Control method and system for rapid response of secondary reheat unit to grid demand

Abstract

The present invention belongs to the field of power grid balance control, and in particular, relates to a control method and system for a secondary reheat unit to quickly respond to power grid demand. The method obtains furnace-side and machine-side operating data through integrated sensors, constructs and trains a multivariable predictive control model after preprocessing, and obtains initial control parameters of the furnace side. Secondly, a dynamic compensation strategy is introduced to obtain real-time heat flow distribution on the furnace side, optimize the initial control parameters of the furnace side, and ensure the accuracy of furnace side control. Thirdly, the machine-side peak-shaving strategy and particle swarm algorithm are used to obtain the initial control parameters of the machine side. Fourthly, a wind and photovoltaic power output prediction model is constructed, and the output of the secondary reheat unit is dynamically adjusted according to the prediction results. When the output demand exceeds the threshold, the pre-furnace-side and machine-side control parameters are used to control the unit to generate electricity, so as to ensure a rapid response to power grid demand. The present invention effectively improves the response speed and operation efficiency of the secondary reheat unit to meet the rapidly changing needs of the power grid.

Description

Technical Field

[0001] The present invention belongs to the field of power grid balance control, and in particular relates to a control method and system for a secondary reheat unit to quickly respond to power grid demand. Background Art

[0002] With the transformation of energy structure and the continuous growth of the proportion of renewable energy, the power grid is facing unprecedented peak load regulation challenges. As the current technological frontier in the field of cogeneration, the double reheat ultra-supercritical coal-fired unit has become a key force in supporting the stable operation of the power grid with its high efficiency and low emission characteristics. This type of unit significantly improves the thermal cycle efficiency through two steam reheating processes and shows significant advantages in reducing pollutant emissions. However, despite the remarkable achievements of double reheat technology in improving efficiency, it still has some technical and operational limitations in responding to the rapidly changing needs of the power grid.

[0003] For example, the patent with authorization announcement number CN112910017B discloses an ultra-supercritical secondary reheat unit under power grid gap.

[0004] The primary frequency regulation method first calculates the difference between the grid frequency and the standard frequency, and calculates the corresponding primary reheater bypass valve opening based on the frequency difference, so that the primary reheater bypass valve is opened to a certain degree, and part of the steam bypasses the primary reheater and directly enters the high-pressure cylinder, thereby increasing the speed at which steam works in the steam turbine, thereby increasing the primary frequency regulation response speed of the secondary reheat unit, and restoring the grid frequency to normal as soon as possible; in order to prevent the primary reheater from overheating, when the primary reheater wall tube temperature reaches the alarm value, the primary reheater bypass valve is fully closed.

[0005] The above existing technologies have the following problems: 1) The limited control of the reheat steam temperature on the furnace side and the peak load regulation capacity on the generator side have become the main bottleneck restricting the flexibility of the unit; 2) It is impossible to achieve intelligent control and accurate and rapid load tracking and automatic adjustment for the rapid response to the balance of wind and solar power during the peak load period; Summary of the invention

[0006] In view of the shortcomings of the prior art, the present invention proposes a control method for a secondary reheat unit to quickly respond to grid demand. The method acquires furnace-side and machine-side operating data through integrated sensors, constructs and trains a multivariable predictive control model after preprocessing, and realizes optimal control of the furnace side. Secondly, a dynamic compensation strategy is introduced to optimize the real-time heat flow distribution on the furnace side to ensure the accuracy of furnace-side control. Thirdly, the machine-side peak-shaving strategy and particle swarm algorithm are used to obtain the optimal control parameters of the machine side. Fourthly, a wind and photovoltaic power output prediction model is constructed to dynamically adjust the output of the secondary reheat unit according to the prediction results. When the output demand exceeds the threshold, the pre-furnace-side and machine-side control parameters are used to control the unit to generate electricity, so as to ensure a rapid response to grid demand. The present invention effectively improves the response speed and operation efficiency of the secondary reheat unit to meet the rapidly changing needs of the grid.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] The control method for the secondary reheat unit to quickly respond to the grid demand includes:

[0009] Step S1, obtaining the furnace side and machine side attribute data, monitoring operation data and load demand power data of the secondary reheat unit through the integrated sensor, and preprocessing the collected data;

[0010] Step S2, constructing a multivariable predictive control model, and obtaining the initial control variable parameters of the furnace side according to the preprocessed furnace side operation data and the multivariable predictive control model;

[0011] Step S3, introducing a dynamic compensation strategy, obtaining the temperature field inside the furnace, obtaining the real-time heat flux distribution information on the furnace side according to the obtained temperature field inside the furnace and the dynamic compensation strategy, feeding the obtained real-time heat flux distribution information back to the multivariable predictive control model, and compensating and correcting the obtained initial control variable parameters;

[0012] Step S4, introducing the machine-side peak-shaving strategy, using the evaluation algorithm to evaluate and obtain the preliminary peak-shaving limit of the steam turbine according to the machine-side attribute data, and at the same time, according to the obtained preliminary peak-shaving limit and the machine-side operation data, the parameter search model constructed by the particle swarm algorithm is used to obtain the machine-side initial control variable parameters;

[0013] Step S5: construct and train a wind and photovoltaic power output prediction model, and calculate the output power of the secondary reheat unit using the wind and photovoltaic power output prediction model according to the acquired wind and photovoltaic power output data and load demand power data;

[0014] Step S6, setting the output threshold of the secondary reheat unit to 0, feeding back the output power of the secondary reheat unit obtained in step S5 to the multivariable predictive control model and the machine-side peak load regulation strategy, and obtaining the furnace-side pre-control variable parameters and the machine-side pre-control variable parameters;

[0015] Step S7, compare the output power of the secondary reheat unit obtained in step S5 with the output threshold of the secondary reheat unit. If it is greater than, use the obtained optimal control variable parameters of the front furnace side and the optimal control variable parameters of the front machine side to control the secondary reheat unit, generate electricity according to the calculated output power of the secondary reheat unit, and output a power value equal to the output power of the secondary reheat unit obtained in step S5 to make up for the power missing from the wind and solar power output. If it is equal, the secondary reheat unit remains in a stopped state.

