Circulating fluidized bed boiler load response system based on adaptive control

Abstract

The invention relates to the technical field of boiler self-adaptive control, and discloses a circulating fluidized bed boiler load response system based on self-adaptive control, which comprises a data acquisition unit and a control unit, wherein the data acquisition unit is used for acquiring boiler operation state data and load change data; the control unit comprises a first processing module used for generating a predicted output load interval of the current boiler according to the boiler operation state data and the load change data; the second processing module is used for generating a corresponding boiler correction decision; and the third processing module is used for correcting the boiler operation parameters. Through self-adaptive control, a preheating combustion technology, accurate fuel injection control and an intelligent wind powder module, quick response to load change is realized, and the combustion efficiency and the system stability are improved.

Description

Technical Field

[0001] The invention relates to the technical field of boiler adaptive control, and in particular to a circulating fluidized bed boiler load response system based on adaptive control. Background Art

[0002] Circulating fluidized bed boiler (CFB boiler) is a highly efficient heat conversion equipment, widely used in power generation and industrial heat processing. It achieves efficient fuel combustion and heat transfer through circulating bed material. As the proportion of renewable energy in the power system gradually increases, traditional coal-fired power units face a more complex and changeable operating environment, especially in situations where rapid response to grid load changes is required. Therefore, improving the load response speed and flexibility of CFB boilers has become an important direction of technological development.

[0003] In summary, CFB boilers face many challenges in the process of rapid load changes, such as large system inertia of flow, heat transfer and combustion in the furnace, as well as problems such as hydrodynamic safety and metal component damage caused by rapid and frequent load changes. These challenges limit the important role of CFB boilers in the grid connection and consumption of new energy, especially in modern power systems that require coal-fired power units to provide flexible adjustment capabilities. Summary of the invention

[0004] The purpose of the present invention is to construct a circulating fluidized bed boiler load response system based on adaptive control to achieve rapid response and stable control to boiler load changes, including: through adaptive control, preheating combustion technology, precise fuel injection control and intelligent air-powder module, rapid response to load changes is achieved, combustion efficiency and system stability are improved, operating costs are reduced, and environmental pollution is reduced.

[0005] In order to achieve the above-mentioned object, the present invention provides a circulating fluidized bed boiler load response system based on adaptive control, comprising: a data acquisition unit, a control unit; The data acquisition unit is used to obtain boiler operation status data and load change data; A control unit is used to establish a boiler control model, generate a boiler correction instruction according to boiler operation status data and load change data, and adjust the boiler output load according to the boiler correction instruction; The control unit also includes: A first processing module, used for generating a predicted output load interval of the current boiler according to the boiler operation status data and the load change data; The second processing module determines a load difference according to the predicted output load interval and the output load demand value, sets a plurality of load difference intervals, and generates a corresponding boiler correction decision based on the load difference intervals; The third processing module generates corresponding correction instructions according to the boiler correction decision and corrects the boiler operating parameters.

[0006] In some embodiments of the present invention, the first processing module is further used for: Score the boiler output load and generate the output load evaluation gradient value P, P = [P1, P2…Pi…Pn]; Where Pi is the output load score of the i-th level, and n represents the number of levels; Obtain historical data on boiler operation status and load change data; Classify the historical data of boiler operation status to generate heat production value Q, Q=[Q1,Q2…Qi…Qn], water level value H, H=[H1,H2…Hi…Hn], steam volume value S, S=[S1,S2…Si…Sn]; Among them, Qi represents the heat production value of the i-th sampling, Hi represents the water level value of the i-th sampling, Si represents the steam value of the i-th sampling, P'i represents the actual value of the output load evaluation of the i-th sampling, and n represents the number of sampling times; And according to the corresponding load change data, the output load is divided into intervals with an interval spacing of d, and the output load evaluation actual value set P' of the sampling period is generated, P'=[P'1,P'2…P'i…P'n]; Among them, P'i represents the actual value of the output load evaluation corresponding to the i-th interval, and n represents the number of intervals; Calculate the corresponding weights based on the boiler operation status history data and the output load evaluation actual value set P' during the sampling period to obtain the weight W1 of the heat production value Q, the weight W2 of the water level value H, and the weight W3 of the steam value S; Generate boiler output state evaluation prediction value P''; P''=W1*Q+W2*H+W3*S; Determined based on boiler output status evaluation prediction value P''.

