A method for predicting the influence of steam turbine expansion difference on the starting time of a combined cycle unit

Abstract

The present disclosure provides a method for predicting the influence of steam turbine expansion difference on the starting time of a combined cycle unit. By collecting key state parameters before cold starting, the dynamic evolution of expansion difference and stress is deduced synchronously by using a time series prediction model to backtrack historical data sequences, the period in which the expansion difference dominates the speed limit of the main steam control valve is accurately locked, and the total stagnation time caused by the expansion difference is quantified. The method realizes the active prediction of unpredictable expansion difference risk, converts the traditional passive waiting "blind operation" in operation into a quantifiable delay forecast, compresses the starting time of the unit, significantly improves the peak shaving response capability, and provides deterministic decision support for power grid dispatching.

Description

Technical Field

[0001] This invention relates to the field of cross-technology of gas-steam combined cycle power generation and industrial heating, and particularly to a method and system for predicting the impact of turbine expansion differential on the start-up time of combined cycle units. Background Technology

[0002] Currently, natural gas power generation is undergoing a new stage of large-scale development. Compared with coal-fired units, gas-steam combined cycle units have significant advantages such as lower pollutant emissions, faster load response, and lower plant power consumption. Among them, Class F units have become the mainstream choice in the industry due to their superior thermodynamic cycle efficiency. These units generate electricity by burning natural gas in a gas turbine to drive a generator, while simultaneously using high-temperature flue gas to generate steam in a waste heat boiler to drive a steam turbine, forming a typical paradigm of energy cascade utilization.

[0003] However, with the increasing demand for rapid peak shaving from the power grid, the equipment wear and time costs caused by frequent unit start-ups and shutdowns are gradually becoming apparent. Particularly in the steam turbine system, during the initial cold start-up phase, the rotor rapidly heats up and expands due to direct contact with steam, while the cylinder, constrained by its large mass and long heat transfer path, heats up more slowly. At this time, the rotor exhibits an axial contraction trend relative to the cylinder. As the steam continues to heat, the cylinder temperature rises at an accelerated rate, and the expansion difference gradually changes from negative to positive. If this dynamic evolution exceeds the design margin of the axial dynamic-static clearance, it can lead to increased steam seal wear and leakage losses, or even cause friction between dynamic and static components, resulting in unit vibration and forcing an operational shutdown.

[0004] Therefore, there is an urgent need to establish a prediction system that can characterize the evolution of expansion differences. Summary of the Invention

[0005] A first aspect of this disclosure provides a method for predicting the impact of turbine differential expansion on the start-up time of a combined cycle unit, comprising the following steps performed before cold start-up of the unit: Acquire measured data of the high-pressure cylinder metal temperature, main steam regulating valve opening, real-time expansion difference value, rotor stress value, expansion difference limiting load rate, and stress limiting load rate of the steam turbine at the initial moment of startup; The measured data is input into the time series prediction model, and by tracing back the data sequence of continuous historical time nodes, the predicted changes in the expansion difference and the predicted changes in the rotor stress during the start-up process are output synchronously. The expansion difference limiting load rate is calculated based on the predicted change in expansion difference, and the stress limiting load rate is calculated based on the predicted change in rotor stress. When the expansion difference limiting load rate is continuously lower than the stress limiting load rate, it is determined that the expansion difference becomes the limiting factor for the opening rate of the main steam control valve during this period. After determining that the expansion difference becomes the limiting factor for the opening rate of the main steam control valve during this period, the total duration of the expansion difference-dominated limiting period is accumulated as the starting stagnation duration caused by the expansion difference.

[0006] In conjunction with the first aspect, the term "tracing back continuous historical time nodes" refers to a data sequence that traces back at least five equally spaced time points from the time of calculation.

[0007] In conjunction with the first aspect, the input of the measured data into the time series prediction model includes the following parameters: The main steam temperature is determined based on the initial metal temperature; Current value and historical sequence of main steam valve opening; Current rotor temperature and its historical sequence; The current value and historical sequence of the inflation difference.

[0008] In conjunction with the first aspect, the calculation method for the expansion difference limiting load rate is as follows: the predicted expansion difference value is substituted into a preset load rate mapping function.

[0009] In conjunction with the first aspect, the method for accumulating the start-up stagnation time is as follows: During the opening of the main steam control valve, when the differential expansion limiting load rate becomes the limiting condition for the actual opening rate, the change in the opening degree of the main steam control valve during this period is recorded as zero. The total duration of all time periods in which the opening change is zero is summed up.