[0016] Specifically, the specific steps of constructing the wind photovoltaic output prediction model in step S5 include:

[0017] S501. Collect historical wind and photovoltaic power output data, load balance power demand data and weather factor data according to sunny, cloudy, overcast and rainy weather conditions, and pre-process the collected data to construct a multi-weather state input sequence. ;in, represents the i-th weather state data, represents the nth wind and solar power output data in the i-th weather state data, represents the mth load balancing power demand data in the i-th weather state data, Represents the kth weather factor data in the i-th weather state data.

[0018] Specifically, the specific steps of constructing the wind photovoltaic output prediction model in step S5 also include:

[0019] S502, using a random forest algorithm, constructing a wind and solar power output prediction model including a clear prediction sub-model, a cloudy prediction sub-model, an overcast prediction sub-model, and a rain prediction sub-model in an integrated manner;

[0020] S503: Input to multiple weather state input sequence , according to the weather state type, it is input into the corresponding sub-model in the photovoltaic output prediction model for training;

[0021] S504, using historical wind and solar power output data and load balance power demand data at the corresponding time to obtain historical real output errors, and using the wind and solar power output data and load balance power demand data predicted at the corresponding historical time to obtain historical predicted output errors;

[0022] S505: Setting training threshold According to the historical actual output error and the historical predicted output error, the secondary training error is obtained and the obtained secondary training error is compared with Compare, if it is less than, the training is completed, otherwise, training is continued until the threshold condition is met.

[0023] Specifically, the specific calculation process for predicting the output power of the secondary reheat unit includes:

[0024] S506: Collect the wind and solar power output data, load balance power demand data and weather factor data for the first 30 hours of the forecast day, input the wind and solar power output data and weather factor data for the first 30 hours into the trained wind and solar power output forecast model, and output the wind and solar power output data for the next 12 hours;

[0025] S507. Based on the wind and solar power output data and load balance power demand data obtained for the next 12 hours, the output power of the secondary reheat unit is calculated using the load demand balance equation. The load demand balance equation is: ,in, Indicates the power data required for load balance at time t, It represents the predicted power data of wind power output at time t, Represents the output power of the secondary reheat unit at time t.

[0026] Specifically, the specific process steps of step S3 include:

[0027] S301, constructing a furnace side three-dimensional geometric model through furnace side attribute data, dividing the furnace side three-dimensional geometric model into N monitoring areas using a grid algorithm, and obtaining temperature distribution data of the N monitoring areas in the furnace through the deployed furnace side sensors;

[0028] S302, according to the acquired temperature distribution data, a heat flux distribution map of each area in the furnace is calculated by combining finite element analysis with thermal radiation and convection fluid dynamics algorithms;

[0029] S303, feeding back the obtained heat flux distribution map of each area to the initial control variable parameter, using the dynamic temperature compensation formula to calculate the correction value of the initial control variable parameter, and performing compensation correction on the initial control variable parameter.

[0030] Specifically, the dynamic temperature compensation formula is:

[0031] ,

[0032] in, represents the compensation amount of the i-th parameter of the initial control variable parameter, represents the parameter dynamic adjustment factor, represents the real-time temperature data corresponding to the jth monitoring area in the furnace, represents the expected temperature data corresponding to the jth monitoring area in the furnace, N represents the number of monitoring areas in the furnace, Indicates temperature deviation The corresponding correction parameters are, Indicates the rate of temperature change The corresponding correction parameters are, Indicates the accumulated temperature deviation The corresponding correction parameters are, Indicates the length of time that the secondary reheat wheel set operates once.

[0033] Specifically, the specific steps of constructing the multivariable predictive control model include:

[0034] S201, preprocessing furnace-side attribute data, operation data, and load demand power data acquired by the integrated sensor to acquire furnace-side control variable data;

[0035] S202, constructing a multivariable predictive control model using a support vector machine, and inputting the acquired furnace-side control variable data into the multivariable predictive control model for training;

[0036] S203, setting the multivariable predictive control model objective function and corresponding constraints to limit the furnace side operating cost, operating efficiency and emissions, so as to minimize fuel consumption while maintaining output power to meet load power requirements.

[0037] Specifically, the specific steps of constructing the multivariable predictive control model also include:

[0038] S204, integrating the constructed objective function and the corresponding constraint conditions into the multivariable predictive control model for training to obtain the trained multivariable predictive control model;

[0039] S205, integrating the trained multivariable predictive control model into the furnace side control subsystem, collecting furnace side operation data in real time through sensors, and inputting the real-time collected furnace side operation data into the multivariable predictive control model to obtain the initial control variable parameters of the furnace side.

[0040] Specifically, the objective function and corresponding constraints in S203 specifically include:

[0041] The specific formula of the objective function is: ,

[0042] The constraints are:

[0043]

[0044] in, represents the furnace side objective constraint function, It represents the fuel consumption cost of one cycle of furnace operation. It indicates the total amount of pollution emissions corresponding to one cycle of furnace operation. Indicates the actual output power value of the secondary reheat unit at time t; represents the fuel consumption at time t, In turn, they represent the maximum and minimum values ​​of fuel consumption per unit time. represents the wind speed entering the furnace at time t, They represent the maximum and minimum wind speeds entering the furnace at time t, respectively. It represents the maximum threshold of the power output of the secondary reheat unit at time t, It represents the threshold value of the total amount of pollution emissions during one cycle of furnace operation. Represents the corresponding weighting coefficient.

[0045] Specifically, the specific formula of the initial peak-shaving interval corresponding to the preliminary peak-shaving limit in step S4 is:

[0046] ,

[0047] in, represents the initial peak-shaving interval, represents the safety margin factor, It represents the minimum output power of the steam turbine that can operate stably at time t. It represents the additional energy loss caused by the turbine starting from shutdown state to full load or shutting down from full load at time t. Indicates the amount of output power that a steam turbine can increase or decrease per unit time.

[0048] Specifically, in step S4, the steam turbine reaction objective function and constraint conditions are set in the parameter search model, specifically:

[0049] , ,

[0050] in represents the machine side operating efficiency objective function, It indicates the difference between the output power of the secondary reheat unit at the current moment and the output power of the secondary reheat unit at the previous moment. Indicates the corresponding change time, Indicates the efficiency of steam turbine operation. This value is predicted by the historical operation data of steam turbine and the turbine efficiency prediction model constructed by support vector machine. Represents the corresponding weighting coefficient.

