A method, device, and storage medium for shutdown control of a thermal power unit

Abstract

The application discloses a kind of shutdown control method, device, equipment and storage medium of thermal power generating unit.The method determines the corresponding set value curve for the target operating parameter of thermal power generating unit in the first shutdown phase;In the second shutdown phase, the control parameter of temperature reducing water for main steam and reheat steam is determined for thermal power generating unit;In the third shutdown phase, at least one target load point of shutdown sub-operation is determined for thermal power generating unit;In the fourth shutdown phase, the PID control parameter of temperature reducing water for main steam and reheat steam is determined for thermal power generating unit, and the stable operation of thermal power generating unit is controlled according to the PID control parameter.The technical scheme of the present application reduces the fluctuation range of main parameters in the process of sliding parameter shutdown, improves the response speed of main steam and reheat steam temperature in the process of temperature reduction, optimizes the entire sliding parameter shutdown process in the form of automatic takeover or recommended guidance, improves the safety of unit, saves the time required for sliding parameter shutdown, and reduces the operating pressure of thermal power generating unit operator.

Description

Technical Field

[0001] This invention relates to the field of thermal power unit shutdown technology, and in particular to a shutdown control method, device, equipment and storage medium for thermal power units. Background Technology

[0002] Thermal power units require regular shutdowns for maintenance to ensure safe operation. Maintenance is categorized into four levels: A, B, C, and D. Level C maintenance typically takes 20-30 days per operation. The first step is to gradually reduce the main and reheat steam temperatures, lowering the high and intermediate pressure rotor probe temperatures to create conditions for turbine turning gear shutdown. The duration of this process significantly impacts the schedule of subsequent maintenance work. Using traditional shutdown methods, reducing the main and reheat steam temperatures to the required levels takes approximately 120 hours, significantly increasing maintenance time. In contrast, using sliding parameter shutdown methods, this can be completed in about 48 hours, greatly saving downtime.

[0003] In the process of developing this invention, the inventors discovered the following defects in the prior art:

[0004] Currently, during sliding parameter shutdowns, problems such as large fluctuations in feedwater flow and main steam temperature, and complex control of desuperheating water flow are often encountered. These issues require frequent intervention from experienced operators; otherwise, the turbine rotor stress may easily exceed the limit during low-load periods, affecting the safety of the unit. Summary of the Invention

[0005] This invention provides a shutdown control method, device, equipment, and storage medium for thermal power units to reduce the fluctuation range of key parameters during sliding parameter shutdown, improve the response speed of main and reheat steam temperatures during desuperheating, optimize the entire sliding parameter shutdown process through automatic takeover or recommended guidance, enhance unit safety, save time required for sliding parameter shutdown, and reduce the operational pressure on thermal power unit operators.

[0006] According to one aspect of the present invention, a shutdown control method for a thermal power unit is provided, the method comprising:

[0007] In the first shutdown phase, the setpoint curve corresponding to the target operating parameters of the thermal power unit is determined, and the thermal power unit is controlled to operate to the second shutdown phase according to the setpoint curve.

[0008] During the second shutdown phase, the desuperheating water control parameters for the main steam and reheat steam of the thermal power unit are determined, and the thermal power unit is controlled to operate to the third shutdown phase based on the desuperheating water control parameters.

[0009] In the third shutdown phase, a target load point corresponding to at least one shutdown sub-operation of the thermal power unit is determined, and the at least one shutdown sub-operation is executed according to each target load point to make the thermal power unit run to the fourth shutdown phase;

[0010] During the fourth shutdown phase, proportional-integral-derivative (PID) control parameters for the main steam and the reheat steam are determined, and the thermal power unit is controlled to operate stably based on the PID control parameters.

[0011] According to another aspect of the present invention, a shutdown control device for a thermal power unit is provided, the device comprising:

[0012] The first-stage control module is used to determine the set value curve corresponding to the target operating parameters of the thermal power unit in the first shutdown stage when the shutdown begins, and control the thermal power unit to run to the second shutdown stage according to the set value curve.

[0013] The second-stage control module is used to determine the desuperheating water control parameters for the main steam and reheat steam of the thermal power unit during the second shutdown stage, and control the thermal power unit to run to the third shutdown stage according to the desuperheating water control parameters.

[0014] The third-stage control module is used to determine, in the third shutdown stage, the target load point corresponding to at least one shutdown sub-operation of the thermal power unit, and execute the at least one shutdown sub-operation according to each target load point to make the thermal power unit run to the fourth shutdown stage;

[0015] The fourth-stage control module is used to determine the proportional-integral-derivative (PID) control parameters for the main steam and the reheat steam during the fourth shutdown stage, and to control the thermal power unit to operate stably according to the PID control parameters.

[0016] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0017] At least one processor; and

[0018] A memory communicatively connected to the at least one processor; wherein,

[0019] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the shutdown control method for thermal power units according to any embodiment of the present invention.

[0020] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions, the computer instructions being configured to cause a processor to execute and implement the shutdown control method for thermal power units according to any embodiment of the present invention.

[0021] The technical solution of this invention addresses the following issues during sliding-parameter shutdown: First, in the initial shutdown phase, setpoint curves are determined for the target operating parameters of the thermal power unit; in the second shutdown phase, desuperheating water control parameters for the main steam and reheat steam are determined; in the third shutdown phase, target load points corresponding to at least one shutdown sub-operation are determined; and in the fourth shutdown phase, proportional-integral-derivative (PID) control parameters for the main steam and reheat steam are determined. Based on these PID control parameters, the thermal power unit is controlled to operate stably. This solution solves the problems of large fluctuations in feedwater flow and steam temperature, complex desuperheating water flow control, and the need for frequent intervention by experienced operators during sliding-parameter shutdowns. Otherwise, turbine rotor stress can easily exceed limits during low-load phases, affecting unit safety. The solution also reduces the fluctuation range of key parameters during sliding-parameter shutdowns, improves the response speed of main and reheat steam temperatures during desuperheating, and optimizes the entire sliding-parameter shutdown process through automatic takeover or recommended guidance. This enhances unit safety, saves time required for sliding-parameter shutdowns, and reduces the operational burden on thermal power unit operators.

[0022] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used 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 those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1a This is a flowchart of a shutdown control method for a thermal power unit provided in Embodiment 1 of the present invention;

[0025] Figure 1b This is a schematic diagram of a thermal power unit shutdown control system provided in Embodiment 1 of the present invention;

[0026] Figure 2a A flowchart of another shutdown control method for thermal power units provided in Embodiment 2 of the present invention;

[0027] Figure 2bThis is a schematic diagram illustrating the construction of a preset turbine rotor stress boundary model provided in Embodiment 2 of the present invention;

[0028] Figure 2c This is a schematic diagram illustrating the construction of a pre-constructed desuperheating water prediction model, taking the main steam system as an example, as provided in Embodiment 2 of the present invention.

