A method and system for intelligent start-stop control of gas turbine power plants under all operating conditions

By identifying the real-time operating condition categories of gas turbine generator sets and generating differentiated control strategies, combined with online deviation adjustment and self-learning optimization, the problem of insufficient adaptability in the existing start-stop control of gas turbine generator sets is solved, thereby improving the safety and economy of control.

CN123109873APending Publication Date: 2026-11-17JIANGSU HUADIAN KUNSHAN THERMAL POWER CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202611392814.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-09-09
Publication Date
2026-11-17

AI Technical Summary

Technical Problem

Existing gas turbine generator start-stop control strategies lack adaptive operating conditions, online deviation compensation mechanisms, and self-learning optimization capabilities, leading to problems such as excessive thermal stress, unstable combustion, and excessively long start-stop times.

Method used

By acquiring real-time operating characteristic parameters of the gas turbine generator set, identifying the current operating condition category, generating differentiated start-stop control strategy sequences, and performing online deviation adjustments during execution, the system utilizes a neural network model for self-learning optimization to achieve operating condition adaptation and iterative optimization of the control strategy.

Benefits of technology

It improves the safety and economy of start-up and shutdown control in gas turbine power plants, shortens start-up and shutdown time, reduces peak thermal stress, and enhances robustness to operating condition fluctuations and model mismatch.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN123109873A_ABST
    Figure CN123109873A_ABST
Patent Text Reader

Abstract

This invention provides a method and system for intelligent start-stop control of gas turbine power plants under all operating conditions, comprising: acquiring the operating characteristic parameters of the gas turbine generator set at the current moment; identifying the current start-stop operating condition category of the gas turbine generator set based on the operating characteristic parameters; determining target control parameters matching the current start-stop operating condition category based on the current start-stop operating condition category; generating a start-stop control strategy sequence corresponding to the current start-stop operating condition category based on the target control parameters and preset unit operating constraint boundaries; executing start-stop control operations according to the start-stop control strategy sequence, and collecting actual response parameters of the gas turbine generator set during execution; adjusting unexecuted control commands in the start-stop control strategy sequence until the gas turbine generator set reaches the target operating state or completes shutdown. This invention can significantly improve the safety, economy, and intelligence level of start-stop control in gas turbine power plants.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This application relates to the field of gas turbine power generation control technology, and more specifically, to a method and system for intelligent start-stop control of gas turbine power plants under all operating conditions. Background Technology

[0002] Gas turbine generator sets play a vital role in power systems due to their advantages such as rapid start-up, flexible operation, and high thermal efficiency, serving important functions such as peak shaving, frequency regulation, and emergency backup. With the continuous increase in the proportion of renewable energy generation, the power grid's requirements for the frequency and response speed of gas turbine generator sets' start-up and shutdown are increasing. Gas turbine power plants need to frequently perform start-up and shutdown operations under various operating conditions, including cold, warm, and hot states.

[0003] However, existing gas turbine generator start-up and shutdown control methods mainly have the following problems: First, traditional start-stop control strategies use a fixed rate and fixed control parameters, which cannot adaptively adjust the control strategy according to the unit's current thermal state and environmental conditions. Under different operating conditions (cold, warm, and hot), the rotor thermal stress distribution, combustion chamber thermal expansion state, and turbine cooling requirements of the unit vary significantly. Using uniform control parameters can easily lead to problems such as excessive thermal stress, unstable combustion, or excessively long start-up times.

[0004] Second, the existing start-stop control process lacks an online adjustment mechanism for actual response deviations. Once the start-stop control strategy is generated, it is executed sequentially. When the actual exhaust temperature, rotor speed, and other response parameters deviate from the expected values, it is impossible to provide timely feedforward compensation for subsequent unexecuted control commands, leading to the accumulation of deviations and affecting the safety and economy of the start-stop process.

[0005] Third, most existing control strategies are open-loop control, lacking the ability to learn and iteratively optimize based on historical operating data. The experience gained from each start-up and shutdown operation cannot be effectively accumulated and used to improve subsequent strategies, making it difficult to achieve continuous evolution of control strategies.

[0006] To address the aforementioned issues, there is an urgent need for a gas turbine generator set intelligent start-stop control scheme capable of adaptively identifying operating condition categories based on the real-time status of the unit, generating differentiated start-stop strategies, adjusting unexecuted instructions online based on actual response deviations during execution, and possessing self-learning optimization capabilities. Summary of the Invention

[0007] This invention aims to overcome the shortcomings of the prior art and provide a method and system for intelligent start-stop control of gas turbine power plants under all operating conditions. It aims to solve the technical problems of the lack of operating condition adaptive capability, lack of online deviation compensation mechanism, and lack of self-learning optimization capability in the start-stop control strategy of the prior art.

[0008] In a first aspect, the present invention provides an intelligent start-stop control method for a gas turbine power plant under all operating conditions, the method comprising: Obtain the operating characteristic parameters of the gas turbine generator set at the current moment; Based on the aforementioned operating characteristic parameters, the current start-up and shutdown condition category of the gas turbine generator set is identified; Based on the current start-stop condition category, a target control parameter matching the current start-stop condition category is determined; the target control parameter includes at least a target rate parameter; Based on the target control parameters and the preset unit operation constraint boundaries, a start-stop control strategy sequence corresponding to the current start-stop condition category is generated; the start-stop control strategy sequence contains multiple control instructions arranged in chronological order. The start-stop control operation is executed according to the start-stop control strategy sequence, and the actual response parameters of the gas turbine generator set are collected during the execution process. Based on the deviation between the actual response parameters and the expected response parameters at the corresponding time in the start-stop control strategy sequence, the control commands that have not been executed in the start-stop control strategy sequence are adjusted until the gas turbine generator set reaches the target operating state or completes shutdown.

