A method, system, medium and device for quickly predicting the flue gas volume of a coal-fired power station

Abstract

The present invention discloses a method, system, medium and device for rapidly predicting the flue gas volume of a coal-fired power station in the technical field of carbon emission data monitoring, aiming to solve the problem that the existing technology cannot meet the actual requirements. Obtain the proximate analysis and ultimate analysis data of the coal fed into the furnace, as well as the operating condition data of the coal-fired power generation unit; according to the operating condition data of the coal-fired power generation unit, based on the trained and optimized unburned carbon content prediction model, obtain the predicted value of the unburned carbon content; according to the proximate analysis and ultimate analysis data of the coal fed into the furnace, the predicted value of the unburned carbon content and the oxygen content data in the flue gas in the operating condition data of the coal-fired power generation unit, based on the material balance in the coal combustion process of the boiler, calculate the predicted value of the flue gas volume of the coal-fired power station. The present invention effectively combines the material balance with the machine learning model to realize the rapid prediction of the flue gas volume of the coal-fired power station, with low cost, high precision, more flexible and reliable, and can help improve the reliability of the carbon emission monitoring data of the coal-fired power station.

Description

Technical Field

[0001] The present invention relates to the technical field of carbon emission data monitoring, and particularly relates to a method, a system, a medium and a device for rapidly predicting the flue gas volume of a coal-fired power plant. Background Art

[0002] In order to improve the reliability of carbon emission data of coal-fired power plants, the accurate calculation of carbon emissions helps coal-fired power plants fully connect to the carbon emission trading market and achieve stable and orderly economic operation and social development. Carbon emission monitoring is an important basis for assisting the carbon accounting system, and flue gas flow monitoring is a key prerequisite for carbon emission accounting. How to accurately monitor and calculate the flow rate in carbon emissions is the focus and difficulty.

[0003] At present, the main methods for directly measuring the flue gas volume of coal-fired power plants are: (1) installing hardware sensors at appropriate positions in the flue to achieve on-line measurement of the flue gas volume; (2) forming a uniform grid by changing the sampling points in different regions of the same cross-section of the flue, sampling and analyzing the flue gas to ensure the representativeness of the sampled gas. However, in method (1), the on-line measurement device is prone to blockage and corrosion, and the sampling position of the flue gas flow is single, resulting in high uncertainty in flow measurement; in method (2), dense measuring points need to be arranged, the sampling and testing work is cumbersome, and the time and labor costs are relatively high. With the development of technology, the increase in unit capacity, and the large random fluctuations in the combustion characteristics of coal-fired power plant boilers and flue gas emission characteristics, it is difficult to measure the flue gas flow accurately, stably and for a long time. The soft measurement method provides a reliable technical approach for the accurate measurement of flue gas flow.

[0004] Soft measurement organically combines the knowledge of the production process, applies computer technology to target variables that are difficult to measure or temporarily cannot be measured (such as flue gas volume, unburned carbon content), selects other easily measurable and reliable associated variables (such as coal quantity, unit power generation load, air volume, air pressure and other unit operation condition parameters), and makes a rapid estimate by constructing a mathematical relationship, so as to use software to replace the function of hardware. The key to combating data fraud is to identify whether the coal detection data and important production data have been tampered with or have large errors. By means of soft measurement technology, the operation condition data of coal-fired power generation units in coal-fired power plants, which are easy to obtain, can be used to construct the mapping relationship with the unburned carbon content, and then combined with the physical model based on material balance, the accurate and rapid measurement of the flue gas volume of coal-fired power plants can be realized. Summary of the Invention

[0005] The purpose of the present invention is to overcome the deficiencies in the prior art, and provide a method, a system, a medium and a device for rapidly predicting the flue gas volume of a coal-fired power plant, which have the advantages of low cost, high precision, flexibility and reliability compared with the traditional flue gas flow detection method, and help to improve the reliability of carbon emission monitoring data of coal-fired power plants.

[0006] To solve the above technical problems, the present invention is implemented by the following technical solutions:

[0007] On the one hand, the present invention provides a method for quickly predicting the flue gas volume of a coal-fired power station, including:

[0008] Obtain the proximate analysis and ultimate analysis data of the coal fed into the furnace, as well as the operating condition data of the coal-fired generating unit;

[0009] Based on the operating condition data of the coal-fired generating unit, obtain the predicted value of the unburned carbon content based on the trained and optimized prediction model of the unburned carbon content ;

[0010] Based on the proximate analysis and ultimate analysis data of the coal fed into the furnace, the predicted value of the unburned carbon content and the oxygen content data in the flue gas in the operating condition data of the coal-fired generating unit, calculate the predicted value of the flue gas volume of the coal-fired power station based on the material balance in the coal combustion process of the boiler.