[0029] Figure 2d This is a schematic diagram of the optimization of main steam temperature control parameters of the main steam system based on the distributed particle swarm algorithm, provided in Embodiment 2 of the present invention.

[0030] Figure 3 This is a schematic diagram of the structure of a shutdown control device for a thermal power unit provided in Embodiment 3 of the present invention;

[0031] Figure 4 This is a schematic diagram of the structure of an electronic device for implementing the shutdown control method of a thermal power unit according to an embodiment of the present invention. Detailed Implementation

[0032] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0033] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0034] Example 1

[0035] Figure 1aThis is a flowchart of a shutdown control method for a thermal power unit provided in Embodiment 1 of the present invention. This embodiment is applicable to the situation of shutdown control of thermal power units. The method can be executed by a shutdown control device of the thermal power unit. The shutdown control device of the thermal power unit can be implemented in hardware and / or software and can be configured in the shutdown control system of the thermal power unit.

[0036] refer to Figure 1b The thermal power unit shutdown control system in this embodiment can adopt a three-layer architecture: an intelligent control layer, a DCS (Distributed Control System) layer, and an actuator layer. The intelligent control layer primarily performs big data analysis, builds relational models, and optimizes controller parameters. The optimized setpoints and control parameters derived from the intelligent control layer need to be transmitted to the DCS layer for control optimization. This requires optimizing the existing logic configuration in the DCS to achieve seamless switching between the thermal power unit shutdown control system and the original control system. Simultaneously, the DCS system also needs to transmit historical operating data to the intelligent server in the intelligent control layer, providing the necessary historical operating data for modeling and control optimization. Finally, the DCS system sends control commands to the actuators of the relevant control loops to achieve a closed-loop control.

[0037] like Figure 1a As shown, the method includes:

[0038] S110. In the first shutdown stage at the start of shutdown, determine the setpoint curve corresponding to the target operating parameters of the thermal power unit, and control the thermal power unit to operate to the second shutdown stage according to the setpoint curve.

[0039] Thermal power units can be those that use coal, oil, or combustible gases as fuel to heat water in a boiler, thereby increasing its temperature, and then use pressurized steam to drive a gas turbine to generate electricity. Target operating parameters may include load, main steam temperature, and reheat steam temperature.

[0040] In this embodiment, during the shutdown of the thermal power unit, the load of the unit gradually decreases, and the control strategies required for different load stages also differ. This embodiment divides the shutdown process into four stages based on the load. For example, if the capacity of the thermal power unit is 600MW, the second shutdown stage begins when the load drops to 75% (450MW), the third shutdown stage begins when the load drops to 50% (300MW), and the fourth shutdown stage begins when the load drops to 20% (120MW).

[0041] In one optional implementation, determining the setpoint curve corresponding to the target operating parameters of the thermal power unit during the first shutdown phase can include: obtaining the current value of the target operating parameters of the thermal power unit during the first shutdown phase; determining the expected rate of decrease of the target operating parameters under each load based on the current value and a preset turbine rotor stress boundary model, based on the upper limit value of the turbine rotor stress of the thermal power unit; and determining the setpoint curve corresponding to the target operating parameters based on the current value and the expected rate of decrease.

[0042] The current values ​​of the target operating parameters can be the current load, the current main steam temperature, and the current reheat steam temperature. The expected rate of decrease can refer to the expected load reduction rate, the expected main steam temperature reduction rate, and the expected reheat steam temperature reduction rate under the condition of the upper limit of turbine rotor stress during the first shutdown phase.

[0043] The preset turbine rotor stress boundary model is mainly a model showing the relationship between the load reduction rate, main steam cooling rate, reheat steam cooling rate and turbine rotor stress during the high load stage (first shutdown stage). It is used to formulate the set curves of load, main steam temperature and reheat steam temperature to achieve automatic load reduction, main steam temperature reduction and reheat temperature reduction.

[0044] Combustion in thermal power boilers is a complex process involving multiple variables and strong coupling nonlinear systems. Constructing a model of the relationship between load, main steam temperature, reheat steam temperature, and turbine rotor stress using mechanistic modeling methods is virtually impossible. Therefore, data modeling methods are considered to construct a model of the relationship between the load reduction rate, main steam cooling rate, reheat steam cooling rate, and turbine rotor stress during high-load phases. This is a typical multivariate nonlinear regression problem, suitable for modeling using neural networks. A neural network is an algorithmic model that mimics the structure and operation of the human brain's neural network. It consists of many simple units or neurons, each receiving input from other neurons and combining these inputs into an output. Neural networks typically consist of multiple layers, including input layers, hidden layers, and output layers, each layer containing several neurons. Training of neural networks usually employs the backpropagation algorithm, which updates the neural network weights by calculating the error gradient to make the neural network's output as close to reality as possible.

[0045] In this embodiment, the current load value, the current main steam temperature value, and the current reheat steam temperature value are input into a preset turbine rotor stress boundary model to determine the expected load reduction rate, the expected main steam cooling rate, and the expected reheat steam cooling rate. Based on the current load value and the expected load reduction rate, the setpoint curve of the load is determined; based on the current main steam temperature value and the expected main steam cooling rate, the setpoint curve of the main steam is determined; and based on the current reheat steam temperature value and the expected reheat steam cooling rate, the setpoint curve of the reheat steam is determined.

[0046] S120. In the second shutdown phase, determine the desuperheating water control parameters for the main steam and reheat steam of the thermal power unit, and control the thermal power unit to operate in the third shutdown phase according to the desuperheating water control parameters.

[0047] The main steam system, located within the boiler, is a component used to reheat the exhaust steam from the high-pressure or intermediate-pressure cylinders of the steam turbine to the required temperature. Its function is to deliver the steam generated by the boiler to various steam-consuming points. It includes all piping and accessories from the boiler superheater outlet to the turbine inlet, from the turbine high-pressure cylinder exhaust to the boiler reheater inlet (reheat cold section piping), and from the reheater outlet to the turbine pressure cylinder inlet (hot section reheat steam piping). After the superheated steam performs work in the turbine, its pressure and temperature decrease. To recycle this steam, it is returned to the boiler's reheater for reheating, improving its quality, and then used for work again. In short, the steam passing through the reheater is called reheat steam. Desuperheating water is used to lower the temperature of both the main steam and the reheat steam. Desuperheating water control parameters can refer to the opening degree and duration of the desuperheating water valve.

