Real-time adjustment method and system for intelligent coal blending and electronic equipment

Abstract

The embodiment of the invention discloses a real-time adjustment method and system for intelligent coal blending and electronic equipment, and the method comprises the steps: collecting coal quality data, fly ash carbon content data and unit operation data of coal as fired in real time, and generating a real-time data set; based on the real-time data set, determining a combustion state index and an operation economic index; constructing a blending combustion database in a stable working condition interval in which the unit load fluctuation does not exceed a set threshold value; based on coal quality data of a coal yard, a target load plan and the blending combustion database, stable working condition samples which are stored in the blending combustion database and conform to target economy are analyzed and matched, the stable working condition samples are stored in the blending combustion database, and a target coal type combination, a target blending combustion proportion and an expected economic index are determined; and performing linkage matching on the current combustion state index and the operation economic index and the stable working condition sample to generate a corresponding blending combustion proportion adjustment scheme, a coal type switching scheme or an air-coal proportion optimization scheme.

Description

Technical Field

[0001] This application relates to the technical field of combustion monitoring and intelligent fuel management in thermal power plants, and in particular to methods, systems and electronic devices for real-time adjustment of intelligent coal blending. Background Technology

[0002] With the continuous advancement of deep peak-shaving and flexibility retrofitting of thermal power units, coal quality fluctuates frequently, and blending combinations are becoming more diversified, posing greater challenges to boiler combustion stability and economy. Traditional coal blending strategies mainly rely on experience-based judgment and lack unified analysis of coal quality, fly ash carbon content, and multi-source operating data, making it difficult to reflect changes in combustion status in a timely manner, leading to problems such as decreased boiler efficiency, increased coal consumption, and fluctuations in emission indicators.

[0003] In recent years, laser spectroscopy for coal quality and online monitoring technologies for fly ash carbon content (such as LIBS) have developed rapidly, providing high-frequency and high-precision data on coal quality and residual carbon during combustion. However, existing technologies generally use this monitoring data for localized analyses, such as coal quality identification or fly ash furnace efficiency assessment, lacking methods for integrating coal quality, fly ash carbon content, and operational status indicators into a unified model. Furthermore, there is a lack of a blending database based on historical stable operating conditions to guide pre-operation coal blending strategies and real-time optimization during operation.

[0004] Therefore, there is an urgent need for an intelligent coal blending and co-firing adjustment scheme that can integrate online coal quality monitoring data, online fly ash carbon content monitoring data, and unit operation data. This scheme would enable quantitative judgment of combustion status and intelligent alerts for deviations in coal blending, thereby improving unit combustion efficiency and economy. Summary of the Invention

[0005] This application proposes a method, system, and electronic equipment for real-time adjustment of intelligent coal blending, in order to overcome the deficiencies of the prior art.

[0006] According to a first aspect of the embodiments of this application, a method for real-time adjustment of intelligent coal blending is provided, comprising: Real-time data collection of coal quality data, fly ash carbon content data, and unit operation data is performed on the coal quality data, fly ash carbon content data, and unit operation data to generate a real-time dataset. Based on the real-time dataset, the coal feed parameters and real-time blending ratio are determined, and the combustion status index and operational economic index are calculated based on the real-time dataset. Within a stable operating range where the unit load fluctuation does not exceed a set threshold, a blending database is constructed. The blending database is used to periodically store the coal quality data of the coal fed into the furnace, the carbon content data of the fly ash, the combustion status indicators, the operating economic indicators, the unit operating parameters and the real-time blending ratio, and is used to correlate coal quality, operating conditions, combustion results and economic status. Based on the coal quality data of the coal yard, the target load plan and the blending database, analyze and match the stable operating condition samples that meet the target economic efficiency stored in the blending database, store the stable operating condition samples in the blending database and determine the target coal type combination, target blending ratio and expected economic indicators. The current combustion status is monitored in real time, and the combustion status index and the corresponding operating economic index corresponding to the current combustion status are linked and matched with the stable operating condition sample. When the result of the linkage matching exceeds the preset matching value, the corresponding blending ratio adjustment scheme, coal type switching scheme or air-coal ratio optimization scheme is generated.

[0007] In some embodiments, the real-time acquisition of coal quality data of the coal fed into the furnace includes: The coal quality data of the coal fed into the furnace is collected in real time using laser spectroscopy technology. The coal quality data of the coal fed into the furnace includes the calorific value, ash content and volatile matter parameters of the coal fed into the furnace. The carbon content data of the fly ash is collected in real time by spectral analysis or a carbon analyzer. The unit operation data is collected in real time based on hierarchical acquisition and plant-level monitoring information. The unit operation data includes unit load, air-coal ratio, oxygen content, furnace temperature and coal feed parameters. The real-time blending ratio is calculated based on the coal feed data of the unit operation data in the real-time dataset.