[0011] Optionally, the proximate analysis and ultimate analysis data of the coal fed into the furnace include: carbon content as received , sulfur content as received , hydrogen content as received , oxygen content as received , nitrogen content as received and moisture content as received .

[0012] Optionally, the operating condition data of the coal-fired generating unit include: unit load, total coal quantity, total air volume, primary air pressure, primary air damper opening, secondary air pressure, secondary air damper opening, SOFA damper opening, SOFA air swing angle, CCOFA damper opening and oxygen content in the flue gas.

[0013] Optionally, the prediction model of the unburned carbon content is constructed based on a machine learning model, and the machine learning model algorithms include artificial neural network, Gaussian process regression, support vector machine, random forest model and gradient boosting tree.

[0014] Optionally, the training and optimization process of the prediction model of the unburned carbon content includes:

[0015] Obtain the operating condition data of the coal-fired generating unit in the coal-fired power station and the actual measured value of the unburned carbon content, and construct a training set;

[0016] Construct a prediction model of the unburned carbon content According to the training set, for the unburned carbon content The prediction model conducts model training and optimizes the unburned carbon content based on a heuristic optimization algorithm The prediction model performs hyperparameter optimization and calculates the root mean square error to evaluate the model and obtain a trained and optimized prediction model for the unburned carbon content ;

[0017] The root mean square error is calculated by the following formula:

[0018]

[0019] where represents the root mean square error between the predicted value and the true value of the unburned carbon content, represents the predicted value of the unburned carbon content, represents the true value of the unburned carbon content, and represents the number of input samples in the training set.

[0020] Optionally, the predicted value of the flue gas volume of the coal-fired power plant is calculated through the following steps:

[0021] Based on the received base carbon content , received base sulfur content , received base hydrogen content , received base oxygen content and the predicted value of the unburned carbon content in the proximate analysis and ultimate analysis data of the coal fed into the furnace, the theoretical air volume is calculated by the following formula:

[0022]

[0023] Based on the received base carbon content , received base sulfur content and the predicted value of the unburned carbon content in the proximate analysis and ultimate analysis data of the coal fed into the furnace, the flue gas volume of triatomic gases is calculated by the following formula:

[0024]

[0025] Based on the theoretical air volume and the received base nitrogen content in the proximate analysis and ultimate analysis data of the coal fed into the furnace, the theoretical nitrogen gas volume is calculated by the following formula:

[0026]

[0027] According to the theoretical air volume and the received-base hydrogen content in the proximate analysis and ultimate analysis data of the coal fed into the furnace and the received-base moisture content , the theoretical steam volume is calculated by the following formula :

[0028]

[0029] According to the theoretical triatomic gas volume , the theoretical nitrogen volume and the theoretical steam volume , the theoretical flue gas volume is calculated by the following formula :

[0030]

[0031] According to the theoretical air volume , the theoretical flue gas volume and the excess air coefficient , the predicted value of the flue gas volume of a coal-fired power plant is calculated by the following formula :

[0032]

[0033] wherein, the excess air coefficient , represents the volume content of oxygen in the outlet flue gas

[0034] In a second aspect, the present invention provides a rapid prediction system for the flue gas volume of a coal-fired power plant, comprising:

[0035] a data acquisition module, configured to: acquire the proximate analysis and ultimate analysis data of the coal fed into the furnace, and the operating condition data of the coal-fired generating unit

[0036] an unburned carbon content prediction module, configured to: obtain the predicted value of the unburned carbon content based on the operating condition data of the coal-fired generating unit and the trained and optimized unburned carbon content prediction model ;

[0037] a flue gas volume prediction module for a coal-fired power plant, configured to: calculate the predicted value of the flue gas volume of the coal-fired power plant based on the proximate analysis and ultimate analysis data of the coal fed into the furnace, the predicted value of the unburned carbon content and the oxygen content data in the flue gas in the operating condition data of the coal-fired generating unit, based on the material balance in the coal combustion process of the boiler

[0038] In a third aspect, the present invention provides a computer-readable storage medium, on which a computer program / instructions are stored. When the computer program / instructions are executed by a processor, the steps of any one of the rapid flue gas volume prediction methods for coal-fired power plants in the first aspect are implemented.