[0048] During the load reduction phase, the main steam and reheat steam are prone to entering the saturation zone, resulting in prolonged periods of no temperature change. Traditional cascade steam temperature control adjusts the opening of the desuperheating water valve based on the temperature deviation. In this situation, the desuperheating water valve may not open in time, leading to significant fluctuations in the main steam temperature, which is not conducive to the load reduction and shutdown of thermal power units.

[0049] Therefore, in this embodiment, the desuperheating water control parameters for the main steam and reheat steam of the thermal power unit can be determined in the second shutdown phase in the following way:

[0050] During the second shutdown phase, the following operations are performed on both the main steam and reheat steam:

[0051] The process involves acquiring the initial steam state, target steam state, and desuperheating water temperature. The initial steam state includes the initial steam temperature and initial steam flow rate, while the target steam state includes the target steam temperature and target steam flow rate. Based on the initial steam state, target steam state, desuperheating water temperature, and a pre-built desuperheating water prediction model, the total desuperheating water demand of the thermal power unit is determined. Based on the total desuperheating water demand and the flow characteristics of the desuperheating water valves, the target opening degree and duration of the target opening degree of the desuperheating water valves are determined. The flow characteristics of the desuperheating water valves include the correspondence between the valve opening degree and the desuperheating water flow rate.

[0052] The initial steam temperature refers to the initial temperature of the main steam and reheat steam during the second shutdown phase. The target steam temperature refers to the expected temperature of the main steam and reheat steam at the end of the second shutdown phase. The desuperheating water temperature is generally ambient temperature. The total desuperheating water demand refers to the total amount of desuperheating water required to reduce the steam temperature from its initial state during the second shutdown phase to the target state. The pre-built desuperheating water prediction model can accurately calculate the desuperheating water flow rate required during the load reduction phase and provide sufficient desuperheating water flow rate in advance using a feedforward approach, thereby improving the control effect of cascade PID steam temperature.

[0053] In this embodiment, the initial steam state, target steam state, and desuperheating water temperature are input into a pre-constructed desuperheating water prediction model to determine the total desuperheating water demand during the second shutdown phase. Furthermore, based on a pre-determined correspondence between the desuperheating water valve opening and the desuperheating water flow rate, the target opening degree of the desuperheating water valve and the duration of the target opening degree under this correspondence are determined.

[0054] S130. In the third shutdown phase, determine the target load point corresponding to at least one shutdown sub-operation of the thermal power unit, and execute at least one shutdown sub-operation according to each target load point to make the thermal power unit run to the fourth shutdown phase.

[0055] At least one of the shutdown sub-operations may include switching between electric and steam pumps, shutting down the mill, starting the high-pressure bypass, and shutting down the high-pressure heater. The target load point may refer to the load point corresponding to the minimum turbine rotor stress when the shutdown sub-operation is executed.

[0056] In one alternative implementation, during the third shutdown phase, determining the target load points corresponding to at least one shutdown sub-operation of the thermal power unit, and performing at least one shutdown sub-operation based on each target load point to run the thermal power unit to the fourth shutdown phase, may include: obtaining historical target load points corresponding to at least one shutdown sub-operation from a pre-built initial benchmark library; determining the historical target load points as target load points; and instructing operators to perform at least one shutdown sub-operation based on the target load points to run the thermal power unit to the fourth shutdown phase.

[0057] The pre-built initial benchmark library can include the correspondence between shutdown sub-operations and historical target load points in historical shutdown phases. In this embodiment, the historical target load point corresponding to the shutdown sub-operation in the initial benchmark library can be pushed to the operator as the target load point for the current third shutdown phase. The operator can judge whether the target load point is suitable based on experience. If it is suitable, the corresponding shutdown sub-operation can be executed at the target load point. If it is not suitable, the target load point can be adjusted before executing the corresponding shutdown sub-operation.

[0058] S140. In the fourth shutdown phase, determine the proportional-integral-derivative (PID) control parameters for the main steam and reheat steam, and control the thermal power unit to operate stably based on the PID control parameters.

[0059] In this embodiment, during the shutdown closing stage (i.e., the fourth shutdown stage), it is sometimes necessary to conduct some experiments on the thermal power unit under low load conditions. At this time, it is necessary to ensure that the thermal power unit operates stably under low load conditions. However, the characteristics of the steam temperature system under low load conditions are very different from those under normal operation. Therefore, it is necessary to quickly find the PID parameters suitable for the low load steam temperature system to avoid large fluctuations in the main steam temperature.

[0060] The technical solution of this invention addresses the following issues during sliding-parameter shutdown: First, in the initial shutdown phase, setpoint curves are determined for the target operating parameters of the thermal power unit; in the second shutdown phase, desuperheating water control parameters for the main steam and reheat steam are determined; in the third shutdown phase, target load points corresponding to at least one shutdown sub-operation are determined; and in the fourth shutdown phase, proportional-integral-derivative (PID) control parameters for the main steam and reheat steam are determined. Based on these PID control parameters, the thermal power unit is controlled to operate stably. This solution solves the problems of large fluctuations in feedwater flow and steam temperature, complex desuperheating water flow control, and the need for frequent intervention by experienced operators during sliding-parameter shutdowns. Otherwise, turbine rotor stress can easily exceed limits during low-load phases, affecting unit safety. The solution also reduces the fluctuation range of key parameters during sliding-parameter shutdowns, improves the response speed of main and reheat steam temperatures during desuperheating, and optimizes the entire sliding-parameter shutdown process through automatic takeover or recommended guidance. This enhances unit safety, saves time required for sliding-parameter shutdowns, and reduces the operational burden on thermal power unit operators.

[0061] Example 2

[0062] Figure 2a This is a flowchart of another shutdown control method for thermal power units provided in Embodiment 2 of the present invention. Based on the above embodiments, this embodiment refines the operation of determining the proportional-integral-derivative (PID) control parameters for main steam and reheat steam in the fourth shutdown stage. For example... Figure 2a As shown, the method includes:

[0063] S210. In the first shutdown stage at the start of shutdown, determine the setpoint curve corresponding to the target operating parameters of the thermal power unit, and control the thermal power unit to operate to the second shutdown stage according to the setpoint curve.

[0064] During the first shutdown phase, the current values ​​of the target operating parameters of the thermal power unit are obtained; based on the current values ​​and the preset turbine rotor stress boundary model, the expected rate of decrease of the target operating parameters under each load is determined based on the upper limit value of the turbine rotor stress of the thermal power unit; based on the current values ​​and the expected rate of decrease, the setpoint curves corresponding to the target operating parameters are determined.