[0007] In some embodiments of the present invention, calculating the corresponding weight includes: Create a training data set D, D = (X, Y); X is the matrix of input variables, X=(Q,H,S), Y is the vector of output variables, Y=P'; Calculate the error square sum E between the boiler output state evaluation prediction value P'' and the load evaluation actual value set P'; E= (Pi'−Pi'') 2 = (Pi'−(W1*Qi+W2*Hi+W3*Si)) 2 Calculate the partial derivatives of W1, W2, and W3 respectively, and take the output value when the partial derivative is equal to 0 as the minimum value of the error square sum E; =−2 Qi*(Pi'−(W1*Qi+W2*Hi+W3*Si))=0 =−2 Hi*(Pi'−(W1*Qi+W2*Hi+W3*Si))=0 =−2 Si*(Pi'−(W1*Qi+W2*Hi+W3*Si))=0 After simplification, the equation in matrix form is: (X T X)w=X T Y Where X is the matrix of input variables, Y is the vector of output variables, and W is the weight vector (W1, W2, W3); Generate the weight vector W by inverting the matrix: W=(X T X) −1 X T Y The weight W1 of the heat production value Q, the weight W2 of the water level value H, and the weight W3 of the steam quantity value S are obtained.

[0008] In some embodiments of the present invention, the second processing module further includes: Determine the load difference according to the predicted output load interval and the output load demand value, set multiple load difference intervals, and generate corresponding boiler correction decisions based on the load difference intervals; Obtain the output load demand value interval R' and the predicted output load interval R, generate the load correction value R'', R''=R'-R; If R'' is positive, the first-level load adjustment instruction is executed; If R'' is negative, the secondary load regulation instruction is executed; If R'' is 0, the boiler operation status monitoring is maintained.

[0009] In some embodiments of the present invention, the primary load adjustment instruction is further used to: Obtain the remaining adjustment amount S' of the steam value and calculate the increment of the remaining adjustment amount S' of the steam value to the boiler output load p1; Increase in boiler output load p, generates the corresponding output load interval increment R1, at this time p= p1; like If R1≥|R''|, a steam valve adjustment instruction is generated to correct the steam valve parameters; like R1<|R''|, then calculate the increment of the remaining adjustment amount H' of the water level value to the boiler output load p2, Increase in boiler output load p, generates the corresponding output load interval increment R2, at this time p= p1+ p2; like If R2≥|R''|, a steam valve adjustment instruction and a water level adjustment instruction are generated to correct the steam valve parameters and the water level parameters; like R2<|R''|, the required heat production value first adjustment amount Q' is calculated, and the first combustion correction instruction is generated according to the required heat production value first adjustment amount Q'.

[0010] In some embodiments of the present invention, the secondary load adjustment instruction includes: Based on the load correction value R'', determine the reduction ∆p' of the boiler output load and calculate the second adjustment amount Q'' of the required heat production value. Q''=( p'-(W2*H+W3*S)) / W1; A second combustion correction instruction is generated according to the second adjustment amount Q″ of the required heat production value.

[0011] In some embodiments of the present invention, the first combustion correction instruction includes: Obtain historical data of combustion conditions, including: fuel supply data, powder delivery air volume data, nozzle angle data, and heating surface temperature data; Establish a heat generation condition control model, and modify the combustion chamber parameters based on the heat generation condition control model; The first adjustment amount Q' of the required heat production value is input to the heat production condition control model, and the preheating combustion correction parameter, the nozzle angle correction parameter and the air powder amount correction parameter are output.