[0039] In a fourth aspect, the present invention provides a computer device / equipment / system, comprising:

[0040] a memory for storing computer programs / instructions;

[0041] a processor for executing the computer programs / instructions to implement the steps of any one of the rapid flue gas volume prediction methods for coal-fired power plants in the first aspect.

[0042] In a fifth aspect, the present invention provides a computer program product, comprising computer programs / instructions, characterized in that when the computer programs / instructions are executed by a processor, the steps of any one of the rapid flue gas volume prediction methods for coal-fired power plants in the first aspect are implemented.

[0043] Compared with the prior art, the beneficial effects achieved by the present invention:

[0044] 1. The rapid flue gas volume prediction method for coal-fired power plants provided by the present invention effectively combines the material balance in the boiler combustion process with a machine learning model, realizing the rapid prediction of the flue gas volume in coal-fired power plants. Compared with traditional flue gas flow detection methods, it has the advantages of low cost, high accuracy, flexibility and reliability, helping to improve the reliability of carbon emission monitoring data in coal-fired power plants;

[0045] 2. The rapid flue gas volume prediction system for coal-fired power plants provided by the present invention jointly realizes the rapid prediction of the flue gas volume in coal-fired power plants by setting up a data acquisition module, an unburned carbon content prediction module and an unburned carbon content prediction module, and has practical significance and good application prospects;

[0046] 3. The computer-readable storage medium, computer device / equipment / system and computer program product provided by the present invention can execute the steps of the rapid flue gas volume prediction method for coal-fired power plants provided by the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 is a working flow chart of the rapid flue gas volume prediction method for coal-fired power plants according to an embodiment of the present invention;

[0048] Figure 2 is a schematic structural diagram of the rapid flue gas volume prediction system for coal-fired power plants according to an embodiment of the present invention;

[0049] Figure 3 is a comparison diagram of the predicted value and the true value of the unburned carbon content based on the random forest model according to an embodiment of the present invention;

[0050] Figure 4 A comparison chart of the predicted value and the true value of the unburned carbon content based on the Gaussian process regression model provided by an embodiment of the present invention;

[0051] Figure 5 A comparison chart of the predicted value and the true value of the unburned carbon content based on the support vector machine model provided by an embodiment of the present invention;

[0052] Figure 6 A comparison chart of the predicted value and the true value of the unburned carbon content based on the artificial neural network model provided by an embodiment of the present invention;

[0053] Figure 7 A comparison chart of the rapid prediction effect of the flow rate based on the material balance of the boiler coal combustion process under the 660MW load of a certain unit provided by an embodiment of the present invention;

[0054] Figure 8 A comparison chart of the rapid prediction effect of the flow rate based on the material balance of the boiler coal combustion process under the 550MW load of a certain unit provided by an embodiment of the present invention. Detailed implementation manners

[0055] The technical solution of the present invention will be described in detail below through the accompanying drawings and specific embodiments. It should be understood that the specific features in the embodiments of the present application and the embodiments are detailed descriptions of the technical solution of the present application, rather than limitations on the technical solution of the present application. Without conflict, the technical features in the embodiments of the present application and the embodiments can be combined with each other.

[0056] It should be noted that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this article generally represents an "or" relationship between the front and rear associated objects.

[0057] Embodiment 1:

[0058] An embodiment of the present invention discloses a method for rapidly predicting the flue gas volume of a coal-fired power plant. Refer to Figure 1 as shown, and specifically includes the following steps:

[0059] S1. Obtain the proximate analysis and ultimate analysis data of the coal entering the furnace, as well as the operating condition data of the coal-fired generating unit;

[0060] S2. Based on the operating condition data of the coal-fired generating unit, obtain the predicted value of the unburned carbon content based on the trained and optimized unburned carbon content prediction model ;

[0061] S3. Based on the proximate analysis and ultimate analysis data of the coal as fired, the predicted value of the unburned carbon content and the oxygen content data in the flue gas among the operating condition data of the coal-fired power generation unit, the predicted value of the flue gas volume of the coal-fired power station is calculated based on the material balance in the coal combustion process of the boiler.

