OIDs ensure the reliable flow of data within the system, providing a solid foundation for realizing the digitalization, intelligentization, and closed-loop control of fuel management in thermal power plants.

[0041] S12 uses blockchain technology to distribute the storage of coal source OIDs, enabling anti-counterfeiting verification for cross-module data traceability.

[0042] Specifically, the system assigns a globally unique OID identifier to each batch of incoming coal in the coal information management module. This OID serves as a unique identity credential for the coal source data and is bound to key attributes such as coal type, supplier, transportation information, and test data. After data entry is completed, the system encapsulates the OID and related metadata (such as coal quality parameters, testing time, and testing institution) of that batch of coal source into a blockchain transaction and writes it into the distributed ledger of the consortium blockchain through a consensus mechanism, ensuring that the data is immutable once it is on the chain.

[0043] Furthermore, the system can adopt a Hyperledger Fabric or Ethereum consortium blockchain architecture, with a minimum of three nodes to ensure data redundancy and consensus efficiency. Each coal source data block has a 256-bit hash length (SHA-256 algorithm) and millisecond-level timestamp precision to ensure the accuracy of the data timeline. The data upload frequency can be set to once per batch or once per hour, depending on business needs, to balance real-time performance and system load. In addition, the system supports an automatic verification mechanism based on smart contracts. When the coal source OID is invoked in the coal yard module or coal flow monitoring module, the smart contract will automatically compare the on-chain data with the coal quality information in the current module. If inconsistencies are found, an anti-counterfeiting warning will be triggered and an anomaly log will be recorded.

[0044] Specifically, this step is widely applied in fuel procurement, inventory management, and combustion control in thermal power plants. For example, in the coal yard module, the system uses OID to access coal quality data from the blockchain and combines it with the current location information of the coal pile to achieve accurate traceability of the coal's origin. In the coal flow monitoring module, the system can verify whether the transported coal is consistent with the original coal source, preventing adulteration or substitution. This technology is particularly suitable for complex fuel management scenarios involving multiple suppliers, multiple batches, and multiple stages, providing thermal power plants with technical support for data anti-counterfeiting, accountability traceability, and compliance auditing.

[0045] Specifically, the technical effect of this step is to significantly improve the credibility and security of coal quality data, and to achieve seamless data integration and consistency verification across modules. By combining OID with blockchain, the system can effectively prevent data tampering and forgery, providing a solid data foundation for fuel management, combustion optimization, and environmental control in thermal power plants, demonstrating high innovation and practicality.

[0046] S2 collects and transfers coal quality data. The coal arrival information management module records procurement, testing, and transportation data. The coal yard management module dynamically updates inventory and environmental parameters. The coal flow monitoring module then monitors the transportation status and coal quality changes in real time, forming a closed-loop data management system.

[0047] Specifically, the technical implementation principle of this step is based on a modular system architecture and a data closed-loop mechanism. Through the coordinated operation of the coal information management module, coal yard management module, and coal flow monitoring module, the data integration and dynamic updating of the entire process from procurement, testing, transportation, storage, delivery to combustion in the furnace are realized.

[0048] Furthermore, the coal arrival information management module first connects to the external procurement system and testing equipment to automatically collect batch information of arriving coal (such as supplier number, transportation method, arrival time, contract specifications, etc.) and combines it with the online rapid testing system to obtain coal quality parameters (such as ash content, volatile matter, sulfur content, calorific value, etc.). Each batch of arriving coal is assigned a unique OID (Object Identifier) ​​to ensure the uniqueness and traceability of the data in the system. The testing data is compared and analyzed with the contract specifications. If the deviation exceeds a set threshold (e.g., calorific value deviation > ...), ... or sulfur content > The system will trigger an intelligent early warning mechanism and record abnormal batches in the coal quality anomaly database, while also marking the supplier's risk level.

[0049] Furthermore, the coal yard management module uses devices such as RFID, laser scanning, and temperature and humidity sensors to collect real-time data on coal pile location, inventory, coal type distribution, and environmental parameters (such as coal pile temperature). Ambient humidity ), and based on historical thermal data and meteorological information (such as , The system predicts the risk of spontaneous combustion. It uses digital twin technology to construct a three-dimensional model of the coal yard, enabling dynamic updates and visualization of the coal storage location status.

[0050] Furthermore, the coal flow monitoring module is deployed at key nodes of the coal conveying system (such as belt conveyors, crushers, and samplers), and collects coal flow data in real time through pressure sensors, infrared rapid detection devices, and weighing systems. Coal quality change trend and equipment operating status When an abnormality in coal flow is detected (such as coal shortage, slippage, or overheating), the system will trigger an alarm and record the abnormal event, providing data support for subsequent combustion coupling analysis.

[0051] Specifically, this step ensures the consistency and real-time nature of coal quality data across modules through standardized data collection, multi-source data fusion, and dynamic circulation mechanisms. This provides a reliable data foundation for fuel management, coal blending, and combustion optimization in thermal power plants, achieving a systematic upgrade from "data silos" to "data closed loops."

[0052] Furthermore, S2 includes: S21 uses digital twin technology to construct a three-dimensional visualization model of the coal yard, and updates coal pile distribution and inventory data in real time.

[0053] Specifically, this step is based on the Industrial Internet of Things (IIoT) and 3D modeling technology to achieve digital mapping and dynamic data fusion of the physical space of the coal yard, thereby improving the visualization, intelligence and real-time performance of coal yard management.

[0054] Specifically, the system first uses a LiDAR scanner or high-precision 3D point cloud acquisition device to spatially model the coal yard, acquiring the geometric shape and spatial coordinate information of the coal pile. The acquisition frequency can be set to once per hour or once every half hour, depending on the intensity of coal yard operations, to ensure the timeliness of the model. The acquired data is preprocessed using point cloud processing algorithms (such as ICP registration, voxel filtering, etc.) to generate a high-precision 3D mesh model, which is then imported into a digital twin platform for visualization rendering. Simultaneously, the system integrates RFID, UWB, or BeiDou positioning systems to bind and update attributes such as batch, coal type, and inventory quantity of the coal pile in real time.

[0055] Furthermore, the system supports automatic calculation of coal pile volume, based on point cloud data and a coal pile density model, using a formula... ,in The total volume of the coal pile. For the first The base area of ​​each grid cell. For the corresponding height. Coal pile density. Usually set to The inventory level is dynamically adjusted based on the characteristics of the coal type. Through formula Real-time calculation with an accuracy of within ±2% meets the high-precision requirements of fuel management in thermal power plants.

[0056] Specifically, this step is widely used in the daily scheduling, safety monitoring, and coal blending decisions of coal yards in thermal power plants. For example, in coal pile operations, the system can dynamically adjust the coal pile path and bin allocation by combining historical coal pile strategies with current coal quality characteristics, avoiding fluctuations in combustion performance caused by mixed coal types. At the same time, the 3D model can be linked with a thermal imaging system to identify areas of spontaneous combustion risk in the coal pile, providing data support for robot inspection path planning.

[0057] Specifically, through digital twin models and real-time data synchronization mechanisms, high-precision visualization and dynamic perception of coal yard status were achieved, providing a reliable data foundation for subsequent intelligent early warning, scheduling optimization and combustion control, and significantly improving the efficiency and safety of fuel management in thermal power plants.

[0058] S22 uses a multi-parameter vector model to perform similarity matching on coal quality characteristics and generates a list of recommended alternative coal types.

[0059] Specifically, this step is based on the multidimensional feature vector representation of coal quality data. Through the vector space model (VSM) or an improved cosine similarity algorithm, the features of the new coal and historical coal types are matched to screen out coal types that are highly similar in key indicators such as chemical composition, calorific value, ash content, volatile matter, and sulfur content, and recommend them as alternatives to the coal blending optimization system.