[0008] In some implementations, calculating combustion status indicators and operational economy indicators based on the real-time dataset includes: Based on the coal quality data of the coal fed into the furnace, the carbon content data of the fly ash, and the unit operation data in the real-time dataset, the combustion state index is calculated, wherein the combustion state index includes the furnace combustion stability coefficient, incomplete combustion loss, excess air coefficient deviation, and furnace temperature uniformity index. Based on the unit operation data and combustion status indicators in the real-time dataset, the operating economic indicators are calculated, including boiler efficiency, standard coal consumption rate, and cost per kilowatt-hour.

[0009] In some embodiments, the set threshold is 2% of the unit's rated output, and the method further includes: When the unit load fluctuation does not exceed the set threshold and other major operating conditions are stable, the current state interval is defined as the stable operating condition interval; The other key operating conditions are stable, including the air-coal ratio, oxygen content, and furnace temperature, with fluctuations not exceeding the corresponding target thresholds.

[0010] In some implementations, the analysis and matching of stable operating condition samples that meet the target economic efficiency, based on coal quality data from the coal yard, target load plans, and the blending database, to determine the target coal type combination, target blending ratio, and expected economic indicators, includes: Based on the coal quality data and inventory information of the coal yard, the target load plan and the electricity market clearing results, as well as the blending database, the stable operating condition samples that meet the target economic efficiency stored in the blending database are analyzed and determined through similarity matching or machine learning modeling. These samples are used to determine the target coal type combination, the target blending ratio, and the expected economic indicators. The expected economic indicators include expected boiler efficiency and combustion risk warnings.

[0011] In some implementations, when the result of the linkage matching exceeds a preset matching value, a corresponding blending ratio adjustment scheme, coal type switching scheme, or air-coal ratio optimization scheme is generated, including: When the linkage matching is triggered by conditions such as combustion state exceeding limits, continuous increase in fly ash carbon content, or boiler efficiency lower than historical similar operating conditions, a corresponding blending ratio adjustment scheme, coal type switching scheme, or air-coal ratio optimization scheme will be generated.

[0012] In some implementations, the blending ratio adjustment scheme includes indicating the possibility of sudden changes in coal quality or the possibility of equipment malfunction.

[0013] According to a second aspect of this application, a real-time adjustment system for intelligent coal blending is provided, comprising: The data acquisition and preprocessing module is used to acquire coal quality data, fly ash carbon content data and unit operation data of coal fed into the furnace in real time, and to perform data synchronization processing, filtering processing, anomaly removal processing and time alignment processing on the coal quality data of coal fed into the furnace, the fly ash carbon content data and the unit operation data to generate a real-time dataset. The multi-index determination module is used to determine the coal feed parameters and real-time blending ratio based on the real-time dataset, and to calculate the combustion state index and operating economy index based on the real-time dataset. The blending database construction module is used to construct a blending database within a stable operating condition range where the unit load fluctuation does not exceed a set threshold. The blending database is used to periodically store the coal quality data of the coal fed into the furnace, the carbon content data of the fly ash, the combustion status indicators, the operating economic indicators, the unit operating parameters and the real-time blending ratio, and is used to associate coal quality, operating conditions, combustion results and economic status. The stable operating condition sample matching module is used to analyze and match stable operating condition samples that meet the target economic efficiency stored in the blending database based on coal quality data, target load plan and the blending database of the coal yard, store the stable operating condition samples in the blending database and determine the target coal type combination, target blending ratio and expected economic indicators. The real-time adjustment and switching module is used to monitor the current combustion state in real time, and to link and match the combustion state index and the corresponding operating economic index of the current combustion state with the stable operating condition sample. When the result of the linkage matching exceeds the preset matching value, the module generates the corresponding blending ratio adjustment scheme, coal type switching scheme or air-coal ratio optimization scheme.

[0014] According to a third aspect of this application, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to said at least one processor; The memory stores instructions that can be executed by the at least one processor, which, when executed by the at least one processor, cause the electronic device to perform a real-time adjustment method for intelligent coal blending as described above.

[0015] According to a fourth aspect of this application, a computer-readable storage medium is provided, on which a computer program is stored, which, when executed by a processor, implements a real-time adjustment method for intelligent coal blending as described above.