[0062] Specifically,

[0063] In step S1, the proximate analysis and ultimate analysis data of the coal as fired include: carbon content on as-received basis , sulfur content on as-received basis , hydrogen content on as-received basis , oxygen content on as-received basis , nitrogen content on as-received basis and moisture content on as-received basis ; the operating condition data of the coal-fired power generation unit include: unit load, total coal quantity, total air volume, primary air pressure, primary air damper opening, secondary air pressure, secondary air damper opening, SOFA damper opening, SOFA air swing angle, CCOFA damper opening and oxygen content in the flue gas; in other embodiments, other relevant variables can also be set in the proximate analysis and ultimate analysis data of the coal as fired, and the operating condition data of the coal-fired power generation unit to increase the characteristic quantities, which helps to improve the accuracy of subsequent prediction work.

[0064] In step S2, the prediction model of the unburned carbon content is constructed based on a machine learning model, and the algorithms of the machine learning model include artificial neural network, Gaussian process regression, support vector machine, random forest model and gradient boosting tree.

[0065] The training and optimization process of the prediction model of the unburned carbon content includes:

[0066] S2.1. Obtain the operating condition data of the coal-fired power generation unit of the coal-fired power station and the actual measured value of the unburned carbon content, and construct a training set;

[0067] S2.2. Construct a prediction model of the unburned carbon content , train the prediction model of the unburned carbon content according to the training set, and perform hyperparameter optimization on the prediction model of the unburned carbon content based on a heuristic optimization algorithm, and perform model evaluation through the root mean square error to obtain a trained and optimized prediction model of the unburned carbon content ;

[0068] The root mean square error is realized through the following formula:

[0069]

[0070] Among them, represents the root mean square error between the predicted value of the unburned carbon content and the true value of the unburned carbon content, represents the predicted value of the unburned carbon content, represents the true value of the unburned carbon content, represents the number of input samples in the training set.

[0071] S2.3. According to the root mean square error , select the machine learning model with the best prediction effect for the unburned carbon content and its hyperparameters, and obtain the trained and optimized unburned carbon content prediction model.

[0072] In step S2.1, in this embodiment, data under the on-site test of the coal-fired boiler of a domestic 660MW main generating unit is obtained, including the proximate analysis and ultimate analysis data of the coal fed into the furnace, the unburned carbon content data and the operating condition data of the coal-fired generating unit, and a training set is constructed.

[0073] In step S2.2, for the same coal-fired power station boiler in step S2.1, the operating condition data of the coal-fired power station generating unit is used as the input of the machine learning model, and the unburned carbon content data of the coal-fired power station boiler is used as the output of the model to construct a machine learning model.

[0074] In this step, the obtained unit condition data is used as the input variables of the model. The input features include unit load, total coal quantity, total air volume, primary air pressure, SOFA damper opening (5), SOFA swing angle (1), CCOFA damper opening (2), furnace secondary damper opening (18), proximate analysis data of the coal fed into the furnace (4), flue gas oxygen content, etc. Taking the unburned carbon content as the model output, 4 different machine learning models are constructed. As shown in Figures 3 to 6 , they are the random forest model ( Figure 3 ), the Gaussian process regression model ( Figure 4 ), the support vector machine model ( Figure 5 ), and the artificial neural network model ( Figure 6 ); The first 80 pieces of the shuffled data are used as the training set to train the model, and the last 20 pieces are used as the test set to test the prediction effect of the model; After the samples are divided, the training set is used to train the model, and the hyperparameters of the model are adjusted and optimized based on the root mean square error RMSE. The test set is used to test the model to verify the generalization of the model. Finally, the machine learning model with the best prediction effect for the unburned carbon content and its hyperparameters are selected to obtain the trained and optimized unburned carbon content Prediction model.

[0075] In this embodiment, the operating condition data of the coal-fired power generation unit are input into four different machine learning models to obtain the predicted value of the unburned carbon content; the experimental results show that the effect of training the random forest model is that the root mean square error of the training set is 0.0499 and the root mean square error of the test set is 0.1468. The comparison graph of the unburned carbon content predicted by this model and the true value is as Figure 3 shown; the effect of training the Gaussian process regression model is that the root mean square error of the training set is 0.0285 and the root mean square error of the test set is 0.1115. The comparison graph of the unburned carbon content predicted by this model and the true value is as Figure 4 shown; the effect of training the support vector machine model is that the root mean square error of the training set is 0.0876 and the root mean square error of the test set is 0.1263. The comparison graph of the unburned carbon content predicted by this model and the true value is as Figure 5 shown; the effect of training the artificial neural network model is that the root mean square error of the training set is 0.1003 and the root mean square error of the test set is 0.1052. The comparison graph of the unburned carbon content predicted by this model and the true value is as Figure 6 shown.

