A support vector machine-based real-time correction method for characteristics of a steam turbine circulating water pump

Abstract

The present application relates to the technical field of valve steam turbine, and particularly relates to a steam turbine circulating water pump characteristic real-time correction method based on a support vector machine, wherein the method comprises the following steps: collecting at least one operation data in a steam turbine circulating water pump; constructing a characteristic curve correction model of the steam turbine circulating water pump according to the at least one operation data; establishing a feature library of the steam turbine circulating water pump according to a circulating water pump power feature and a circulating water pump flow feature; classifying first training data and second training data of the steam turbine circulating water pump based on the feature library and a circulating water pump current, a circulating water pump rotating speed and a circulating water pump power by using a support vector machine; and establishing a steam turbine circulating water pump characteristic curve dynamic correction model for correcting the characteristic curve of the steam turbine circulating water pump according to the classified training data. Thus, the problems that related technologies cannot comprehensively understand the state of the steam turbine circulating water pump from different dimensions and different angles, and cannot improve the accuracy of circulating water pump operation adjustment are solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of valve steam turbine, in particular to a steam turbine circulating water pump characteristic real-time correction method based on support vector machine. BACKGROUND

[0002] The steam turbine needs to adjust the circulating water pump power to adjust the circulating water flow to cool the condenser of the steam turbine, reduce the back pressure of the steam turbine and improve the economy of the unit. The characteristic curve provided by the hardware equipment manufacturer often has a large difference with the actual unit, so the real-time correction of the steam turbine circulating water pump characteristic curve has guiding significance for the operation of the steam turbine of the power plant.

[0003] In related technologies, the acquisition method of the steam turbine circulating water pump characteristic curve is usually based on theoretical calculation or experimental test, and the current steam turbine power is calculated according to the correction curve of the steam turbine power with respect to the exhaust pressure, and the net benefit of the unit power with respect to the circulating water quantity is changed.

[0004] However, the related technology cannot comprehensively understand the state of the steam turbine circulating water pump from different dimensions and different angles, and it cannot improve the accuracy of the operation adjustment of the circulating water pump, which needs to be improved. SUMMARY

[0005] The present application provides a steam turbine circulating water pump characteristic real-time correction method based on support vector machine to solve the problem that the related technology cannot comprehensively understand the state of the steam turbine circulating water pump from different dimensions and different angles, and it cannot improve the accuracy of the operation adjustment of the circulating water pump.

[0006] The first aspect of the present application provides a steam turbine circulating water pump characteristic real-time correction method based on support vector machine, applied to the model construction stage, including the following steps: collecting at least one operating data of the steam turbine circulating water pump; constructing a characteristic curve correction model of the steam turbine circulating water pump according to the at least one operating data; based on the characteristic curve correction model, extracting circulating water pump power features and circulating water pump flow features of the steam turbine circulating water pump, and establishing a feature library of the steam turbine circulating water pump according to the circulating water pump power features and the circulating water pump flow features; based on the feature library and the circulating water pump current, the circulating water pump speed and the circulating water pump power, the first training data and the second training data of the steam turbine circulating water pump are classified by using support vector machine to generate classified data, and a steam turbine circulating water pump characteristic curve dynamic correction model for correcting the steam turbine circulating water pump characteristic curve is established according to the classified training data.

[0007] Optionally, in an embodiment of the present application, the at least one operation data of the steam turbine circulating water pump includes at least one of circulating water pump flow, circulating water pump current, circulating water pump inlet and outlet water temperature, condenser back pressure, circulating water pump design curve parameters and condenser design parameters of the steam turbine circulating water pump.

[0008] Optionally, in an embodiment of the present application, the constructing the characteristic curve correction model of the steam turbine circulating water pump according to the at least one data includes: constructing curve equation coefficients of the steam turbine circulating water pump based on characteristic curves of the steam turbine circulating water pump; appending a time stamp to the at least one operation data to generate target operation data of the steam turbine circulating water pump; classifying the target operation data to determine a data group corresponding to the curve equation coefficients, and establishing the characteristic curve correction model of the steam turbine circulating water pump according to the data group.

[0009] Optionally, in an embodiment of the present application, the extracting the circulating water pump power characteristic and the circulating water pump flow characteristic of the steam turbine circulating water pump and establishing a feature library of the steam turbine circulating water pump according to the circulating water pump power characteristic and the circulating water pump flow characteristic includes: extracting parameter data of the steam turbine circulating water pump from a preset equation group coefficient database; performing steam turbine cold-end thermodynamic analysis according to the parameter data to generate at least one operation data characteristic including the circulating water pump power characteristic and the circulating water pump flow characteristic; appending the time stamp to the at least one operation data characteristic to establish the feature library of the steam turbine circulating water pump.

[0010] Optionally, in an embodiment of the present application, before classifying the first training data and the second training data of the steam turbine circulating water pump by using a support vector machine based on the feature library and circulating water pump current, circulating water pump rotating speed and circulating water pump power, it further includes: extracting corresponding data from the feature library respectively, and establishing a first training database and a second training database according to the corresponding data; analyzing the first training database by using linear and nonlinear classifiers to obtain the first training data, and analyzing the second training database by using linear regression and nonlinear regression to obtain the second training data.

[0011] The second aspect embodiment of the present application provides a steam turbine circulating water pump characteristic real-time correction method based on a support vector machine, which is applied to a model application stage and includes the following steps: obtaining at least one operation data feature of a steam turbine circulating water pump and inputting the at least one operation data feature into a pre-established steam turbine circulating water pump characteristic curve dynamic correction model to correct a circulating water pump characteristic curve by using the pre-established steam turbine circulating water pump characteristic curve dynamic correction model, wherein the steam turbine circulating water pump characteristic curve dynamic correction model is obtained from data in a feature database.