[0051] The control system of the secondary reheat unit that quickly responds to grid demand includes: data processing module, furnace side control module, machine side control module, wind and solar power output prediction module and feedback control module;

[0052] The data processing module is used to collect monitoring data and load demand power data of the furnace side and the machine side using integrated sensors, and pre-process the collected data;

[0053] The wind and photovoltaic power output prediction module is used to construct and train a wind and photovoltaic power output prediction model, calculate the predicted wind and photovoltaic power output data according to the trained model, and calculate the output power of the secondary reheat unit through the predicted wind and photovoltaic power output data and load demand power data.

[0054] Specifically, the furnace side control module includes a multivariable control unit and a dynamic compensation unit;

[0055] The multivariable control unit is used to construct a multivariable predictive control model and obtain the initial control variable parameters of the furnace side according to the obtained furnace side operation data and control strategy; the dynamic compensation unit is used to construct a dynamic compensation strategy, calculate the real-time heat flux distribution information of the furnace side according to the obtained temperature field information inside the furnace and the compensation strategy, and use the heat flux distribution information to compensate and correct the initial control variable parameters of the furnace side.

[0056] Specifically, the machine-side control module includes a peak load evaluation unit and a parameter calculation unit;

[0057] The peak-shaving evaluation unit is used to comprehensively evaluate the steam turbine based on the acquired machine-side attribute data using an evaluation algorithm to obtain the preliminary peak-shaving limit of the steam turbine; the parameter calculation unit is used to obtain the initial control variable parameters of the machine side through a particle swarm algorithm based on the acquired preliminary peak-shaving limit and the machine-side operation data.

[0058] Specifically, the feedback control module includes a parameter feedback optimization unit and a discrimination control unit;

[0059] The parameter feedback optimization unit is used to perform feedback optimization on the furnace side initial control variable parameters and the machine side initial control variable parameters according to the obtained secondary reheat unit output power, and obtain the furnace side pre-control variable parameters and the machine side pre-control variable parameters; the discrimination control unit is used to set the secondary reheat unit output threshold, and compare the threshold with the obtained secondary reheat unit output power to determine whether to generate electricity. If power is generated, the obtained furnace side pre-control variable parameters and the machine side pre-control variable parameters are used to control the unit to generate electricity, and output a power value equal to the secondary reheat unit output power.

[0060] A computer-readable storage medium stores computer instructions, which, when executed, execute a control method for a secondary reheat unit to quickly respond to grid demand.

[0061] An electronic device comprises a memory and a processor, wherein the memory stores a computer program and the processor implements a control method for a secondary reheat unit to quickly respond to grid demand when executing the computer program.

[0062] Compared with the prior art, the present invention has the following beneficial effects:

[0063] In view of the deficiencies of the prior art, the present invention constructs a multivariable predictive control model and introduces a dynamic compensation strategy to more accurately predict and regulate the furnace side operating parameters of the secondary reheat unit, especially the furnace side reheat steam temperature, thereby effectively breaking through the bottleneck of furnace side reheat steam temperature control and improving the overall flexibility of the unit. Secondly, by introducing the machine-side peak-shaving strategy and the parameter search model constructed by the particle swarm algorithm, it is possible to quickly evaluate and optimize the peak-shaving limit of the steam turbine based on the machine-side attribute data and operation data, thereby improving the peak-shaving capacity of the machine side and ensuring that the unit can operate stably and efficiently during peak load periods. Thirdly, through the construction and training of the wind and photovoltaic power output prediction model, it is possible to accurately predict the wind and photovoltaic power output, and combine the load demand power data to calculate the output power of the secondary reheat unit through the load demand balance equation. This process not only realizes a rapid response to the wind and photovoltaic power balance, but also can realize accurate and rapid load tracking and automatic adjustment, ensuring that the unit can maintain stable power output when the wind and photovoltaic power output fluctuates. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 This is a flow chart of a control method for a secondary reheat unit to quickly respond to grid demand in Example 1 of the present invention;

[0065] Figure 2 This is a control method architecture diagram of a secondary reheat unit that quickly responds to grid demand in Example 1 of the present invention;

[0066] Figure 3 This is a diagram of the wind and solar power output prediction model architecture of Example 1 of the present invention;

[0067] Figure 4 This is a control system module architecture diagram for a secondary reheat unit that quickly responds to grid demand in Example 2 of the present invention; DETAILED DESCRIPTION

[0068] Example 1

[0069] See also Figure 1 and Figure 2 The present invention provides an embodiment: a control method for a secondary reheat unit to quickly respond to grid demand, comprising the following steps:

[0070] Step S1, obtain the furnace side and machine side attribute data of the secondary reheat unit, monitor the operation data and the load demand power data through the integrated sensor, and pre-process the collected data; further, the furnace side attribute data includes the furnace side geometric dimensions and structure, material properties, design parameters and equipment specifications; the furnace side geometric dimensions and structure include the furnace size (such as diameter, height, volume), furnace lining material, number and arrangement of tuyere, cooling system structure (such as cooling wall, cooling plate position and material); material properties include thermal conductivity, high temperature resistance and thermal expansion coefficient of refractory materials; design parameters include rated capacity, Design fuel type, theoretical combustion air demand, design thermal efficiency; equipment specifications include the model, capacity and performance parameters of auxiliary equipment such as fans, pumps, valves, etc.; furnace side operation data include furnace internal temperature (temperature distribution at different monitoring points), furnace outlet temperature, furnace wall temperature, cooling water inlet and outlet temperature, furnace pressure, furnace top pressure, furnace bottom pressure, flue pressure, steam pressure, fuel flow (coal powder, natural gas, etc.), combustion air flow, cooling water flow, thermal efficiency, actual output power, load rate, combustion control parameters (such as air supply volume, fuel supply rate, excess air coefficient),

[0071] Step S2, constructing a multivariable predictive control model, and obtaining the initial control variable parameters of the furnace side according to the preprocessed furnace side operation data and the multivariable predictive control model;