[0065] The preset turbine rotor stress boundary model can be obtained in the following ways:

[0066] Step 1: Obtain historical operating data of thermal power units and determine multiple historical shutdown start points and historical shutdown end points from the historical operating data;

[0067] Step 2: Based on multiple sets of historical shutdown start points and historical shutdown end points, filter multiple sets of historical operation data for shutdown phases from the historical operation data;

[0068] Step 3: Obtain load sample data, main steam temperature sample data, reheat steam temperature sample data, and turbine rotor stress sample data from the historical operating data of each shutdown phase;

[0069] Step 4: Perform backward differential processing on the load sample data, main steam temperature sample data, and reheat steam temperature sample data according to the preset sampling interval to determine the load reduction rate, main steam cooling rate, and reheat steam cooling rate.

[0070] Step 5: Based on the average value of the two data before and after each preset sampling interval, perform sample data addition processing on the load sample data, main steam temperature sample data and reheat steam temperature sample data respectively to obtain the processed load sample data, processed main steam temperature sample data and processed reheat steam temperature sample data.

[0071] Step 6: Using the load reduction rate, main steam cooling rate, reheat steam cooling rate, processed load sample data, processed main steam temperature sample data, and processed reheat steam temperature sample data as inputs, and the turbine rotor stress sample data as outputs, train the neural network model to obtain the preset turbine rotor stress boundary model.

[0072] For details, please refer to Figure 2b First, the intelligent server can collect massive amounts of historical operating data from the DCS system through the data interface. It can filter historical data of the shutdown phase by labeling "load". Specifically, it can mark the points in the historical operating data where the load is 0, take each point where the load is 0 as the starting point (equivalent to the historical shutdown end point), find the first point where the load is not 0 (equivalent to the historical shutdown start point), and collect the unit's historical operating data for the 120 hours before that non-zero point, thus obtaining the initial screened historical data of the shutdown phase.

[0073] Next, the historical data of the initial shutdown phase can be further filtered. In order to ensure that the shutdown data is covered as completely as possible, the 120-hour collection interval set in step (1) is used. However, most shutdown processes may not last that long. Therefore, a second judgment needs to be made manually to determine the accurate shutdown start position in order to obtain the final historical operation data of the shutdown phase (equivalent to multiple sets of historical operation data of the shutdown phase).

[0074] Further, a dataset was constructed using "load," "main steam temperature," "reheat steam temperature," and "turbine rotor stress." Since the goal is to establish a model relating the load reduction rate, cooling rate, and turbine rotor stress, the basic data needs to be processed to obtain the "load reduction rate" and "cooling rate." Specifically, a suitable sampling interval (generally 5-10 seconds) was selected to discretize the data. Back-difference was performed on "load," "main steam temperature," and "reheat steam temperature" to obtain the "load reduction rate," "main steam cooling rate," and "reheat steam cooling rate." Simultaneously, the average of the two "load," "main steam temperature," "reheat steam temperature," and "turbine rotor stress" values ​​before and after each sampling interval was calculated as new data. This completed the processing of the modeling dataset.

[0075] Finally, a neural network model was built and trained using a modeling dataset. The model inputs were: load reduction rate (x1), main steam cooling rate (x2), reheat steam cooling rate (x3), load (x4), main steam temperature (x5), and reheat steam temperature (x6); the model output was the turbine rotor stress (y). After the model training was completed, the upper limit of the turbine rotor stress was determined according to the turbine design parameters. The allowable values ​​of "load reduction rate," "main steam cooling rate," and "reheat steam cooling rate" under each load were calculated, and based on this, setpoint curves for "load," "main steam temperature," and "reheat steam temperature" during the high-load phase were established.

[0076] This operation establishes a model relating the load reduction rate, cooling rate, and turbine rotor stress. This model quantitatively defines the set boundaries for the load reduction rate and cooling rate, replacing the trial-and-error method based on human experience, and reducing the fluctuation range of key parameters such as main and reheat steam temperatures during shutdown.

[0077] S220. In the second shutdown phase, determine the desuperheating water control parameters for the main steam and reheat steam of the thermal power unit, and control the thermal power unit to operate in the third shutdown phase according to the desuperheating water control parameters.

[0078] During the second shutdown phase, the following operations are performed on both the main steam and reheat steam:

[0079] Obtain the initial steam state, target steam state, and desuperheating water temperature; determine the total desuperheating water demand of the thermal power unit based on the initial steam state, target steam state, desuperheating water temperature, and the pre-built desuperheating water prediction model; determine the target opening degree and duration of the desuperheating water valve based on the total desuperheating water demand and the flow characteristics of the desuperheating water valve.

[0080] Based on the principle of energy conservation, the heat released by fuel combustion is ultimately absorbed by steam at a fixed energy conversion ratio. The energy change during the load reduction phase can be calculated using the steam state parameters and fuel quantity parameters at the beginning and end of the load reduction stage. After eliminating the heat difference caused by changes in fuel quantity, the energy transfer process during the load reduction stage can be equivalently viewed as the heat released by the main steam as it cools from its initial state to its final state being absorbed by the injected desuperheating water, which then transforms into steam in the final state.

[0081] Based on the above analysis, taking the main steam system as an example, Figure 2c This is a schematic diagram illustrating the construction of a pre-built desuperheating water prediction model provided in Embodiment 2.

[0082] A steam energy model (desuperheating water prediction model) is established using parameters such as main steam temperature, main steam flow rate, desuperheating water temperature, and desuperheating water flow rate. The initial main steam temperature and flow rate, as well as the target main steam temperature, flow rate, and desuperheating water temperature, are all known quantities (the heat difference of the fuel quantity has been eliminated). The total amount of desuperheating water required during the load reduction stage can be calculated using this model.

[0083] Finally, data on the opening degree of the desuperheating water valve and the flow rate of the desuperheating water were collected to determine the relationship between the valve opening degree and the flow rate. Based on the required flow rate of the desuperheating water, the required opening degree and duration of the desuperheating water valve were determined.

[0084] The above method enables accurate prediction of the desuperheating water flow rate during the shutdown and load reduction phase, greatly improving the control effect of the steam temperature control system when the main steam and reheat steam enter the saturation zone, reducing the fluctuation range of steam temperature during the shutdown and load reduction phase, improving the response speed of the main and reheat steam temperatures during the desuperheating process, and further saving the time required for sliding parameter shutdown.

