Method for controlling steam temperature at outlet of waste heat boiler of waste incineration power plant
Through integrated sensor and grouping model fitting and combined with MPC algorithm to optimize the control system, the problem of insufficient steam temperature control accuracy of waste heat boiler outlet of waste incineration power plants is solved, and more stable and efficient control is achieved, improving the overall operating efficiency and economic benefits of the system .
Patent Information
- Application Number
- CN202411157239.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-22
- Publication Date
- 2024-11-26
AI Technical Summary
The steam temperature control accuracy of the waste heat boiler outlet of waste incineration power plants is insufficient, and traditional control strategies are difficult to adapt to the rapid changes in combustion conditions, resulting in unstable steam temperature and affecting the power generation quality and equipment life.
Integrate a variety of sensors to collect real-time boiler data, perform preprocessing and grouping model fitting, build an intelligent control architecture, optimize the control system based on the MPC algorithm, and realize fine control of the outlet steam temperature.
It improves control accuracy and reaction speed, enhances system stability and prediction capabilities, improves energy utilization efficiency and reduces emissions.
Smart Images

Figure CN119022283A_ABST
Abstract
Description
Technical Field
[0001] The invention relates to the field of automatic control of electric power production, and in particular to a method for controlling the outlet steam temperature of a waste heat boiler of a garbage incineration power plant. Background Art
[0002] The technology of waste incineration power generation is constantly developing. As a core component, the control of the outlet steam temperature of the waste heat boiler directly affects the power generation efficiency and equipment safety. Traditional control strategies such as PID control and manual adjustment have limited control accuracy in the face of fluctuations in waste composition and calorific value. Although the temperature of the cooling water control can be adjusted, it responds slowly and is difficult to adapt to rapidly changing combustion conditions, resulting in unstable steam temperature, affecting the power generation quality and equipment life. Over-reliance on manual operation not only increases the manpower burden, but also makes it difficult to ensure control accuracy and consistency under complex working conditions, limiting the improvement of the automation level of power plants and the exploration of energy efficiency potential. Summary of the invention
[0003] In view of the above existing problems, the present invention is proposed.
[0004] Therefore, the present invention provides a method for controlling the outlet steam temperature of a waste heat boiler of a waste incineration power plant, which solves the problem of insufficient control accuracy of the outlet steam temperature of a waste heat boiler of a waste incineration power plant.
[0005] In order to solve the above technical problems, the present invention provides the following technical solutions:
[0006] In a first aspect, an embodiment of the present invention provides a method for controlling the outlet steam temperature of a waste heat boiler of a waste incineration power plant, which includes integrating multiple sensors, collecting real-time data of the boiler, and performing preprocessing;
[0007] Based on the real-time data of pre-processed boilers, group model fitting is performed;
[0008] Based on the group fitting model, a synthetic outlet steam temperature prediction model is developed;
[0009] Build an intelligent control architecture based on the outlet steam temperature prediction model;
[0010] Optimize existing control systems based on intelligent control architecture;
[0011] Based on the optimized control system, the outlet steam temperature is controlled.
[0012] As a preferred solution of the method for controlling the outlet steam temperature of the waste heat boiler of a waste incineration power plant described in the present invention, the multiple sensors include temperature sensors, pressure sensors and flow sensors; the real-time data of the boiler collected include recycled flue gas flow R, leachate backspray volume L, cooling water volume C, main steam flow M, garbage feed volume W, boiler primary fan air inlet volume P, boiler secondary fan air inlet volume S and outlet steam temperature O.
[0013] As a preferred solution of the method for controlling the outlet steam temperature of the waste heat boiler of a waste incineration power plant according to the present invention, the real-time data of the boiler is collected and pre-processed, and the specific steps are as follows:
[0014] The collected real-time boiler data is cleaned using the Z-score method, timestamps are added, and sliding window averaging is used to reduce noise.
[0015] As a preferred solution of the method for controlling the outlet steam temperature of the waste heat boiler of a waste incineration power plant according to the present invention, wherein: based on the waste feed amount W, the primary fan air intake amount P and the secondary fan air intake amount S, a combustion efficiency model is established to calculate the combustion efficiency O CEI , expressed as,
[0016]
[0017] In the formula, O CEI is the combustion efficiency, α1 is the intercept of the model, β 11 is the coefficient of the Gaussian kernel function, W is the amount of garbage input, μ w is the average value of the waste feed volume W, σ w is the standard deviation of the mean value of the waste feed volume W, β 12 is the coefficient of the logarithmic function of the primary fan air volume P, where P is the primary fan air volume of the boiler, and β 13 is the coefficient of the square root function of the secondary fan air volume S, S is the air volume of the boiler secondary fan, and ω1(t) is the dynamic weight function;
[0018] Based on the desuperheating water volume C and the main steam flow rate M, a temperature regulation model is established to calculate the temperature regulation range O TRG It is expressed as,
[0019]
[0020] In the formula, O TRG is the temperature adjustment range, α2 is the intercept of the model, β 21 is the coefficient of the power function of the ratio of the desuperheating water volume C and the main steam flow rate M, where C is the desuperheating water volume, M is the main steam flow rate, Φ is the exponent, and β 22 is the coefficient of the cube root function of the cooling water volume C, ω2(t) is the dynamic weight function;
[0021] The heat recovery model is established based on the recirculated flue gas flow rate R and the leachate back injection volume L, and the heat recovery range O is calculated. HRG It is expressed as,
[0022] O HRG =α3+β 31 sin(R)+β 32 tanh(L)+ω3(t)·sin(R)·tanh(L);
[0023] In the formula, O HRG is the heat recovery range, α3 is the intercept of the model, β 31 is the coefficient of the sinusoidal function of the recirculating flue gas flow rate R, R is the recirculating flue gas flow rate, β 32 is the coefficient of the hyperbolic tangent function of the leachate backspray volume L, L is the leachate backspray volume, and ω3 is the dynamic weight function.