[0072] Step S3, introducing a dynamic compensation strategy, obtaining the temperature field inside the furnace, obtaining the real-time heat flux distribution information on the furnace side according to the obtained temperature field inside the furnace and the dynamic compensation strategy, feeding the obtained real-time heat flux distribution information back to the multivariable predictive control model, and compensating and correcting the obtained initial control variable parameters;

[0073] Step S4, introducing the machine-side peak-shaving strategy, using the evaluation algorithm to evaluate and obtain the preliminary peak-shaving limit of the steam turbine according to the machine-side attribute data, and at the same time, according to the obtained preliminary peak-shaving limit and the machine-side operation data, the parameter search model constructed by the particle swarm algorithm is used to obtain the machine-side initial control variable parameters;

[0074] Step S5: construct and train a wind and photovoltaic power output prediction model, and calculate the output power of the secondary reheat unit using the wind and photovoltaic power output prediction model according to the acquired wind and photovoltaic power output data and load demand power data;

[0075] Step S6, setting the output threshold of the secondary reheat unit to 0, feeding back the output power of the secondary reheat unit obtained in step S5 to the multivariable predictive control model and the machine-side peak load regulation strategy, and obtaining the furnace-side pre-control variable parameters and the machine-side pre-control variable parameters;

[0076] Step S7, compare the output power of the secondary reheat unit obtained in step S5 with the output threshold of the secondary reheat unit. If it is greater than, use the obtained optimal control variable parameters of the front furnace side and the optimal control variable parameters of the front machine side to control the secondary reheat unit, generate electricity according to the calculated output power of the secondary reheat unit, and output a power value equal to the output power of the secondary reheat unit obtained in step S5 to make up for the power missing from the wind and solar power output. If it is equal, the secondary reheat unit remains in a stopped state.

[0077] For further information, see Figure 3 The specific steps of constructing the wind photovoltaic output prediction model in S5 include:

[0078] S501. Collect historical wind and photovoltaic power output data, load balance power demand data and weather factor data according to sunny, cloudy, overcast and rainy weather conditions, and pre-process the collected data to construct a multi-weather state input sequence. ;in, represents the i-th weather state data, represents the nth wind and solar power output data in the i-th weather state data, represents the mth load balancing power demand data in the i-th weather state data, represents the kth weather factor data in the i-th weather state data; further, in this embodiment, the length of the wind photovoltaic output data, load balancing power demand data and weather factor data in the multi-weather state input sequence is 15 minutes;

[0079] S502. Using the random forest algorithm, a wind and solar power output prediction model including a clear prediction sub-model, a cloudy prediction sub-model, an overcast prediction sub-model, and a rain prediction sub-model is constructed in an integrated form; further, in this embodiment, the number of decision trees corresponding to the random forest algorithm in the clear prediction sub-model, the cloudy prediction sub-model, the overcast prediction sub-model, and the rain prediction sub-model is set to 30;

[0080] S503: Input to multiple weather state input sequence , according to the weather state type, it is input into the corresponding sub-model in the photovoltaic output prediction model for training;

[0081] S504, using historical wind and solar power output data and load balance power demand data at the corresponding time to obtain historical real output errors, and using the wind and solar power output data and load balance power demand data predicted at the corresponding historical time to obtain historical predicted output errors;

[0082] S505: Setting training threshold According to the historical actual output error and the historical predicted output error, the secondary training error is obtained and the obtained secondary training error is compared with If the value is less than the threshold, the training is completed; otherwise, the training is continued until the threshold condition is met. The size of is 0.05;

[0083] S506: Collect the wind and solar power output data, load balance power demand data and weather factor data for the first 30 hours of the forecast day, input the wind and solar power output data and weather factor data for the first 30 hours into the trained wind and solar power output forecast model, and output the wind and solar power output data for the next 12 hours;

[0084] S507. Based on the wind and solar power output data and load balance power demand data obtained for the next 12 hours, the output power of the secondary reheat unit is calculated using the load demand balance equation. The load demand balance equation is: ,in, Indicates the power data required for load balance at time t, It represents the predicted power data of wind power output at time t, Represents the output power of the secondary reheat unit at time t.

[0085] Furthermore, the specific process steps of S3 include:

[0086] S301, constructing a furnace side three-dimensional geometric model through furnace side attribute data, dividing the furnace side three-dimensional geometric model into N monitoring areas by using a grid algorithm, and obtaining temperature distribution data of the N monitoring areas in the furnace through the deployed furnace side sensors; further, this step is implemented in the actual execution process through three-dimensional modeling software (such as SolidWorks, CATIA, etc.) and grid generation software (such as GAMSCAD, NETGEN, ICEM, etc.), and the specific steps include:

[0087] S3011. Input detailed geometric information of the furnace side, including size, shape, material, and structural layout data, into a three-dimensional modeling software to construct a three-dimensional geometric model of the furnace side;

[0088] S3012, input the constructed furnace side three-dimensional geometric model into the grid generation software, and set the grid shape, grid size and grid density according to the flow characteristics of the fluid in the furnace, the heat conduction properties and the complexity of the furnace structure; in this embodiment, the constructed furnace side three-dimensional geometric model is meshed using a quadrilateral grid shape;

[0089] S3013. According to the grid division results, sensor deployment points are planned at key locations in each monitoring area, temperature data is collected through a sensor network or wired / wireless methods, and the collected temperature data is displayed in the corresponding grid using different colors; for example, red is used to mark the high temperature area, blue is used to mark the low temperature area, and transition areas are represented by transition colors, which are set by those skilled in the art according to usage habits;

[0090] S302, according to the acquired temperature distribution data, a heat flux distribution map of each area in the furnace is calculated by combining finite element analysis with thermal radiation and convection fluid dynamics algorithms;

[0091] S303, feeding back the heat flux distribution map of each region to the initial control variable parameter, using the dynamic temperature compensation formula to calculate the correction value of the initial control variable parameter, and performing compensation correction on the initial control variable parameter. The dynamic temperature compensation formula is specifically:

[0092] ,

[0093] in, represents the compensation amount of the i-th parameter of the initial control variable parameter, represents the parameter dynamic adjustment factor, represents the real-time temperature data corresponding to the jth monitoring area in the furnace, represents the expected temperature data corresponding to the jth monitoring area in the furnace, N represents the number of monitoring areas in the furnace, Indicates temperature deviation The corresponding correction parameters are, Indicates the rate of temperature change The corresponding correction parameters are, Indicates the accumulated temperature deviation The corresponding correction parameters are, Indicates the length of time that the secondary reheat wheel group operates once; further, in this embodiment, The introduction of the time rate of change consideration can enhance the dynamic response to temperature changes, especially the control of transient processes. The cumulative effect of historical temperature deviation is utilized to help eliminate long-term static errors and improve control accuracy. In this embodiment, the parameters , , and By using the historical operation data of the furnace side, the genetic algorithm is used to periodically search and obtain the parameters , , and The corresponding optimal value; Ability to dynamically adjust based on historical control effects, current operating conditions stability or external disturbance intensity to achieve adaptability of control strategies;

[0094] Furthermore, the specific steps of obtaining the heat flow distribution map in S302 of this embodiment include:

[0095] S3021. According to the monitoring area divided in S301, a group of heat transfer equations in the furnace is constructed by combining the Navier-Stokes equation and the energy equation with the heat conduction, convection, and Rayleigh-Boltzmann equation. The technology involved in the equation is the prior art and will not be described in detail here. Those skilled in the art will set the group of equations according to the operating data in the actual work of the furnace side.

[0096] S3022. According to the furnace side attribute data and the furnace side operation requirements, the furnace side inlet boundary conditions, furnace wall boundary conditions, and furnace side pressure boundary conditions are set. Further, in this embodiment, the furnace side inlet boundary conditions, furnace wall boundary conditions, and pressure boundary conditions belong to the furnace side basic attribute parameter restriction conditions. The corresponding conditions are set by those skilled in the art according to the furnace side attribute data, the furnace side operation requirement data, and the power data to be output; further, the corresponding boundary conditions in S3022 include:

[0097] Boundary conditions at the furnace inlet: , which specifies the velocity of the fluid entering the furnace. represents the velocity of the fluid entering the furnace at time t, Indicates the fixed value of the velocity of the fluid entering the furnace; , which is used to set the temperature of the inlet fluid. represents the initial temperature of the fluid entering the furnace at time t, It indicates the fixed initial temperature of the fluid entering the furnace;

[0098] Furnace wall boundary conditions: , which is used to indicate that there is no heat exchange between the furnace wall and the outside world, and the temperature gradient of the furnace wall is zero in the direction perpendicular to the surface. represents the furnace wall surface temperature at time t;

[0099] Furnace side pressure boundary conditions: , this condition is used to indicate that the rate of change of the pressure in the furnace along the direction of the boundary normal is a fixed value, and the pressure in the furnace changes uniformly. Indicates the pressure in the furnace at time t;

[0100] S3023. Based on the above-constructed equations and boundary conditions, the above equations are solved using finite element analysis software to calculate the heat flux distribution and temperature field, and obtain the heat flux density and direction; the finite element analysis software includes ANSYS, COMSOL, and ABAQUS;

[0101] S3024. Generate a heat flux distribution map using visualization software based on the calculated heat flux distribution and temperature field; the heat flux distribution map includes furnace side temperature field, heat flow line diagram, isotherms, and heat flux density diagram; the visualization software includes: MATLAB, ParaView, Tecplot;

[0102] Furthermore, in step S2 of this embodiment, the specific steps of obtaining the initial control variable parameters of the furnace side include:

[0103] S201, preprocessing furnace-side attribute data, operation data, and load demand power data acquired by the integrated sensor to acquire furnace-side control variable data;

[0104] S202, constructing a multivariable predictive control model using a support vector machine, and inputting the acquired furnace-side control variable data into the multivariable predictive control model for training;

[0105] S203, setting the multivariable predictive control model objective function and corresponding constraints to limit the furnace side operating cost, operating efficiency and emissions, so as to minimize fuel consumption while maintaining the output power to meet the load power demand. The specific formula of the objective function is: , the constraints are:

[0106]

[0107] in, represents the furnace side objective constraint function, It represents the fuel consumption cost of one cycle of furnace operation. It indicates the total amount of pollution emissions corresponding to one cycle of furnace operation. Indicates the actual output power value of the secondary reheat unit at time t; represents the fuel consumption at time t, In turn, they represent the maximum and minimum values ​​of fuel consumption per unit time. represents the wind speed entering the furnace at time t, They represent the maximum and minimum wind speeds entering the furnace at time t, respectively. represents the corresponding weighting coefficient, and is obtained through the historical furnace side operation data and calculated using the random forest algorithm; The threshold value represents the total amount of pollution emissions during a cycle of furnace operation. The threshold value is set by the fixed amount of pollutants emitted per unit time stipulated by the state. The total amount of pollution emissions in this embodiment is the amount of carbon dioxide emitted by the furnace per unit time multiplied by the length of one cycle of furnace operation. represents the maximum threshold of the power output of the secondary reheat unit at time t, which is obtained and set according to the performance attributes of the secondary reheat unit and by those skilled in the art based on experiments;

[0108] By minimizing the operating cost through the objective function, the emission can reduce the consumption cost on the furnace side and increase the combustion rate of the input combustion materials. At the same time, minimizing the predicted output power of the secondary reheat unit and the actual output power of the secondary reheat unit at time t can improve the control of the insufficient power demand of the load demand by the method of this embodiment, understand the load demand in advance, and realize the rapid response of the secondary reheat unit to the power grid and load demand;

[0109] S204, integrating the constructed objective function and the corresponding constraint conditions into the multivariable predictive control model for training to obtain the trained multivariable predictive control model, integrating the trained multivariable predictive control model into the furnace side control subsystem, collecting furnace side operation data in real time through sensors, and inputting the real-time collected furnace side operation data into the multivariable predictive control model to obtain the furnace side initial control variable parameters; further, the furnace side initial control variable parameters of this embodiment include fuel flow rate, wind speed, steam pressure in the furnace, excess air coefficient and steam temperature in the furnace;

[0110] Furthermore, the specific steps of obtaining the preliminary peak shaving limit in this embodiment include:

[0111] S401, collecting machine-side attribute data and historical operation data and preprocessing the collected data, the machine-side attribute data includes the maximum threshold of the power output of the secondary reheat unit, the minimum steady-state load, the start-up and shutdown losses, the transient response capability, the safety margin, the steam parameters under the design conditions (such as pressure and temperature), the material properties of the turbine blades, and the design parameters of the flow-through part (such as the flow area and blade shape), and the historical operation data includes the rated power during actual operation, the fluctuation range of steam parameters, the operation efficiency, the start-up and shutdown records, and the performance test data of the second turbine under different loads;

[0112] S402, constructing a turbine peak-shaving interval prediction model through a neural network, and setting an initial peak-shaving interval corresponding to a preliminary peak-shaving limit. The specific formula for the initial peak-shaving interval is:

[0113] ,

[0114] in, represents the initial peak-shaving interval, It represents the safety margin coefficient, which is a coefficient less than 1 set in actual operation to leave room for unforeseen events. In this embodiment, the value is between 0.8 and 0.9. It represents the minimum output power of the steam turbine that can operate stably at time t. This data is obtained by a technician in this field through an experimental process. It represents the additional energy loss caused by the turbine starting from shutdown state to full load or shutting down from full load at time t. It indicates the amount of output power that a steam turbine can increase or decrease per unit time;

[0115] S403, inputting the pre-processed machine-side attribute data and historical operation data into the peak-shaving interval prediction model for training, and obtaining a trained peak-shaving interval prediction model;

[0116] S404, input the real-time collected machine-side operation data and attribute data into the peak-shaving interval prediction model, predict the parameters corresponding to the peak-shaving interval, and use the predicted parameters to calculate the specific peak-shaving interval at the corresponding time; the corresponding parameters in this embodiment include and ;

[0117] Furthermore, in this embodiment, the specific steps of obtaining the initial control variable parameters on the machine side include:

[0118] S405, collecting and preprocessing the machine side operation data and attribute data, and setting the steam valve opening, cooling water volume, and extraction steam pressure setting values ​​as machine side control variables;

[0119] S406, according to all possible control variable combinations within the current operating state and the initial peak regulation limit, set the search space of the parameter search model constructed based on the particle swarm algorithm, and set the turbine reaction objective function and constraint conditions, specifically: , ,in represents the machine side operating efficiency objective function, It indicates the difference between the output power of the secondary reheat unit at the current moment and the output power of the secondary reheat unit at the previous moment. Indicates the corresponding change time, Indicates the efficiency of the steam turbine operation. This value is predicted by the historical operating efficiency data of the steam turbine and the steam turbine efficiency prediction model constructed by the support vector machine to obtain the steam turbine efficiency data at the corresponding moment in the future; represents the corresponding weighting coefficient;

[0120] S407, setting the iteration cycle of the particle swarm algorithm, inputting the pre-processed machine-side operation data and attribute data into the particle swarm algorithm with the objective function and constraint conditions set for training and searching, and obtaining the trained particle swarm parameter search model; the iteration cycle of this embodiment is 200;

[0121] S408, the obtained particle swarm parameter search model is transferred to the machine side control subsystem, the machine side operation data and attribute data collected by the sensor in real time are input into the particle swarm parameter search model, and the initial control variable parameters of the machine side are obtained.

[0122] Example 2

[0123] See also Figure 4 , another embodiment provided by the present invention: a control system for a secondary reheat unit to quickly respond to grid demand, comprising: a data processing module, a furnace side control module, a machine side control module, a wind and photovoltaic power output prediction module and a feedback control module;

[0124] The data processing module is used to collect the monitoring data of the furnace side and the machine side and the load demand power data by using the integrated sensors, and pre-process the collected data. The pre-processing process includes: cleaning, format conversion and standardization;

[0125] The furnace side control module is used to construct a furnace side control and compensation strategy based on the furnace side operation data to optimize the furnace side operation control parameters to improve efficiency and response speed; the furnace side control module includes a multivariable control unit and a dynamic compensation unit;

[0126] The multivariable control unit is used to construct a multivariable predictive control model and obtain the initial control variable parameters of the furnace side according to the obtained furnace side operation data and control strategy; the dynamic compensation unit is used to construct a dynamic compensation strategy, calculate the real-time heat flow distribution information of the furnace side according to the obtained furnace internal temperature field information and compensation strategy, and use the heat flow distribution information to compensate and correct the initial control variable parameters of the furnace side;

[0127] The machine-side control module is used to optimize the steam turbine control parameters according to the acquired machine-side operation data so as to meet the peak load demand; the machine-side control module includes a peak load evaluation unit and a parameter calculation unit;

[0128] The peak load evaluation unit is used to comprehensively evaluate the steam turbine using the evaluation algorithm according to the acquired machine-side attribute data to obtain the preliminary peak load limit of the steam turbine; the parameter calculation unit is used to obtain the initial control variable parameters of the machine-side according to the acquired preliminary peak load limit and the machine-side operation data through the particle swarm algorithm;

[0129] The wind and photovoltaic power output prediction module is used to build and train the wind and photovoltaic power output prediction model, calculate the predicted wind and photovoltaic power output data according to the trained model, and calculate the output power of the secondary reheat unit through the predicted wind and photovoltaic power output data and the load demand power data;

[0130] A feedback control module is used to optimize the control strategies of the furnace side and the machine side according to the obtained output power feedback of the secondary reheat unit, and control the rapid output response of the secondary unit; the feedback control module includes a parameter feedback optimization unit and a discrimination control unit;

[0131] The parameter feedback optimization unit is used to perform feedback optimization on the furnace side initial control variable parameters and the machine side initial control variable parameters according to the obtained secondary reheat unit output power, and obtain the furnace side pre-control variable parameters and the machine side pre-control variable parameters; the discrimination control unit is used to set the secondary reheat unit output threshold, and compare the threshold with the obtained secondary reheat unit output power to determine whether to generate electricity. If power is generated, the obtained furnace side pre-control variable parameters and the machine side pre-control variable parameters are used to control the unit to generate electricity, and output a power value equal to the secondary reheat unit output power to make up for the power missing from the wind and solar power output.

[0132] Example 3

[0133] A computer-readable storage medium stores computer instructions, which, when executed, execute a control method for a secondary reheat unit to quickly respond to grid demand.

