Automatic induced draft fan control system and method based on DCS

Abstract

The invention relates to the technical field of induced draft fan automatic control, and discloses an induced draft fan automatic control system and method based on a DCS, and the system comprises an obtaining module which is used for obtaining the historical rotating speed data of an induced draft fan, the historical vibration data of a plurality of key positions, and the historical control data; the first construction module is used for determining a plurality of historical resonance intervals and constructing a resonance interval analysis model; the second construction module is used for determining an association relationship between historical boiler operation data and historical control parameters, determining target control parameters in combination with a first control parameter interval corresponding to each historical resonance interval, and constructing a control analysis model; and the control module is used for collecting real-time related operation data, real-time rotating speed data and real-time vibration data and judging whether a control instruction is generated or not by combining the resonance interval analysis model and the control analysis model, so that the normal operation of the boiler is ensured, the resonance risk is reduced, and the operation efficiency is improved.

Description

Technical Field

[0001] The present application relates to the technical field of induced draft fan automation control, and in particular to a DCS-based induced draft fan automation control system and method. Background Art

[0002] During the operation of a thermal power plant, the induced draft fan (IDF), a crucial auxiliary equipment, has a direct impact on the safe and economical operation of the entire plant. Currently, induced draft fans (IDFs), particularly dynamically regulated axial flow fans, are prone to resonance throughout their entire speed range. When the fan's operating speed coincides with the resonant frequency, severe vibrations occur, impacting the equipment's service life and potentially causing safety incidents. Furthermore, existing IDF fan regulation often relies solely on its own parameters, failing to fully integrate key boiler operating parameters. This results in low operating efficiency and makes it difficult to meet the demands of efficient and stable thermal power plant operation. Summary of the Invention

[0003] To solve the above technical problems, the present application provides a DCS-based induced draft fan automation control system and method. By constructing a resonance interval analysis model and a control analysis model, the resonance interval is accurately judged, and a comprehensive analysis is performed based on important boiler parameters and induced draft fan operating efficiency to generate reasonable control instructions. This ensures the normal operation of the boiler while reducing the resonance risk and improving operating efficiency.

[0004] In some embodiments of the present application, a DCS-based induced draft fan automation control system is provided, including: An acquisition module is used to obtain historical speed data of the induced draft fan, historical vibration data of several key locations, and historical control data; A first construction module is used to determine a number of historical resonance intervals based on historical speed data, historical vibration data, and historical control data, and to construct a resonance interval analysis model; The second construction module is used to determine the correlation between historical boiler operation data and historical control parameters, and determine the target control parameters in combination with the first control parameter interval corresponding to each historical resonance interval, and construct a control analysis model; The control module is used to determine whether to generate a control instruction based on the resonance interval analysis model and the control analysis model.

[0005] In some embodiments of the present application, historical speed data of the induced draft fan, historical vibration data of several key locations, and historical control data are obtained, including: Determine the type of induced draft fan based on the basic information of the current induced draft fan; Acquire multiple historical monitoring logs of the current induced draft fan type during multiple full life cycles, and extract historical initial speed data, historical initial vibration data, and historical initial control data at multiple identical historical monitoring nodes in each historical monitoring log; Preprocessing the historical initial speed data, historical initial vibration data, and historical initial control data at each historical monitoring node, wherein the preprocessing includes removing noise, filling missing values, and standardizing; The historical speed data, historical vibration data and historical control data are obtained respectively according to the pre-processed historical initial speed data, historical initial vibration data and historical initial control data.

[0006] In some embodiments of the present application, based on historical speed data, historical vibration data, and historical control data, several historical resonance intervals are determined, including: Perform feature extraction on the historical speed data and historical vibration data at each identical historical monitoring node to obtain historical speed features and historical vibration features; Capturing historical speed characteristics and historical vibration characteristics at a plurality of consecutive identical historical monitoring nodes based on preset capture conditions, wherein the preset capture conditions include a first preset capture condition, a second preset capture condition, and a third preset capture condition; Determine a number of historical resonance intervals based on the capture results, and each historical resonance interval is mapped with a corresponding preset capture condition and a corresponding capture feature; The historical resonance intervals are classified according to the preset capture conditions and capture characteristics to obtain several historical resonance intervals of the same category, and a historical resonance interval group of each category is constructed; Several historical resonance intervals in each category of the historical resonance interval group are analyzed to determine a first resonance interval, a first data interval set, several second resonance intervals, and a corresponding second data interval set corresponding to the historical resonance interval group.

[0007] In some embodiments of the present application, determining a first resonance interval, a first data interval set, a plurality of second resonance intervals, and a corresponding second data interval set corresponding to a historical resonance interval group includes: Comparing and analyzing multiple historical resonance intervals in the same historical resonance interval group to obtain the difference in the first resonance interval between different historical resonance intervals; Determining a cluster corresponding to a historical resonance interval group according to a plurality of first resonance interval difference amounts, wherein the cluster includes a plurality of historical resonance intervals; generating a first resonance interval according to a number of historical resonance intervals in the cluster; Obtaining a number of historical operating data and corresponding historical data intervals at the historical monitoring nodes corresponding to the historical resonance intervals in the clusters; generating a first data interval corresponding to the historical operation data according to multiple historical data intervals corresponding to the same historical operation data; Each historical resonance interval that does not belong to a cluster in the same historical resonance interval group is set as a second resonance interval; Acquire a number of historical operating data and a corresponding historical data interval at a historical monitoring node corresponding to each resonance interval in the same historical resonance interval group, and set the historical data interval as a second data interval corresponding to the historical operating data; Comparing the first data interval of the same historical operating data with the second data interval of the historical operating data corresponding to each second resonance interval to obtain a data interval difference; Constructing a data interval difference matrix of the corresponding historical operation data from multiple data interval difference amounts of the same historical operation data, wherein the data interval difference matrix includes a plurality of data interval difference amounts sorted by size, and each data interval difference amount is mapped to a corresponding second resonance interval difference amount; Determine whether there is a dependency relationship between a plurality of data interval difference quantities in the data interval difference quantity matrix and a plurality of mapped second resonance interval difference quantities; if so, calculate the dependency coefficient; if not, remove the corresponding historical operation data; Calculate the number of data interval differences in the data interval difference matrix of the same historical running data that are greater than a preset data interval difference threshold; Calculate the correlation coefficient of the corresponding historical operation data based on the number of data interval differences in the data interval difference matrix of the same historical operation data that are greater than the preset data interval difference threshold and the dependence coefficient; Determining historical operating data having a correlation coefficient greater than a preset correlation coefficient threshold as relevant operating data; constructing a first data interval set based on first data intervals of a plurality of related data; A second data interval set is constructed according to a plurality of second data intervals of a plurality of related data, and each second data interval is mapped to a corresponding second resonance interval.