[0024] As a preferred solution of the method for controlling the outlet steam temperature of the waste heat boiler of a waste incineration power plant described in the present invention, wherein: based on the group fusion model, a synthesis outlet steam temperature prediction model is performed, and the specific steps are as follows:
[0025] Weighted Composite O CEI , O TRG and O HRG , the outlet steam temperature prediction model is synthesized, and the predicted outlet steam temperature OT is expressed as,
[0026] OT=w1O CEI +w2O TRG +w3O HRG +∈;
[0027] Where OT is the predicted outlet steam temperature, w1 is a fixed weight, w2 is a fixed weight, w3 is a fixed weight, ε is the error term, O CEI is the output of the combustion efficiency model, O TRG is the output of the temperature regulation model, O HRG is the output of the heat recovery model.
[0028] As a preferred solution of the method for controlling the outlet steam temperature of the waste heat boiler of a waste incineration power plant according to the present invention, an intelligent control architecture is constructed based on the outlet steam temperature prediction model, and the specific steps are as follows:
[0029] Use the MPC algorithm to build an intelligent control architecture and integrate the outlet steam temperature prediction model;
[0030] In the MPC algorithm, the cost function J is defined as:
[0031]
[0032] Where J represents the total cost that needs to be minimized in the MPC algorithm, and N p represents the number of time steps of the MPC algorithm in predicting future outputs, w dev Represents the weight of the output bias term, OT k represents the predicted value of the outlet steam temperature at the kth time step, SP represents the target value of the outlet steam temperature, and N c represents the number of time steps based on which the MPC algorithm optimizes the control input, w s represents the weight of the control input change rate term, Δu i,k represents the change of the i-th control variable between the k-th and k+1-th time steps;
[0033] Define operating constraints, including the recirculated flue gas flow rate R MPC , Leachate back spray volume L MPC , cooling water volume C MPC , Main steam flow M MPC , garbage feed amount W MPC , Boiler primary fan air intake volume P MPC , Boiler secondary fan air intake volume S MPC and outlet steam temperature O MPC .
[0034] As a preferred solution of the method for controlling the outlet steam temperature of the waste heat boiler of a waste incineration power plant according to the present invention, the existing control system is optimized by using the constructed intelligent control architecture, and the specific steps are as follows:
[0035] The intelligent control architecture is integrated into the control system, which contains multiple control loops;
[0036] Each control loop in the control system contains a main controller and a backup controller;
[0037] The recirculated flue gas flow control loop is defined as RFL, using a variable frequency fan, which adjusts the frequency of the variable frequency drive fan according to the MPC command;
[0038] The leachate back-spray control loop is defined as LSP, and the actuator uses a metering pump, whose speed is controlled by the MPC instruction;
[0039] The cooling water control loop is defined as CTW, the actuator uses an electric regulating valve, and the MPC instruction determines the valve opening;
[0040] The main steam flow control loop is defined as MSV, the actuator uses an electric control valve, and the MPC instruction determines the valve opening;
[0041] The waste feed quantity control loop is defined as WTF, the actuator uses a feed conveyor with an adjustable speed motor, and the MPC command adjusts the motor speed;
[0042] The boiler primary fan control loop is defined as PFF, and the actuator uses a variable frequency fan, which adjusts the frequency of the variable frequency drive fan according to the MPC command;
[0043] The boiler secondary fan control loop is defined as SSF, and the actuator uses a variable frequency fan to adjust the variable frequency drive fan frequency according to the MPC command.
[0044] As a preferred solution of the method for controlling the outlet steam temperature of the waste heat boiler of a waste incineration power plant according to the present invention, the control variable of each control loop in the output instruction of the MPC algorithm is defined as R MPC , L MPC , C MPC 、M MPC , W MPC , P MPC and S MPC , corresponding to RFL, LSP, CTW, MSV, WTF, PFF and SSF control loops respectively;
[0045] The optimized control system continuously receives real-time data from the boiler, forming a real-time feedback mechanism;
[0046] The real-time data of the boiler is input into the optimized control system. The MPC algorithm in the system calculates the control variable R in the next control cycle according to the current operating conditions and the preset target value. MPC , L MPC , C MPC 、M MPC , W MPC , P MPC and S MPC The set point;
[0047] The main controller adjusts the actuators in each control loop according to the output instructions of the MPC algorithm;
[0048] The backup controller is on standby and will take over immediately if the main controller fails;
[0049] In the MPC algorithm, the expected value range and tolerance limit of the outlet steam temperature O are set as the main control target of the system;
[0050] When the outlet steam temperature deviates from the set value, the intelligent control architecture automatically adjusts R according to the influence of each control variable on the temperature predicted by the dynamic model. MPC , L MPC , C MPC 、M MPC , W MPC , P MPCand S MPC The set point;
[0051] The adjustment process involves fine control of the recirculated flue gas flow rate R, leachate back-spray volume L, desuperheating water volume C, garbage feed volume W, and the air intake volumes P and S of the primary and secondary fans;
[0052] By utilizing the rolling optimization characteristics of the MPC algorithm, the set values of each control loop are re-evaluated at regular control cycles to adapt to changes in external conditions such as combustion conditions and changes in garbage properties.
