Turbine backpressure-based unit coal consumption prediction correction method and system

Abstract

The invention discloses a turbine backpressure-based unit coal consumption prediction correction method and system, and the method comprises the steps: obtaining historical operation data and historical coal consumption data of a unit, analyzing the historical operation data and historical coal consumption data, and determining operation characteristic parameters affecting the coal consumption of the unit; building a coal consumption prediction model of the unit based on the operation characteristic parameters and a preset neural network model, and performing prediction to obtain predicted coal consumption; acquiring historical backpressure data of the steam turbine, analyzing the historical backpressure data and the historical coal consumption data, and determining influence change characteristics of the backpressure of the steam turbine on the coal consumption of the unit; evaluating and calculating the influence degree of the turbine backpressure on the unit coal consumption based on the influence change characteristics to obtain an evaluation value of the influence degree of the turbine backpressure on the unit coal consumption; and determining a coal consumption correction coefficient according to the influence degree evaluation value, and correcting the predicted coal consumption according to the coal consumption correction coefficient to obtain final coal consumption. The coal consumption prediction of the unit is corrected according to the influence of the back pressure of the steam turbine on the coal consumption of the unit, so that the accuracy of coal consumption prediction is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of thermal power generation, and in particular to a method and system for predicting and correcting unit coal consumption based on steam turbine back pressure. Background Art

[0002] With the increasing pressure of energy cost and environmental protection, efficient use and conservation of energy has become an important task for industrial enterprises. In many industrial production processes, steam turbines are common energy conversion equipment, and the coal consumption of the unit is one of the important criteria for measuring its energy efficiency.

[0003] However, traditional unit coal consumption prediction methods are mostly based on the operating parameters of the unit, and the impact of turbine back pressure on unit coal consumption is often ignored. Especially in actual operation, changes in back pressure may have a significant impact on coal consumption. Therefore, traditional unit coal consumption prediction methods cannot provide accurate coal consumption predictions. Summary of the invention

[0004] In order to solve the above technical problems, the present invention provides a method and system for predicting and correcting unit coal consumption based on steam turbine back pressure, comprising:

[0005] Obtain historical operating data and historical coal consumption data of the unit, analyze the historical operating data and historical coal consumption data, and determine the operating characteristic parameters that affect the coal consumption of the unit;

[0006] A coal consumption prediction model for the unit is constructed based on the operating characteristic parameters and the preset neural network model, and prediction is performed according to the coal consumption prediction model to obtain the predicted coal consumption of the unit;

[0007] Obtain historical back pressure data of steam turbines, analyze historical back pressure data and historical coal consumption data, and determine the changing characteristics of the impact of steam turbine back pressure on unit coal consumption;

[0008] Based on the influence change characteristics, the influence degree of steam turbine back pressure on the unit coal consumption is evaluated and calculated, and the evaluation value of the influence degree of steam turbine back pressure on the unit coal consumption is obtained;

[0009] The coal consumption correction factor is determined according to the impact assessment value, and the predicted coal consumption is corrected according to the coal consumption correction factor to obtain the corrected final coal consumption of the unit.

[0010] Furthermore, the acquiring of historical operation data and historical coal consumption data of the unit, and analyzing the historical operation data and historical coal consumption data to determine the operation characteristic parameters affecting the coal consumption of the unit include:

[0011] Acquire historical operation data and historical coal consumption data of the steam turbine, and divide the historical operation data into several groups of operation parameter data according to parameter types;

[0012] Perform cluster analysis on each operating parameter data group and the historical coal consumption data, respectively, to obtain a first cluster structure corresponding to each operating parameter data group and a second cluster structure corresponding to the historical coal consumption data;

[0013] Analyze the structural similarity between the first clustering structure corresponding to each operating parameter data group and the second clustering structure corresponding to the historical coal consumption data, and determine the operating parameter data group whose structural similarity exceeds a preset similarity value as a candidate operating parameter data group;

[0014] The correlation between each set of candidate operating parameter data and the historical coal consumption data is analyzed, and the parameters corresponding to the candidate operating parameter data sets with correlations higher than a preset correlation value are determined as operating characteristic parameters affecting coal consumption.