[0010] In conjunction with the first aspect, the cold start is determined by the following combined conditions: The initial metal temperature of the high-pressure cylinder of the steam turbine shall not exceed 289℃; The unit has been continuously shut down for more than 72 hours.

[0011] A second aspect of this disclosure provides a system for predicting the impact of turbine differential expansion on the start-up time of a combined cycle unit, comprising: The data acquisition module is used to acquire the turbine high-pressure cylinder metal temperature, main steam regulating valve opening, real-time expansion difference value, rotor stress value, expansion difference limiting load rate and stress limiting load rate at the initial moment of cold start. The time-series prediction module is connected to the data acquisition module. By tracing back the data sequence of continuous historical time nodes, it synchronously outputs the predicted changes in expansion difference and rotor stress. The limitation determination module is connected to the timing prediction module. It calculates the expansion difference limiting load rate based on the predicted change in expansion difference and the stress limiting load rate based on the predicted change in rotor stress. When the expansion difference limiting load rate is continuously lower than the stress limiting load rate, it outputs the expansion difference dominant limiting signal. The duration accumulation module is connected to the limitation determination module. In response to the expansion difference-dominated limitation signal, it accumulates the total duration of the period when the change in the main steam valve opening is zero, and outputs the start-up stagnation duration caused by the expansion difference.

[0012] In conjunction with the second aspect, the time series prediction module includes: The data backtracking unit stores data sequences from at least five consecutive historical time points; The neural network processor executes a timing prediction algorithm, with input parameters including main steam temperature, main steam regulating valve opening sequence, rotor temperature sequence, and expansion difference value sequence. The steam temperature calculation unit generates a constant main steam temperature value based on the initial metal temperature.

[0013] A third aspect of this disclosure provides an electronic device comprising: One or more processors; A storage unit is used to store one or more programs that, when executed by one or more processors, enable the one or more processors to implement the method for predicting the impact of turbine differential expansion on the start-up time of a combined cycle unit.

[0014] A fourth aspect of this disclosure provides a computer-readable storage medium having a computer program stored thereon, characterized in that, when the computer program is executed by a processor, it can implement the method for predicting the influence of turbine differential expansion on the start-up time of a combined cycle unit.

[0015] Beneficial effects: The method and system disclosed herein for predicting the impact of turbine expansion differential on the start-up time of combined cycle units, by collecting key state parameters before cold start-up and using a time-series prediction model to backtrack historical data sequences to synchronously deduce the dynamic evolution of expansion differential and stress, accurately pinpoints the period during which expansion differential dominates the speed limit of the main steam regulating valve, and quantifies the total stagnation time caused by it. This enables proactive prediction of unforeseen expansion differential risks, transforming the traditional passive waiting "blind operation" into a quantifiable delay forecast, reducing unit start-up time, significantly improving peak-shaving response capability, and providing deterministic decision support for grid dispatch. Attached Figure Description

[0016] Figure 1 This is a schematic diagram of the combined cycle unit structure according to an embodiment of the present disclosure; Figure 2 This is a flowchart illustrating a method for predicting the impact of turbine differential expansion on the start-up time of a combined cycle unit, according to an embodiment of this disclosure. Figure 3 This is a schematic diagram of the structure of a system for predicting the impact of turbine differential expansion on the start-up time of a combined cycle unit, according to an embodiment of this disclosure. Figure 4 An electronic device according to an embodiment of this disclosure. Detailed Implementation

[0017] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with those disclosed herein.

[0018] The terminology used in this disclosure is for the purpose of describing particular embodiments only and is not intended to be limiting of the present disclosure. The singular forms “a,” “the,” and “the” as used in this disclosure and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any and all possible combinations of one or more of the associated listed items.

[0019] It should be understood that although the terms first, second, third, etc., may be used to describe various information in embodiments of this disclosure, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, first information may also be referred to as second information without departing from the scope of embodiments of this disclosure, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to a determination."

[0020] This disclosure relates to an F-class combined cycle unit, which consists of a gas turbine power generation unit, a waste heat recovery unit, and a steam turbine power generation unit.

