Steam turbine operation control method, intelligent agent and electronic device

Abstract

The present application discloses a steam turbine operation control method, an intelligent agent, and an electronic device. The method includes: obtaining the current operation parameters of high-temperature components of the steam turbine; respectively inputting the current operation parameters into a stress prediction model during the start-stop stage and a stress prediction model during the load adjustment stage to obtain a predicted stress parameter during the start-stop stage and a predicted stress parameter during the load adjustment stage; calculating a predicted value of low-cycle fatigue crack initiation loss and a predicted cumulative loss of low-cycle fatigue crack initiation during the start-stop stage, and calculating a predicted value of low-cycle fatigue crack initiation loss and a predicted cumulative loss of low-cycle fatigue crack initiation during the load adjustment stage; determining target deep peak shaving operation control parameters during the start-stop stage and target deep peak shaving operation control parameters during the load adjustment stage that satisfy the stress and life constraint conditions; and controlling the steam turbine according to the control parameters. That is, the solution of the present application enables the steam turbine to meet the demand for deep peak shaving response while reducing losses.

Description

Technical Field

[0001] The present application relates to the technical field of steam turbines, and in particular to a steam turbine operation control method, an intelligent body, and an electronic device. Background Art

[0002] Deep peak shaving refers to an operation method in which the power system adjusts the output of generator sets during periods of low load, causing them to operate far below rated power to maintain a balanced supply and demand. With the rapid adjustment of the energy structure and the large-scale integration of new energy sources into the power grid, the peak-to-valley difference in the power system continues to increase. Deep peak shaving has become a key measure to ensure stable grid operation. Steam turbines, as the mainstay of traditional power generation equipment, are primarily used for frequent deep peak shaving, which allows generator sets to operate far below rated power.

[0003] At present, the turbine is mainly divided into cold, warm and hot start-up according to its temperature, and then deep peak regulation is carried out, with different peak regulation rates adopted for different temperatures.

[0004] However, in the process of frequent deep peak regulation of the steam turbine, frequent changes in the operating conditions of the steam turbine will cause drastic changes in the internal stress of the steam turbine components, causing serious damage to the steam turbine components, thereby reducing the service life of the steam turbine. Summary of the Invention

[0005] The present application provides a steam turbine operation control method, intelligent body and electronic equipment to solve the problem in the prior art that during the frequent deep peak regulation of the steam turbine, frequent changes in the operating conditions of the steam turbine will cause drastic changes in the internal stress of the steam turbine components, causing serious damage to the steam turbine components, thereby reducing the service life of the steam turbine.

[0006] In a first aspect, the present application provides a method for controlling operation of a steam turbine, the method comprising:

[0007] Obtain the current operating parameters of the high-temperature components of the steam turbine;

[0008] Inputting the current operating parameters into a stress prediction model for a high-temperature component of a steam turbine during a start-up and shutdown phase and a stress prediction model for a high-temperature component of a steam turbine during a load adjustment phase, respectively, to obtain predicted stress parameters for the start-up and shutdown phase outputted by the stress prediction model for the high-temperature component of the steam turbine, and to obtain predicted stress parameters for the load adjustment phase outputted by the stress prediction model for the high-temperature component of the steam turbine; wherein the predicted stress parameters include stress value, material Poisson's ratio, and material elastic modulus;

[0009] Calculate the predicted value of low-cycle fatigue crack initiation loss and the predicted cumulative loss of low-cycle fatigue crack initiation in the start-stop stage according to the Poisson's ratio and elastic modulus of the material in the start-stop stage, and calculate the predicted value of low-cycle fatigue crack initiation loss and the predicted cumulative loss of low-cycle fatigue crack initiation in the load adjustment stage according to the Poisson's ratio and elastic modulus of the material in the load adjustment stage;

[0010] Determine the target deep peak shaving operation control parameters in the start-stop stage that meet the stress and life constraint conditions according to the predicted stress in the start-stop stage, the predicted value of low-cycle fatigue crack initiation loss in the start-stop stage, and the predicted cumulative loss of low-cycle fatigue crack initiation in the start-stop stage, and determine the target deep peak shaving operation control parameters in the load adjustment stage that meet the stress and life constraint conditions according to the predicted stress in the load adjustment stage, the predicted value of low-cycle fatigue crack initiation loss in the load adjustment stage, and the predicted cumulative loss of low-cycle fatigue crack initiation in the load adjustment stage;

[0011] Control the steam turbine in the start-stop stage according to the target deep peak shaving operation control parameters in the start-stop stage, and control the steam turbine in the load adjustment stage according to the target deep peak shaving operation control parameters in the load adjustment stage.

[0012] Optionally, the stress prediction model for the start-stop stage of the high-temperature components of the steam turbine is obtained through the following steps:

[0013] Establish a thermo-mechanical coupling finite element model of the high-temperature components of the steam turbine by using the geometric structure and material parameters of the high-temperature components of the steam turbine;

[0014] For each preset temperature, in the start-up speed-up stage of the steam turbine, determine the stress parameters corresponding to each speed-up rate of the high-temperature components of the steam turbine according to the thermo-mechanical coupling finite element model of the high-temperature components of the steam turbine, and use them as the stress parameter group in the speed-up stage corresponding to the preset temperature;

[0015] Take the stress parameter groups in the speed-up stage corresponding to multiple preset temperatures as the stress data set in the start-up speed-up stage of the high-temperature components of the steam turbine;

[0016] For each preset temperature, in the shutdown speed-down stage of the steam turbine, determine the stress parameters corresponding to each speed-down rate of the high-temperature components of the steam turbine according to the thermo-mechanical coupling finite element model of the high-temperature components of the steam turbine, and use them as the stress parameter group in the speed-down stage corresponding to the preset temperature;

[0017] Take the stress parameter groups in the speed-down stage corresponding to multiple preset temperatures as the stress data set in the shutdown speed-down stage of the high-temperature components of the steam turbine;

[0018] Based on the stress datasets in the startup speed-up stage and the shutdown speed-down stage, an artificial intelligence algorithm is used to construct a stress prediction model for the start-stop stage of the high-temperature components of the steam turbine.

[0019] Optionally, the stress prediction model for the load adjustment stage of the high-temperature components of the steam turbine is obtained through the following steps:

[0020] Construct a stress dataset for the load increase stage and a stress dataset for the load decrease stage;

[0021] Based on the stress dataset for the load increase stage and the stress dataset for the load decrease stage, an artificial intelligence algorithm is used to construct a stress prediction model for the load adjustment stage of the high-temperature components of the steam turbine.

[0022] Optionally, the construction of the stress dataset for the load increase stage and the stress dataset for the load decrease stage includes:

[0023] At the first initial load, for each preset temperature, in the load increase stage of the steam turbine, according to the thermo-mechanical coupling finite element model of the high-temperature components of the steam turbine, determine the stress parameters corresponding to each load when the high-temperature components of the steam turbine increase the load at different load increase rates, as the stress parameter group for the load increase stage corresponding to the preset temperature at the first initial load; wherein, the first initial load is the first initial load in the preset initial load group, and the preset initial load group is a set of data arranged from small to large;

[0024] Store the stress parameter group for the load increase stage corresponding to the preset temperature at the first initial load into the stress dataset for the load increase stage;

[0025] Take the next load of the first initial load in the preset initial load group as the new first initial load, and return to execute the step of "at the first initial load, for each preset temperature, in the load increase stage of the steam turbine, according to the thermo-mechanical coupling finite element model of the high-temperature components of the steam turbine, determine the stress parameters corresponding to each load when the high-temperature components of the steam turbine increase the load at different load increase rates, as the stress parameter group for the load increase stage corresponding to the preset temperature at the first initial load", until each initial load in the preset initial load group is traversed to obtain the stress dataset for the load increase stage;

[0026] At the second initial load, for each preset temperature, during the load rejection stage of the steam turbine, according to the thermo-mechanical coupling finite element model of the high-temperature components of the steam turbine, when the high-temperature components of the steam turbine reduce the load at different load rejection rates, the corresponding stress parameters at each load are determined as the stress parameter group during the load rejection stage corresponding to the preset temperature at the second initial load; wherein, the second initial load is the last initial load in the preset initial load group;

[0027] Store the stress parameter group during the load rejection stage corresponding to the preset temperature at the second initial load into the load rejection stage stress data set;

[0028] Take the load before the second initial load in the preset initial load group as the new second initial load, and return to execute the step of "At the second initial load, for each preset temperature, during the load rejection stage of the steam turbine, according to the thermo-mechanical coupling finite element model of the high-temperature components of the steam turbine, when the high-temperature components of the steam turbine reduce the load at different load rejection rates, the corresponding stress parameters at each load are determined as the stress parameter group during the load rejection stage corresponding to the preset temperature at the second initial load", until each initial load in the preset initial load group is traversed to obtain the load rejection stage stress data set.

[0029] Optionally, before determining the start-stop stage target deep peak shaving operation control parameters that meet the stress and life constraint conditions according to the start-stop stage predicted stress, the start-stop stage low-cycle fatigue crack initiation loss prediction value, and the start-stop stage low-cycle fatigue crack initiation cumulative loss prediction value, the method further includes:

[0030] Construct the stress and life constraint conditions according to the start-stop stage stress prediction model of the high-temperature components of the steam turbine, the load adjustment stage stress prediction model of the high-temperature components of the steam turbine, and the current operating parameters.

[0031] Optionally, determining the start-stop stage target deep peak shaving operation control parameters that meet the stress and life constraint conditions according to the start-stop stage predicted stress, the start-stop stage low-cycle fatigue crack initiation loss prediction value, and the start-stop stage low-cycle fatigue crack initiation cumulative loss prediction value includes:

[0032] Obtain the operation control instruction of the high-temperature components of the steam turbine;

[0033] Construct a time-based steam turbine deep peak shaving objective function based on the operation control instruction;

[0034] An optimization algorithm is adopted. When the stress and life constraint conditions are met, the deep peak shaving objective function of the steam turbine is minimized according to the predicted stress in the start-stop stage, the predicted value of the low-cycle fatigue crack initiation loss in the start-stop stage, and the predicted value of the cumulative low-cycle fatigue crack initiation loss in the start-stop stage, so as to obtain the target deep peak shaving operation control parameters in the start-stop stage that meet the stress and life constraint conditions.