[0008] In some embodiments of the present application, the correlation coefficient of the corresponding historical operation data is calculated based on the number of data interval differences in the data interval difference matrix of the same historical operation data that are greater than a preset data interval difference threshold and the dependence coefficient, including: The calculation formula of the correlation coefficient is: ; Where H is the correlation coefficient, n1 is the number of data interval differences in the data interval difference matrix that are greater than the preset data interval difference threshold, n2 is the total number of data interval differences in the data interval difference matrix, ji is the i-th data interval difference, is the mean value of the data interval difference in the data interval difference matrix, gi is the difference of the i-th second resonance interval, is the mean value of the second resonance interval difference in the data interval difference matrix.

[0009] In some embodiments of the present application, constructing a resonance interval analysis model includes: Using historical speed data, historical vibration data, and a corresponding first data interval set as first training input data, and the corresponding first resonance interval as first training output data; Using the historical speed data, the historical vibration data, and the corresponding second data interval set as second training input data, and the corresponding second resonance interval as second training output data; A neural network training is performed according to the first training input data, the first training output data, the second training input data and the second training output data to obtain a resonance interval analysis model.

[0010] In some embodiments of the present application, determining the correlation between historical boiler operation data and historical control parameters, and determining target control parameters in combination with the first control parameter interval corresponding to each historical resonance interval, and constructing a control analysis model include: Setting a first preset load segment, a second preset load segment, a third preset load segment and a plurality of preset load points in each preset load segment for the induced draft fan load; Extract historical load data, historical control data, and historical boiler operation data from historical monitoring logs; According to the correspondence between the historical load data and the preset load segments, a first analysis data set for the first preset load segment, a second analysis data set for the second preset load segment, and a third analysis data set for the third preset load segment are constructed, wherein each analysis data set includes a plurality of analysis data subsets, and each analysis data subset corresponds to a preset load point; Performing correlation analysis on each historical boiler operation data and historical control data in each analysis data subset to obtain a correlation relationship between each historical boiler operation data and historical control data; The correlation relationship includes whether there is a correlation and the historical second influence coefficient; Setting historical boiler operation data having a correlation relationship and having a historical second influence coefficient greater than a preset influence coefficient threshold as historical boiler key parameters; Determine the target control parameter based on the historical boiler key parameters and the corresponding correlation relationship, and judge whether the target control parameter is within the corresponding first control parameter range; If not, the target air volume is calculated based on the boiler operation requirements and target control parameters; Construct a control parameter-air volume-efficiency curve for each analysis data subset; Map the target control parameters and target air volume to the corresponding control parameter-air volume-efficiency curve to obtain the target efficiency value; Determine whether the target efficiency value is within the preset high efficiency range. If so, use the preset load point, historical boiler key parameters, and corresponding target control parameters as a training parameter group, where the preset load point and historical boiler key parameters are training input parameters, and the corresponding target control parameters are training output parameters; generating a number of training parameter sets for each subset of analyzed data; The neural network is trained according to several training parameter groups of each analysis data subset to obtain a control analysis model.

[0011] In some embodiments of the present application, correlation analysis is performed on each historical boiler operation data and historical control data in each analysis data subset, including: Performing a single factor correlation analysis on each historical boiler operation data and historical control data in each analysis data subset to obtain the historical first influence coefficient of each historical boiler operation data on the historical control data; Filter out historical boiler operation data with a historical influence coefficient greater than a preset influence coefficient threshold for each analysis data subset, and use them as input variables. Use the corresponding historical control data as output variables to generate a variable training set and a variable test set. Establish a multiple linear regression equation; The historical second influence coefficient of each selected historical boiler operation data on the historical control data is calculated based on the multivariate linear regression equation.

[0012] In some embodiments of the present application, determining whether to generate a control instruction based on the resonance interval analysis model and the control analysis model includes: Collect real-time relevant operating data, real-time speed data, real-time vibration data and real-time boiler key parameters; Analyze real-time related operating data, real-time speed data, and real-time vibration data based on the resonance analysis model to determine the real-time resonance range; determining a corresponding real-time first control parameter interval based on the real-time resonance interval; Extract the real-time load points from the real-time relevant operating data, input the real-time load points and real-time boiler key parameters into the control analysis model, and determine the real-time target control parameters; determining whether the real-time target control parameter is within the real-time first control parameter interval, and if not, generating a control instruction according to the real-time target control parameter; If so, the real-time target control parameter is fine-tuned, and the efficiency value corresponding to the fine-tuned real-time target control parameter is in the preset high-efficiency range, and a control instruction is generated according to the fine-tuned real-time target control parameter.

