A flexible operation capacity evaluation method, system, device and medium based on steam turbine rotor expansion difference prediction

Abstract

This invention discloses a method, system, equipment, and medium for assessing the flexible operation capability of a steam turbine based on rotor expansion difference prediction, belonging to the field of power technology. The method includes: constructing a real-time prediction model for turbine expansion difference based on collected multi-dimensional operating data, obtaining an expansion difference prediction algorithm; setting a future target power value to determine the power change trend, and inputting the parameters corresponding to the power change trend into the expansion difference prediction algorithm to calculate the expansion difference prediction value sequence under the current target power; comparing the expansion difference prediction value sequence corresponding to each target power with a preset threshold to determine whether the target power allows for safe adjustment under the current state. This invention can proactively predict expansion difference changes under different power adjustment schemes, quantify the safe adjustment range and rate, provide scientific guidance for the flexible operation of the unit, fully explore peak-shaving potential while ensuring safety, and improve the unit's flexible operation capability.

Description

Technical Field

[0001] This invention relates to the field of power technology, and specifically to a method, system, equipment, and medium for assessing the flexibility of operation based on the prediction of turbine rotor expansion difference. Background Technology

[0002] With the large-scale grid connection of new energy power, especially during deep peak-shaving operation, the expansion difference between the turbine rotor and cylinder often fluctuates violently due to frequent and significant changes in unit load. Once the expansion difference exceeds the safety limit, it may cause serious problems such as unit vibration and friction between moving and stationary parts, or even unplanned shutdowns. It can be said that the stability of the expansion difference is directly related to the safe operation of the turbine and must be monitored and strictly controlled in real time.

[0003] Currently, assessments of the flexible operation capabilities of thermal power units largely focus on economic indicators such as power regulation range, response rate, and coal consumption rate, often neglecting the critical safety constraint parameter of expansion difference. Traditional deep peak-shaving control methods also primarily rely on passive adjustments based on real-time monitoring data, lacking accurate prediction and dynamic assessment of expansion difference. This makes it difficult for units to provide early warnings and avoid the risk of exceeding expansion difference limits during rapid peak-shaving, not only creating safety hazards but also hindering the full realization of the flexible peak-shaving capabilities of thermal power units.

[0004] In fact, turbine differential expansion is complexly influenced by multiple factors, including main steam parameters, extraction conditions, cylinder temperature, and unit power. These factors are highly coupled and change dynamically over time, making it difficult to accurately describe using simple mathematical models. Therefore, how to construct an effective differential expansion prediction model and, based on real-time operating conditions, scientifically quantify the unit's load regulation capacity and rate within a safe range, thereby achieving precise assessment and safe management of the flexible operation capability of thermal power units, has become a pressing technical challenge for the power industry. Summary of the Invention

[0005] In view of the above-mentioned problems, the present invention is proposed.

[0006] Therefore, the present invention aims to provide a flexible operation capability assessment method based on turbine rotor expansion difference prediction, accurately predict the expansion difference change trend under different power regulation schemes, further improve the safety of peak shaving operation of thermal power units, and alleviate the safety problems existing in the current deep peak shaving control method.

[0007] To solve the above-mentioned technical problems, the present invention provides the following technical solution: a method for evaluating the flexibility of operation based on the prediction of turbine rotor differential expansion, comprising, Based on the collected multi-dimensional operational data, a real-time prediction model for turbine expansion difference is constructed. Inertial elements are configured and weighted to form expansion difference prediction values. A future target power value is set to determine the power change trend, and the parameters corresponding to the power change trend are used for expansion difference prediction to calculate the expansion difference prediction value sequence under the current target power. The expansion difference prediction value sequence corresponding to each target power is compared with a preset threshold to determine whether the target power is allowed to be safely adjusted under the current state. In response to being determined to be allowed to be safely adjusted, quantitative indicators characterizing the unit's current flexible operation capability are statistically analyzed and calculated.