[0016] The beneficial effects of the intelligent coal blending real-time adjustment method, system, and electronic equipment of the embodiments of this application include at least the following: This application's embodiments comprehensively process coal quality, fly ash carbon content, and operational data to construct a real-time combustion status index system, accurately reflecting boiler combustion stability, furnace efficiency, and deviations, thus achieving quantitative judgment of combustion status. By integrating and storing coal quality, combustion indicators, and economic indicators under various stable operating conditions, a correlation database of coal quality, operating conditions, and combustion results is formed, providing interpretable basis for coal blending optimization and constructing a blending database, forming a unit-specific knowledge base. Utilizing coal quality distribution in the coal yard, power market clearing load, and historical blending effects, coal blending suggestions are provided in advance, achieving optimal operational preparation in terms of economy and stability, realizing intelligent coal blending strategy generation before operation. Based on real-time index monitoring and database matching to identify operating condition deviations, suggestions for blending ratio, coal type switching, or coal feed rate adjustment are given, achieving dynamic optimization and realizing real-time blending adjustment during operation. By reducing incomplete combustion, high fly ash carbon content, and increased coal consumption caused by coal quality fluctuations, energy saving and consumption reduction, and lower operating costs are achieved, improving boiler efficiency and economy. Attached Figure Description

[0017] Figure 1 A flowchart illustrating the real-time adjustment method for intelligent coal blending according to an embodiment of this application; Figure 2 This is a schematic diagram of the data acquisition and transmission system architecture according to an embodiment of this application; Figure 3 This is a schematic diagram illustrating the core data processing and function generation process of an embodiment of this application; Figure 4 This is a schematic diagram of the structure of a real-time adjustment system for intelligent coal blending according to an embodiment of this application; Figure 5 This is a schematic diagram of the structure of a coal-fired power plant system according to an embodiment of this application. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the following description of the real-time adjustment method, system, and electronic equipment for intelligent coal blending, in conjunction with the accompanying drawings, will clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the described embodiments are only some, not all, of the embodiments of this application. The components of the embodiments of this application described and shown in the accompanying drawings can typically be arranged and designed in various different configurations.

[0019] Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the claimed embodiments of the present application, but merely to illustrate selected embodiments of the present application. Other embodiments obtained by those skilled in the art based on the embodiments of the present application without inventive effort are all within the scope of protection of the embodiments of the present application.

[0020] It can be noted that similar reference numerals and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it will not be further defined and explained in subsequent figures according to the embodiments of this application.

[0021] This application discloses a real-time adjustment method, system, and electronic device for intelligent coal blending. The real-time adjustment method for intelligent coal blending is implemented based on the real-time adjustment system for intelligent coal blending. The purpose of this method is to provide a solution suitable for evaluating the effect of coal blending and for deviation alarms, based on online characterization of coal quality and fly ash carbon content using laser spectroscopy, combustion state determination using boiler operating data, and the construction of a blending database.

[0022] See attached document Figure 1 As shown, the real-time adjustment method for intelligent coal blending includes the following steps 110-150.

[0023] Step 110: Real-time acquisition of coal quality data, fly ash carbon content data, and unit operation data of the coal fed into the furnace, and data synchronization processing, filtering processing, anomaly removal processing, and time alignment processing of the coal quality data, fly ash carbon content data, and unit operation data of the coal fed into the furnace, as well as the unit operation data, to generate a real-time dataset.

[0024] In some implementations, the real-time acquisition of coal quality data of the coal fed into the furnace includes: acquiring the coal quality data of the coal fed into the furnace in real time using laser spectroscopy; acquiring the carbon content data of the fly ash in real time using spectral analysis or a carbon analyzer; acquiring the unit's operating data in real time based on hierarchical acquisition and plant-level monitoring information, including unit load, air-to-coal ratio, oxygen content, furnace temperature, and coal feed parameters; and calculating the real-time blending ratio based on the coal feed data of the unit's operating data collected in the real-time dataset.

[0025] The coal quality data for the coal fed into the furnace includes the calorific value, ash content, and volatile matter parameters of the coal.

[0026] See attached document Figure 2 The diagram shows a schematic representation of the data acquisition and transmission system architecture according to an embodiment of this application. Figure 2 As shown, the data acquisition layer consists of "online coal quality detection equipment based on laser spectroscopy" and "online fly ash carbon content detection equipment based on laser spectroscopy," enabling source sensing of core fuel and combustion state parameters. Unit operation data is acquired through the power plant's distributed control system (DCS) and plant-level monitoring information system (SIS). All data ultimately converges to the "control platform" (i.e., the hardware and software platform for executing the method of this invention) for unified processing. This diagram clearly illustrates the acquisition path and integration method of multi-source heterogeneous data, corresponding to the equipment source and transmission logic for "real-time acquisition" of this data in the claims.

[0027] This application embodiment establishes a high-quality, highly reliable data foundation based on step 110. This step aims to address the real-time, synchronization, and consistency issues in the acquisition of multi-source heterogeneous data from thermal power plants, providing accurate input for subsequent intelligent analysis. Based on systematic acquisition and a rigorous preprocessing procedure, the raw, messy field data is transformed into a clean, consistent, and reliable real-time dataset. This dataset is the sole and reliable data source for all subsequent calculations, judgments, optimizations, and recommendations, fundamentally ensuring the overall accuracy, real-time performance, and feasibility of the method of this invention.