[0012] Optionally, in an embodiment of the present application, the step of correcting the circulating water pump characteristic curve by using the pre-established steam turbine circulating water pump characteristic curve dynamic correction model includes the following steps: correcting equation coefficients in a first training database and a second training database to generate corresponding correction values; connecting the steam turbine circulating water pump characteristic curve dynamic correction model to a real-time data interface based on the correction values and dynamically updating the first training database and the second training database by using data input by the real-time data interface to generate updated first and second training databases; and adjusting correction parameters according to the updated first and second training databases to correct the circulating water pump characteristic curve according to the adjusted correction parameters.

[0013] The third aspect embodiment of the present application provides a steam turbine circulating water pump characteristic real-time correction device based on a support vector machine, which is applied to a model construction stage and includes the following modules: a collection module for collecting at least one operation data of a steam turbine circulating water pump; a construction module for constructing a characteristic curve correction model of the steam turbine circulating water pump according to the at least one operation data; an extraction module for extracting a circulating water pump power feature and a circulating water pump flow feature of the steam turbine circulating water pump based on the characteristic curve correction model and establishing a feature database of the steam turbine circulating water pump according to the circulating water pump power feature and the circulating water pump flow feature; and an establishment module for classifying first training data and second training data of the steam turbine circulating water pump by using a support vector machine based on the feature database and circulating water pump current, circulating water pump speed and circulating water pump power to generate classified data and establishing a steam turbine circulating water pump characteristic curve dynamic correction model for correcting a steam turbine circulating water pump characteristic curve according to the classified training data.

[0014] Optionally, in an embodiment of the present application, the collection module includes a collection unit for collecting the at least one operation data of the steam turbine circulating water pump, such as circulating water pump flow, circulating water pump current, circulating water pump inlet and outlet water temperature, condenser back pressure, circulating water pump design curve parameters and condenser design parameters.

[0015] Optionally, in an embodiment of the present application, the constructing module comprises: a constructing unit configured to construct a curve equation coefficient of the steam turbine circulating water pump based on a characteristic curve of the steam turbine circulating water pump; a generating unit configured to time stamp the at least one operation data to generate target operation data of the steam turbine circulating water pump; and a determining unit configured to classify the target operation data to determine a data group corresponding to the curve equation coefficient, and establish a characteristic curve correction model of the steam turbine circulating water pump according to the data group.

[0016] Optionally, in an embodiment of the present application, the extracting module comprises: an extracting unit configured to extract parameter data of the steam turbine circulating water pump from a preset equation group coefficient database; an analyzing unit configured to perform steam turbine cold-end thermodynamic analysis according to the parameter data to generate at least one operation data feature including a circulating water pump power feature and a circulating water pump flow feature; and an appending unit configured to time stamp the at least one operation data feature to establish a feature library of the steam turbine circulating water pump.

[0017] Optionally, in an embodiment of the present application, further comprising: a data extracting module configured to extract corresponding data from the feature library respectively before classifying first training data and second training data of the steam turbine circulating water pump by using a support vector machine based on the feature library and circulating water pump current, circulating water pump rotating speed and circulating water pump power, and establish a first training database and a second training database according to the corresponding data; and a training data generating module configured to analyze the first training database by using a linear and nonlinear classifier to obtain the first training data, and analyze the second training database by using a linear regression and nonlinear regression method to obtain the second training data.

[0018] An embodiment of the fourth aspect of the present application provides a steam turbine circulating water pump characteristic real-time correction device based on a support vector machine, applied to a model application stage, comprising: an obtaining module configured to obtain at least one operation data feature of a steam turbine circulating water pump; and a correction module configured to input the at least one operation data feature into a pre-established steam turbine circulating water pump characteristic curve dynamic correction model to correct a circulating water pump characteristic curve by using the pre-established steam turbine circulating water pump characteristic curve dynamic correction model, wherein the steam turbine circulating water pump characteristic curve dynamic correction model is constructed by data in a feature database.

[0019] Optionally, in an embodiment of the present application, the correction module comprises: a value generation unit configured to correct equation coefficients by using parameters in the first training database and the second training database to generate corresponding correction values; an updating unit configured to connect the dynamic correction model of the steam turbine circulating water pump characteristic curve to a real-time data interface based on the correction values, and dynamically update the first training database and the second training database by using data input by the real-time data interface to generate updated first training database and second training database; and a correction unit configured to adjust correction parameters according to the updated first training database and the second training database, and correct the circulating water pump characteristic curve according to the adjusted correction parameters.

[0020] An electronic device is provided in a fifth aspect of the embodiments of the present application, and comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor executes the program to implement a real-time correction method of a steam turbine circulating water pump characteristic based on a support vector machine.

[0021] The embodiments of the present application obtain data from different circulating water pumps by using a support vector machine, and comprehensively understand the state of the steam turbine circulating water pump from different dimensions and different angles through detection results of multiple features and combined models, thereby improving the accuracy of the steam turbine circulating water pump operation characteristic monitoring and the accuracy of the steam turbine circulating water pump operation adjustment.

[0022] Additional aspects and advantages of the present application will be given in part in the following description, will become apparent in part from the following description, or will be learned by practice of the present application. BRIEF DESCRIPTION OF DRAWINGS

[0023] The above and / or additional aspects and advantages of the present application will become apparent and be readily understood from the following description, taken in conjunction with the accompanying drawings, in which:

[0024] Figure 1 A flowchart of a real-time correction method of a steam turbine circulating water pump characteristic based on a support vector machine provided by an embodiment of the present application applied to a model construction stage;

[0025] Figure 2 A flowchart of a real-time correction method of a steam turbine circulating water pump characteristic based on a support vector machine according to an embodiment of the present application;

[0026] Figure 3 A flowchart of a real-time correction method of a steam turbine circulating water pump characteristic based on a support vector machine provided by an embodiment of the present application applied to a model application stage;

[0027] Figure 4 A structure schematic diagram of a steam turbine circulating water pump characteristic real-time correction device based on a support vector machine provided by an embodiment of the present application is applied to a model construction stage;

[0028] Figure 5 A structure schematic diagram of a steam turbine circulating water pump characteristic real-time correction device based on a support vector machine provided by an embodiment of the present application is applied to a model application stage;

[0029] Figure 6 A structure schematic diagram of an electronic device provided by an embodiment of the present application.