[0012] In some embodiments of the present invention, the preheating combustion correction parameters include: Preheating combustion correction parameters, used to adjust fuel preheating time and fuel quantity; By correcting the fuel preheating time, the time for the fuel to be converted from a solid state to a gas-like fuel is controlled, and the gas-like fuel is delivered to the ventilation duct subsystem.

[0013] In some embodiments of the present invention, the ventilation duct subsystem includes: Fan driver, air volume valve, and delivery pipeline; The conveying pipeline is provided with spiral blades inside to mix the gas fuel and the pulverized coal; Distributed optical fiber sensors are installed outside the pipeline to monitor pipeline leakage.

[0014] In some embodiments of the present invention, the nozzle angle correction parameters include: The fuel supply and air volume at different fuel nozzle injection angles and speeds are determined through the historical parameters of the boiler operating status. The control unit monitors the working status of the fuel nozzle in real time and corrects the injection angle and speed of the fuel nozzle according to the combustion condition level.

[0015] Compared with the prior art, the circulating fluidized bed boiler load response system based on adaptive control in the embodiment of the present invention has the following beneficial effects: By real-time monitoring of boiler operating status and load changes, an adaptive control model is established based on historical data and real-time data to improve the prediction accuracy of changing loads, keep the predicted value of boiler output power consistent with the demand value, and reduce deviations and response time.

[0016] By converting solid fuel into gas-like fuel, improving combustion efficiency and reducing incomplete combustion emissions, high-temperature preheating modification technology ensures full combustion of the fuel. High-temperature preheating modification of the fuel can greatly improve the boiler's climbing ability while reducing pollution to the environment.

[0017] Through the quantitative scoring mechanism and detailed grading method, the accuracy of boiler load performance evaluation is improved, making subsequent adjustments more targeted and scientific. The output load range is automatically adjusted according to actual load changes, enhancing the system's adaptability and response speed to dynamic working environments.

[0018] By accurately calculating and adjusting the boiler's steam value, water level and heat production value, the first-level load regulation instruction can quickly respond to load changes, ensuring that the boiler output is synchronized with grid demand, thereby improving the stability and responsiveness of the grid.

[0019] By real-time monitoring of the physical state of the fuel nozzle and the amount of fuel supplied, the fuel injection angle, speed and supply amount are ensured to be accurate, thus improving combustion efficiency and system safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 It is a structural diagram of a circulating fluidized bed boiler load response system based on adaptive control provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0021] The specific implementation of the present invention is further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0022] In the description of the present invention, 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 drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying 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 the present invention.

[0023] The terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, unless otherwise specified, "plurality" means two or more.

[0024] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0025] Embodiment 1: A circulating fluidized bed boiler load response system based on adaptive control, such as Figure 1 As shown, it includes: a data acquisition unit and a control unit; The data acquisition unit is used to obtain boiler operation status data and load change data; A control unit is used to establish a boiler control model, generate a boiler correction instruction according to boiler operation status data and load change data, and adjust the boiler output load according to the boiler correction instruction; The control unit also includes: A first processing module, used for generating a predicted output load interval of the current boiler according to the boiler operation status data and the load change data; The second processing module determines a load difference according to the predicted output load interval and the output load demand value, sets a plurality of load difference intervals, and generates a corresponding boiler correction decision based on the load difference intervals; The third processing module generates corresponding correction instructions according to the boiler correction decision and corrects the boiler operating parameters.

[0026] Embodiment 2: The first processing module is also used for: Score the boiler output load and generate the output load evaluation gradient value P, P = [P1, P2…Pi…Pn]; Where Pi is the output load score of the i-th level, and n represents the number of levels; Obtain historical data on boiler operation status and load change data; Classify the historical data of boiler operation status to generate heat production value Q, Q=[Q1,Q2…Qi…Qn], water level value H, H=[H1,H2…Hi…Hn], steam volume value S, S=[S1,S2…Si…Sn]; Among them, Qi represents the heat production value of the i-th sampling, Hi represents the water level value of the i-th sampling, Si represents the steam value of the i-th sampling, P'i represents the actual value of the output load evaluation of the i-th sampling, and n represents the number of sampling times; And according to the corresponding load change data, the output load is divided into intervals with an interval spacing of d, and the output load evaluation actual value set P' of the sampling period is generated, P'=[P'1,P'2…P'i…P'n]; Among them, P'i represents the actual value of the output load evaluation corresponding to the i-th interval, and n represents the number of intervals; Calculate the corresponding weights based on the boiler operation status history data and the output load evaluation actual value set P' during the sampling period to obtain the weight W1 of the heat production value Q, the weight W2 of the water level value H, and the weight W3 of the steam value S; Generate boiler output state evaluation prediction value P''; P''=W1*Q+W2*H+W3*S; Determined based on boiler output status evaluation prediction value P''.