[0028] Step 120: Based on the real-time dataset, determine the coal feed parameters and the real-time blending ratio, and calculate the combustion status index and the operational economy index based on the real-time dataset.

[0029] In some implementations, the calculation of combustion state indicators and operational economic indicators based on the real-time dataset includes: calculating the combustion state indicators based on the coal quality data of the coal fed into the furnace, the carbon content data of the fly ash, and the unit operating data in the real-time dataset, wherein the combustion state indicators include the furnace combustion stability coefficient, incomplete combustion loss, excess air coefficient deviation, and furnace temperature uniformity index; and calculating the operational economic indicators based on the unit operating data and the combustion state indicators in the real-time dataset, wherein the operational economic indicators include boiler efficiency, standard coal consumption rate, and cost per kilowatt-hour.

[0030] In this embodiment, after preprocessing, the real-time dataset first extracts the coal feed parameters from the unit operation data and calculates the real-time blending ratio based on the coal feed data for each coal type. Then, the system comprehensively calculates combustion status indicators and operational economic indicators based on this real-time dataset: Combustion status indicators are derived by analyzing coal quality, fly ash carbon content, and key operating parameters in the dataset, including furnace combustion stability coefficient and incomplete combustion loss, used to quantitatively assess the stability and completeness of the combustion process; operational economic indicators are calculated by combining unit operation data and combustion status indicators, including boiler efficiency and standard coal consumption rate, directly reflecting the economic level of operation. This step transforms multi-source real-time data into quantifiable and assessable key performance indicators, providing a core basis for subsequent database construction and intelligent optimization suggestions.

[0031] Step 130: Within the stable operating range where the unit load fluctuation does not exceed the set threshold, construct the co-firing database.

[0032] For example, the blending database is used to periodically store the coal quality data of the coal fed into the furnace, the carbon content data of the fly ash, the combustion status index, the operating economic index, the unit operating parameters and the real-time blending ratio, and is used to associate coal quality, operating conditions, combustion results and economic status.

[0033] For example, the threshold is set at 2% of the unit's rated output.

[0034] In some implementations, the method further includes defining the current state interval as a stable operating condition interval when the unit load fluctuation does not exceed a set threshold and other major operating conditions are stable; the stability of other major operating conditions includes the fluctuation range of air-coal ratio, oxygen content, and furnace temperature not exceeding the corresponding target threshold.

[0035] The construction of the blending database in this application embodiment is the core foundation for realizing intelligent coal blending adjustment. Its key lies in accurately defining stable operating conditions and systematically storing related data. Specifically, the system defines a period of time as a stable operating condition when the unit load fluctuation does not exceed a set threshold (e.g., 2% relative to the rated load) and other major operating conditions (such as air-coal ratio, oxygen content, furnace temperature, etc.) remain stable. Under this condition, the system automatically collects and stores multi-source data, including real-time coal quality, fly ash carbon content, combustion status indicators (such as furnace combustion stability coefficient), operational economic indicators (such as boiler efficiency), real-time blending ratio, and operating parameters. This forms a related database structured around coal quality, operating parameters, combustion indicators, economic indicators, and the optimal blending strategy. This process ensures the representativeness and reliability of the data, providing data support based on historical best practices for subsequent pre-operation coal blending recommendations and real-time adjustments during operation, ultimately improving the economy and stability of boiler combustion.

[0036] Step 140: Based on the coal quality data of the coal yard, the target load plan and the blending database, analyze and match the stable operating condition samples that meet the target economic efficiency stored in the blending database, store the stable operating condition samples in the blending database and determine the target coal type combination, target blending ratio and expected economic indicators.

[0037] In some implementations, the coal quality data, target load plan, and blending database of the coal yard are analyzed and matched with stable operating condition samples that meet the target economic performance stored in the blending database to determine the target coal type combination, target blending ratio, and expected economic indicators. This includes: based on the coal quality data and inventory information of the coal yard, the target load plan and electricity market clearing results, and the blending database, analyzing and determining stable operating condition samples that meet the target economic performance stored in the blending database through similarity matching or machine learning modeling, which are used to determine the target coal type combination, target blending ratio, and expected economic indicators.

[0038] For example, the expected economic indicators include expected boiler efficiency and combustion risk warnings.

[0039] The core of generating pre-operation coal blending recommendations in step 140 of this embodiment lies in using historical data to achieve intelligent decision-making. Based on real-time coal quality data from the coal yard, target load plans (such as future power generation plans or electricity market clearing results), and the established blending database, the system analyzes stable operating condition samples stored in the database that meet the target economics (such as optimal boiler efficiency or lowest standard coal consumption) through similarity matching or machine learning modeling. By matching these samples, the system automatically determines the target coal type combination, target blending ratio, and expected economic indicators (such as boiler efficiency and coal consumption), thereby providing operators with data-driven optimization strategies before operation and improving the economy and stability of coal blending. This process embodies the intelligent closed-loop optimization concept of extracting knowledge from historical best practices and applying it to future planning.

