A coal quality control system and method for a thermal power plant

Abstract

The application discloses a kind of coal quality control system and method of power plant into furnace, it is related to boiler detection technical field, method includes collecting the original coal quality data of coal to be into furnace and unit real-time operation data, forms original collection data set;It is pretreated, and the coal quality-operation data set after pretreatment is generated;Coal quality core feature index set is extracted based on the data set, and the coal quality quality grade evaluation is carried out according to this, and evaluation result is generated;Combining evaluation result and unit operation demand parameter, coal blending optimization model is constructed and solved, and coal blending ratio scheme is generated;According to scheme, coal handling operation is executed and real-time coal quality monitoring data of coal into furnace is collected;Real-time monitoring data is compared with coal quality core feature index set, and deviation analysis result is generated;According to deviation result, dynamically adjust coal blending ratio scheme parameter, complete coal quality closed-loop control into furnace.It can improve the disconnection problem of existing control link, improve the coherence and accuracy of coal quality control into furnace, adapt to unit operation control demand.

Description

Technical Field

[0001] This invention relates to the field of boiler testing technology, and in particular to a coal quality control system and method for coal entering the boiler in a thermal power plant. Background Technology

[0002] Precise control of coal quality entering the furnace at thermal power plants is a core element in ensuring the safe and stable operation of the unit, directly affecting the combustion state in the furnace and the overall operating conditions of the unit. Therefore, the industry generally carries out coal quality control work by collecting coal quality data and formulating coal blending plans.

[0003] In existing coal quality control processes at thermal power plants, the various control links lack a logical connection and closed-loop control mechanism throughout the entire process. From the collection and processing of coal quality and unit operation data, coal quality grade assessment, and coal blending scheme formulation to the execution of coal feeding operations, the established coal blending scheme cannot be dynamically adjusted based on real-time coal quality monitoring data collected during the coal feeding process. The operations and data outputs of each link are disconnected, resulting in the inability to form a data-driven, closed-loop management system for coal quality control. Ultimately, this leads to insufficient accuracy and effectiveness in coal quality control, making it difficult to achieve precise and dynamic control of coal quality entering the furnace. To address these issues, there is an urgent need to propose a logically interconnected method for coal quality control at thermal power plants, which can improve the accuracy and effectiveness of coal quality control by constructing a closed-loop management system throughout the entire process. Summary of the Invention

[0004] To address the technical problems existing in the prior art, the present invention provides a coal quality control system and method for coal fed into a thermal power plant.

[0005] The technical solution adopted in this invention is:

[0006] The first aspect of this application provides a method for controlling the quality of coal fed into a thermal power plant, comprising the following steps:

[0007] Step 1: Collect raw coal quality data of coal to be fed into the furnace and real-time operating data of the unit to form the raw data set.

[0008] Step 2: Perform data preprocessing on the original collected dataset to generate a preprocessed coal quality-operation dataset;

[0009] Step 3: Extract coal quality features based on the preprocessed coal quality-operation dataset to generate a set of core coal quality feature indicators;

[0010] Step 4: Conduct a quality grade assessment of the coal entering the furnace based on the set of core coal quality characteristic indicators, and generate coal quality assessment results;

[0011] Step 5: Combining the coal quality assessment results and unit operation requirements parameters, construct and solve the coal blending optimization model to generate the coal blending ratio scheme to be fed into the furnace.

[0012] Step 6: Perform coal feeding operation according to the coal blending ratio plan, and collect real-time coal quality monitoring data of the coal entering the furnace at the same time;

[0013] Step 7: Compare and analyze the real-time coal quality monitoring data with the set of core coal quality characteristic indicators to generate coal quality deviation analysis results;

[0014] Step 8: Dynamically adjust the parameters of the coal blending scheme based on the coal quality deviation analysis results to complete the closed-loop control of the coal quality entering the furnace.