[0021] The gas turbine power generation unit includes a gas turbine. The gas turbine system adopts the Brayton cycle and uses air as the working medium. The air is compressed by the compressor and mixed with fuel (natural gas, coal gas, etc.) in the combustion chamber to generate high-temperature gas, which drives the turbine to rotate and drive the generator to generate electricity. The waste heat recovery unit includes a three-pressure reheat type waste heat boiler, which uses the waste heat from the exhaust of the gas turbine to produce high-temperature and high-pressure steam. The waste heat boiler is equipped with heat exchange modules of three pressure levels: high pressure, medium pressure, and low pressure, which correspond to the high-pressure cylinder, medium-pressure cylinder, and low-pressure cylinder of the steam turbine, respectively. Energy cascade utilization is achieved through pressure gradient configuration. The steam turbine power generation unit includes a multi-stage steam turbine and a condensing system. It uses high-temperature and high-pressure steam generated by a waste heat boiler to drive the turbine, which in turn drives the generator to generate electricity.

[0022] The gas turbine, steam turbine, and generator are arranged in a coaxial configuration via rigid couplings, forming a clutchless mechanical transmission system.

[0023] refer to Figure 1 This is a schematic diagram of the combined cycle unit structure according to an embodiment of the present disclosure.

[0024] The gas turbine includes a compressor 2, a combustion chamber 3, and a turbine 5. Ambient air 1 is adiabatically compressed by the compressor 2 to form high-pressure gas. This compressed air enters the combustion chamber 3 and isobarically combusted with natural gas 4 to generate high-temperature flue gas. The high-temperature flue gas enters the turbine 5 and expands adiabatically to do work, driving the generator 26 to output electrical energy. The flue gas with an exhaust temperature reduced to 550-630℃ is introduced into the waste heat boiler 6 through a pipeline system for waste heat recovery.

[0025] Waste heat boiler 6 is equipped with three independent heat exchange modules: high pressure, medium pressure, and low pressure. Each pressure level module includes an economizer, evaporator, and superheater assembly. Flue gas undergoes heat transfer sequentially along the thermal gradient within the boiler and is finally discharged into the atmosphere at an emission temperature of 80±5℃ through the tail flue.

[0026] The steam circulation system process is as follows: Condensate pump 23 pressurizes the condensate produced by condenser 25 and then first enters the low-pressure economizer 19. This low-pressure system is equipped with a recirculation pump 20.

[0027] After being preheated, the working fluid forms three independent loops after the low-pressure evaporator 18: High-pressure steam circuit: After being pressurized by high-pressure feedwater pump 22, it passes through high-pressure economizer 16, high-pressure evaporator 11, high-pressure superheater 10, and high-pressure superheater 8 in sequence to generate high-temperature and high-pressure steam to drive the high-pressure cylinder 29 of the steam turbine. Medium-pressure steam circuit: After being pressurized by the medium-pressure feedwater pump 21, it flows sequentially through the medium-pressure economizer 17, medium-pressure economizer 15, medium-pressure evaporator 14 and medium-pressure superheater 13. The generated medium-pressure steam merges with the exhaust steam from the high-pressure cylinder and enters the reheater 9 and reheater 7, finally forming reheated steam to drive the intermediate-pressure cylinder 28 of the steam turbine. Low-pressure steam circuit: The working fluid directly enters the low-pressure superheater 12 to complete the final superheating, forming saturated steam to drive the low-pressure cylinder 27 of the steam turbine to do work.

[0028] The exhaust steam from the low-pressure cylinder 27 of the steam turbine eventually flows into the condenser (25), where it undergoes phase change condensation under the cooling effect of the circulating water (24), forming a closed thermodynamic cycle.

[0029] Preferably, the high-pressure cylinder 29 and the intermediate-pressure cylinder 28 of the steam turbine adopt a symmetrical structural design, and the dynamic stability of the rotor system is achieved through axial thrust balance configuration.

[0030] This integrated design effectively improves the unit's thermal efficiency.

[0031] Continue to refer to Figure 1The gas turbine, steam turbine high-pressure cylinder 29, steam turbine intermediate-pressure cylinder 28, steam turbine low-pressure cylinder 27 and generator 26 are located on the same shaft system. The shaft system consists of multiple rotors, and adjacent rotors are connected in series through couplings. Therefore, during the start-up and operation of the unit, the gas turbine, steam turbine and generator always maintain the same speed.

[0032] Turbine expansion difference refers to the difference in axial expansion between the turbine rotor and cylinder due to differences in thermal inertia during hot operation. Its mathematical expression is: , In the formula, The coefficient of linear expansion of the rotor material. The effective expansion section length of the rotor. The average temperature rise of the rotor, , where is the coefficient of linear expansion of the cylinder material. The effective expansion section length of the cylinder, This represents the average temperature rise of the cylinder.