[0008] As a preferred embodiment of the flexible operation capability assessment method based on turbine rotor expansion difference prediction described in this invention, the construction of the real-time prediction model for turbine expansion difference includes: Three-dimensional unsteady-state thermal conduction control equations were established for the turbine rotor and cylinder respectively. Based on the preset axial and radial boundary conditions, the temperature distribution at the rotor position and the temperature distribution at the cylinder position at different times were calculated. Based on the temperature distribution, the thermal deformation field is simulated and solved to obtain the axial elongation of the rotor and the axial elongation of the cylinder, which are then input into the expansion difference prediction algorithm.

[0009] As a preferred embodiment of the flexible operation capability assessment method based on turbine rotor expansion difference prediction described in this invention, the step of configuring inertial elements and weighting them together as input parameters includes: The multi-dimensional operational data is used as input parameters to establish first-order inertial links for dynamic processing. The inertial time constant of the input parameter is set in the first-order inertial element to simulate the time lag required for the current parameter change to be transmitted to the expansion difference; Simultaneously, corresponding weighting coefficients are assigned to the first-order inertial element, and all dynamically processed parameter output values ​​and weighting coefficients are linearly superimposed to form the expansion difference prediction value.

[0010] As a preferred embodiment of the flexible operation capability assessment method based on turbine rotor expansion difference prediction described in this invention, wherein: the step of setting a future target power value to determine the power change trend includes: Based on the difference between the target power and the current power, the magnitude and direction of the power change are determined, and the initial power change rate is set according to the magnitude and direction of the power change. The parameter change trend is determined through the power change, and the design characteristic curve of the unit is constructed. Based on the unit's design characteristic curve, the theoretical optimal parameters under the current power change range are obtained, and the theoretical range of parameter changes is determined based on the theoretical optimal parameters, thus obtaining the theoretical change trajectory. By combining the statistical patterns of the same operating conditions in historical operating data, the correlation strength between parameters and power is quantified through correlation analysis to determine key influencing parameters. In conjunction with the initial power change rate, the theoretical change trajectory is corrected to generate a parameter change sequence. Substitute the parameter change sequence into the turbine expansion difference real-time prediction model, and calculate the expansion difference prediction curve for the future time period under each target power. Meanwhile, real-time stress state feedback of the steam turbine is introduced during the prediction process. In response to the real-time stress being greater than or equal to the allowable stress threshold of the material, the rate of change of the expansion difference is reduced.

[0011] As a preferred embodiment of the flexible operation capability assessment method based on turbine rotor differential expansion prediction described in this invention, the step of determining whether the target power allows for safe adjustment under the current state includes: The expansion difference prediction curve is compared with the current unit's preset alarm threshold, wherein the alarm threshold includes an upper limit value for expansion difference alarm and a lower limit value for expansion difference alarm; If all predicted values ​​in the current expansion difference prediction curve are less than the lower limit of the expansion difference alarm, then it is determined that adjusting the current target power is feasible and safe adjustment is allowed. If any predicted value in the current expansion difference prediction curve is greater than or equal to the expansion difference alarm upper limit, it is determined that adjusting the current target power under the current set power change trend poses a risk of exceeding the expansion difference limit, which is not feasible and safe adjustment is not allowed.

[0012] As a preferred embodiment of the flexible operation capability assessment method based on turbine rotor expansion difference prediction described in this invention, wherein: the calculation of the quantitative index characterizing the current flexible operation capability of the unit includes: Among all the target power adjustments deemed feasible, the closed interval formed by the minimum power value and the maximum power value is taken as the safe adjustment range at the current moment. Within the safe adjustment range at the current moment, the conditions under which the predicted value of the expansion difference does not exceed the limit are tested under different power change rates. The maximum allowable power change per unit time is found and quantified as the maximum safe adjustment rate at the current moment. Based on the maximum safe adjustment rate and the safe adjustment range, the time required for the turbine unit to adjust from the current power to the range boundary at the current maximum safe adjustment rate is calculated and recorded as the continuous adjustment duration.

[0013] As a preferred embodiment of the flexible operation capability assessment method based on turbine rotor expansion difference prediction described in this invention, the method includes: after obtaining the expansion difference prediction value sequence, an early warning step is performed, and the expansion difference prediction value is compared with the expansion difference alarm threshold in real time. When the predicted value fails to reach the expansion difference alarm threshold, an early warning signal is automatically generated and issued to prompt the operator to adjust the currently implemented power regulation strategy.

