Circulating fluidized bed boiler control method and system, computing equipment and storage medium
By acquiring and processing the status data of the circulating fluidized bed boiler, using the finite impulse response model and predictive control parameters derived from the regression model, the difficulty caused by the control lag and coal quality changes of the circulating fluidized bed boiler is solved, and efficient and stable control effect.
Patent Information
- Application Number
- CN202410953319.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-16
- Publication Date
- 2024-11-05
AI Technical Summary
Due to its nonlinear, strong coupling and large hysteresis characteristics, existing PID control is difficult to achieve efficient and stable control, especially when coal quality changes, the difficulty of control increases.
By obtaining the current status data of the boiler, calculating the verification parameters and filtering the condition status data, using the finite impulse response model and the predicted control parameters from the regression model, the target control parameters are sent to the execution system after correction, and the boiler working parameters are adjusted.
It realizes efficient and stable control of circulating fluidized bed boilers, reduces control lag, and maintains control accuracy and stability when coal quality changes.
Smart Images

Figure CN118897488A_ABST
Abstract
Description
Technical Field
[0001] The embodiments of this specification relate to the field of automatic control technology, and more particularly to a circulating fluidized bed boiler control system, method, computing device and storage medium. Background Art
[0002] Circulating fluidized bed boilers use clean coal combustion technology with a high degree of industrialization and fluidized combustion. Circulating fluidized bed boilers are widely used due to their good combustion adaptability, high combustion efficiency, wide load adjustment range, and low combustion pollutant emissions.
[0003] At present, circulating fluidized bed boilers generally use DCS control systems (distributed control systems) and use PID to adjust the control loop. However, due to the serious nonlinearity, strong coupling and large hysteresis of circulating fluidized bed boilers, it is difficult to achieve efficient and stable control with conventional PID control. In addition, boiler fuel coal often involves changes in coal types or blending. Even the same type of coal has changes in volatile matter and calorific value, that is, frequent changes in coal quality, which also increases the difficulty of control.
[0004] Therefore, it is necessary to provide a solution to solve the above problems. Summary of the invention
[0005] In view of this, an embodiment of this specification provides a circulating fluidized bed boiler control method. One or more embodiments of this specification also relate to a circulating fluidized bed boiler control device, a computing device and a computer-readable storage medium to solve the technical defects existing in the prior art.
[0006] According to a first aspect of an embodiment of this specification, a circulating fluidized bed boiler control method is provided, comprising:
[0007] Acquire the status data of the boiler at the current moment, wherein the status data is derived from at least one monitoring and control system;
[0008] Calculating verification parameters according to the state data, filtering out conditional state data from the state data according to preset conditions, and calculating prediction control parameters according to the conditional state data;
[0009] Correcting the predicted control parameter based on the verification parameter to obtain a target control parameter;
[0010] The target control parameter is sent to the monitoring execution control system, so that the monitoring execution control system adjusts the operating parameters of the boiler based on the target control parameter at the next moment, wherein the monitoring execution control system is a system in the at least one monitoring control system that controls the operation of the boiler.
[0011] In one embodiment of the present specification, the at least one monitoring and control system includes an electric power integrated automation system, a video monitoring system and a distributed control system; the obtaining of the status data of the boiler at the current moment includes:
[0012] Acquire the working electrical signal of the boiler from the electric power integrated automation system;
[0013] Acquiring furnace image data from the video monitoring system;
[0014] Acquiring production process data from the distributed control system;
[0015] The state data of the boiler at the current moment is determined according to the working electrical signal, the furnace image data and the production process data.
[0016] In one embodiment of the present specification, the working electrical signal at least includes current signals, voltage signals and frequency signals of corresponding frequency converters of primary fans, secondary fans, induced draft fans, etc.; the state data of the boiler at the current moment is determined based on the working electrical signal, process parameters such as furnace negative pressure, steam pressure, steam temperature, the furnace image data, flue gas oxygen content, nitrogen oxides and other production process data, including:
[0017] Extracting features from the furnace image data to obtain combustion image features, wherein the combustion image features are used to characterize the combustion intensity and combustion status of the furnace flame;
[0018] Using the working electrical signal, the combustion image feature and the production process data as the status data;
[0019] Accordingly, the verification parameters include operating parameters and raw material parameters, and the calculation of the verification parameters according to the state data includes:
[0020] A data model is constructed based on the working electrical signal, the combustion image characteristics and the production process data, and the operating parameters and the raw material parameters are obtained by calculation according to the data model.
[0021] In one embodiment of the present specification, the calculating the prediction control parameter according to the condition state data includes:
[0022] Inputting the conditional state data into a finite impulse response model to obtain an intermediate state value output by the finite impulse response model;
[0023] The intermediate state value and the disturbance value are superimposed to obtain an output quantity observation value, and the prediction control parameter is calculated based on the output quantity observation value.
[0024] In one embodiment of the present specification, the correcting the predicted control parameter based on the verification parameter to obtain the target control parameter includes:
[0025] determining a deviation value of the prediction control parameter relative to the verification parameter;
[0026] When the deviation value is less than or equal to a preset deviation value, taking the verification parameter as a target control parameter;
[0027] When the deviation value is greater than a preset deviation value, the predicted control parameter is used as the target control parameter.
[0028] In one embodiment of the present specification, after the predicted control parameter is corrected based on the verification parameter to obtain the target control parameter, the method further includes:
[0029] The target control parameter is sent to the user terminal based on the user viewing request.
[0030] In one embodiment of the present specification, filtering out conditional state data from the state data according to a preset condition includes:
[0031] Acquire historical operating parameters and historical status data, and determine preset conditions based on the degree of influence of the historical status data on the historical operating parameters, wherein the historical status data refers to the status data of the boiler before the current moment, and the historical operating parameters refer to the operating parameters of the boiler corresponding to the historical status data before the current moment;
[0032] Filter out conditional status data from the status data according to preset conditions.