[0027] In this embodiment, data collection and scoring: collect the operating data of the most recent week, record the boiler's heat output value Q, water level value H, and steam value S every 10 minutes, and score the output load based on the boiler's operating efficiency and fuel consumption to form an evaluation gradient value P.

[0028] Interval division: Divide the output load into 5% intervals, for example, 50%-55%, 55%-60%, etc.

[0029] Weight calculation: Based on the relationship between Q, H, S and score P' in each interval within a week, W1, W2, and W3 are calculated by the least squares method.

[0030] Prediction and analysis: Input the current Q, H, and S values ​​into the calculated weight model to predict the boiler output state prediction value P'' for the next hour.

[0031] Through the quantitative scoring mechanism and detailed grading method, the accuracy of boiler load performance evaluation is improved, making subsequent adjustments more targeted and scientific.

[0032] The output load range is automatically adjusted according to actual load changes, which enhances the system's adaptability and response speed to dynamic working environments.

[0033] The introduction of historical data and weight calculation makes the predicted value P'' closer to the actual situation and effectively guides future load adjustment strategies.

[0034] The calculation of weights ensures the reasonable configuration of key boiler parameters (such as calorific value, water level, and steam volume) in complex environments, thereby achieving optimal resource utilization and optimal operating status.

[0035] Continuously monitor and analyze the changing trends of output load and its related parameters, identify potential risks in advance, assist preventive maintenance, and reduce unplanned downtime.

[0036] Through fine management and intelligent prediction, the system can make timely load adjustments, avoid energy waste, and improve overall operating efficiency.

[0037] Real-time data analysis and dynamic adjustments help maintain the safe operating range of the boiler and prevent safety accidents caused by abnormal parameters.

[0038] Embodiment 3: Calculate the corresponding weights, including: Create a training data set D, D = (X, Y); X is the matrix of input variables, X=(Q,H,S), Y is the vector of output variables, Y=P'; Calculate the error square sum E between the boiler output state evaluation prediction value P'' and the load evaluation actual value set P'; E= (Pi'−Pi'') 2 = (Pi'−(W1*Qi+W2*Hi+W3*Si)) 2 Calculate the partial derivatives of W1, W2, and W3 respectively, and take the output value when the partial derivative is equal to 0 as the minimum value of the error square sum E; =−2 Qi*(Pi'−(W1*Qi+W2*Hi+W3*Si))=0 =−2 Hi*(Pi'−(W1*Qi+W2*Hi+W3*Si))=0 =−2 Si*(Pi'−(W1*Qi+W2*Hi+W3*Si))=0 After simplification, the equation in matrix form is: (X T X)w=X T Y Where X is the matrix of input variables, Y is the vector of output variables, and W is the weight vector (W1, W2, W3); Generate the weight vector W by inverting the matrix: W=(X T X) −1 X T Y The weight W1 of the heat production value Q, the weight W2 of the water level value H, and the weight W3 of the steam quantity value S are obtained.

[0039] In this embodiment, Input variable matrix X: Heat output Q (unit: kW): [1500, 1600, 1700, 1800, 1900] Water level value H (unit: cm): [45, 50, 55, 60, 65] Steam volume value S (unit: kg / h): [500, 550, 600, 650, 700] Output variable vector Y (output load evaluation actual value set P'): [60, 65, 70, 75, 80] Calculate the error sum of squares E First, we assume the initial weights W1=1, W2=1, W2=1. Then, we calculate the predicted value P'' and find the sum of squared errors E.