[0035] Optionally, determining the target deep peak shaving operation control parameters in the load adjustment stage that meet the stress and life constraint conditions according to the predicted stress in the load adjustment stage, the predicted value of the low-cycle fatigue crack initiation loss in the load adjustment stage, and the predicted value of the cumulative low-cycle fatigue crack initiation loss in the load adjustment stage includes:

[0036] An optimization algorithm is adopted. When the stress and life constraint conditions are met, the deep peak shaving objective function of the steam turbine is minimized according to the predicted stress in the load adjustment stage, the predicted value of the low-cycle fatigue crack initiation loss in the load adjustment stage, and the predicted value of the cumulative low-cycle fatigue crack initiation loss in the load adjustment stage, so as to obtain the target deep peak shaving operation control parameters in the load adjustment stage that meet the stress and life constraint conditions.

[0037] Optionally, it further includes:

[0038] Real-time monitor the operating state of the steam turbine;

[0039] If the steam turbine appears in an abnormal condition, suspend the operation control of the steam turbine and send an alarm message to the target user device.

[0040] In a second aspect, the present application provides an intelligent agent for steam turbine operation control, including:

[0041] An acquisition module for acquiring the current operating parameters of the high-temperature components of the steam turbine;

[0042] An input module for respectively inputting the current operating parameters into the stress prediction model of the high-temperature components of the steam turbine in the start-stop stage and the stress prediction model of the high-temperature components of the steam turbine in the load adjustment stage, to obtain the predicted stress parameters in the start-stop stage output by the stress prediction model of the high-temperature components of the steam turbine in the start-stop stage, and to obtain the predicted stress parameters in the load adjustment stage output by the stress prediction model of the high-temperature components of the steam turbine in the load adjustment stage; wherein, the predicted stress parameters include stress values, material Poisson's ratios, and material elastic moduli;

[0043] A calculation module, configured to calculate the predicted value of low-cycle fatigue crack initiation loss and the predicted value of cumulative low-cycle fatigue crack initiation loss during the start-stop stage according to the Poisson's ratio and elastic modulus of the material in the start-stop stage, and calculate the predicted value of low-cycle fatigue crack initiation loss and the predicted value of cumulative low-cycle fatigue crack initiation loss during the load adjustment stage according to the Poisson's ratio and elastic modulus of the material in the load adjustment stage;

[0044] A determination module, configured to determine the target deep peak shaving operation control parameters for the start-stop stage that meet the stress and life constraint conditions according to the predicted stress in the start-stop stage, the predicted value of low-cycle fatigue crack initiation loss in the start-stop stage, and the predicted value of cumulative low-cycle fatigue crack initiation loss in the start-stop stage, and determine the target deep peak shaving operation control parameters for the load adjustment stage that meet the stress and life constraint conditions according to the predicted stress in the load adjustment stage, the predicted value of low-cycle fatigue crack initiation loss in the load adjustment stage, and the predicted value of cumulative low-cycle fatigue crack initiation loss in the load adjustment stage;

[0045] A control module, configured to control the steam turbine in the start-stop stage according to the target deep peak shaving operation control parameters for the start-stop stage, and control the steam turbine in the load adjustment stage according to the target deep peak shaving operation control parameters for the load adjustment stage.

[0046] In a third aspect, the present application provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the steam turbine operation control method as described in the first aspect of the present application is implemented.

[0047] In a fourth aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, the steam turbine operation control method as described in the first aspect of the present application is implemented.

[0048] In a fifth aspect, the present application provides a computer program product, including a computer program. When the computer program is executed by a processor, the steam turbine operation control method as described in the first aspect of the present application is implemented.

[0049] The solution of this application is to obtain the current operating parameters of the high-temperature components of the steam turbine; input the current operating parameters into the stress prediction model for the start-up and shut-down stages of the high-temperature components of the steam turbine and the stress prediction model for the load adjustment stage of the high-temperature components of the steam turbine respectively, to obtain the predicted stress parameters for the start-up and shut-down stages output by the stress prediction model for the start-up and shut-down stages of the high-temperature components of the steam turbine, and the predicted stress parameters for the load adjustment stage output by the stress prediction model for the load adjustment stage of the high-temperature components of the steam turbine; wherein, the predicted stress parameters include stress value, material Poisson's ratio and material elastic modulus; calculate the predicted value of low-cycle fatigue crack initiation loss and the predicted cumulative loss of low-cycle fatigue crack initiation for the start-up and shut-down stages according to the material Poisson's ratio and material elastic modulus for the start-up and shut-down stages, and calculate the predicted value of low-cycle fatigue crack initiation loss and the predicted cumulative loss of low-cycle fatigue crack initiation for the load adjustment stage according to the material Poisson's ratio and material elastic modulus for the load adjustment stage; determine the target deep peak shaving operation control parameters for the start-up and shut-down stages that meet the stress and life constraint conditions according to the predicted stress for the start-up and shut-down stages, the predicted value of low-cycle fatigue crack initiation loss for the start-up and shut-down stages and the predicted cumulative loss of low-cycle fatigue crack initiation for the start-up and shut-down stages, and determine the target deep peak shaving operation control parameters for the load adjustment stage that meet the stress and life constraint conditions according to the predicted stress for the load adjustment stage, the predicted value of low-cycle fatigue crack initiation loss for the load adjustment stage and the predicted cumulative loss of low-cycle fatigue crack initiation for the load adjustment stage; control the steam turbine in the start-up and shut-down stages according to the target deep peak shaving operation control parameters for the start-up and shut-down stages, and control the steam turbine in the load adjustment stage according to the target deep peak shaving operation control parameters for the load adjustment stage. That is, the solution of this application determines the control parameters of the steam turbine from the aspects of stress and loss in the start-up and shut-down stages and the load adjustment stage of the steam turbine, so as to be able to improve the operating performance of the steam turbine while avoiding modifying the control system architecture of the in-service steam turbine, that is, avoiding exceeding the stress load and loss load of the steam turbine, thereby enabling the steam turbine to meet the response deep peak shaving demand while reducing the component loss of the steam turbine, increasing the service life of the steam turbine, and realizing the refined management and performance mining of the deep peak shaving process of the steam turbine. Description of the Drawings

[0050] In order to more clearly illustrate the technical solution of this application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, without creative efforts, other related drawings can also be obtained based on these drawings.

[0051] Figure 1 It is a flow schematic diagram of the steam turbine operation control method provided by this application;

[0052] Figure 2It is a schematic flow chart of the process for determining the stress prediction model during the start-up and shutdown stages of the high-temperature components of a steam turbine provided by this application.

[0053] Figure 3 It is a schematic structural diagram of the stress prediction model during the start-up and shutdown stages of the high-temperature components of a steam turbine provided by this application.

[0054] Figure 4 It is a schematic structural diagram of an intelligent agent for steam turbine operation control provided by this application.

[0055] Figure 5 It is a schematic structural diagram of an electronic device provided by this application. Detailed implementation manners

[0056] In order to enable those skilled in the art to better understand the solutions of this application, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all the embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of this application.

[0057] Figure 1 It is a schematic flow chart of a steam turbine operation control method provided by this application. This method can be executed by an intelligent agent for steam turbine operation control, and this intelligent agent can be implemented in software and / or hardware. In a specific embodiment, this intelligent agent can be applied in an electronic device, and the electronic device can be a computer. The following embodiments will be described by taking the application of this device in the controller of a construction equipment as an example. Refer to Figure 1 , and the method can specifically include the following steps:

[0058] Step 101, obtain the current operating parameters of the high-temperature components of the steam turbine.

[0059] Specifically, the current operating parameters include the surface temperature of the high-temperature component, the average volume temperature of the high-temperature component, the rate of increase, the rate of decrease, the rotational speed, and the start-up and shutdown states. The current operating parameters of the high-temperature components of the steam turbine can be obtained through the Digital Electro-Hydraulic Control System (DEH) or the Turbine Control System (TCS) of the steam turbine.

[0060] Step 102: Input the current operating parameters into the stress prediction model for the start-up and shut-down stages of the high-temperature components of the steam turbine and the stress prediction model for the load adjustment stage of the high-temperature components of the steam turbine, to obtain the predicted stress parameters for the start-up and shut-down stages output by the stress prediction model for the start-up and shut-down stages of the high-temperature components of the steam turbine, and the predicted stress parameters for the load adjustment stage output by the stress prediction model for the load adjustment stage of the high-temperature components of the steam turbine.

[0061] Among them, the predicted stress parameters include stress value, material Poisson's ratio, and material elastic modulus.

[0062] Specifically, input the current operating parameters into the stress prediction model for the start-up and shut-down stages of the high-temperature components of the steam turbine and the stress prediction model for the load adjustment stage of the high-temperature components of the steam turbine, such as inputting the initial surface temperature, initial volume temperature, rate of rise, rate of fall, rotational speed, and start-up / shut-down status flag, to obtain the predicted stress parameters for the start-up and shut-down stages output by the stress prediction model for the start-up and shut-down stages of the high-temperature components of the steam turbine, and the predicted stress parameters for the load adjustment stage output by the stress prediction model for the load adjustment stage of the high-temperature components of the steam turbine, such as equivalent stress, allowable stress, material Poisson's ratio, material elastic modulus, where the equivalent stress includes the combined stress of thermal stress and centrifugal stress. The stress prediction model for the start-up and shut-down stages can be obtained according to the following steps: use the geometric structure and material parameters of the high-temperature components of the steam turbine to establish a finite element model, set different surface temperatures and volume temperatures as the calculation initial conditions, set different rates of rise, and calculate the equivalent stress, allowable stress, material Poisson's ratio, and material elastic modulus of the high-temperature components of the steam turbine at each rotational speed, where the equivalent stress is the combined stress including thermal stress and centrifugal stress, and construct a stress data set for the high-temperature components of the steam turbine during the start-up speed-rising stage.

[0063] Optionally, the stress prediction model for the load adjustment stage of the high-temperature components of the steam turbine is obtained through steps 1021 to 1022.

[0064] Step 1021: Construct a stress data set for the load-rising stage and a stress data set for the load-falling stage.

[0065] Specifically, use the geometric structure and material parameters of the high-temperature components of the steam turbine to establish a finite element model, select different initial load values, obtain different initial surface temperatures and volume temperatures, and use these as the calculation initial conditions, set different load-rising rates, and calculate the equivalent stress and allowable stress of the high-temperature components of the steam turbine at each load, and construct a data set of the equivalent stress and allowable stress of the high-temperature components of the steam turbine during the load-rising stage.

[0066] Optionally, step 1021 can be implemented through steps 11 to 16.