[0085] S230. In the third shutdown phase, determine the target load point corresponding to at least one shutdown sub-operation of the thermal power unit, and execute at least one shutdown sub-operation according to each target load point to make the thermal power unit run to the fourth shutdown phase.

[0086] Specifically, in the third shutdown phase, historical target load points corresponding to at least one shutdown sub-operation can be obtained from the pre-built initial benchmark library; the historical target load points are determined as target load points, and operators are instructed to perform at least one shutdown sub-operation based on the target load points to run the thermal power unit to the fourth shutdown phase.

[0087] The initial benchmark library is constructed in the following way: obtaining the standard load intervals corresponding to at least one shutdown sub-operation; taking the minimum turbine rotor stress as the objective, obtaining the historical target load points corresponding to at least one shutdown sub-operation from multiple sets of historical operating data during the shutdown phase; using the standard load intervals as the boundaries of the initial benchmark library, and constructing the initial benchmark library based on the historical target load points corresponding to at least one shutdown sub-operation.

[0088] Optionally, after executing at least one shutdown sub-operation based on each target load point to bring the thermal power unit to the fourth shutdown stage, the following can also be done: record the actual load point and actual turbine rotor stress corresponding to at least one shutdown operation in the third stage shutdown operation; compare the actual correspondence between the actual load point and the actual turbine rotor stress with the historical correspondence matched in the initial benchmark library; if the actual turbine rotor stress in the actual correspondence is less than the historical turbine rotor stress in the historical correspondence, update the historical correspondence in the initial benchmark library using the actual correspondence.

[0089] By optimizing historical data, the optimal load points for operations such as switching between electric pumps and steam pumps, mill shutdown, high-pressure bypass start-up, and high-pressure heater shutdown are found. The latest data is collected during each shutdown process and iteratively updated to achieve rolling optimization.

[0090] S240. In the fourth shutdown phase, operations S240-S270 are performed for both main steam and reheat steam: the cascade PID control loop is obtained according to the preset transfer function, and the current steam temperature is obtained.

[0091] The preset transfer function can be obtained in the following ways:

[0092] Multiple sets of shutdown phase sample data matching the fourth shutdown phase were obtained from historical operation data of multiple shutdown phases. These shutdown phase sample data included the steam temperature, the temperature of the superheated desuperheating water after spraying, and the valve opening of the superheated desuperheating water in the fourth shutdown phase. The initial transfer function was then calculated based on the shutdown phase sample data and a preset particle swarm optimization algorithm (traditional particle swarm optimization algorithm). The parameters K, T, n, and τ are optimized, and the preset transfer function is determined based on the optimization results; where K represents the gain, T represents the inertia time, n represents the order, and τ represents the delay time. That is, the transfer function of the main steam system during the historical fourth-stage operation is identified using the collected historical operating data. This step can be performed offline based on the historical operating data, and there is no speed limit for the identification. Based on the general control system transfer function structure: The parameters K, T, n, and τ can be identified by using the traditional particle swarm optimization algorithm for regression optimization.

[0093] S250: Obtain the current steam temperature through the cascade PID control loop and determine the absolute value of the deviation based on the output temperature and the preset desired output temperature.

[0094] S260. With the goal of minimizing the integral of the absolute value of the deviation over time, the PID control parameters of the cascade PID control loop are optimized using a distributed particle swarm optimization algorithm to determine the PID control parameters.

[0095] For the operation of S250 and S260, taking the main steam system as an example, please refer to... Figure 2d A simulation loop (i.e., a cascaded PID control loop) can be built based on the preset transfer function of S240 to optimize the PID parameters, typically aiming to minimize the absolute value of the deviation multiplied by the time integral. Traditional particle swarm optimization algorithms require hundreds or thousands of particles to iterate for hundreds of generations to obtain the optimal parameters. However, since the PID parameters need to be transmitted to the controller in real time, the optimization results need to be obtained within a short time, making traditional particle swarm optimization algorithms unsuitable for this scenario. This invention proposes a distributed particle swarm optimization algorithm to solve this problem. Essentially, distributed particle swarm optimization is an optimization algorithm that sacrifices spatial dimension to optimize the time dimension. Thanks to the powerful parallel computing capabilities of current processors, this algorithm can be implemented at a relatively low cost. The distributed particle swarm optimization algorithm improves optimization efficiency through a distributed-total optimization approach. Its principle is as follows: multiple small-scale particle swarm optimizations are executed in parallel by distributed computing units to obtain preliminary optimization solutions and narrow down the optimization domain. Then, the best result in the distributed optimization is used as the initial state for the secondary optimization, and the union of all optimization solutions is used as the new optimization domain. Another small-scale optimization is then performed to obtain the final optimized PID parameters.

[0096] The adaptive sliding parameter shutdown control system for thermal power units designed in this invention effectively solves problems such as large fluctuations in feedwater flow and main steam temperature, complex control of desuperheating water flow, and difficulty in determining control parameters in traditional sliding parameter shutdown by integrating the above-mentioned control methods. Applying the adaptive sliding parameter shutdown control system for thermal power units enables fully automated sliding parameter shutdown, achieving both rapid and safe shutdown, and significantly reducing the operational burden on thermal power unit operators.

[0097] A distributed particle swarm optimization algorithm is adopted to implement a distributed-total parallel optimization, which reduces the number of iterations for a single optimization and improves the efficiency of PID parameter optimization.

[0098] S270: Control the thermal power unit to operate stably according to PID control parameters.

[0099] The technical solution of this invention addresses the following issues during sliding-parameter shutdown: First, in the initial shutdown phase, setpoint curves are determined for the target operating parameters of the thermal power unit; in the second shutdown phase, desuperheating water control parameters for the main steam and reheat steam are determined; in the third shutdown phase, target load points corresponding to at least one shutdown sub-operation are determined; and in the fourth shutdown phase, proportional-integral-derivative (PID) control parameters for the main steam and reheat steam are determined. Based on these PID control parameters, the thermal power unit is controlled to operate stably. This solution solves the problems of large fluctuations in feedwater flow and steam temperature, complex desuperheating water flow control, and the need for frequent intervention by experienced operators during sliding-parameter shutdowns. Otherwise, turbine rotor stress can easily exceed limits during low-load phases, affecting unit safety. The solution also reduces the fluctuation range of key parameters during sliding-parameter shutdowns, improves the response speed of main and reheat steam temperatures during desuperheating, and optimizes the entire sliding-parameter shutdown process through automatic takeover or recommended guidance. This enhances unit safety, saves time required for sliding-parameter shutdowns, and reduces the operational burden on thermal power unit operators.