[0030] Among them, 10-a steam turbine circulating water pump characteristic real-time correction device based on a support vector machine; 100-acquisition module, 200-construction module, 300-extraction module, 400-establishment module; 20-a steam turbine circulating water pump characteristic real-time correction device based on a support vector machine, 500-acquisition module, 600-correction module; 601-memory, 602-processor, 603-communication interface. DETAILED DESCRIPTION

[0031] The embodiments of the present application are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar notations represent the same or similar elements or elements with the same or similar functions throughout. The embodiments described below by referring to the accompanying drawings are exemplary and are intended to explain the present application, and cannot be understood as a limitation of the present application.

[0032] A steam turbine circulating water pump characteristic real-time correction method based on a support vector machine is described below according to an embodiment of the present application. In view of the problem that the related art mentioned in the above background technology cannot comprehensively understand the state of the steam turbine circulating water pump from different dimensions and different angles, and cannot improve the accuracy of the circulating water pump operation adjustment, the present application provides a steam turbine circulating water pump characteristic real-time correction method based on a support vector machine. In this method, through the support vector machine, data from different circulating water pumps are obtained, and the state of the steam turbine circulating water pump is comprehensively understood from different dimensions and different angles through the detection results of multiple characteristics and combined models, thereby improving the accuracy of the steam turbine circulating water pump operation characteristic monitoring and the accuracy of the steam turbine circulating water pump operation adjustment. Thus, the problem that the related art cannot comprehensively understand the state of the steam turbine circulating water pump from different dimensions and different angles, and cannot improve the accuracy of the circulating water pump operation adjustment is solved.

[0033] Specifically, Figure 1 A flowchart of a steam turbine circulating water pump characteristic real-time correction method based on a support vector machine provided by an embodiment of the present application is applied to a model construction stage.

[0034] As Figure 1 shown, the steam turbine circulating water pump characteristic real-time correction method based on a support vector machine comprises the following steps:

[0035] In step S101, at least one operating data of the steam turbine circulating water pump is collected.

[0036] It can be understood that the data collected by the circulating water pump in the embodiment of the application includes real-time operating related data and historical operating related data.

[0037] In actual execution, as Figure 2 shown, the embodiment of the application can collect at least one operating data of the steam turbine circulating water pump, thereby providing support for subsequent construction of a characteristic curve correction model of the steam turbine circulating water pump, and further improving the accuracy of steam turbine circulating water pump operation monitoring.

[0038] Optionally, in an embodiment of the application, collecting at least one operating data of the steam turbine circulating water pump comprises: collecting at least one operating data of circulating water pump flow, circulating water pump current, circulating water pump inlet and outlet water temperature, condenser back pressure, circulating water pump design curve parameters and condenser design parameters of the steam turbine circulating water pump.

[0039] It can be understood that the circulating water pump flow in the embodiment of the application can be the amount of water passing through the circulating water pump per unit time; the circulating water pump current can reflect the working state and load condition of the pump; the circulating water pump inlet and outlet water temperature can monitor the inlet and outlet water temperature; the condenser back pressure can be the pressure after steam condensation; the circulating water pump design curve parameters include various performance indicators preset by the circulating water pump during design; and the condenser design parameters relate to the design specifications of the condenser.

[0040] Specifically, the embodiment of the application can collect at least one operating data of circulating water pump flow, circulating water pump current, circulating water pump inlet and outlet water temperature, condenser back pressure, circulating water pump design curve parameters and condenser design parameters of the steam turbine circulating water pump, wherein the circulating water pump flow measurement error is required to be not more than 1%. The condenser design parameters include: condenser circulating water flow design value, condenser area, design cleanliness coefficient, condenser water resistance curve, and condenser heat load-back pressure characteristic curve.

[0041] The embodiment of the application can collect at least one operating data, improve the real-time performance and accuracy of the steam turbine circulating water pump operation state evaluation: improve the real-time performance of the circulating water pump operation state evaluation without increasing the number of measuring point sensors, reduce the result deviation caused by the time difference between the test correction time point and the actual operation process, and improve the accuracy of the circulating water pump evaluation result.

[0042] In step S102, a characteristic curve correction model of the circulating water pump of the steam turbine is constructed according to at least one operation data.

[0043] It can be understood that the embodiment of the present application can construct the characteristic curve correction model of the circulating water pump of the steam turbine according to at least one operation data, and the present application can serve as a guide for the adjustment of the cold end system of the steam turbine. The online characteristic curve correction algorithm can accurately evaluate the current operation state of the circulating water pump of the steam turbine without relying on additional measuring point sensors, and can optimize the influencing factors of the circulating water pump in the economic operation process of the cold end system of the steam turbine.

[0044] Optionally, in an embodiment of the present application, the characteristic curve correction model of the circulating water pump of the steam turbine is constructed according to at least one data, which comprises: constructing the curve equation coefficient of the circulating water pump of the steam turbine based on the characteristic curve of the circulating water pump of the steam turbine; attaching a time stamp to the at least one operation data to generate target operation data of the circulating water pump of the steam turbine; classifying the target operation data to determine a data group corresponding to the curve equation coefficient, and establishing the characteristic curve correction model of the circulating water pump of the steam turbine according to the data group.

[0045] It can be understood that the curve equation coefficient in the embodiment of the present application can be represented by A0, A1 and A2.