[0015] Further, the analysis of the structural similarity between the first clustering structure corresponding to each operating parameter data group and the second clustering structure corresponding to the historical coal consumption data includes:

[0016] Obtaining shapes and positions of clusters corresponding to the first clustering structure and the second clustering structure respectively, and calculating shape similarity and position similarity between the clusters corresponding to the first clustering structure and the second clustering structure respectively;

[0017] The shape similarity and position similarity between corresponding clusters are added together to obtain the structural similarity between the first clustering structure and the second clustering structure.

[0018] Furthermore, the coal consumption prediction model of the unit is constructed based on the operation characteristic parameters and the preset neural network model, and prediction is performed according to the coal consumption prediction model to obtain the predicted coal consumption of the unit, including:

[0019] A data set is constructed based on the operating characteristic parameters and the corresponding historical coal consumption data, and the data set is input into a preset neural network model to construct an initial coal consumption prediction model;

[0020] The data set is divided into a training set and a test set according to a certain ratio, and the training set and the test set are input into the initial model of coal consumption prediction;

[0021] The initial coal consumption prediction model is trained and tested until the initial coal consumption prediction model meets the preset convergence conditions, thereby obtaining a coal consumption prediction model;

[0022] The real-time operation data of the steam turbine is obtained, and the real-time operation data is input into the coal consumption prediction model. The coal consumption prediction model performs prediction to obtain the predicted coal consumption of the steam turbine.

[0023] Furthermore, the acquisition of historical back pressure data of the steam turbine, and analysis of the historical back pressure data and the historical coal consumption data to determine the changing characteristics of the impact of the steam turbine back pressure on the coal consumption of the unit include:

[0024] Obtain historical back pressure data of the steam turbine, and plot the historical back pressure data and historical coal consumption data into time series curves to obtain a historical back pressure curve and a historical coal consumption curve;

[0025] Align the historical back pressure curve and the historical coal consumption curve in chronological order, determine several change cycles from the historical back pressure curve, and obtain the maximum and minimum values ​​of the historical back pressure data and the historical coal consumption data in each change cycle;

[0026] The difference between the maximum and minimum values ​​of the historical back pressure data in each change cycle is calculated to obtain a first extreme difference value, and the difference between the maximum and minimum values ​​of the historical coal consumption data in each change cycle is calculated to obtain a second extreme difference value;

[0027] The first extreme difference value and the second extreme difference value of each change cycle are determined as the change characteristics of the impact of turbine back pressure on the coal consumption of the unit.

[0028] Furthermore, the influence degree of the steam turbine back pressure on the unit coal consumption is evaluated and calculated based on the influence change characteristics to obtain the evaluation value of the influence degree of the steam turbine back pressure on the unit coal consumption, including:

[0029] Obtain the first extreme difference value and the second extreme difference value of each change cycle, calculate the ratio of the first extreme difference value to the second extreme difference value of each change cycle, and evaluate the comparison value to obtain the impact change evaluation value of each change cycle;

[0030] Obtain the time length of each change cycle, determine the proportion of the time length of each change cycle in the curve graph, and use the proportion as the weight of each change cycle;

[0031] The impact change assessment value of each change cycle is weightedly added to the corresponding weight to obtain the assessment value of the impact of turbine back pressure on the unit coal consumption.

[0032] Furthermore, the coal consumption correction coefficient is determined according to the coal consumption difference evaluation value, including:

[0033] A correction coefficient-coal consumption difference assessment value interval correspondence relationship is preset, and a corresponding correction coefficient is associated with each coal consumption difference assessment value interval;

[0034] Obtain a coal consumption difference assessment value, and based on the mapping relationship between the coal consumption difference assessment value interval to which the coal consumption difference assessment value belongs and the correction coefficient corresponding to the coal consumption difference assessment value interval, select the correction coefficient corresponding to the coal consumption difference assessment value interval.