[0014] Another objective of this invention is to provide a flexible operation capability assessment system based on turbine rotor expansion difference prediction.

[0015] To solve the above-mentioned technical problems, the present invention provides the following technical solution: a flexible operation capability assessment system based on turbine rotor expansion difference prediction, comprising: expansion difference prediction module, correction module, capability assessment module, and quantification module; The expansion difference prediction module constructs a real-time prediction model for turbine expansion difference based on collected multi-dimensional operating data, configures inertial elements and performs weighting to form the expansion difference prediction value; The correction module sets a future target power value to determine the power change trend, and performs expansion difference prediction on the parameters corresponding to the power change trend, and calculates the expansion difference prediction value sequence under the current target power. The capability assessment module compares the predicted expansion difference value sequence corresponding to each target power with a preset threshold to determine whether the target power is allowed to be safely adjusted under the current state. The quantification module, in response to being deemed permissible for safe adjustments, statistically analyzes and calculates quantitative indicators characterizing the unit's current flexible operating capability.

[0016] The present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, characterized in that the processor executes the computer program to implement the steps of the method for evaluating the flexibility of operation based on the prediction of turbine rotor expansion difference.

[0017] The present invention 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 implements the steps of the method for evaluating the flexibility of operation based on the prediction of turbine rotor expansion difference.

[0018] The beneficial effects of the present invention are as follows: The prediction model established by the present invention, by collecting multi-dimensional operating data in real time, constructs an expansion difference prediction model based on inertial links, which can accurately predict the expansion difference change trend in the future period. The prediction model evaluates the expansion difference change under different future power, solves the problem that traditional methods cannot predict the risk of expansion difference exceeding the limit in advance, provides effective guidance for unit power regulation, and significantly improves the safety of peak-shaving operation of thermal power units.

[0019] Furthermore, the prediction model of this invention obtains the predicted value of the expansion difference under each target power and the preset expansion difference alarm threshold. Combined with the expansion difference alarm threshold and real-time stress state, it can quantify the flexible operation capability indicators such as the safe adjustment range and maximum adjustment rate of the unit, realize the scientific evaluation of the flexible operation capability, avoid the problem of blindly pursuing the peak shaving depth while ignoring safety constraints, and give full play to the flexible operation potential of the unit under the premise of ensuring safety.

[0020] Unlike traditional deep peak shaving control methods that rely solely on feedback regulation, this invention can dynamically update the evaluation results based on the unit's operating status. It should be noted that the model is based on a weighted combination of inertial elements, which can effectively simulate the dynamic lag characteristics of the influence of each input parameter on the expansion difference, adapt to the strong coupling and time-varying nature of the expansion difference, and has high prediction accuracy and strong adaptability. It is suitable for evaluating the flexible operation capability of different types of thermal power units, provides safety constraint support for deep peak shaving control, and alleviates the safety hazards of existing deep peak shaving control methods. Attached Figure Description

[0021] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 The following is an overall flowchart of a method for evaluating the flexibility of operation based on the prediction of turbine rotor expansion difference, provided as an embodiment of the present invention. Detailed Implementation

[0023] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present invention.

[0024] Example 1, referring to Figure 1 This is one embodiment of the present invention, which provides a method for evaluating the flexibility of operation based on the prediction of turbine rotor expansion difference, including: S100. Based on the collected multi-dimensional operating data, a real-time prediction model for turbine expansion difference is constructed, inertial elements are configured and weighted to form the predicted value of expansion difference; S200: Set a future target power value to determine the power change trend, and predict the expansion difference of the parameters corresponding to the power change trend, and calculate the expansion difference prediction value sequence under the current target power. S300. Compare the predicted value sequence of expansion difference corresponding to each target power with the preset alarm threshold to determine whether the target power is allowed to be safely adjusted in the current state. S400: In response to being determined to be allowed to make safe adjustments, statistically analyze and calculate quantitative indicators characterizing the unit's current flexible operating capability. It should be noted that existing technologies have shortcomings, such as relying on real-time monitoring of expansion differentials for passive regulation and difficulty in adapting to flexible operation requirements such as deep peak shaving of generating units.