[0015] The second aspect of this application provides a coal quality control system for a thermal power plant, which applies the above-mentioned method for coal quality control in a thermal power plant, including:

[0016] The coal quality operation data acquisition module is used to collect the original coal quality data of coal to be fed into the furnace and the real-time operation data of the unit in the thermal power plant, forming the original acquisition dataset;

[0017] A coal quality-operation data preprocessing module is used to perform data preprocessing operations on the original collected dataset to generate a preprocessed coal quality-operation dataset.

[0018] A coal quality core feature extraction module is used to extract coal quality features based on the preprocessed coal quality-operation dataset and generate a set of coal quality core feature indicators.

[0019] The coal quality grade assessment module is used to conduct coal quality grade assessment based on the set of core characteristic indicators of coal quality and generate coal quality assessment results.

[0020] The coal blending optimization model solving module is used to combine the coal quality assessment results and the unit operation requirements parameters to construct and solve the coal blending optimization model, and generate the coal blending ratio scheme of the coal to be fed into the furnace.

[0021] The coal feeding execution and coal quality monitoring module is used to execute the coal feeding operation according to the coal blending ratio scheme, and at the same time collect real-time coal quality monitoring data of the coal entering the furnace;

[0022] The coal quality data deviation analysis module is used to compare and analyze real-time coal quality monitoring data with a set of core coal quality characteristic indicators to generate coal quality deviation analysis results.

[0023] The coal blending ratio dynamic adjustment module is used to dynamically adjust the parameters of the coal blending ratio scheme based on the coal quality deviation analysis results, thereby completing the closed-loop control of the coal quality entering the furnace.

[0024] The beneficial effects of this invention are as follows: By setting up logically interconnected end-to-end control steps, a closed-loop control system is constructed, from raw data collection to dynamic adjustment of coal blending ratios. This effectively improves the problem of disconnection between various links in the existing coal quality control process, enhancing the continuity of coal quality control. Simultaneously, through comparative analysis of real-time coal quality monitoring data and the set of core coal quality characteristic indicators, combined with dynamic adjustments to the coal blending ratio scheme, the accuracy of coal quality control can be improved, enhancing the overall effectiveness of coal quality control and helping to better adapt to the coal quality control requirements of thermal power plant units. Attached Figure Description

[0025] Figure 1 This is a schematic diagram of the method flow of the present invention. Detailed Implementation

[0026] The embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0027] Example 1

[0028] A method for controlling the quality of coal fed into a thermal power plant, such as Figure 1 As shown, it includes the following steps:

[0029] Step 1: Collect raw coal quality data of coal to be fed into the furnace and real-time operating data of the unit to form the raw data set.

[0030] It should be noted that the raw coal quality data is the basic physical property data and composition data of the coal to be fed into the furnace without any treatment, while the real-time operation data of the unit is the various operating status data generated in real time during the operation of the thermal power plant unit. The original collection dataset is a comprehensive data set formed by integrating the above two types of data.

[0031] The core foundation for coal quality control in the furnace is coal quality data and unit operation data. Only by collecting both types of data comprehensively and accurately can we provide data support for subsequent data analysis, coal blending scheme formulation, and other operations. If there are any omissions or deviations in the data collection process, the effectiveness of all subsequent control operations will be affected. Therefore, this step is the basic prerequisite for the entire coal quality control method in the furnace.

[0032] In the specific implementation process, real-time operating data of the unit is continuously collected through online monitoring equipment, while the raw coal quality data of the coal to be fed into the furnace is detected and collected through offline detection methods. The real-time operating data of the unit collected by the online monitoring equipment and the raw coal quality data obtained by offline detection methods are integrated and summarized, and the two types of data are uniformly organized according to the preset data format to finally form the original collection dataset.

[0033] For example, real-time load data of the unit and real-time combustion data in the furnace can be collected by online detection equipment deployed on the coal conveyor belt. The original coal quality data such as calorific value and ash content of the coal to be fed into the furnace can be detected by laboratory testing methods. The collected unit load data, furnace combustion data and detected coal calorific value and ash content data can be integrated to form an original collection dataset containing multiple types of data.