[0060] Furthermore, the coal quality characteristic vector consists of several key parameters, including but not limited to: received basis lower heating value. (Unit: MJ / kg), Ash content (Unit: %), Volatile Matter (Unit: %) Total Sulfur (Unit: %), Hastings Grindability Index Slagging index Ash melting point (Unit: °C), etc. After standardization preprocessing, these parameters are mapped into vectors of uniform dimension, forming a coal type feature space.

[0061] Furthermore, the system uses a cosine similarity algorithm to match coal type vectors, and the calculation formula is as follows: ; in, and These represent the feature vectors of the two coal types, The angle between the vectors, The closer the value is to 1, the more similar the two coal types are. The system sets a similarity threshold (e.g., ...). The system filters out coal types that meet the substitution criteria and generates a recommendation list by sorting them according to similarity.

[0062] Specifically, in practical applications, this step can dynamically adjust the recommended strategy based on the coal yard inventory status and current boiler combustion demand. For example, when the inventory of a certain type of coal in the coal yard is insufficient, the system can automatically retrieve similar coal types from the database and assess their impact on the coal grinding system, combustion efficiency, emission control, etc., providing scientific alternative decision support for fuel managers.

[0063] Specifically, the system enables in-depth mining and intelligent matching of coal quality data, effectively improving the flexibility and economy of coal blending and combustion, while reducing the risk of combustion instability caused by coal quality fluctuations, providing a solid data foundation for fuel optimization and environmentally friendly operation of thermal power plants.

[0064] S3 verifies data consistency and triggers early warnings. It automatically compares rapid test data with laboratory data to identify anomalies, generates deviation reports by combining contract comparison analysis, and links intelligent diagnostic functions to issue early warnings for spontaneous combustion risk points and abnormal coal flow in coal yards.

[0065] Specifically, this step is a key link in the coal quality data management system of thermal power plants to realize data quality control and risk early warning, and it has a high degree of intelligence and automation.

[0066] Furthermore, this step involves constructing a data consistency verification engine to achieve real-time comparison between rapid testing systems (such as online infrared detection and near-infrared spectroscopy analysis) and laboratory testing data. The system employs a multi-dimensional parameter matching mechanism, including but not limited to calorific value (C). ), ash content ( ), volatile matter ( ), sulfur content ( Key coal quality indicators, such as threshold ranges, are set (e.g.) or When the deviation between rapid test and laboratory data exceeds a set threshold, the system automatically marks the abnormal batch and records the source of the difference. Simultaneously, the system has a built-in contract comparison and analysis module that compares the test results with contractually agreed indicators (such as...). , A item-by-item comparison is performed to generate a structured deviation report, which includes deviation items, deviation magnitudes, contract clause references, and risk level assessments.

[0067] Furthermore, the system supports custom settings for the detection error tolerance range and the accuracy of contract clause matching (such as...). ,in The system sets error tolerances for users and verifies data according to national standards such as GB / T 212-2008 "Industrial Analysis Methods for Coal". The early warning mechanism employs a tiered response strategy; for example, when the coal pile temperature exceeds... And the duration is greater than When the fire occurs, the system triggers a Level 1 spontaneous combustion warning and coordinates with the fire protection and ventilation systems to intervene.

[0068] Specifically, this step is widely used in key nodes of thermal power plants, such as fuel receiving, coal storage, and coal conveying. For example, during coal conveying, the system monitors the belt operation status in real time through pressure sensing and image recognition technology. When abnormalities such as coal flow interruption, slippage, or overheating are detected, an early warning is immediately triggered and the abnormal timestamp and equipment status are recorded, providing data support for subsequent fault tracing and equipment maintenance.

[0069] Specifically, by linking data consistency verification with intelligent early warning, the accuracy and reliability of coal quality data are effectively improved, reducing combustion efficiency decline and safety hazards caused by data deviations. Simultaneously, the automatic generation of deviation reports provides quantitative evidence for fuel procurement and contract performance, enhancing the system's decision support capabilities in fuel management and achieving closed-loop management from data collection to risk control.

[0070] Furthermore, S3 includes: S31, calculate the deviation rate between rapid test data and laboratory data.

[0071] Specifically, the core principle of this step lies in establishing a data-driven automated verification mechanism. This mechanism quantifies the consistency between online rapid testing data and standardized laboratory test results to identify measurement deviations, equipment malfunctions, or unexpected fluctuations in coal quality. Its scientific basis lies in using laboratory analysis results as a high-precision benchmark for continuous online calibration and performance evaluation of the rapid testing system. By calculating and monitoring the deviation rate between the two, the system can fundamentally distinguish between random measurement errors and systematic deviations. This allows for a closer approximation of the true quality of incoming coal and an indirect perception of the health status of the testing equipment itself, providing objective and quantitative evidence for subsequent early warning and decision-making.

[0072] Specifically, the system first collects coal quality index data (such as calorific value, sulfur content, and ash content) from rapid testing devices such as online infrared and gamma rays on the coal conveyor belt in real time or near real time through a standardized data interface. This data is then automatically matched and correlated with authoritative results generated from standard chemical analysis of the corresponding coal sample in the Laboratory Management System (LIMS). The matching is based on a unified coal sample identifier, generated during sampling and used throughout the rapid testing and analysis process. Subsequently, the system calls a built-in deviation analysis algorithm to calculate the values ​​for each successfully matched index data pair according to a preset formula. The calculation process and results, along with metadata such as timestamps, batch numbers, and equipment numbers, are stored in the verification log database, forming a traceable verification history and providing training data for the dynamic threshold adjustment model.

[0073] Furthermore, the calculation of the deviation rate involves key parameters and indicators. The core calculation formula is defined as: for a certain coal quality indicator (denoted as...) ), its deviation rate It can be expressed as .in, and These represent the rapid test value and the laboratory value, respectively. (Function) Based on the specific characteristics of the indicator, the threshold values ​​can typically be the laboratory values ​​themselves (calculating the relative deviation) or the allowable tolerance specified by the national standard for that indicator (calculating the standardized deviation). Furthermore, the system presets multiple levels of dynamic thresholds, including warning thresholds and action thresholds. These thresholds are not fixed values ​​but are dynamically adjusted through machine learning models based on historical statistical data, coal type characteristics, and equipment accuracy records to adapt to different coal sources and operating conditions, ensuring the scientific validity and adaptability of the criteria.

[0074] Specifically, this function is mainly applied in the following core scenarios: First, in the incoming coal acceptance process, as an auxiliary judgment for quality control, when the deviation rate continuously exceeds the action threshold, the system automatically prompts for re-sampling of the batch of coal or initiates a manual intervention process. Second, in production process monitoring, it is used for online diagnosis of the operating status of rapid testing equipment. If a systematic positive or negative deviation occurs, it may indicate probe contamination, calibration drift, or mechanical failure. Third, as the data basis for fuel cost accounting and supplier performance evaluation, the system can automatically generate deviation rate analysis reports by supplier and coal source, providing a basis for procurement decisions. Fourth, this data stream is further integrated into the coal quality knowledge graph to correct and enrich the association rules between coal quality characteristics, improving the prediction accuracy of the coal blending model.

[0075] Specifically, firstly, this step enables process control over data quality, transforming traditional discrete checks relying on manual comparison into automated, continuous monitoring, significantly improving verification efficiency and timeliness. Secondly, it establishes early warning capabilities; through trend analysis of deviation rates, it can issue warnings before equipment fails completely or coal quality deviates significantly, achieving predictive maintenance and proactive risk management. Thirdly, it enhances the reliability of decision support, ensuring the accuracy and consistency of the basic data sources relied upon for subsequent advanced applications such as coal blending optimization and combustion adjustment, reducing the risk of decision-making errors due to data distortion. Finally, by ensuring the integrity of the entire data chain, this mechanism improves the intelligence level and overall economic benefits of the entire fuel management system.