[0009] Preferably, the operating characteristic parameters include ambient temperature, ambient pressure, air humidity, current rotor speed, and current exhaust temperature. Therefore, identifying the current start-stop condition category of the gas turbine generator set based on the operating characteristic parameters includes: Based on the relationship between the current rotor speed and the zero speed value, and the relationship between the current exhaust temperature and the ambient temperature, the current start-stop condition category is obtained by matching from multiple preset operating condition categories; The multiple preset operating condition categories include cold start condition, warm start condition, hot start condition, and shutdown condition.

[0010] Preferably, the step of matching the current start-stop condition category from multiple preset operating condition categories based on the relationship between the current rotor speed and the zero speed value and the relationship between the current exhaust temperature and the ambient temperature includes: When the current rotor speed is zero and the difference between the current exhaust temperature and the ambient temperature is less than or equal to the first temperature difference threshold, it is determined to be the cold start condition. When the current rotor speed is zero and the difference between the current exhaust temperature and the ambient temperature is greater than the first temperature difference threshold and less than or equal to the second temperature difference threshold, it is determined to be the warm-state start-up condition. When the current rotor speed is zero and the difference between the current exhaust temperature and the ambient temperature is greater than the second temperature difference threshold, it is determined to be the hot start condition. When the current rotor speed is greater than zero and a shutdown command is received, the shutdown condition is determined.

[0011] Preferably, the target rate parameters include a target rate of increase and a target rate of decrease. Then, determining the target control parameters matching the current start-stop condition category based on the current start-stop condition category includes: Based on the current start-stop condition category, determine the base rise rate and base cooldown rate; The base rate of increase is compensated based on the deviation between the ambient temperature and the standard ambient temperature to obtain the target rate of increase; the base rate of decrease is compensated based on the deviation between the current exhaust temperature and the standard exhaust temperature to obtain the target rate of decrease. The target rate of ascent is calculated using the following formula: , The target cooling rate is calculated using the following formula: , in, The target rate of ascent, For the aforementioned base rate of ascent, The preset first temperature compensation factor, The ambient temperature is... Standard ambient temperature, The target cooling rate, The base cooling rate, This is the preset second temperature compensation factor. The current exhaust temperature, This is the standard exhaust temperature.

[0012] Preferably, generating the start-stop control strategy sequence corresponding to the current start-stop condition category based on the target control parameters and preset unit operation constraint boundaries includes: The setpoint for rotational speed or exhaust temperature at each moment is determined based on the target speed parameter. Based on the speed setpoint or the exhaust temperature setpoint, the unit operation constraint boundary is superimposed to generate a coarse-grained control sequence; the unit operation constraint boundary includes the upper limit of rotor thermal stress, the upper limit of combustion chamber temperature, and the limit of exhaust temperature change rate. Based on the current start-stop condition category, the corresponding empirical correction curve is obtained, and the coarse-grained control sequence is corrected using the empirical correction curve to obtain the start-stop control strategy sequence; each control command in the start-stop control strategy sequence includes a fuel flow rate setpoint and / or an inlet guide vane angle setpoint.

[0013] Preferably, adjusting the unexecuted control commands in the start-stop control strategy sequence based on the deviation between the actual response parameters and the expected response parameters at the corresponding time in the start-stop control strategy sequence includes: During the start / stop control operation, the first The actual exhaust temperature in the actual response parameters collected after the execution of the first control command is compared with the first... The expected exhaust temperature corresponding to each control command is compared to obtain the temperature deviation value; When the absolute value of the temperature deviation is greater than the preset deviation tolerance threshold, the compensation amount is calculated based on the temperature deviation value. The compensation amount is used to address the unexecuted first step in the start / stop control strategy sequence. The first to the second Feedforward compensation is applied to the fuel flow setpoint of each control command. The preset number of feedforward compensation steps; The compensation amount is calculated using the following formula: , in, The compensation amount is... This is a preset proportional coefficient. For the first The temperature deviation value after the execution of each control command. The preset integral coefficient, This is the time interval between two adjacent control commands.

[0014] Preferably, it further includes: Collect full-condition operating data of the gas turbine generator set during the start-stop control operation; Based on the full-condition operation data, a start-stop process database is constructed; Using the aforementioned start-stop process database, a start-stop strategy optimization model is trained through a neural network model; The optimized target control parameters output by the start-stop strategy optimization model are fed back into the process of generating the start-stop control strategy sequence.

[0015] Secondly, the present invention provides an intelligent start-stop control system for a gas turbine power plant under all operating conditions, comprising: The characteristic parameter acquisition module is used to acquire the operating characteristic parameters of the gas turbine generator set at the current moment. The current start-stop condition category identification module is used to identify the current start-stop condition category of the gas turbine generator set based on the operating characteristic parameters. The target control parameter determination module is used to determine target control parameters that match the current start-stop condition category based on the current start-stop condition category; the target control parameters include at least a target rate parameter; The start-stop control strategy sequence generation module is used to generate a start-stop control strategy sequence corresponding to the current start-stop condition category based on the target control parameters and preset unit operation constraint boundaries; the start-stop control strategy sequence includes multiple control instructions arranged in chronological order. The start-stop control operation execution module is used to execute start-stop control operations according to the start-stop control strategy sequence, and to collect the actual response parameters of the gas turbine generator set during the execution process; The control command adjustment module is used to adjust the unexecuted control commands in the start-stop control strategy sequence based on the deviation between the actual response parameters and the expected response parameters at the corresponding time in the start-stop control strategy sequence, until the gas turbine generator set reaches the target operating state or completes shutdown.

[0016] Thirdly, the present invention provides a readable medium including executable instructions, which, when executed by a processor of an electronic device, cause the electronic device to perform any of the methods described in the first aspect.

[0017] Fourthly, the present invention provides an electronic device including a processor and a memory storing execution instructions, wherein when the processor executes the execution instructions stored in the memory, the processor performs the method as described in any of the first aspects.