[0033] Figure 2 This is a flowchart illustrating a method for predicting the impact of turbine differential expansion on the start-up time of a combined cycle unit, according to an embodiment of this disclosure, including: S101: Acquire the measured data of the turbine high-pressure cylinder metal temperature, main steam regulating valve opening, real-time expansion difference value, rotor stress value, expansion difference limiting load rate and stress limiting load rate at the initial moment of startup. Specifically, the current calculation time is set as Then the previous moment was The initial moment when the damper opens is .

[0034] Get Time unit steam turbine high pressure cylinder metal control temperature Main steam regulating valve opening of the unit Turbine expansion differential Stress in the high-pressure cylinder of the steam turbine Turbine load rate limited by expansion difference Stress-limited turbine load rate .

[0035] Controlling the metal temperature of the high-pressure cylinder Main steam regulating valve opening of the unit Turbine expansion differential Stress in the high-pressure cylinder of the steam turbine Turbine load rate limited by expansion difference Stress-limited turbine load rate Data screening was performed to remove invalid data, and missing data was filled using interpolation. Furthermore, the term "backtracking continuous historical time nodes" refers to tracing back at least five equally spaced time points from the calculation time.

[0036] Preferably, at the start of the calculation, all five backward time points are used. The data at each time point, including the five selected backward time points, all utilize... Data at any given moment.

[0037] S102: Input the measured data into the time series prediction model, and output the predicted changes in the expansion difference and rotor stress during the start-up process by tracing back the data sequence of continuous historical time nodes. Furthermore, the step of inputting the measured data into the time series prediction model includes the following parameters: The main steam temperature is determined based on the initial metal temperature; Current value and historical sequence of main steam valve opening; Current rotor temperature and its historical sequence; The current value and historical sequence of the inflation difference.

[0038] Specifically, in obtaining After taking the measured data at each moment and the data from five backward time points, the main steam temperature before the main steam regulating valve is further calculated.

[0039] During the main steam regulating valve opening phase, the turbine operates at constant parameters, therefore the main steam temperature before the main steam regulating valve remains constant. According to the unit's embedded control system, this temperature is only related to the initial rotor temperature (i.e.,...). Moment Related to, namely: , The main steam temperature before the main steam regulating valve, and the five time points traced back. , Input NARX neural network prediction Rotor temperature at all times; Calculation using rotor heat transfer fitting formula The internal temperature of the rotor at any given time, i.e.: , Calculation using rotor stress fitting formula The rotor stress at any given time (the predicted change in rotor stress), i.e.: , Input the main steam temperature before the main steam regulating valve, and the five time points of the forward backtracking. , and To predict using NARX neural networks The turbine expansion difference at any given time (the predicted change in the expansion difference).

[0040] S103: Calculate the expansion difference limiting load rate based on the predicted change in expansion difference, and calculate the stress limiting load rate based on the predicted change in rotor stress. When the expansion difference limiting load rate is continuously lower than the stress limiting load rate, it is determined that the expansion difference becomes the limiting factor for the opening rate of the main steam control valve during this period. Specifically, the fitting formula is used to calculate... The turbine load rate limited by constant stress, i.e.: , Furthermore, the calculation method for the expansion difference limiting load rate is as follows: the predicted expansion difference value is substituted into a preset load rate mapping function.

[0041] Specifically, the fitting formula is used to calculate... The turbine load rate limited by the constant expansion difference, i.e.: , in, The preset load rate mapping function is used for the expansion difference limit.

[0042] When the differential expansion load rate is consistently lower than the stress load rate, the differential expansion is determined to be the limiting factor for the opening rate of the main steam control valve during that period.

[0043] S104: After determining that the expansion difference becomes the limiting factor for the opening rate of the main steam control valve during the time period, the total duration of the expansion difference-dominated limiting period is accumulated as the starting stagnation duration caused by the expansion difference.

[0044] Furthermore, during the opening of the main steam control valve, when the differential expansion limiting load rate becomes the limiting condition for the actual opening rate, the change in the opening degree of the main steam control valve during that period is recorded as zero. The total duration of all time periods in which the opening change is zero is summed up.

[0045] Specifically, after determining that the expansion difference becomes the limiting factor for the opening rate of the main steam control valve during this period, the integral calculation is performed based on the unit's embedded control system. Main steam valve opening at any given time: , when When it reaches 100%, the main steam valve is considered fully open. This is calculated from the moment when the expansion difference is determined to be the limiting factor for the main steam valve opening rate during that period until... The time to reach 100% is taken as the start-up stall duration caused by the expansion difference.

[0046] It should be noted that the above - Each has its own corresponding preset mapping function.