[0076] S32: When the deviation rate exceeds the preset threshold, a deviation report containing the supplier name, batch number, and abnormal indicators will be automatically generated.

[0077] Specifically, this step is based on the data interaction between the coal arrival information management module and the coal quality database module, combined with the comparison logic between the contractually agreed indicators and the actual test results, to achieve the identification and reporting output of abnormal coal quality data.

[0078] Specifically, the system first obtains the coal quality test data for the current batch from the coal arrival module through a standardized data interface, including key indicators such as calorific value, ash content, volatile matter, and sulfur content. Simultaneously, it extracts the contractually agreed-upon values ​​for this batch of coal from the contract management module. The system employs a multi-parameter vector comparison algorithm to compare the actual test values ​​with the contract values ​​item by item, calculating the deviation rate for each indicator. Its definition is: ; in, Indicates the first The actual value of each test indicator This represents the contractually agreed value. When any indicator... The system determined that the batch of coal had an abnormality and initiated the report generation process.

[0079] Furthermore, Typically, thresholds are set according to industry standards (such as the "Technical Specification for Fuel Management of Thermal Power Plants" DL / T1083-2019), for example, the calorific value deviation rate should not exceed 5%, and the ash content deviation rate should not exceed 3%. The system supports user-defined threshold configurations to adapt to the contract requirements of different coal types and different suppliers.

[0080] Furthermore, the system will automatically extract the supplier name, batch number (identified by a unique OID), and abnormal indicator information to construct a structured report template. The report content includes, but is not limited to: basic batch information, contract specifications, test results, deviation analysis, and risk level assessment. The system supports multiple output formats (such as PDF and Excel) and can be sent to relevant management personnel via pre-defined email or messaging interfaces.

[0081] Specifically, this step is widely used in practical applications for quality control of fuel procurement in thermal power plants, supplier performance evaluation, and traceability management of abnormal coal quality. Through automated report generation, manual intervention can be effectively reduced, anomaly response efficiency improved, and the traceability and consistency of coal quality data ensured.

[0082] Specifically, this step enables intelligent verification and closed-loop management of coal quality data, providing reliable data support for subsequent coal blending optimization and combustion performance prediction. It also enhances the automation and intelligence level of the fuel management system and improves the overall capabilities of thermal power plants in terms of fuel economy and operational safety.

[0083] S4 constructs a coal quality knowledge graph and realizes algorithm linkage. Through the coal quality database module, it integrates multi-source data and establishes a correlation network of coal source, coal type, chemical characteristics and combustion performance, providing dynamic data support for coal blending optimization and combustion prediction models.

[0084] Specifically, this step integrates multi-source heterogeneous data from the coal supply information management module, coal yard management module, and coal flow monitoring module to establish a semantic association network between coal source, coal type, chemical properties, and combustion performance, thereby forming a structured and reasonable coal quality knowledge system.

[0085] Specifically, this step first uses a unified OID (Object Identifier) ​​system to uniquely code each batch of coal, ensuring data traceability and consistency across different modules. The system then uses an ETL (Extract, Transform, Load) process to clean, standardize, and structure the raw data, including coal quality analysis data (such as volatile matter, fixed carbon, ash, and sulfur), coal source information, transportation methods, inventory status, and combustion efficiency indicators. Subsequently, the system uses graph database technologies (such as Neo4j and JanusGraph) to construct a knowledge graph. Nodes represent entities such as coal source, coal type, chemical composition, and combustion parameters, while edges represent semantic relationships between them, such as "coal source - coal type," "coal type - chemical characteristics," and "chemical characteristics - combustion performance."

[0086] Furthermore, the system supports multi-dimensional coal quality characteristic modeling, such as volatile matter. Ash content Low heat generation , sulfur content Data, including coal type descriptions, were collected and stored in accordance with national standards such as GB / T 212-2008 "Industrial Analysis Methods for Coal" and GB / T 213-2008 "Determination of Calorific Value of Coal". During the knowledge graph construction process, text vectorization methods such as TF-IDF or Word2Vec were used to extract features from coal type descriptions. Combined with coal quality parameters, a multi-parameter vector model was constructed for intelligent retrieval and alternative recommendations of similar coal types.

[0087] Specifically, this step provides dynamic data support for coal blending optimization and combustion prediction models in thermal power plants. For example, during coal blending, the system can automatically recommend the optimal blending scheme based on the chemical characteristics and target combustion performance (such as NOx emissions and combustion efficiency) of the currently stocked coal types. In the combustion prediction model, the system uses historical combustion performance data from a knowledge graph, combined with current coal quality parameters, and employs regression analysis or machine learning models (such as XGBoost and LSTM) to predict combustion efficiency and pollutant emission trends.

[0088] Specifically, by constructing a coal quality knowledge graph, the system achieves full-chain data association and intelligent reasoning from coal source to combustion performance, significantly improving the scientific and economic efficiency of fuel management. Simultaneously, the algorithm linkage mechanism ensures efficient interaction between data and models, providing a solid data foundation and decision support for combustion optimization and environmental control in thermal power plants.

[0089] Furthermore, S4 includes: S41, based on historical coal arrival data and coal yard stockpiling records, establishes a coal quality prediction model.

[0090] Specifically, by employing data mining and machine learning methods, this study reveals and quantifies the intrinsic correlation and temporal evolution patterns between historical coal quality characteristics and the dynamics of coal yard storage and stockpiling operations, thereby constructing a predictive mathematical model. Its scientific basis lies in recognizing that coal quality is not a static attribute; its changes within the plant are influenced by a combination of factors, including the coal's inherent characteristics, storage environment, stockpiling and mixing strategies, and time cycles. By learning the complex nonlinear mapping relationship between "coal source input - storage operations" and "coal quality index output" from massive historical data, the model can, in principle, infer and extrapolate trends of key coal quality parameters (such as calorific value, sulfur content, and volatile matter) for inventory coal that has not yet undergone detailed testing, or for coal expected to arrive in the future, thus achieving a shift from passive recording to proactive prediction.

[0091] Furthermore, the system first extracts structured historical datasets from the coal quality database module, including: complete coal quality test indicators for each batch of incoming coal, corresponding coal source and coal type information, arrival time, specific coal pile number and location, storage duration, time and amount of coal extraction operations for that coal pile, and relevant environmental monitoring data (such as average temperature). Subsequently, feature engineering methods are used to construct the model input feature vector, which can include numerical features (such as storage days, highest temperature), categorical features (such as coal type classification, location area), and time-series aggregated features (such as weekly average coal extraction amount). Training is performed using methods such as Gradient Boosting Decision Tree (GBDT), Long Short-Term Memory (LSTM), or a hybrid model. The model uses the coal quality indicators of a specific coal pile or virtual coal pile unit at a future time or during a specific coal extraction operation as the prediction target. The trained model is packaged as a service, receiving real-time or planned extraction operation instructions and the current coal yard status as input, and outputting predicted coal quality data.

[0092] Furthermore, the key parameters and indicators involved in the model cover three levels: input, output, and performance. Input parameters mainly include: historical coal quality indicators (calorific value, sulfur, ash, volatile matter, moisture, etc.), physical storage parameters (stockpiling location, stockpile height, volume), time parameters (stockpiling start time, duration), environmental parameters (temperature at monitoring points inside the coal pile, ambient temperature and humidity), and operational parameters (coal extraction frequency, coal extraction quantity). Output indicators are the targets predicted by the model, typically key coal quality indicators of core concern to the power plant, such as net calorific value on an as-received basis, dry ash-free volatile matter, and sulfur content on an as-received basis. Model performance indicators are used to evaluate prediction accuracy, including root mean square error (RMSE), mean absolute percentage error (MAPE), and confidence interval estimation of the prediction results. The system sets an allowable range for prediction error and uses model accuracy as the basis for continuous optimization and iteration.