[0100] Example 3

[0101] Figure 3 This is a schematic diagram of the structure of a shutdown control device for a thermal power unit provided in Embodiment 3 of the present invention. Figure 3 As shown, the device includes: a first-stage control module 310, a second-stage control module 320, a third-stage control module 330, and a fourth-stage control module 340. Wherein:

[0102] The first-stage control module 310 is used to determine the set value curve corresponding to the target operating parameters of the thermal power unit in the first shutdown stage when the shutdown begins, and control the thermal power unit to run to the second shutdown stage according to the set value curve.

[0103] The second-stage control module 320 is used to determine the desuperheating water control parameters for the main steam and reheat steam of the thermal power unit during the second shutdown stage, and control the thermal power unit to run to the third shutdown stage according to the desuperheating water control parameters.

[0104] The third-stage control module 330 is used to determine, in the third shutdown stage, a target load point corresponding to at least one shutdown sub-operation of the thermal power unit, and execute the at least one shutdown sub-operation according to each target load point to make the thermal power unit run to the fourth shutdown stage;

[0105] The fourth-stage control module 340 is used to determine the proportional-integral-derivative (PID) control parameters for the main steam and the reheat steam during the fourth shutdown stage, and to control the thermal power unit to operate stably according to the PID control parameters.

[0106] The technical solution of this invention addresses the following issues during sliding-parameter shutdown: First, in the initial shutdown phase, setpoint curves are determined for the target operating parameters of the thermal power unit; in the second shutdown phase, desuperheating water control parameters for the main steam and reheat steam are determined; in the third shutdown phase, target load points corresponding to at least one shutdown sub-operation are determined; and in the fourth shutdown phase, proportional-integral-derivative (PID) control parameters for the main steam and reheat steam are determined. Based on these PID control parameters, the thermal power unit is controlled to operate stably. This solution solves the problems of large fluctuations in feedwater flow and steam temperature, complex desuperheating water flow control, and the need for frequent intervention by experienced operators during sliding-parameter shutdowns. Otherwise, turbine rotor stress can easily exceed limits during low-load phases, affecting unit safety. The solution also reduces the fluctuation range of key parameters during sliding-parameter shutdowns, improves the response speed of main and reheat steam temperatures during desuperheating, and optimizes the entire sliding-parameter shutdown process through automatic takeover or recommended guidance. This enhances unit safety, saves time required for sliding-parameter shutdowns, and reduces the operational burden on thermal power unit operators.

[0107] Optionally, the loads corresponding to the first shutdown phase, the second shutdown phase, the third shutdown phase, and the fourth shutdown phase are reduced sequentially.

[0108] Accordingly, the first-stage control module 310 can be specifically used for:

[0109] During the first shutdown phase, the current values ​​of the target operating parameters of the thermal power unit are obtained; wherein, the target operating parameters include load, main steam temperature and reheat steam temperature;

[0110] Based on the current value and the preset turbine rotor stress boundary model, the expected rate of decrease of the target operating parameters under each load is determined based on the upper limit value of the turbine rotor stress of the thermal power unit.

[0111] Based on the current value and the expected descent rate, determine the setpoint curve corresponding to the target operating parameter.

[0112] Optionally, the preset turbine rotor stress boundary model is obtained in the following way:

[0113] The historical operating data of the thermal power unit is obtained, and multiple sets of historical shutdown start points and historical shutdown end points are determined from the historical operating data;

[0114] Based on the multiple sets of historical shutdown start points and historical shutdown end points, multiple sets of historical operation data for shutdown phases are filtered from the historical operation data;

[0115] Load sample data, main steam temperature sample data, reheat steam temperature sample data, and turbine rotor stress sample data are obtained from the historical operating data of each shutdown phase.

[0116] The load sample data, the main steam temperature sample data, and the reheat steam temperature sample data are subjected to backward differential processing according to the preset sampling interval to determine the load reduction rate, the main steam cooling rate, and the reheat steam cooling rate.

[0117] Based on the average of the two data points before and after each preset sampling interval, the load sample data, main steam temperature sample data, and reheat steam temperature sample data are processed to add new sample data, resulting in processed load sample data, processed main steam temperature sample data, and processed reheat steam temperature sample data.

[0118] The preset turbine rotor stress boundary model is obtained by using the load reduction rate, the main steam cooling rate, the reheat steam cooling rate, the processed load sample data, the processed main steam temperature sample data, and the processed reheat steam temperature sample data as inputs and the turbine rotor stress sample data as outputs to train the neural network model.

[0119] Optional, the second-stage control module 320 can be used for:

[0120] During the second shutdown phase, the following operations are performed on both the main steam and the reheat steam:

[0121] The initial steam state, target steam state, and desuperheating water temperature are obtained; wherein, the initial steam state includes the initial steam temperature and the initial steam flow rate, and the target steam state includes the target steam temperature and the target steam flow rate;

[0122] Based on the initial steam state, the target steam state, the desuperheating water temperature, and the pre-constructed desuperheating water prediction model, the total desuperheating water demand of the thermal power unit is determined.

[0123] Based on the total demand for desuperheating water and the flow characteristics of the desuperheating water valve, the target opening degree of the desuperheating water valve and the duration of the target opening degree are determined; wherein, the flow characteristics of the desuperheating water valve include the correspondence between the opening degree of the desuperheating water valve and the flow rate of the desuperheating water.

[0124] Optional, the third-stage control module 330 can be used for:

[0125] Obtain historical target load points corresponding to each of the at least one shutdown sub-operation from a pre-built initial benchmark library;

[0126] The historical target load point is determined as the target load point, and the operator is instructed to perform at least one shutdown sub-operation based on the target load point to make the thermal power unit run to the fourth shutdown stage;

[0127] The initial benchmark library is constructed in the following way:

[0128] Obtain the standard load interval segment corresponding to each of the at least one shutdown sub-operation;

[0129] With the goal of minimizing turbine rotor stress, historical target load points corresponding to each of the at least one shutdown sub-operation are obtained from the multiple sets of historical operating data during the shutdown phase.

[0130] Using the standard load interval as the boundary of the initial benchmark library, the initial benchmark library is constructed based on the historical target load points corresponding to the at least one shutdown sub-operation.

[0131] Optionally, the shutdown control of the thermal power unit further includes an initial benchmark library update module, used to update the benchmark library after the thermal power unit has been operated to the fourth shutdown stage by performing at least one shutdown sub-operation according to each of the target load points:

[0132] Record the actual load point and actual turbine rotor stress corresponding to at least one shutdown operation in the third stage shutdown operation;

[0133] The actual correspondence between the actual load point and the actual turbine rotor stress is compared with the historical correspondence matched in the initial benchmark library;

[0134] If the actual turbine rotor stress in the actual correspondence is less than the historical turbine rotor stress in the historical correspondence, the historical correspondence in the initial benchmark library is updated using the actual correspondence.