[0046] In actual execution process, the embodiment of the present application can fit the curve with various curve equations and construct the parameter equation based on the characteristic curve of the circulating water pump designed, and let A0, A1 and A2 represent the curve equation coefficient. The at least one operation related data obtained in the above step is time stamped to generate the target operation data of the circulating water pump of the steam turbine, the target operation data is divided into 5 categories, and let the labels D1, D2, D3, D4 and D5 represent the data groups corresponding to the 5 coefficient equations, and the characteristic curve correction model of the circulating water pump of the steam turbine is established according to the data group.

[0047] Further, the basis for data classification is the mathematical properties of each curve equation, including but not limited to the coefficient relationship of quadratic equation, linear equation, circle, ellipse, hyperbola, etc. Taking the standard quadratic polynomial as an example, the label D1 can represent the data group of the quadratic term coefficient A0, the linear term A1 and the constant term A2, and taking the standard linear equation as an example, the label D2 represents the data group of the two coefficients of the linear slope A1 and the intercept A2.

[0048] Further, the classification basis of the label includes:

[0049] 1) Classification basis of long-time historical data feature library: the time length of at least one year covers all operating conditions, and the characteristics of this part of the database can represent the average operation level of the unit and will not be affected by individual factors.

[0050] 2) Wide range of operating data feature library classification basis: the latest time as a priority factor, the range of data covers the upper and lower limit range of certain limit value, while ensuring that the wide range of intervals is only taken but not less than a certain limited number as a representative.

[0051] 3) The most frequent operating data feature library: the latest time as a priority factor, according to the normal distribution probability, taking the standard deviation width of the probability distribution above a certain limit value as the classification basis.

[0052] 4) The maximum value of the operating data feature library: considering the actual machine value and the design value, the data range of a certain limit value below the maximum value and the design maximum value.

[0053] 5) The minimum value of the operating data feature library: considering the actual machine value and the design value, the data range of a certain limit value below the minimum value and the design minimum value.

[0054] The embodiment of the present application can effectively construct the characteristic curve correction model of the steam turbine circulating water pump, realize accurate monitoring and optimization of its performance, not only improve the monitoring accuracy, but also improve the economy and reliability of the system without increasing additional sensors.

[0055] In step S103, based on the characteristic curve correction model, the circulating water pump power feature and the circulating water pump flow feature in the steam turbine circulating water pump are extracted, and the characteristic library of the steam turbine circulating water pump is established according to the circulating water pump power feature and the circulating water pump flow feature.

[0056] It can be understood that the feature library in the embodiment of the present application can be established according to different classification basis to adapt to different needs.

[0057] In actual execution process, the embodiment of the present application can extract the circulating water pump power feature and the circulating water pump flow feature in the steam turbine circulating water pump based on the characteristic curve correction model according to the steam turbine cold end thermodynamic principle, and establish the characteristic library of the steam turbine circulating water pump according to the circulating water pump power feature and the circulating water pump flow feature.

[0058] The embodiment of the present application can comprehensively understand the state of the steam turbine circulating water pump from different dimensions and different angles through the detection results of multiple features and combined models, so as to improve the accuracy of circulating water pump operation adjustment.

[0059] Optionally, in an embodiment of the present application, the circulating water pump power characteristic and the circulating water pump flow characteristic in the circulating water pump of the steam turbine are extracted, and a characteristic library of the circulating water pump of the steam turbine is established according to the circulating water pump power characteristic and the circulating water pump flow characteristic, including: extracting parameter data of the circulating water pump of the steam turbine from a preset equation set coefficient database; performing steam turbine cold-end thermodynamic analysis according to the parameter data to generate at least one operation data characteristic including the circulating water pump power characteristic and the circulating water pump flow characteristic; and attaching a time stamp to the at least one operation data characteristic to establish the characteristic library of the circulating water pump of the steam turbine.

[0060] It can be understood that the preset equation set coefficient database in the embodiment of the present application can be 3.

[0061] In actual execution process, the embodiment of the present application can extract data from 3 equation set coefficient databases, and perform steam turbine cold-end thermodynamic analysis on the extracted data to complete characteristic value extraction, including the circulating water pump power characteristic and the circulating water pump flow characteristic. After the above extracted characteristic values are time-stamped, they are stored in the characteristic libraries with labels F1, F2, F3, F4 and F5, wherein F1 corresponds to a long-time historical data characteristic library, F2 corresponds to a wide-range operating data characteristic library, F3 corresponds to an operating data characteristic library of the most frequent condition, F4 corresponds to an operating data characteristic library near the maximum value, and F5 corresponds to an operating data characteristic library near the minimum value.

[0062] In the embodiment of the present application, the physical characteristic values include: circulating water pump flow calculated based on condenser back pressure, and circulating water pump power calculated based on circulating water pump current-voltage-resistance relationship theory; and the time characteristic values are mean value, root mean square, standard deviation, minimum value, maximum value, autocorrelation function, partial autocorrelation function, moving average, moving standard deviation and exponential weighted moving average of each corresponding characteristic in the physical characteristic values.

[0063] The embodiment of the present application can establish the characteristic library of the circulating water pump of the steam turbine, and further comprehensively understand the state of the circulating water pump of the steam turbine from different dimensions and different angles, so as to improve the accuracy of circulating water pump operation regulation.

[0064] In step S104, based on the characteristic library and the circulating water pump current, the circulating water pump speed and the circulating water pump power, the first training data and the second training data of the circulating water pump of the steam turbine are classified by using the support vector machine to generate classified data, and a dynamic correction model of the characteristic curve of the circulating water pump of the steam turbine for correcting the characteristic curve of the circulating water pump of the steam turbine is established according to the classified training data.

[0065] It can be understood that the embodiment of the present application can obtain data from different circulating water pumps at the same time through the support vector machine.