[0093] Specifically, this coal quality prediction model is mainly applied to the following core business scenarios: First, before coal blending decisions, it provides real-time and accurate predicted coal quality data for each coal pile for optimization calculations, replacing outdated measured data or empirical values, thereby improving the accuracy and economy of blending schemes. Second, at the procurement and inventory management level, combined with future power generation plans, it predicts the comprehensive coal quality trend of coal stored in the plant in the medium and long term, providing data-driven decision support for which coal sources to procure and when to procure them, so as to achieve proactive control of the inventory coal quality structure. Third, in coal yard operation scheduling, it evaluates the impact of different stockpiling and extraction schemes on the coal quality blending effect and potential calorific value loss, thereby guiding the formulation of the optimal storage and extraction strategy. Fourth, the output of this model is an important feedforward input for the combustion optimization system, enabling the boiler control system to perceive the changing trend of coal quality entering the furnace in advance and adjust parameters such as air-coal ratio in advance to stabilize combustion.

[0094] Specifically, implementing the coal quality prediction model established in this step has brought about significant improvements in technical performance. First, it enables predictive coal quality management, shifting the management focus from "knowable after testing" to "predictable before operation," thus gaining a window of opportunity for proactive optimization. Second, it improves the overall plant economy by providing more accurate coal quality predictions, allowing the coal blending optimization model to solve problems based on more realistic data, reducing fuel costs and minimizing boiler efficiency losses and environmental risks caused by coal quality fluctuations. Third, it enhances the intelligence level of system decision-making, solidifying expert experience into quantifiable and iterative data models, reducing reliance on individual experience in management, and making the decision-making process more scientific and transparent. Finally, this model, as the core embodiment of in-depth value mining of fuel data, constitutes a key technological bridge from basic data management to advanced intelligent applications, significantly enhancing the core competitiveness and practical value of the entire management system.

[0095] S42 constructs a four-layer relational network by combining coal source, coal type, chemical properties, and combustion performance data to achieve topological analysis of non-obvious features.

[0096] Specifically, this step constructs a four-layer topology that includes coal source, coal type, chemical properties, and combustion performance by defining entity nodes and relational edges, thereby enabling in-depth mining and correlation analysis of the non-obvious characteristics of coal quality data.

[0097] Specifically, the coal source data is first standardized, including geographical location, transportation method, and supplier information, and then bound to batch information using a unique identifier (OID). Coal type information is categorized based on coal classification standards (such as GB / T5751-2009 "Classification of Coal") to ensure data comparability and consistency. Chemical property data covers key indicators such as volatile matter (V), fixed carbon (FC), ash (A), total sulfur (S), and calorific value (Q), typically in the form of numerical values ​​output from laboratory test reports or online rapid testing systems. Combustion performance data includes combustion efficiency (η), slagging index (CSR), and ash deposition index, which can be extracted from historical combustion records or combustion simulation models (such as CFD combustion simulation).

[0098] Furthermore, the system constructs a four-layer relational network using graph databases (such as Neo4j and JanusGraph). Coal source nodes and coal type nodes are connected through a "source-type" relationship; coal type and chemical properties are established through a "coal type-attribute" relationship; and chemical properties and combustion performance are mapped through an "attribute-performance" relationship. During the construction process, graph expansion algorithms based on attribute similarity, such as cosine similarity or Euclidean distance, are used to match the chemical properties between coal types, thereby achieving topological analysis of non-obvious features.

[0099] Furthermore, the system supports multi-dimensional modeling of coal quality data, such as volatile matter. (Dry basis), calorific value (Received base price), etc., must all comply with the standard definitions in the "Technical Guidelines for Fuel Management of Thermal Power Plants" (DL / T 1083-2008). Simultaneously, the system supports slagging index for different coal types. Combustion efficiency For dynamic evaluation, the calculation formula can be found as follows: ; ; in, This is the melting characteristic index of coal ash. The melting characteristic index of slag. The total heat input into the furnace, Heat is lost during combustion.

[0100] Specifically, this four-layer interconnected network can be widely applied to scenarios such as coal blending optimization, combustion performance prediction, and coal source risk assessment in thermal power plants. For example, in coal quality similarity retrieval, the system can automatically match alternative coal types with good historical combustion performance based on the chemical characteristics of currently stocked coal types, assisting in the formulation of blending strategies. In coal source tracing, the system can combine coal source location, transportation route, and coal quality data to evaluate the economics and combustion adaptability of different coal sources, providing data support for procurement decisions.

[0101] Specifically, by constructing a four-layer interconnected network, the system can overcome the limitations of data isolation in traditional coal quality management, realize the structuring, semanticization, and visualization of coal quality data, and thus provide in-depth data insights and intelligent decision support for fuel management, combustion optimization, and environmental control in thermal power plants.

[0102] S5 uses a dynamic correlation evaluation algorithm for combustion efficiency to analyze the real-time relationship between coal flow fluctuations and boiler combustion efficiency, and generates combustion optimization suggestions.

[0103] Specifically, the technical principle of this step is based on multi-source data fusion and dynamic response mechanism. By collecting key parameters in the coal flow transportation process (such as coal flow rate, coal quality composition, furnace temperature, combustion air ratio, etc.), and combining historical data of boiler combustion efficiency with real-time operating status, a dynamic correlation model of coal flow and combustion efficiency is constructed.

[0104] Specifically, the system uses sensors deployed at key nodes such as coal conveyor belts, crushers, and weighing devices to collect real-time coal quality parameters such as flow rate, particle size distribution, moisture content, ash content, and volatile matter. Simultaneously, it obtains combustion efficiency indicators, such as boiler thermal efficiency, from the boiler combustion control system. Excess Combustion Air Coefficient Furnace temperature Components of flue gas emissions (such as , , These data are linked through a unified OID identification system to ensure the traceability and consistency of coal flow and combustion data.

[0105] Furthermore, the system employs a sliding time window mechanism to... For the time interval, the fluctuation of coal flow With changes in combustion efficiency Dynamic regression analysis was performed. Among them, The timeout is typically set to 5 to 15 minutes to accommodate the response delay of the combustion system in thermal power plants. By constructing a multiple linear regression model or a machine learning-based predictive model between combustion efficiency and coal quality parameters, the system can identify the sensitivity of coal quality changes to combustion efficiency, thereby generating optimization suggestions such as adjusting primary air volume, secondary air ratio, and coal feed rate.

[0106] Specifically, this step is widely used in the combustion optimization control system of thermal power plants, especially under conditions of large fluctuations in coal quality and blending of multiple coal types, which can significantly improve combustion efficiency and environmental performance. For example, with the support of the coal quality database module, the system can predict the impact of current coal flow changes on combustion efficiency based on the correlation between historical coal quality and combustion efficiency, and trigger early warnings or automatically adjust combustion parameters in the coal flow monitoring module.

[0107] Specifically, by dynamically assessing the relationship between coal flow and combustion efficiency in real time, adaptive adjustments to combustion parameters can be achieved, thereby improving boiler operating efficiency, reducing pollutant emissions, and providing data-driven decision support for the economic and environmental benefits of thermal power plants.

[0108] S6, based on the coal flow data and equipment status information collected by the coal flow monitoring module, calls the expert system to generate anomaly handling plans and pushes them to the control terminal.