[0034] This step collects data by using a combination of online monitoring and offline detection, enabling comprehensive collection of raw coal quality data and real-time unit operation data. The resulting raw dataset retains the original information of both types of data, providing comprehensive and accurate basic data support for subsequent steps and preventing deviations in subsequent control operations due to missing data.

[0035] Step 2: Perform data preprocessing on the original collected dataset to generate a preprocessed coal quality-operation dataset.

[0036] It should be noted that data preprocessing is a collective term for a series of operations that target and process various types of data in the original acquired dataset. The preprocessed coal quality-operation dataset is a structured data set of the original acquired dataset after data preprocessing, removing invalid data and completing standardization.

[0037] The various types of data in the raw dataset come from different collection and detection methods, which can easily lead to problems such as data anomalies, missing data, and inconsistent data formats. These problems can directly affect the accuracy of subsequent operations such as coal quality feature extraction and quality grade assessment. Therefore, it is necessary to preprocess the raw dataset to transform it into a standardized dataset that meets the requirements of subsequent operations.

[0038] In the specific implementation process, firstly, outlier identification is performed on all data in the original collected dataset. Abnormal data in the dataset is filtered out and removed through data verification rules. Next, missing values ​​are filled in the dataset after outlier removal. Data imputation methods are used to fill in the missing data in the dataset. Finally, the dataset after outlier removal and missing value filling is normalized to convert data with different dimensions and different numerical ranges into values ​​with a unified standard, and finally, a preprocessed coal quality-operation dataset is generated.

[0039] For example, abnormal unit load data that is significantly outside the reasonable range can be identified and removed from the original collected dataset. Missing coal sulfur content data in the dataset can be supplemented by the average sulfur content of the same batch of coal. The numerical range of unit load and the numerical range of coal calorific value can be uniformly converted to a preset range. After completing the above operations, a preprocessed coal quality-operation dataset is obtained.

[0040] This step involves a series of preprocessing operations on the original collected dataset, which can effectively remove invalid data, supplement missing data, and standardize the data. The resulting preprocessed coal quality-operation dataset has structured and standardized characteristics, which can effectively improve the accuracy and efficiency of subsequent data analysis operations.

[0041] Step 3: Extract coal quality features based on the preprocessed coal quality-operation dataset to generate a set of core coal quality feature indicators.

[0042] It should be noted that coal quality feature extraction is an operation that selects and extracts indicators that can reflect the core coal quality characteristics of the coal to be fed into the furnace from the pre-processed coal quality-operation data set. The coal quality core feature index set is an index set formed after integrating and refining the core coal quality feature indicators. Each index in this set forms a correlation mapping relationship with the real-time operation data of the unit.

[0043] The pre-processed coal quality-operation dataset contains a large amount of data, some of which has limited practical significance for the control of coal quality entering the furnace. If subsequent quality level assessments are conducted directly based on the full dataset, it will increase the complexity of the operation and reduce the pertinence of the assessment. Therefore, it is necessary to extract indicators from the dataset that can reflect the core characteristics of coal quality and are related to unit operation, so as to provide accurate indicator basis for subsequent quality level assessments.

[0044] In the specific implementation process, the feature screening method is first used to select coal quality indicators that are closely related to coal quality characteristics and have a significant impact on unit operation from the preprocessed coal quality-operation dataset. Then, the selected coal quality indicators are subjected to feature dimensionality reduction processing to remove indicators with redundant correlations and retain key indicators that can reflect the core coal quality characteristics. These key indicators are then integrated and a correlation mapping relationship between each indicator and the real-time operation data of the unit is established to finally generate a set of core coal quality feature indicators.

[0045] For example, indicators related to coal quality characteristics and unit combustion, such as calorific value, ash content, volatile matter, and sulfur content, can be screened from the pre-processed coal quality-operation dataset. Other coal quality indicators that are highly redundant with the above indicators can be removed. The remaining calorific value, ash content, volatile matter, and sulfur content indicators can be integrated into a set of core coal quality characteristic indicators, and the correlation mapping relationship between each indicator and unit load data and furnace combustion data can be established.