[0040] Take the first set of data as an example: Prediction value P'' = W11500 + W245 + W3*500 Actual value P' = 60 The error sum of squares E = (60 - P'')² We repeat this calculation for each set of data.

[0041] Solving for weight W Method for finding the minimum value using partial derivatives: Calculate the partial derivatives of E with respect to W1, W2, and W3 and set them equal to 0.

[0042] Simplify the equation to get the matrix form: (X T X)W = X T Y Compute the product of the inverse matrix (XTX) and XTY.

[0043] Implementation steps Construct matrix X and vector Y: X = [[1500, 45, 500], [1600, 50, 550], [1700, 55, 600], [1800, 60,650], [1900, 65, 700]] Y = [60, 65, 70, 75, 80] Construct the equation: X T X = [[Σ(Qi²), Σ(QiHi), Σ(QiSi)], [Σ(QiHi), Σ(Hi²), Σ(HiSi)], [Σ(QiSi), Σ(HiSi), Σ(Si²)]] X T Y = [Σ(P'iQi), Σ(P'iHi), Σ(P'iSi)] Compute the inverse matrix and the product: W = (X T X)⁻¹X T Y Solving for W: W1 (heat value weight) = 0.003 W2 (water level weight) = 0.05 W3 (steam value weight) = 0.0015 This means that when predicting the boiler output state evaluation predicted value P'', the influence of the heat production value Q is small, while the influence of the water level value H is large, and the influence of the steam volume value S is between the two.

[0044] Embodiment 4: The second processing module also includes: Determine the load difference according to the predicted output load interval and the output load demand value, set multiple load difference intervals, and generate corresponding boiler correction decisions based on the load difference intervals; Obtain the output load demand value interval R' and the predicted output load interval R, generate the load correction value R'', R''=R'-R; If R'' is positive, the first-level load adjustment instruction is executed; If R'' is negative, the secondary load regulation instruction is executed; If R'' is 0, the boiler operation status monitoring is maintained.

[0045] Embodiment 5: The primary load regulation command is also used for: Obtain the remaining adjustment amount S' of the steam value and calculate the increment of the remaining adjustment amount S' of the steam value to the boiler output load p1; Increase in boiler output load p, generates the corresponding output load interval increment R1, at this time p= p1; like If R1≥|R''|, a steam valve adjustment instruction is generated to correct the steam valve parameters; like R1<|R''|, then calculate the increment of the remaining adjustment amount H' of the water level value to the boiler output load p2, Increase in boiler output load p, generates the corresponding output load interval increment R2, at this time p= p1+ p2; like If R2≥|R''|, a steam valve adjustment instruction and a water level adjustment instruction are generated to correct the steam valve parameters and the water level parameters; like R2<|R''|, the required heat production value first adjustment amount Q' is calculated, and the first combustion correction instruction is generated according to the required heat production value first adjustment amount Q'.

[0046] In this embodiment, by accurately calculating and adjusting the steam value, water level value and heat production value of the boiler, the first-level load regulation instruction can quickly respond to load changes, ensuring that the boiler output is synchronized with the grid demand, thereby improving the stability and responsiveness of the grid. Through real-time monitoring of the boiler's operating status and historical data analysis, the first-level load adjustment instruction can optimize the control strategy, achieve more refined and efficient load distribution, and improve the operating efficiency of the boiler. The first-level load regulation instruction can improve the accuracy of load regulation and reduce energy waste and equipment wear caused by improper regulation through algorithm optimization and parameter adjustment. The first-level load regulation instruction allows the boiler to be flexibly adjusted under different operating conditions. Whether it is operating at full load or part load, it can maintain a high degree of regulation flexibility and adapt to the variability of the grid load. By optimizing the operating parameters of the boiler, the first-level load regulation instruction helps to reduce fuel consumption and emissions, meeting the current requirements of energy conservation and environmental protection. The implementation of the first-level load regulation instruction is usually accompanied by the application of an automated control system, which not only improves the execution efficiency of the regulation instruction, but also reduces the workload of operators and improves the automation level of the entire system.