[0033] According to a second aspect of the embodiments of this specification, there is provided a circulating fluidized bed boiler control system, comprising: a data processing platform and at least one monitoring control system, wherein the data processing platform comprises a verification module and a prediction module;
[0034] The monitoring and control system is configured to monitor the current state of the boiler and obtain corresponding state data, and send the state data to the verification module;
[0035] The verification module is configured to obtain the status data of the boiler at the current moment, wherein the status data is derived from at least one monitoring and control system; and calculate the verification parameter according to the status data;
[0036] The prediction module is configured to filter out conditional state data from the state data according to a preset condition, and calculate a prediction control parameter according to the conditional state data;
[0037] The verification module is further configured to correct the predicted control parameters based on the verification parameters to obtain target control parameters; send the target control parameters to the monitoring execution control system, so that the monitoring execution control system adjusts the operating parameters of the boiler based on the target control parameters at the next moment, wherein the monitoring execution control system is a system that controls the operation of the boiler in the at least one monitoring control system.
[0038] According to a third aspect of an embodiment of this specification, a computing device is provided, including:
[0039] Memory and processor;
[0040] The memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions. When the computer executable instructions are executed by the processor, the steps of the above-mentioned circulating fluidized bed boiler control method are implemented.
[0041] According to a fourth aspect of the embodiments of this specification, a computer-readable storage medium is provided, which stores computer-executable instructions, and when the instructions are executed by a processor, the steps of the above-mentioned circulating fluidized bed boiler control method are implemented.
[0042] An embodiment of the present specification realizes automatic monitoring of boiler status data and realizes boiler control by processing the status data. It can monitor the boiler status even when the coal quality changes frequently, reduce the control difficulty, realize the prediction of boiler control data, and reduce the lag of boiler control. At the same time, the predicted control parameters are verified by verification parameters, so that the final target control parameters are more accurate, thereby realizing efficient and stable control of the boiler. BRIEF DESCRIPTION OF THE DRAWINGS
[0043] Figure 1 is a flow chart of a circulating fluidized bed boiler control method provided by one embodiment of this specification;
[0044] Figure 2 It is a schematic diagram of boiler status data monitoring in a circulating fluidized bed boiler control method provided by another embodiment of the present specification;
[0045] Figure 3 It is a schematic diagram of a predictive control parameter calculation process in a circulating fluidized bed boiler control method provided by another embodiment of the present specification;
[0046] Figure 4 It is a schematic diagram of a finite impulse response model in a circulating fluidized bed boiler control method provided by another embodiment of this specification;
[0047] Figure 5It is a schematic diagram of the influence of adjustment of boiler working parameters on state data in a circulating fluidized bed boiler control method provided in another embodiment of the present specification;
[0048] Figure 6 is a structural schematic diagram of a circulating fluidized bed boiler control system provided by another embodiment of this specification;
[0049] Figure 7 is a structural schematic diagram of a circulating fluidized bed boiler control system provided by another embodiment of this specification;
[0050] Figure 8 It is a structural block diagram of a computing device provided by an embodiment of this specification. DETAILED DESCRIPTION
[0051] Many specific details are described in the following description to facilitate a full understanding of this specification. However, this specification can be implemented in many other ways than those described herein, and those skilled in the art can make similar generalizations without violating the connotation of this specification, so this specification is not limited to the specific implementation disclosed below.
[0052] The terms used in one or more embodiments of this specification are only for the purpose of describing specific embodiments, and are not intended to limit one or more embodiments of this specification. The singular forms of "a", "said" and "the" used in one or more embodiments of this specification and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used in one or more embodiments of this specification refers to and includes any or all possible combinations of one or more associated listed items.
[0053] It should be understood that although the terms first, second, etc. may be used to describe various information in one or more embodiments of this specification, this information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of one or more embodiments of this specification, the first may also be referred to as the second, and similarly, the second may also be referred to as the first. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".
[0054] In addition, it should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in one or more embodiments of this specification are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.
[0055] First, the terms involved in one or more embodiments of this specification are explained.
[0056] Finite impulse response model: An alternative filter is a finite support filter that does not require feedback, called a finite impulse response (FIR) filter. For a FIR filter, each output is a weighted sum of a finite number of samples in the neighborhood of the input sample.
[0057] Auto-Regressive with Extra Inputs (ARX) model is a time series analysis method. Its model parameters condense important information about the system state. An accurate ARX model can express the operating laws of the system in a profound and concentrated manner.
[0058] Circulating fluidized bed boilers are widely used due to their advantages such as good combustion adaptability, high combustion efficiency, wide load adjustment range, and low combustion pollutant emissions. However, there is a serious lag problem in the control technology of existing circulating fluidized bed boilers, that is, the operating status of the boiler cannot be adjusted in time according to the operating status of the boiler.
[0059] In this regard, in this specification, a circulating fluidized bed boiler control method is provided. This specification also involves a circulating fluidized bed boiler control device, a computing device, and a computer-readable storage medium, which are described in detail one by one in the following embodiments.
[0060] See also Figure 1 , Figure 1 It is a flow chart of a circulating fluidized bed boiler control method provided in an embodiment of the present specification, which is applied to a data processing platform and specifically includes the following steps.
[0061] Step 102: Acquire the status data of the boiler at the current moment, wherein the status data comes from at least one monitoring and control system.
[0062] Specifically, the boiler refers to a circulating fluidized bed boiler, and the operating parameters need to be adjusted in real time during the production process. The state data refers to the characteristics of the boiler in different dimensions during operation. For example, the state data can be the flame combustion state, furnace temperature, furnace negative pressure, main steam pressure, main steam temperature, etc. The monitoring and control system is used to monitor the state of the boiler in real time, and control the boiler according to the final target control data, and the system is used to replace the original manual operation.