[0025] Therefore, to address the aforementioned problems, the steps S100-S400 are applied to flexible peak-shaving and frequency-regulating operation scenarios of thermal power units. By collecting key operating parameters of thermal power units in real time, a differential expansion prediction model based on inertial links is constructed to predict the differential expansion after a period of time. The model is then compared with the actual differential expansion and alarm values ​​to evaluate the differential expansion under different future power levels and determine whether the power can be successfully increased or decreased to the target power. This invention can assess the feasibility of safe operation of the unit under different future power levels and quantify its flexible operation capability.

[0026] Example 2, refer to Figure 1 This is one embodiment of the present invention, which provides a method for evaluating the flexibility of operation based on the prediction of turbine rotor expansion difference, including: In this embodiment of the invention, S100 involves constructing a real-time prediction model for turbine expansion difference based on collected multi-dimensional operational data, configuring inertial elements and weighting them to form a predicted expansion difference value, including the following steps S101-S103: S101. Data is transmitted in real time at different measuring points through on-site sensors.

[0027] The collected operational data includes main steam temperature, main steam pressure, extraction steam temperature at each stage, cylinder temperature at each position, current unit power, real-time turbine differential pressure, shaft displacement, etc.

[0028] This not only ensures the real-time nature and continuity of the data, but also provides data support for subsequent model building and prediction.

[0029] Among them, the main steam temperature and pressure reflect the steam state entering the turbine, and their rate of change is a key factor affecting the rotor's temperature rise and expansion. The temperature of the extracted steam at each stage directly affects the heating state of the cylinder, which in turn affects the relative expansion difference between the rotor and the cylinder. The cylinder temperature at each position is used to characterize the cylinder's temperature distribution and thermal expansion state; the current power reflects the unit's load level, and its rate of change directly affects the dynamic change of the differential pressure. Real-time differential expansion and shaft displacement are direct feedback on changes in differential expansion.

[0030] S102. Based on the collected multi-dimensional operational data, a real-time prediction model for expansion difference based on the combination of inertial links is constructed. This model processes each input parameter through an independent inertial link to simulate the dynamic hysteresis characteristics of the influence of each parameter on expansion difference.

[0031] Three-dimensional unsteady-state thermal conduction control equations were established for the turbine rotor and cylinder respectively. Based on the preset axial and radial boundary conditions, the temperature distribution at the rotor position and the temperature distribution at the cylinder position at different times were calculated. Based on the temperature distribution, the thermal deformation field is simulated and solved to obtain the axial elongation of the rotor and the axial elongation of the cylinder, which are then input into the expansion difference prediction algorithm.

[0032] Specifically, in the operation of steam turbines in thermal power units, differential expansion is a core monitoring parameter during turbine start-up, shutdown, and variable load operation, directly affecting the safe and stable operation of the unit. Differential expansion refers to the difference in axial expansion between the turbine rotor and the cylinder. ,in, For the differential expansion of the steam turbine, This refers to the axial elongation of the rotor. This refers to the axial elongation of the cylinder block.

[0033] S1021. For the rotor position temperature distribution of the steam turbine, the radial coordinate is... , The rotor's radial length is [value]; the axial coordinate is [value]. , , This refers to the axial length of the rotor. Let t be the temperature at time t; The three-dimensional unsteady-state heat conduction control equations for the turbine rotor are as follows: in, The rotor thermal diffusivity, The thermal conductivity of the rotor material is... For density, Given the specific heat capacity; initial time is known. At that time, the temperature distribution inside the rotor is as follows: .

[0034] Boundary conditions are set including radial boundary conditions and axial boundary conditions, wherein the radial boundary condition is: When the rotor center At that time, under axisymmetric conditions, the radial heat flux density is 0: Rotor outer surface At that time, the rotor exchanges heat with the steam via convection: in, The heat transfer coefficient between the rotor and the steam convection is... Let be the steam temperature at axial position x and time t.