[0013] In some embodiments of the present application, a DCS-based induced draft fan automation control method is also included: Obtain historical speed data of the induced draft fan, historical vibration data of several key locations, and historical control data; Based on historical speed data, historical vibration data, and historical control data, several historical resonance intervals are determined, and a resonance interval analysis model is constructed; Determine the correlation between historical boiler operation data and historical control parameters, and determine the target control parameters in combination with the first control parameter interval corresponding to each historical resonance interval, and construct a control analysis model; Whether to generate a control instruction is determined based on the resonance interval analysis model and the control analysis model.

[0014] The DCS-based induced draft fan automation control system and method of the embodiment of the present application has the following beneficial effects compared with the prior art: By constructing a resonance interval analysis model and a control analysis model, the resonance interval can be accurately determined. A comprehensive analysis is conducted based on important boiler parameters and the operating efficiency of the induced draft fan to generate reasonable control instructions. This ensures the normal operation of the boiler while reducing the resonance risk and improving operating efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 Schematic diagram of a DCS-based induced draft fan automation control system in an embodiment of the present application; Figure 2 It is a flow chart of a DCS-based induced draft fan automation control method in an embodiment of the present application. DETAILED DESCRIPTION

[0016] The following embodiments are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0017] In the description of this application, it should be understood that the terms "center", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating the orientation or position relationship, are based on the orientation or position relationship shown in the accompanying drawings, and are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on this application.

[0018] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature specified as "first" or "second" may explicitly or implicitly include one or more of such features. Throughout this application, unless otherwise specified, "plurality" means two or more.

[0019] In the description of this application, it should be noted that, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood in a broad sense. For example, they can refer to fixed, detachable, or integral connections; mechanical or electrical connections; direct or indirect connections through an intermediate medium; and internal communication between two components. Those skilled in the art will understand the specific meanings of the above terms in this application based on the specific circumstances.

[0020] like Figure 1 As shown, an induced draft fan automation control system based on a DCS in an embodiment of the present application includes: An acquisition module is used to obtain historical speed data of the induced draft fan, historical vibration data of several key locations, and historical control data; A first construction module is used to determine a number of historical resonance intervals based on historical speed data, historical vibration data, and historical control data, and to construct a resonance interval analysis model; The second construction module is used to determine the correlation between historical boiler operation data and historical control parameters, and determine the target control parameters in combination with the first control parameter interval corresponding to each historical resonance interval, and construct a control analysis model; The control module is used to determine whether to generate a control instruction based on the resonance interval analysis model and the control analysis model.

[0021] In this embodiment, the historical vibration data includes vibration amplitudes, vibration spectra, and phases at multiple key locations.

[0022] In this embodiment, the key positions refer to the bearing seat on the fan, the casing near the impeller, the motor bearing, etc. Vibration sensors are installed at the key positions, and vibration signals are collected according to the vibration sensors and converted into vibration data, namely vibration amplitude, vibration spectrum and phase.

[0023] In some embodiments of the present application, historical speed data of the induced draft fan, historical vibration data of several key locations, and historical control data are obtained, including: Determine the type of induced draft fan based on the basic information of the current induced draft fan; Acquire multiple historical monitoring logs of the current induced draft fan type during multiple full life cycles, and extract historical initial speed data, historical initial vibration data, and historical initial control data at multiple identical historical monitoring nodes in each historical monitoring log; Preprocessing the historical initial speed data, historical initial vibration data, and historical initial control data at each historical monitoring node, wherein the preprocessing includes removing noise, filling missing values, and standardizing; The historical speed data, historical vibration data and historical control data are obtained respectively according to the pre-processed historical initial speed data, historical initial vibration data and historical initial control data.

[0024] In this embodiment, the basic information of the induced draft fan includes core structural parameters (such as impeller parameters, shaft system parameters, and casing structure parameters that affect the natural frequency), material properties, component configuration, etc. The category of the current induced draft fan, i.e., the induced draft fan category, is determined through this basic information, and several historical monitoring logs of the corresponding induced draft fan category throughout its life cycle are extracted, laying the foundation for the subsequent determination of the historical resonance range and historical control strategy.

[0025] In some embodiments of the present application, based on historical speed data, historical vibration data, and historical control data, several historical resonance intervals are determined, including: Perform feature extraction on the historical speed data and historical vibration data at each identical historical monitoring node to obtain historical speed features and historical vibration features; Capturing historical speed characteristics and historical vibration characteristics at a plurality of consecutive identical historical monitoring nodes based on preset capture conditions, wherein the preset capture conditions include a first preset capture condition, a second preset capture condition, and a third preset capture condition; Determine a number of historical resonance intervals based on the capture results, and each historical resonance interval is mapped with a corresponding preset capture condition and a corresponding capture feature; The historical resonance intervals are classified according to the preset capture conditions and capture characteristics to obtain several historical resonance intervals of the same category, and a historical resonance interval group of each category is constructed; Several historical resonance intervals in each category of the historical resonance interval group are analyzed to determine a first resonance interval, a first data interval set, several second resonance intervals, and a corresponding second data interval set corresponding to the historical resonance interval group.

[0026] In this embodiment, feature extraction of historical speed data and historical vibration data refers to extracting the change values ​​of historical speed data and historical vibration data, that is, historical speed features refer to historical speed adjustment values, historical speed mutation values, etc., and historical vibration features refer to historical vibration amplitude change values, historical vibration phase mutation values, etc.