[0063] Based on this, the data processing platform obtains the status data of the boiler at the current moment from at least one monitoring and control system, so as to make predictive control on the operation of the boiler at a future moment based on the status data.
[0064] Furthermore, the at least one monitoring and control system includes an integrated power automation system, a video monitoring system and a distributed control system; the acquisition of the boiler's current state data includes: acquiring the boiler's working electrical signal from the integrated power automation system; acquiring furnace image data from the video monitoring system; acquiring production process data from the distributed control system; and determining the boiler's current state data based on the working electrical signal, the furnace image data and the production process data.
[0065] Specifically, at least one monitoring and control system is used to monitor status data of different dimensions of the boiler, and in addition, can also control the boiler.
[0066] Based on this, the monitoring and control system includes: an integrated power automation system, which is used to obtain the working electrical signals of the boiler, i.e., the electrical signals related to electricity during the working process of the boiler, such as the current signals, voltage signals and corresponding inverter frequency signals of the primary fan, secondary fan, induced draft fan, etc.; a video monitoring system, which is used to obtain furnace image data, i.e., images of the inside of the furnace of the boiler to be monitored, such as the flame combustion state, smoke emission state, etc.; a distributed control system (i.e., a DCS control system), which is mainly used to obtain gas-related data generated in the boiler, production process data such as furnace negative pressure, flue gas content and oxygen content, etc.; a PLC control system, which is used to control the current and frequency of the boiler fan (including induced draft fan, primary fan, secondary fan), as well as the start and stop of the fan and the control of the fan supporting facilities (such as the oil system, etc.).
[0067] See also Figure 2 , Figure 2This is a schematic diagram of monitoring the status data of a boiler in a circulating fluidized bed boiler control method provided in another embodiment of this specification. In one embodiment of this specification, the video monitoring system includes a flame monitoring camera for monitoring the flame combustion in the boiler furnace to obtain furnace image data. The DCS system and its associated instruments are used to monitor the gas-related data in the furnace and flue, such as steam pressure, steam temperature, furnace negative pressure, flue gas nitrogen oxide content, flue gas oxygen content and induced draft. Figure 2 The total coal feed and total air volume data in the monitoring control system are the working parameters controlled by the control system.
[0068] The status data of the boiler at the current moment is determined based on the data obtained from different monitoring and control systems.
[0069] The embodiments of this specification can achieve more accurate control of the boiler according to the status of the boiler in different dimensions by acquiring data from different monitoring systems, so that the control strategy can be optimized and the control means can be more flexible.
[0070] Since different monitoring systems have their own unique data collection methods, precision and standards, the collected data may differ in type, format, unit, quality, etc. Some data may not be directly used for analysis or modeling due to incompatible formats, noise, missing values, outliers or other quality issues. Therefore, it is necessary to process these data that cannot be used directly. The state data of the boiler at the current moment is determined based on the working electrical signal, the furnace image data and the production process data, including: extracting features from the furnace image data to obtain combustion image features, and the combustion image features are used to characterize the combustion intensity and combustion status of the furnace flame; using the working electrical signal, the combustion image features and the flow data as the state data.
[0071] Specifically, furnace image data generally refers to pictures or videos obtained by a camera that can show the combustion situation in the furnace. The data processing platform needs to extract the features of the furnace image data to obtain the combustion image features. Specifically, the flame light intensity signal in the picture or video of the combustion situation in the furnace is converted into real-time data. For example, the combustion intensity characteristic value, that is, the combustion image feature, is identified by the neural network algorithm ANN. The combustion image feature can reflect the combustion intensity and combustion status of the furnace flame, and then further processing is achieved. The combustion image feature is introduced into the control system as a detection signal to participate in the control of the main steam pressure temperature, coal supply, primary air volume, secondary air volume and flue gas oxygen content. The combustion image feature is extracted as a combustion variable, which is an indicator variable for the direct combustion of the coal and air ratio mixture, and is also an advance feedback of the main steam pressure temperature. At the same time, it is related to the flue gas after combustion, mainly oxygen content, NOX emissions, etc. Through the furnace flame, the change of coal quality can also be indirectly reflected. In addition, according to the processing requirements of the data processing platform, the working electrical signal, combustion image feature and production process data can also be processed by data format conversion, effective value screening and other processing.
[0072] The processed working electrical signals, combustion image characteristics and production process data are used as boiler status data.
[0073] In the prior art, the inlet of the boiler furnace controls the fuel quantity and air volume, and the outlet controls the main steam pressure and main steam temperature. There is a long lag in the middle, and it cannot be adjusted in time. By introducing the furnace flame signal, it is converted into a digital signal, and the feature extraction obtains the combustion image feature. When an abnormal situation occurs in the combustion process, the change value of the combustion image feature is obtained in time, and the control and adjustment are timely avoided. The situation of intervening in the adjustment only after a large deviation occurs improves the timeliness and accuracy of the adjustment.
[0074] The embodiments of this specification can process state data of different dimensions before performing calculations, thereby improving the calculation efficiency of the data processing platform.
[0075] Step 104: Calculate verification parameters according to the state data, filter out conditional state data from the state data according to preset conditions, and calculate prediction control parameters according to the conditional state data.
[0076] Since the status data contains different dimensional states from different monitoring systems, the verification data also contains verification parameters of different dimensions accordingly, and the verification parameters include operating parameters and raw material parameters. The verification parameters are calculated according to the status data, including: constructing a data model based on the working electrical signal, the combustion image characteristics and the production process data, and obtaining the operating parameters and the raw material parameters according to the data model.