[0040] Step 150: Monitor the current combustion status in real time, and link the combustion status index and the corresponding operating economic index of the current combustion status with the stable operating condition sample. When the result of the link matching exceeds the preset matching value, generate the corresponding blending ratio adjustment scheme, coal type switching scheme or air-coal ratio optimization scheme.

[0041] In some implementations, when the result of the linkage matching exceeds a preset matching value, a corresponding blending ratio adjustment scheme, coal type switching scheme, or air-coal ratio optimization scheme is generated, including: when the linkage matching is based on the combustion state exceeding the limit, the carbon content of fly ash continuously increasing, or the boiler efficiency being lower than that of similar historical operating conditions, a corresponding blending ratio adjustment scheme, coal type switching scheme, or air-coal ratio optimization scheme is triggered.

[0042] For example, the blending ratio adjustment scheme includes indicating the possibility of sudden changes in coal quality or the possibility of equipment malfunction.

[0043] See attached document Figure 3 The diagram illustrates the core data processing and function generation process of an embodiment of this application. Figure 3 As shown, the online coal quality monitoring data and the online fly ash carbon content monitoring data are used as inputs (see Appendix). Figure 5 The system then proceeds to the module for calculating combustion status and economic indicators. The generated indicators and related parameters are stored in a blending database, which supports the generation of two core application functions: pre-operation coal blending recommendations and in-operation blending adjustment recommendations. Figure 3 It uses a concise logical diagram to summarize the complete information flow and functional implementation path from raw data to intelligent suggestions.

[0044] In this embodiment, step 150 involves real-time monitoring of combustion state indicators (such as furnace combustion stability coefficient and incomplete combustion loss) and operational economic indicators (such as boiler efficiency and standard coal consumption rate) corresponding to the current combustion state. These real-time indicators are then linked and matched with pre-stored stable operating condition samples in the blending database (for example, calculating the similarity or deviation between the current indicators and historical best operating condition indicators). When the matching result (such as deviation or difference value) exceeds a preset matching threshold, it indicates a significant deviation in the combustion state. Based on the matching result, the system automatically generates targeted optimization schemes, including adjusting the blending ratio to optimize the coal type ratio, switching to a more suitable coal type (such as high calorific value or high volatile matter coal), or adjusting the air-coal ratio (such as the ratio of primary air to secondary air), thereby achieving dynamic closed-loop optimization of the combustion process and improving economy and stability. This process embodies a closed-loop control logic from real-time data to intelligent decision-making.

[0045] This application's embodiments comprehensively process coal quality, fly ash carbon content, and operational data to construct a real-time combustion status index system, accurately reflecting boiler combustion stability, furnace efficiency, and deviations, thus achieving quantitative judgment of combustion status. By integrating and storing coal quality, combustion indicators, and economic indicators under various stable operating conditions, a correlation database of coal quality, operating conditions, and combustion results is formed, providing interpretable basis for coal blending optimization and constructing a blending database, forming a unit-specific knowledge base. Utilizing coal quality distribution in the coal yard, power market clearing load, and historical blending effects, coal blending suggestions are provided in advance, achieving optimal operational preparation in terms of economy and stability, realizing intelligent coal blending strategy generation before operation. Based on real-time index monitoring and database matching to identify operating condition deviations, suggestions for blending ratio, coal type switching, or coal feed rate adjustment are given, achieving dynamic optimization and realizing real-time blending adjustment during operation. By reducing incomplete combustion, high fly ash carbon content, and increased coal consumption caused by coal quality fluctuations, energy saving and consumption reduction, and lower operating costs are achieved, improving boiler efficiency and economy.

[0046] See attached document Figure 4 As shown, this application also discloses a real-time adjustment system for intelligent coal blending, including: a data acquisition and preprocessing module 410, a multi-index determination module 420, a blending database construction module 430, a stable operating condition sample matching module 440, and a real-time adjustment and switching module 450.

[0047] For example, the data acquisition and preprocessing module 410 is used to acquire coal quality data, fly ash carbon content data and unit operation data of coal fed into the furnace in real time, and to perform data synchronization processing, filtering processing, anomaly removal processing and time alignment processing on the coal quality data of coal fed into the furnace, the fly ash carbon content data and the unit operation data to generate a real-time dataset.

[0048] For example, the multi-index determination module 420 is used to determine the coal feed parameters and real-time blending ratio based on the real-time dataset, and to calculate the combustion state index and operating economy index based on the real-time dataset.