[0109] Specifically, the technical implementation of this step relies on key technologies such as real-time data acquisition, status recognition, knowledge reasoning, and control command issuance. The coal flow monitoring module collects key parameters such as coal flow rate, equipment operating status, temperature, and vibration in real time through a sensor network deployed on the coal conveyor belt, crusher, sampling device, and weighing system. For example, coal flow data can be acquired through the weighing sensor of the belt scale at a sampling frequency of 10Hz per second, while equipment status information, including equipment start / stop status, fault codes, and running time, is read through the PLC or DCS system interface. When the system detects abnormal coal flow (such as coal shortage, slippage, or overheating) or equipment operating parameters exceeding preset thresholds (such as temperature exceeding...), the system will monitor the coal flow. When an abnormal event is triggered, the expert system reasoning process is entered.

[0110] Furthermore, the expert system performs reasoning based on a rule base and a knowledge graph. The rule base is built from the experience of experts in the field of fuel transportation in thermal power plants, covering typical failure modes and handling strategies. For example, when belt slippage is detected, the system can generate corresponding handling instructions based on the rule "If the belt speed decreases by more than 20% and the duration is greater than 30 seconds, then activate the belt tensioning device and reduce the conveying rate." The knowledge graph is used to correlate coal quality characteristics with equipment response, such as the relationship model between coal type's caking properties, moisture content, and the probability of belt slippage.

[0111] Furthermore, the system sets multi-level alarm thresholds, including Level 1 warning (e.g., coal flow interruption), Level 2 warning (e.g., abnormal coal temperature), and Level 3 warning (e.g., abnormal equipment vibration). The system determines whether to generate a response plan based on the warning level. Once generated, the response plan is pushed to the control terminal in real time via OPC UA or Modbus TCP protocol. The control terminal can be a DCS system, PLC controller, or mobile maintenance terminal, ensuring timely response from on-site operators or the automation system.

[0112] Specifically, this step plays a crucial role in fuel management in thermal power plants. It not only enhances the stability and safety of the coal transport system but also reduces the frequency of manual intervention and improves system response efficiency through intelligent handling mechanisms. Its technological value lies in the rapid identification and precise handling of abnormal events, providing reliable data support and decision-making basis for subsequent combustion optimization and equipment maintenance.

[0113] This invention discloses a coal quality data management method for thermal power plants. It establishes a full-process data association based on a unified object identifier system and collaboratively implements closed-loop data collection and intelligent flow across four modules: coal information management, coal yard management, coal flow monitoring, and a coal quality database. Furthermore, it constructs a four-layer knowledge graph encompassing coal source, coal type, chemical characteristics, and combustion performance, and integrates algorithms for automatic data consistency verification, coal quality prediction, and dynamic combustion efficiency evaluation. This effectively solves the problems of crude fuel management and delayed decision-making caused by data silos, missing verification, and superficial application in existing technologies. It achieves integrated management and control from multi-source data connectivity and intelligent early warning to in-depth analysis and optimization recommendations, significantly improving the consistency, traceability, and value mining capabilities of coal quality data, and enhancing the system's practical effectiveness and intelligence level in supporting the comprehensive optimization of power plant safety, environmental protection, and economic efficiency.

[0114] Example 2 To achieve the above invention, embodiments of the present invention also provide a full-process management system for coal quality data in thermal power plants, such as... Figure 2 As shown, it includes: Specifically, the system is structured around four functional modules throughout the fuel lifecycle: coal arrival information management, coal yard management, coal flow monitoring, and coal quality database, forming an integrated digital management platform for the entire coal quality process in thermal power plants. Through standardized data collection, intelligent analysis, and multi-source fusion, the system achieves traceability, visualization, intelligent processing, and collaborative sharing of coal data, providing unified data support for fuel management, coal blending, and combustion optimization.

[0115] Furthermore, the coal delivery module serves as the starting point for fuel management, recording, tracking, and managing the entire process information for each batch of coal arriving at the power plant. This covers the entire process from fuel supplier delivery, transportation to the plant, sampling and testing, to warehousing decisions. It establishes traceability and consistency of coal source data; constructs a standardized coal delivery data system; and provides fundamental data support for coal yard management, coal blending decisions, and combustion optimization. The main functions of the coal delivery module include five aspects: Batch information management automatically collects and registers coal batches, transportation methods, supplier information, test results, and contract indicators. Intelligent early warning function triggers a coal source risk warning when multiple batches of coal from a supplier are found to be of low quality or when the tested coal quality information is inconsistent with the reported information. Batch geographical tracking function visualizes the distribution of coal sources, transportation routes, and arrival dynamics at the plant, preparing for subsequent procurement planning and economic analysis. Contract comparison analysis function compares test indicators with contractually agreed indicators and automatically generates deviation reports. The multi-energy expansion function further supports the information management of multiple energy sources such as coal, oil, and gas, providing data support for the current low-load stable combustion, hydrogen blending, and nitrogen blending combustion in thermal power plants. Through the coal supply module, the entire data loop and quality control management of incoming fuel are realized.

[0116] Specifically, the coal yard module is the central link connecting "fuel delivery" and "coal blending," used for dynamic monitoring and digital display of coal yard inventory, storage locations, temperature and humidity, and equipment status. Its core objectives are to achieve real-time perception of coal yard inventory and storage location status; to establish a digital twin model of the coal yard to support safety and scheduling management; and to provide real-time inventory and coal quality characteristic data for coal blending decisions. The module's main functions include five aspects: visual management of the coal yard, displaying coal pile distribution, inventory levels, and storage location status through a 2D / 3D digital twin interface; monitoring environmental parameters of the coal yard, collecting real-time data on temperature, humidity, gas concentration, and equipment operation; intelligent diagnosis and early warning, identifying natural risk points in the coal pile and providing early warnings based on historical thermal data and meteorological conditions; optimizing inspection and monitoring tasks, automatically generating robot inspection paths based on thermal distribution data to improve inspection efficiency and automatically eliminating potential hazards from spontaneous combustion points; and providing a unified data interface for coordinated scheduling support, supporting coal yard transportation, coal blending, and storage safety management. Through the coal yard module, digital twin and intelligent visual management of coal yard operations is achieved.

[0117] Specifically, the coal flow monitoring module is located in the middle of the "coal yard management" and "furnace blending" chain, serving as a core bridge for dynamic fuel data tracking and combustion control. Its goals are to achieve real-time monitoring and visualization of the entire coal transportation process; identify coal flow anomalies and establish an alarm linkage mechanism; and support coal quality balance analysis and combustion optimization. Its main functions include six aspects: monitoring the operating status of systems such as belt conveyor, crushing, sampling, and weighing, as well as changes in coal flow, to achieve real-time monitoring; combining online infrared and belt sampling data to calculate the trend of coal quality changes in real time, achieving dynamic coal quality identification; establishing anomaly identification and early warning functions for coal flow blockage, coal shortage, slippage, and overheating; achieving combustion coupling analysis by monitoring coal flow fluctuations and boiler combustion efficiency; dynamically correlating and evaluating relevant data; and providing three-dimensional visualization, displaying the panoramic dynamics and transportation status of the coal flow in a digital twin manner. The coal flow detection module achieves intelligent monitoring of the entire process of fuel flow status and coal quality changes.

[0118] Specifically, the final module is the coal quality database module. It provides the core data and algorithmic support layer for the subsequent intelligent system construction, and is used for centralized storage, management, and analysis of incoming coal samples, batches, test results, and all relevant characteristic information in the entire coal management process. Its core objectives are to build a unified coal quality data center and knowledge graph; provide rapid retrieval and algorithmic support capabilities; and support the operation of coal blending optimization and combustion prediction models. Its main functions include five aspects: centralized data management (storing and structurally managing coal quality, testing, procurement, and operational data generated by each module); intelligent retrieval (rapidly matching similar coal types through a multi-parameter vector model to achieve coal quality characteristic similarity queries and subsequent coal blending scheme alternative coal type recommendations); coal quality trend analysis (establishing an annual coal quality change model based on historical incoming coal data and coal yard data to assist in procurement, scheduling, and blending decisions); and the formation of a coal quality knowledge graph (constructing a network of relationships between coal source, coal type, chemical characteristics, and combustion performance, enabling analysis of coal types beyond sampling and testing).