[0067] Step 11, at the first initial load, for each preset temperature, during the load increase stage of the steam turbine, according to the thermo-solid coupling finite element model of the high-temperature components of the steam turbine, determine the stress parameters corresponding to each load when the high-temperature components of the steam turbine increase the load at different load increase rates, and use them as the stress parameter group corresponding to the load increase stage for the preset temperature at the first initial load.

[0068] Among them, the first initial load is the first initial load in the preset initial load group, and the preset initial load group is a set of data arranged from small to large.

[0069] Specifically, in the preset initial load group composed of multiple initial loads, the first initial load is the first initial load. The preset temperature includes the surface temperature and the average volume temperature. For each preset temperature, during the load increase stage of the steam turbine, according to the thermo-solid coupling finite element model of the high-temperature components of the steam turbine, determine the stress parameters corresponding to each load when the high-temperature components of the steam turbine increase the load at different load increase rates, and use them as the stress parameter group corresponding to the load increase stage for the preset temperature at the first initial load.

[0070] Optionally, the surface temperature can be selected as the metal temperature at 90% of the wall thickness depth of the high-temperature components of the steam turbine, and the volume temperature can be selected as the metal temperature at 50% of the wall thickness depth.

[0071] Optionally, according to the temperature ranges of cold state, warm state, hot state, and extremely hot state, divide different surface temperatures and volume temperatures. The temperature range covers the cold state and the extremely hot state, and is divided at intervals of 10°C, so that the initial calculation conditions are not limited to the four states of cold state, warm state, hot state, and extremely hot state. For example, the cold state is when the cylinder metal temperature of the steam turbine is below 150°C, the warm state is when the cylinder metal temperature is between 150°C and 300°C, the hot state is when the cylinder metal temperature is between 300°C and 450°C, and the extremely hot state is when the cylinder metal temperature is above 450°C. At this time, the temperature range can be from 120°C to 500°C, and is divided at intervals of 10°C.

[0072] Step 12, store the stress parameter group corresponding to the load increase stage for the preset temperature at the first initial load into the load increase stage stress data set.

[0073] Step 13, take the next load of the first initial load in the preset initial load group as the new first initial load, and return to execute Step 11 until each initial load in the preset initial load group is traversed to obtain the load increase stage stress data set.

[0074] Specifically, take the next load of the first initial load as the new first initial load, and return to execute step 11 until each initial load in the preset initial load group is traversed. At this time, the stress parameter groups corresponding to each initial load in the load increasing stage are stored in the load increasing stage stress data set, so as to obtain the load increasing stage stress data set.

[0075] Step 14, at the second initial load, for each preset temperature, in the load decreasing stage of the steam turbine, according to the thermo-mechanical coupling finite element model of the high-temperature components of the steam turbine, determine the stress parameters corresponding to each load when the high-temperature components of the steam turbine reduce the load at different load decreasing rates, and take them as the load decreasing stage stress parameter groups corresponding to the preset temperature at the second initial load.

[0076] Among them, the second initial load is the last initial load in the preset initial load group.

[0077] Specifically, in the preset initial load group composed of multiple initial loads, the last initial load is the second initial load. The preset temperatures include the surface temperature and the average volume temperature. For each preset temperature, in the load decreasing stage of the steam turbine, according to the thermo-mechanical coupling finite element model of the high-temperature components of the steam turbine, determine the stress parameters corresponding to each load when the high-temperature components of the steam turbine reduce the load at different load decreasing rates, and take them as the load decreasing stage stress parameter groups corresponding to the preset temperature at the second initial load.

[0078] Step 15, store the load decreasing stage stress parameter groups corresponding to the preset temperature at the second initial load into the load decreasing stage stress data set.

[0079] Step 16, take the load before the second initial load in the preset initial load group as the new second initial load, and return to execute step 14 until each initial load in the preset initial load group is traversed, and obtain the load decreasing stage stress data set.

[0080] Specifically, take the load before the second initial load as the new second initial load, and return to execute step 14 until each initial load in the preset initial load group is traversed. At this time, the load decreasing stage stress parameter groups corresponding to each initial load are stored in the load decreasing stage stress data set, so as to obtain the load decreasing stage stress data set.

[0081] Step 1022, based on the load increasing stage stress data set and the load decreasing stage stress data set, use an artificial intelligence algorithm to construct a stress prediction model for the load adjustment stage of the high-temperature components of the steam turbine.

[0082] Specifically, based on the stress datasets during the load increase stage and the load decrease stage, with the initial surface temperature, initial volume temperature, load increase rate, load decrease rate, load, and load increase / decrease status flag bits as inputs, and the equivalent stress and allowable stress as outputs, an artificial intelligence algorithm and a cross-validation training method are used to train and obtain a thermal stress prediction model for the load adjustment stage. For example, the thermal stress prediction model for the load adjustment stage obtained by training is shown in Equation 1.

[0083] Equation 1;

[0084] Among them, is the equivalent stress of the high-temperature component, is the allowable stress of the high-temperature component, is the Poisson's ratio of the high-temperature component material, is the elastic modulus of the high-temperature component material, is the initial surface temperature of the high-temperature component, is the initial volume temperature of the high-temperature component, is the load increase rate of the steam turbine, is the load decrease rate of the steam turbine, is the load of the steam turbine, is the load adjustment status flag bit of the steam turbine (1 for load increase, 2 for load decrease, and 0 for other states), is the thermal stress prediction model for the load adjustment stage.

[0085] Optionally, Figure 3 is a schematic structural diagram of the stress prediction model for the start-up and shut-down stages of the high-temperature components of the steam turbine provided by this application. Since the thermal stress of the high-temperature components of the steam turbine is related to its temperature field, and due to the thermal inertia of the material, the thermal stress at the current moment is related not only to the current input but also to the previous state. Therefore, the artificial intelligence algorithm can be model structures such as autoregressive neural network, recurrent neural network, etc. Taking the autoregressive neural network model as an example, the model structure is as Figure 3 shown. The initial surface temperature, initial volume temperature, load increase rate, load decrease rate, load, and load increase / decrease status flag bits are used as inputs and enter the normalization layer, input layer, hidden layer, and output layer of the autoregressive neural network model, and then anti-normalization is performed to obtain the equivalent stress of the high-temperature component, the allowable stress of the high-temperature component, the Poisson's ratio of the high-temperature component material, and the elastic modulus of the high-temperature component material.

[0086] Step 103: Calculate the predicted value of low-cycle fatigue crack initiation loss and the predicted cumulative loss of low-cycle fatigue crack initiation during the start-stop stage according to the Poisson's ratio and elastic modulus of the material in the start-stop stage, and calculate the predicted value of low-cycle fatigue crack initiation loss and the predicted cumulative loss of low-cycle fatigue crack initiation during the load adjustment stage according to the Poisson's ratio and elastic modulus of the material in the load adjustment stage.

[0087] Specifically, determine the material strain according to the Poisson's ratio and elastic modulus of the material in the start-stop stage, and determine the predicted value of low-cycle fatigue crack initiation loss in the start-stop stage according to the material strain and material stress. The predicted cumulative loss of low-cycle fatigue crack initiation in the start-stop stage refers to the value obtained by adding the predicted loss values corresponding to multiple rotational speed values during a single start-stop process. Determine the material strain according to the Poisson's ratio and elastic modulus of the material in the load adjustment stage, and determine the predicted value of low-cycle fatigue crack initiation loss in the load adjustment stage according to the material strain and material stress. The predicted cumulative loss of low-cycle fatigue crack initiation in the load adjustment stage refers to the value obtained by adding the predicted loss values corresponding to each load value in the load adjustment stage during a single load adjustment stage.

[0088] Step 104: Determine the target deep peak shaving operation control parameters for the start-stop stage that meet the stress and life constraint conditions according to the predicted stress in the start-stop stage, the predicted value of low-cycle fatigue crack initiation loss in the start-stop stage, and the predicted cumulative loss of low-cycle fatigue crack initiation in the start-stop stage, and determine the target deep peak shaving operation control parameters for the load adjustment stage that meet the stress and life constraint conditions according to the predicted stress in the load adjustment stage, the predicted value of low-cycle fatigue crack initiation loss in the load adjustment stage, and the predicted cumulative loss of low-cycle fatigue crack initiation in the load adjustment stage.

[0089] Specifically, obtain the current state parameters and operation control instructions of the deep peak shaving steam turbine through the DEH system or TCS system of the steam turbine, and construct a time-based target function for the deep peak shaving of the steam turbine based on the operation control instructions. This target function is the target function that can characterize the stress and life constraint conditions. That is, use the stress prediction model for the start-stop stage of the high-temperature components of the steam turbine, the stress prediction model for the load adjustment stage of the high-temperature components of the steam turbine, and the current state parameters to construct a constraint function for the deep peak shaving of the steam turbine based on stress and life. Use an optimization method to calculate the fastest deep peak shaving operation control parameters that meet the stress and life constraint conditions, where the deep peak shaving operation control parameters can include the rotational speed increase rate, rotational speed decrease rate, load increase rate, and load decrease rate.

[0090] In some embodiments, the optimization objective function for the deep peak shaving of a steam turbine includes an optimization function for the deep peak shaving of a steam turbine based on stress, an optimization function for the deep peak shaving of a steam turbine based on the low-cycle fatigue crack initiation loss value, and an optimization function for the deep peak shaving of a steam turbine based on the low-cycle fatigue crack initiation cumulative loss value.

[0091] In some embodiments, the process of constructing an optimization function for the deep peak shaving of a steam turbine based on stress includes constructing a time-related objective function according to the deep peak shaving instruction, and constructing a stress-related constraint function with stress as the constraint condition, which together constitute the optimization function for the deep peak shaving of a steam turbine based on stress.

[0092] In some embodiments, the process of constructing a time-related objective function according to the deep peak shaving instruction includes, if it is the start-stop stage of the deep peak shaving of the steam turbine, dividing the deviation between the target speed value and the current speed by the speed change rate. If it is the load increase-decrease stage of the deep peak shaving of the steam turbine, dividing the deviation between the target power value and the current power by the load change rate to obtain the objective function.

