CN-121996950-A - Method and device for analyzing coal quality of coal-fired boiler

CN121996950ACN 121996950 ACN121996950 ACN 121996950ACN-121996950-A

Abstract

The application discloses a method and a device for analyzing coal quality of a coal-fired boiler. The method comprises the steps of obtaining a current operation monitoring parameter set corresponding to fire coal to be analyzed, judging whether the operation monitoring parameters meet preset conditions or not, wherein the preset conditions are that abnormal data do not exist in the operation monitoring parameters, determining a coal quality analysis result corresponding to the fire coal to be analyzed based on a plurality of preset formulas and the operation monitoring parameters if the abnormal data do not meet the preset conditions, determining a coal quality analysis result corresponding to the fire coal to be analyzed based on a coal quality analysis model and the operation monitoring parameters if the abnormal data do not meet the preset conditions, and generating a target refined combustion operation adjustment scheme corresponding to the fire coal to be analyzed according to the coal quality analysis result.

Inventors

JIANG LONG
MOU XIAOZHE
Tong Boheng
XU YANG
SONG YUNCHANG
LI YUANYUAN
YANG XUETING
LI JINJING

Assignees

华北电力科学研究院有限责任公司
国家电网有限公司

Dates

Publication Date: 20260508
Application Date: 20251231

Claims (10)