[0035] The present invention also provides a unit coal consumption prediction and correction system based on steam turbine back pressure, comprising:

[0036] A determination module is used to obtain historical operation data and historical coal consumption data of the unit, analyze the historical operation data and historical coal consumption data, and determine the operation characteristic parameters that affect the coal consumption of the unit;

[0037] A prediction module is used to construct a coal consumption prediction model of the unit based on the operating characteristic parameters and the preset neural network model, and to perform prediction according to the coal consumption prediction model to obtain the predicted coal consumption of the unit;

[0038] The analysis module is used to obtain the historical back pressure data of the steam turbine, analyze the historical back pressure data and the historical coal consumption data, and determine the changing characteristics of the impact of the steam turbine back pressure on the coal consumption of the unit;

[0039] An evaluation module is used to evaluate and calculate the influence of the steam turbine back pressure on the unit coal consumption based on the influence change characteristics, and obtain an evaluation value of the influence of the steam turbine back pressure on the unit coal consumption;

[0040] The correction module is used to determine the coal consumption correction coefficient according to the impact degree assessment value, and to correct the predicted coal consumption according to the coal consumption correction coefficient to obtain the final coal consumption of the unit after correction.

[0041] Compared with the prior art, the method and system for predicting and correcting unit coal consumption based on steam turbine back pressure in the embodiment of the present invention have the following beneficial effects:

[0042] The present invention predicts the coal consumption of the unit based on the construction model of historical data and neural network model, realizes the preliminary prediction of the coal consumption of the unit, and determines the influence of turbine back pressure on the coal consumption of the unit by analyzing the historical back pressure data and coal consumption data, so as to determine the coal consumption correction coefficient, further correct the predicted coal consumption, and obtain the final coal consumption of the unit after correction, thereby improving the accuracy and reliability of coal consumption prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 1 is a schematic diagram of the flow structure of a method for predicting and correcting unit coal consumption based on steam turbine back pressure in an embodiment of the present invention;

[0044] Figure 2 It is a schematic diagram of the composition of a unit coal consumption prediction and correction system based on turbine back pressure in an embodiment of the present invention. DETAILED DESCRIPTION

[0045] The specific implementation methods of the present application are further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0046] In the description of the present application, it should be understood that the terms "center", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the platform or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0047] The terms "second" and "second" are used for descriptive purposes only and should not be understood as indicating or implying a relative degree of importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined with "second" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, unless otherwise specified, "multiple" means two or more.

[0048] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technical personnel in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0049] like Figure 1 As shown, in an embodiment of the present application, a method for predicting and correcting unit coal consumption based on turbine back pressure is provided, including: S100: obtaining historical operation data and historical coal consumption data of the unit, and analyzing the historical operation data and historical coal consumption data to determine the operation characteristic parameters that affect the unit coal consumption; S200: constructing a coal consumption prediction model for the unit based on the operation characteristic parameters and a preset neural network model, and predicting according to the coal consumption prediction model to obtain the predicted coal consumption of the unit; S300: obtaining historical back pressure data of the turbine, and analyzing the historical back pressure data and historical coal consumption data to determine the influence change characteristics of the turbine back pressure on the unit coal consumption; S400: evaluating and calculating the degree of influence of the turbine back pressure on the unit coal consumption based on the influence change characteristics to obtain an evaluation value of the degree of influence of the turbine back pressure on the unit coal consumption; S500: determining a coal consumption correction coefficient based on the influence degree evaluation value, and correcting the predicted coal consumption according to the coal consumption correction coefficient to obtain the corrected final coal consumption of the unit.

[0050] Furthermore, the present invention predicts the unit's coal consumption based on the constructed model of historical data and the neural network model, realizes the preliminary prediction of the unit's coal consumption, and determines the degree of influence of turbine back pressure on the unit's coal consumption by analyzing historical back pressure data and coal consumption data, thereby determining the coal consumption correction coefficient, further correcting the predicted coal consumption, and obtaining the unit's corrected final coal consumption, thereby improving the accuracy and reliability of coal consumption prediction.