[0053] In a second aspect, an embodiment of the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, it implements any step of the method for controlling the outlet steam temperature of the waste heat boiler of a waste incineration power plant as described in the first aspect of the present invention.
[0054] In a third aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the method for controlling the outlet steam temperature of a waste heat boiler of a waste incineration power plant as described in the first aspect of the present invention.
[0055] The beneficial effects of the present invention are:
[0056] By integrating multiple sensors and collecting pre-processed boiler real-time data, comprehensive monitoring of the boiler's operating status is achieved, which can respond to various operating condition changes in a timely manner, improve the system's reaction speed and accuracy, and ultimately achieve the beneficial effect of improving the stability of boiler operation.
[0057] By fitting the group model, three sub-models of combustion efficiency, temperature regulation and heat recovery were established, which refined the various factors affecting the steam temperature, making the control more refined, thereby improving the pertinence and efficiency of the control strategy, and ultimately achieving the beneficial effect of optimizing the steam temperature control accuracy.
[0058] By synthesizing the outlet steam temperature prediction model and integrating the group models, a comprehensive prediction capability is formed, which can predict the outlet steam temperature more accurately and enable the control system to make adjustments in advance to avoid temperature fluctuations, ultimately achieving the beneficial effect of enhancing the system's prediction capability and stability.
[0059] By building an intelligent control architecture and optimizing the control system, the MPC algorithm is adopted to achieve rolling optimization of control variables. It can not only quickly respond to changes in operating conditions, but also balance long-term goals and short-term control, ultimately achieving the beneficial effect of improving the overall operating efficiency and economic benefits of the system.
[0060] By controlling the outlet steam temperature in real time based on the optimized control system, a closed-loop control mechanism is formed, which can quickly adjust the control strategy according to real-time data, ensuring the stability of the outlet steam temperature, and ultimately achieving the beneficial effects of improving energy efficiency and reducing emissions. BRIEF DESCRIPTION OF THE DRAWINGS
[0061] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.
[0062] Figure 1 This is a flow chart of the method for controlling the outlet steam temperature of the waste heat boiler of a waste incineration power plant in Example 1.
[0063] Figure 2 This is a diagram for determining whether to switch to a standby PID controller in Example 1. DETAILED DESCRIPTION
[0064] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.
[0065] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.
[0066] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.
[0067] Example 1, reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, provides a method for controlling the outlet steam temperature of a waste heat boiler of a waste incineration power plant, comprising the following steps:
[0068] S1. Integrate multiple sensors to collect real-time boiler data and perform preprocessing, including the following steps:
[0069] A variety of sensors include temperature sensors, pressure sensors and flow sensors; real-time boiler data collected include recirculating flue gas flow R, leachate back-spray volume L, cooling water volume C, main steam flow M, garbage feed volume W, boiler primary fan air inlet volume P, boiler secondary fan air inlet volume S and outlet steam temperature O.
[0070] The recirculated flue gas flow rate R and the leachate back-spray volume L coordinately regulate the combustion conditions to improve efficiency and reduce emissions; the cooling water volume C and the main steam flow rate M ensure that the steam temperature is appropriate, maintain equipment safety and stable power output; the garbage feed volume W, the boiler primary fan air inlet volume P and the boiler secondary fan air inlet volume S are precisely controlled to ensure stable combustion, affecting energy output and waste treatment; the outlet steam temperature O is monitored to ensure system efficiency.
[0071] The collected real-time boiler data is cleaned using the Z-score method, timestamps are added, and sliding window averaging is used to reduce noise. This enables the model to be trained based on more accurate information, thereby improving prediction accuracy and control performance. Using Z-score, data can be standardized and outliers can be detected, ensuring that model training is based on high-quality data and improving prediction accuracy. Applying sliding window averaging reduces noise and smoothes data sequences, allowing the model to capture trends more accurately and enhance the stability of prediction and control. Timestamps ensure that data is arranged in chronological order, which is crucial for time series analysis. It helps the model understand the dynamic changes of data and achieve more accurate real-time control and prediction.
[0072] S2. Based on the real-time data of the pre-processed boiler, a grouping model is fitted, including the following steps:
[0073] Based on the garbage feed volume W, the primary fan air volume P and the secondary fan air volume S, a combustion efficiency model is established to calculate the combustion efficiency O CEI , expressed as,
[0074]
[0075] In the formula, O CEI is the combustion efficiency, α1 is the intercept of the model, which can be determined by the least squares method, and β 11 is the coefficient of the Gaussian kernel function, reflecting the nonlinear effect of the garbage feed amount W on the combustion efficiency, which can be estimated by the kernel regression method in machine learning. W is the garbage feed amount, μ w is the average value of the waste feed volume W, σ w is the standard deviation of the mean value of the waste feed volume W, β 12 is the coefficient of the logarithmic function of the primary fan air volume P, which indicates the contribution of P to the combustion efficiency. It can also be obtained through regression analysis. P is the air volume of the boiler primary fan, β 13It is the coefficient of the square of the secondary fan air volume S, reflecting the influence of S on the combustion efficiency, which can be obtained through regression analysis. S is the air volume of the boiler secondary fan, and ω1(t) is the dynamic weight function. Time series analysis is used to reflect the dynamic characteristics of the system that change over time.