[0077] Specifically, the operating parameters may include control parameters for the negative pressure in the furnace of the boiler, such as furnace pressure increase or furnace pressure decrease, and the raw material parameters may include the coal feed rate or air feed rate of the boiler.
[0078] The embodiments of this specification calculate verification data based on status data of different dimensions to facilitate adjustment of prediction data in subsequent processes and improve the accuracy of target prediction data.
[0079] Furthermore, there are two situations for generating preset conditions. The first situation is that the preset conditions can be set manually according to actual needs, and the second situation is that the data processing platform can automatically generate the preset conditions according to historical data.
[0080] In the second case, conditional status data is filtered out from the status data according to preset conditions, including: obtaining historical working parameters and historical status data, and determining the preset conditions based on the degree of influence of the historical status data on the historical working parameters, wherein the historical status data refers to the status data of the boiler before the current moment, and the historical working parameters refer to the working parameters of the boiler corresponding to the historical status data before the current moment; conditional status data is filtered out from the status data according to the preset conditions.
[0081] Specifically, historical status data refers to the status data related to the production process of the boiler that can be recorded, queried, and displayed before the current moment, and historical working parameters refer to the working parameters that can be recorded, queried, and displayed for adjusting the production process of the boiler before the current moment. Working parameters are, for example, operating parameters of the boiler.
[0082] Based on this, after obtaining the historical working parameters and historical status data, the preset conditions are determined based on the degree of influence of the historical status data on the historical working parameters. For example, the corresponding status dimensions of a preset number of historical status data with the largest change in the historical status data as the historical working parameters change are used as preset conditions, and the conditional status data is filtered out from the status data at the current moment according to the preset conditions.
[0083] For example, historical status data includes historical working electrical signals, historical furnace image data and historical production process data, and historical working parameters include historical operating parameters and historical raw material parameters. When historical operating parameters and historical raw material parameters change, the fan frequency in the historical working electrical signals, historical furnace image data and production process data have the largest change range. Therefore, the fan frequency, furnace image data and production process data are used as preset conditions, and status data with the same dimension are filtered out from the current status data as conditional status data.
[0084] The embodiments of this specification can filter out more effective conditional state data from the state data and improve the accuracy of subsequent calculation of target control parameters by determining preset conditions for filtering state data according to the degree of mutual influence between historical state data and historical operating parameters.
[0085] Furthermore, the calculation of the predicted control parameters based on the conditional state data includes: inputting the conditional state data into a finite impulse response model to obtain an intermediate state value output by the finite impulse response model; superimposing the intermediate state value with the disturbance to obtain an output quantity observation value, and obtaining the predicted control parameters based on the output quantity observation value.
[0086] Specifically, the prediction module is calculated by combining the wired pulse response model with the organic exogenous regression model. The finite pulse response model does not consider the influence of the historical data of the controlled variable, so the calculation speed is fast. It is suitable for process object models with rapid changes such as pressure and flow, and matches the actual process. The organic exogenous regression model needs to consider the historical data of the controlled variable. For process objects with large inertia links such as main steam temperature and superheater temperature, the historical data has a greater impact on them, which is bound to increase the amount of calculation. Combine the two together and establish a model matrix according to different process objects. The process object refers to the system that needs to be controlled in the process production process, in which the main control parameters such as the main steam temperature, the related field equipment and associated equipment and the mutual influence constitute a process object. The process object and the control system are combined to form an independent control system. Computer control first needs to collect the relevant parameters of the process object, and then identify the model matrix through system identification, which is the modeling process. The model matrix is to express the model to be identified in the form of a mathematical matrix.
[0087] See also Figure 3 , Figure 4 , Figure 3 is a schematic diagram of a predictive control parameter calculation process in a circulating fluidized bed boiler control method provided by another embodiment of the present specification, Figure 4It is a schematic diagram of a finite impulse response model in a circulating fluidized bed boiler control method provided by another embodiment of the present specification. Among them, the monitoring control system is specifically a DCS control system. After the DCS control system monitors the status data of the boiler, the status data is sent to the prediction model, and processed by the finite impulse response model combined with the natural regression model, and the prediction control parameters are obtained after processing. The prediction control parameters are verified by the optimization control module to obtain the target control parameters, and the target control parameters are returned to the DCS control system, so that the DCS control system controls the boiler according to the target control parameters, wherein the optimization control module calculates the verification parameters through CV and its restrictions and MV and its restrictions (i.e., the status data of the boiler), and verifies the prediction control parameters according to the verification parameters. In addition, the process object is the above-mentioned process object.
[0088] After acquiring the conditional state data, the prediction module needs to determine the predicted control parameters calculated by the wired impulse response model or the active autoregressive model.
[0089] Specifically, the finite impulse response model does not consider the influence of the historical data of the controlled variable, so the calculation speed is fast, which is suitable for process object models with rapid changes such as pressure and flow, and matches the actual process. However, the self-regression model needs to consider the historical data of the controlled variable, and the historical data of the process object with large inertia links such as main steam temperature and superheater temperature has a greater impact on it, which is bound to increase the amount of calculation.
[0090] According to the model features corresponding to the finite impulse response model and the organic regression model, the first data type corresponding to the finite impulse response model and the second data type corresponding to the organic regression model are preset. For example, the first data type is data with a fast dynamic response speed, including pressure data, flow data, etc., and the second data type is data with a slow dynamic response speed, including temperature data, liquid level data, gas component content data, etc. After the prediction module obtains the conditional state data, it determines whether to use the finite impulse response model or the organic regression model for calculation according to the data type to which the conditional state belongs.