[0027] In this embodiment, the first preset capture condition refers to the situation where the vibration amplitude at a certain speed point (or a small range) suddenly exceeds a preset threshold value during the speed change (e.g., it is more than 50% higher than the vibration amplitude at the adjacent speed). The second preset capture condition refers to the situation where, at this speed, the amplitude proportion of the "1x speed frequency" in the vibration spectrum increases significantly (e.g., exceeds 60%), and there are no other obvious fault frequencies (e.g., bearing and gear characteristic frequencies). The third preset capture condition is the situation where the vibration amplitude shows a "sudden increase and decrease" trend as the speed "enters and exits this range" (e.g., when the speed increases from 1300 r / min to 1400 r / min, the vibration jumps from 0.3 mm / s to 1.2 mm / s, and then drops back to 0.4 mm / s when it increases to 1500 r / min).

[0028] In this embodiment, the capture feature corresponds to the corresponding preset capture condition. For example, when the first preset capture condition is used, the capture feature is the vibration amplitude change value during the rotational speed change process.

[0029] In this embodiment, the same historical resonance interval group refers to the historical resonance intervals under the same conditions such as the same vibration amplitude mutation value and the spectrum ratio value. The first resonance interval refers to the standard resonance interval in the historical resonance interval group, that is, the resonance interval that is not affected by the relevant operating data of the load condition, equipment aging, etc. The second resonance interval refers to the resonance interval after the standard resonance interval deviates from the standard resonance interval under the influence of the relevant operating data of the load condition, equipment aging, etc.

[0030] In this embodiment, by determining the speed characteristics and vibration characteristics to determine whether the preset capture conditions are triggered, the historical resonance interval under the corresponding characteristics is determined, and a historical resonance interval group is constructed. The relevant operating data, the first data interval and several second data intervals that affect the historical resonance interval are determined, laying the foundation for constructing an accurate resonance interval analysis model and improving the accuracy of subsequent resonance intervals.

[0031] In some embodiments of the present application, determining a first resonance interval, a first data interval set, a plurality of second resonance intervals, and a corresponding second data interval set corresponding to a historical resonance interval group includes: Comparing and analyzing multiple historical resonance intervals in the same historical resonance interval group to obtain the difference in the first resonance interval between different historical resonance intervals; Determining a cluster corresponding to a historical resonance interval group according to a plurality of first resonance interval difference amounts, wherein the cluster includes a plurality of historical resonance intervals; generating a first resonance interval according to a number of historical resonance intervals in the cluster; Obtaining a number of historical operating data and corresponding historical data intervals at the historical monitoring nodes corresponding to the historical resonance intervals in the clusters; generating a first data interval corresponding to the historical operation data according to multiple historical data intervals corresponding to the same historical operation data; Each historical resonance interval that does not belong to a cluster in the same historical resonance interval group is set as a second resonance interval; Acquire a number of historical operating data and a corresponding historical data interval at a historical monitoring node corresponding to each resonance interval in the same historical resonance interval group, and set the historical data interval as a second data interval corresponding to the historical operating data; Comparing the first data interval of the same historical operating data with the second data interval of the historical operating data corresponding to each second resonance interval to obtain a data interval difference; Constructing a data interval difference matrix of the corresponding historical operation data from multiple data interval difference amounts of the same historical operation data, wherein the data interval difference matrix includes a plurality of data interval difference amounts sorted by size, and each data interval difference amount is mapped to a corresponding second resonance interval difference amount; Determine whether there is a dependency relationship between a plurality of data interval difference quantities in the data interval difference quantity matrix and a plurality of mapped second resonance interval difference quantities; if so, calculate the dependency coefficient; if not, remove the corresponding historical operation data; Calculate the number of data interval differences in the data interval difference matrix of the same historical running data that are greater than a preset data interval difference threshold; Calculate the correlation coefficient of the corresponding historical operation data based on the number of data interval differences in the data interval difference matrix of the same historical operation data that are greater than the preset data interval difference threshold and the dependence coefficient; Determining historical operating data having a correlation coefficient greater than a preset correlation coefficient threshold as relevant operating data; constructing a first data interval set based on first data intervals of a plurality of related data; A second data interval set is constructed according to a plurality of second data intervals of a plurality of related data, and each second data interval is mapped to a corresponding second resonance interval.

[0032] In this embodiment, the resonance interval difference is obtained by quantifying the comprehensive difference between the interval length difference, the interval center position difference, and the overlap difference of different historical resonance intervals.

[0033] In this embodiment, the resonance interval difference value between any two historical resonance intervals in the cluster is lower than the preset resonance interval difference threshold. The preset data difference threshold can be set according to the total resonance interval difference mean in the same historical resonance interval group, for example, 1 / 2 of the total interval difference mean.

[0034] In this embodiment, the first resonance interval is obtained by performing endpoint mean processing on multiple historical resonance intervals in the cluster, and the second resonance interval difference is calculated by calculating the resonance interval difference between the historical resonance interval that does not belong to the cluster in the same historical resonance interval group and the first resonance interval.

[0035] In this embodiment, the historical operation data includes historical load conditions, historical life data, and historical fault data, etc. The historical life data can be used to obtain the degree of equipment aging.

[0036] In this embodiment, the first data interval refers to the interval union of historical data intervals corresponding to several historical operating data at the historical monitoring node corresponding to the historical resonance interval in the cluster.

[0037] In this embodiment, the data interval difference matrix includes two columns, one of which is a plurality of data interval differences, and the other is a plurality of second resonance interval differences between the second resonance interval and the first resonance interval mapped by the data interval difference.

[0038] In this embodiment, determining whether a dependency relationship exists refers to plotting the data interval difference amounts arranged in order in the data interval difference amount matrix and the mapped second resonance interval difference amounts into the same blank dot graph to obtain a scatter plot of the data interval difference amounts and a scatter plot of the second resonance interval difference amounts. If the scatter plot shows a linear trend, there is a dependency relationship; if it does not show a linear trend, there is no dependency relationship, and the historical operating data of the data interval difference amount matrix is ​​eliminated.