[0076] Based on the desuperheating water volume C and the main steam flow rate M, a temperature regulation model is established to calculate the temperature regulation range O TRG It is expressed as,
[0077]
[0078] In the formula, O TRG is the temperature adjustment range, α2 is the intercept of the model, determined by the least squares method, and β 21 is the coefficient of the power function of the ratio of the desuperheating water volume C and the main steam flow rate M, which is solved using the gradient descent method. C is the desuperheating water volume, M is the main steam flow rate, Φ is the exponent, and β 22 It is the coefficient of the cube root function of the cooling water volume C. It is necessary to first perform a cube root transformation on the cooling water volume C and solve it through linear regression analysis. ω2(t) is a dynamic weight function, which is solved using time series analysis methods such as ARIMA, state space model or LSTM to capture the dynamic characteristics that change over time.
[0079] The heat recovery model is established based on the recirculated flue gas flow rate R and the leachate back injection volume L, and the heat recovery range O is calculated. HRG It is expressed as,
[0080] O HRG =α3+β 31 sin(R)+β 32 tanh(L)+ω3(t)·sin(R)·tanh(L);
[0081] In the formula, O HRG is the heat recovery range, α3 is the intercept of the model, determined by the least squares method, and β 31 is the coefficient of the sinusoidal function of the recirculating flue gas flow rate R, which is solved using the gradient descent method. R is the recirculating flue gas flow rate, β 32 is the coefficient of the hyperbolic tangent function of the leachate backwash volume L, which is solved using the gradient descent method. L is the leachate backwash volume, and ω3 is the dynamic weight function, which relies on time series analysis techniques such as ARIMA, state space model or LSTM to reflect the dynamic weight that changes over time.
[0082] S3, based on the group fitting model, synthesizing the outlet steam temperature prediction model, including the following steps:
[0083] Based on the group fusion model, the outlet steam temperature prediction model is synthesized. The specific steps are as follows: CEI, O TRG and O HRG , the outlet steam temperature prediction model is synthesized, and the predicted outlet steam temperature OT is expressed as,
[0084] OT=w1O CEI +w2O TRG +w3O HRG +∈;
[0085] Where OT is the predicted outlet steam temperature, which combines the prediction results of the three grouping models to provide a more comprehensive temperature prediction, and w1 is a fixed weight used to adjust O CEI Contribution to OT, w2 is a fixed weight used to adjust O TRG Contribution to OT, w3 is a fixed weight used to adjust O HRG The contribution to OT, ε is the error term, reflecting the difference between the model prediction and the actual outlet steam temperature, O CEI is the output of the combustion efficiency model, O TRG is the output of the temperature regulation model, O HRG is the output of the heat recovery model.
[0086] The solution of fixed weights w1, w2, w3 is a key step, which determines the relative importance of each grouping model in the final composite model. The selection of weights should be based on the performance and reliability of each model in predicting the outlet steam temperature. The following is a method to determine the weights:
[0087] Independent Evaluation of Combustion Efficiency Model O CEI , Temperature Regulation Model O TRG and heat recovery model O HRG The prediction performance of the model can be calculated by calculating the mean square error (MSE), root mean square error (RMSE) or coefficient of determination (R 2 ) and other statistics; preliminarily set the values of w1, w2, and w3. For example, a preliminary allocation can be made based on the performance indicators of the model, and a model with better performance is given a higher weight; use an optimization algorithm
[0088] (such as gradient descent, genetic algorithm or particle swarm optimization, etc.) to iteratively adjust the weights to minimize the prediction error of the synthetic model OT. Specifically, a loss function (such as MSE or RMSE) can be defined, and w1, w2, w3 can be optimized as variables until a weight combination that minimizes the loss function is found; in order to ensure the generalization ability of the weights, cross-validation techniques should be used to test the robustness of the weights. This involves dividing the dataset into a training set and a validation set, solving the weights with the training set, and then testing the model performance on the validation set; through the above steps, a set of weight values that minimize the prediction error can be determined, and these values are the final values of w1, w2, and w3.
[0089] S4. Based on the outlet steam temperature prediction model, an intelligent control architecture is constructed, including the following steps:
[0090] The MPC (Model Predictive Control) algorithm is a model-based control strategy that determines future control actions by solving an optimization problem based on the current state information and prediction model at each step. Its core lies in rolling optimization, where the MPC algorithm re-solves the optimization problem at each sampling moment and makes decisions based on the latest system state and prediction information; constraint processing, where the MPC algorithm can directly handle various operational constraints to ensure the feasibility of the control strategy; and dynamic optimization, where the MPC algorithm can optimize the entire control process, not just the immediate control effect, by defining cost functions and operational constraints.
[0091] In order to solve the optimization problem in the MPC algorithm, various numerical optimization techniques can be used, such as quadratic programming, linear programming, interior point method or sequential quadratic programming, etc. This solution uses quadratic programming.
[0092] In the MPC algorithm, the cost function J is defined as:
[0093]
[0094] Where J is the cost function in the MPC algorithm, which belongs to the quadratic programming cost function, and N p represents the number of time steps of the MPC algorithm in predicting future outputs, w dev Indicates the weight of the output deviation term, which is set based on engineer experience and is set to 1. k represents the predicted value of the outlet steam temperature at the kth time step, SP represents the target value of the outlet steam temperature, and N c represents the number of time steps considered by the MPC algorithm when optimizing the control input, w smo Represents the weight of the control input change rate term, which is set based on engineer experience and is set to 1. i,k represents the change of the i-th control variable between the k-th and k+1-th time steps;
[0095] Define operating constraints, including upper and lower limits of R, L, C, M, W, P, and S, and the allowable fluctuation range of O.