[0091] The conditional state data of the boiler is input into the prediction model, and the input target state value is processed by the finite impulse response model. The target state value u(k) of the boiler is used as the input value and input into the finite impulse response model. After calculation through the object G(z,θ), the intermediate state value x(k) is obtained. x(k) is also the open-loop value of the input u(k) acting on the object G(z,θ). The disturbance v(k) is obtained, and the output value y(k) is superimposed on x(k) and v(k) to obtain the prediction control parameter. The specific processing process is as follows:
[0092] Decompose the object mathematical model of formula (1) and the difference equation of formula (2),
[0093]
[0094] Extract the coefficients in equation (1) and equation (2) respectively, and obtain θ and H in equation (3).
[0095]
[0096] The matrix of linear equations with observation data length L is (4):
[0097] Z L =H L θ+n(L)(4)
[0098]
[0099] For the finite impulse response difference equation model:
[0100] y(k)=Ψ T (k)θ+e(k) (7)
[0101] In the formula, y(k) is the k-th observed value of the system output, y(k-1) is the k-1-th observed value of the system output, and so on; u(k) is the k-th input value of the system, u(k-1) is the k-1-th input value of the system, and so on; e(k) is random noise with a mean of zero.
[0102] The process of decomposing equations (1) and (2) through the self-regression model is as follows:
[0103]
[0104] After Z-transformation of equation (9), we get equation (10):
[0105]
[0106] h(k)=[-z(k-1),-z(k-2),…,-z(kn a ),u(k-1),u(k-2),…,u(kn b )] T (10)
[0107] z(k)=h T (k)θ+e(k)
[0108] The output value z(k) obtained after transformation is used as the predictive control parameter.
[0109] It should be noted that A(z -1 ) or B(z -1), are obtained through z-transformation. The so-called z-transformation is to transform into (z -1 ) in mathematical function form, z -1 Represents a sampling period, the value of the first beat; z -k It represents the value of the kth beat in k sampling cycles. The important meaning of z change lies in delay and discreteness.
[0110] A(z -1 )z(k) represents the transformed form of the left side of equation (8), A represents the matrix, A(z -1 ) indicates that the variable is z -1 The function matrix formed by z(k) represents a vector, A(z -1 )z(k) is the mathematical transformation of the left side of equation (8) converted into a matrix through z transformation.
[0111] Similarly, the right side of equation 8 is converted into a matrix-vector product form by changing z. -1 ) indicates that the variable is z -1 The function matrix formed by u(k) represents the input vector, which represents the number of steps from the first beat to the bth beat. n The vector of the combined shot, B(z -1 )u(k) is the mathematical transformation form of the right side of equation (8) converted into a matrix through z-transformation.
[0112] It should be noted that the focus of the embodiments of this specification is to use combustion image characteristics and electrical signals as parameters calculated by the prediction module to participate in the calculation of predictive control parameters, and to calculate the predictive control parameters of the boiler from a variety of different dimensions, making the calculation results of the predictive control parameters more accurate.
[0113] The embodiments of this specification can improve the calculation speed while considering the influence of historical data by combining the wired impulse response model and the organic self-regression model.
[0114] Step 106: Correct the predicted control parameters based on the verification parameters to obtain target control parameters.
[0115] Specifically, the validation parameter is a parameter used to determine whether the prediction parameter is accurate.
[0116] Furthermore, the prediction control parameter is corrected based on the verification parameter to obtain the target control parameter, including: determining a deviation value of the prediction control parameter relative to the verification parameter; when the deviation value is less than or equal to a preset deviation value, using the verification parameter as the target control parameter; when the deviation value is greater than a preset deviation value, using the prediction control parameter as the target control parameter.
[0117] Specifically, the deviation value refers to the absolute value of the difference between the predicted control parameter and the verification parameter.
[0118] Based on this, the prediction control parameters are adjusted according to the size of the deviation value. When the deviation value is less than or equal to the preset deviation value, it means that the verification parameters are consistent with the prediction control parameters, and the verification parameters are used as the target control parameters; when the deviation value is greater than the preset deviation value, it means that the verification parameters are inconsistent with the prediction control parameters, and the prediction control parameters are used as the target control parameters.
[0119] In the embodiment of this specification, each time the target control parameter is calculated, the predicted control parameter is corrected by the verification parameter, so that each calculation result can be optimized and the boiler combustion condition can be controlled more accurately.
[0120] In order to facilitate the user to browse the data, after the target control parameters are determined, the target control parameters as well as the status data, historical status data and historical working parameters of the controlled boiler can be sent to the user terminal for display.
[0121] In order to facilitate the user to adjust the data, the prediction control parameter is corrected based on the verification parameter, and after the target control parameter is obtained, the method further includes:
[0122] The target control parameters are sent to the user terminal based on the user's viewing request. The user terminal includes a user interface, which can view the target control parameters. Specifically, the user can initiate a viewing request to the data processing platform at any time through the browser interface in the mobile phone, computer and other terminals. The viewing request can include the target data that needs to be viewed. After receiving the viewing request, the data processing platform sends the corresponding target data to the user terminal. The interface can present the combustion image characteristics, working electrical signal parameters, operating parameters, raw material parameters and other related design parameters, input and output parameters, and the calculation process of intermediate variables. The presentation method can be text, graphics, video and other methods, which is convenient for users to learn and debug the control algorithm online.
[0123] The embodiments of this specification realize data transparency of the control process and facilitate supervision by feeding back and sharing all data in the control process to the user according to the user's needs.
[0124] Step 108: Send the target control parameter to the monitoring execution control system, so that the monitoring execution control system adjusts the operating parameters of the boiler based on the target control parameter at the next moment, wherein the monitoring execution control system is a system in the at least one monitoring control system that controls the operation of the boiler.
[0125] Specifically, the monitoring execution control system refers to a system that needs to adjust the working parameters of the boiler according to the target control parameters, and the monitoring execution control system can be one or more of at least one monitoring control system. The working parameters refer to the relevant parameters of the working state of the boiler corresponding to the next moment, such as the coal supply amount, the air supply amount, etc.