[0039] In this embodiment, the preset data interval difference threshold is set based on the statistical characteristics of the data interval difference in the data interval difference matrix. Specifically, it can be set to a certain multiple of the data interval difference mean, such as 1.5 times, to ensure that only data intervals that significantly deviate from the cluster cluster will be regarded as data intervals with large differences.

[0040] In some embodiments of the present application, the correlation coefficient of the corresponding historical operation data is calculated based on the number of data interval differences in the data interval difference matrix of the same historical operation data that are greater than a preset data interval difference threshold and the dependence coefficient, including: The calculation formula of the correlation coefficient is: ; Where H is the correlation coefficient, n1 is the number of data interval differences in the data interval difference matrix that are greater than the preset data interval difference threshold, n2 is the total number of data interval differences in the data interval difference matrix, ji is the i-th data interval difference, is the mean value of the data interval difference in the data interval difference matrix, gi is the difference of the i-th second resonance interval, is the mean value of the second resonance interval difference in the data interval difference matrix.

[0041] In this embodiment,

[0042] is the dependence coefficient, and the value range of the dependence coefficient is (0, 1). When it is closer to 1, the correlation coefficient is larger, and vice versa.

[0043] In this embodiment, relevant operating data that affect the resonance interval are selected by calculating the correlation coefficient. According to the first data interval and several second data intervals of the relevant operating data, the precise first resonance interval and several second resonance intervals are determined, thereby improving the accuracy of the judgment of the resonance interval, thereby avoiding the resonance interval frequency, and providing a key basis for the subsequent construction of the control analysis model.

[0044] In some embodiments of the present application, constructing a resonance interval analysis model includes: Using historical speed data, historical vibration data, and a corresponding first data interval set as first training input data, and the corresponding first resonance interval as first training output data; Using the historical speed data, the historical vibration data, and the corresponding second data interval set as second training input data, and the corresponding second resonance interval as second training output data; A neural network training is performed according to the first training input data, the first training output data, the second training input data and the second training output data to obtain a resonance interval analysis model.

[0045] In some embodiments of the present application, determining the correlation between historical boiler operation data and historical control parameters, and determining target control parameters in combination with the first control parameter interval corresponding to each historical resonance interval, and constructing a control analysis model include: Setting a first preset load segment, a second preset load segment, a third preset load segment and a plurality of preset load points in each preset load segment for the induced draft fan load; Extract historical load data, historical control data, and historical boiler operation data from historical monitoring logs; According to the correspondence between the historical load data and the preset load segments, a first analysis data set for the first preset load segment, a second analysis data set for the second preset load segment, and a third analysis data set for the third preset load segment are constructed, wherein each analysis data set includes a plurality of analysis data subsets, and each analysis data subset corresponds to a preset load point; Performing correlation analysis on each historical boiler operation data and historical control data in each analysis data subset to obtain a correlation relationship between each historical boiler operation data and historical control data; The correlation relationship includes whether there is a correlation and the historical second influence coefficient; Setting historical boiler operation data having a correlation relationship and having a historical second influence coefficient greater than a preset influence coefficient threshold as historical boiler key parameters; Determine the target control parameter based on the historical boiler key parameters and the corresponding correlation relationship, and judge whether the target control parameter is within the corresponding first control parameter range; If not, the target air volume is calculated based on the boiler operation requirements and target control parameters; Construct a control parameter-air volume-efficiency curve for each analysis data subset; Map the target control parameters and target air volume to the corresponding control parameter-air volume-efficiency curve to obtain the target efficiency value; Determine whether the target efficiency value is within the preset high efficiency range. If so, use the preset load point, historical boiler key parameters, and corresponding target control parameters as a training parameter group, where the preset load point and historical boiler key parameters are training input parameters, and the corresponding target control parameters are training output parameters; generating a number of training parameter sets for each subset of analyzed data; The neural network is trained according to several training parameter groups of each analysis data subset to obtain a control analysis model.

[0046] In this embodiment, historical boiler operating data refers to important operating data that characterizes the operating status of the boiler, such as steam pressure, temperature, flow rate, and furnace negative pressure, and historical boiler key parameters refer to data that have a large correlation with the speed or opening.

[0047] In this embodiment, the historical control parameters include rotation speed and opening degree.

[0048] In this embodiment, the first preset load segment refers to a low load of 30%-50%, the second preset load segment refers to a medium load of 50%-80%, and the third preset load segment refers to a high load of 80%-100%. Each load segment is further divided into five preset load points. For example, the preset load points of the first preset load segment are 30, 35, 40, 45, and 50, thereby ensuring that the full operating range of the induced draft fan is covered.

[0049] In this embodiment, the analysis data set is constructed based on the historical control data and historical boiler operation data of the historical load data in the corresponding preset load segment, and the analysis data subset is constructed based on the historical control data and historical boiler operation data at each same preset load point in the preset load segment of the historical load data.

[0050] In this embodiment, a first control parameter interval is determined based on each historical resonance interval. The first control parameter interval refers to the speed interval with the same frequency as the resonance interval, and the first control parameter interval corresponding to the target control parameter is the first control parameter interval of the historical resonance interval determined based on the relevant operating data at the same historical node as the historical boiler key parameters.

[0051] In this embodiment, when the first control parameter range is not maintained, the risk of resonance caused by the repetition of the rotational speed and the resonance frequency during the operation of the induced draft fan can be effectively avoided, thereby ensuring the safe and stable operation of the induced draft fan and related equipment and extending the service life of the equipment.