[0018] This invention provides an intelligent start-stop control method and system for gas turbine power plants under all operating conditions. By acquiring real-time operating characteristic parameters of the gas turbine generator set and identifying the current start-stop condition category accordingly, adaptive judgment of the operating condition is achieved, avoiding the problem of insufficient applicability of traditional unified control parameters under different operating conditions. By matching target rate parameters according to the operating condition category and superimposing unit operating constraint boundaries to generate a differentiated start-stop control strategy sequence, the control strategy can meet both thermodynamic safety constraints and adapt to the current thermal state, effectively shortening the start-stop time and reducing the peak thermal stress. By collecting actual response parameters during execution and comparing them with expected parameters, a feedforward compensation mechanism is used to adjust unexecuted control commands online. The combination of proportional and integral terms and feedforward compensation for multiple unexecuted commands are introduced into the compensation calculation, which can promptly curb the accumulation and propagation of deviations, significantly improving the robustness of the start-stop process to operating condition fluctuations and model mismatch. By collecting full-condition operating data to construct a start-stop process database and using a neural network model to train and optimize the model, the optimized target control parameters are fed back to the strategy generation process, realizing closed-loop iterative optimization and continuous evolution of the control strategy. This invention has multiple technical advantages, including adaptive operating condition identification, online deviation feedforward compensation, and self-learning optimization of control strategies, which can significantly improve the safety, economy, and intelligence level of start-up and shutdown control in gas turbine power plants.

[0019] The further effects of the aforementioned non-conventional preferred method will be explained below in conjunction with specific embodiments. Attached Figure Description

[0020] To more clearly illustrate the embodiments of the present invention or the existing technical solutions, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a schematic diagram of an intelligent start-stop control method for a gas turbine power plant under all operating conditions, provided in an embodiment of the present invention. Figure 2 This is a schematic diagram of another intelligent start-stop control method for gas turbine power plants under all operating conditions, provided by an embodiment of the present invention; Figure 3 This is a schematic diagram illustrating the composition of an intelligent start-stop control system for a gas turbine power plant under all operating conditions, provided in an embodiment of the present invention. Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0022] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this invention, and not all of them. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0023] See Figure 1 The image shows a specific embodiment of the intelligent start-stop control method for gas turbine power plants under all operating conditions provided by the present invention. In this embodiment, the intelligent start-stop control method for gas turbine power plants under all operating conditions includes:

[0024] Step 101: Obtain the operating characteristic parameters of the gas turbine generator set at the current moment; Specifically, the operating characteristic parameters in this embodiment include ambient temperature, ambient pressure, air humidity, current rotor speed, and current exhaust temperature. Ambient temperature refers to the air temperature at the inlet of the gas turbine generator set, measured in degrees Celsius (°C), and is obtained by a temperature sensor located at the inlet. Ambient pressure refers to the air pressure at the inlet of the gas turbine generator set, measured in kilopascals (kPa), and is obtained by a pressure sensor located at the inlet. Air humidity refers to the relative humidity of the air at the inlet of the gas turbine generator set, expressed as a percentage, and is obtained by a humidity sensor located at the inlet. Current rotor speed refers to the actual rotational speed of the gas turbine generator set rotor shaft at the current moment, measured in revolutions per minute (rpm), and is obtained by a speed sensor located at the rotor shaft end. Current exhaust temperature refers to the exhaust temperature of the turbine exhaust diffuser section of the gas turbine generator set at the current moment, measured in degrees Celsius (°C), and is obtained by a thermocouple located in the exhaust diffuser section. The aforementioned sensor group collects data in real time at a preset sampling frequency (e.g., 10Hz) and transmits it to the gas turbine control system via a data acquisition card. The control system stores the received data as operating characteristic parameters in a temporary buffer area.

[0025] Step 102: Identify the current start-up and shutdown condition category of the gas turbine generator set based on the operating characteristic parameters; Furthermore, this current start-stop condition category characterizes the thermal and operational state of the gas turbine generator set at the current moment, serving as a prerequisite for subsequently determining the target control parameters. The current start-stop condition category includes cold start, warm start, hot start, and shutdown conditions. Cold start refers to the start-up process where the gas turbine generator set is in a fully cooled state, where the temperature of all components has reached equilibrium with the ambient temperature. Warm start refers to the start-up process where the gas turbine generator set is in a partially cooled state, where the turbine components still retain residual heat above the ambient temperature but are not yet fully cooled. Hot start refers to the start-up process where the gas turbine generator set is in a high-temperature holding state, where the turbine components remain at a relatively high temperature level. Shutdown refers to the process of the gas turbine generator set transitioning from an operating state to a stopped state.

[0026] In this step, the current start-stop operating condition category is determined by matching the current rotor speed with the zero-speed value and the current exhaust temperature with the ambient temperature from multiple preset operating condition categories. The zero-speed value refers to the rotor speed being zero revolutions per minute, used to determine whether the gas turbine generator set is in a stationary state. The difference between the current exhaust temperature and the ambient temperature is used to quantify the residual heat level of the internal components of the gas turbine generator set at the current moment. The larger this difference, the more heat is accumulated inside the unit, and the closer the corresponding start-up operating condition is to the hot state.

[0027] Specifically, when the current rotor speed is zero and the difference between the current exhaust temperature and the ambient temperature is less than or equal to the first temperature difference threshold, it is determined to be a cold start condition. The first temperature difference threshold is a pre-set temperature difference limit used to distinguish the boundary between cold and warm states. This threshold is determined according to the thermodynamic characteristics of the gas turbine generator set. For example, in a specific application scenario, the first temperature difference threshold is set to 50°C.

[0028] When the current rotor speed is zero and the difference between the current exhaust temperature and the ambient temperature is greater than the first temperature difference threshold but less than or equal to the second temperature difference threshold, it is determined to be a warm-state start-up condition. The second temperature difference threshold is a pre-set temperature difference limit used to distinguish the boundary between the warm state and the hot state. This threshold is also determined according to the thermodynamic characteristics of the gas turbine generator set, and its value is greater than the first temperature difference threshold. For example, in a specific application scenario, the second temperature difference threshold is set to 200℃.