[0046] This step extracts coal quality features through a combination of feature screening and feature dimensionality reduction. It can extract core coal quality feature indicators from massive amounts of data. The generated set of core coal quality feature indicators is highly targeted and has low redundancy. Furthermore, each indicator is correlated with the real-time operating data of the unit, which can provide accurate and effective indicator basis for subsequent evaluation of the quality grade of coal entering the furnace, thereby improving the efficiency and targeting of the evaluation operation.

[0047] Step 4: Conduct a coal quality grade assessment based on the core characteristic index set of coal quality, and generate coal quality assessment results.

[0048] It should be noted that the assessment of the quality grade of coal entering the furnace is an operation based on the set of core characteristic indicators of coal quality to determine the grade and compliance of the indicators of the coal entering the furnace. The coal quality assessment result is a comprehensive assessment conclusion that includes the quality grade of the coal to be entered into the furnace and the compliance results of each characteristic indicator.

[0049] The set of core coal quality characteristics reflects the core coal quality characteristics of the coal to be fed into the furnace. By evaluating this set of indicators in conjunction with the preset coal quality evaluation standards, it is possible to determine whether the quality of the coal to be fed into the furnace meets the unit's operating requirements. This provides a direct quality basis for the subsequent construction of the coal blending optimization model and the formulation of the coal blending ratio scheme. It is a key step connecting coal quality characteristic analysis and coal blending scheme formulation.

[0050] In the specific implementation process, the coal quality evaluation standard preset by the thermal power plant is first retrieved. This standard includes the reasonable range of each core characteristic indicator of coal quality and the basis for judging different quality grades. Then, the values ​​of each indicator in the set of core characteristic indicators of coal quality are matched one by one with the preset coal quality evaluation standard. Based on the matching results, it is determined whether each characteristic indicator meets the standard requirements. Then, combined with the conformity judgment results of each indicator, the quality grade of the coal to be fed into the furnace is determined according to the preset grade judgment rules. Finally, the conformity judgment results of each indicator and the quality grade of the coal to be fed into the furnace are integrated to generate the coal quality assessment result.

[0051] For example, a preset coal quality evaluation standard may specify reasonable numerical ranges for calorific value, ash content, volatile matter, and sulfur content, as well as the criteria for judging three quality grades: high-quality, qualified, and needing optimization. The values ​​of indicators such as calorific value and ash content, which are the core characteristic indicators of coal quality, are matched with the preset range. It is determined that the calorific value meets the standard and the sulfur content slightly exceeds the standard. Then, combined with the matching results of each indicator, the quality grade of the batch of coal to be fed into the furnace is determined to be needing optimization. The above judgment results are integrated to form the coal quality assessment result.

[0052] This step assesses the quality grade of coal to be fed into the furnace based on a set of core coal quality characteristic indicators. It can accurately determine the quality grade of the coal to be fed into the furnace and the compliance of each core indicator. The generated coal quality assessment results can clearly reflect the quality status of the coal to be fed into the furnace, providing a clear quality basis for the construction of subsequent coal blending optimization models, and making the subsequent coal blending ratio scheme more targeted.

[0053] Step 5: Combining the coal quality assessment results and unit operation requirements, construct and solve the coal blending optimization model to generate the coal blending ratio scheme for the coal to be fed into the furnace.

[0054] It should be noted that the unit operation requirements parameters are the various parameter requirements for the coal quality of the coal fed into the furnace during the operation of the thermal power plant unit. The coal blending optimization model is a mathematical model constructed by combining the coal quality assessment results and the unit operation requirements parameters to optimize the coal blending scheme. The coal blending ratio scheme is obtained after solving the coal blending optimization model and includes the blending ratio of different coal types and the coal feeding sequence.

[0055] The coal quality assessment results reflect the actual quality of the coal to be fed into the furnace, while the unit operation requirements parameters clarify the unit's requirements for the quality of the coal to be fed into the furnace. Only by combining the two to construct a coal blending optimization model can the formulated coal blending scheme be adapted to both the actual coal quality of the coal to be fed into the furnace and the unit's operation requirements. If only one of them is considered, the coal blending scheme will lack practicality and rationality. Therefore, this step is the core step in realizing the optimized design of the coal blending scheme.