[0051] In an embodiment of the present application, a method for predicting and correcting unit coal consumption based on turbine back pressure is provided, wherein historical operation data and historical coal consumption data of the unit are obtained, and the historical operation data and historical coal consumption data are analyzed to determine the operation characteristic parameters affecting the unit coal consumption, including: obtaining the historical operation data and historical coal consumption data of the steam turbine, and dividing the historical operation data into several groups of operation parameter data groups according to parameter type; clustering each operation parameter data group and historical coal consumption data respectively to obtain a first clustering structure corresponding to each operation parameter data group and a second clustering structure corresponding to the historical coal consumption data respectively; analyzing the structural similarity between the first clustering structure corresponding to each operation parameter data group and the second clustering structure corresponding to the historical coal consumption data, and determining the operation parameter data groups whose structural similarity exceeds a preset similarity value as candidate operation parameter data groups; analyzing the correlation between each group of candidate operation parameter data groups and the historical coal consumption data, and determining the parameters corresponding to the candidate operation parameter data groups whose correlation is higher than the preset correlation value as operation characteristic parameters affecting coal consumption.

[0052] Specifically, historical operating data and historical coal consumption data of the steam turbine are obtained, which include various operating parameters (such as temperature, pressure, speed, etc.) and corresponding coal consumption data, and the historical operating data are divided into multiple groups according to parameter type, for example, temperature-related data are placed in one group, pressure-related data are placed in another group, and so on; cluster analysis is performed on each operating parameter data group and historical coal consumption data respectively to obtain a first clustering structure corresponding to each operating parameter data group and a second clustering structure corresponding to the historical coal consumption data; the structural similarity between the first clustering structure corresponding to each operating parameter data group and the second clustering structure corresponding to the historical coal consumption data is analyzed, and the operating parameter data groups that exceed the preset similarity value are determined as candidate operating parameter data groups; the correlation between each group of candidate operating parameter data groups and the historical coal consumption data is analyzed, and the parameters corresponding to the candidate operating parameter data groups with correlations higher than the preset correlation value are determined as operating characteristic parameters that affect coal consumption. This step can help identify the operating parameters that have a significant impact on coal consumption and determine their structural characteristics through cluster analysis and structural similarity analysis of historical data. Through correlation analysis, it can find candidate operating parameter data groups with a high correlation with coal consumption, thereby determining the operating characteristic parameters that affect coal consumption and providing a basis for subsequent modeling and analysis.

[0053] In an embodiment of the present application, a method for predicting and correcting unit coal consumption based on turbine back pressure is provided, and the structural similarity between the first clustering structure corresponding to each operating parameter data group and the second clustering structure corresponding to the historical coal consumption data is analyzed, including: respectively obtaining the shapes and positions of the clusters corresponding to the first clustering structure and the second clustering structure, and respectively calculating the shape similarity and position similarity between the clusters corresponding to the first clustering structure and the second clustering structure; adding the shape similarity and position similarity between the corresponding clusters to obtain the structural similarity between the first clustering structure and the second clustering structure.

[0054] Specifically, the first clustering structure and the second clustering structure are analyzed to find the shape and position features of each cluster; for each corresponding cluster, their shape similarity and position similarity can be calculated. The shape similarity involves the comparison of cluster features such as outline and area, while the position similarity may involve the comparison of features such as distance and offset of cluster centers; the shape similarity and position similarity between corresponding clusters are added together to obtain the structural similarity between the first clustering structure and the second clustering structure. This similarity value can help evaluate the overall similarity between the two clustering structures. This step can better understand the clustering results of the data and provide a more accurate basis for subsequent data analysis and modeling.

[0055] In an embodiment of the present application, a method for predicting and correcting unit coal consumption based on turbine back pressure is provided, wherein a coal consumption prediction model for the unit is constructed based on operating characteristic parameters and a preset neural network model, and prediction is performed according to the coal consumption prediction model to obtain the predicted coal consumption of the unit, including: constructing a data set based on operating characteristic parameters and corresponding historical coal consumption data, and inputting the data set into a preset neural network model to construct an initial model for coal consumption prediction; dividing the data set into a training set and a test set according to a certain ratio, and inputting the training set and the test set into the initial model for coal consumption prediction; training and testing the initial model for coal consumption prediction until the initial model for coal consumption prediction meets the preset convergence conditions to obtain the coal consumption prediction model; acquiring real-time operating data of the steam turbine, and inputting the real-time operating data into the coal consumption prediction model, and predicting by the coal consumption prediction model to obtain the predicted coal consumption of the steam turbine.