[0029] When the current rotor speed is zero and the difference between the current exhaust temperature and the ambient temperature is greater than the second temperature difference threshold, it is determined to be a hot start condition.

[0030] When the current rotor speed is greater than zero and a shutdown command is received, the system is considered to be in a shutdown condition. A shutdown command is a control command issued by the power grid dispatch system or the gas turbine power plant operator to stop the unit from operating.

[0031] Step 103: Determine the target control parameters that match the current start-stop condition category; the target control parameters shall include at least the target rate parameter. The target control parameters must include at least the target rate parameters. The target rate parameters include the target acceleration rate and the target cooling rate. The target acceleration rate refers to the target increment of the rotor speed per unit time during the startup phase of the gas turbine generator set, from the turning gear speed to the rated speed. The unit is revolutions per second (rpm / s) or revolutions per minute (rpm / min). The magnitude of this parameter directly determines the speed of the startup process and the level of rotor thermal stress. The target cooling rate refers to the target decrease in exhaust temperature per unit time during the shutdown phase of the gas turbine generator set. The unit is degrees Celsius per second (°C / s) or degrees Celsius per minute (°C / min). The magnitude of this parameter directly determines the speed of the shutdown process and the uniformity of unit cooling.

[0032] In this step, the base acceleration rate and base cooling rate are first determined based on the current start-stop condition category. The base acceleration rate refers to the rotor speed acceleration reference value corresponding to the current start-stop condition category, without environmental factor correction; this reference value is pre-stored in the control system's rate configuration table. The base cooling rate refers to the exhaust temperature cooling rate reference value corresponding to the current start-stop condition category, without environmental factor correction; this reference value is also pre-stored in the rate configuration table. For example, the rate configuration table can set the base acceleration rate to 150 rpm / min and the base cooling rate to 30℃ / min for cold start conditions, 250 rpm / min and 40℃ / min for warm start conditions, 350 rpm / min and 50℃ / min for hot start conditions, and 35℃ / min for shutdown conditions.

[0033] Then, the base rate of increase is compensated based on the deviation between the ambient temperature and the standard ambient temperature to obtain the target rate of increase. The standard ambient temperature is a pre-set reference temperature value, for example, 15℃ in a specific application scenario. The deviation between the ambient temperature and the standard ambient temperature reflects the degree of deviation of the current environmental conditions from the standard state. This deviation directly affects the compressor's intake density and intake flow rate, thereby affecting the compressor's operating characteristics and turbine cooling effect. When the ambient temperature rises, the air density decreases, and the compressor's intake flow rate decreases. To prevent the compressor from entering the surge region and ensure that the turbine blades are adequately cooled, the base rate of increase needs to be adaptively reduced.

[0034] The target rate of ascent is calculated using the following formula: , in, For the target acceleration rate, Based on the rate of increase, The preset first temperature compensation factor (dimensionless coefficient, for example, a value of 0.3 in a specific application scenario). For ambient temperature, This refers to the standard ambient temperature.

[0035] Simultaneously, the base cooling rate is compensated based on the deviation between the current exhaust temperature and the standard exhaust temperature to obtain the target cooling rate. The standard exhaust temperature is a pre-set reference exhaust temperature value, corresponding to the exhaust temperature of the gas turbine generator set under a certain reference cooling state. For example, in a specific application scenario, the standard exhaust temperature is set to 300℃. The deviation between the current exhaust temperature and the standard exhaust temperature reflects the degree of deviation of the current thermal state of the unit from the reference cooling state. The greater the deviation, the more heat is accumulated inside the unit. During shutdown, a faster cooling rate is needed to release the heat to avoid thermal stress concentration. At the same time, the thermal fatigue problem that may be caused by an excessively rapid cooling rate must also be considered.

[0036] The target cooling rate is calculated using the following formula: , in, For the target cooling rate, Based on the cooling rate, The second temperature compensation factor is a preset value (a dimensionless coefficient, for example, a value of 0.2 in a specific application scenario). The current exhaust temperature. This is the standard exhaust temperature.

[0037] Step 104: Based on the target control parameters and the preset unit operation constraint boundaries, generate the start-stop control strategy sequence corresponding to the current start-stop condition category; the start-stop control strategy sequence contains multiple control instructions arranged in chronological order. Furthermore, the start-stop control strategy sequence comprises multiple control commands arranged chronologically. Each control command corresponds to a discrete control moment, containing at least one of the following: a fuel flow rate setpoint and an inlet guide vane angle setpoint that the gas turbine generator set needs to execute at that moment. The fuel flow rate setpoint refers to the target value of the fuel mass flow rate supplied to the gas turbine combustion chamber, measured in kilograms per second (kg / s). This setpoint directly determines the fuel heat release rate and turbine inlet temperature within the combustion chamber. The inlet guide vane angle setpoint refers to the target value of the blade angle of the compressor inlet guide vanes, measured in degrees (°). This setpoint directly determines the compressor's intake flow rate and pressure ratio characteristics.

[0038] In this step, the setpoints for engine speed or exhaust temperature at each moment are first determined based on the target rate parameter. For the startup process, the setpoints for engine speed at each moment are determined based on the target rate of increase. Specifically, this is calculated by adding the product of the target rate of increase and the running time to the turning speed. ,in The turning speed (e.g., 300 rpm). This refers to the running time after startup. For the shutdown process, the exhaust temperature setpoint at each moment is determined based on the target cooling rate. Specifically, this is calculated by subtracting the product of the target cooling rate and the running time from the current exhaust temperature at the moment the shutdown command is received. ,in The exhaust temperature at the moment the shutdown command is received.