[0134] An electronic device comprises a memory and a processor. The memory stores a computer program. When the processor executes the computer program, a control method for a secondary reheat unit to quickly respond to grid demand is implemented.

[0135] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation modes, which are merely illustrative rather than restrictive. Under the guidance of the present invention, ordinary technicians in the field may also change, modify, replace and modify the above-mentioned embodiments without departing from the scope of protection of the purpose of the present invention and the claims, and all of these are within the protection of the present invention.

Claims

1. A control method for a secondary reheat unit to quickly respond to grid demand, characterized in that: The specific steps include: Step S1, obtaining the furnace side and machine side attribute data, monitoring operation data and load demand power data of the secondary reheat unit through the integrated sensor, and preprocessing the collected data; Step S2, constructing a multivariable predictive control model, and obtaining the initial control variable parameters of the furnace side according to the preprocessed furnace side operation data and the multivariable predictive control model; Step S3, introducing a dynamic compensation strategy, obtaining the temperature field inside the furnace, obtaining the real-time heat flux distribution information on the furnace side according to the obtained temperature field inside the furnace and the dynamic compensation strategy, feeding the obtained real-time heat flux distribution information back to the multivariable predictive control model, and compensating and correcting the obtained initial control variable parameters; Step S4, introducing the machine-side peak-shaving strategy, using the evaluation algorithm to evaluate and obtain the preliminary peak-shaving limit of the steam turbine according to the machine-side attribute data, and at the same time, according to the obtained preliminary peak-shaving limit and the machine-side operation data, the parameter search model constructed by the particle swarm algorithm is used to obtain the machine-side initial control variable parameters; Step S5: construct and train a wind and photovoltaic power output prediction model, and calculate the output power of the secondary reheat unit using the wind and photovoltaic power output prediction model according to the acquired wind and photovoltaic power output data and load demand power data; Step S6, setting the output threshold of the secondary reheat unit to 0, feeding back the output power of the secondary reheat unit obtained in step S5 to the multivariable predictive control model and the machine-side peak load regulation strategy, and obtaining the furnace-side pre-control variable parameters and the machine-side pre-control variable parameters; Step S7, compare the output power of the secondary reheat unit obtained in step S5 with the output threshold of the secondary reheat unit. If it is greater than, use the obtained optimal control variable parameters of the front furnace side and the optimal control variable parameters of the front machine side to control the secondary reheat unit, generate electricity according to the calculated output power of the secondary reheat unit, and output a power value equal to the output power of the secondary reheat unit obtained in step S5 to make up for the power missing from the wind and solar power output. If it is equal, the secondary reheat unit remains in a stopped state.

2. The control method for a secondary reheat unit to quickly respond to grid demand according to claim 1, characterized in that: The specific steps of constructing the wind photovoltaic output prediction model in step S5 include: S501. Collect historical wind and photovoltaic power output data, load balance power demand data and weather factor data according to sunny, cloudy, overcast and rainy weather conditions, and pre-process the collected data to construct a multi-weather state input sequence. ;in, represents the i-th weather state data, represents the nth wind and solar power output data in the i-th weather state data, represents the mth load balancing power demand data in the i-th weather state data, Represents the kth weather factor data in the i-th weather state data.

3. The control method for a secondary reheat unit to quickly respond to grid demand as claimed in claim 2, characterized in that: The specific steps of constructing the wind photovoltaic output prediction model in step S5 also include: S502, using a random forest algorithm, constructing a wind and solar power output prediction model including a clear prediction sub-model, a cloudy prediction sub-model, an overcast prediction sub-model, and a rain prediction sub-model in an integrated manner; S503: Input to multiple weather state input sequence , according to the weather state type, it is input into the corresponding sub-model in the photovoltaic output prediction model for training; S504, using historical wind and solar power output data and load balance power demand data at the corresponding time to obtain historical real output errors, and using the wind and solar power output data and load balance power demand data predicted at the corresponding historical time to obtain historical predicted output errors; S505: Setting training threshold According to the historical actual output error and the historical predicted output error, the secondary training error is obtained and the obtained secondary training error is compared with Compare, if it is less than, the training is completed, otherwise, training is continued until the threshold condition is met.

4. The control method for a secondary reheat unit to quickly respond to grid demand as claimed in claim 3, characterized in that: The specific calculation process of predicting the output power of the secondary reheat unit includes: S506: Collect the wind and solar power output data, load balance power demand data and weather factor data for the first 30 hours of the forecast day, input the wind and solar power output data and weather factor data for the first 30 hours into the trained wind and solar power output forecast model, and output the wind and solar power output data for the next 12 hours; S507. Based on the wind and solar power output data and load balance power demand data obtained for the next 12 hours, the output power of the secondary reheat unit is calculated using the load demand balance equation. The load demand balance equation is: ,in, Indicates the power data required for load balance at time t, It represents the predicted power data of wind power output at time t, Represents the output power of the secondary reheat unit at time t.

5. The control method for a secondary reheat unit to quickly respond to grid demand as claimed in claim 4, characterized in that: The specific process steps of step S3 include: S301, constructing a furnace side three-dimensional geometric model through furnace side attribute data, dividing the furnace side three-dimensional geometric model into N monitoring areas using a grid algorithm, and obtaining temperature distribution data of the N monitoring areas in the furnace through the deployed furnace side sensors; S302, according to the acquired temperature distribution data, a heat flux distribution map of each area in the furnace is calculated by combining finite element analysis with thermal radiation and convection fluid dynamics algorithms; S303, feeding back the obtained heat flux distribution map of each area to the initial control variable parameter, using the dynamic temperature compensation formula to calculate the correction value of the initial control variable parameter, and performing compensation correction on the initial control variable parameter.

6. The control method for a secondary reheat unit to quickly respond to grid demand as claimed in claim 5, characterized in that: The dynamic temperature compensation formula is specifically: ， in, represents the compensation amount of the i-th parameter of the initial control variable parameter, represents the parameter dynamic adjustment factor, represents the real-time temperature data corresponding to the jth monitoring area in the furnace, represents the expected temperature data corresponding to the jth monitoring area in the furnace, N represents the number of monitoring areas in the furnace, Indicates temperature deviation The corresponding correction parameters are, Indicates the rate of temperature change The corresponding correction parameters are, Indicates the accumulated temperature deviation The corresponding correction parameters are, Indicates the length of time that the secondary reheat wheel set operates once.