[0119] Furthermore, the constructed coal quality knowledge graph enables deep semantic associations between coal source, coal type, chemical properties, and combustion performance. The specific steps include: extracting structured coal quality data from a SQL Server relational database and combining it with unstructured data such as coal industry standards and geological exploration reports; using Natural Language Processing (NLP) technology for entity recognition and attribute extraction; modeling the coal quality ontology and establishing four core entity classes: 1. Coal source entities, including mining area, stratigraphy, and geographical coordinates; 2. Coal type entities, including coal formation type and metamorphic degree classification; 3. Chemical property entities, including industrial analysis indicators, elemental analysis indicators, and ash fusion point; 4. Combustion performance entities, including ignition temperature, burnout rate, slagging tendency, and NOx emission characteristics; thereby constructing a "entity-relationship-entity" triple structure, establishing semantic relationship mapping, and forming a logical topological network between dimensions. Through association path mining, rule-based knowledge reasoning, and multiple semantic associations, the knowledge graph association logic of coal source-coal type-chemical properties-combustion performance is constructed. This transforms coal quality indicators, originally isolated in SQL tables, into a semantically related knowledge network, enabling a shift from local data querying to knowledge discovery across the entire industry chain.

[0120] Specifically, the system enables algorithmic linkage, providing data interfaces and algorithmic inputs for the coal blending and combustion optimization modules, and automatically recommending blending schemes. The coal quality database module is a crucial data support for achieving in-depth utilization of fuel data and intelligent decision-making.

[0121] This invention discloses a coal quality data management system for thermal power plants. By constructing a collaborative control architecture centered on four core modules—coal supply, coal yard, coal flow, and database—and integrating a unified identification system, digital twins, and intelligent verification mechanisms, it effectively solves the problems of inefficient fuel management and delayed decision-making caused by data silos, information conflicts, and insufficient analytical capabilities in existing technologies. It achieves end-to-end data connectivity, consistency maintenance, and knowledge-driven correlation analysis from fuel procurement to combustion, significantly improving the traceability of coal quality data, the timeliness of anomaly warnings, and the scientific nature of coal blending optimization. This enhances the system's overall effectiveness and engineering practicality in supporting the safe operation, environmental compliance, and economic improvement of thermal power plants.

[0122] Example 3 To achieve the above invention, embodiments of the present invention also provide a specific application of a full-process management system for coal quality data in thermal power plants, including: This invention relates to a specific application of a full-process management system for coal quality data in thermal power plants. The system is structured around the entire life cycle of fuel in a thermal power plant, comprising four functional modules: coal arrival information management module, coal yard management module, coal flow monitoring module, and coal quality database module.

[0123] Furthermore, the four functional modules are interconnected, and coal quality-related information flows between the functions, forming a basic data structure that supports the in-depth utilization of fuel data and intelligent decision-making. Specifically, in a practical application of a full-process management system for coal quality data in a thermal power plant, the processing of coal quality data begins with the incoming coal information module. This module records the quality information of the purchased coal, along with coal quality testing information. After analyzing the basic coal quality information, the coal is managed for entry into the coal yard through the coal yard information module. Once the incoming coal reaches the coal yard information module, a coal stockpiling plan is calculated based on the coal quality information and historical stockpiling plans, and stockpiling is executed. When the incoming coal is used, it is taken out, and the relevant coal quality information is transferred to the coal flow monitoring module. In the coal flow monitoring module, the incoming coal is monitored via the conveyor belt and ultimately burned in the furnace. All information from the above three stages is stored in the coal quality database module for unified management, thereby realizing full-process management of power plant fuel from procurement to combustion.

[0124] Specifically, the main business process of the coal arrival module is to sample and test the incoming coal. After the test results are confirmed to be correct, the relevant coal quality information is entered. If there is any objection to the test results, the relevant batch of incoming coal will be marked for retesting. If the retest still fails to meet the requirements, it will be entered into the coal quality anomaly database and the supplier will be marked.

[0125] Furthermore, the coal delivery module serves as the starting point for fuel management, recording, tracking, and managing the entire process information for each batch of coal entering the power plant, covering the entire process from fuel supplier delivery, transportation to the plant, sampling and testing, to warehousing decisions. This establishes traceability and consistency of coal source data; constructs a standardized coal delivery data system; and provides fundamental data support for coal yard management, coal blending decisions, and combustion optimization.

[0126] Furthermore, the main functions of the coal delivery module include five aspects: batch information management, intelligent early warning function, batch geographic tracking, contract Dolby analysis, and multi-energy information extension.

[0127] Furthermore, the batch information management function automatically collects and registers the batch of incoming coal, transportation method, supplier information, test results, and contract specifications, along with the OID (Original ID) that uniquely associates the fuel name with the batch. This ensures the uniqueness of the incoming coal recorded in the system and avoids conflicts between different batches of the same coal type. The OID is a globally unique coding mechanism that follows international standards. By assigning a unique digital tag to each specific "fuel name-batch" combination, it achieves precise location, logical uniqueness, and traceability throughout the entire lifecycle of coal quality data when exchanged between different information systems.

[0128] Furthermore, when the intelligent early warning function detects incoming coal, if it finds that the quality of coal from a certain supplier is low for multiple consecutive batches or that the detected coal quality information is inconsistent with the reported information, the system will trigger a coal source risk warning, record the incoming coal in the coal quality anomaly database, and trigger an alarm to remind the relevant supplier to pay attention.

[0129] Furthermore, the batch geographic tracking function can visualize the distribution of coal sources, transportation routes and arrival dynamics at the plant, calculate vehicle and vessel costs based on historical transportation information, provide data support for subsequent procurement planning and economic analysis, and statistically display the coal source preferences of power plants, enabling map and chart display.

[0130] Furthermore, the contract comparison and analysis function compares the test indicators with the contractually agreed indicators and automatically generates deviation reports, providing data support for subsequent combustion performance prediction.

[0131] Furthermore, the multi-energy information extension function further supports the management of information on multiple energy sources such as coal, oil, and gas, providing data support for the current low-load stable combustion, hydrogen blending, and nitrogen blending combustion in thermal power plants.

[0132] Specifically, the coal delivery module enables closed-loop data management and quality control of the entire fuel supply chain.

[0133] Specifically, the main business process of the coal yard module involves simultaneously acquiring current coal stockpiling information and receiving current incoming coal information from the incoming coal information module. Based on the current coal yard silos and coal type status, the optimal stockpiling plan is calculated. After executing the stockpiling strategy, the silo status is automatically updated. Simultaneously, the coal yard monitors relevant data in real time and activates related alarms and safety devices, achieving comprehensive management of coal quality and equipment.

[0134] Furthermore, the coal yard module serves as the central link connecting "fuel delivery" and "coal blending," providing dynamic monitoring and digital display of coal yard inventory, storage locations, temperature and humidity, and equipment status. Its core objectives are to achieve real-time perception of coal yard inventory and storage location status; to establish a digital twin model of the coal yard to support safety and scheduling management; and to provide real-time inventory and coal quality characteristic data for coal blending decisions. Specifically, the core of the digital twin model lies in the real mapping from the physical to the virtual and the virtual feedback from the physical to the physical. By synchronizing real-time changes in the physical coal yard's status (fuel delivery, inventory, storage relocation) to the digital model, and after simulating coal blending schemes in the model to verify their safety and economy, the model provides reverse guidance for the scheduling of physical equipment. For example, consider the physical model of stack-reclaim operations and changes in storage volume: ;in, and The values ​​represent the instantaneous mass flow rates at entry and exit points, measured by a belt scale, ensuring the absolute physical accuracy of the model's geometry. In the actual construction of a digital twin model, multiple physical models need to be described. Digital twins are not simply 3D modeling, but rather a deep fusion of data-driven and physics / empirical formula-driven approaches, recreating and predicting the dynamic evolution of physical entities in real time within a mathematical model.