[0135] Optional, the fourth-stage control module 340 can be used for:

[0136] During the fourth shutdown phase, the following operations are performed on both the main steam and the reheat steam:

[0137] The cascaded PID control loop is obtained according to the preset transfer function, and the current steam temperature is obtained;

[0138] The current steam temperature is obtained as the output temperature of the cascaded PID control loop, and the absolute value of the deviation is determined based on the output temperature and the preset desired output temperature.

[0139] With the goal of minimizing the integral of the absolute value of the deviation over time, the PID control parameters of the cascaded PID control loop are optimized using a distributed particle swarm optimization algorithm to determine the PID control parameters.

[0140] The preset transfer function is obtained in the following way:

[0141] Multiple sets of shutdown phase sample data matching the fourth shutdown phase are obtained from the historical operation data of the multiple shutdown phases; the shutdown phase sample data includes the steam temperature of the fourth shutdown phase, the temperature of the superheated desuperheating water after spraying in the fourth shutdown phase, and the opening degree of the superheated desuperheating water valve in the fourth shutdown phase.

[0142] Based on the sample data from the shutdown phase and the preset particle swarm optimization algorithm, the initial transfer function is... The parameters K, T, n, and τ are optimized, and the preset transfer function is determined based on the optimization results; where K represents the gain, T represents the inertia time, n represents the order, and τ represents the delay time.

[0143] The shutdown control device for thermal power units provided in this embodiment of the invention can execute the shutdown control method for thermal power units provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0144] Example 4

[0145] Figure 4 A schematic diagram of an electronic device 400 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers or various forms of mobile devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0146] like Figure 4As shown, the electronic device 400 includes at least one processor 401 and a memory, such as a read-only memory (ROM) 402 and a random access memory (RAM) 403, communicatively connected to the at least one processor 401. The memory stores computer programs executable by the at least one processor. The processor 401 can perform various appropriate actions and processes based on the computer program stored in the ROM 402 or loaded into the RAM 403 from storage unit 408. The RAM 403 may also store various programs and data required for the operation of the electronic device 400. The processor 401, ROM 402, and RAM 403 are interconnected via a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0147] Multiple components in electronic device 400 are connected to I / O interface 405, including: input unit 406, such as keyboard, mouse, etc.; output unit 407, such as various types of displays, speakers, etc.; storage unit 408, such as disk, optical disk, etc.; and communication unit 409, such as network card, modem, wireless transceiver, etc. Communication unit 409 allows electronic device 400 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0148] Processor 401 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 401 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 401 performs the various methods and processes described above, such as the shutdown control methods for thermal power units.

[0149] In some embodiments, the shutdown control method for thermal power units may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 408. In some embodiments, part or all of the computer program may be loaded into and / or installed on electronic device 400 via ROM 402 and / or communication unit 409. When the computer program is loaded into RAM 403 and executed by processor 401, one or more steps of the shutdown control method for thermal power units described above may be performed. Alternatively, in other embodiments, processor 401 may be configured to perform the shutdown control method for thermal power units by any other suitable means (e.g., by means of firmware).

[0150] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific target products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0151] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0152] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0153] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0154] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0155] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0156] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0157] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A shutdown control method for a thermal power unit, characterized in that, include: In the first shutdown phase, the current values ​​of the target operating parameters of the thermal power unit are acquired. These target operating parameters include load, main steam temperature, and reheat steam temperature. Based on the current values ​​and a preset turbine rotor stress boundary model, the expected rate of decrease of the target operating parameters under each load is determined based on the upper limit of the turbine rotor stress of the thermal power unit. Based on the current values ​​and the expected rate of decrease, a setpoint curve corresponding to the target operating parameters is determined, and the thermal power unit is controlled to operate until the second shutdown phase based on the setpoint curve. During the second shutdown phase, the desuperheating water control parameters for the main steam and reheat steam of the thermal power unit are determined, and the thermal power unit is controlled to operate to the third shutdown phase according to the desuperheating water control parameters; the desuperheating water control parameters refer to the opening degree and opening duration of the desuperheating water valve; In the third shutdown phase, a target load point corresponding to at least one shutdown sub-operation of the thermal power unit is determined, and the at least one shutdown sub-operation is executed according to each target load point to make the thermal power unit run to the fourth shutdown phase; In the fourth shutdown phase, proportional-integral-derivative (PID) control parameters for the main steam and the reheat steam are determined, and the thermal power unit is controlled to operate stably based on the PID control parameters. The PID control parameters are determined by optimizing the PID control parameters of the cascade PID control loop using a distributed particle swarm optimization algorithm. The loads of the thermal power units corresponding to the first shutdown phase, the second shutdown phase, the third shutdown phase, and the fourth shutdown phase are reduced in sequence. The preset turbine rotor stress boundary model is obtained through the following method: The historical operating data of the thermal power unit is obtained, and multiple sets of historical shutdown start points and historical shutdown end points are determined from the historical operating data; Based on the multiple sets of historical shutdown start points and historical shutdown end points, multiple sets of historical operation data for shutdown phases are filtered from the historical operation data; Load sample data, main steam temperature sample data, reheat steam temperature sample data, and turbine rotor stress sample data are obtained from the historical operating data of each shutdown phase. The load sample data, the main steam temperature sample data, and the reheat steam temperature sample data are subjected to backward differential processing according to the preset sampling interval to determine the load reduction rate, the main steam cooling rate, and the reheat steam cooling rate. Based on the average of the two data points before and after each preset sampling interval, the load sample data, main steam temperature sample data, and reheat steam temperature sample data are processed to add new sample data, resulting in processed load sample data, processed main steam temperature sample data, and processed reheat steam temperature sample data. The preset turbine rotor stress boundary model is obtained by using the load reduction rate, the main steam cooling rate, the reheat steam cooling rate, the processed load sample data, the processed main steam temperature sample data, and the processed reheat steam temperature sample data as inputs and the turbine rotor stress sample data as outputs to train the neural network model.