7. The control method for a secondary reheat unit to quickly respond to grid demand as claimed in claim 6, characterized in that: The specific steps of constructing the multivariable predictive control model include: S201, preprocessing furnace-side attribute data, operation data, and load demand power data acquired by the integrated sensor to acquire furnace-side control variable data; S202, constructing a multivariable predictive control model using a support vector machine, and inputting the acquired furnace-side control variable data into the multivariable predictive control model for training; S203, setting the multivariable predictive control model objective function and corresponding constraints to limit the furnace side operating cost, operating efficiency and emissions, so as to minimize fuel consumption while maintaining output power to meet load power requirements.

8. The control method for a secondary reheat unit to quickly respond to grid demand as claimed in claim 7, characterized in that: The specific steps of constructing the multivariable predictive control model also include: S204, integrating the constructed objective function and the corresponding constraint conditions into the multivariable predictive control model for training to obtain the trained multivariable predictive control model; S205, integrating the trained multivariable predictive control model into the furnace side control subsystem, collecting furnace side operation data in real time through sensors, and inputting the real-time collected furnace side operation data into the multivariable predictive control model to obtain the initial control variable parameters of the furnace side.

9. The control method for a secondary reheat unit to quickly respond to grid demand as claimed in claim 8, characterized in that: The objective function and corresponding constraints in S203 specifically include: The specific formula of the objective function is: , The constraints are: ； in, represents the furnace side objective constraint function, It represents the fuel consumption cost of one cycle of furnace operation. It indicates the total amount of pollution emissions corresponding to one cycle of furnace operation. Indicates the actual output power value of the secondary reheat unit at time t; represents the fuel consumption at time t, In turn, they represent the maximum and minimum values ​​of fuel consumption per unit time. represents the wind speed entering the furnace at time t, They represent the maximum and minimum wind speeds entering the furnace at time t, respectively. It represents the maximum threshold of the power output of the secondary reheat unit at time t, It represents the threshold value of the total amount of pollution emissions during one cycle of furnace operation. Represents the corresponding weighting coefficient.

10. The control method for a secondary reheat unit to quickly respond to grid demand as claimed in claim 9, characterized in that: The specific formula of the initial peak-shaving interval corresponding to the preliminary peak-shaving limit in step S4 is: ， in, represents the initial peak-shaving interval, represents the safety margin factor, It represents the minimum output power of the steam turbine that can operate stably at time t. It represents the additional energy loss caused by the turbine starting from shutdown state to full load or shutting down from full load at time t. Indicates the amount of output power that a steam turbine can increase or decrease per unit time.

11. The control method for a secondary reheat unit to quickly respond to grid demand as claimed in claim 10, characterized in that: In the step S4, the steam turbine reaction objective function and constraint conditions are set in the parameter search model, specifically: ， ， in represents the machine side operating efficiency objective function, It indicates the difference between the output power of the secondary reheat unit at the current moment and the output power of the secondary reheat unit at the previous moment. Indicates the corresponding change time, Indicates the efficiency of steam turbine operation. This value is predicted by the historical operation data of steam turbine and the turbine efficiency prediction model constructed by support vector machine. Represents the corresponding weighting coefficient.

12. A control system for a secondary reheat unit to quickly respond to grid demand, which is implemented based on a control method for a secondary reheat unit to quickly respond to grid demand according to any one of claims 1 to 11, characterized in that: include: Data processing module, furnace side control module, generator side control module, wind and photovoltaic power output prediction module and feedback control module; The data processing module is used to collect monitoring data and load demand power data of the furnace side and the machine side using integrated sensors, and pre-process the collected data; The wind and photovoltaic power output prediction module is used to construct and train a wind and photovoltaic power output prediction model, calculate the predicted wind and photovoltaic power output data according to the trained model, and calculate the output power of the secondary reheat unit through the predicted wind and photovoltaic power output data and load demand power data.

13. The control system for a secondary reheat unit that quickly responds to grid demand as claimed in claim 12, characterized in that: The furnace side control module includes a multivariable control unit and a dynamic compensation unit; The multivariable control unit is used to construct a multivariable predictive control model and obtain the initial control variable parameters of the furnace side according to the acquired furnace side operation data and control strategy; the dynamic compensation unit is used to construct a dynamic compensation strategy, calculate the real-time heat flux distribution information of the furnace side according to the acquired temperature field information inside the furnace and the compensation strategy, and use the heat flux distribution information to compensate and correct the initial control variable parameters of the furnace side.

14. The control system for a secondary reheat unit that quickly responds to grid demand as claimed in claim 13, characterized in that: The machine-side control module includes a peak load evaluation unit and a parameter calculation unit; The peak shaving evaluation unit is used to comprehensively evaluate the steam turbine using an evaluation algorithm based on the acquired machine-side attribute data to obtain a preliminary peak shaving limit of the steam turbine; the parameter calculation unit is used to obtain the initial control variable parameters of the machine side through a particle swarm algorithm based on the acquired preliminary peak shaving limit and the machine-side operation data.

15. The control system for a secondary reheat unit that quickly responds to grid demand as claimed in claim 14, characterized in that: The feedback control module includes a parameter feedback optimization unit and a discrimination control unit; The parameter feedback optimization unit is used to perform feedback optimization on the furnace side initial control variable parameters and the machine side initial control variable parameters according to the obtained secondary reheat unit output power, and obtain the furnace side pre-control variable parameters and the machine side pre-control variable parameters; the discrimination control unit is used to set the secondary reheat unit output threshold, and compare the threshold with the obtained secondary reheat unit output power to obtain whether to generate electricity. If power generation is to be performed, the obtained furnace side pre-control variable parameters and the machine side pre-control variable parameters are used to control the unit to generate electricity, and output a power value equal to the secondary reheat unit output power.

16. A computer-readable storage medium, characterized in that: Computer instructions are stored thereon, and when the computer instructions are executed, the control method for the secondary reheat unit to quickly respond to the power grid demand as described in any one of claims 1-11 is executed.

17. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the control method for the secondary reheat unit to quickly respond to power grid demand as described in any one of claims 1-11 is implemented.

Images