[0093] In some embodiments, the process of constructing a stress-related constraint function with stress as the constraint condition includes, if it is the start-stop stage of the deep peak shaving of the steam turbine, using the stress prediction model for the start-stop stage of the high-temperature components of the steam turbine to calculate the stress corresponding to different speed values at a given speed change rate, and selecting the maximum stress among them. Taking the condition that the maximum stress is less than or equal to the allowable stress as the constraint condition. If it is the load adjustment stage of the deep peak shaving of the steam turbine, using the stress prediction model for the load adjustment stage of the high-temperature components of the steam turbine to calculate the stress corresponding to different load values at a given load change rate, and selecting the maximum stress. Taking the condition that the maximum stress is less than or equal to the set allowable stress as the constraint condition.

[0094] In some embodiments, the process of constructing an optimization function for the deep peak shaving of a steam turbine based on the low-cycle fatigue crack initiation loss includes constructing a time-related objective function according to the deep peak shaving instruction, and constructing a life-related constraint function with the low-cycle fatigue crack initiation loss as the constraint condition, which together constitute the optimization function for the deep peak shaving of a steam turbine based on the low-cycle fatigue crack initiation loss.

[0095] In some embodiments, the process of constructing a life-related constraint function with the low-cycle fatigue crack initiation loss as the constraint condition includes first using the stress prediction model for the start-stop stage of the high-temperature components of the steam turbine and the stress prediction model for the load adjustment stage of the high-temperature components of the steam turbine to calculate the stress, then calculating the low-cycle fatigue crack initiation loss during the deep peak shaving process through the stress, and selecting the maximum loss. Taking the condition that the maximum low-cycle fatigue crack initiation loss is less than or equal to the set loss value as the constraint condition.

[0096] In some embodiments, the process of constructing a steam turbine deep peak shaving optimization function based on the cumulative loss of low-cycle fatigue crack initiation includes constructing a time-related objective function according to the deep peak shaving instruction, and constructing a life-related constraint function with the cumulative loss of low-cycle fatigue crack initiation as a constraint condition, jointly constituting a steam turbine deep peak shaving optimization function based on the cumulative loss of low-cycle fatigue crack initiation.

[0097] In some embodiments, the process of constructing a life-related constraint function with the cumulative loss of low-cycle fatigue crack initiation as a constraint condition includes calculating the stress using a stress prediction model for the start-stop stage of high-temperature components of the steam turbine and a stress prediction model for the load adjustment stage of high-temperature components of the steam turbine, then calculating the low-cycle fatigue crack initiation loss during the deep peak shaving process through the stress, and calculating the total loss of the entire process. Taking the total cumulative loss of low-cycle fatigue crack initiation being less than or equal to the set cumulative loss value as a constraint condition.

[0098] In some embodiments, the optimal control parameters for steam turbine deep peak shaving include the optimal control parameters for steam turbine deep peak shaving based on stress, the optimal control parameters for steam turbine deep peak shaving based on the low-cycle fatigue crack initiation loss value, and the optimal control parameters for steam turbine deep peak shaving based on the cumulative low-cycle fatigue crack initiation loss value.

[0099] In some embodiments, the process of obtaining the optimal control parameters for steam turbine deep peak shaving based on stress includes using optimization algorithms such as genetic algorithms and particle swarm optimization algorithms to solve the aforementioned optimization function with the optimization objective function for steam turbine deep peak shaving based on stress being minimized, and its solution being the optimal control parameters for steam turbine deep peak shaving based on stress. If it is the start-stop stage of steam turbine deep peak shaving, the optimal control parameter is the rotational speed change rate. If it is the load increase or decrease stage of steam turbine deep peak shaving, the optimal control parameter is the load change rate.

[0100] In some embodiments, the process of obtaining the optimal control parameters for steam turbine deep peak shaving based on the low-cycle fatigue crack initiation loss value includes using optimization algorithms such as genetic algorithms and particle swarm algorithms to solve the aforementioned optimization function with the optimization objective function for steam turbine deep peak shaving based on the low-cycle fatigue crack initiation loss value being minimized, and its solution being the optimal control parameters for steam turbine deep peak shaving based on the low-cycle fatigue crack initiation loss value. If it is the start-stop stage of steam turbine deep peak shaving, the optimal control parameter is the rotational speed change rate. If it is the load increase or decrease stage of steam turbine deep peak shaving, the optimal control parameter is the load change rate.

[0101] In some embodiments, the process of obtaining the optimal control parameters for deep peak shaving of a steam turbine based on the cumulative loss value of low-cycle fatigue crack initiation includes using optimization algorithms such as genetic algorithms and particle swarm algorithms to solve the aforementioned optimization function with the optimization objective function for deep peak shaving of a steam turbine based on the cumulative loss value of low-cycle fatigue crack initiation being minimized, and the solution thereof being the optimal control parameters for deep peak shaving of a steam turbine based on the cumulative loss value of low-cycle fatigue crack initiation. If it is the start-stop stage of deep peak shaving of a steam turbine, the optimal control parameter is the rate of change of rotational speed. If it is the load increase and decrease stage of deep peak shaving of a steam turbine, the optimal control parameter is the rate of change of load.

[0102] In some embodiments, the process of obtaining the optimal control parameters for deep peak shaving of a steam turbine based on the remaining calendar life value of crack initiation includes using optimization algorithms such as genetic algorithms and particle swarm algorithms to solve the aforementioned optimization function with the optimization objective function for deep peak shaving of a steam turbine based on the remaining calendar life value of crack initiation being minimized, and the solution thereof being the optimal control parameters for deep peak shaving of a steam turbine based on the remaining calendar life value of crack initiation. If it is the start-stop stage of deep peak shaving of a steam turbine, the optimal control parameter is the rate of change of rotational speed. If it is the load increase and decrease stage of deep peak shaving of a steam turbine, the optimal control parameter is the rate of change of load.

[0103] Optionally, the stress and life constraint conditions include the stress and life constraint conditions in the start-stop stage and the stress and life constraint conditions in the load adjustment stage. Before performing step 104, step 1041 can also be executed.

[0104] Step 1041: Construct stress and life constraint conditions according to the stress prediction model of high-temperature components of a steam turbine in the start-stop stage, the stress prediction model of high-temperature components of a steam turbine in the load adjustment stage, and the current operating parameters.

[0105] Specifically, the process of determining the constraint conditions based on stress is to use the stress prediction model of high-temperature components of a steam turbine in the start-stop stage, the stress prediction model of high-temperature components of a steam turbine in the load adjustment stage, and the current state parameters to calculate the relative safety stress ratio for each rotational speed value or load value. For example, the calculation of the relative safety stress ratio for each rotational speed value or load value is shown in Formulas 2 and 3.

[0106] Formula 2;

[0107] Formula 3;

[0108] Among them, is the equivalent stress of the th rotational speed or load operating value, is the allowable stress corresponding to the th rotational speed or load operating value, is the equivalent stress of the first output of the stress prediction model of high-temperature components of a steam turbine, It is the allowable stress which is the second output of the stress prediction model for high-temperature components of the steam turbine. It is the initial surface temperature of the high-temperature component, It is the initial volume temperature of the high-temperature component, It is the rising rate of the control variable, It is the decreasing rate of the control variable, It is the number. When starting and stopping, select the above stress prediction model for the starting and stopping stages of the high-temperature components of the steam turbine. At this time represents the rotational speed as , and at this time C j represents the th rotational speed corresponding to the rotational speed value, It is the load adjustment status flag (1 for increasing load, 2 for decreasing load, and 0 for other statuses); when adjusting the load, select the above stress prediction model for the load adjustment stage of the high-temperature components of the steam turbine. At this time represents the power , and at this time C j represents the th power corresponding to the load operation value, It is the starting and stopping status flag of the steam turbine (1 for starting and increasing speed, 2 for stopping and decreasing speed, and 0 for other statuses). It is the target value of the control variable, It is the change rate of the control variable.

[0109] Calculate the maximum relative safety stress ratio during the entire control process. For example, the maximum relative safety stress ratio is obtained through Formula 4.

[0110] Formula 4;

[0111] Among them, It is the equivalent stress of the maximum relative safety stress operating value, to represents the equivalent stress from the first rotational speed or load operation value to the mth rotational speed or load operation value, It is the allowable stress of the maximum relative safety stress operating value, to represents the allowable stress from the first rotational speed or load operation value to the mth rotational speed or load operation value.

[0112] During the deep peak shaving process of the steam turbine, the maximum relative safety stress ratio needs to be within the allowable range. Therefore, the constraint function is defined as shown in Formula 5.

[0113] Formula 5;

[0114] Among them, It is the allowable maximum relative safety stress ratio.

[0115] The life - based constraint conditions include the constraint conditions based on the low - cycle fatigue crack initiation loss value and the cumulative loss value of low - cycle fatigue crack initiation.

[0116] The process of determining the constraint condition based on the low - cycle fatigue crack initiation loss value is to use the stress prediction model during the start - up and shut - down stages of the high - temperature components of the steam turbine, the stress prediction model during the load adjustment stage of the high - temperature components of the steam turbine, and the current state parameters to calculate the cyclic low - cycle fatigue strain amplitude of the high - temperature components of the steam turbine for each rotational speed value or load value, as shown in Equation 6:

[0117] Equation 6;

[0118] Where, is the cyclic low - cycle fatigue strain amplitude of the high - temperature components of the steam turbine, is the cyclic low - cycle fatigue strain amplitude of the high - temperature components of the steam turbine for the j - th rotational speed value or load value. is the Poisson's ratio of the high - temperature component material output by the third output of the stress prediction model of the high - temperature components of the steam turbine, is the elastic modulus of the high - temperature component material output by the fourth output of the stress prediction model of the high - temperature components of the steam turbine.

[0119] Use the experimental data curve of the low - cycle fatigue crack initiation life of the material of the high - temperature components of the steam turbine , determine the low - cycle fatigue crack initiation life of the high - temperature components of the steam turbine for the -th rotational speed or load operation value, and calculate as shown in Equation 7:

[0120] Equation 7;

[0121] Where, is the low - cycle fatigue crack initiation life of the high - temperature components of the steam turbine, is the experimental data curve of the low - cycle fatigue crack initiation life of the material of the high - temperature components of the steam turbine.

[0122] Adopt symmetric - cycle low - cycle fatigue to determine the low - cycle fatigue crack initiation life loss of the high - temperature components of the steam turbine, and calculate as shown in Equation 8:

[0123] Equation 8;

[0124] Where, is the low - cycle fatigue crack initiation life loss of the high - temperature components of the steam turbine, is the low - cycle fatigue crack initiation life loss of the high - temperature components of the steam turbine for the j - th rotational speed value or load value.