[0096] S5. Based on the intelligent control architecture, optimize the existing control system, including the following steps:
[0097] The control system adopts an intelligent control architecture and integrates multiple control loops, each of which is responsible for adjusting specific process variables to maintain efficient and stable operation of the waste heat boiler of the waste incineration power plant. Each control loop is equipped with a main controller and a backup PID controller to ensure that the system can maintain uninterrupted operation even if the main controller fails.
[0098] The recirculation flue gas flow control loop is defined as RFL, which consists of using a variable frequency fan whose frequency is adjusted by the MPC command; the control process is that the MPC algorithm is based on the combustion efficiency model O CEI The output of the fan is adjusted to adjust the fan frequency and control the recirculated flue gas flow rate to optimize combustion conditions and reduce NOx emissions.
[0099] The leachate back-spray control loop is defined as LSP, which includes the use of a metering pump whose speed is controlled by an MPC instruction; the control process is that the MPC instruction adjusts the pump speed to control the leachate back-spray amount, affecting the temperature in the combustion chamber and the drying effect.
[0100] The cooling water control loop is defined as CTW, which consists of using an electric control valve and MPC instructions to determine the valve opening; the control process is that MPC adjusts the model O according to the temperature TRG output, adjust the valve opening, control the amount of cooling water, and ensure stable steam temperature.
[0101] The main steam flow control loop is defined as MSV, which consists of using an electric control valve and MPC instructions to determine the valve opening. The control process is that the MPC algorithm adjusts the main steam valve opening and controls the main steam flow to match the power generation demand and system stability.
[0102] The waste feed rate control loop is defined as WTF, which consists of using a feed conveyor with an adjustable speed motor and adjusting the motor speed with MPC instructions. The control process is that the MPC instructions adjust the waste feed rate according to the combustion efficiency and heat recovery model to ensure combustion stability and energy output.
[0103] The boiler primary fan control loop is defined as PFF, which consists of using a variable frequency fan and adjusting the frequency of the variable frequency drive fan according to the MPC instruction; the control process is that the MPC algorithm controls the primary fan frequency, adjusts the air intake volume, and optimizes the combustion process.
[0104] The boiler secondary fan control loop is defined as SSF, which consists of using a variable frequency fan to adjust the frequency of the variable frequency drive fan according to the MPC instruction; the control process is that the MPC instruction adjusts the secondary fan frequency, controls the secondary air intake, promotes oxidation in the later stage of combustion, and reduces CO emissions.
[0105] The control process flow steps are as follows:
[0106] Data Collection: Sensors continuously monitor system variables such as temperature, flow, pressure, etc.
[0107] Data preprocessing: Clean and standardize the collected data to remove outliers and noise.
[0108] Model prediction: Use the synthetic outlet steam temperature prediction model OT to predict future system status.
[0109] Cost function minimization: The MPC algorithm is based on the cost function J and finds the optimal sequence of future control actions by adjusting the control variables.
[0110] Control signal generation: The MPC algorithm generates the control signal for the first time step and sends it to the corresponding actuator in the control loop.
[0111] Execution and feedback: Actuators (such as variable frequency fans, electric control valves, metering pumps) are adjusted according to the control signal, and the system status is fed back to the MPC algorithm.
[0112] Closed-loop iteration: The MPC algorithm repeats steps 3 to 6 at each sampling time to achieve dynamic optimization and control.
[0113] The backup controller means that in each control loop, when the MPC algorithm of the main controller fails, the backup PID controller immediately takes over to ensure the continuous operation of the control loop. The PID controller is based on the proportional, integral, and differential control laws, and quickly responds to system deviations by adjusting the control signal until the main controller is restored or manual intervention occurs.
[0114] S6. Based on the optimized control system, the outlet steam temperature is controlled in real time, including the following steps:
[0115] The control variable of each control loop in the MPC algorithm output instruction is defined as R MPC , L MPC , C MPC 、M MPC , W MPC , P MPC and S MPC , corresponding to RFL, LSP, CTW, MSV, WTF, PFF and SSF control loops respectively.
[0116] The optimized control system continuously receives real-time data from the boiler, forming a real-time feedback mechanism;
[0117] The real-time data of the boiler is input into the optimized control system. The MPC algorithm in the system calculates the control variable R in the next control cycle according to the current operating conditions and the preset target value. MPC , L MPC , C MPC 、MMPC , W MPC , P MPC and S MPC The set point;
[0118] The main controller adjusts the actuators in each control loop according to the output instructions of the MPC algorithm;
[0119] The backup controller is on standby and will take over immediately if the main controller fails;
[0120] In the MPC algorithm, the expected value range and tolerance limit of the outlet steam temperature O are set as the main control target of the system;
[0121] When the outlet steam temperature deviates from the set value, the intelligent control architecture automatically adjusts R according to the influence of each control variable on the temperature predicted by the dynamic model. MPC , L MPC , C MPC 、M MPC , W MPC , P MPC and S MPC The set point;
[0122] The adjustment process involves fine control of the recirculated flue gas flow rate R, leachate back-spray volume L, desuperheating water volume C, garbage feed volume W, and the air intake volumes P and S of the primary and secondary fans;
[0123] By utilizing the rolling optimization characteristics of the MPC algorithm, the set values of each control loop are re-evaluated at regular control cycles to adapt to changes in external conditions such as combustion conditions and changes in garbage properties.