[0056] In the specific implementation process, the unit operation requirements parameters of the thermal power plant are first collected. The coal quality assessment results and unit operation requirements parameters are used as model input conditions. With coal quality stability and unit operation economy as optimization objectives, a coal blending optimization model is constructed. Then, a suitable model solving algorithm is used to solve the coal blending optimization model. During the solution process, the coal quality characteristics of different coal types and unit operation requirements are comprehensively considered to determine the optimal blending ratio and reasonable coal feeding sequence of different coal types. The above solution results are integrated to finally generate the coal blending ratio scheme of the coal to be fed into the furnace.

[0057] For example, the collected unit operation requirements parameters include the unit's rated load parameters, furnace combustion optimization parameters, and pollutant emission compliance parameters. Combined with the coal quality assessment results, which indicate that the coal to be fed into the furnace is of an unoptimized grade and has excessive sulfur content, a coal blending optimization model is constructed with the optimization objectives of ensuring stable coal quality and reducing unit operating costs. By solving the model, the blending ratio of high-sulfur coal to low-sulfur coal is determined to be 7:3, and the coal feeding order is low-sulfur coal first, followed by high-sulfur coal. After integration, a coal blending ratio scheme is generated.

[0058] This step combines the coal quality assessment results with the unit's operating requirements to construct and solve the coal blending optimization model. This allows the generated coal blending scheme to not only adapt to the actual quality of the coal to be fed into the furnace but also meet the unit's operating requirements. Furthermore, by optimizing coal quality stability and unit operating economy, the coal blending scheme can be both reasonable and economical, providing a scientific and feasible basis for subsequent coal feeding operations.

[0059] Step 6: Perform the coal feeding operation according to the coal blending ratio plan, and at the same time collect real-time coal quality monitoring data of the coal entering the furnace.

[0060] It should be noted that the coal feeding operation is the execution of transporting different types of coal to the furnace of a thermal power plant according to the coal blending ratio scheme. The real-time coal quality monitoring data is the coal quality data obtained by real-time monitoring of the coal that is about to be put into the furnace during the coal feeding operation.

[0061] The formulation of the coal blending scheme ultimately needs to be implemented through coal feeding operations. During the coal feeding operation, the coal quality may deviate to some extent due to transportation, blending, and other processes. If coal feeding is carried out in accordance with the scheme without real-time coal quality monitoring, it is impossible to grasp the actual coal quality entering the furnace in a timely manner, and it is also impossible to provide data support for subsequent deviation analysis and scheme adjustment. Therefore, this step is the execution and data collection step for the implementation of the coal blending scheme and subsequent closed-loop management.

[0062] In the specific implementation process, according to the blending ratio of different coal types and the coal feeding sequence determined in the coal blending scheme, the coal feeding operation is carried out through the coal conveying system of the thermal power plant. Coal quality monitoring equipment is deployed at key nodes of the coal feeding operation to continuously monitor the quality of the mixed coal that is about to be fed into the furnace in real time, collect the coal quality data generated during the monitoring process, and perform preliminary processing on the collected real-time coal quality data to obtain the real-time coal quality monitoring data of the coal fed into the furnace.

[0063] For example, according to the coal blending ratio of 7:3 for high-sulfur coal and low-sulfur coal, and the order of coal feeding from low-sulfur coal to high-sulfur coal, the two types of coal are transported to the furnace via a coal conveyor belt. Online coal quality monitoring equipment is installed near the furnace on the coal conveyor belt to monitor the calorific value, sulfur content and other coal quality indicators of the blended coal in real time. The real-time data obtained from the monitoring is processed to obtain the real-time coal quality monitoring data of the coal entering the furnace.

[0064] This step involves feeding coal according to the coal blending scheme, ensuring the implementation of the coal blending plan. At the same time, real-time coal quality monitoring data is collected during the coal feeding process, which allows for timely understanding of the actual coal quality entering the furnace. This provides real-time and accurate data support for subsequent coal quality deviation analysis, enabling the simultaneous execution of the coal blending plan and real-time coal quality monitoring.