[0125] Calculate the maximum low - cycle fatigue crack initiation life loss during the entire control process, as shown in Equation 9:

[0126] Formula 9;

[0127] Wherein, is the maximum low - cycle fatigue crack initiation life loss, and the subscript is the number of divisions of the rotational speed or load operation value during the depth - peaking process.

[0128] During the depth - peaking process of the steam turbine, the maximum low - cycle fatigue crack initiation life loss needs to be within the allowable range. Therefore, a constraint function as shown in Formula 10 is defined:

[0129] Formula 10;

[0130] Wherein, is the maximum low - cycle fatigue crack initiation life loss allowed for a single depth - peaking.

[0131] The process of determining the constraint condition based on the cumulative loss value of low - cycle fatigue crack initiation is to use the stress prediction model during the start - stop stage of the high - temperature components of the steam turbine, the stress prediction model during the load - adjustment stage of the high - temperature components of the steam turbine, and the current state parameters to calculate the low - cycle fatigue crack initiation life loss of the high - temperature components of the steam turbine for each rotational speed value or load value , and the calculation method is the same as that of the low - cycle fatigue crack initiation loss value, so it will not be elaborated here.

[0132] Calculate the cumulative loss of low - cycle fatigue crack initiation during a single depth - peaking process , as shown in Formula 11:

[0133] Formula 11;

[0134] During the depth - peaking process of the steam turbine, the cumulative loss of low - cycle fatigue crack initiation life needs to be within the allowable range. Therefore, a constraint function as shown in Formula 12 is defined:

[0135] Formula 12;

[0136] Wherein is the maximum cumulative loss of low - cycle fatigue crack initiation life allowed for a single depth - peaking. Considering that the target intervals of each depth - peaking may be different, the maximum cumulative loss of low - cycle fatigue crack initiation life allowed can be calculated based on the maximum allowable average low - cycle fatigue crack initiation life loss, as shown in Formula 13:

[0137] Formula 13;

[0138] Wherein, is the maximum allowable average low - cycle fatigue crack initiation life loss. The number of divisions for the rotational speed or load operating value during the deep peak shaving process. Optionally, during the rotational speed increase or decrease stage, is the maximum low-cycle fatigue crack initiation life loss allowed for every 1% change in rotational speed; during the load increase or decrease stage, is the maximum low-cycle fatigue crack initiation life loss allowed for every 1% change in load.

[0139] The above provides a steam turbine deep peak shaving constraint function based on stress, low-cycle fatigue crack initiation loss value, and low-cycle fatigue crack initiation cumulative loss value. On this basis, stress can be combined with the low-cycle fatigue crack initiation loss value or the low-cycle fatigue crack initiation cumulative loss value to achieve a constraint function that fuses stress and life, which is the stress and life constraint condition during the start-up and shutdown stages.

[0140] Optionally, the start-up and shutdown stage target deep peak shaving operation control parameters that meet the stress and life constraint conditions can be determined based on the predicted stress during the start-up and shutdown stages, the predicted value of low-cycle fatigue crack initiation loss during the start-up and shutdown stages, and the predicted value of low-cycle fatigue crack initiation cumulative loss during the start-up and shutdown stages, and can be achieved through steps 41 to 43.

[0141] Step 41: Obtain the operation control instructions for the high-temperature components of the steam turbine.

[0142] Specifically, the operation control instructions for the high-temperature components of the steam turbine include start-up control instructions, shutdown control instructions, target rotational speed control instructions, target load control instructions, etc. The operation control instructions for the high-temperature components of the steam turbine can be obtained through the DEH or TCS of the steam turbine.

[0143] Step 42: Construct a time-based steam turbine deep peak shaving objective function based on the operation control instructions.

[0144] Specifically, for a steam turbine used for deep peak shaving, it is necessary to reach the target rotational speed or target load as quickly as possible. Therefore, an objective function based on the peak shaving operation time is constructed using the control target deviation and control rate, as shown in Formula 14:

[0145] Formula 14;

[0146] Where, is the peak shaving time, is the control variable target value, is the control variable initial value, is the control variable change rate.

[0147] When the steam turbine needs to start up from the shutdown state, at this time is the rotational speed target value, usually the grid-connected rotational speed of 3000 rpm, is the current rotational speed, usually the turning gear rotational speed value, is the rotational speed increase rate.

[0148] When the steam turbine is in the full-speed no-load state and needs to reduce the speed for shutdown, at this time is the speed target value, usually the turning gear speed value, is the current speed, usually the full-speed no-load speed of 3000 rpm, is the speed reduction rate.

[0149] When the steam turbine is at partial load and needs to increase the load, at this time is the power target value, is the current power, is the load increase rate. Conversely, when the load needs to be reduced, is the load reduction rate.

[0150] Optionally, for a steam turbine used for deep peak shaving, the target speed or target load can be segmented, and then different control rates are adopted for each segment to operate. Based on this, an objective function based on the peak shaving operation time is constructed, as shown in Formula 15:

[0151] Formula 15;

[0152] Among them, is the peak shaving time, is the number of segmented controls, is the segmented control serial number, is the target value of the control variable for the th segment, is the initial value of the control variable for the th segment, is the change rate of the control variable for the

[0153] Step 43: Adopt an optimization algorithm. When the stress and life constraint conditions are met, minimize the deep peak shaving objective function of the steam turbine according to the predicted stress during the start-stop stage, the predicted value of the low-cycle fatigue crack initiation loss during the start-stop stage, and the predicted cumulative loss of low-cycle fatigue crack initiation during the start-stop stage, and obtain the target deep peak shaving operation control parameters that meet the stress and life constraint conditions.

[0154] Adopt an optimization algorithm to solve, under the constraint function, the that minimizes the objective function. The optimization description problem is shown in Formula 16:

[0155] Formula 16;

[0156] Optionally, the optimization algorithm can select the gradient descent method, Newton method, genetic algorithm, particle swarm algorithm, etc.

[0157] Optimally solved based on the predicted stress during the start-stop stage, the predicted value of low-cycle fatigue crack initiation loss during the start-stop stage, and the predicted cumulative loss of low-cycle fatigue crack initiation during the start-stop stage are the optimal control parameters for the deep peak shaving of steam turbines based on stress.

[0158] Using an optimization algorithm, solve for the one that minimizes the objective function under the constraint function , where s.t. represents the constraint function, and the optimization description problem is shown in Equation 17:

[0159] Equation 17;

[0160] Optimally solved based on the predicted stress during the start-stop stage, the predicted value of low-cycle fatigue crack initiation loss during the start-stop stage, and the predicted cumulative loss of low-cycle fatigue crack initiation during the start-stop stage are the optimal control parameters for the deep peak shaving of steam turbines based on the low-cycle fatigue crack initiation life loss.

[0161] Using an optimization algorithm, solve for the one that minimizes the objective function under the constraint function , and the optimization description problem is shown in Equation 18:

[0162] Equation 18;

[0163] Optimally solved based on the predicted stress during the start-stop stage, the predicted value of low-cycle fatigue crack initiation loss during the start-stop stage, and the predicted cumulative loss of low-cycle fatigue crack initiation during the start-stop stage are the optimal control parameters for the deep peak shaving of steam turbines based on the low-cycle fatigue crack initiation life cumulative loss.

[0164] Using an optimization algorithm, solve for the one that minimizes the objective function under the constraint function , and the optimization description problem with stress, low-cycle fatigue crack initiation loss value, and low-cycle fatigue crack initiation cumulative loss value as constraints simultaneously is shown in Equation 19:

[0165] Equation 19;

[0166] Optimally solved based on the predicted stress during the start-stop stage, the predicted value of low-cycle fatigue crack initiation loss during the start-stop stage, and the predicted cumulative loss of low-cycle fatigue crack initiation during the start-stop stage are the optimal control parameters for the deep peak shaving of steam turbines based on the fusion of stress and life, and are the target deep peak shaving operation control parameters during the start-stop stage that satisfy the stress and life constraint conditions.

[0167] Optionally, determining the target depth peak shaving operation control parameters in the load adjustment stage that meet the stress and life constraint conditions based on the predicted stress in the load adjustment stage, the predicted value of low-cycle fatigue crack initiation loss in the load adjustment stage, and the predicted value of cumulative low-cycle fatigue crack initiation loss in the load adjustment stage can be achieved through step 43.

[0168] Step 43: Using an optimization algorithm, when meeting the stress and life constraint conditions, minimize the turbine depth peak shaving objective function according to the predicted stress in the load adjustment stage, the predicted value of low-cycle fatigue crack initiation loss in the load adjustment stage, and the predicted value of cumulative low-cycle fatigue crack initiation loss in the load adjustment stage, and obtain the target depth peak shaving operation control parameters in the load adjustment stage that meet the stress and life constraint conditions.

[0169] Using an optimization algorithm to solve, under the constraint function, the one that minimizes the objective function Taking the stress, low-cycle fatigue crack initiation loss value, and low-cycle fatigue crack initiation cumulative loss value as constraints simultaneously, the optimization description problem is shown in Equation 20:

[0170] Equation 20;

[0171] Optionally, the optimization algorithm can be selected from gradient descent method, Newton method, genetic algorithm, particle swarm algorithm, etc.

[0172] Based on the predicted stress in the load adjustment stage, the predicted value of low-cycle fatigue crack initiation loss in the load adjustment stage, and the predicted value of cumulative low-cycle fatigue crack initiation loss in the load adjustment stage, the optimized solution obtained is the optimal control parameter for turbine depth peak shaving based on the fusion of stress and life, and is the target depth peak shaving operation control parameter in the start-stop stage that meets the stress and life constraint conditions.

[0173] Step 105: Control the turbine in the start-stop stage according to the target depth peak shaving operation control parameters in the start-stop stage, and control the turbine in the load adjustment stage according to the target depth peak shaving operation control parameters in the load adjustment stage.

[0174] Specifically, controlling the turbine in the start-stop stage according to the target depth peak shaving operation control parameters in the start-stop stage, and controlling the turbine in the load adjustment stage according to the target depth peak shaving operation control parameters in the load adjustment stage can be directly controlling the turbine for depth peak shaving operation according to the corresponding operation control parameters, or sending the above operation control parameters to the turbine DEH or TCS, and DEH or TCS receives the operation control parameters and controls the turbine for depth peak shaving operation. For example, when the turbine needs to start, the turbine accelerates at a rotational speed increase rate; when the turbine needs to stop, the turbine decelerates at a Perform speed reduction control at the reduced rotation speed rate; when the steam turbine needs to increase the load, the steam turbine performs load increase control at the load increase rate; when the steam turbine needs to reduce the load, the steam turbine performs load reduction control at the load reduction rate. Optionally, when the objective function of the steam turbine adopts piecewise calculation, the steam turbine performs speed or load control according to the corresponding speed or load interval and adopts the optimal control parameters in each interval.