[0035] The axial boundary condition is assumed to be thermally adiabatic at both ends: S1022. Regarding the temperature distribution at the cylinder block location, the axial length of the cylinder block is... axial coordinates are radial coordinates of the cylinder block , This indicates the inner wall radius of the cylinder, which is the radial coordinate position of the inner surface of the cylinder (the side in contact with steam). This represents the outer radius of the cylinder block, i.e., the radial coordinate position of the outer surface of the cylinder block (the side in contact with the environment); the temperature is... The convective heat transfer between the inner wall and the steam, and the convective heat transfer between the outer wall and the environment, are represented by the three-dimensional unsteady-state heat conduction equation of the cylinder block as follows: in, The thermal diffusivity of the cylinder block is... The thermal conductivity of the cylinder block material. For density, Specific heat capacity.

[0036] Boundary conditions are set including radial boundary conditions and axial boundary conditions, wherein the radial boundary condition is: Cylinder body surface Heat exchange with steam via convection: in, The coefficient of heat transfer between the rotor and the steam convection is denoted as .

[0037] outer surface of cylinder Heat exchange with the environment via convection: in, The coefficient of heat transfer between the rotor and the steam convection is denoted as .

[0038] The axial boundary condition is that the cylinder shaft end exchanges heat with the environment: in, The ambient temperature.

[0039] The core function of calculating the axial length of the turbine rotor and cylinder is to solve the temperature distribution through the heat conduction equation, thereby deriving the dynamically changing axial elongation, and ultimately serving the calculation of the expansion difference.

[0040] It should be noted that the essence of the expansion difference is the difference in thermal expansion between the rotor and the cylinder, and this difference is determined by the rate of temperature change and the distribution pattern of the two. Therefore, it is essential to calculate the temperature distribution and change.

[0041] The calculation results directly support the two key parameters: the inertial time constant and the weighting coefficients. The following explanation is provided: For inertial time constant In other words, it characterizes the lag of input parameters on the expansion difference. The characteristics of the rotor and cylinder, such as their heat transfer rate and heat capacity, determine the lag time of the influence of parameters like main steam temperature and cylinder temperature on the expansion difference. For example, a large rotor heat capacity means a longer time for temperature changes to propagate throughout the system, corresponding to a longer inertial time constant. It is larger, providing a physical basis for its calibration.

[0042] For weighting coefficients In other words, it characterizes the contribution of a single input parameter to the variation of turbine differential expansion. The larger the value, the more significant the effect of the parameter on the expansion difference; The smaller the value, the weaker the effect of the parameter on the expansion difference. The value of this parameter needs to be determined by considering the physical characteristics of the steam turbine, historical operating data, and parameter sensitivity analysis. Parameters that directly affect differential expansion... It will be assigned a large value; parameters that have an indirect or weak effect on the expansion difference. It will be assigned a smaller value. These are the key coefficients after inertial processing. They are weighted to reflect the priority of different input parameters, ensuring that the model can accurately reflect the actual impact weight of each parameter on the expansion difference.

[0043] S103. Using the multi-dimensional operational data as input parameters, establish first-order inertial elements for dynamic processing. The first-order differential equation is described as follows: in, Sampling time, The real-time value of the i-th input parameter, such as main steam temperature, main steam pressure, power, ambient temperature, etc. The output value of the i-th input parameter after processing by the inertial circuit. Let be the inertial time constant corresponding to the i-th input parameter, representing the degree of lag; The weighting coefficient for the i-th input parameter represents the strength of the parameter's influence on the expansion difference.

[0044] Increase time constant Improving system stability, but reducing response speed; reducing the time constant This can speed up the response, but may introduce overshoot and oscillation; By combining a PID controller or other compensators, the dynamic performance and steady-state accuracy of inertial components can be further improved.

[0045] The inertial time constant of the input parameter is set in the first-order inertial element to simulate the time lag required for the current parameter change to be transmitted to the expansion difference; Simultaneously, corresponding weighting coefficients are assigned to the first-order inertial element, and all dynamically processed parameter output values ​​and weighting coefficients are linearly superimposed to form the expansion difference prediction value: Where n is the total number of input parameters involved in the inflation difference prediction, representing the number of all key operational parameters affecting the inflation difference when constructing the prediction model, i.e., the input dimension of the model. n determines the number of terms in the linear combination, meaning the prediction model needs to process each of the n input parameters through an inertial process, and then through their respective... After weighting and summing, the final predicted value of the inflation difference is obtained.