[0135] Furthermore, the main functions of the coal yard module include five aspects: visual management of coal yard storage locations, coal yard environmental monitoring, intelligent diagnosis and early warning, optimization of inspection and monitoring tasks, and support for coordinated scheduling.

[0136] Furthermore, the visual management of coal yard storage locations allows for the calculation of coal stacking plans by scanning the current storage location status, and enables a two-dimensional / three-dimensional digital twin interface to display the distribution of coal piles, inventory levels, and storage location status. Furthermore, coal yard environmental monitoring involves real-time collection of data on temperature, humidity, gas concentration, and equipment operation to assess and monitor the safety and economic efficiency of the coal yard.

[0137] Furthermore, intelligent diagnosis and early warning, based on historical thermal data and local meteorological conditions, identify coal pile spontaneous combustion risk points and issue early warnings, linking with safe and economical equipment to detect and eliminate spontaneous combustion risk points early.

[0138] Furthermore, the inspection and monitoring tasks are optimized by automatically generating robot inspection paths based on thermal distribution data, thereby improving inspection efficiency and automatically eliminating potential hazards at spontaneous combustion points.

[0139] Furthermore, the coordinated dispatch support provides a unified data interface for coal yard transportation, coal allocation, and storage safety management.

[0140] Specifically, the coal yard module enables digital twinning and intelligent visual management of coal yard operations.

[0141] Specifically, the main business process of the coal flow monitoring module is to perform real-time monitoring of the coal taken from the coal yard before it is blended into the furnace, while simultaneously detecting relevant equipment information. When abnormalities occur in the coal or equipment, an alarm is triggered, and the system automatically records the relevant alarm information. Subsequent handling prompts can be provided in conjunction with an expert system. Important alarm information is correlated with corresponding coal flow data for analysis, and relevant information and handling methods are recorded.

[0142] Furthermore, the coal flow monitoring module, positioned between "coal yard management" and "furnace blending," serves as a crucial bridge for dynamic fuel data tracking and combustion control. Its objectives are to achieve real-time monitoring and visualization of the entire coal transportation process; identify coal flow anomalies and establish alarm linkage mechanisms; and support coal quality balance analysis and combustion optimization.

[0143] Furthermore, the main functions of the coal flow monitoring module include six aspects: real-time coal flow monitoring, dynamic identification of coal quality, anomaly identification and early warning, combustion coupling analysis, and three-dimensional visualization.

[0144] Furthermore, the coal flow is monitored in real time, including the operation status of systems such as belt conveyor, crushing, sampling, and weighing, as well as changes in coal flow.

[0145] Furthermore, the dynamic coal quality identification function uses an installed rapid detection device to verify and compare the coal quality, and combines it with belt sampling data to calculate the trend of coal quality changes in real time. Furthermore, the anomaly identification and early warning function establishes the identification and alarm for over-limit conditions such as coal flow blockage, coal shortage, slippage, and over-temperature through monitoring equipment and pressure sensing equipment, and collects and records relevant equipment information.

[0146] Furthermore, the combustion coupling analysis function monitors coal flow fluctuations and boiler combustion efficiency, dynamically correlating and evaluating relevant data. Furthermore, the three-dimensional visualization displays the panoramic dynamics and transportation status of the coal flow in a digital twin format.

[0147] Specifically, the coal flow detection module enables intelligent monitoring of the entire process of fuel flow status and coal quality changes.

[0148] Specifically, the main business process of the coal quality database module involves inputting existing global coal quality data and simultaneously inputting incoming coal data after detailed analysis. Based on more detailed information about the incoming coal, the coal quality inference model is validated. This is combined with regional, coal type, and basic information to calculate information related to coal grinding, ash accumulation, and slagging, forming a coal quality calculation model. This model is then populated into the global coal quality database. If the incoming coal involves a coal type already listed in the global coal quality database, the model is refined by comparing the calculated coal quality model data with subsequent verification data. This module also enables rapid assessment, retrieval, and access to coal quality data, providing a data foundation for subsequent intelligent decision-making.

[0149] Furthermore, the coal quality database module provides the core data and algorithmic support layer for the subsequent intelligent system construction. It is used for centralized storage, management, and analysis of incoming coal samples, batches, test results, and all relevant characteristic information in the entire coal management process. Its core objectives are to build a unified coal quality data center and knowledge graph; provide rapid retrieval and algorithmic support capabilities; and support the operation of coal blending optimization and combustion prediction models.

[0150] Furthermore, an embodiment of the present invention provides a method for establishing a coal quality database based on SQL Server, comprising: constructing an entity-relationship diagram (ER diagram) based on coal quality analysis indicators (such as total moisture Mt, ash Ad, volatile matter Vdaf, total sulfur St,d) and sampling information, establishing the association between the coal sample information table, the experimental data table, and the metadata dataset; creating a database file group in the SQL Server instance, and implementing physical isolation of data by defining a main file (.mdf) and a secondary file (.ndf) to optimize the I / O read / write speed of large-scale coal quality data; using SQL Server's NOT NULL, UNIQUE, and FOREIGN KEY constraints to ensure the uniqueness of coal sample numbers in the entire table and the consistency of experimental data; and designing the database stored procedures using T-SQL stored procedures for automated calculation of the benchmark conversion of coal quality indicators.

[0151] Furthermore, the main functions of the coal quality database module include five aspects: centralized data management, intelligent retrieval, coal quality trend analysis, coal quality knowledge graph, and algorithm linkage module.

[0152] Furthermore, centralized data management enables the storage and structured management of coal quality, testing, procurement, and operational data generated by each module based on the unique batch coal type OID.

[0153] Furthermore, the intelligent search function can quickly match similar coal types through a multi-parameter vector model, realize coal quality characteristic similarity query, realize the recommendation of alternative coal types for subsequent coal blending schemes, and display similar coal types.

[0154] Furthermore, coal quality trend analysis establishes single-coal quality prediction models and annual coal quality change models based on detailed coal quality information from historical coal arrival data and coal yard stockpiling data, to assist in procurement, scheduling, and blending decisions.

[0155] Furthermore, coal quality knowledge graphs can construct a network linking coal source, coal type, chemical properties, and combustion performance, enabling analysis beyond sampling and testing to achieve diverse and functional evaluations of coal quality. Furthermore, the algorithm linkage enables the coal quality database to provide data interfaces and algorithm inputs for the coal blending and combustion optimization module, automatically recommending blending schemes.

[0156] Specifically, the coal quality database module is a crucial data support for realizing in-depth utilization of fuel data and intelligent decision-making.

[0157] This invention discloses a specific application of a full-process coal quality data management system for thermal power plants. Through a collaborative management architecture built upon modules for coal supply, coal yard, coal flow, and database, it achieves seamless data flow throughout the entire fuel lifecycle, from procurement and storage to transportation and combustion. Specifically, the application is manifested as follows: starting with the coal supply module, a data source based on a unified OID identifier is established to ensure the uniqueness and traceability of coal quality information; a digital twin model of the coal yard module enables dynamic visualization monitoring and intelligent scheduling of inventory and environmental status; the coal flow monitoring module provides real-time tracking and anomaly warnings for the transportation process; and finally, the coal quality database module integrates the entire chain of data, constructs a knowledge graph, and drives coal blending and combustion optimization algorithms. This effectively solves the problems of data silos and disconnected management, achieving integrated, intelligent, and closed-loop management of the entire fuel lifecycle, significantly improving the overall efficiency of thermal power plants in terms of safety, environmental protection, and economic operation.