[0047] Figure 3 This is a schematic diagram of the structure of a system for predicting the impact of turbine differential expansion on the start-up time of a combined cycle unit, according to an embodiment of this disclosure, including: Data acquisition module 210 is used to acquire the turbine high-pressure cylinder metal temperature, main steam regulating valve opening, real-time expansion difference value, rotor stress value, expansion difference limiting load rate and stress limiting load rate at the initial moment of cold start; The time-series prediction module 220 is connected to the data acquisition module. By tracing back the data sequence of continuous historical time nodes, it synchronously outputs the predicted change in expansion difference and the predicted change in rotor stress. The limitation determination module 230 is connected to the timing prediction module. It calculates the expansion difference limiting load rate based on the predicted change in expansion difference and the stress limiting load rate based on the predicted change in rotor stress. When the expansion difference limiting load rate is continuously lower than the stress limiting load rate, it outputs the expansion difference dominant limiting signal. The duration accumulation module 240 is connected to the limitation determination module. In response to the expansion difference-dominated limitation signal, it accumulates the total duration of the period when the change in the main steam valve opening is zero, and outputs the start-up stagnation duration caused by the expansion difference.

[0048] Specifically, the data acquisition module 210 immediately activates upon triggering the cold start command, acquiring six key parameters from the unit's distributed control system (DCS) real-time database at the initial moment: the first-stage metal temperature of the turbine high-pressure cylinder, the main steam regulating valve opening, the real-time expansion differential value, the rotor stress value, the expansion differential limiting load rate, and the stress limiting load rate. This module incorporates data cleaning logic: data exceeding the range (e.g., temperature > 650℃) is directly discarded; for missing data caused by communication interruptions, Lagrange interpolation of the effective values ​​within 5 seconds before and after the interruption is used to fill the gaps. At that moment, the data from the five historical nodes required for backtracking are forcibly assigned a unified value. Actual measured values ​​ensure the completeness of the time series model input.

[0049] The time series prediction module 220 is connected to the acquisition module via a high-speed data bus. Its core is an industrial-grade FPGA chip integrating the NARX neural network algorithm. This module receives the real-time data stream transmitted from the acquisition module and dynamically backtracks the data sequence of five consecutive equally spaced historical nodes (time resolution configurable from 10 to 60 seconds). The prediction process simultaneously performs two key calculations: First, based on the main steam temperature, the main steam regulating valve opening sequence, and the rotor temperature sequence, predict the rotor temperature value at the future time step. Second, based on the same steam temperature, main steam valve opening sequence, rotor temperature sequence, and expansion difference value sequence, the expansion difference change prediction curve is output.

[0050] The limitation determination module 230 contains two parallel calculation paths: the left path inputs the received expansion difference prediction value into a preset load rate mapping function to generate the expansion difference limitation load rate; For example, the right path inputs the rotor stress prediction value into the function and outputs the stress-limited load rate. The two signals are compared in real time: when the differential expansion load rate is lower than the stress-limited load rate (adjustable threshold) for 300 seconds, the digital signal "differential expansion dominant limit flag" is triggered, and this flag signal is maintained until the comparison relationship is reversed.

[0051] The duration accumulation module 240 starts working after receiving the "expansion difference dominance limit flag," and internally constructs a function for the change in the main steam valve opening. When the flag is valid, the module records that the opening change rate for that period is zero. The system scans the opening change status in real time, performs millisecond-level precision accumulation on all periods with a change rate of zero, and finally generates the total value of the expansion difference stagnation duration.

[0052] Optionally, the result can be output as two visual messages through the human-machine interface: the stagnation period is marked in red on the startup process curve, and a prediction conclusion window pops up on the operation terminal, displaying a quantitative prompt that "the expansion difference will cause the valve to stagnate for XX minutes and XX seconds".

[0053] Electronic device 400 can be a desktop computer, laptop, handheld computer, cloud server, or other electronic device. Electronic device 400 may include, but is not limited to, processor 401 and memory 402. Those skilled in the art will understand that... Figure 4 This is merely an example of electronic device 400 and does not constitute a limitation on electronic device 400. It may include more or fewer components than shown, or combine certain components, or different components. For example, electronic device may also include input / output devices, network access devices, buses, etc.

[0054] Processor 401 can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor.

[0055] The memory 402 can be an internal storage unit of the electronic device 400, such as a hard disk or memory of the electronic device 300. The memory 402 can also be an external storage device of the electronic device 400, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the electronic device 400. Furthermore, the memory 402 can include both internal and external storage units of the electronic device 400. The memory 402 is used to store the computer program 403 and other programs and data required by the electronic device. The memory 402 can also be used to temporarily store data that has been output or will be output.