[0065] Step 7: Compare and analyze the real-time coal quality monitoring data with the set of core coal quality characteristic indicators to generate coal quality deviation analysis results.

[0066] It should be noted that coal quality deviation analysis is an operation that compares real-time coal quality monitoring data with a set of core coal quality characteristic indicators to analyze the degree of difference between the two. The results of coal quality deviation analysis reflect the analytical conclusions on the deviation between real-time coal quality monitoring data and the set of core coal quality characteristic indicators.

[0067] The set of core coal quality characteristic indicators is the core basis for the subsequent coal blending scheme. It represents the expected coal quality condition entering the furnace, while real-time coal quality monitoring data is the actual coal quality condition entering the furnace. By comparing and analyzing the two, we can clarify the deviation between the actual coal quality entering the furnace and the expected coal quality. If there is a deviation, we can promptly identify the problem and provide direction for adjusting the subsequent coal blending scheme. This is a key analytical step to achieve closed-loop management.

[0068] In the specific implementation process, firstly, each coal quality indicator in the real-time coal quality monitoring data is compared with the corresponding indicators in the coal quality core characteristic indicator set, and the numerical difference between each indicator is calculated. Then, according to the preset deviation judgment standard, it is analyzed whether the numerical difference of each indicator is within a reasonable range, and deviation indicators that exceed the reasonable range are identified. Finally, the comparison results, numerical differences and deviation judgment of each indicator are integrated to generate the coal quality deviation analysis results.

[0069] For example, the calorific value and sulfur content in real-time coal quality monitoring data can be compared with the calorific value and sulfur content corresponding to the core characteristic indicators of coal quality. If the numerical difference of the calorific value is within a reasonable range, and the numerical difference of the sulfur content exceeds a reasonable range, the sulfur content is identified as a deviation indicator. The above comparison and judgment results are integrated to form the coal quality deviation analysis results.

[0070] This step compares and analyzes real-time coal quality monitoring data with a set of core coal quality characteristic indicators. It can accurately identify the deviation between the actual coal quality fed into the furnace and the expected coal quality. The generated coal quality deviation analysis results can clearly reflect the deviation indicators and the degree of deviation, providing a clear direction and basis for subsequent coal blending and proportioning scheme adjustments, making the scheme adjustments more targeted.

[0071] Step 8: Dynamically adjust the parameters of the coal blending scheme based on the coal quality deviation analysis results to complete the closed-loop control of the coal quality entering the furnace.

[0072] It should be noted that the parameters of the coal blending scheme are the adjustable core execution parameters included in the coal blending scheme, including the blending ratio of different coal types, coal feeding amount and coal feeding rhythm. Closed-loop management refers to the full-process management from data collection, scheme formulation, execution and implementation to deviation analysis and scheme adjustment. Through the cyclical connection of each step, continuous dynamic management of the coal quality entering the furnace can be achieved.

[0073] The coal quality deviation analysis results clearly show the deviation between the actual coal quality fed into the furnace and the expected coal quality. If the coal blending scheme is not adjusted according to the deviation results, the actual coal quality fed into the furnace will continue to deviate from the expected requirements, making it impossible to achieve precise control over the coal quality fed into the furnace. Therefore, it is necessary to dynamically adjust the parameters of the coal blending scheme according to the deviation analysis results and synchronize the adjusted scheme to the execution system to achieve cyclical connection of each step and complete the closed-loop control of the coal quality fed into the furnace.

[0074] In the specific implementation process, firstly, based on the coal quality deviation analysis results, the types of parameters that need to be adjusted in the coal blending scheme are determined. For the identified deviation indicators, the blending ratio of different coal types is adjusted. At the same time, the coal feeding amount and the coal feeding rhythm are corrected according to the real-time operating status of the unit. After the parameter adjustment is completed, a new coal blending scheme is generated. The adjusted coal blending scheme is then simultaneously sent to the coal feeding execution system of the thermal power plant. The coal feeding execution system continues to execute the coal feeding operation according to the adjusted scheme, while continuously collecting real-time coal quality monitoring data, and enters the next round of deviation analysis and scheme adjustment process, ultimately completing the closed-loop control of the coal quality entering the furnace.