[0066] The embodiment of the present application can generate classified data by using the support vector machine to classify the first training data and the second training data of the steam turbine circulating water pump based on the feature library and the circulating water pump current, circulating water pump rotating speed and circulating water pump power, and establish a steam turbine circulating water pump characteristic curve dynamic correction model for correcting the steam turbine circulating water pump characteristic curve according to the classified training data.

[0067] The embodiment of the present application can improve the accuracy of the steam turbine circulating water pump operation monitoring: through feature extraction and feature library classification, data from sensors of different circulating water pumps are acquired, and the state of the steam turbine circulating water pump operation is comprehensively understood from different dimensions and different angles through a plurality of features and the result of combining the support vector machine model, so that the accuracy of the circulating water pump adjustment is improved.

[0068] Optionally, in an embodiment of the present application, before the first training data and the second training data of the steam turbine circulating water pump are classified by using the support vector machine based on the feature library and the circulating water pump current, circulating water pump rotating speed and circulating water pump power, it further includes: corresponding data are extracted from the feature library respectively, and a first training database and a second training database are established according to the corresponding data; the first training database is analyzed by using a linear and nonlinear classifier to obtain the first training data, and the second training database is analyzed by using a linear regression and nonlinear regression mode to obtain the second training data.

[0069] It can be understood that the first training database in the embodiment of the present application is a T1 training database, and the second training database is a T2 training database.

[0070] In actual execution process, the embodiment of the present application can extract data from the feature libraries F1, F2, F3, F4 and F5 respectively, and establish two training databases, which are T1 and T2 training databases; the T1 data is derived from F1 and F2, and a weight is set for each feature library, for example, the recent data runs more stably, and the coverage is also wider, so a higher weight can be set for F2, if the recent data is poor, a higher weight is set for F1, the T2 data is derived from F3, F4 and F5, and a weight is set for each feature library, and the weight is set according to the time proximity of the data.

[0071] Further, the support vector machine classification analysis is performed on the T1 training database, and the support vector machine classification analysis construction method includes a linear and nonlinear classifier. The support vector machine regression analysis is performed on the T2 training database, and the regression model construction method includes a linear regression and a nonlinear regression.

[0072] Further, the support vector machine classification is used on the above training data, and the classification basis includes but is not limited to: circulating water pump current size, circulating water pump rotating speed size and circulating water pump power size.

[0073] Further, Figure 3 A support vector machine-based real-time correction method for turbine circulating water pump characteristics provided by the embodiment of the application is applied to the process schematic diagram of the model application stage.

[0074] As Figure 3 shown, the support vector machine-based real-time correction method for turbine circulating water pump characteristics includes the following steps:

[0075] Step S301: Obtain at least one operating data feature of the turbine circulating water pump.

[0076] In the embodiment of the application, at least one operating data feature of the turbine circulating water pump can be obtained, thereby providing support for subsequent model construction, and further improving the accuracy of turbine circulating water pump operation monitoring.

[0077] Step S302: Input the at least one operating data feature into a pre-established turbine circulating water pump characteristic curve dynamic correction model to correct the circulating water pump characteristic curve by using the pre-established turbine circulating water pump characteristic curve dynamic correction model, wherein the turbine circulating water pump characteristic curve dynamic correction model is constructed by data in a feature database.

[0078] In the embodiment of the application, the at least one operating data feature can be input into the pre-established turbine circulating water pump characteristic curve dynamic correction model to correct the circulating water pump characteristic curve by using the pre-established turbine circulating water pump characteristic curve dynamic correction model, wherein the turbine circulating water pump characteristic curve dynamic correction model is composed of data in the feature database, and the application can adapt to different types of turbine circulating water pumps: different types of turbine circulating water pumps have different working conditions and measurement point types, but all have their own characteristic curves. By using multiple models, online correction can be performed on different types of circulating water pump characteristic curves, and the application has more extensive applicability.

[0079] Optionally, in an embodiment of the application, the pre-established turbine circulating water pump characteristic curve dynamic correction model is used to correct the circulating water pump characteristic curve, including: using the parameter correction equation coefficients in the first training database and the second training database to generate corresponding correction values; based on the correction values, connecting the turbine circulating water pump characteristic curve dynamic correction model to a real-time data interface, and dynamically updating the first training database and the second training database by using the data input by the real-time data interface to generate updated first training database and second training database; adjusting the correction parameters according to the updated first training database and the second training database, and correcting the circulating water pump characteristic curve according to the adjusted correction parameters.

[0080] Wherein, the embodiment of the present application can utilize the parameters obtained by the T1 training database and the T2 training database to correct the equation coefficients established in the above steps, generate corresponding correction values, take the curve polynomial expression constructed by the coefficients as the expression of the circulating water pump characteristic curve, and take the upper and lower boundaries of the circulating water pump characteristic curve as the definition domain of the polynomial expression. The steam turbine circulating water pump characteristic curve dynamic correction model accesses the real-time data interface, dynamically updates the above training database according to the input data, calculates and adjusts the correction parameters, and realizes the real-time correction method of the steam turbine circulating water pump characteristic curve.

[0081] According to the steam turbine circulating water pump characteristic real-time correction method based on the support vector machine provided by the embodiment of the present application, the data from different circulating water pumps is obtained by the support vector machine, and the state of the steam turbine circulating water pump is comprehensively understood from different dimensions and different angles through the detection results of various features and combined models, so that the accuracy of the steam turbine circulating water pump operation characteristic monitoring and the accuracy of the steam turbine circulating water pump operation regulation are improved. Therefore, the problem that the related art cannot comprehensively understand the state of the steam turbine circulating water pump from different dimensions and different angles, and cannot improve the accuracy of the circulating water pump operation regulation is solved.

[0082] Secondly, the steam turbine circulating water pump characteristic real-time correction device based on the support vector machine according to the embodiment of the present application is described with reference to the accompanying drawings.

[0083] Figure 4 is a structural schematic diagram of the steam turbine circulating water pump characteristic real-time correction device based on the support vector machine according to the embodiment of the present application.