[0175] In some embodiments, one mode can be selected from the stress-based, low-cycle fatigue crack initiation loss value-based, and low-cycle fatigue crack initiation cumulative loss value-based modes for the deep peak shaving operation of the steam turbine. After the selected mode is determined, the corresponding optimal parameter speed change rate or load change rate is transmitted to the steam turbine control systems DEH or TCS to perform closed-loop control on the deep peak shaving process of the steam turbine.

[0176] In some embodiments, any combination of the above three modes can be used for the deep peak shaving operation of the steam turbine. At this time, the optimal control parameters that meet multiple objectives are calculated and transmitted to the steam turbine control systems DEH or TCS to perform closed-loop control on the deep peak shaving process of the steam turbine.

[0177] Optionally, after step 105 is executed, steps 51 to 52 can also be executed.

[0178] Step 51, monitor the operating state of the steam turbine in real time.

[0179] Specifically, monitor the state of the steam turbine during operation in real time, such as obtaining the rotation speed, differential expansion, axial displacement, vibration, upper and lower cylinder temperature difference, etc. of the steam turbine in real time.

[0180] Step 52, if the steam turbine appears in an abnormal condition, suspend the operation control of the steam turbine and send an alarm message to the target user device.

[0181] Specifically, the abnormal condition of the steam turbine is the condition during abnormal operation, such as the rotation speed exceeding 110% of the rated rotation speed, differential expansion exceeding the limit, axial displacement exceeding the limit, vibration exceeding the limit, upper and lower cylinder temperature difference exceeding 50°C, etc. The target user device is the user device of the maintenance personnel. If the steam turbine appears in an abnormal condition, suspend the operation control of the steam turbine. The suspension method can be to send a locking signal for the optimal control of the deep peak shaving of the steam turbine based on stress and life. And send an alarm message to the target user device for the maintenance personnel to handle.

[0182] The solution of this application is to obtain the current operating parameters of the high-temperature components of the steam turbine; input the current operating parameters into the stress prediction model for the start-up and shutdown stages of the high-temperature components of the steam turbine and the stress prediction model for the load adjustment stage of the high-temperature components of the steam turbine respectively, to obtain the predicted stress parameters for the start-up and shutdown stages output by the stress prediction model for the start-up and shutdown stages of the high-temperature components of the steam turbine, and the predicted stress parameters for the load adjustment stage output by the stress prediction model for the load adjustment stage of the high-temperature components of the steam turbine; wherein, the predicted stress parameters include stress values, material Poisson's ratios, and material elastic moduli; calculate the predicted value of low-cycle fatigue crack initiation loss and the predicted cumulative loss of low-cycle fatigue crack initiation for the start-up and shutdown stages according to the material Poisson's ratio and material elastic modulus for the start-up and shutdown stages, and calculate the predicted value of low-cycle fatigue crack initiation loss and the predicted cumulative loss of low-cycle fatigue crack initiation for the load adjustment stage according to the material Poisson's ratio and material elastic modulus for the load adjustment stage; determine the target deep peak shaving operation control parameters for the start-up and shutdown stages that meet the stress and life constraint conditions according to the predicted stress for the start-up and shutdown stages, the predicted value of low-cycle fatigue crack initiation loss for the start-up and shutdown stages, and the predicted cumulative loss of low-cycle fatigue crack initiation for the start-up and shutdown stages, and determine the target deep peak shaving operation control parameters for the load adjustment stage that meet the stress and life constraint conditions according to the predicted stress for the load adjustment stage, the predicted value of low-cycle fatigue crack initiation loss for the load adjustment stage, and the predicted cumulative loss of low-cycle fatigue crack initiation for the load adjustment stage; control the steam turbine in the start-up and shutdown stages according to the target deep peak shaving operation control parameters for the start-up and shutdown stages, and control the steam turbine in the load adjustment stage according to the target deep peak shaving operation control parameters for the load adjustment stage. That is, the solution of this application determines the control parameters of the steam turbine from the aspects of stress and loss in the start-up and shutdown stages and the load adjustment stage of the steam turbine, so as to be able to improve the operating performance of the steam turbine while avoiding modifying the control system architecture of the in-service steam turbine, that is, avoiding exceeding the stress load and loss load of the steam turbine, thereby enabling the steam turbine to meet the demand for deep peak shaving while reducing the component loss of the steam turbine, increasing the service life of the steam turbine, and realizing the refined management and performance excavation in the deep peak shaving process of the steam turbine.

[0183] Figure 2 It is a schematic flow chart of the determination process of the stress prediction model for the start-up and shutdown stages of the high-temperature components of the steam turbine in the steam turbine operation control method provided by this application. In this embodiment, Figure 1 On the basis of the embodiments shown and various optional implementation schemes, the determination steps of the stress prediction model for the start-up and shutdown stages of the high-temperature components of the steam turbine are described in detail. As Figure 2 shown, the method may include the following steps:

[0184] Step 201, use the geometric structure and material parameters of the high-temperature components of the steam turbine to establish a thermo-solid coupling finite element model of the high-temperature components of the steam turbine.

[0185] Specifically, a finite element model is established by using the geometric structure and material parameters of high-temperature components of a steam turbine. For example, the surface temperature and volume temperature corresponding to different load values are set as the initial calculation conditions. Using large-scale finite element analysis software, the equivalent stress, allowable stress, material Poisson's ratio, and material elastic modulus of the high-temperature components of the steam turbine corresponding to each load value are calculated under different load increase rates and load decrease rates. The equivalent stress is a composite stress including thermal stress and centrifugal stress. A thermo-solid coupling finite element model of the high-temperature components of the steam turbine is obtained by combining the equivalent stress, allowable stress, material Poisson's ratio, and material elastic modulus.

[0186] Step 202: For each preset temperature, during the starting and accelerating stage of the steam turbine, determine the stress parameters corresponding to each acceleration rate of the high-temperature components of the steam turbine according to the thermo-solid coupling finite element model of the high-temperature components of the steam turbine, and use them as the stress parameter group for the accelerating stage corresponding to the preset temperature.

[0187] Specifically, at each preset temperature, using large-scale finite element analysis software, during the starting and accelerating stage of the steam turbine, determine the stress parameters corresponding to each acceleration rate of the high-temperature components of the steam turbine according to the thermo-solid coupling finite element model of the high-temperature components of the steam turbine, and use them as the stress parameter group for the accelerating stage corresponding to the preset temperature.

[0188] Step 203: Use the stress parameter groups for the accelerating stage corresponding to multiple preset temperatures as the stress data set for the starting and accelerating stage of the high-temperature components of the steam turbine.

[0189] Step 204: For each preset temperature, during the shutdown and decelerating stage of the steam turbine, determine the stress parameters corresponding to each deceleration rate of the high-temperature components of the steam turbine according to the thermo-solid coupling finite element model of the high-temperature components of the steam turbine, and use them as the stress parameter group for the decelerating stage corresponding to the preset temperature.

[0190] Specifically, at each preset temperature, using large-scale finite element analysis software, during the shutdown and decelerating stage of the steam turbine, determine the stress parameters corresponding to each deceleration rate of the high-temperature components of the steam turbine according to the thermo-solid coupling finite element model of the high-temperature components of the steam turbine, and use them as the stress parameter group for the decelerating stage corresponding to the preset temperature.

[0191] Step 205: Use the stress parameter groups for the decelerating stage corresponding to multiple preset temperatures as the stress data set for the shutdown and decelerating stage of the high-temperature components of the steam turbine.

[0192] Step 206: Based on the stress data set for the starting and accelerating stage and the stress data set for the shutdown and decelerating stage, use an artificial intelligence algorithm to construct a stress prediction model for the starting and stopping stages of the high-temperature components of the steam turbine.

[0193] Specifically, based on the stress datasets in the startup speed-up stage and shutdown speed-down stage, with the initial surface temperature, initial volume temperature, speed-up rate, speed-down rate, rotational speed, and startup / shutdown status flag as inputs, and the equivalent stress, allowable stress, material Poisson's ratio, and material elastic modulus as outputs, an artificial intelligence algorithm and a cross-validation training method are used to train and obtain a stress prediction model for the startup and shutdown stages. Exemplarily, a stress prediction model for the startup and shutdown stages of high-temperature components of a steam turbine is constructed through Formula 21.

[0194] Formula 21;

[0195] Among them, is the equivalent stress of the high-temperature component, is the allowable stress of the high-temperature component, is the material Poisson's ratio of the high-temperature component, is the material elastic modulus of the high-temperature component, is the initial surface temperature of the high-temperature component, is the initial volume temperature of the high-temperature component, is the speed-up rate of the steam turbine rotational speed, is the speed-down rate of the steam turbine rotational speed, is the steam turbine rotational speed, is the startup / shutdown status flag of the steam turbine (1 for startup speed-up, 2 for shutdown speed-down, and 0 for other states), is the thermal stress prediction model for the startup and shutdown stages.

[0196] Optionally, since the thermal stress of the high-temperature components of the steam turbine is related to its temperature field, and due to the thermal inertia of the material, the thermal stress at the current moment is related not only to the current input but also to the previous state. Therefore, the artificial intelligence algorithm can be a model structure such as an autoregressive neural network or a recurrent neural network.

[0197] In the solution of the present application, by separately determining the stress dataset in the speed-up stage during startup and the stress dataset in the speed-down stage during shutdown, the operation process of the steam turbine is refined, and the accuracy of model training is further improved, thereby further enhancing the refined control of the deep peak shaving process of the steam turbine.

[0198] Figure 4 is a schematic structural diagram of an intelligent agent for steam turbine operation control provided by the present application, and this intelligent agent is suitable for executing the steam turbine operation control method provided by the present application. As Figure 4 shown, this intelligent agent may specifically include:

[0199] An acquisition module 301, configured to acquire the current operating parameters of the high-temperature components of the steam turbine.