[0039] Then, based on the speed setpoint or exhaust temperature setpoint, coarse-grained control sequences are generated by overlaying unit operating constraints. These constraints include the upper limit for rotor thermal stress, the upper limit for combustion chamber temperature, and the limit for the rate of change of exhaust temperature. The upper limit for rotor thermal stress refers to the maximum thermal stress that the rotor components of the gas turbine generator set are allowed to withstand during operation. This value is determined by the thermal stress calculation model provided by the gas turbine manufacturer. For example, in a specific application scenario, the upper limit for rotor thermal stress is set to 300 MPa; exceeding this value will lead to accelerated consumption of the rotor's low-cycle fatigue life. The upper limit for combustion chamber temperature refers to the highest temperature allowed to be reached within the combustion chamber. This value is determined by the heat-resistant materials and cooling design of the combustion chamber. For example, in a specific application scenario, the upper limit for combustion chamber temperature is set to 1600℃. The limit for the rate of change of exhaust temperature refers to the maximum rate at which the exhaust temperature is allowed to change per unit time. For example, in a specific application scenario, this is set to ±100℃ / min. The specific implementation method of superimposed unit operation constraint boundary is as follows: input the speed setpoint or exhaust temperature setpoint at each moment into the gas turbine thermodynamic model for calculation, verify whether the rotor thermal stress, combustion chamber temperature and exhaust temperature change rate meet their respective upper limit or limit value requirements, limit or smooth the setpoint that does not meet the constraint conditions, so that the adjusted setpoint is within all constraint conditions.

[0040] Next, based on the current start-stop operating condition category, the corresponding experience correction curve is retrieved from a pre-set start-stop experience database. The start-stop experience database is a database storing experience correction curves from historical successful start-stop operations under various operating condition categories. Each experience correction curve reflects the distribution over time of the typical adjustment amount of the fuel flow setpoint and inlet guide vane angle setpoint relative to the baseline value under the corresponding operating condition category. The coarse-grained control sequence is corrected using the experience correction curves. Specifically, at each control moment in the coarse-grained control sequence, the baseline fuel flow setpoint and baseline inlet guide vane angle setpoint are respectively superimposed with the correction amount from the corresponding moment in the experience correction curve to obtain the corrected control command. The corrected start-stop control strategy sequence is then obtained, where each control command includes at least one of the fuel flow setpoint and inlet guide vane angle setpoint.

[0041] Step 105: Execute start-stop control operations according to the start-stop control strategy sequence, and collect the actual response parameters of the gas turbine generator set during the execution process; Furthermore, the actual response parameters include the actual rotor speed, actual exhaust temperature, and combustion chamber dynamic pressure. The actual rotor speed refers to the actual rotational speed reached by the rotor shaft of the gas turbine generator set during start-stop control operations, and is collected in real time by a speed sensor. The actual exhaust temperature refers to the actual exhaust temperature of the turbine exhaust diffuser section of the gas turbine generator set during start-stop control operations, and is collected in real time by a thermocouple. The combustion chamber dynamic pressure refers to the dynamic component of the gas pressure fluctuation within the combustion chamber over time, and is collected in real time by a high-frequency dynamic pressure sensor installed on the combustion chamber casing. This parameter is used to monitor for signs of unstable combustion within the combustion chamber.

[0042] In this step, the control system sequentially sends the fuel flow setpoint and the inlet guide vane angle setpoint to the fuel regulating valve actuator and the inlet guide vane actuator according to the time sequence of each control command in the start-stop control strategy sequence, thereby controlling the operating status of the gas turbine generator set. After executing each control command, the control system collects the actual response parameters at the current moment through the sensor group and associates and stores the collected actual response parameters with the expected response parameters corresponding to the current control command.

[0043] Step 106: Based on the deviation between the actual response parameters and the expected response parameters at the corresponding time in the start-stop control strategy sequence, adjust the unexecuted control commands in the start-stop control strategy sequence until the gas turbine generator set reaches the target operating state or completes shutdown.

[0044] Furthermore, the target operating state refers to the stable operating state that the gas turbine generator set needs to achieve after completing the startup process. For example, for a gas turbine generator set connected to the grid, the target operating state includes reaching the rated speed (e.g., 3000 rpm or 3600 rpm) and meeting the grid connection conditions. Completing the shutdown process means that the rotor speed of the gas turbine generator set drops to zero and the exhaust temperature drops to a safe range after completing the shutdown process.

[0045] In this step, during the execution of the start / stop control operation, the first... The actual exhaust temperature in the actual response parameters collected after the execution of the first control command is related to the first... The expected exhaust temperature corresponding to each control command is compared to obtain the temperature deviation value. A positive integer, representing the sequence number of the control command in the execution sequence. The expected exhaust temperature refers to the temperature at which the start / stop control strategy sequence is generated in step 104. The theoretical target exhaust temperature value corresponding to each control command is determined when the control strategy is generated.

[0046] When the absolute value of the temperature deviation exceeds the preset deviation tolerance threshold, it indicates that the actual response deviates from the expected trajectory and compensation adjustments are required. The deviation tolerance threshold is a pre-defined allowable temperature deviation range; for example, in a specific application scenario, the deviation tolerance threshold may be set to 15°C.

[0047] When the absolute value of the temperature deviation exceeds the deviation tolerance threshold, a compensation amount is calculated based on the temperature deviation value. The compensation amount is expressed as a correction to the fuel flow rate, in kilograms per second (kg / s). The compensation amount is calculated using the following formula:

[0048] , in, For compensation amount, This is a preset proportional coefficient. For the first Temperature deviation value (in °C) after each control command is executed. The preset integral coefficient, This is the time interval between two adjacent control commands (for example, a value of 1 second in a specific application scenario). Indicates from the first control command to the... The sum of the cumulative temperature deviation of each control command multiplied by the time interval; this cumulative term is used to eliminate steady-state deviation.

[0049] Then, the compensation amount is used to address the unexecuted steps in the start-stop control strategy sequence. The first to the second Feedforward compensation is applied to the fuel flow setpoint of each control command. The preset number of feedforward compensation steps indicates the number of unexecuted control instructions that require feedforward compensation, for example, in a specific application scenario. The value is set to 5. The specific compensation method is as follows: [The value is then set to 5]. The first to the second Each control command's original fuel flow setpoint is increased by a compensation amount. The corrected fuel flow setpoint is obtained. Through this feedforward compensation mechanism, the temperature deviation detected at the current moment can be eliminated in advance in multiple subsequent control cycles, avoiding the accumulation and propagation of the deviation.