[0075] For example, based on the conclusion that the sulfur content in the coal quality deviation analysis results exceeds the reasonable range, the blending ratio of high-sulfur coal to low-sulfur coal is adjusted from 7:3 to 6:4. At the same time, based on the current load status of the unit, the coal feeding amount is appropriately modified and the coal feeding pace is slowed down, generating an adjusted coal blending scheme. This scheme is then sent to the coal conveying system, which performs the coal feeding operation according to the new scheme, while continuously monitoring the sulfur content and other indicators of the coal entering the furnace, before proceeding to the next round of analysis and adjustment.

[0076] This step dynamically adjusts the parameters of the coal blending scheme based on the coal quality deviation analysis results. It can promptly correct the deviation between the actual coal quality fed into the furnace and the expected coal quality, ensuring that the coal blending scheme always adapts to the actual coal quality and unit operation requirements. At the same time, the adjusted scheme is synchronized to the coal feeding execution system to achieve cyclical connection between each step, complete the closed-loop control of the coal quality fed into the furnace, and effectively improve the real-time performance and accuracy of coal quality control.

[0077] Example 2

[0078] A coal quality control system for a thermal power plant, employing the aforementioned method for coal quality control in a thermal power plant, includes:

[0079] The coal quality operation data acquisition module is used to collect the original coal quality data of coal to be fed into the furnace and the real-time operation data of the unit in the thermal power plant, forming the original acquisition dataset;

[0080] A coal quality-operation data preprocessing module is used to perform data preprocessing operations on the original collected dataset to generate a preprocessed coal quality-operation dataset.

[0081] A coal quality core feature extraction module is used to extract coal quality features based on the preprocessed coal quality-operation dataset and generate a set of coal quality core feature indicators.

[0082] The coal quality grade assessment module is used to conduct coal quality grade assessment based on the set of core characteristic indicators of coal quality and generate coal quality assessment results.

[0083] The coal blending optimization model solving module is used to combine the coal quality assessment results and the unit operation requirements parameters to construct and solve the coal blending optimization model, and generate the coal blending ratio scheme of the coal to be fed into the furnace.

[0084] The coal feeding execution and coal quality monitoring module is used to execute the coal feeding operation according to the coal blending ratio scheme, and at the same time collect real-time coal quality monitoring data of the coal entering the furnace;

[0085] The coal quality data deviation analysis module is used to compare and analyze real-time coal quality monitoring data with a set of core coal quality characteristic indicators to generate coal quality deviation analysis results.

[0086] The coal blending ratio dynamic adjustment module is used to dynamically adjust the parameters of the coal blending ratio scheme based on the coal quality deviation analysis results, thereby completing the closed-loop control of the coal quality entering the furnace.

[0087] The embodiments described above are merely illustrative of specific implementations of the present invention, and while the descriptions are detailed, they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these modifications and improvements all fall within the scope of protection of the present invention.

Claims

1. A method for controlling the quality of coal fed into a thermal power plant, characterized in that, Includes the following steps: Step 1: Collect raw coal quality data of coal to be fed into the furnace and real-time operating data of the unit to form the raw data set. Step 2: Perform data preprocessing on the original collected dataset to generate a preprocessed coal quality-operation dataset; Step 3: Extract coal quality features based on the preprocessed coal quality-operation dataset to generate a set of core coal quality feature indicators; Step 4: Conduct a quality grade assessment of the coal entering the furnace based on the set of core coal quality characteristic indicators, and generate coal quality assessment results; Step 5: Combining the coal quality assessment results and unit operation requirements parameters, construct and solve the coal blending optimization model to generate the coal blending ratio scheme to be fed into the furnace. Step 6: Perform coal feeding operation according to the coal blending ratio plan, and collect real-time coal quality monitoring data of the coal entering the furnace at the same time; Step 7: Compare and analyze the real-time coal quality monitoring data with the set of core coal quality characteristic indicators to generate coal quality deviation analysis results; Step 8: Dynamically adjust the parameters of the coal blending scheme based on the coal quality deviation analysis results to complete the closed-loop control of the coal quality entering the furnace.