[0052] In this embodiment, the target control parameters are calculated based on historical load conditions, historical boiler key parameters, and their associated relationships. For example, when the boiler steam pressure decreases by 10 MPa and the steam flow rate increases or decreases by 50 t / h (corresponding to 65% of the rated load), the target induced draft fan speed is 1200 r / min and the opening is +10°, calculated based on the parameter weight coefficients in the associated relationship and the historical second influence coefficient.

[0053] In this embodiment, the boiler operation demand refers to the boiler exhaust demand and stable operation demand. For example, based on the boiler operation demand and the boiler heat balance calculation formula, the required exhaust air volume is calculated as follows: the boiler steam pressure is reduced by 10 MPa, the steam flow rate is increased or decreased by 50 t / h (corresponding to 65% of the rated load), the target speed of the induced draft fan is 1200 r / min, and the opening is +10°. .

[0054] In this embodiment, the preset high efficiency range is 80%-100%.

[0055] In this embodiment, the control parameter-air volume-efficiency curve includes a speed-air volume-efficiency curve and an opening-air volume-efficiency curve. When the load is low, the opening-air volume-efficiency curve is used first, and when the load is medium to high, the speed-air volume-efficiency curve is used first.

[0056] In this embodiment, several historical speeds are screened out at each preset load point in the historical monitoring log. For example, when the historical speed is 1200r / min, the historical air volume and historical efficiency values ​​at the historical adjustment opening from -30° to +25° are screened out. The opening is used as the horizontal coordinate, the air volume is used as the vertical coordinate, and the efficiency value is used as an auxiliary parameter (marked at the corresponding air volume). The opening-air volume-efficiency curves at different historical speeds are obtained, thereby constructing the opening-air volume-efficiency curve diagram. The speed-air volume-efficiency curve diagram is similar to the above-mentioned construction method and will not be repeated here.

[0057] In this embodiment, by collecting and analyzing various historical control parameters of the induced draft fan in different load sections and historical boiler operating data, and comparing the changes in the induced draft fan control parameters and the operating efficiency of the induced draft fan under different boiler operating data, the boiler operating parameters are involved in the joint regulation of the fan, avoiding the resonance of the fan speed while maximizing the fan operating efficiency of each load section.

[0058] In some embodiments of the present application, correlation analysis is performed on each historical boiler operation data and historical control data in each analysis data subset, including: Performing a single factor correlation analysis on each historical boiler operation data and historical control data in each analysis data subset to obtain the historical first influence coefficient of each historical boiler operation data on the historical control data; Filter out historical boiler operation data with a historical influence coefficient greater than a preset influence coefficient threshold for each analysis data subset, and use them as input variables. Use the corresponding historical control data as output variables to generate a variable training set and a variable test set. Establish a multiple linear regression equation; The historical second influence coefficient of each selected historical boiler operation data on the historical control data is calculated based on the multivariate linear regression equation.

[0059] In this embodiment, the historical first influence coefficient refers to fixing other parameters and analyzing the relationship between a single historical boiler operating data and historical control data. For example, when the steam flow rate increases from 300 t / h to 670 t / h, the changing trends of the induced draft fan speed and opening are recorded. It is found that for every 100 t / h increase in steam flow rate, the induced draft fan speed needs to increase by an average of 120 r / min and the opening by an average of 5°. The historical first influence coefficient is calculated based on the ratio of the steam flow increase to the speed increase and the opening increase. When the steam flow increase is smaller but the resulting speed increase and opening increase are larger, the historical first influence coefficient is larger, and vice versa.

[0060] In this embodiment, the historical control data are the induced draft fan speed and the rotor blade opening.

[0061] In this embodiment, the screened historical boiler operation data include steam flow x1, furnace negative pressure x2, flue gas oxygen content x3 and steam pressure x4. The steam flow x1, furnace negative pressure x2, flue gas oxygen content x3 and steam pressure x4 are used as input variables, and the induced draft fan speed y1 and moving blade opening y2 are used as output variables. A plurality of change samples are constructed as a variable training set, and a regression equation is constructed. The speed regression equation is: y1=a0+a1x1+a2x2+a3x3+a4x4, and the opening regression equation is: y2=b0+b1x1+b2x2+b3x3+b4x4. a0-b4 (i.e., the historical second influence coefficient) is calculated using the variable training set, and the accuracy is tested based on the variable test set to improve the accuracy of the historical second influence coefficient, thereby laying a data foundation for the subsequent construction of the control analysis model.

[0062] In this embodiment, the historical boiler key parameters are determined based on the historical second influence coefficient and the corresponding parameter weight coefficients are set, laying the foundation for the subsequent calculation of the target control parameters. The target control parameters refer to the speed or opening that meets the stable operation of the boiler and the smoke exhaust requirements. In some embodiments of the present application, determining whether to generate a control instruction based on the resonance interval analysis model and the control analysis model includes: Collect real-time relevant operating data, real-time speed data, real-time vibration data and real-time boiler key parameters; Analyze real-time related operating data, real-time speed data, and real-time vibration data based on the resonance analysis model to determine the real-time resonance range; determining a corresponding real-time first control parameter interval based on the real-time resonance interval; Extract the real-time load points from the real-time relevant operating data, input the real-time load points and real-time boiler key parameters into the control analysis model, and determine the real-time target control parameters; determining whether the real-time target control parameter is within the real-time first control parameter interval, and if not, generating a control instruction according to the real-time target control parameter; If so, the real-time target control parameter is fine-tuned, and the efficiency value corresponding to the fine-tuned real-time target control parameter is in the preset high-efficiency range, and a control instruction is generated according to the fine-tuned real-time target control parameter.