[0050] The control commands, after compensation and correction, continue to be executed in sequence, repeating the above process of deviation comparison and compensation adjustment until the gas turbine generator set reaches the target operating state or completes shutdown.

[0051] As can be seen from the above technical solutions, the beneficial effects of this embodiment are: it can adaptively identify the operating condition category and match differentiated control parameters according to the real-time operating status of the gas turbine generator set, and dynamically adjust the unexecuted instructions through online deviation detection and feedforward compensation mechanisms, effectively improving the accuracy and robustness of start-stop control.

[0052] Figure 1 The embodiments shown are merely basic examples of the method of the present invention. Other preferred embodiments of the method can be obtained by making certain optimizations and extensions based on them.

[0053] like Figure 2 The image shows another specific embodiment of the intelligent start-stop control method for gas turbine power plants under all operating conditions according to the present invention. This embodiment is a further description based on the foregoing embodiments. In this embodiment, the method includes the following steps:

[0054] Step 201: Collect full-condition operating data of the gas turbine generator set during the start-stop control operation; Full-condition operating data refers to the complete set of data related to the operating status and control behavior generated by the gas turbine generator set during each start-up and shutdown control operation. This data set covers the entire time history from the start to the end of the start-up and shutdown operation, including operating characteristic parameters, actual response parameters, temperature deviation values, and fuel flow compensation. Operating characteristic parameters include ambient temperature, ambient pressure, air humidity, current rotor speed, and current exhaust temperature. Actual response parameters include actual rotor speed, actual exhaust temperature, and combustion chamber dynamic pressure. Temperature deviation value refers to the difference between the actual exhaust temperature and the expected exhaust temperature at each control moment during execution. Fuel flow compensation refers to the fuel flow correction calculated and actually applied based on the temperature deviation value at each control moment during execution.

[0055] After each start-stop control operation is completed, the control system organizes and formats all the data collected during the operation in chronological order to form a complete full-condition operation data record. Each record contains unique identification information for that start-stop operation (such as operation time, operation type, operating condition category, etc.) and all time-series data from the start to the end of the operation.

[0056] Step 202: Construct a start-stop process database based on full-condition operating data; The start-stop process database is a structured data warehouse used to store and manage operational data from multiple start-stop operations under all operating conditions. The database is categorized and indexed according to operating condition types, including cold start, warm start, hot start, and shutdown. For each start-stop process data record, the database stores data according to the following structure: the input condition field stores the operating characteristic parameters at the start of the operation (including ambient temperature, ambient pressure, air humidity, current rotor speed, and current exhaust temperature); the control strategy field stores the actual sequence of control commands executed during the operation (including fuel flow setpoints and inlet guide vane angle setpoints at various times); the response result field stores the actual response parameter sequence during the operation (including curves showing the changes in actual rotor speed, actual exhaust temperature, and combustion chamber dynamic pressure over time); and the evaluation index field stores the performance evaluation results of the operation (including total start-stop time, peak thermal stress during the process, combustion stability coefficient, etc.). As the number of gas turbine generator unit operations increases, the data records in the start-stop process database continuously accumulate, forming a historical big data resource covering various environmental conditions and operating conditions.

[0057] Step 203: Using the start-stop process database, train the start-stop strategy optimization model through a neural network model; The start-stop strategy optimization model is a machine learning model built on a neural network architecture, used to output optimized target control parameters based on input operational feature parameters. The training process of this model is as follows:

[0058] The input data consists of the operating characteristic parameters from each record in the start-up and shutdown process database, including ambient temperature, ambient pressure, air humidity, current rotor speed, and current exhaust temperature. The output data (i.e., the target labels for model training) consists of the optimized target control parameters corresponding to each record, including the target rate of acceleration and the target rate of deceleration. The target labels are determined as follows: for each record in the start-up and shutdown process database, using the total start-up and shutdown time and peak thermal stress of the operation as the optimization objectives, a multi-objective optimization algorithm is used to back-calculate the optimal target rate of acceleration and the target rate of deceleration, while ensuring that the unit's operating constraints are not violated. This optimal value is then used as the label for that record.

[0059] The neural network model is structured as a three-layer fully connected feedforward neural network, consisting of an input layer, hidden layers, and an output layer. The input layer contains 5 nodes, corresponding to 5 input features (ambient temperature, ambient pressure, air humidity, current rotor speed, and current exhaust temperature). The hidden layer contains 32 nodes and employs the ReLU activation function (Rectified Linear Unit). The mathematical expression for this activation function is: This introduces nonlinear transformation capabilities. The output layer contains two nodes, corresponding to the target heating rate and the target cooling rate, respectively. No activation function is used in the output layer to ensure that the output value can continuously vary within the real number range. Supervised learning is used for model training, with the Mean Squared Error (MSE) loss function used to measure the difference between the model's predicted value and the label value. The optimizer uses the Adam optimization algorithm (Adaptive Moment Estimation), with a learning rate of 0.001, a batch size of 32, and 500 training epochs or until the loss function converges. During training, the data in the start-stop process database is randomly divided into training and validation sets in an 8:2 ratio. The training set is used to update model parameters, and the validation set is used to monitor overfitting. Training is terminated early when the validation set loss no longer decreases after 50 consecutive training epochs.

[0060] Step 204: Feed back the optimized target control parameters output by the start-stop strategy optimization model to the start-stop control strategy sequence generation process.