[0084] As Figure 4 shown, the steam turbine circulating water pump characteristic real-time correction device 10 based on the support vector machine includes an acquisition module 100, a construction module 200, an extraction module 300, and an establishment module 400.

[0085] Specifically, the acquisition module 100 is configured to acquire at least one operation data of the steam turbine circulating water pump.

[0086] The construction module 200 is configured to construct a characteristic curve correction model of the steam turbine circulating water pump according to the at least one operation data.

[0087] The extraction module 300 is configured to extract a circulating water pump power feature and a circulating water pump flow feature of the steam turbine circulating water pump based on the characteristic curve correction model, and establish a feature library of the steam turbine circulating water pump according to the circulating water pump power feature and the circulating water pump flow feature.

[0088] The establishing module 400 is configured to classify first training data and second training data of the circulating water pump of the steam turbine based on the feature library and the circulating water pump current, the circulating water pump rotating speed and the circulating water pump power, to generate classified data, and to establish a dynamic correction model for correcting the characteristic curve of the circulating water pump of the steam turbine according to the classified training data.

[0089] Optionally, in an embodiment of the present application, the collecting module 100 comprises a collecting unit.

[0090] The collecting unit is configured to collect at least one operating data of the circulating water pump of the steam turbine, such as the circulating water pump flow, the circulating water pump current, the circulating water pump inlet and outlet water temperature, the condenser back pressure, the circulating water pump design curve parameter and the condenser design parameter.

[0091] Optionally, in an embodiment of the present application, the constructing module 200 comprises a constructing unit, a generating unit and a determining unit.

[0092] The constructing unit is configured to construct the curve equation coefficient of the circulating water pump of the steam turbine based on the characteristic curve of the circulating water pump of the steam turbine.

[0093] The generating unit is configured to timestamp the at least one operating data to generate target operating data of the circulating water pump of the steam turbine.

[0094] The determining unit is configured to classify the target operating data to determine a data group corresponding to the curve equation coefficient, and to establish a characteristic curve correction model of the circulating water pump of the steam turbine according to the data group.

[0095] Optionally, in an embodiment of the present application, the extracting module 300 comprises an extracting unit, an analyzing unit and an attaching unit.

[0096] The extracting unit is configured to extract parameter data of the circulating water pump of the steam turbine from a preset equation group coefficient database.

[0097] The analyzing unit is configured to perform steam turbine cold-end thermodynamic analysis according to the parameter data to generate at least one operating data feature including the circulating water pump power feature and the circulating water pump flow feature.

[0098] The attaching unit is configured to timestamp the at least one operating data feature to establish a feature library of the circulating water pump of the steam turbine.

[0099] Optionally, in an embodiment of the present application, the steam turbine circulating water pump characteristic real-time correction device 10 based on the support vector machine further comprises a data extracting module and a training data generating module.

[0100] The data extraction module is configured to extract corresponding data from the feature database before classifying the first training data and the second training data of the circulating water pump of the steam turbine by using the support vector machine based on the feature database and the circulating water pump current, the circulating water pump rotating speed and the circulating water pump power, and to establish the first training database and the second training database according to the corresponding data.

[0101] The training data generation module is configured to analyze the first training database by using the linear and nonlinear classifiers to obtain the first training data, and to analyze the second training database by using the linear regression and nonlinear regression to obtain the second training data.

[0102] Figure 5 The application provides a steam turbine circulating water pump characteristic real-time correction device 20 based on a support vector machine, which is applied to a model application stage and comprises an acquisition module 500 and a correction module 600.

[0103] Specifically, the acquisition module 500 is configured to acquire at least one running data feature of the steam turbine circulating water pump.

[0104] The correction module 600 is configured to input the at least one running data feature into a pre-established steam turbine circulating water pump characteristic curve dynamic correction model, so as to correct the circulating water pump characteristic curve by using the pre-established steam turbine circulating water pump characteristic curve dynamic correction model, wherein the steam turbine circulating water pump characteristic curve dynamic correction model is constructed by data in a feature database.

[0105] Optionally, in an embodiment of the application, the correction module 600 comprises a numerical value generation unit, an updating unit and a correction unit.

[0106] The numerical value generation unit is configured to correct equation coefficients in the first training database and the second training database to generate corresponding correction numerical values.

[0107] The updating unit is configured to connect the steam turbine circulating water pump characteristic curve dynamic correction model to a real-time data interface based on the correction numerical values, and to dynamically update the first training database and the second training database by using data input by the real-time data interface to generate updated first training database and second training database.

[0108] The correction unit is configured to adjust correction parameters according to the updated first training database and the second training database, and to correct the circulating water pump characteristic curve according to the adjusted correction parameters.

[0109] It should be noted that the foregoing description of the embodiment of the steam turbine circulating water pump characteristic real-time correction method based on the support vector machine is also applicable to the embodiment of the steam turbine circulating water pump characteristic real-time correction device based on the support vector machine, and thus will not be described herein again.

[0110] The application provides a support vector machine-based real-time correction device for the characteristics of a circulating water pump of a steam turbine.

[0111] Figure 6 The electronic device can comprise:

[0112] The memory 601, the processor 602 and the computer program stored in the memory 601 and executable on the processor 602.

[0113] The processor 602 implements the support vector machine-based real-time correction method for the characteristics of a circulating water pump of a steam turbine.

[0114] Further, the electronic device further comprises:

[0115] The communication interface 603 is used for communication between the memory 601 and the processor 602.

[0116] The memory 601 is used for storing the computer program executable on the processor 602.

[0117] The memory 601 can comprise a high-speed RAM memory, and can also comprise a non-volatile memory, for example, at least one disk memory.

[0118] If the memory 601, the processor 602 and the communication interface 603 are independently implemented, the communication interface 603, the memory 601 and the processor 602 can be connected with each other through a bus and complete communication between each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the convenience of representation, Figure 6 Only one thick line is used in the figure, but it does not mean that there is only one bus or only one type of bus.