[0076] In step S3, the material balance refers to the corresponding balance relationship between the materials in the furnace and the boiler load. The predicted value of the flue gas volume of the coal-fired power station is calculated through the following steps:

[0077] According to the received-base carbon content , received-base sulfur content , received-base hydrogen content , received-base oxygen content and the predicted value of the unburned carbon content in the proximate analysis and ultimate analysis data of the coal as fired, the theoretical air volume is calculated through the following formula:

[0078]

[0079] According to the received-base carbon content , received-base sulfur content and the predicted value of the unburned carbon content in the proximate analysis and ultimate analysis data of the coal as fired, the flue gas volume of the triatomic gas is calculated through the following formula:

[0080]

[0081] According to the theoretical air volume and the received-base nitrogen content in the proximate analysis and ultimate analysis data of the coal as fired, the theoretical nitrogen quantity is calculated through the following formula :

[0082]

[0083] According to the theoretical air quantity and the received-based hydrogen content in the proximate analysis and ultimate analysis data of the coal fed into the furnace and the received-based moisture , the theoretical water vapor quantity is calculated through the following formula :

[0084]

[0085] According to the theoretical triatomic gas quantity , the theoretical nitrogen quantity and the theoretical water vapor quantity , the theoretical flue gas quantity is calculated through the following formula :

[0086]

[0087] According to the theoretical air quantity , the theoretical flue gas quantity and the excess air coefficient , the predicted value of the flue gas quantity of a coal-fired power station is calculated through the following formula :

[0088]

[0089] Among them, the excess air coefficient , represents the volume content of oxygen in the outlet flue gas.

[0090] In this step, based on the different coal quality analysis data and unburned carbon content data collected under the 660MW load, the flue gas flow rate value under 660MW was quickly estimated through material balance, and compared with the actual measured value of the flow online monitoring device. As Figure 7 shown, obviously, under multiple tests, the estimated value of the boiler flue gas flow rate model under the 660MW load in this embodiment is in good agreement with the actual measured value, verifying the accuracy and reliability of the rapid prediction of the flue gas quantity of the coal-fired power station mentioned in this patent.

[0091] In this step, based on the different coal quality analysis data and unburned carbon content data collected under the 550MW load, the flue gas flow rate value under 550MW was quickly estimated through material balance, and compared with the actual measured value of the flow online monitoring device. As Figure 8As shown, obviously, under multiple tests, the estimated values of the boiler flue gas flow model at a load of 550 MW in this embodiment are in good agreement with the actual measured values, verifying the accuracy and reliability of the rapid prediction of the flue gas volume in coal-fired power plants mentioned in this patent.

[0092] In summary, the rapid prediction method of the flue gas volume in coal-fired power plants proposed in the embodiment of the present invention takes the operating condition data of coal-fired generating units obtained as input variables, accurately predicts the unburned carbon content in coal-fired power plants, combines the industrial analysis and elemental analysis data of coal, and quickly estimates the value of the flue gas volume in coal-fired power plants based on the material balance during the coal combustion process in the boiler; it can be used for the rapid verification process of the flue gas volume value in coal-fired power plants, thereby reducing the adverse effects caused by data quality and data verification problems due to the difficulty of measuring flue gas flow; realizing the rapid prediction of the flue gas volume in coal-fired power plants, which has the advantages of low cost, high precision, flexibility and reliability compared with traditional flue gas flow detection methods, and helps to improve the reliability of carbon emission monitoring data in coal-fired power plants.

[0093] Embodiment 2:

[0094] Based on the same inventive concept as Embodiment 1, the embodiment of the present invention discloses a rapid prediction system for the flue gas volume in coal-fired power plants. Refer to Figure 2 As shown, specifically including:

[0095] A data acquisition module, used for: obtaining the industrial analysis and elemental analysis data of the coal fed into the furnace, as well as the operating condition data of the coal-fired generating unit;

[0096] An unburned carbon content prediction module, used for: based on the operating condition data of the coal-fired generating unit, and based on the trained and optimized unburned carbon content prediction model, obtaining the predicted value of the unburned carbon content ;

[0097] A flue gas volume prediction module for coal-fired power plants, used for: according to the industrial analysis and elemental analysis data of the coal fed into the furnace, the predicted value of the unburned carbon content and the flue gas oxygen content data in the operating condition data of the coal-fired generating unit, calculating the predicted value of the flue gas volume in the coal-fired power plant based on the material balance during the coal combustion process in the boiler.