[0158] Example 4 To achieve the above invention, such as Figure 3 As shown, this embodiment also provides a full-process management device 10 for coal quality data in thermal power plants, which includes: The Unified Object Identifier Management Module 100 is used to establish a unified object identifier system, assign unique identifiers to coal source, batch, equipment and coal quality data, and realize the full-link association of fuel life cycle data.

[0159] The coal quality data acquisition and transfer module 200 is used to collect and transfer coal quality data. It records procurement, testing and transportation data through the coal arrival information management module, dynamically updates inventory and environmental parameters through the coal yard management module, and then monitors the transportation status and coal quality changes in real time through the coal flow monitoring module, forming a closed-loop data management system.

[0160] The data consistency verification and early warning module 300 is used to verify data consistency and trigger early warnings. It identifies anomalies based on the automatic comparison between rapid test data and laboratory data, generates deviation reports by combining contract comparison analysis, and links with intelligent diagnostic functions to provide early warnings for spontaneous combustion risk points and abnormal coal flow in coal yards.

[0161] The coal quality knowledge graph construction and algorithm linkage module 400 is used to construct a coal quality knowledge graph and realize algorithm linkage. Through the coal quality database module, it integrates multi-source data and establishes a correlation network of coal source-coal type-chemical characteristics-combustion performance, providing dynamic data support for coal blending optimization and combustion prediction models.

[0162] In one embodiment of the present invention, it further includes: a combustion efficiency dynamic correlation evaluation module, used to analyze the real-time relationship between coal flow fluctuations and boiler combustion efficiency through a combustion efficiency dynamic correlation evaluation algorithm, and generate combustion optimization suggestions; and an anomaly handling plan generation module, used to call an expert system to generate an anomaly handling plan based on the coal flow data and equipment status information collected by the coal flow monitoring module and push it to the control terminal.

[0163] This invention discloses a full-process management device for coal quality data in thermal power plants. It constructs an integrated hardware and software architecture that operates collaboratively by setting up modules for unified object identifier management, coal quality data acquisition and transfer, data consistency verification and early warning, and coal quality knowledge graph construction and algorithm linkage. This device effectively solves the problems of fragmented fuel management and delayed decision-making caused by dispersed data sources, inconsistent standards, missing verification, and weak correlations in existing technologies. It achieves end-to-end connectivity from data source identification, closed-loop data acquisition, intelligent verification and early warning to knowledge-driven in-depth analysis, significantly improving the consistency, traceability, and value mining capabilities of coal quality data. This provides real-time and reliable data support and decision-making basis for coal blending, combustion optimization, and safe and economical operation of thermal power plants.

[0164] To implement the methods of the above embodiments, the present invention also provides a computer device, such as... Figure 4 As shown, the computer device 600 includes a memory 601 and a processor 602; wherein, the processor 602 reads the executable program code stored in the memory 601 to run a program corresponding to the executable program code, so as to implement the various steps of the above-described method for full-process management of coal quality data in thermal power plants.

[0165] To implement the above embodiments, this application also proposes a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements a full-process management method for coal quality data in thermal power plants as described in the foregoing embodiments.

[0166] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of the present invention. 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.

[0167] 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 invention, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified.

Claims

1. A method for full-process management of coal quality data in thermal power plants, characterized in that, include: S1. Establish a unified object identifier system to assign unique identifiers to coal source, batch, equipment and coal quality data, and realize the full-link association of fuel life cycle data; S2 collects and transfers coal quality data, records procurement, testing and transportation data through the coal arrival information management module, dynamically updates inventory and environmental parameters through the coal yard management module, and then monitors the transportation status and coal quality changes in real time through the coal flow monitoring module, forming a closed-loop data management system. S3 verifies data consistency and triggers an alert. It automatically compares rapid test data with laboratory data to identify anomalies, generates a deviation report by combining contract comparison analysis, and links with intelligent diagnostic functions to issue early warnings for coal yard spontaneous combustion risk points and coal flow anomalies. S4 constructs a coal quality knowledge graph and realizes algorithm linkage. Through the coal quality database module, it integrates multi-source data and establishes a correlation network of coal source, coal type, chemical characteristics and combustion performance, providing dynamic data support for coal blending optimization and combustion prediction models.

2. The method as described in claim 1, characterized in that, Establish a unified object identifier system, including: S11 generates a coal source OID based on coal source location, transportation method and supplier information, and ensures that the identifier cannot be tampered with through a hash algorithm; S12 uses blockchain technology to distribute the storage of coal source OIDs, enabling anti-counterfeiting verification for cross-module data traceability.

3. The method as described in claim 1, characterized in that, Collect and transfer coal quality data, including: S21 uses digital twin technology to build a three-dimensional visualization model of the coal yard and updates coal pile distribution and inventory data in real time. S22 uses a multi-parameter vector model to perform similarity matching on coal quality characteristics and generates a list of recommended alternative coal types.

4. The method as described in claim 1, characterized in that, Verify data consistency and trigger alerts, including: S31, calculate the deviation rate between rapid test data and laboratory data; S32: When the deviation rate exceeds the preset threshold, a deviation report containing the supplier name, batch number, and abnormal indicators will be automatically generated.

5. The method as described in claim 1, characterized in that, Constructing a coal quality knowledge graph and implementing algorithmic linkage, including: S41, based on historical coal arrival data and coal yard stockpiling records, and establish a coal quality prediction model; S42 constructs a four-layer relational network by combining coal source, coal type, chemical properties, and combustion performance data to achieve topological analysis of non-obvious features.

6. The method as described in claim 1, characterized in that, Also includes: S5 uses a dynamic correlation evaluation algorithm for combustion efficiency to analyze the real-time relationship between coal flow fluctuations and boiler combustion efficiency, and generates combustion optimization suggestions. S6, based on the coal flow data and equipment status information collected by the coal flow monitoring module, calls the expert system to generate anomaly handling plans and pushes them to the control terminal.

7. A device for managing the entire process of coal quality data in thermal power plants, characterized in that, include: The unified object identifier management module is used to establish a unified object identifier system, assign unique identifiers to coal source, batch, equipment and coal quality data, and realize the full-link association of fuel life cycle data; The coal quality data acquisition and transfer module is used to collect and transfer coal quality data. The coal arrival information management module records procurement, testing and transportation data, the coal yard management module dynamically updates inventory and environmental parameters, and the coal flow monitoring module monitors the transportation status and coal quality changes in real time, forming a closed-loop data management system. The data consistency verification and early warning module is used to verify data consistency and trigger early warnings. It identifies anomalies based on the automatic comparison between rapid test data and laboratory data, generates deviation reports by combining contract comparison analysis, and links with intelligent diagnostic functions to provide early warnings for coal yard spontaneous combustion risk points and coal flow anomalies. The coal quality knowledge graph construction and algorithm linkage module is used to construct a coal quality knowledge graph and realize algorithm linkage. Through the coal quality database module, it integrates multi-source data and establishes a correlation network of coal source, coal type, chemical characteristics and combustion performance, providing dynamic data support for coal blending optimization and combustion prediction models.

8. The apparatus as claimed in claim 7, characterized in that, Also includes: The combustion efficiency dynamic correlation evaluation module is used to analyze the real-time relationship between coal flow fluctuations and boiler combustion efficiency through the combustion efficiency dynamic correlation evaluation algorithm, and generate combustion optimization suggestions. The anomaly handling plan generation module is used to generate anomaly handling plans based on the coal flow data and equipment status information collected by the coal flow monitoring module, and then push them to the control terminal.

9. An electronic device, comprising: processor; The memory stores executable instructions; when the processor executes the instructions, it implements the whole-process management method for coal quality data in thermal power plants as described in any one of claims 1-6.

10. A computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, it implements a method for full-process management of coal quality data in a thermal power plant as described in any one of claims 1-6.

Images