[0119] Optionally, in a specific implementation, if the memory 601, the processor 602 and the communication interface 603 are integrated on a chip, the memory 601, the processor 602 and the communication interface 603 can complete the communication among each other through an internal interface.

[0120] The processor 602 can be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement one or more embodiments of the present application.

[0121] In the description of the present application, the description of the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In the present specification, the illustrative description of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any appropriate manner in one or N embodiments or examples. In addition, the person skilled in the art can combine and combine the different embodiments or examples described in the present specification and the features of the different embodiments or examples, without contradiction.

[0122] In addition, the terms "first", "second" are only for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined with "first", "second" can explicitly or implicitly include at least one of the features. In the description of the present application, the meaning of "N" is at least two, for example, two, three, etc., unless otherwise explicitly specified.

[0123] Any process or method descriptions in flow charts or described elsewhere herein can be understood as representing one or N executable steps, code segments, or portions of code, including a software program, that can be implemented by one or N processors, and the scope of the preferred embodiments of the present application includes additional implementation involving other processes or methods. Where the steps, function, objects, etc. are not performed in the order described in the figures, or are performed concurrently, the scope of the preferred embodiments of the present application includes other order or concurrent performance or performance of functions according to the functions involved, which should be understood by those skilled in the art.

[0124] The logic and / or steps represented in flow diagrams or otherwise described herein, for example, can be considered as a sequence of executable instructions, and can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For purposes of this specification, a "computer-readable medium" can be any apparatus that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. The computer-readable medium can be a product of the manufacturing and / or processing. The computer-readable medium can include, but is not limited to, the following: an electronic connection (an electronic device with one or N wires), a portable computer diskette (a magnetic device), a RAM (random access memory), a ROM (read-only memory), an EPROM (erasable programmable ROM) or a Flash memory, an optical fiber, and a portable CD ROM. In addition, the computer-readable medium can even be paper or another suitable medium upon which the program can be printed, as the program can be electronically captured, via the optically scanning of the paper or other medium, then compiled, interpreted, or otherwise processed in a suitable manner, if necessary, and stored in the computer memory.

[0125] It should be understood that aspects of the application can be implemented in hardware, software, firmware or combinations thereof. In the above embodiments, the N steps or methods can be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. As such, if implemented in hardware and in another embodiment, any of the following technologies, known in the art, or their combinations can be used: discrete logic circuitry having logic gates for implementing logic functions on data signals, application specific integrated circuits having appropriate combinational logic gates, programmable gate arrays (PGA), field programmable gate arrays (FPGA), and the like.

[0126] Those of ordinary skill in the art can understand that all or part of the steps carried out by the above-mentioned embodiment methods can be completed by programs instructing relevant hardware, and the programs can be stored in a computer-readable storage medium. When the programs are executed, one or a combination of the steps of the method embodiments is included.

[0127] In addition, each function unit in each embodiment of the present application can be integrated in one processing module, or each unit can be physically present separately, or two or more units can be integrated in one module. The integrated module can be realized in the form of hardware or in the form of a software function module. When the integrated module is realized in the form of a software function module and sold or used as an independent product, it can also be stored in a computer readable storage medium.

[0128] The storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it should be understood that the above embodiments are exemplary and should not be construed as limiting the present application, and those skilled in the art can make changes, modifications, replacements and variations to the above embodiments within the scope of the present application.

Claims

1. A method for real-time correction of steam turbine circulating water pump characteristics based on support vector machines, characterized in that, Applied to the model construction stage, comprising the following steps: Collect at least one operating data of the circulating water pump of the steam turbine; According to the at least one operating data, a characteristic curve correction model of the circulating water pump of the steam turbine is constructed; Based on the characteristic curve correction model, the circulating water pump power characteristics and the circulating water pump flow characteristics of the circulating water pump of the steam turbine are extracted, and a feature library of the circulating water pump of the steam turbine is established according to the circulating water pump power characteristics and the circulating water pump flow characteristics; Based on the feature library and the circulating water pump current, the circulating water pump speed and the circulating water pump power, the first training data and the second training data of the circulating water pump of the steam turbine are classified by using support vector machine to generate classified data, and a steam turbine circulating water pump characteristic curve dynamic correction model for correcting the characteristic curve of the circulating water pump of the steam turbine is established according to the classified training data; Wherein, according to the at least one data, the characteristic curve correction model of the circulating water pump of the steam turbine is constructed, including: based on the characteristic curve of the circulating water pump of the steam turbine, the curve equation coefficient of the circulating water pump of the steam turbine is constructed; The target operating data of the circulating water pump of the steam turbine is generated by attaching a time stamp to the at least one operating data; The data group corresponding to the curve equation coefficient is determined by classifying the target operating data, and the characteristic curve correction model of the circulating water pump of the steam turbine is established according to the data group; The circulating water pump power characteristics and the circulating water pump flow characteristics of the circulating water pump of the steam turbine are extracted, and the feature library of the circulating water pump of the steam turbine is established according to the circulating water pump power characteristics and the circulating water pump flow characteristics, including: the parameter data of the circulating water pump of the steam turbine is extracted from the preset equation group coefficient database; The circulating water pump of the steam turbine is analyzed according to the parameter data to generate at least one operating data feature including the circulating water pump power characteristics and the circulating water pump flow characteristics; The feature library of the circulating water pump of the steam turbine is established by attaching the time stamp to the at least one operating data feature; The circulating water pump power characteristics and the circulating water pump flow characteristics of the circulating water pump of the steam turbine are extracted, and the feature library of the circulating water pump of the steam turbine is established according to the circulating water pump power characteristics and the circulating water pump flow characteristics, including: the extracted feature value is marked with the time stamp, and then stored in the feature library with labels F1, F2, F3, F4 and F5, wherein F1 corresponds to long time historical data feature library, F2 corresponds to wide range operating data feature library, F3 corresponds to the most frequent operating data feature library, F4 corresponds to the maximum value near the operating data feature library, and F5 corresponds to the minimum value near the operating data feature library.