[0098] For the specific function implementation of the above modules, refer to the relevant content in the method of Embodiment 1 and will not be elaborated.

[0099] Embodiment 3:

[0100] This embodiment provides a computer-readable storage medium, on which computer programs / instructions are stored. When the computer programs / instructions are executed by a processor, the steps of the rapid prediction method of the flue gas volume in coal-fired power plants as described in any one of Embodiment 1 are implemented.

[0101] Embodiment 4:

[0102] This embodiment provides a computer device / system / apparatus, including:

[0103] a memory for storing computer programs / instructions;

[0104] a processor for executing the computer programs / instructions to implement the steps of the rapid prediction method for the flue gas volume of a coal-fired power plant as described in any one of Embodiment 1.

[0105] Embodiment 5:

[0106] This embodiment provides a computer program product, including computer programs / instructions, characterized in that when the computer programs / instructions are executed by a processor, the steps of the rapid prediction method for the flue gas volume of a coal-fired power plant as described in any one of Embodiment 1 are implemented.

[0107] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) containing computer-usable program codes.

[0108] The present invention is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of the flows and / or blocks in the flowchart and / or block diagram can also be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for implementing the functions specified in Figure 1 one or more flows and / or Figure 1 blocks or multiple blocks.

[0109] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device, and the instruction device implements the functions specified in Figure 1 one or more flows and / or Figure 1 blocks or multiple blocks.

[0110] These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus, so that a series of operation steps are performed on the computer or other programmable apparatus to produce a computer-implemented process, thereby providing instructions for implementing the process Figure 1 one process or a plurality of processes and / or blocks Figure 1 steps for the functions specified in one block or a plurality of blocks.

[0111] The embodiments of the present invention have been described above in conjunction with the accompanying drawings. However, the present invention is not limited to the above specific embodiments. The above specific embodiments are merely illustrative and not restrictive. Under the inspiration of the present invention, those of ordinary skill in the art can also make many forms without departing from the spirit of the present invention and the scope protected by the claims. All of these are within the protection scope of the present invention.

Claims

1. A method for quickly predicting flue gas volume in a coal-fired power plant, characterized in that: include: Obtain industrial analysis and elemental analysis data of coal entering the furnace, as well as operating condition data of coal-fired power generation units; According to the operating condition data of the coal-fired power generation unit, based on the trained and optimized unburned carbon content Prediction model to obtain the predicted value of unburned carbon content ; According to the industrial analysis and elemental analysis data of the coal fed into the furnace, the predicted value of the unburned carbon content As well as the flue gas oxygen content data in the operating condition data of the coal-fired power generation unit, based on the material balance of the boiler coal combustion process, the predicted value of the flue gas volume of the coal-fired power plant is calculated; The predicted value of the flue gas volume of the coal-fired power plant is calculated by the following steps: According to the industrial analysis and elemental analysis data of the incoming coal, the received carbon content , received basic sulfur content , received basic hydrogen content , received oxygen content and the predicted value of unburned carbon content , the theoretical air volume is calculated by the following formula : ； According to the industrial analysis and elemental analysis data of the incoming coal, the received carbon content , received basic sulfur content and the predicted value of unburned carbon content The theoretical triatomic gas amount is calculated by the following formula: : ； According to the theoretical air volume and received nitrogen content in industrial analysis and elemental analysis data of incoming coal The theoretical nitrogen volume is calculated by the following formula: : ； According to the theoretical air volume and received basic hydrogen content in industrial analysis and elemental analysis data of incoming coal and received base moisture The theoretical water vapor volume is calculated by the following formula: : ； According to the theoretical triatomic gas , Theoretical nitrogen volume and theoretical water vapor The theoretical flue gas volume is calculated by the following formula: : ； According to the theoretical air volume , Theoretical flue gas volume and excess air coefficient The predicted value of flue gas volume of coal-fired power plants is calculated by the following formula: : ； Among them, the excess air coefficient , Indicates the volume content of oxygen in the outlet flue gas.