2. The method according to claim 1, characterized in that, During the second shutdown phase, the desuperheating water control parameters for the main steam and reheat steam of the thermal power unit are determined, including: During the second shutdown phase, the following operations are performed on both the main steam and the reheat steam: The initial steam state, target steam state, and desuperheating water temperature are obtained; wherein, the initial steam state includes the initial steam temperature and the initial steam flow rate, and the target steam state includes the target steam temperature and the target steam flow rate; Based on the initial steam state, the target steam state, the desuperheating water temperature, and the pre-constructed desuperheating water prediction model, the total desuperheating water demand of the thermal power unit is determined. Based on the total demand for desuperheating water and the flow characteristics of the desuperheating water valve, the target opening degree of the desuperheating water valve and the duration of the target opening degree are determined; wherein, the flow characteristics of the desuperheating water valve include the correspondence between the opening degree of the desuperheating water valve and the flow rate of the desuperheating water.

3. The method according to claim 1, characterized in that, In the third shutdown phase, a target load point corresponding to at least one shutdown sub-operation of the thermal power unit is determined, and the at least one shutdown sub-operation is executed according to each target load point to bring the thermal power unit to the fourth shutdown phase, including: Obtain historical target load points corresponding to each of the at least one shutdown sub-operation from a pre-built initial benchmark library; The historical target load point is determined as the target load point, and the operator is instructed to perform at least one shutdown sub-operation based on the target load point to make the thermal power unit run to the fourth shutdown stage; The initial benchmark library is constructed in the following way: Obtain the standard load interval segment corresponding to each of the at least one shutdown sub-operation; With the goal of minimizing turbine rotor stress, historical target load points corresponding to each of the at least one shutdown sub-operation are obtained from the multiple sets of historical operating data during the shutdown phase. Using the standard load interval as the boundary of the initial benchmark library, the initial benchmark library is constructed based on the historical target load points corresponding to the at least one shutdown sub-operation.

4. The method according to claim 3, characterized in that, After performing at least one shutdown sub-operation according to each of the target load points to bring the thermal power unit to the fourth shutdown stage, the method further includes: Record the actual load point and actual turbine rotor stress corresponding to at least one shutdown operation in the third shutdown stage; The actual correspondence between the actual load point and the actual turbine rotor stress is compared with the historical correspondence matched in the initial benchmark library; If the actual turbine rotor stress in the actual correspondence is less than the historical turbine rotor stress in the historical correspondence, the historical correspondence in the initial benchmark library is updated using the actual correspondence.

5. The method according to claim 1, characterized in that, In the fourth shutdown phase, the proportional-integral-derivative (PID) control parameters for the main steam and the reheat steam are determined, including: During the fourth shutdown phase, the following operations are performed on both the main steam and the reheat steam: The cascaded PID control loop is obtained according to the preset transfer function, and the current steam temperature is obtained; The current steam temperature is obtained as the output temperature of the cascaded PID control loop, and the absolute value of the deviation is determined based on the output temperature and the preset desired output temperature. With the goal of minimizing the integral of the absolute value of the deviation over time, the PID control parameters of the cascaded PID control loop are optimized using a distributed particle swarm optimization algorithm to determine the PID control parameters. The preset transfer function is obtained in the following way: Multiple sets of shutdown phase sample data matching the fourth shutdown phase are obtained from the historical operation data of the multiple shutdown phases; the shutdown phase sample data includes the steam temperature of the fourth shutdown phase, the temperature of the superheated desuperheating water after spraying in the fourth shutdown phase, and the opening degree of the superheated desuperheating water valve in the fourth shutdown phase. Based on the sample data from the shutdown phase and the preset particle swarm optimization algorithm, the initial transfer function is... of , , and Parameter optimization is performed, and the preset transfer function is determined based on the optimization results; wherein... Indicates gain. Indicates inertial time, Indicates order, Indicates the delay time.

6. A shutdown control device for a thermal power unit, characterized in that, include: The first-stage control module is used to acquire the current values ​​of the target operating parameters of the thermal power unit during the first shutdown stage. These target operating parameters include load, main steam temperature, and reheat steam temperature. Based on the current values ​​and a preset turbine rotor stress boundary model, the module determines the expected rate of decrease of the target operating parameters under each load, using the upper limit of the turbine rotor stress of the thermal power unit. Based on the current values ​​and the expected rate of decrease, the module determines the setpoint curve corresponding to the target operating parameters and controls the thermal power unit to operate to the second shutdown stage based on the setpoint curve. The second-stage control module is used to determine the desuperheating water control parameters for the main steam and reheat steam of the thermal power unit during the second shutdown stage, and control the thermal power unit to operate to the third shutdown stage according to the desuperheating water control parameters; the desuperheating water control parameters refer to the opening degree and opening duration of the desuperheating water valve. The third-stage control module is used to determine, in the third shutdown stage, the target load point corresponding to at least one shutdown sub-operation of the thermal power unit, and execute the at least one shutdown sub-operation according to each target load point to make the thermal power unit run to the fourth shutdown stage; The fourth-stage control module is used to determine the proportional-integral-derivative (PID) control parameters for the main steam and the reheat steam during the fourth shutdown stage, and to control the thermal power unit to operate stably according to the PID control parameters; the PID control parameters are determined by optimizing the PID control parameters of the cascade PID control loop using a distributed particle swarm optimization algorithm. The loads of the thermal power units corresponding to the first shutdown phase, the second shutdown phase, the third shutdown phase, and the fourth shutdown phase are reduced in sequence. The preset turbine rotor stress boundary model is obtained through the following method: The historical operating data of the thermal power unit is obtained, and multiple sets of historical shutdown start points and historical shutdown end points are determined from the historical operating data; Based on the multiple sets of historical shutdown start points and historical shutdown end points, multiple sets of historical operation data for shutdown phases are filtered from the historical operation data; Load sample data, main steam temperature sample data, reheat steam temperature sample data, and turbine rotor stress sample data are obtained from the historical operating data of each shutdown phase. The load sample data, the main steam temperature sample data, and the reheat steam temperature sample data are subjected to backward differential processing according to the preset sampling interval to determine the load reduction rate, the main steam cooling rate, and the reheat steam cooling rate. Based on the average of the two data points before and after each preset sampling interval, the load sample data, main steam temperature sample data, and reheat steam temperature sample data are processed to add new sample data, resulting in processed load sample data, processed main steam temperature sample data, and processed reheat steam temperature sample data. The preset turbine rotor stress boundary model is obtained by using the load reduction rate, the main steam cooling rate, the reheat steam cooling rate, the processed load sample data, the processed main steam temperature sample data, and the processed reheat steam temperature sample data as inputs and the turbine rotor stress sample data as outputs to train the neural network model.

7. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the shutdown control method for thermal power units according to any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the shutdown control method for thermal power units as described in any one of claims 1-5.

Images