[0200] An input module 302 is configured to input the current operating parameters into a stress prediction model for the start-up and shut-down stages of high-temperature components of a steam turbine and a stress prediction model for the load adjustment stage of high-temperature components of a steam turbine respectively, so as to obtain predicted stress parameters for the start-up and shut-down stages output by the stress prediction model for the start-up and shut-down stages of high-temperature components of a steam turbine, and predicted stress parameters for the load adjustment stage output by the stress prediction model for the load adjustment stage of high-temperature components of a steam turbine; wherein, the predicted stress parameters include stress values, material Poisson's ratios, and material elastic moduli.

[0201] A calculation module 303 is configured to calculate a predicted value of low-cycle fatigue crack initiation loss and a predicted value of cumulative low-cycle fatigue crack initiation loss for the start-up and shut-down stages according to the material Poisson's ratio and material elastic modulus for the start-up and shut-down stages, and calculate a predicted value of low-cycle fatigue crack initiation loss and a predicted value of cumulative low-cycle fatigue crack initiation loss for the load adjustment stage according to the material Poisson's ratio and material elastic modulus for the load adjustment stage.

[0202] A determination module 304 is configured to determine target deep peak shaving operation control parameters for the start-up and shut-down stages that meet stress and life constraint conditions according to the predicted stress for the start-up and shut-down stages, the predicted value of low-cycle fatigue crack initiation loss for the start-up and shut-down stages, and the predicted value of cumulative low-cycle fatigue crack initiation loss for the start-up and shut-down stages, and determine target deep peak shaving operation control parameters for the load adjustment stage that meet stress and life constraint conditions according to the predicted stress for the load adjustment stage, the predicted value of low-cycle fatigue crack initiation loss for the load adjustment stage, and the predicted value of cumulative low-cycle fatigue crack initiation loss for the load adjustment stage.

[0203] A control module 305 is configured to control a steam turbine in the start-up and shut-down stages according to the target deep peak shaving operation control parameters for the start-up and shut-down stages, and control a steam turbine in the load adjustment stage according to the target deep peak shaving operation control parameters for the load adjustment stage.

[0204] For the specific working processes and achievable beneficial effects of the steam turbine operation control agent of the present application and various optional implementation manners, reference may be made to the corresponding processes and beneficial effects in the foregoing method embodiments, which will not be elaborated herein.

[0205] The present application further provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, and when the processor executes the program, it implements the steam turbine operation control method provided in any one of the foregoing embodiments.

[0206] The present application further provides a computer-readable medium, on which a computer program is stored, and when the program is executed by a processor, it implements the steam turbine operation control method provided in any one of the foregoing embodiments.

[0207] Next, refer to Figure 5, which shows a schematic structural diagram of an electronic device 400 suitable for implementing the present application. Figure 5 The illustrated electronic device is merely an example and should not impose any limitation on the functions and scope of use of the present application.

[0208] As Figure 5 shown, the electronic device 400 includes a central processing unit (CPU) 401, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 402 or the program loaded from the storage section 408 into the random access memory (RAM) 403. In the RAM 403, various programs and data required for the operation of the electronic device 400 are also stored. The CPU 401, ROM 402, and RAM 403 are connected to each other via a bus 404. The input / output (I / O) interface 405 is also connected to the bus 404.

[0209] The following components are connected to the I / O interface 405: an input section 406 including a keyboard, a mouse, etc.; an output section 407 including, for example, a cathode ray tube (CRT), a liquid crystal display (LCD), etc. and a speaker, etc.; a storage section 408 including a hard disk, etc.; and a communication section 409 including a network interface card such as a LAN card, a modem, etc. The communication section 409 performs communication processing via a network such as the Internet. A drive 410 is also connected to the I / O interface 405 as required. A removable medium 411, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 410 as required so that a computer program read from it can be installed into the storage section 408 as required.

[0210] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes program codes for performing the methods shown in the flowcharts. In such an embodiment, the computer program can be downloaded and installed from the network through the communication section 409, and / or installed from the removable medium 411. When the computer program is executed by the central processing unit (CPU) 401, the above functions defined in the system of the present application are executed.

[0211] It should be noted that the computer-readable medium shown in this application can be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of a computer-readable storage medium can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this application, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. And in this application, a computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, in which computer-readable program code is carried. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on a computer-readable medium can be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0212] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in the flowchart or block diagram can represent a module, a program segment, or a part of code that contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram or flowchart, as well as combinations of blocks in the block diagram or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or operations, or by a combination of dedicated hardware and computer instructions.

[0213] The modules and / or units involved in this application can be implemented in software or in hardware. The described modules and / or units can also be provided in a processor. For example, it can be described as: a processor includes an acquisition module, an input module, a calculation module, a determination module, and a control module. Among them, the names of these modules do not constitute a limitation to the module itself in some cases.

[0214] As another aspect, this application also provides a computer-readable medium, which can be included in the device described in the above embodiments; or it can exist alone without being assembled into the device. The above computer-readable medium carries one or more programs. When the above one or more programs are executed by a device, the device performs the following operations:

[0215] Obtain the current operating parameters of the high-temperature components of the steam turbine; input the current operating parameters into the stress prediction model for the start-up and shutdown stages of the high-temperature components of the steam turbine and the stress prediction model for the load adjustment stage of the high-temperature components of the steam turbine respectively, to obtain the predicted stress parameters for the start-up and shutdown stages output by the stress prediction model for the start-up and shutdown stages of the high-temperature components of the steam turbine, and the predicted stress parameters for the load adjustment stage output by the stress prediction model for the load adjustment stage of the high-temperature components of the steam turbine; where the predicted stress parameters include stress values, material Poisson's ratios, and material elastic moduli; calculate the predicted value of low-cycle fatigue crack initiation loss and the predicted cumulative loss of low-cycle fatigue crack initiation for the start-up and shutdown stages according to the material Poisson's ratio and material elastic modulus for the start-up and shutdown stages, and calculate the predicted value of low-cycle fatigue crack initiation loss and the predicted cumulative loss of low-cycle fatigue crack initiation for the load adjustment stage according to the material Poisson's ratio and material elastic modulus for the load adjustment stage; determine the target deep peak shaving operation control parameters for the start-up and shutdown stages that meet the stress and life constraint conditions according to the predicted stress for the start-up and shutdown stages, the predicted value of low-cycle fatigue crack initiation loss for the start-up and shutdown stages, and the predicted cumulative loss of low-cycle fatigue crack initiation for the start-up and shutdown stages, and determine the target deep peak shaving operation control parameters for the load adjustment stage that meet the stress and life constraint conditions according to the predicted stress for the load adjustment stage, the predicted value of low-cycle fatigue crack initiation loss for the load adjustment stage, and the predicted cumulative loss of low-cycle fatigue crack initiation for the load adjustment stage; control the steam turbine in the start-up and shutdown stages according to the target deep peak shaving operation control parameters for the start-up and shutdown stages, and control the steam turbine in the load adjustment stage according to the target deep peak shaving operation control parameters for the load adjustment stage.

[0216] According to the technical solution of the present application, the current operating parameters of the high-temperature components of the steam turbine are obtained; the current operating parameters are respectively input into the stress prediction model for the start-stop stage of the high-temperature components of the steam turbine and the stress prediction model for the load adjustment stage of the high-temperature components of the steam turbine, and the predicted stress parameters for the start-stop stage output by the stress prediction model for the start-stop stage of the high-temperature components of the steam turbine and the predicted stress parameters for the load adjustment stage output by the stress prediction model for the load adjustment stage of the high-temperature components of the steam turbine are obtained; wherein, the predicted stress parameters include stress values, material Poisson's ratios, and material elastic moduli; calculate the predicted value of low-cycle fatigue crack initiation loss and the predicted cumulative loss of low-cycle fatigue crack initiation for the start-stop stage according to the material Poisson's ratio and material elastic modulus in the start-stop stage, and calculate the predicted value of low-cycle fatigue crack initiation loss and the predicted cumulative loss of low-cycle fatigue crack initiation for the load adjustment stage according to the material Poisson's ratio and material elastic modulus in the load adjustment stage; determine the target deep peak shaving operation control parameters for the start-stop stage that meet the stress and life constraint conditions according to the predicted stress in the start-stop stage, the predicted value of low-cycle fatigue crack initiation loss in the start-stop stage, and the predicted cumulative loss of low-cycle fatigue crack initiation in the start-stop stage, and determine the target deep peak shaving operation control parameters for the load adjustment stage that meet the stress and life constraint conditions according to the predicted stress in the load adjustment stage, the predicted value of low-cycle fatigue crack initiation loss in the load adjustment stage, and the predicted cumulative loss of low-cycle fatigue crack initiation in the load adjustment stage; control the steam turbine in the start-stop stage according to the target deep peak shaving operation control parameters for the start-stop stage, and control the steam turbine in the load adjustment stage according to the target deep peak shaving operation control parameters for the load adjustment stage. That is, the solution of the present application determines the control parameters of the steam turbine from the aspects of stress and loss in the start-stop stage and load adjustment stage of the steam turbine, so that while avoiding modifying the control system architecture of the in-service steam turbine, the operating performance of the steam turbine can be improved, that is, avoiding exceeding the stress load and loss load of the steam turbine, thereby enabling the steam turbine to meet the response deep peak shaving demand while reducing the component loss of the steam turbine, increasing the service life of the steam turbine, and realizing the refined management and performance excavation of the steam turbine deep peak shaving process.

[0217] The embodiment of the present application also provides a computer program product, including a computer program, which realizes the steam turbine operation control method provided in any embodiment of the present application when executed by a processor.

[0218] In the process of implementing the computer program product, computer program code for performing the operations of this application can be written in one or more programming languages or combinations thereof. The programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, executed as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any kind of network - including a local area network (LAN) or a wide area network (WAN) - or, it can be connected to an external computer (for example, by using an Internet service provider to connect through the Internet).

[0219] It should be understood that various forms of the processes shown above can be used, steps can be reordered, added or deleted. For example, the steps described in this application can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of this application can be achieved, and no limitation is made herein.

[0220] The above specific embodiments do not constitute a limitation on the protection scope of this application. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can occur depending on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application shall be included within the protection scope of this application.