[0061] After the start-stop strategy optimization model is trained, it is deployed to the gas turbine control system. In actual operation, when the gas turbine generator unit enters a new start-stop operation, the control system first executes step 101 to obtain the operating characteristic parameters at the current moment, and then inputs these operating characteristic parameters into the start-stop strategy optimization model. After forward calculation, the model outputs the optimized target acceleration rate and target cooling rate. The control system uses the model output value as the target rate parameter in step 103 (i.e., directly as the target acceleration rate and target cooling rate), replacing the original compensation calculation result, and then uses it for the generation of the start-stop control strategy sequence in step 104. Through the above feedback mechanism, the experience accumulated in historical start-stop operations is solidified in the form of model parameters and used to guide subsequent control decisions, forming a complete closed-loop iterative process of "data acquisition - model training - strategy optimization - feedback application". As the number of start-stop operations continues to increase, the start-stop process database continues to expand, and the start-stop strategy optimization model continuously updates its parameters through periodic retraining. Its output target control parameters gradually approach the global optimum, and the performance of the start-stop control strategy continues to improve.

[0062] As can be seen from the above technical solutions, the beneficial effects of this embodiment are: by constructing a start-stop process database and using a neural network model to train a start-stop strategy optimization model, the optimized target control parameters are fed back to the control strategy generation process, thereby realizing the self-learning and continuous evolution of the start-stop control strategy based on historical operating data.

[0063] This invention also provides an intelligent start-stop control system for gas turbine power plants under all operating conditions. See also Figure 3 The image shows a specific embodiment of an intelligent start-stop control system for gas turbine power plants under all operating conditions provided by the present invention. This embodiment of the system is used to execute... Figures 1-2 The physical apparatus of the method. Its technical solution is essentially the same as the embodiments described above, and the corresponding descriptions in the embodiments above also apply to this embodiment. The system includes:

[0064] The operating characteristic parameter acquisition module 301 is configured to acquire the operating characteristic parameters of the gas turbine generator set at the current moment; The current start-stop condition category identification module 302 is configured to identify the current start-stop condition category of the gas turbine generator set based on operating characteristic parameters; The target control parameter determination module 303 is configured to determine target control parameters that match the current start-stop condition category based on the current start-stop condition category; the target control parameters include at least the target rate parameter; The start-stop control strategy sequence generation module 304 is configured to generate a start-stop control strategy sequence corresponding to the current start-stop operating condition category based on the target control parameters and preset unit operating constraint boundaries; the start-stop control strategy sequence contains multiple control instructions arranged in chronological order. The start-stop control operation execution module 305 is configured to execute start-stop control operations according to the start-stop control strategy sequence, and to collect the actual response parameters of the gas turbine generator set during the execution process; The control command adjustment module 306 is configured to adjust the unexecuted control commands in the start-stop control strategy sequence based on the deviation between the actual response parameters and the expected response parameters at the corresponding time in the start-stop control strategy sequence, until the gas turbine generator set reaches the target operating state or completes shutdown.

[0065] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and a memory. The memory may include main memory, such as high-speed random-access memory (RAM), or it may also include non-volatile memory, such as at least one disk storage device. Of course, the electronic device may also include other hardware required for other services.

[0066] The processor, network interface, and memory can be interconnected via an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 4 The symbol is represented by a single double-headed arrow, but this does not mean that there is only one bus or one type of bus.

[0067] Memory is used to store instructions for execution. Specifically, instructions for execution are computer programs that can be executed. Memory can include main memory and non-volatile memory, and it provides the processor with execution instructions and data.

[0068] In one possible implementation, the processor reads the corresponding execution instructions from non-volatile memory into main memory and then executes them. Alternatively, it can obtain the corresponding execution instructions from other devices to form a fully intelligent start-stop control device for a gas turbine power plant at the logical level. The processor executes the execution instructions stored in the memory to implement the fully intelligent start-stop control method for a gas turbine power plant provided in any embodiment of the present invention.

[0069] The above is as described in the present invention. Figure 3The method for implementing a full-condition intelligent start-stop control system for a gas turbine power plant, as provided in the illustrated embodiment, can be applied to or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed through integrated logic circuits in the processor's hardware or through software instructions. The processor can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this invention. The general-purpose processor can be a microprocessor or any conventional processor.

[0070] The steps of the method disclosed in the embodiments of this invention can be directly manifested as being executed by a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software modules can reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. This storage medium is located in memory, and the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method.

[0071] This invention also proposes a readable medium storing execution instructions. When these instructions are executed by a processor of an electronic device, the device can perform a full-condition intelligent start-stop control method for gas turbine power plants provided in any embodiment of this invention, specifically for executing, as... Figure 1 , Figure 2 The method shown.

[0072] The electronic devices in the foregoing embodiments may be computers.

[0073] Those skilled in the art will understand that embodiments of the present invention can be provided as methods or computer program products. Therefore, the present invention can be implemented in a completely hardware embodiment, a completely software embodiment, or a combination of software and hardware.

[0074] The various embodiments in this invention are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the apparatus embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0075] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0076] The above are merely embodiments of the present invention and are not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of the present invention should be included within the scope of the claims of the present invention.

Claims

1. A method for intelligent start-stop control of a gas turbine power plant under all operating conditions, characterized in that, The method includes: Obtain the operating characteristic parameters of the gas turbine generator set at the current moment; Based on the aforementioned operating characteristic parameters, the current start-up and shutdown condition category of the gas turbine generator set is identified; Based on the current start-stop condition category, a target control parameter matching the current start-stop condition category is determined; the target control parameter includes at least a target rate parameter; Based on the target control parameters and the preset unit operation constraint boundaries, a start-stop control strategy sequence corresponding to the current start-stop condition category is generated; the start-stop control strategy sequence contains multiple control instructions arranged in chronological order. The start-stop control operation is executed according to the start-stop control strategy sequence, and the actual response parameters of the gas turbine generator set are collected during the execution process. Based on the deviation between the actual response parameters and the expected response parameters at the corresponding time in the start-stop control strategy sequence, the control commands that have not been executed in the start-stop control strategy sequence are adjusted until the gas turbine generator set reaches the target operating state or completes shutdown.