[0056] Specifically, a data set is constructed based on the operating characteristic parameters and the corresponding historical coal consumption data, which includes taking the operating characteristic parameters as input features and the historical coal consumption data as output labels to form the data set required for the training model; the data set is input into a preset neural network model to construct an initial coal consumption prediction model, the data set is divided into a training set and a test set according to a certain ratio, and then the training set and the test set are input into the initial coal consumption prediction model, the initial coal consumption prediction model is trained and tested until the model meets the preset convergence conditions, and a coal consumption prediction model is obtained; the real-time operating data of the steam turbine is obtained, and the real-time operating data is input into the coal consumption prediction model, and the coal consumption prediction model is used to predict and obtain the predicted coal consumption of the steam turbine. This step can realize the accurate prediction of the coal consumption of the steam turbine, which helps to optimize the operation strategy, improve energy efficiency, and reduce costs.

[0057] In an embodiment of the present application, a method for predicting and correcting unit coal consumption based on turbine back pressure is provided, wherein historical back pressure data of the turbine is obtained, and the historical back pressure data and the historical coal consumption data are analyzed to determine the changing characteristics of the influence of the turbine back pressure on the unit coal consumption, including: obtaining the historical back pressure data of the turbine, and respectively plotting the historical back pressure data and the historical coal consumption data into time series curves to obtain a historical back pressure curve and a historical coal consumption curve; aligning the historical back pressure curve and the historical coal consumption curve in chronological order, determining a number of change cycles from the historical back pressure curve, and obtaining the maximum and minimum values ​​of the historical back pressure data and the historical coal consumption data in each change cycle; calculating the difference between the maximum and minimum values ​​of the historical back pressure data in each change cycle to obtain a first extreme difference value, and calculating the difference between the maximum and minimum values ​​of the historical coal consumption data in each change cycle to obtain a second extreme difference value; determining the first extreme difference value and the second extreme difference value of each change cycle as the changing characteristics of the influence of the turbine back pressure on the unit coal consumption.

[0058] Specifically, the historical back pressure data and the historical coal consumption data are plotted into a time series curve to obtain the historical back pressure curve and the historical coal consumption curve, and the historical back pressure curve and the historical coal consumption curve are aligned in chronological order for subsequent analysis; several change cycles are determined from the historical back pressure curve, and the maximum and minimum values ​​of the historical back pressure data and the historical coal consumption data in each change cycle are obtained, which can help find the periodic changes between back pressure and coal consumption; the difference between the maximum and minimum values ​​of the historical back pressure data in each change cycle is calculated to obtain the first extreme difference value, and the difference between the maximum and minimum values ​​of the historical coal consumption data in each change cycle is calculated to obtain the second extreme difference value; the first extreme difference value and the second extreme difference value of each change cycle are determined as the change characteristics of the impact of the turbine back pressure on the unit coal consumption. Through these characteristics, the influence of back pressure on coal consumption can be better understood. This step can analyze the relationship between back pressure and coal consumption and find out the characteristics of the impact of back pressure changes on coal consumption.

[0059] In an embodiment of the present application, a method for predicting and correcting unit coal consumption based on turbine back pressure is provided, wherein the degree of influence of turbine back pressure on unit coal consumption is evaluated and calculated based on the influence change characteristics to obtain an evaluation value of the degree of influence of turbine back pressure on unit coal consumption, including: obtaining the first extreme difference value and the second extreme difference value of each change cycle, calculating the ratio of the first extreme difference value to the second extreme difference value of each change cycle, and evaluating the ratio to obtain an evaluation value of the influence change of each change cycle; obtaining the time length of each change cycle, and determining the proportion of the time length of each change cycle in the curve chart, and using the proportion as the weight of each change cycle; performing weighted addition calculation on the influence change evaluation value of each change cycle and the corresponding weight to obtain an evaluation value of the degree of influence of turbine back pressure on unit coal consumption.

[0060] Specifically, the first extreme difference value and the second extreme difference value of each change cycle are obtained, and then their ratio is calculated, and the comparison value is evaluated to determine the impact change evaluation value; the time length of each change cycle is obtained, and the proportion of the time length of each change cycle in the curve chart is determined, and the proportion value is used as the weight of each change cycle to reflect the contribution of different change cycles to the overall impact; the impact change evaluation value of each change cycle is weighted and added with the corresponding weight. This step can comprehensively consider the impact of different change cycles, and obtain the comprehensive impact evaluation value of the turbine back pressure on the unit coal consumption, which helps to understand the overall impact of back pressure changes on coal consumption and provides an important basis for the adjustment and optimization of operation strategies.