[0126] Based on this, due to the characteristics of the fluidized bed boiler itself, the use of conventional control systems has the problem of fluidized bed boiler control lag. Therefore, the embodiment of this specification controls the working state of the boiler at future moments by introducing target control parameters, that is, the target control parameters are used to predict the working state of the boiler at the next moment, and adjust the boiler according to the predicted working state, make adjustments in advance, and improve the control quality.
[0127] For example, the target control parameters include the fan frequency, the coal feeder voltage corresponding to different coal feeders, and the coal feed amount and air feed amount of the boiler are controlled according to the target control parameters.
[0128] In one embodiment of the present specification, the target control parameter can be stored in the data processing platform, and the monitoring execution control system can call it from the data processing platform when it is needed. In addition, in other embodiments of the present specification, the data processing platform can also send the target control parameter directly to the corresponding monitoring execution control system after obtaining it, and the monitoring execution control system can directly obtain it from its own storage space when needed.
[0129] Furthermore, in the embodiments of the present specification, the operating parameters of the boiler are finally adjusted according to the target control parameters. Therefore, after the operating parameters of the boiler change, they will affect the state data of the boiler again, forming a complete cycle process. Figure 5 It is a schematic diagram of the influence of adjustment of boiler operating parameters on state data in a circulating fluidized bed boiler control method provided in another embodiment of the present specification.
[0130] Figure 5 The manipulated variables are equivalent to the above working parameters, and the controlled variables are equivalent to the above state data. According to the target control parameters, the parameters such as the coal feed rate, total air volume and induced draft volume of the boiler at the next moment are adjusted. After the adjustment, the state data of the boiler's steam pressure, flue gas oxygen content and furnace negative pressure change.
[0131] The embodiment of this specification predicts the future working state of the boiler through the target control parameters. When the next moment comes, the working parameters of the boiler can be directly controlled according to the pre-calculated target control parameters, avoiding the calculation process or data transmission process causing delays in the control of the boiler.
[0132] Furthermore, in the prior art, the four coal feeders corresponding to the boiler are usually controlled manually, and the operator manually adjusts the speed of the coal feeder based on personal experience to control the amount of fuel coal added. Since the output of each coal feeder is inconsistent, it is easy to cause biased burning of the boiler, and the steam temperature generated on the left and right sides will deviate, affecting the combustion efficiency of the boiler.
[0133] The embodiments of the present specification establish a combustion image feature that characterizes the furnace flame detection signal, and a model that is associated with primary air, secondary air, coal feeder rate, main steam pressure, load and furnace temperature. The boiler maintains a reasonable load, pressure and furnace temperature range, and adjusts the rate of the coal feeder to balance the coal feeding rate of the coal feeder, so that the combustion tends to be balanced and biased burning is avoided.
[0134] Corresponding to the above method embodiment, this specification also provides a circulating fluidized bed boiler control system embodiment. Figure 6 , Figure 6 It is a structural diagram of a circulating fluidized bed boiler control system provided in another embodiment of this specification. In one embodiment of this specification, in order to facilitate the deployment and debugging of the prediction module, the prediction module 604 can be independent of the data processing platform (verification module) 602, and the data processing platform only includes the verification module. The monitoring and control system includes an electric power integrated automation system 606, a video monitoring system 607, a distributed control system 608 and / or a PLC control system 609, etc.
[0135] After the prediction control data is calculated in the prediction module, the prediction control parameters can be sent to the data processing platform. The verification module of the data processing platform verifies the prediction control parameters to obtain the target control parameters. The data processing platform sends the target control parameters to the prediction module 604, which then performs calculations and sends the calculation results directly to the monitoring and control system for execution.
[0136] Figure 7 FIG. 1 is a schematic diagram of a circulating fluidized bed boiler control system provided in another embodiment of the present specification. Figure 7 As shown, the system includes: a data processing platform and at least one monitoring execution control system 706, the data processing platform includes a verification module 702 and a prediction module 704;
[0137] The monitoring execution control system 706 is configured to monitor the current state of the boiler and obtain corresponding state data, and send the state data to the verification module 702;
[0138] The verification module 702 is configured to obtain the status data of the boiler at the current moment, wherein the status data is derived from at least one monitoring execution control system 706; and calculate the verification parameter according to the status data;
[0139] The prediction module 704 is configured to filter out conditional state data from the state data according to a preset condition, and calculate a prediction control parameter according to the conditional state data;
[0140] The verification module 702 is further configured to correct the predicted control parameters based on the verification parameters to obtain target control parameters; send the target control parameters to the monitoring execution control system 706, so that the monitoring execution control system 706 adjusts the operating parameters of the boiler based on the target control parameters at the next moment, wherein the monitoring execution control system 706 is a system that controls the operation of the boiler in at least one monitoring execution control system 706.
[0141] Optionally, the at least one monitoring execution control system 706 includes:
[0142] An electric power integrated automation system, configured to obtain an operating electrical signal of the boiler from equipment belonging to the boiler;
[0143] a video monitoring system configured to obtain furnace image data from the video monitoring system;
[0144] a distributed control system configured to obtain production process data from the distributed control system;
[0145] The status data determination module is configured to determine the status data of the boiler at a current moment according to the working electrical signal, the furnace image data and the production process data.
[0146] Optionally, the status data determination module includes:
[0147] A feature extraction submodule is configured to extract features from the furnace image data to obtain combustion image features;
[0148] a data generation submodule, configured to use the working electrical signal, the combustion image feature and the production process data as the status data;
[0149] Accordingly, the verification parameters include operation parameters and raw material parameters, and the verification module 702 includes:
[0150] A data model is constructed based on the working electrical signal, the combustion image characteristics and the production process data, and the operating parameters and the raw material parameters are obtained by calculation according to the data model.