[0047] Embodiment 6: Secondary load adjustment instructions, including: Based on the load correction value R'', determine the reduction ∆p' of the boiler output load and calculate the second adjustment amount Q'' of the required heat production value. Q''=( p'-(W2*H+W3*S)) / W1; A second combustion correction instruction is generated according to the second adjustment amount Q″ of the required heat production value.

[0048] Embodiment 7: The first combustion correction instruction includes: Obtain historical data of combustion conditions, including: fuel supply data, powder delivery air volume data, nozzle angle data, and heating surface temperature data; Establish a heat generation condition control model, and modify the combustion chamber parameters based on the heat generation condition control model; The first adjustment amount Q' of the required heat production value is input to the heat production condition control model, and the preheating combustion correction parameter, the nozzle angle correction parameter and the air powder amount correction parameter are output.

[0049] Embodiment 8: Preheat combustion correction parameters, including: Preheating combustion correction parameters, used to adjust fuel preheating time and fuel quantity; By correcting the fuel preheating time, the time for the fuel to be converted from a solid state to a gas-like fuel is controlled, and the gas-like fuel is delivered to the ventilation duct subsystem.

[0050] In this embodiment, the fuel preheating time is corrected: This refers to adjusting the fuel preheating time according to the ambient temperature, fuel type and specific conditions of the burner. The length of the preheating time directly affects the conversion efficiency of the fuel from solid to gas. If the preheating time is too short, the fuel may not be fully converted, resulting in incomplete combustion; conversely, too long a preheating time may cause energy waste.

[0051] Fuel quantity correction: adjust the fuel supply according to the actual needs of the combustion chamber and the combustion efficiency. The correction of the fuel quantity needs to take into account the temperature and pressure of the combustion chamber and the emission standards after combustion. The appropriate fuel quantity can not only improve the combustion efficiency, but also reduce the emission of harmful substances.

[0052] Ventilation duct subsystem parameter adjustment: The ventilation duct subsystem is the key to transporting gaseous fuels. The adjustment of its parameters (such as ventilation volume, ventilation speed, etc.) directly affects the fuel transportation efficiency and combustion stability. The ventilation duct subsystem needs to ensure uniform distribution of fuel to avoid incomplete fuel combustion due to poor local ventilation.

[0053] Embodiment 9: Ventilation duct subsystem, including: Fan driver, air volume valve, and delivery pipeline; The conveying pipeline is provided with spiral blades inside to mix the gas fuel and the pulverized coal; Distributed optical fiber sensors are installed outside the pipeline to monitor pipeline leakage.

[0054] In this embodiment, spiral blades are provided in the delivery pipeline, and distributed optical fiber sensors are arranged on the periphery of the pipeline to monitor whether the pipeline is leaking.

[0055] In this embodiment, the air volume and wind speed requirements are determined by calculating the required air volume and wind speed according to the combustion state and requirements of the fuel nozzles.

[0056] Fan drive and air volume valve adjustment: The control unit adjusts the fan speed and air volume valve opening according to demand.

[0057] Function of spiral blades: Ensure that fuel and air are evenly mixed in the delivery pipeline to improve combustion efficiency.

[0058] Leak detection and early warning: Distributed fiber optic sensors monitor pipeline status in real time and immediately sound an alarm if an abnormality is detected to prevent fuel leakage.

[0059] Embodiment 10: Nozzle angle correction parameters include: The fuel supply and air volume at different fuel nozzle injection angles and speeds are determined through the historical parameters of the boiler operating status. The control unit monitors the working status of the fuel nozzle in real time and corrects the injection angle and speed of the fuel nozzle according to the combustion condition level.

[0060] Finally, it should be noted that it is obvious that those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the present invention and its equivalent technology, the present invention is also intended to include these modifications and variations.