[0061] In an embodiment of the present application, a method for predicting and correcting unit coal consumption based on turbine back pressure is provided, wherein the coal consumption correction coefficient is determined according to the coal consumption difference assessment value, including: pre-setting a correction coefficient-coal consumption difference assessment value interval correspondence relationship, wherein the correction coefficient-coal consumption difference assessment value interval correspondence relationship is associated with a corresponding correction coefficient for each coal consumption difference assessment value interval; obtaining the coal consumption difference assessment value, and selecting the correction coefficient corresponding to the coal consumption difference assessment value interval based on a mapping relationship between the coal consumption difference assessment value interval to which the coal consumption difference assessment value belongs within the correction coefficient-coal consumption difference assessment value interval correspondence relationship.

[0062] Specifically, for each interval of coal consumption difference assessment value, a corresponding correction coefficient is pre-set; the coal consumption difference assessment value is obtained, and based on the coal consumption difference assessment value interval to which the coal consumption difference assessment value belongs, a mapping relationship is selected within the correction coefficient-coal consumption difference assessment value interval correspondence relationship to obtain the correction coefficient corresponding to the coal consumption difference assessment value interval. This mapping relationship can help determine the correction coefficient, which is then used to adjust the model or correct the coal consumption data. Through this step, the corresponding correction coefficient can be selected according to the interval of the coal consumption difference assessment value. These correction coefficients can be used to adjust the output of the model or correct the coal consumption data to more accurately reflect the actual situation. This method can help improve the accuracy of the coal consumption prediction model and provide a more reliable basis for actual operational decisions.

[0063] like Figure 2 As shown, in an embodiment of the present application, a unit coal consumption prediction and correction system based on turbine back pressure is provided, including: a determination module, used to obtain historical operation data and historical coal consumption data of the unit, and analyze the historical operation data and historical coal consumption data to determine the operation characteristic parameters that affect the unit coal consumption; a prediction module, used to construct a coal consumption prediction model of the unit based on the operation characteristic parameters and a preset neural network model, and predict according to the coal consumption prediction model to obtain the predicted coal consumption of the unit; an analysis module, used to obtain the historical back pressure data of the turbine, and analyze the historical back pressure data and historical coal consumption data to determine the influence change characteristics of the turbine back pressure on the unit coal consumption; an evaluation module, used to evaluate and calculate the degree of influence of the turbine back pressure on the unit coal consumption based on the influence change characteristics, and obtain an evaluation value of the degree of influence of the turbine back pressure on the unit coal consumption; a correction module, used to determine the coal consumption correction coefficient according to the influence degree evaluation value, and correct the predicted coal consumption according to the coal consumption correction coefficient to obtain the corrected final coal consumption of the unit.

[0064] In summary, the embodiment of the present invention provides a method and system for predicting and correcting unit coal consumption based on turbine back pressure, which includes: obtaining historical operation data and historical coal consumption data of the unit, analyzing them, and determining the operation characteristic parameters that affect the unit coal consumption; constructing a coal consumption prediction model of the unit based on the operation characteristic parameters and a preset neural network model, and predicting to obtain the predicted coal consumption; obtaining historical back pressure data of the turbine, and analyzing it and the historical coal consumption data to determine the change characteristics of the influence of the turbine back pressure on the unit coal consumption; evaluating and calculating the degree of influence of the turbine back pressure on the unit coal consumption based on the influence change characteristics, and obtaining the evaluation value of the degree of influence of the turbine back pressure on the unit coal consumption; determining the coal consumption correction coefficient according to the evaluation value of the influence degree, and correcting the predicted coal consumption according to it to obtain the final coal consumption. The present invention improves the accuracy of the coal consumption prediction by correcting the unit coal consumption prediction according to the influence of the turbine back pressure on the unit coal consumption.