[0124] When the system oscillates, the MPC algorithm fails, and the standby PID controller is enabled. The outlet steam temperature rating is 445°C, which is used as the control target, and the control object is the cooling water valve. The outlet steam flow of the waste heat boiler is superimposed on the target setting value SP of the control loop to overcome the disturbance caused by the change in boiler evaporation. Logical configuration, set the initial parameters. Target setting value SP = 445-boiler outlet steam temperature-boiler outlet steam flow / 35+y+deviation setting value. y = f(x), x is the boiler outlet steam flow, y is the temperature value. Deviation setting value = 10. The specific function relationship of y = f(x) is provided, where y = f(x), x is the boiler outlet steam flow, and y is the temperature value. Initial parameter settings: x=0, y=0; x=45, y=375; x=50, y=370; x=55, y=365; x=60, y=360; x=65, y=355; x=70, y=350; x=75, y=345; x=80, y=340; x=85, y=335; x=90, y=330; x=95, y=325; x=100, y=320. Deviation setting value = 10. The control loop is put into automatic mode and the parameters are adjusted. Put the control loop into automatic mode, adjust the PID parameters, adjust the y=f(x) parameters, and adjust the deviation setting value. Conduct a disturbance test to verify that the maximum value of the boiler outlet steam temperature is less than 460℃ and the control cycle is within 3 cycles.
[0125] This embodiment also provides a computer device, which is suitable for the method of controlling the outlet steam temperature of the waste heat boiler of a waste incineration power plant, including: a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the method of controlling the outlet steam temperature of the waste heat boiler of a waste incineration power plant proposed in the above embodiment.
[0126] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.
[0127] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the method for controlling the outlet steam temperature of the waste heat boiler of a waste incineration power plant proposed in the above embodiment is implemented; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic storage, flash memory, magnetic disk or optical disk.
[0128] In summary, the present invention realizes comprehensive monitoring of the boiler operating status by integrating multiple sensors and collecting pre-processed boiler real-time data, so as to be able to respond to various operating condition changes in a timely manner, improve the reaction speed and accuracy of the system, and ultimately achieve the beneficial effect of improving the stability of boiler operation.
[0129] By fitting the group model, three sub-models of combustion efficiency, temperature regulation and heat recovery were established, which refined the various factors affecting the steam temperature, making the control more refined, thereby improving the pertinence and efficiency of the control strategy, and ultimately achieving the beneficial effect of optimizing the steam temperature control accuracy.
[0130] By synthesizing the outlet steam temperature prediction model and integrating the group models, a comprehensive prediction capability is formed, which can predict the outlet steam temperature more accurately and enable the control system to make adjustments in advance to avoid temperature fluctuations, ultimately achieving the beneficial effect of enhancing the system's prediction capability and stability.
[0131] By building an intelligent control architecture and optimizing the control system, the MPC algorithm is adopted to achieve rolling optimization of control variables. It can not only quickly respond to changes in operating conditions, but also balance long-term goals and short-term control, ultimately achieving the beneficial effect of improving the overall operating efficiency and economic benefits of the system.
[0132] By controlling the outlet steam temperature in real time based on the optimized control system, a closed-loop control mechanism is formed, which can quickly adjust the control strategy according to real-time data, ensuring the stability of the outlet steam temperature, and ultimately achieving the beneficial effects of improving energy efficiency and reducing emissions.
[0133] Example 2
[0134] Referring to Table 1, which is the second embodiment of the present invention, in order to further verify the advancement of the present invention, experimental simulation data of a method for controlling the outlet steam temperature of a waste heat boiler of a waste incineration power plant is provided.
[0135] In order to verify the effectiveness and innovation of the method for controlling the outlet steam temperature of the waste heat boiler of a waste incineration power plant, this embodiment designed a series of experiments to evaluate the advantages of the method of the present invention over traditional control strategies under different operating conditions. The experiment was conducted in a simulation environment, simulating the typical operation of the waste heat boiler of a waste incineration power plant, covering the main variables in the waste incineration process. The simulation platform used in the experiment has high flexibility and accuracy, and can truly reflect the behavior of the actual system.
[0136] First, during the experimental preparation stage, a variety of sensors, including temperature sensors, pressure sensors, and flow sensors, were integrated to collect real-time data. These data include recirculated flue gas flow R, leachate backspray volume L, cooling water volume C, main steam flow M, garbage feed volume W, boiler primary fan air intake volume P, boiler secondary fan air intake volume S, and outlet steam temperature O. After data collection, the Z-score method was used to clean the data, add timestamps, and use sliding window averaging to reduce noise to ensure that model training is based on high-quality data.
[0137] Then, based on the preprocessed real-time data, the group model was fitted and the combustion efficiency model was established. CEI , Temperature Regulation Model O TRG and heat recovery model O HRG The establishment of the model takes into account the complex relationship between variables and uses Gaussian kernel function, logarithmic function, square function, sine function and hyperbolic tangent function to capture nonlinear effects. The introduction of the dynamic weight function ω(t) enables the model to better reflect the dynamic characteristics of the system that changes over time.
[0138] Subsequently, based on the group fitting model, the synthetic outlet steam temperature prediction model OT was constructed. By weighted synthesis of three group models, the effects of combustion efficiency, temperature regulation and heat recovery were comprehensively considered to provide a comprehensive temperature prediction.