[0049] For example, the blending database construction module 430 is used to construct a blending database within a stable operating range where the unit load fluctuation does not exceed a set threshold. The blending database is used to periodically store the coal quality data of the coal fed into the furnace, the carbon content data of the fly ash, the combustion status index, the operating economic index, the unit operating parameters and the real-time blending ratio, and is used to associate coal quality, operating conditions, combustion results and economic status.

[0050] For example, the stable operating condition sample matching module 440 is used to analyze and match stable operating condition samples that meet the target economic efficiency stored in the blending database based on the coal quality data of the coal yard, the target load plan and the blending database, store the stable operating condition sample in the blending database and determine the target coal type combination, the target blending ratio and the expected economic indicators.

[0051] For example, the real-time adjustment and switching module 450 is used to monitor the current combustion state in real time, and to perform linkage matching between the combustion state index and the corresponding operating economic index corresponding to the current combustion state and the stable operating condition sample. When the result of the linkage matching exceeds the preset matching value, the module generates the corresponding blending ratio adjustment scheme, coal type switching scheme or air-coal ratio optimization scheme.

[0052] See attached document Figure 5 The diagram shows a structural schematic of a coal-fired power plant system according to an embodiment of this application. Figure 5 As shown, coal from different zones is collected by a bucket wheel excavator and then transported to the corresponding raw coal bunker and coal mill, before finally being fed into the boiler furnace for combustion. This embodiment integrates a key online coal quality monitoring system into the coal mill inlet pipe for real-time data collection of incoming coal quality; an online fly ash carbon content monitoring system is deployed in the electrostatic precipitator inlet flue for real-time monitoring of fly ash carbon content. This clarifies the physical location and process background of data collection in this embodiment, demonstrating the complete process from fuel preparation and combustion to pollutant monitoring, and providing a specific system scenario for the industrial application of this embodiment.

[0053] This application uses a coal-fired power plant as an example to achieve intelligent adjustment of coal blending through a layered architecture. Specific steps include: implementation of the data source layer, implementation of the indicator layer calculation, implementation of the blending database construction, and implementation of the application layer functions. The data source layer implements real-time acquisition of multi-source data through hardware sensors and edge computing devices. Specifically, a laser spectrometer is used to monitor key parameters such as calorific value, ash content, and volatile matter of the coal fed into the boiler, achieving online coal quality monitoring data acquisition with a sampling frequency of once per second to ensure timely capture of coal quality changes. A carbon spectrometer continuously monitors the unburned carbon content in the fly ash from the boiler tail flue, achieving online fly ash carbon content monitoring data acquisition; this data is collected synchronously with coal quality monitoring. Parameters such as unit load, air-coal ratio, oxygen content, furnace temperature, and coal feed rate are acquired in real-time from the power plant's distributed control system (DCS), achieving unit operation data acquisition; this data is updated at millisecond-level frequencies. All acquired raw data is sent to edge computing devices (such as industrial gateways) for synchronization alignment, digital filtering (such as low-pass filtering to remove noise), outlier removal (based on the 3σ criterion to identify outliers), and timestamp processing to form a high-quality real-time dataset, which is then input into the index calculation module.

[0054] The implementation of the indicator layer calculation includes: based on the preprocessed real-time dataset, the system calculates two types of indicators to quantify combustion status and economy. The combustion status indicator calculation includes: obtaining the furnace combustion stability coefficient by analyzing the frequency and amplitude of furnace pressure fluctuations; directly correlating the monitored fly ash carbon content to calculate the percentage of carbon loss, thus obtaining the incomplete combustion loss; calculating the excess air coefficient deviation based on the deviation between actual oxygen content and theoretical optimal oxygen content; and evaluating the furnace temperature uniformity index through the standard deviation of data from multiple furnace temperature measurement points. The system monitors in real time whether the above indicators exceed limits (e.g., setting a stability coefficient threshold of ±5%), triggering an alarm if limits are exceeded. The operational economic indicator calculation includes: calculating boiler efficiency based on the heat balance equation, considering coal calorific value and flue gas losses; converting actual coal consumption to a standard coal benchmark to obtain the standard coal consumption rate; and combining fuel cost, operation and maintenance cost, and power generation to obtain the cost per kilowatt-hour. Economic indicators are linked to combustion indicators; for example, when the fly ash carbon content increases, the system automatically correlates this with increased incomplete combustion loss and decreased boiler efficiency, forming a comprehensive evaluation result.