[0065] Finally, it should be noted that: Obviously, a person skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the present invention and its equivalent technology, the present invention is also intended to include these modifications and variations.

[0066] The above is only an example of implementation of the present invention, but it cannot be used to limit the scope of the present invention. Any structural changes made according to the present invention, as long as they do not lose the essence of the present invention, should be regarded as falling within the scope of protection of the present invention and being restricted. Technical personnel in the relevant technical field can clearly understand that for the convenience and simplicity of description, the specific working process and related instructions of the platform described above can refer to the corresponding process in the aforementioned platform embodiment, and will not be repeated here.

[0067] The term "comprises" or any other similar term is intended to cover a non-exclusive inclusion such that a process, platform, article, or apparatus / platform that includes a list of elements includes not only those elements but also other elements not expressly listed or inherent to such process, platform, article, or apparatus / platform.

[0068] So far, the technical solutions of the present invention have been described in conjunction with the further embodiments shown in the accompanying drawings. However, it is easy for a person skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, a person skilled in the art can make equivalent changes or substitutions to closely related technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0069] The above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention.

Claims

1. A method for predicting and correcting unit coal consumption based on steam turbine back pressure, characterized in that: include: Obtain historical operation data and historical coal consumption data of the unit, analyze the historical operation data and historical coal consumption data, and determine the operating characteristic parameters that affect the coal consumption of the unit; A coal consumption prediction model for the unit is constructed based on the operating characteristic parameters and the preset neural network model, and prediction is performed according to the coal consumption prediction model to obtain the predicted coal consumption of the unit; Obtain historical back pressure data of steam turbines, analyze historical back pressure data and historical coal consumption data, and determine the changing characteristics of the impact of steam turbine back pressure on unit coal consumption; Based on the influence change characteristics, the influence degree of steam turbine back pressure on the unit coal consumption is evaluated and calculated, and the evaluation value of the influence degree of steam turbine back pressure on the unit coal consumption is obtained; The coal consumption correction factor is determined according to the impact assessment value, and the predicted coal consumption is corrected according to the coal consumption correction factor to obtain the corrected final coal consumption of the unit.

2. A method for predicting and correcting unit coal consumption based on turbine back pressure according to claim 1, characterized in that: The obtaining of historical operation data and historical coal consumption data of the unit, and analyzing the historical operation data and historical coal consumption data to determine the operation characteristic parameters affecting the coal consumption of the unit include: Acquire historical operation data and historical coal consumption data of the steam turbine, and divide the historical operation data into several groups of operation parameter data according to parameter types; Perform cluster analysis on each operating parameter data group and the historical coal consumption data, respectively, to obtain a first cluster structure corresponding to each operating parameter data group and a second cluster structure corresponding to the historical coal consumption data; Analyze the structural similarity between the first clustering structure corresponding to each operating parameter data group and the second clustering structure corresponding to the historical coal consumption data, and determine the operating parameter data group whose structural similarity exceeds a preset similarity value as a candidate operating parameter data group; The correlation between each set of candidate operating parameter data and the historical coal consumption data is analyzed, and the parameters corresponding to the candidate operating parameter data sets with correlations higher than a preset correlation value are determined as operating characteristic parameters affecting coal consumption.

3. A method for predicting and correcting unit coal consumption based on turbine back pressure according to claim 2, characterized in that: The analyzing the structural similarity between the first clustering structure corresponding to each operating parameter data group and the second clustering structure corresponding to the historical coal consumption data includes: Respectively obtaining the shapes and positions of the clusters corresponding to the first clustering structure and the second clustering structure, and respectively calculating the shape similarity and position similarity between the clusters corresponding to the first clustering structure and the second clustering structure; The shape similarity and position similarity between corresponding clusters are added together to obtain the structural similarity between the first clustering structure and the second clustering structure.