[0061] The above is only an example of implementation of the present invention, but it cannot be used to limit the scope of the present invention. Any structural changes made according to the present invention, as long as they do not lose the essence of the present invention, should be regarded as falling within the scope of protection of the present invention and being restricted. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working process and related instructions of the platform described above can refer to the corresponding process in the aforementioned platform embodiment, and will not be repeated here.

[0062] The term "comprising" or any other similar term is intended to cover a non-exclusive inclusion such that a process, platform, article, or apparatus / platform that comprises a list of elements includes not only those elements but also other elements not expressly listed or also includes elements inherent to such process, platform, article, or apparatus / platform.

[0063] So far, the technical solutions of the present invention have been described in conjunction with the further embodiments shown in the accompanying drawings, but it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0064] The above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention.

Claims

1. A circulating fluidized bed boiler load response system based on adaptive control, characterized in that: include: Data acquisition unit, control unit; Wherein, the data acquisition unit is used to obtain boiler operation status data and load change data; A control unit is used to establish a boiler control model, generate a boiler correction instruction according to boiler operation status data and load change data, and adjust the boiler output load according to the boiler correction instruction; The control unit also includes: A first processing module, used for generating a predicted output load interval of the current boiler according to the boiler operation status data and the load change data; The second processing module determines the load difference value according to the predicted output load interval and the output load demand value; It also includes and sets a plurality of load difference intervals, and generates corresponding boiler correction decisions based on the load difference intervals; The third processing module generates corresponding correction instructions according to the boiler correction decision and corrects the boiler operating parameters.

2. The circulating fluidized bed boiler load response system based on adaptive control according to claim 1, characterized in that: The first processing module is also used for: Score the boiler output load and generate the output load evaluation gradient value P, P = [P1, P2…Pi…Pn]; Where Pi is the output load score of the i-th level, and n represents the number of levels; Obtain boiler operating status historical data and load change data; Classify the historical data of boiler operation status to generate heat production value Q, Q=[Q1,Q2…Qi…Qn], water level value H, H=[H1,H2…Hi…Hn], steam volume value S, S=[S1,S2…Si…Sn]; Among them, Qi represents the heat production value of the i-th sampling, Hi represents the water level value of the i-th sampling, Si represents the steam value of the i-th sampling, P'i represents the actual value of the output load evaluation of the i-th sampling, and n represents the number of sampling times; And according to the corresponding load change data, the output load is divided into intervals with an interval spacing of d, and the output load evaluation actual value set P' of the sampling period is generated, P'=[P'1,P'2…P'i…P'n]; Among them, P'i represents the actual value of the output load evaluation corresponding to the i-th interval, and n represents the number of intervals; Calculate the corresponding weights based on the boiler operation status history data and the output load evaluation actual value set P' during the sampling period to obtain the weight W1 of the heat production value Q, the weight W2 of the water level value H, and the weight W3 of the steam value S; Generate boiler output state evaluation prediction value P''; P''=W1*Q+W2*H+W3*S; Determined based on boiler output status evaluation prediction value P''.

3. The circulating fluidized bed boiler load response system based on adaptive control according to claim 2, characterized in that: The calculation of corresponding weights is also used for: Create a training data set D, D = (X, Y); X is the matrix of input variables, X=(Q,H,S), Y is the vector of output variables, Y=P'; Calculate the error square sum E between the boiler output state evaluation prediction value P'' and the load evaluation actual value set P'; E= (Pi'−Pi'') 2 = (Pi'−(W1*Qi+W2*Hi+W3*Si)) 2 Calculate the partial derivatives of W1, W2, and W3 respectively, and take the output value when the partial derivative is equal to 0 as the minimum value of the error square sum E; =−2 Qi*(Pi'−(W1*Qi+W2*Hi+W3*Si))=0 =−2 Hi*(Pi'−(W1*Qi+W2*Hi+W3*Si))=0 =−2 Si*(Pi'−(W1*Qi+W2*Hi+W3*Si))=0 After simplification, the equation in matrix form is: (X T X)w=X T Y Where X is the matrix of input variables, Y is the vector of output variables, and W is the weight vector (W1, W2, W3); Generate the weight vector W by inverting the matrix: W=(X T X) −1 X T Y The weight W1 of the heat production value Q, the weight W2 of the water level value H, and the weight W3 of the steam quantity value S are obtained.