2. The method for controlling the quality of coal fed into a thermal power plant according to claim 1, characterized in that, In step 1, the raw coal quality data consists of the basic physical properties and composition data of the coal to be fed into the furnace, and the real-time operation data of the unit consists of the unit load data, furnace combustion data and pollutant emission data. The raw data set is obtained through the collaborative collection of online monitoring equipment and offline detection methods.

3. The method for controlling the quality of coal fed into a thermal power plant according to claim 1, characterized in that, In step 2, the data preprocessing operations sequentially perform outlier identification and removal, missing data completion, and data normalization transformation. After preprocessing, the coal quality-operation dataset becomes a structured dataset with invalid data removed and standardized.

4. The method for controlling the quality of coal fed into a thermal power plant according to claim 1, characterized in that, In step 3, coal quality feature extraction adopts a combination of feature screening and feature dimensionality reduction. The core feature index set of coal quality includes calorific value feature index, ash content feature index, volatile matter feature index and sulfur content feature index. Each index forms a correlation mapping relationship with the real-time operation data of the unit.

5. The method for controlling the quality of coal fed into a thermal power plant according to claim 1, characterized in that, In step 4, the coal quality grade assessment is performed by matching the set of core coal quality characteristic indicators with the preset coal quality evaluation standards. The coal quality assessment results include the quality grade of the coal to be fed into the furnace and the conformity determination results of each characteristic indicator.

6. The method for controlling the quality of coal fed into a thermal power plant according to claim 1, characterized in that, In step 5, the unit operation requirements parameters include the unit rated load parameters, furnace combustion optimization parameters, and pollutant emission compliance parameters. The coal blending optimization model takes coal quality stability and unit operation economy as optimization objectives. The coal blending ratio scheme generated after solving includes the blending ratio of different coal types and the coal feeding sequence.

7. The method for controlling the quality of coal fed into a thermal power plant according to claim 1, characterized in that, In step 8, the parameters of the dynamic coal blending scheme include adjusting the blending ratio of each type of coal, correcting the coal feeding amount, and adjusting the coal feeding rhythm. The adjusted coal blending scheme is then simultaneously sent to the coal feeding execution system.

8. A coal quality control system for a thermal power plant, characterized in that, The method for controlling the quality of coal fed into a thermal power plant according to any one of claims 1-7 includes: The coal quality operation data acquisition module is used to collect the original coal quality data of coal to be fed into the furnace and the real-time operation data of the unit in the thermal power plant, forming the original acquisition dataset; A coal quality-operation data preprocessing module is used to perform data preprocessing operations on the original collected dataset to generate a preprocessed coal quality-operation dataset. A coal quality core feature extraction module is used to extract coal quality features based on the preprocessed coal quality-operation dataset and generate a set of coal quality core feature indicators. The coal quality grade assessment module is used to conduct coal quality grade assessment based on the set of core characteristic indicators of coal quality and generate coal quality assessment results. The coal blending optimization model solving module is used to combine the coal quality assessment results and the unit operation requirements parameters to construct and solve the coal blending optimization model, and generate the coal blending ratio scheme of the coal to be fed into the furnace. The coal feeding execution and coal quality monitoring module is used to execute the coal feeding operation according to the coal blending ratio scheme, and at the same time collect real-time coal quality monitoring data of the coal entering the furnace; The coal quality data deviation analysis module is used to compare and analyze real-time coal quality monitoring data with a set of core coal quality characteristic indicators to generate coal quality deviation analysis results. The coal blending ratio dynamic adjustment module is used to dynamically adjust the parameters of the coal blending ratio scheme based on the coal quality deviation analysis results, thereby completing the closed-loop control of the coal quality entering the furnace.

Images