4. A method for predicting and correcting unit coal consumption based on turbine back pressure according to claim 2, characterized in that: The coal consumption prediction model of the unit is constructed based on the operation characteristic parameters and the preset neural network model, and prediction is performed according to the coal consumption prediction model to obtain the predicted coal consumption of the unit, including: A data set is constructed based on the operating characteristic parameters and the corresponding historical coal consumption data, and the data set is input into a preset neural network model to construct an initial coal consumption prediction model; The data set is divided into a training set and a test set according to a certain ratio, and the training set and the test set are input into the initial model of coal consumption prediction; The initial coal consumption prediction model is trained and tested until the initial coal consumption prediction model meets the preset convergence conditions, thereby obtaining a coal consumption prediction model; The real-time operation data of the steam turbine is obtained, and the real-time operation data is input into the coal consumption prediction model, and the coal consumption prediction model performs prediction to obtain the predicted coal consumption of the steam turbine.

5. A method for predicting and correcting unit coal consumption based on turbine back pressure according to claim 4, characterized in that: The obtaining of historical back pressure data of the steam turbine, and analyzing the historical back pressure data and the historical coal consumption data to determine the changing characteristics of the impact of the steam turbine back pressure on the coal consumption of the unit include: Obtain historical back pressure data of the steam turbine, and plot the historical back pressure data and historical coal consumption data into time series curves to obtain a historical back pressure curve and a historical coal consumption curve; Align the historical back pressure curve and the historical coal consumption curve in chronological order, determine several change cycles from the historical back pressure curve, and obtain the maximum and minimum values ​​of the historical back pressure data and the historical coal consumption data in each change cycle; The difference between the maximum and minimum values ​​of the historical back pressure data in each change cycle is calculated to obtain a first extreme difference value, and the difference between the maximum and minimum values ​​of the historical coal consumption data in each change cycle is calculated to obtain a second extreme difference value; The first extreme difference value and the second extreme difference value of each change cycle are determined as the change characteristics of the impact of turbine back pressure on the coal consumption of the unit.

6. A method for predicting and correcting unit coal consumption based on turbine back pressure according to claim 4, characterized in that: The evaluation and calculation of the influence degree of the steam turbine back pressure on the unit coal consumption based on the influence change characteristics to obtain the evaluation value of the influence degree of the steam turbine back pressure on the unit coal consumption includes: Obtain the first extreme difference value and the second extreme difference value of each change cycle, calculate the ratio of the first extreme difference value to the second extreme difference value of each change cycle, and evaluate the comparison value to obtain the impact change evaluation value of each change cycle; Obtain the time length of each change cycle, determine the proportion of the time length of each change cycle in the curve graph, and use the proportion as the weight of each change cycle; The impact change assessment value of each change cycle is weightedly added to the corresponding weight to obtain the assessment value of the impact of turbine back pressure on the unit coal consumption.

7. A method for predicting and correcting unit coal consumption based on turbine back pressure according to claim 6, characterized in that: Determining the coal consumption correction coefficient according to the coal consumption difference assessment value includes: A correction coefficient-coal consumption difference assessment value interval correspondence relationship is preset, and a corresponding correction coefficient is associated with each coal consumption difference assessment value interval; Obtain a coal consumption difference assessment value, and based on the mapping relationship between the coal consumption difference assessment value interval to which the coal consumption difference assessment value belongs and the correction coefficient corresponding to the coal consumption difference assessment value interval, select the correction coefficient corresponding to the coal consumption difference assessment value interval.

8. A unit coal consumption prediction and correction system based on steam turbine back pressure, characterized in that: include: A determination module is used to obtain historical operation data and historical coal consumption data of the unit, analyze the historical operation data and historical coal consumption data, and determine the operation characteristic parameters that affect the coal consumption of the unit; A prediction module is used to construct a coal consumption prediction model of the unit based on the operating characteristic parameters and the preset neural network model, and to perform prediction according to the coal consumption prediction model to obtain the predicted coal consumption of the unit; The analysis module is used to obtain the historical back pressure data of the steam turbine, analyze the historical back pressure data and the historical coal consumption data, and determine the changing characteristics of the impact of the steam turbine back pressure on the coal consumption of the unit; An evaluation module is used to evaluate and calculate the influence of the steam turbine back pressure on the unit coal consumption based on the influence change characteristics, and obtain an evaluation value of the influence of the steam turbine back pressure on the unit coal consumption; The correction module is used to determine the coal consumption correction coefficient according to the impact degree assessment value, and to correct the predicted coal consumption according to the coal consumption correction coefficient to obtain the final coal consumption of the unit after correction.

Images