2. The method for rapid prediction of flue gas volume in a coal-fired power plant according to claim 1, characterized in that: The industrial analysis and elemental analysis data of the incoming coal include: received basis carbon content , received basic sulfur content , received basic hydrogen content , received oxygen content , received nitrogen content and received base moisture .

3. The method for rapid prediction of flue gas volume in a coal-fired power plant according to claim 1, characterized in that: The operating condition data of the coal-fired power generation unit include: unit load, total coal volume, total air volume, primary air pressure, primary air door opening, secondary air pressure, secondary air door opening, SOFA air door opening, SOFA wind swing angle, CCOFA air door opening and flue gas oxygen content.

4. The method for rapid prediction of flue gas volume in a coal-fired power plant according to claim 1, characterized in that: The unburned carbon content The prediction model is built based on a machine learning model, and the machine learning model algorithms include artificial neural network, Gaussian process regression, support vector machine, random forest model and gradient boosting tree.

5. The method for rapid prediction of flue gas volume in a coal-fired power plant according to claim 4, characterized in that: The unburned carbon content The training and optimization process of the prediction model includes: Obtain the operating condition data of coal-fired power generation units and the actual measured values ​​of unburned carbon content to build a training set; Constructing unburned carbon content The prediction model predicts the unburned carbon content according to the training set. The prediction model is trained and the unburned carbon content is estimated based on a heuristic optimization algorithm. The prediction model is optimized for hyperparameters by using the root mean square error Evaluate the model and get trained and optimized unburned carbon content Predictive models; The root mean square error This is achieved through the following formula: ； in, represents the root mean square error between the predicted value of unburned carbon content and the true value of unburned carbon content, represents the predicted value of the unburned carbon content, Indicates the true value of the unburned carbon content, Represents the number of input samples in the training set.

6. A rapid prediction system for flue gas volume in a coal-fired power plant, characterized in that: include: The data acquisition module is used to obtain industrial analysis and elemental analysis data of the coal entering the furnace, as well as the operating condition data of the coal-fired power generation unit; The unburned carbon content prediction module is used to: predict the unburned carbon content based on the trained and optimized unburned carbon content according to the operating condition data of the coal-fired power generation unit Prediction model to obtain the predicted value of unburned carbon content ; The flue gas volume prediction module of a coal-fired power plant is used to: predict the value of the unburned carbon content based on the industrial analysis and elemental analysis data of the coal entering the furnace As well as the flue gas oxygen content data in the operating condition data of the coal-fired power generation unit, based on the material balance of the boiler coal combustion process, the predicted value of the flue gas volume of the coal-fired power plant is calculated; The predicted value of the flue gas volume of the coal-fired power plant is calculated by the following steps: According to the industrial analysis and elemental analysis data of the incoming coal, the received carbon content , received basic sulfur content , received basic hydrogen content , received oxygen content and the predicted value of unburned carbon content , the theoretical air volume is calculated by the following formula : ； According to the industrial analysis and elemental analysis data of the incoming coal, the received carbon content , received basic sulfur content and the predicted value of unburned carbon content The theoretical triatomic gas amount is calculated by the following formula: : ； According to the theoretical air volume and received nitrogen content in industrial analysis and elemental analysis data of incoming coal The theoretical nitrogen volume is calculated by the following formula: : ； According to the theoretical air volume and received basic hydrogen content in industrial analysis and elemental analysis data of incoming coal and received base moisture The theoretical water vapor volume is calculated by the following formula: : ； According to the theoretical triatomic gas , Theoretical nitrogen volume and theoretical water vapor The theoretical flue gas volume is calculated by the following formula: : ； According to the theoretical air volume , Theoretical flue gas volume and excess air coefficient The predicted value of flue gas volume of coal-fired power plants is calculated by the following formula: : ； Among them, the excess air coefficient , Indicates the volume content of oxygen in the outlet flue gas.

7. A computer-readable storage medium having a computer program / instruction stored thereon, characterized in that: When the computer program / instruction is executed by a processor, the steps of the method for quickly predicting the flue gas volume of a coal-fired power plant described in any one of claims 1-5 are implemented.

8. A computer device, characterized in that: include: Memory, for storing computer programs / instructions; A processor is used to execute the computer program / instructions to implement the steps of the method for quickly predicting the flue gas volume of a coal-fired power plant according to any one of claims 1 to 5.

9. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instruction is executed by a processor, the steps of the method for quickly predicting the flue gas volume of a coal-fired power plant described in any one of claims 1-5 are implemented.

Images