[0139] Finally, based on the outlet steam temperature prediction model OT, an intelligent control architecture was constructed, using the MPC algorithm and integrating the outlet steam temperature prediction model to optimize the existing control system. The rolling optimization characteristics of the MPC algorithm ensure the real-time and flexibility of the control strategy, and can effectively respond to changes in operating conditions and maintain the stability of the outlet steam temperature.
[0140] The details are shown in Table 1:
[0141] Table 1 Experimental record of MPC algorithm controlling outlet steam temperature
[0142]
[0143] Through the analysis of experimental data, it can be seen that the control strategy proposed in the present invention has shown significant advantages in maintaining the stability of the outlet steam temperature. Under different operating conditions, the outlet steam temperature O has a small change range, indicating the robustness and stability of the control strategy. Especially in experiments No. 1 to 6, although there are large fluctuations in the control variables such as R, L, C, M, W, P and S, the fluctuation range of the outlet steam temperature O is only between 448 and 455 degrees Celsius, showing the effectiveness of the intelligent control architecture.
[0144] Compared with the traditional PID control strategy, under similar operating conditions, the fluctuation range of the outlet steam temperature often exceeds 10 degrees Celsius, while the temperature fluctuation range of the method of the present invention is controlled within 7 degrees Celsius, which not only improves the energy utilization efficiency, but also reduces the thermal stress impact on the equipment and extends the equipment life.
[0145] Further analysis shows that the present invention optimizes the set points of control variables through the MPC algorithm, especially the recirculated flue gas flow R, leachate back spray volume L, cooling water volume C and garbage feed volume W. The refined control of these variables enables the system to reduce pollutant emissions while maintaining high efficiency, reflecting environmental benefits. At the same time, the optimization adjustment of the main steam flow M and the fan air intake volume P and S ensures the stability of power output and the maximization of energy output.
[0146] In summary, the control strategy of the present invention has significant creativity and novel effects compared with the existing technology in improving system efficiency, stabilizing outlet steam temperature, reducing pollutant emissions and optimizing energy output, which fully demonstrates its advancement and practicality in the field of waste heat boiler control in waste incineration power plants.
[0147] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.
Claims
1. A method for controlling the outlet steam temperature of a waste heat boiler of a garbage incineration power plant, characterized in that: include, Integrate multiple sensors to collect real-time boiler data and perform pre-processing; Based on the real-time data of pre-processed boilers, group model fitting is performed; Based on the group fitting model, a synthetic outlet steam temperature prediction model is developed; Build an intelligent control architecture based on the outlet steam temperature prediction model; Optimize existing control systems based on intelligent control architecture; Based on the optimized control system, the outlet steam temperature is controlled.
2. The method for controlling the outlet steam temperature of a waste heat boiler of a waste incineration power plant according to claim 1, characterized in that: The multiple sensors include temperature sensors, pressure sensors and flow sensors; the real-time data collected from the boiler include recycled flue gas flow R, leachate back-spray volume L, cooling water volume C, main steam flow M, garbage feed volume W, boiler primary fan air inlet volume P, boiler secondary fan air inlet volume S and outlet steam temperature O.
3. The method for controlling the outlet steam temperature of a waste heat boiler of a waste incineration power plant according to claim 2, characterized in that: Collect real-time boiler data and perform preprocessing. The specific steps are as follows: The collected real-time boiler data is cleaned using the Z-score method, timestamps are added, and sliding window averaging is used to reduce noise.
4. The method for controlling the outlet steam temperature of a waste heat boiler of a waste incineration power plant as claimed in claim 3, characterized in that: Based on the garbage feed volume W, the primary fan air volume P and the secondary fan air volume S, a combustion efficiency model is established to calculate the combustion efficiency O CEI , expressed as, In the formula, O CEI is the combustion efficiency, α1 is the intercept of the model, β 11 is the coefficient of the Gaussian kernel function, W is the amount of garbage input, μ w is the average value of the waste feed volume W, σ w is the standard deviation of the mean value of the waste feed volume W, β 12 is the coefficient of the logarithmic function of the primary fan air volume P, where P is the primary fan air volume of the boiler, and β 13 is the coefficient of the square root function of the secondary fan air volume S, S is the air volume of the boiler secondary fan, and ω1(t) is the dynamic weight function; Based on the desuperheating water volume C and the main steam flow rate M, a temperature regulation model is established to calculate the temperature regulation range O TRG It is expressed as, In the formula, O TRG is the temperature adjustment range, α2 is the intercept of the model, β 21 is the coefficient of the power function of the ratio of the desuperheating water volume C and the main steam flow rate M, where C is the desuperheating water volume, M is the main steam flow rate, Φ is the exponent, and β 22 is the coefficient of the cube root function of the cooling water volume C, ω2(t) is the dynamic weight function; The heat recovery model is established based on the recirculated flue gas flow rate R and the leachate back-spray volume L, and the heat recovery range O is calculated. HRG It is expressed as, The HRG =α3+β 31 sin(R)+β 32 tanh(L)+ω3(t); sin(R); tanh(L); In the formula, O HRG is the heat recovery range, α3 is the intercept of the model, β 31 is the coefficient of the sinusoidal function of the recirculating flue gas flow rate R, R is the recirculating flue gas flow rate, β 32 is the coefficient of the hyperbolic tangent function of the leachate backspray volume L, L is the leachate backspray volume, and ω3 is the dynamic weight function.