4. The circulating fluidized bed boiler load response system based on adaptive control according to claim 1, characterized in that: The second processing module is also used for: Determine the load difference according to the predicted output load interval and the output load demand value, set multiple load difference intervals, and generate corresponding boiler correction decisions based on the load difference intervals; Obtain the output load demand value interval R' and the predicted output load interval R, generate the load correction value R'', R''=R'-R; If R'' is positive, the first-level load adjustment instruction is executed; If R'' is negative, the secondary load adjustment instruction is executed; If R'' is 0, the boiler operation status monitoring is maintained.

5. The circulating fluidized bed boiler load response system based on adaptive control according to claim 4, characterized in that: The first-level load adjustment instruction is also used to: Obtain the remaining adjustment amount S' of the steam value and calculate the increment of the remaining adjustment amount S' of the steam value to the boiler output load p1; Increase in boiler output load p, generates the corresponding output load interval increment R1, at this time p= p1; like If R1≥|R''|, a steam valve adjustment instruction is generated to correct the steam valve parameters; like R1<|R''|, then calculate the increment of the remaining adjustment amount H' of the water level value to the boiler output load p2, Increase in boiler output load p, generates the corresponding output load interval increment R2, at this time p= p1+ p2; like If R2≥|R''|, a steam valve adjustment instruction and a water level adjustment instruction are generated to correct the steam valve parameters and the water level parameters; like R2<|R''|, the required heat production value first adjustment amount Q' is calculated, and the first combustion correction instruction is generated according to the required heat production value first adjustment amount Q'.

6. The circulating fluidized bed boiler load response system based on adaptive control according to claim 5, characterized in that: The first combustion correction instruction is further used to: Obtain historical data of combustion conditions, including: fuel supply data, powder delivery air volume data, nozzle angle data, and heating surface temperature data; Establish a heat generation condition control model, and modify the combustion chamber parameters based on the heat generation condition control model; The first adjustment amount Q' of the required heat production value is input to the heat production condition control model, and the preheating combustion correction parameter, the nozzle angle correction parameter and the air powder amount correction parameter are output.

7. The circulating fluidized bed boiler load response system based on adaptive control according to claim 4, characterized in that: The secondary load adjustment instruction is also used to: Based on the load correction value R'', determine the reduction ∆p' of the boiler output load and calculate the second adjustment amount Q'' of the required heat production value. Q’’=( p’-(W2*H+W3*S)) / W1; A second combustion correction instruction is generated according to the second adjustment amount Q″ of the required heat production value.

8. The circulating fluidized bed boiler load response system based on adaptive control according to claim 6, characterized in that: The preheat combustion correction parameter is also used for: Preheating combustion correction parameters, used to adjust fuel preheating time and fuel quantity; By correcting the fuel preheating time, the time for the fuel to be converted from a solid state to a gas-like fuel is controlled, and the gas-like fuel is delivered to the ventilation duct subsystem.

9. The circulating fluidized bed boiler load response system based on adaptive control according to claim 8, characterized in that: The ventilation duct subsystem also includes: Fan driver, air volume valve, and delivery pipeline; The conveying pipeline is provided with spiral blades inside, and the spiral blades are used to mix the gas fuel and the coal powder; A distributed optical fiber sensor is arranged outside the delivery pipeline, and the distributed optical fiber sensor is used to monitor pipeline leakage.

10. The circulating fluidized bed boiler load response system based on adaptive control according to claim 8, characterized in that: The nozzle angle correction parameter is also used for: The fuel supply and air volume at different fuel nozzle injection angles and speeds are determined through the historical parameters of the boiler operating status. The control unit monitors the working status of the fuel nozzle in real time and corrects the injection angle and speed of the fuel nozzle according to the required calorific value adjustment level.

Images