[0046] After obtaining the predicted expansion difference value sequence, an early warning step is performed, and the predicted expansion difference value is compared with the expansion difference alarm threshold in real time. When the predicted value fails to reach the alarm threshold, an early warning signal is automatically generated and issued to prompt operators to adjust the currently implemented power regulation strategy.

[0047] In this embodiment of the invention, step S200 sets a future target power value to determine the power change trend, predicts the expansion difference based on the parameters corresponding to the power change trend, and calculates the expansion difference prediction value sequence under the current target power, including the following steps S201-S203: S201 covers the possible power adjustment range of the unit, including the current power increase / decrease direction and different change amplitudes, and then sets multiple future target power values, determines the parameter change trend corresponding to the target power, and constructs the unit's design characteristic curve through the parameter change trend: Based on the difference between the target power and the current power, the magnitude and direction of the power change are determined, and the initial power change rate is set according to the magnitude and direction of the power change. Theoretical derivation and practical correction derivation are performed respectively.

[0048] The theoretical derivation is as follows: based on the difference between the target power and the current power, the magnitude and direction of the power change are determined, and based on the design characteristic curve of the unit, the theoretical optimal parameters under the current power change magnitude are obtained, that is, the peak value of the characteristic curve. Based on the design characteristic curve, the theoretical range of parameter variation is determined based on the theoretically optimal parameters, and the theoretical variation trajectory is obtained.

[0049] The actual correction derivation is based on filtering historical operating data that are similar to the current operating state and statistically analyzing patterns. Correlation analysis is used to quantify the correlation strength between parameters such as main steam temperature and pressure and power, and to identify key influencing parameters, including but not limited to main steam temperature, pressure, and extraction steam temperature. The fitting parameter is used to modify the theoretical trajectory of power variation, and the current power variation rate is combined with the modification to generate a parameter variation sequence. Ultimately, the parameter change trend of theoretical value plus actual correction value is formed, ensuring that the derivation results not only conform to the unit design principle, but also adapt to the actual operating characteristics, providing accurate input parameter change basis for the expansion difference prediction model.

[0050] S202. Substitute the parameter change sequence into the turbine expansion difference real-time prediction model, and calculate the expansion difference prediction curve for each target power in the future time period. S203 introduces real-time stress state feedback of the steam turbine during the prediction process. In response to the real-time stress being greater than or equal to the allowable stress threshold of the material, the rate of change of the expansion difference is reduced. The allowable stress threshold of the material is determined based on the material's factory inspection report and national standards, defining its basic strength indicators. A safety factor is introduced, and the allowable stress benchmark value is calculated to ensure equipment safety. The allowable stress needs to incorporate a safety factor based on the material's basic strength indicators, using the following formula: in, This is the allowable stress reference value. The limit is the ultimate strength index of the material, and S is the safety factor, which is determined by the unit design specifications and the level of operational risk. The safety factor of the steam turbine of the thermal power unit is usually 1.5 to 3.0, and the safety factor of key components such as the rotor is higher, mostly 2.0 to 3.0.

[0051] The actual allowable stress threshold needs to be corrected based on the real-time operating conditions of the steam turbine. The core correction factors include high temperature correction, fatigue correction, and aging correction. High-temperature correction is necessary because the material strength decreases as the temperature increases. The allowable stress needs to be adjusted according to the actual working temperature. The higher the temperature, the lower the allowable stress. When fatigue correction is performed to deep peak shaving, power fluctuates frequently and the material is subjected to alternating stress. The accumulation of fatigue damage needs to be considered, and the allowable stress threshold should be appropriately reduced to avoid the initiation of fatigue cracks. Aging correction is necessary because as the operating years of the unit increase, the strength of the material decreases due to oxidation and creep, and the allowable stress needs to be adjusted according to the degree of aging.

[0052] It should be noted that this invention integrates the key safety constraint parameter of expansion difference into the flexible operation capability assessment system, which solves the problem of traditional methods neglecting safety constraints. In addition, a real-time prediction model of expansion difference based on the combination of inertial links is constructed. By modeling and weighting the dynamic lag characteristics of each input parameter, accurate prediction of expansion difference is achieved, which significantly improves the prediction accuracy and adaptability of the model and solves the problem that traditional models are difficult to deal with the strong coupling and time-varying nature of expansion difference.