[0055] The construction and implementation of the blending database includes: defining a stable operating condition as a unit load fluctuation ≤ 2% of the rated load (threshold is configurable), and short-term fluctuations of key operating parameters such as air-coal ratio, oxygen content, and furnace temperature not exceeding their respective set thresholds (e.g., air-coal ratio fluctuation ±3%). Under these conditions, for each stable operating period (e.g., lasting more than 10 minutes), the following information is automatically stored in the blending database: real-time coal quality of the coal fed into the furnace (calorific value, ash content, etc.); fly ash carbon content and combustion status indicators (stability coefficient, deviation, etc.); economic indicators such as boiler efficiency and standard coal consumption rate; the blending ratio at that time (calculated based on coal feed rate) and operating parameters (load, air-coal ratio, etc.); and external conditions (e.g., planned load, electricity market clearing power). The database structure is organized according to the association model of coal quality, operating condition parameters, combustion indicators, economic indicators, and optimal blending strategy, and uses time-series database storage to support fast querying and pattern matching.

[0056] The implementation of application-layer functions includes providing two types of optimization suggestions based on databases and real-time data: pre-operation coal blending suggestions and real-time blending adjustment suggestions during operation. Pre-operation coal blending suggestions include: inputting coal quality and inventory information from the coal yard, future planned load (e.g., the next day's 96-hour load curve), electricity market clearing results, and historical best operating condition samples from the blending database (screening records with the best economic indicators). Through similarity matching (e.g., Euclidean distance algorithm) or machine learning modeling (e.g., regression model), the current conditions are compared with the historical best samples. The output includes the optimal coal combination (e.g., a mixture of high-volatile coal and high-calorific-value coal), the optimal blending ratio (e.g., 70%:30%), expected boiler efficiency and coal consumption, and combustion risk warnings when coal quality fluctuates significantly. Operators formulate pre-scheduled coal blending strategies based on this information. Real-time blending adjustment suggestions during operation include: trigger conditions such as real-time monitoring of combustion status indicators exceeding limits, fly ash carbon content increasing for three consecutive sampling periods, or boiler efficiency falling below the historical average for similar operating conditions by more than 5%. Based on the current coal quality and operating parameters, the system matches and processes the results with the best results from similar operating conditions (load ±2%, similar coal quality) in the blending database. Real-time suggestions are output, such as: adjusting the blending ratio (increasing the proportion of high-calorific-value coal), switching coal types (changing to coal with higher volatile matter), fine-tuning the coal feed rate or air-coal ratio, and alerting to possible sudden changes in coal quality or equipment malfunctions. The system pushes suggestions through a human-machine interface, forming a closed-loop optimization process.

[0057] This embodiment achieves fully intelligent coal blending and combustion through data acquisition, index calculation, database construction, and application-layer linkage. Before operation, it is recommended to improve the ability to predict economic performance; during operation, real-time adjustments are made to ensure combustion stability, ultimately optimizing boiler efficiency and reducing coal consumption. All processing is based on document logic, with no exaggerated numerical effects, and conforms to practical application needs.

[0058] This application also discloses an electronic device, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, which, when executed by the at least one processor, cause the electronic device to perform the above-described intelligent coal blending real-time adjustment method.

[0059] This application also discloses a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the above-described intelligent coal blending real-time adjustment method.

[0060] It is understood that the above embodiments are merely exemplary implementations used to illustrate the principles of this application, and this application is not limited thereto. For those skilled in the art, various modifications and improvements can be made without departing from the spirit and substance of this application, and these modifications and improvements are also considered to represent the scope of protection of this application.

Claims

1. A method for real-time adjustment of intelligent coal blending, characterized in that, include: Real-time data collection of coal quality data, fly ash carbon content data, and unit operation data is performed on the coal quality data, fly ash carbon content data, and unit operation data to generate a real-time dataset. Based on the real-time dataset, the coal feed parameters and real-time blending ratio are determined, and the combustion status index and operational economic index are calculated based on the real-time dataset. Within a stable operating range where the unit load fluctuation does not exceed a set threshold, a blending database is constructed. The blending database is used to periodically store the coal quality data of the coal fed into the furnace, the carbon content data of the fly ash, the combustion status indicators, the operating economic indicators, the unit operating parameters and the real-time blending ratio, and is used to correlate coal quality, operating conditions, combustion results and economic status. Based on the coal quality data of the coal yard, the target load plan and the blending database, analyze and match the stable operating condition samples that meet the target economic efficiency stored in the blending database, store the stable operating condition samples in the blending database and determine the target coal type combination, target blending ratio and expected economic indicators. The current combustion status is monitored in real time, and the combustion status index and the corresponding operating economic index corresponding to the current combustion status are linked and matched with the stable operating condition sample. When the result of the linkage matching exceeds the preset matching value, the corresponding blending ratio adjustment scheme, coal type switching scheme or air-coal ratio optimization scheme is generated.