Claims

1. A steam turbine operation control method, characterized in that, The method includes: Obtaining the current operating parameters of the high-temperature components of the steam turbine; Respectively inputting the current operating parameters into the stress prediction model for the start-up and shut-down stages of the high-temperature components of the steam turbine and the stress prediction model for the load adjustment stage of the high-temperature components of the steam turbine, to obtain the predicted stress parameters for the start-up and shut-down stages output by the stress prediction model for the start-up and shut-down stages of the high-temperature components of the steam turbine, and the predicted stress parameters for the load adjustment stage output by the stress prediction model for the load adjustment stage of the high-temperature components of the steam turbine; wherein, the predicted stress parameters include stress values, material Poisson's ratios, and material elastic moduli; Calculating the predicted value of low-cycle fatigue crack initiation loss and the predicted cumulative loss of low-cycle fatigue crack initiation for the start-up and shut-down stages according to the material Poisson's ratio and material elastic modulus for the start-up and shut-down stages, and calculating the predicted value of low-cycle fatigue crack initiation loss and the predicted cumulative loss of low-cycle fatigue crack initiation for the load adjustment stage according to the material Poisson's ratio and material elastic modulus for the load adjustment stage; Determining the target deep peak shaving operation control parameters for the start-up and shut-down stages that meet the stress and life constraint conditions according to the predicted stress for the start-up and shut-down stages, the predicted value of low-cycle fatigue crack initiation loss for the start-up and shut-down stages, and the predicted cumulative loss of low-cycle fatigue crack initiation for the start-up and shut-down stages, and determining the target deep peak shaving operation control parameters for the load adjustment stage that meet the stress and life constraint conditions according to the predicted stress for the load adjustment stage, the predicted value of low-cycle fatigue crack initiation loss for the load adjustment stage, and the predicted cumulative loss of low-cycle fatigue crack initiation for the load adjustment stage; Controlling the steam turbine in the start-up and shut-down stages according to the target deep peak shaving operation control parameters for the start-up and shut-down stages, and controlling the steam turbine in the load adjustment stage according to the target deep peak shaving operation control parameters for the load adjustment stage.

2. The method according to claim 1, characterized in that, The stress prediction model for the start-up and shut-down stages of the high-temperature components of the steam turbine is obtained through the following steps: Using the geometric structure and material parameters of the high-temperature components of the steam turbine to establish a thermo-solid coupling finite element model of the high-temperature components of the steam turbine; For each preset temperature, in the start-up speed-up stage of the steam turbine, determining the stress parameters corresponding to each speed-up rate of the high-temperature components of the steam turbine according to the thermo-solid coupling finite element model of the high-temperature components of the steam turbine, as the stress parameter group for the speed-up stage corresponding to the preset temperature; Taking the stress parameter groups for the speed-up stages corresponding to multiple preset temperatures as the stress data set for the start-up speed-up stage of the high-temperature components of the steam turbine; For each preset temperature, in the shut-down speed-down stage of the steam turbine, determining the stress parameters corresponding to each speed-down rate of the high-temperature components of the steam turbine according to the thermo-solid coupling finite element model of the high-temperature components of the steam turbine, as the stress parameter group for the speed-down stage corresponding to the preset temperature; Taking the stress parameter groups for the speed-down stages corresponding to multiple preset temperatures as the stress data set for the shut-down speed-down stage of the high-temperature components of the steam turbine; Based on the stress data set for the start-up speed-up stage and the stress data set for the shut-down speed-down stage, using an artificial intelligence algorithm to construct the stress prediction model for the start-up and shut-down stages of the high-temperature components of the steam turbine.

3. The method according to claim 2, wherein The stress prediction model for the high-temperature components of the steam turbine during the load adjustment stage is obtained through the following steps: Construct a stress dataset for the load increasing stage and a stress dataset for the load decreasing stage; Based on the stress dataset for the load increasing stage and the stress dataset for the load decreasing stage, use an artificial intelligence algorithm to construct the stress prediction model for the high-temperature components of the steam turbine during the load adjustment stage.

4. The method according to claim 3, wherein The construction of the stress dataset for the load increasing stage and the stress dataset for the load decreasing stage includes: At the first initial load, for each preset temperature, during the load increasing stage of the steam turbine, according to the thermo-mechanical coupling finite element model of the high-temperature components of the steam turbine, determine the stress parameters corresponding to each load when the high-temperature components of the steam turbine increase the load at different load increasing rates, and use them as the stress parameter group for the load increasing stage corresponding to the preset temperature at the first initial load; where the first initial load is the first initial load in the preset initial load group, and the preset initial load group is a set of data arranged from small to large; Store the stress parameter group for the load increasing stage corresponding to the preset temperature at the first initial load into the stress dataset for the load increasing stage; Take the next load of the first initial load in the preset initial load group as the new first initial load, and return to execute the step of "at the first initial load, for each preset temperature, during the load increasing stage of the steam turbine, according to the thermo-mechanical coupling finite element model of the high-temperature components of the steam turbine, determine the stress parameters corresponding to each load when the high-temperature components of the steam turbine increase the load at different load increasing rates, and use them as the stress parameter group for the load increasing stage corresponding to the preset temperature at the first initial load", until each initial load in the preset initial load group is traversed to obtain the stress dataset for the load increasing stage; At the second initial load, for each preset temperature, during the load decreasing stage of the steam turbine, according to the thermo-mechanical coupling finite element model of the high-temperature components of the steam turbine, determine the stress parameters corresponding to each load when the high-temperature components of the steam turbine decrease the load at different load decreasing rates, and use them as the stress parameter group for the load decreasing stage corresponding to the preset temperature at the second initial load; where the second initial load is the last initial load in the preset initial load group; Store the stress parameter group for the load decreasing stage corresponding to the preset temperature at the second initial load into the stress dataset for the load decreasing stage; Take the previous load of the second initial load in the preset initial load group as the new second initial load, and return to execute the step of "at the second initial load, for each preset temperature, during the load decreasing stage of the steam turbine, according to the thermo-mechanical coupling finite element model of the high-temperature components of the steam turbine, determine the stress parameters corresponding to each load when the high-temperature components of the steam turbine decrease the load at different load decreasing rates, and use them as the stress parameter group for the load decreasing stage corresponding to the preset temperature at the second initial load", until each initial load in the preset initial load group is traversed to obtain the stress dataset for the load decreasing stage.

5. The method according to claim 1, characterized in that, Before determining the start-stop stage target deep peak shaving operation control parameters that meet the stress and life constraint conditions based on the predicted stress in the start-stop stage, the predicted value of low-cycle fatigue crack initiation loss in the start-stop stage, and the predicted cumulative loss of low-cycle fatigue crack initiation in the start-stop stage, the method further includes: Construct the stress and life constraint conditions according to the start-stop stage stress prediction model of the high-temperature components of the steam turbine, the stress prediction model of the high-temperature components of the steam turbine during the load adjustment stage, and the current operating parameters.

6. The method according to claim 5, wherein Determining the start-stop stage target deep peak shaving operation control parameters that meet the stress and life constraint conditions based on the predicted stress in the start-stop stage, the predicted value of low-cycle fatigue crack initiation loss in the start-stop stage, and the predicted cumulative loss of low-cycle fatigue crack initiation in the start-stop stage includes: Obtain the operation control instruction of the high-temperature components of the steam turbine; Construct a time-based steam turbine deep peak shaving objective function based on the operation control instruction; Using an optimization algorithm, when the stress and life constraint conditions are met, minimize the steam turbine deep peak shaving objective function according to the predicted stress in the start-stop stage, the predicted value of low-cycle fatigue crack initiation loss in the start-stop stage, and the predicted cumulative loss of low-cycle fatigue crack initiation in the start-stop stage, so as to obtain the start-stop stage target deep peak shaving operation control parameters that meet the stress and life constraint conditions.

7. The method according to claim 6, characterized in that, Determining the load adjustment stage target deep peak shaving operation control parameters that meet the stress and life constraint conditions based on the predicted stress in the load adjustment stage, the predicted value of low-cycle fatigue crack initiation loss in the load adjustment stage, and the predicted cumulative loss of low-cycle fatigue crack initiation in the load adjustment stage includes: Using an optimization algorithm, when the stress and life constraint conditions are met, minimize the steam turbine deep peak shaving objective function according to the predicted stress in the load adjustment stage, the predicted value of low-cycle fatigue crack initiation loss in the load adjustment stage, and the predicted cumulative loss of low-cycle fatigue crack initiation in the load adjustment stage, so as to obtain the load adjustment stage target deep peak shaving operation control parameters that meet the stress and life constraint conditions.

8. The method according to claim 1, wherein The method further includes: Monitor the operating state of the steam turbine in real time; If the steam turbine appears in an abnormal condition, suspend the operation control of the steam turbine and send an alarm message to the target user device.

9. An intelligent agent for steam turbine operation control, characterized in that, The intelligent agent includes: An acquisition module for acquiring the current operating parameters of the high-temperature components of the steam turbine; An input module for respectively inputting the current operating parameters into the start-stop stage stress prediction model of the high-temperature components of the steam turbine and the stress prediction model of the high-temperature components of the steam turbine during the load adjustment stage, to obtain the predicted stress parameters in the start-stop stage output by the start-stop stage stress prediction model of the high-temperature components of the steam turbine, and to obtain the predicted stress parameters in the load adjustment stage output by the stress prediction model of the high-temperature components of the steam turbine during the load adjustment stage; wherein, the predicted stress parameters include stress value, material Poisson's ratio, and material elastic modulus; A calculation module, configured to calculate a predicted value of low-cycle fatigue crack initiation loss and a predicted value of cumulative low-cycle fatigue crack initiation loss during the start-stop stage according to the Poisson's ratio and elastic modulus of the material in the start-stop stage, and calculate a predicted value of low-cycle fatigue crack initiation loss and a predicted value of cumulative low-cycle fatigue crack initiation loss during the load adjustment stage according to the Poisson's ratio and elastic modulus of the material in the load adjustment stage; A determination module, configured to determine the target depth peak shaving operation control parameters in the start-stop stage that meet the stress and life constraint conditions according to the predicted stress in the start-stop stage, the predicted value of low-cycle fatigue crack initiation loss in the start-stop stage, and the predicted value of cumulative low-cycle fatigue crack initiation loss in the start-stop stage, and determine the target depth peak shaving operation control parameters in the load adjustment stage that meet the stress and life constraint conditions according to the predicted stress in the load adjustment stage, the predicted value of low-cycle fatigue crack initiation loss in the load adjustment stage, and the predicted value of cumulative low-cycle fatigue crack initiation loss in the load adjustment stage; A control module, configured to control the steam turbine in the start-stop stage according to the target depth peak shaving operation control parameters in the start-stop stage, and control the steam turbine in the load adjustment stage according to the target depth peak shaving operation control parameters in the load adjustment stage.

10. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steam turbine operation control method according to any one of claims 1 to 8.

Images