2. The method of claim 1, wherein the method is characterized by: The at least one operating data of the circulating water pump of the steam turbine is collected, including: Collect at least one operating data of the circulating water pump of the steam turbine; 3. The method of claim 1, wherein the method is characterized by: Before the first training data and the second training data of the circulating water pump of the steam turbine are classified by using support vector machine based on the feature library and the circulating water pump current, the circulating water pump speed and the circulating water pump power, it further includes: Corresponding data is extracted from the feature library respectively, and a first training database and a second training database are established according to the corresponding data; The first training database is analyzed by using linear and nonlinear classifiers to obtain the first training data, and the second training database is analyzed by using linear regression and nonlinear regression to obtain the second training data.

4. A method for real-time correction of characteristics of a steam turbine circulating water pump based on a support vector machine, characterized in that, Applied to the model application stage, comprising the following steps: At least one operating data feature of the steam turbine circulating water pump is obtained; The at least one operating data feature is input into a pre-established steam turbine circulating water pump characteristic curve dynamic correction model to correct the circulating water pump characteristic curve by using the pre-established steam turbine circulating water pump characteristic curve dynamic correction model, wherein the steam turbine circulating water pump characteristic curve dynamic correction model is trained by the method of claim 1; The pre-established steam turbine circulating water pump characteristic curve dynamic correction model is used to correct the circulating water pump characteristic curve, including: using the parameters in the first training database and the second training database to correct the equation coefficients to generate corresponding correction values; based on the correction values, the steam turbine circulating water pump characteristic curve dynamic correction model is connected to a real-time data interface, and the first training database and the second training database are dynamically updated by using the data input by the real-time data interface to generate updated first training database and second training database; the correction parameters are adjusted according to the updated first training database and second training database, and the circulating water pump characteristic curve is corrected according to the adjusted correction parameters.

5. A support vector machine based real time correction device for turbine circulating water pump characteristics, characterized in that, Applied to the model construction stage, comprising: A collection module is used to collect at least one operating data of the steam turbine circulating water pump; A construction module is used to construct a characteristic curve correction model of the steam turbine circulating water pump according to the at least one operating data; An extraction module is used to extract circulating water pump power features and circulating water pump flow features of the steam turbine circulating water pump based on the characteristic curve correction model, and to establish a feature library of the steam turbine circulating water pump according to the circulating water pump power features and the circulating water pump flow features; An establishment module is used to classify first training data and second training data of the steam turbine circulating water pump by using support vector machines based on the feature library and circulating water pump current, circulating water pump speed and circulating water pump power to generate classified data, and to establish a steam turbine circulating water pump characteristic curve dynamic correction model for correcting the steam turbine circulating water pump characteristic curve according to the classified training data; The construction module includes: a construction unit for constructing equation coefficients of the characteristic curve of the steam turbine circulating water pump based on the characteristic curve of the steam turbine circulating water pump; a generation unit for attaching a time stamp to the at least one operating data to generate target operating data of the steam turbine circulating water pump; a determination unit for classifying the target operating data to determine a data group corresponding to the equation coefficients, and establishing the characteristic curve correction model of the steam turbine circulating water pump according to the data group; The extraction module comprises: an extraction unit configured to extract parameter data of the steam turbine circulating water pump from a preset equation group coefficient database; an analysis unit configured to perform steam turbine cold-end thermodynamic analysis based on the parameter data to generate at least one operation data characteristic comprising a circulating water pump power characteristic and a circulating water pump flow characteristic; and an attachment unit configured to attach the at least one operation data characteristic to the timestamp to establish a characteristic library of the steam turbine circulating water pump. The attachment of the at least one operation data characteristic to the timestamp to establish the characteristic library of the steam turbine circulating water pump comprises: after the extracted characteristic values are timestamped, the extracted characteristic values are stored in the characteristic libraries labeled as F1, F2, F3, F4 and F5, wherein F1 corresponds to a long-time historical data characteristic library, F2 corresponds to a wide-range operating condition data characteristic library, F3 corresponds to a most-frequently-occurring operating condition data characteristic library, F4 corresponds to a maximum-value-adjacent operating data characteristic library, and F5 corresponds to a minimum-value-adjacent operating data characteristic library.

6. A support vector machine based real time correction device for steam turbine circulating water pump characteristics, characterized in that, The application is applied to a model application stage, comprising: An acquisition module configured to acquire at least one operation data characteristic of a steam turbine circulating water pump; A correction module configured to input the at least one operation data characteristic into a pre-established steam turbine circulating water pump characteristic curve dynamic correction model to correct a circulating water pump characteristic curve by using the pre-established steam turbine circulating water pump characteristic curve dynamic correction model, wherein the steam turbine circulating water pump characteristic curve dynamic correction model is trained by the device of claim 5; The correction module comprises: a numerical generation unit configured to generate corresponding correction numerical values by using parameter correction equation coefficients in the first training database and the second training database; an update unit configured to connect the steam turbine circulating water pump characteristic curve dynamic correction model to a real-time data interface based on the correction numerical values, and dynamically update the first training database and the second training database by using data input by the real-time data interface to generate updated first training database and second training database; and a correction unit configured to adjust correction parameters according to the updated first training database and the second training database, and correct the circulating water pump characteristic curve according to the adjusted correction parameters.

7. An electronic device, comprising: The application comprises: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the support vector machine-based real-time correction method of a steam turbine circulating water pump characteristic according to any one of claims 1-3 or the support vector machine-based real-time correction method of a steam turbine circulating water pump characteristic according to claim 4.

Images