2. The method according to claim 1, characterized in that, The operating characteristic parameters include ambient temperature, ambient pressure, air humidity, current rotor speed, and current exhaust temperature. Therefore, identifying the current start-stop condition category of the gas turbine generator set based on these operating characteristic parameters includes: Based on the relationship between the current rotor speed and the zero speed value, and the relationship between the current exhaust temperature and the ambient temperature, the current start-stop condition category is obtained by matching from multiple preset operating condition categories; The multiple preset operating condition categories include cold start condition, warm start condition, hot start condition, and shutdown condition.

3. The method according to claim 2, characterized in that, The process of matching the current start-stop condition category from multiple preset operating condition categories based on the relationship between the current rotor speed and zero speed, and the relationship between the current exhaust temperature and the ambient temperature, includes: When the current rotor speed is zero and the difference between the current exhaust temperature and the ambient temperature is less than or equal to the first temperature difference threshold, it is determined to be the cold start condition. When the current rotor speed is zero and the difference between the current exhaust temperature and the ambient temperature is greater than the first temperature difference threshold and less than or equal to the second temperature difference threshold, it is determined to be the warm-state start-up condition. When the current rotor speed is zero and the difference between the current exhaust temperature and the ambient temperature is greater than the second temperature difference threshold, it is determined to be the hot start condition. When the current rotor speed is greater than zero and a shutdown command is received, the shutdown condition is determined.

4. The method according to claim 2, characterized in that, The target rate parameters include the target rate of increase and the target rate of decrease. Therefore, determining the target control parameters that match the current start-stop condition category based on the current start-stop condition category includes: Based on the current start-stop condition category, determine the base rise rate and base cooldown rate; The base rate of increase is compensated based on the deviation between the ambient temperature and the standard ambient temperature to obtain the target rate of increase; the base rate of decrease is compensated based on the deviation between the current exhaust temperature and the standard exhaust temperature to obtain the target rate of decrease. The target rate of ascent is calculated using the following formula: , The target cooling rate is calculated using the following formula: , in, The target rate of ascent, For the aforementioned base rate of ascent, The preset first temperature compensation factor, The ambient temperature is... Standard ambient temperature, The target cooling rate, The basic cooling rate, This is the preset second temperature compensation factor. The current exhaust temperature, This is the standard exhaust temperature.

5. The method according to claim 1, characterized in that, The step of generating the start-stop control strategy sequence corresponding to the current start-stop condition category based on the target control parameters and preset unit operation constraint boundaries includes: The setpoint for rotational speed or exhaust temperature at each moment is determined based on the target speed parameter. Based on the speed setpoint or the exhaust temperature setpoint, the unit operation constraint boundary is superimposed to generate a coarse-grained control sequence; the unit operation constraint boundary includes the upper limit of rotor thermal stress, the upper limit of combustion chamber temperature, and the limit of exhaust temperature change rate. Based on the current start-stop condition category, the corresponding empirical correction curve is obtained, and the coarse-grained control sequence is corrected using the empirical correction curve to obtain the start-stop control strategy sequence; each control command in the start-stop control strategy sequence includes a fuel flow rate setpoint and / or an inlet guide vane angle setpoint.

6. The method according to claim 1, characterized in that, The step of adjusting the unexecuted control commands in the start-stop control strategy sequence based on the deviation between the actual response parameters and the expected response parameters at the corresponding time in the start-stop control strategy sequence includes: During the start / stop control operation, the first The actual exhaust temperature in the actual response parameters collected after the execution of the first control command is compared with the first... The expected exhaust temperature corresponding to each control command is compared to obtain the temperature deviation value; When the absolute value of the temperature deviation is greater than the preset deviation tolerance threshold, the compensation amount is calculated based on the temperature deviation value. The compensation amount is used to address the unexecuted first step in the start / stop control strategy sequence. The first to the second Feedforward compensation is applied to the fuel flow setpoint of each control command. The preset number of feedforward compensation steps; The compensation amount is calculated using the following formula: , in, The compensation amount is... This is a preset proportional coefficient. For the first The temperature deviation value after the execution of each control command. The preset integral coefficient, This is the time interval between two adjacent control commands.

7. The method according to any one of claims 1 to 6, characterized in that, Also includes: Collect full-condition operating data of the gas turbine generator set during the start-stop control operation; Based on the full-condition operation data, a start-stop process database is constructed; Using the aforementioned start-stop process database, a start-stop strategy optimization model is trained through a neural network model; The optimized target control parameters output by the start-stop strategy optimization model are fed back into the process of generating the start-stop control strategy sequence.

8. A fully intelligent start-stop control system for gas turbine power plants, characterized in that, include: The characteristic parameter acquisition module is used to acquire the operating characteristic parameters of the gas turbine generator set at the current moment. The current start-stop condition category identification module is used to identify the current start-stop condition category of the gas turbine generator set based on the operating characteristic parameters. The target control parameter determination module is used to determine the target control parameters that match the current start-stop condition category based on the current start-stop condition category. The target control parameters include at least the target rate parameter; The start-stop control strategy sequence generation module is used to generate a start-stop control strategy sequence corresponding to the current start-stop condition category based on the target control parameters and preset unit operation constraint boundaries; the start-stop control strategy sequence includes multiple control instructions arranged in chronological order. The start-stop control operation execution module is used to execute start-stop control operations according to the start-stop control strategy sequence, and to collect the actual response parameters of the gas turbine generator set during the execution process; The control command adjustment module is used to adjust the unexecuted control commands in the start-stop control strategy sequence based on the deviation between the actual response parameters and the expected response parameters at the corresponding time in the start-stop control strategy sequence, until the gas turbine generator set reaches the target operating state or completes shutdown.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein the program, when executed, performs the method of any one of claims 1 to 7.

10. An electronic device, characterized in that, The electronic device includes: processor; Memory used to store the processor's executable instructions; The processor is configured to read the executable instructions from the memory and execute the instructions to implement the method described in any one of claims 1 to 7.