[0056] The above embodiments are only used to illustrate the technical solutions of this disclosure, and are not intended to limit it. Although this disclosure has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this disclosure, and should all be included within the protection scope of this disclosure.

Claims

1. A method for predicting the impact of turbine differential expansion on the start-up time of a combined cycle unit, characterized in that, Perform the following steps before starting the unit in a cold state: Acquire measured data of the high-pressure cylinder metal temperature, main steam regulating valve opening, real-time expansion difference value, rotor stress value, expansion difference limiting load rate, and stress limiting load rate of the steam turbine at the initial moment of startup; The measured data is input into the time series prediction model, and by tracing back the data sequence of continuous historical time nodes, the predicted changes in the expansion difference and the predicted changes in the rotor stress during the start-up process are output synchronously. The expansion difference limiting load rate is calculated based on the predicted change in expansion difference, and the stress limiting load rate is calculated based on the predicted change in rotor stress. When the expansion difference limiting load rate is continuously lower than the stress limiting load rate, it is determined that the expansion difference becomes the limiting factor for the opening rate of the main steam control valve during this period. After determining that the expansion difference becomes the limiting factor for the opening rate of the main steam control valve during this period, the total duration of the expansion difference-dominated limiting period is accumulated as the starting stagnation duration caused by the expansion difference.

2. The method according to claim 1, characterized in that, The term "backtracking continuous historical time nodes" refers to a data sequence that traces back at least five equally spaced time points from the calculation time.

3. The method according to claim 1, characterized in that, The step of inputting the measured data into the time series prediction model includes the following parameters: The main steam temperature is determined based on the initial metal temperature; Current value and historical sequence of main steam valve opening; Current rotor temperature and its historical sequence; The current value and historical sequence of the inflation difference.

4. The method according to claim 1, characterized in that, The method for calculating the load rate limiting the expansion difference is as follows: the predicted expansion difference value is substituted into a preset load rate mapping function.

5. The method according to claim 1, characterized in that, The method for accumulating the start-up pause time is as follows: During the opening of the main steam control valve, when the differential expansion limiting load rate becomes the limiting condition for the actual opening rate, the change in the opening degree of the main steam control valve during this period is recorded as zero. The total duration of all time periods in which the opening change is zero is summed up.

6. The method according to claim 1, characterized in that, The cold start is determined by a combination of the following conditions: The initial metal temperature of the high-pressure cylinder of the steam turbine shall not exceed 100℃; The unit has been continuously shut down for more than 72 hours.

7. A system for predicting the impact of turbine differential expansion on the start-up time of a combined cycle unit, characterized in that, include: The data acquisition module is used to acquire the turbine high-pressure cylinder metal temperature, main steam regulating valve opening, real-time expansion difference value, rotor stress value, expansion difference limiting load rate and stress limiting load rate at the initial moment of cold start. The time-series prediction module is connected to the data acquisition module. By tracing back the data sequence of continuous historical time nodes, it synchronously outputs the predicted changes in expansion difference and rotor stress. The limitation determination module is connected to the timing prediction module. It calculates the expansion difference limiting load rate based on the predicted change in expansion difference and the stress limiting load rate based on the predicted change in rotor stress. When the expansion difference limiting load rate is continuously lower than the stress limiting load rate, it outputs the expansion difference dominant limiting signal. The duration accumulation module is connected to the limitation determination module. In response to the expansion difference-dominated limitation signal, it accumulates the total duration of the period when the change in the main steam valve opening is zero, and outputs the start-up stagnation duration caused by the expansion difference.

8. The system according to claim 7, characterized in that, The time series prediction module includes: The data backtracking unit stores data sequences from at least five consecutive historical time points; The neural network processor executes a timing prediction algorithm, with input parameters including main steam temperature, main steam regulating valve opening sequence, rotor temperature sequence, and expansion difference value sequence. The steam temperature calculation unit generates a constant main steam temperature value based on the initial metal temperature.

9. An electronic device, characterized in that, include: One or more processors; A storage unit is used to store one or more programs that, when executed by one or more processors, enable the one or more processors to implement the method for predicting the effect of turbine differential expansion on the start-up time of a combined cycle unit as described in claims 1-6.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it can implement the method for predicting the impact of turbine expansion differential on the start-up time of combined cycle units as described in claims 1-6.

Images