1. A method of analyzing the quality of coal in a coal-fired boiler, the method comprising: acquiring a current operation monitoring parameter set corresponding to the fire coal to be analyzed, wherein the current operation monitoring parameter set comprises a plurality of operation monitoring parameters; judging whether the operation monitoring parameters meet preset conditions or not, wherein the preset conditions are that abnormal data do not exist in the operation monitoring parameters; If the coal quality analysis results are not met, determining the coal quality analysis results corresponding to the coal to be analyzed and the coal to be fired on the basis of a coal quality analysis model and a plurality of operation monitoring parameters; And generating a target refined combustion operation adjustment scheme corresponding to the to-be-analyzed fire coal.
2. The method of claim 1, wherein the plurality of operation monitoring parameters include a standard flue gas amount, a coal amount, a boiler outlet flue gas volume moisture content, an excess air factor, a SO 2 concentration in a boiler outlet flue gas, a CO concentration in a boiler outlet flue gas, a NO concentration in a boiler outlet flue gas, an oxygen content in a boiler outlet flue gas, and a particulate matter concentration in a boiler outlet flue gas corresponding to the incoming coal to be analyzed, and wherein the determining the coal quality analysis result corresponding to the incoming coal to be analyzed based on the plurality of preset formulas and the plurality of operation monitoring parameters comprises: Acquiring a constant item set corresponding to the coal to be analyzed and fed into the furnace, wherein the constant item set comprises a coefficient for converting sulfur in the coal into SO 2 and a total ash ratio of fly ash; Substituting the standard flue gas amount, the coal amount, the coefficient of converting sulfur in the coal into SO 2 and the SO 2 concentration in the boiler outlet flue gas into a first preset formula to calculate the received base sulfur content corresponding to the target fired coal; Substituting the ash total amount ratio of the fly ash, the standard state smoke amount, the coal amount and the particulate matter concentration in the boiler outlet flue gas into a second preset formula to calculate the received base ash content corresponding to the to-be-analyzed coal entering the boiler; Substituting the standard flue gas amount, the coal amount, the volume moisture content of the boiler outlet flue gas, the excess air coefficient, the SO 2 concentration in the boiler outlet flue gas, the CO concentration in the boiler outlet flue gas, the NO concentration in the boiler outlet flue gas, the oxygen content in the boiler outlet flue gas, the received base sulfur content and the received base ash content into a preset positive equation set to calculate the received base carbon content, the received base hydrogen content, the received base oxygen content, the received base nitrogen content and the received base moisture content corresponding to the target fired coal; And determining the received base sulfur content, the received base ash content, the received base carbon content, the received base hydrogen content, the received base oxygen content, the received base nitrogen content and the received base water content corresponding to the to-be-analyzed coal-fired coal as the coal quality analysis result.
3. The method of claim 1, wherein the plurality of operation monitoring parameters include a standard flue gas amount, a coal amount, a boiler outlet flue gas volume moisture content, an excess air factor, a SO 2 concentration in a boiler outlet flue gas, a CO concentration in a boiler outlet flue gas, a NO concentration in a boiler outlet flue gas, an oxygen content in a boiler outlet flue gas, and a particulate matter concentration in a boiler outlet flue gas corresponding to the incoming coal to be analyzed, and wherein determining the coal analysis result corresponding to the incoming coal to be analyzed based on the coal analysis model and the plurality of operation monitoring parameters comprises: removing abnormal data in the operation monitoring parameters; inputting the operation monitoring parameters subjected to the elimination treatment into a coal quality analysis model to determine the coal quality analysis result; The coal quality analysis model is used for determining the received base sulfur content, the received base ash content, the received base carbon content, the received base hydrogen content, the received base oxygen content, the received base nitrogen content and the received base water content corresponding to the to-be-analyzed fired coal according to a plurality of operation monitoring parameters after the elimination treatment, and determining the received base sulfur content, the received base ash content, the received base carbon content, the received base hydrogen content, the received base oxygen content, the received base nitrogen content and the received base water content as the coal quality analysis result.
4. A method according to claim 3, characterized in that the method further comprises: Acquiring a first training sample set, wherein the first training sample set comprises a plurality of first training samples, and the first training samples comprise sample operation monitoring parameter sets corresponding to sample coal, sample received basal sulfur content, sample received basal ash content, sample received basal carbon content, sample received basal hydrogen content, sample received basal oxygen content, sample received basal nitrogen content, sample received basal water content and sample coal analysis results; Performing iterative training on the first deep learning model based on the first training sample set, wherein, In each training round, judging whether the loss function of the first deep learning model is converged or not; if the loss function converges, determining the first deep learning model obtained after the round of training as the coal quality analysis model; and if the loss function is not converged, carrying out optimization adjustment on the model parameters of the first deep learning model according to the loss function, and entering the next training round based on the optimized and adjusted first deep learning model.
5. The method according to any one of claims 1 to 4, wherein the generating the target fine combustion operation adjustment scheme corresponding to the coal to be analyzed into the furnace according to the coal quality analysis result comprises: inputting the coal quality analysis result into a scheme generation model to generate the target refined combustion operation adjustment scheme; the scheme generation model is used for generating the target refined combustion operation adjustment scheme according to the coal quality analysis result.
6. The method of claim 5, wherein the method further comprises: Acquiring a second training sample set, wherein the second training sample set comprises a plurality of second training samples, and the second training samples comprise sample coal quality analysis results corresponding to sample coal and a sample refined combustion operation adjustment scheme; Performing iterative training on a second deep learning model based on the second training sample set, wherein, In each training round, judging whether the loss function of the second deep learning model is converged or not; If the loss function converges, determining the second deep learning model obtained after the round of training as the scheme generation model; And if the loss function is not converged, carrying out optimization adjustment on the model parameters of the second deep learning model according to the loss function, and entering the next training round based on the optimized and adjusted second deep learning model.
7. An apparatus for analyzing the quality of coal in a coal-fired boiler, said apparatus comprising: The system comprises an acquisition unit, a control unit and a control unit, wherein the acquisition unit is used for acquiring a current operation monitoring parameter set corresponding to a fire coal to be analyzed, and the current operation monitoring parameter set comprises a plurality of operation monitoring parameters; The judging unit is used for judging whether the operation monitoring parameters meet preset conditions or not, wherein the preset conditions are that abnormal data do not exist in the operation monitoring parameters; the first determining unit is used for determining a coal quality analysis result corresponding to the fire coal to be analyzed based on a plurality of preset formulas and a plurality of operation monitoring parameters when the operation monitoring parameters are judged to be in accordance with the preset conditions; The second determining unit is used for determining a coal quality analysis result corresponding to the to-be-analyzed fire coal based on a coal quality analysis model and the operation monitoring parameters when the operation monitoring parameters are judged not to meet the preset conditions; And the generating unit is used for generating a target refined combustion operation adjustment scheme corresponding to the coal to be analyzed and fed into the furnace according to the coal quality analysis result.
8. A computer device comprising a memory, a processor and a computer program stored on the memory, characterized in that the processor executes the computer program to carry out the steps of the method according to any one of claims 1 to 6.
9. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method according to any one of claims 1 to 6.
10. A computer program product comprising a computer program, characterized in that the computer program, when executed by a processor, implements the steps of the method according to any one of claims 1 to 6.