[0151] Optionally, the prediction module 704 includes:
[0152] An intermediate quantity calculation submodule is configured to input the conditional state data into a finite impulse response model to obtain an intermediate state value output by the finite impulse response model;
[0153] The predicted quantity calculation submodule is configured to superimpose the intermediate state value and the disturbance quantity to obtain an output quantity observation value, and calculate the predicted control parameter based on the output quantity observation value.
[0154] Optionally, the verification module 702 includes:
[0155] a deviation determination submodule, configured to determine a deviation value of the prediction control parameter relative to the verification parameter;
[0156] When the deviation value is less than or equal to a preset deviation value, taking the verification parameter as a target control parameter;
[0157] When the deviation value is greater than a preset deviation value, the predicted control parameter is used as the target control parameter.
[0158] Optionally, the data processing platform further includes:
[0159] The feedback submodule is configured to send the target control parameter to the user terminal based on the user viewing request.
[0160] Optionally, the prediction module 704 includes:
[0161] A preset condition determination submodule is configured to obtain historical operating parameters and historical status data, and determine the preset conditions based on the degree of influence of the historical status data on the historical operating parameters, wherein the historical status data refers to the status data of the boiler before the current moment, and the historical operating parameters refer to the operating parameters of the boiler corresponding to the historical status data before the current moment;
[0162] The screening submodule is configured to screen out conditional status data from the status data according to preset conditions.
[0163] The above is a schematic scheme of a circulating fluidized bed boiler control device of this embodiment. It should be noted that the technical scheme of the circulating fluidized bed boiler control device and the technical scheme of the above-mentioned circulating fluidized bed boiler control method belong to the same concept, and the details not described in detail in the technical scheme of the circulating fluidized bed boiler control device can be referred to the description of the technical scheme of the above-mentioned circulating fluidized bed boiler control method.
[0164] This manual Figure 6 The functions of each module in the embodiment and other data processing processes can be referred to Figure 7 The embodiments are not described in detail here.
[0165] The embodiments of this specification use the industrial Internet platform to integrate the furnace flame signal from the video monitoring system (or flame TV system) into the industrial Internet platform, and integrate the boiler draft fan, primary fan, secondary fan current, frequency feedback, power, etc. from the electric power integrated automation system (or electric power SCADA system) signals into the industrial Internet platform. By integrating the data of multiple industrial interconnection systems into the industrial Internet platform, it is possible to share data among systems and facilitate data calls by users of other systems. It is also possible to integrate with the circulating fluidized bed boiler control system to achieve comprehensive control and optimize the control scheme. The current signal and flame detection signal are uniformly introduced into the optimized control system to participate in the control, so that the control strategy can be optimized and the control means are more flexible, thereby achieving the "1+1>2" comprehensive system integration benefit.
[0166] Figure 8 800 is a block diagram of a computing device provided by an embodiment of the present specification. The components of the computing device 800 include but are not limited to a memory 810 and a processor 820. The processor 820 is connected to the memory 810 via a bus 830, and the database 850 is used to store data.
[0167] The computing device 800 also includes an access device 840 that enables the computing device 800 to communicate via one or more networks 860. Examples of these networks include a public switched telephone network (PSTN), a local area network (LAN), a wide area network (WAN), a personal area network (PAN), or a combination of communication networks such as the Internet. The access device 840 may include one or more of any type of network interface, wired or wireless (e.g., a network interface card (NIC)), such as an IEEE 802.11 wireless local area network (WLAN) wireless interface, a World Wide Interoperability for Microwave Access (Wi-MAX) interface, an Ethernet interface, a Universal Serial Bus (USB) interface, a cellular network interface, a Bluetooth interface, and a Near Field Communication (NFC).
[0168] In one embodiment of the present specification, the above components of the computing device 800 and Figure 8 Other components not shown in the figure may also be connected to each other, for example, via a bus. It should be understood that Figure 8 The computing device structure block diagram shown is only for the purpose of illustration, and is not intended to limit the scope of this specification. Those skilled in the art can add or replace other components as needed.
[0169] The computing device 800 may be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., a tablet computer, a personal digital assistant, a laptop computer, a notebook computer, a netbook, etc.), a mobile phone (e.g., a smart phone), a wearable computing device (e.g., a smart watch, smart glasses, etc.), or other types of mobile devices, or a stationary computing device such as a desktop computer or a personal computer (PC). The computing device 800 may also be a mobile or stationary server.
[0170] The processor 820 is used to execute the following computer executable instructions, which, when executed by the processor, implement the steps of the above-mentioned circulating fluidized bed boiler control method.
[0171] The above is a schematic scheme of a computing device of this embodiment. It should be noted that the technical scheme of the computing device and the technical scheme of the above-mentioned circulating fluidized bed boiler control method belong to the same concept, and the details not described in detail in the technical scheme of the computing device can be referred to the description of the technical scheme of the above-mentioned circulating fluidized bed boiler control method.
[0172] An embodiment of the present specification further provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the above-mentioned circulating fluidized bed boiler control method.
[0173] The above is a schematic scheme of a computer-readable storage medium of this embodiment. It should be noted that the technical scheme of the storage medium and the technical scheme of the above-mentioned circulating fluidized bed boiler control method belong to the same concept, and the details not described in detail in the technical scheme of the storage medium can be referred to the description of the technical scheme of the above-mentioned circulating fluidized bed boiler control method.
[0174] An embodiment of the present specification further provides a computer program, wherein when the computer program is executed in a computer, the computer is caused to execute the steps of the above-mentioned circulating fluidized bed boiler control method.