[0063] In this embodiment, the real-time first control parameter interval refers to a speed interval in which the automatic control system avoids the real-time resonance interval frequency, ensuring that the induced draft fan operating speed and the resonance frequency do not overlap, thereby avoiding the risk of resonance.

[0064] In this embodiment, the real-time target control parameter refers to a control parameter that ensures the normal operation of the boiler and has a high operating efficiency.

[0065] In some embodiments of the present application, Figure 2 As shown, it also includes a DCS-based induced draft fan automation control method: Step S201: Acquire historical speed data of the induced draft fan, historical vibration data of several key positions, and historical control data; Step S202: Based on the historical speed data, historical vibration data, and historical control data, determine a number of historical resonance intervals and construct a resonance interval analysis model; Step S203: determining the correlation between historical boiler operation data and historical control parameters, and determining target control parameters based on the first control parameter interval corresponding to each historical resonance interval, and constructing a control analysis model; Step S204: Determine whether to generate a control instruction based on the resonance interval analysis model and the control analysis model.

[0066] The above is only a preferred embodiment of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and replacements can be made without departing from the technical principles of the present application. These improvements and replacements should also be regarded as the scope of protection of the present application.

Claims

1. A DCS-based induced draft fan automation control system, characterized in that: include: An acquisition module is used to obtain historical speed data of the induced draft fan, historical vibration data of several key locations, and historical control data; A first construction module is used to determine a number of historical resonance intervals based on historical speed data, historical vibration data, and historical control data, and to construct a resonance interval analysis model; The second construction module is used to determine the correlation between historical boiler operation data and historical control parameters, and determine the target control parameters in combination with the first control parameter interval corresponding to each historical resonance interval, and construct a control analysis model; The control module is used to determine whether to generate a control instruction based on the resonance interval analysis model and the control analysis model.

2. The DCS-based induced draft fan automation control system according to claim 1, characterized in that: Obtain historical speed data of the induced draft fan, historical vibration data of several key locations, and historical control data, including: Determine the type of induced draft fan based on the basic information of the current induced draft fan; Acquire multiple historical monitoring logs of the current induced draft fan type during multiple full life cycles, and extract historical initial speed data, historical initial vibration data, and historical initial control data at multiple identical historical monitoring nodes in each historical monitoring log; Preprocessing the historical initial speed data, historical initial vibration data, and historical initial control data at each historical monitoring node, wherein the preprocessing includes removing noise, filling missing values, and standardizing; The historical speed data, historical vibration data and historical control data are obtained respectively according to the pre-processed historical initial speed data, historical initial vibration data and historical initial control data.

3. The DCS-based induced draft fan automation control system according to claim 2, characterized in that: Based on historical speed data, historical vibration data, and historical control data, several historical resonance intervals are determined, including: Perform feature extraction on the historical speed data and historical vibration data at each identical historical monitoring node to obtain historical speed features and historical vibration features; Capturing historical speed characteristics and historical vibration characteristics at a plurality of consecutive identical historical monitoring nodes based on preset capture conditions, wherein the preset capture conditions include a first preset capture condition, a second preset capture condition, and a third preset capture condition; Determine a number of historical resonance intervals based on the capture results, and each historical resonance interval is mapped with a corresponding preset capture condition and a corresponding capture feature; The historical resonance intervals are classified according to the preset capture conditions and capture characteristics to obtain several historical resonance intervals of the same category, and a historical resonance interval group of each category is constructed; Several historical resonance intervals in each category of the historical resonance interval group are analyzed to determine a first resonance interval, a first data interval set, several second resonance intervals, and a corresponding second data interval set corresponding to the historical resonance interval group.

4. The DCS-based induced draft fan automation control system according to claim 3, characterized in that: Determining a first resonance interval, a first data interval set, a plurality of second resonance intervals, and corresponding second data interval sets corresponding to a historical resonance interval group includes: Comparing and analyzing multiple historical resonance intervals in the same historical resonance interval group to obtain the difference in the first resonance interval between different historical resonance intervals; Determining a cluster corresponding to a historical resonance interval group according to a plurality of first resonance interval difference amounts, wherein the cluster includes a plurality of historical resonance intervals; generating a first resonance interval according to a number of historical resonance intervals in the cluster; Obtaining a number of historical operating data and corresponding historical data intervals at the historical monitoring nodes corresponding to the historical resonance intervals in the clusters; generating a first data interval corresponding to the historical operation data according to multiple historical data intervals corresponding to the same historical operation data; Each historical resonance interval that does not belong to a cluster in the same historical resonance interval group is set as a second resonance interval; Acquire a number of historical operating data and a corresponding historical data interval at a historical monitoring node corresponding to each resonance interval in the same historical resonance interval group, and set the historical data interval as a second data interval corresponding to the historical operating data; Comparing the first data interval of the same historical operating data with the second data interval of the historical operating data corresponding to each second resonance interval to obtain a data interval difference; Constructing a data interval difference matrix of the corresponding historical operation data from multiple data interval difference amounts of the same historical operation data, wherein the data interval difference matrix includes a plurality of data interval difference amounts sorted by size, and each data interval difference amount is mapped to a corresponding second resonance interval difference amount; Determine whether there is a dependency relationship between a plurality of data interval difference quantities in the data interval difference quantity matrix and a plurality of mapped second resonance interval difference quantities; if so, calculate the dependency coefficient; if not, remove the corresponding historical operation data; Calculate the number of data interval differences in the data interval difference matrix of the same historical running data that are greater than a preset data interval difference threshold; Calculate the correlation coefficient of the corresponding historical operation data based on the number of data interval differences in the data interval difference matrix of the same historical operation data that are greater than the preset data interval difference threshold and the dependence coefficient; Determining historical operating data having a correlation coefficient greater than a preset correlation coefficient threshold as relevant operating data; constructing a first data interval set based on first data intervals of a plurality of related data; A second data interval set is constructed according to a plurality of second data intervals of a plurality of related data, and each second data interval is mapped to a corresponding second resonance interval.