5. The method for controlling the outlet steam temperature of a waste heat boiler of a garbage incineration power plant according to claim 4, characterized in that: Based on the group fusion model, the outlet steam temperature prediction model is synthesized. The specific steps are as follows: Weighted Composite O CEI , O TRG and O HRG , the outlet steam temperature prediction model is synthesized, and the predicted outlet steam temperature OT is expressed as, OT=w1O CEI +w2O TRG +w3O HRG +∈; Where OT is the predicted outlet steam temperature, w1 is a fixed weight, w2 is a fixed weight, w3 is a fixed weight, ε is the error term, O CEI is the output of the combustion efficiency model, O TRG is the output of the temperature regulation model, O HRG is the output of the heat recovery model.
6. The method for controlling the outlet steam temperature of a waste heat boiler of a waste incineration power plant according to claim 5, characterized in that: Based on the outlet steam temperature prediction model, an intelligent control architecture is constructed. The specific steps are as follows: Use the MPC algorithm to build an intelligent control architecture and integrate the outlet steam temperature prediction model; In the MPC algorithm, the cost function J is defined as: Where J represents the total cost that needs to be minimized in the MPC algorithm, and N p represents the number of time steps of the MPC algorithm in predicting future outputs, w dev Represents the weight of the output bias term, OT k represents the predicted value of the outlet steam temperature at the kth time step, SP represents the target value of the outlet steam temperature, and N c represents the number of time steps based on which the MPC algorithm optimizes the control input, w s represents the weight of the control input change rate term, Δu i,k represents the change of the i-th control variable between the k-th and k+1-th time steps; Define operating constraints, including the recirculated flue gas flow rate R MPC , Leachate back spray volume L MPC , cooling water volume C MPC , Main steam flow M MPC , garbage feed amount W MPC , Boiler primary fan air intake volume P MPC , Boiler secondary fan air intake volume S MPC and outlet steam temperature O MPC .
7. The method for controlling the outlet steam temperature of a waste heat boiler of a waste incineration power plant according to claim 6, characterized in that: The existing control system is optimized by using the constructed intelligent control architecture. The specific steps are as follows: The intelligent control architecture is integrated into the control system, which contains multiple control loops; Each control loop in the control system contains a main controller and a backup controller; The recirculated flue gas flow control loop is defined as RFL, using a variable frequency fan, which adjusts the frequency of the variable frequency drive fan according to the MPC command; The leachate back-spray control loop is defined as LSP, and the actuator uses a metering pump, whose speed is controlled by the MPC instruction; The cooling water control loop is defined as CTW, the actuator uses an electric regulating valve, and the MPC instruction determines the valve opening; The main steam flow control loop is defined as MSV, the actuator uses an electric control valve, and the MPC instruction determines the valve opening; The waste feed quantity control loop is defined as WTF, the actuator uses a feed conveyor with an adjustable speed motor, and the MPC command adjusts the motor speed; The boiler primary fan control loop is defined as PFF, and the actuator uses a variable frequency fan, which adjusts the frequency of the variable frequency drive fan according to the MPC command; The boiler secondary fan control loop is defined as SSF, and the actuator uses a variable frequency fan to adjust the variable frequency drive fan frequency according to the MPC command.
8. The method for controlling the outlet steam temperature of a waste heat boiler of a garbage incineration power plant according to claim 7, characterized in that: Based on the optimized control system, the real-time control of the outlet steam temperature is completed. The specific steps are as follows: The control variable of each control loop in the MPC algorithm output instruction is defined as R MPC , L MPC , C MPC 、M MPC , W MPC , P MPC and S MPC , corresponding to RFL, LSP, CTW, MSV, WTF, PFF and SSF control loops respectively; The optimized control system continuously receives real-time data from the boiler, forming a real-time feedback mechanism; The real-time data of the boiler is input into the optimized control system. The MPC algorithm in the system calculates the control variable R in the next control cycle according to the current operating conditions and the preset target value. MPC , L MPC , C MPC 、M MPC , W MPC , P MPC and S MPC The set point; The main controller adjusts the actuators in each control loop according to the output instructions of the MPC algorithm; The backup controller is on standby and will take over immediately if the main controller fails; In the MPC algorithm, the expected value range and tolerance limit of the outlet steam temperature O are set as the main control target of the system; When the outlet steam temperature deviates from the set value, the intelligent control architecture automatically adjusts R according to the influence of each control variable on the temperature predicted by the dynamic model. MPC , L MPC , C MPC 、M MPC , W MPC , P MPC and S MPC The set point; The adjustment process involves fine control of the recirculated flue gas flow rate R, leachate back-spray volume L, desuperheating water volume C, garbage feed volume W, and the air intake volumes P and S of the primary and secondary fans; By utilizing the rolling optimization characteristics of the MPC algorithm, the set values of each control loop are re-evaluated at regular control cycles to adapt to changes in external conditions such as combustion conditions and changes in garbage properties.
9. A method for controlling the outlet steam temperature of a waste heat boiler of a waste incineration power plant, characterized in that: When the model executes the computer program, the steps of the method for controlling the outlet steam temperature of a waste heat boiler in a waste incineration power plant as described in any one of claims 1 to 8 are implemented.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for controlling the outlet steam temperature of a waste heat boiler of a waste incineration power plant according to any one of claims 1 to 8 are implemented.
Citation Information
Cited By
Intermittent steam generator control method and system for wafer drying
CN119270748A
Method and system for optimizing heat absorption rate of heating surface of refuse incinerator
CN120830849A