[0175] The above is a schematic scheme of a computer program of this embodiment. It should be noted that the technical scheme of the computer program and the technical scheme of the above-mentioned circulating fluidized bed boiler control method belong to the same concept, and the details not described in detail in the technical scheme of the computer program can be referred to the description of the technical scheme of the above-mentioned circulating fluidized bed boiler control method.
[0176] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
[0177] The computer instructions include computer program codes, which may be in source code form, object code form, executable files or some intermediate forms, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium may be appropriately increased or decreased according to the requirements of patent practice. For example, in some regions, according to patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.
[0178] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the embodiments of this specification are not limited by the order of the actions described, because according to the embodiments of this specification, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the embodiments of this specification.
[0179] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0180] The preferred embodiments of this specification disclosed above are only used to help explain this specification. The optional embodiments do not describe all the details in detail, nor do they limit the invention to only the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of the embodiments of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the embodiments of this specification, so that technicians in the relevant technical field can well understand and use this specification. This specification is only limited by the claims and their full scope and equivalents.
Claims
1. A circulating fluidized bed boiler control method, It is characterized in that Applied to data processing platforms, including: Acquire the status data of the boiler at the current moment, wherein the status data is derived from at least one monitoring and control system; Calculating verification parameters according to the state data, filtering out conditional state data from the state data according to preset conditions, and calculating prediction control parameters according to the conditional state data; Correcting the predicted control parameter based on the verification parameter to obtain a target control parameter; The target control parameter is sent to the monitoring execution control system, so that the monitoring execution control system adjusts the operating parameters of the boiler based on the target control parameter at the next moment, wherein the monitoring execution control system is a system in the at least one monitoring control system that controls the operation of the boiler.
2. The circulating fluidized bed boiler control method according to claim 1, It is characterized in that The at least one monitoring and control system includes an electric power integrated automation system, a video monitoring system and a distributed control system; The obtaining of the status data of the boiler at the current moment includes: Acquire working electrical signals of equipment belonging to the boiler from the electric power integrated automation system; Acquiring furnace image data from the video monitoring system; Acquiring production process data from the distributed control system; The state data of the boiler at the current moment is determined according to the working electrical signal, the furnace image data and the production process data.
3. The circulating fluidized bed boiler control method according to claim 2, It is characterized in that Determining the state data of the boiler at the current moment according to the working electrical signal, the furnace image data and the production process data includes: Extracting features from the furnace image data to obtain combustion image features, wherein the combustion image features are used to characterize the combustion intensity and combustion status of the furnace flame; Using the working electrical signal, the combustion image feature and the production process data as the status data; Accordingly, the verification parameters include operating parameters and raw material parameters, and the calculation of the verification parameters according to the state data includes: A data model is constructed based on the working electrical signal, the combustion image characteristics and the production process data, and the operating parameters and the raw material parameters are obtained by calculation according to the data model.
4. The circulating fluidized bed boiler control method according to claim 1, It is characterized in that The calculating of the prediction control parameters according to the condition state data comprises: Inputting the conditional state data into a finite impulse response model to obtain an intermediate state value output by the finite impulse response model; The intermediate state value and the disturbance value are superimposed to obtain an output quantity observation value, and the prediction control parameter is calculated based on the output quantity observation value.
5. The circulating fluidized bed boiler control method according to claim 1, It is characterized in that The step of correcting the predicted control parameter based on the verification parameter to obtain the target control parameter includes: determining a deviation value of the prediction control parameter relative to the verification parameter; When the deviation value is less than or equal to a preset deviation value, taking the verification parameter as a target control parameter; When the deviation value is greater than a preset deviation value, the predicted control parameter is used as the target control parameter.
6. The circulating fluidized bed boiler control method according to claim 1, It is characterized in that After the prediction control parameter is corrected based on the verification parameter to obtain the target control parameter, the method further includes: The target control parameter is sent to the user terminal based on the user viewing request.
7. The circulating fluidized bed boiler control method according to claim 1, It is characterized in that Filtering out conditional status data from the status data according to preset conditions includes: Acquire historical operating parameters and historical status data, and determine preset conditions based on the degree of influence of the historical status data on the historical operating parameters, wherein the historical status data refers to the status data of the boiler before the current moment, and the historical operating parameters refer to the operating parameters of the boiler corresponding to the historical status data before the current moment; Filter out conditional status data from the status data according to preset conditions.
8. A circulating fluidized bed boiler control system, It is characterized in that include: A data processing platform and at least one monitoring and control system, wherein the data processing platform includes a verification module and a prediction module; The monitoring and control system is configured to monitor the current state of the boiler and obtain corresponding state data, and send the state data to the verification module; The verification module is configured to obtain the status data of the boiler at the current moment, wherein the status data is derived from at least one monitoring and control system; and calculate the verification parameter according to the status data; The prediction module is configured to filter out conditional state data from the state data according to a preset condition, and calculate a prediction control parameter according to the conditional state data; The verification module is further configured to correct the predicted control parameters based on the verification parameters to obtain target control parameters; send the target control parameters to the monitoring execution control system, so that the monitoring execution control system adjusts the operating parameters of the boiler based on the target control parameters at the next moment, wherein the monitoring execution control system is a system that controls the operation of the boiler in the at least one monitoring control system.
9. A computing device, It is characterized in that include: Memory and processor; The memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions. When the computer executable instructions are executed by the processor, the steps of the circulating fluidized bed boiler control method according to any one of claims 1 to 7 are implemented.
10. A computer-readable storage medium, It is characterized in that It stores computer executable instructions, which, when executed by a processor, implement the steps of the circulating fluidized bed boiler control method according to any one of claims 1 to 7.
Citation Information
Cited By
Method for monitoring alumina calcination process based on DCS (Distributed Control System) control
CN120783904A