5. The DCS-based induced draft fan automation control system according to claim 4, characterized in that: The correlation coefficient of the corresponding historical operation data is calculated based on the number of data interval differences in the data interval difference matrix of the same historical operation data that are greater than the preset data interval difference threshold and the dependence coefficient, including: The calculation formula of the correlation coefficient is: ； Where H is the correlation coefficient, n1 is the number of data interval differences in the data interval difference matrix that are greater than the preset data interval difference threshold, n2 is the total number of data interval differences in the data interval difference matrix, ji is the i-th data interval difference, is the mean value of the data interval difference in the data interval difference matrix, gi is the difference of the i-th second resonance interval, is the mean value of the second resonance interval difference in the data interval difference matrix.

6. The DCS-based induced draft fan automation control system according to claim 5, characterized in that: Construct a resonance interval analysis model, including: Using historical speed data, historical vibration data, and a corresponding first data interval set as first training input data, and the corresponding first resonance interval as first training output data; Using the historical speed data, the historical vibration data, and the corresponding second data interval set as second training input data, and the corresponding second resonance interval as second training output data; A neural network training is performed according to the first training input data, the first training output data, the second training input data and the second training output data to obtain a resonance interval analysis model.

7. The DCS-based induced draft fan automation control system according to claim 6, characterized in that: Determine the correlation between historical boiler operation data and historical control parameters, and determine the target control parameters in combination with the first control parameter interval corresponding to each historical resonance interval, and build a control analysis model, including: Setting a first preset load segment, a second preset load segment, a third preset load segment and a plurality of preset load points in each preset load segment for the induced draft fan load; Extract historical load data, historical control data, and historical boiler operation data from historical monitoring logs; According to the correspondence between the historical load data and the preset load segments, a first analysis data set for the first preset load segment, a second analysis data set for the second preset load segment, and a third analysis data set for the third preset load segment are constructed, wherein each analysis data set includes a plurality of analysis data subsets, and each analysis data subset corresponds to a preset load point; Performing correlation analysis on each historical boiler operation data and historical control data in each analysis data subset to obtain a correlation relationship between each historical boiler operation data and historical control data; The correlation relationship includes whether there is a correlation and the historical second influence coefficient; Setting historical boiler operation data having a correlation relationship and having a historical second influence coefficient greater than a preset influence coefficient threshold as historical boiler key parameters; Determine the target control parameter based on the historical boiler key parameters and the corresponding correlation relationship, and judge whether the target control parameter is within the corresponding first control parameter range; If not, the target air volume is calculated based on the boiler operation requirements and target control parameters; Construct a control parameter-air volume-efficiency curve for each analysis data subset; Map the target control parameters and target air volume to the corresponding control parameter-air volume-efficiency curve to obtain the target efficiency value; Determine whether the target efficiency value is within the preset high efficiency range. If so, use the preset load point, historical boiler key parameters, and corresponding target control parameters as a training parameter group, where the preset load point and historical boiler key parameters are training input parameters, and the corresponding target control parameters are training output parameters; generating a number of training parameter sets for each subset of analyzed data; The neural network is trained according to several training parameter groups of each analysis data subset to obtain a control analysis model.

8. The DCS-based induced draft fan automation control system according to claim 7, characterized in that: Perform correlation analysis on each historical boiler operation data and historical control data in each analysis data subset, including: Performing a single factor correlation analysis on each historical boiler operation data and historical control data in each analysis data subset to obtain the historical first influence coefficient of each historical boiler operation data on the historical control data; Filter out historical boiler operation data with a historical influence coefficient greater than a preset influence coefficient threshold for each analysis data subset, and use them as input variables. Use the corresponding historical control data as output variables to generate a variable training set and a variable test set. Establish a multiple linear regression equation; The historical second influence coefficient of each selected historical boiler operation data on the historical control data is calculated based on the multivariate linear regression equation.

9. The DCS-based induced draft fan automation control system according to claim 8, characterized in that: Determining whether to generate a control instruction based on the resonance interval analysis model and the control analysis model includes: Collect real-time relevant operating data, real-time speed data, real-time vibration data and real-time boiler key parameters; Analyze real-time related operating data, real-time speed data, and real-time vibration data based on the resonance analysis model to determine the real-time resonance range; determining a corresponding real-time first control parameter interval based on the real-time resonance interval; Extract the real-time load points from the real-time relevant operating data, input the real-time load points and real-time boiler key parameters into the control analysis model, and determine the real-time target control parameters; determining whether the real-time target control parameter is within the real-time first control parameter interval, and if not, generating a control instruction according to the real-time target control parameter; If so, the real-time target control parameter is fine-tuned, and the efficiency value corresponding to the fine-tuned real-time target control parameter is in the preset high-efficiency range, and a control instruction is generated according to the fine-tuned real-time target control parameter.

10. A DCS-based induced draft fan automation control method, characterized in that: include: Obtain historical speed data of the induced draft fan, historical vibration data of several key locations, and historical control data; Based on historical speed data, historical vibration data, and historical control data, several historical resonance intervals are determined, and a resonance interval analysis model is constructed; Determine the correlation between historical boiler operation data and historical control parameters, and determine the target control parameters in combination with the first control parameter interval corresponding to each historical resonance interval, and construct a control analysis model; Whether to generate a control instruction is determined based on the resonance interval analysis model and the control analysis model.

Images