2. The method according to claim 1, characterized in that, The real-time collection of coal quality data for coal entering the furnace includes: The coal quality data of the coal fed into the furnace is collected in real time using laser spectroscopy technology. The coal quality data of the coal fed into the furnace includes the calorific value, ash content and volatile matter parameters of the coal fed into the furnace. The carbon content data of the fly ash is collected in real time by spectral analysis or a carbon analyzer. The unit operation data is collected in real time based on hierarchical acquisition and plant-level monitoring information. The unit operation data includes unit load, air-coal ratio, oxygen content, furnace temperature and coal feed parameters. The real-time blending ratio is calculated based on the coal feed data of the unit operation data in the real-time dataset.

3. The method according to claim 1, characterized in that, The calculation of combustion status indicators and operational economy indicators based on the real-time dataset includes: Based on the coal quality data of the coal fed into the furnace, the carbon content data of the fly ash, and the unit operation data in the real-time dataset, the combustion state index is calculated, wherein the combustion state index includes the furnace combustion stability coefficient, incomplete combustion loss, excess air coefficient deviation, and furnace temperature uniformity index. Based on the unit operation data and combustion status indicators in the real-time dataset, the operating economic indicators are calculated, including boiler efficiency, standard coal consumption rate, and cost per kilowatt-hour.

4. The method according to claim 1, wherein the set threshold is 2% of the rated output of the unit, characterized in that, The method further includes: When the unit load fluctuation does not exceed the set threshold and other major operating conditions are stable, the current state interval is defined as the stable operating condition interval. The other key operating conditions are stable, including the fluctuation range of air-coal ratio, oxygen content, and furnace temperature, all of which do not exceed the corresponding target thresholds.

5. The method according to claim 1, characterized in that, The coal quality data from the coal yard, the target load plan, and the blending database are analyzed and matched with stable operating condition samples that meet the target economic efficiency stored in the blending database to determine the target coal type combination, target blending ratio, and expected economic indicators, including: Based on the coal quality data and inventory information of the coal yard, the target load plan and the electricity market clearing results, as well as the blending database, the stable operating condition samples that meet the target economic efficiency stored in the blending database are analyzed and determined through similarity matching or machine learning modeling. These samples are used to determine the target coal type combination, the target blending ratio, and the expected economic indicators. The expected economic indicators include expected boiler efficiency and combustion risk warnings.

6. The method according to claim 1, characterized in that, When the result of the linkage matching exceeds a preset matching value, a corresponding blending ratio adjustment scheme, coal type switching scheme, or air-coal blending ratio optimization scheme is generated, including: When the linkage matching is triggered by conditions such as combustion state exceeding limits, continuous increase in fly ash carbon content, or boiler efficiency lower than historical similar operating conditions, a corresponding blending ratio adjustment scheme, coal type switching scheme, or air-coal ratio optimization scheme will be generated.

7. The method according to claim 1, characterized in that, The blending ratio adjustment scheme includes indicating the possibility of sudden changes in coal quality or the possibility of equipment malfunction.

8. A real-time adjustment system for intelligent coal blending, characterized in that, include: The data acquisition and preprocessing module is used to acquire coal quality data, fly ash carbon content data and unit operation data of coal fed into the furnace in real time, and to perform data synchronization processing, filtering processing, anomaly removal processing and time alignment processing on the coal quality data of coal fed into the furnace, the fly ash carbon content data and the unit operation data to generate a real-time dataset. The multi-index determination module is used to determine the coal feed parameters and real-time blending ratio based on the real-time dataset, and to calculate the combustion state index and operating economy index based on the real-time dataset. The blending database construction module is used to construct a blending database within a stable operating range where the unit load fluctuation does not exceed a set threshold. The blending database is used to periodically store the coal quality data of the coal fed into the furnace, the carbon content data of the fly ash, the combustion status indicators, the operating economic indicators, the unit operating parameters and the real-time blending ratio, and is used to associate coal quality, operating conditions, combustion results and economic status. The stable operating condition sample matching module is used to analyze and match stable operating condition samples that meet the target economic efficiency stored in the blending database based on coal quality data, target load plan and the blending database of the coal yard, store the stable operating condition samples in the blending database and determine the target coal type combination, target blending ratio and expected economic indicators. The real-time adjustment and switching module is used to monitor the current combustion state in real time, and to link and match the combustion state index and the corresponding operating economic index of the current combustion state with the stable operating condition sample. When the result of the linkage matching exceeds the preset matching value, the module generates the corresponding blending ratio adjustment scheme, coal type switching scheme or air-coal ratio optimization scheme.

9. An electronic device, characterized in that, include: At least one processor; And, a memory communicatively connected to the at least one processor; The memory stores instructions that can be executed by the at least one processor, which, when executed by the at least one processor, cause the electronic device to perform a real-time adjustment method for intelligent coal blending as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements a real-time adjustment method for intelligent coal blending as described in any one of claims 1 to 7.

Images