Description

Method and device for analyzing coal quality of coal-fired boiler Technical Field The application relates to the technical field of coal quality analysis, in particular to a method and a device for analyzing coal quality of a coal-fired boiler. Background In the running process of the coal-fired boiler in the coal-fired power plant, the coal quality of the fired coal is accurately and real-timely mastered, and favorable data support can be provided for fine combustion adjustment of the coal-fired boiler, so that the power generation efficiency of the coal-fired boiler can be effectively improved, the pollutant emission is reduced, and the equipment safety is ensured. At present, a mode of manual sampling and off-line assay is generally adopted to analyze the coal quality of the fired coal boiler, namely, a worker periodically collects the coal sample manually on a coal conveying belt or in a coal powder pipeline, and sends the collected coal sample to a laboratory for industrial analysis and element analysis, so that a coal quality analysis result of the fired coal is obtained. However, the coal quality analysis mode of manual sampling and off-line test has obvious hysteresis, the current coal quality of actual combustion coal of the coal-fired boiler cannot be reflected, so that the operation adjustment of the coal-fired boiler is seriously delayed, and the representative deficiency of manual sampling and the difference of operation standardization are extremely easy to introduce errors, so that the coal quality analysis result is difficult to truly represent the whole condition of the coal fed into the boiler. Disclosure of Invention The embodiment of the application provides a method and a device for analyzing coal quality of a coal-fired boiler, which mainly aim to improve the efficiency and accuracy of analyzing the coal quality of the coal fed into the boiler in the running process of the coal-fired boiler, thereby improving the efficiency of adjusting the running of the coal-fired boiler. In order to solve the technical problems, the embodiment of the application provides the following technical scheme: In a first aspect, the present application provides a method of analyzing coal quality of a coal-fired boiler, the method comprising: acquiring a current operation monitoring parameter set corresponding to the fire coal to be analyzed, wherein the current operation monitoring parameter set comprises a plurality of operation monitoring parameters; judging whether the operation monitoring parameters meet preset conditions or not, wherein the preset conditions are that abnormal data do not exist in the operation monitoring parameters; If the coal quality analysis results are not met, determining the coal quality analysis results corresponding to the coal to be analyzed and the coal to be fired on the basis of a coal quality analysis model and a plurality of operation monitoring parameters; And generating a target refined combustion operation adjustment scheme corresponding to the to-be-analyzed fire coal. In a second aspect, the present application also provides an apparatus for analyzing coal quality of a coal-fired boiler, the apparatus comprising: The system comprises an acquisition unit, a control unit and a control unit, wherein the acquisition unit is used for acquiring a current operation monitoring parameter set corresponding to a fire coal to be analyzed, and the current operation monitoring parameter set comprises a plurality of operation monitoring parameters; The judging unit is used for judging whether the operation monitoring parameters meet preset conditions or not, wherein the preset conditions are that abnormal data do not exist in the operation monitoring parameters; the first determining unit is used for determining a coal quality analysis result corresponding to the fire coal to be analyzed based on a plurality of preset formulas and a plurality of operation monitoring parameters when the operation monitoring parameters are judged to be in accordance with the preset conditions; The second determining unit is used for determining a coal quality analysis result corresponding to the to-be-analyzed fire coal based on a coal quality analysis model and the operation monitoring parameters when the operation monitoring parameters are judged not to meet the preset conditions; And the generating unit is used for generating a target refined combustion operation adjustment scheme corresponding to the coal to be analyzed and fed into the furnace according to the coal quality analysis result. In a third aspect, embodiments of the present application provide a computer device comprising a memory, a processor and a computer program stored on the memory, the processor executing the computer program to carry out the steps of the method of the first aspect. In a fourth aspect, embodiments of the present application provide a computer-readable storage medium having stored thereon a computer program which