[0053] In an embodiment of the present invention, step S300 compares the predicted expansion difference value sequence corresponding to each target power with a preset alarm threshold to determine whether the target power is allowed to be safely adjusted in the current state, including the following steps S301-S302: S301. Compare the expansion difference prediction curve with the current preset alarm threshold. The preset alarm threshold includes an upper limit value and a lower limit value for expansion difference alarm. The alarm threshold is determined by statistical analysis of the historical maximum and minimum values ​​of expansion difference and the critical value when the fault occurs during the long-term operation of the unit, combined with safe operation experience under similar operating conditions. If all predicted values ​​in the current expansion difference prediction curve are less than the lower limit of the expansion difference alarm, then it is determined that adjusting the current target power is feasible and safe adjustment is allowed. S302. If any predicted value in the current expansion difference prediction curve is greater than or equal to the expansion difference alarm upper limit, it is determined that under the current set power change trend, adjusting the current target power has the risk of exceeding the expansion difference limit, which is not feasible and safety adjustment is not allowed. The power change amplitude or rate needs to be adjusted and re-evaluated.

[0054] The adjustment of the power change amplitude or rate is explained as follows: Adjusting the power change rate is important because it directly affects the expansion difference fluctuation. The faster the rate, the greater the difference in thermal expansion between the rotor and the cylinder, and the easier it is for the expansion difference to exceed the limit. Therefore, the rate should be preferentially reduced or increased according to the type of expansion difference exceeding the limit: If the predicted positive expansion difference exceeds the limit, that is, the rotor expands too quickly, then reduce the load increase rate, extend the power rise time, give the cylinder sufficient time to heat up and expand, and reduce the expansion difference between the rotor and the cylinder. If the predicted negative expansion difference exceeds the limit, i.e. the cylinder body contracts rapidly, then reduce the load reduction rate to avoid the cylinder body from rapidly cooling and contracting due to a sudden decrease in steam flow, thus suppressing the increase in negative expansion difference.

[0055] If the expansion difference still exceeds the limit after reducing the rate, it indicates that the difference between the target power and the current power, i.e., the change range, is too large. It is necessary to reduce the change range and approach the target power in stages.

[0056] Furthermore, based on the above operations, this invention can combine real-time operating status and safety thresholds to dynamically quantify the unit's flexible operating capability indicators such as safe adjustment range and maximum adjustment rate, realizing the transformation from passive control to active prediction and providing a scientific basis for peak shaving operations.

[0057] In an embodiment of the present invention, in step S400, in response to being determined to allow safe adjustments, a quantitative indicator characterizing the current flexible operating capability of the unit is statistically calculated, including the following steps S401-S403: S401. Among all the target power adjustments deemed feasible, the closed interval formed by the lowest and highest power values ​​shall be used as the safe adjustment range at the current moment: ; in, This represents the output of unit i during time period t. , These represent the upper and lower limits of the output power of generator set i, respectively. During operation, the generator set output power must operate within the upper and lower limits.

[0058] S402. Within the safe adjustment range at the current moment, test the condition that the predicted value of the expansion difference does not exceed the limit under different power change rates, find the maximum allowable power change per unit time, and quantify it as the maximum safe adjustment rate at the current moment: ; Specifically, This represents the maximum output that unit i can increase or decrease in each time period, and the output difference between adjacent time periods cannot exceed [a certain value]. ; judge It is related to whether the generating unit is in deep peak shaving: If it is currently in the normal operating phase, i.e., output power Equal to or higher than Then the maximum value of the output force that can be added or subtracted is ; If we are currently in a deep peak shaving phase, i.e., power output Less than Then the maximum value of the output force that can be added or subtracted is .

[0059] S403. Based on the maximum safe adjustment rate and the safe adjustment range, calculate the time required for the turbine unit to adjust from the current power to the range boundary at the current maximum safe adjustment rate, and record it as the continuous adjustment duration.

[0060] Based on the above judgment results, the quantitative indicators of the unit's flexible operation capability include safe adjustment range, maximum safe adjustment rate, and continuous adjustment duration.

[0061] In addition, when the predicted expansion difference approaches the alarm threshold, the system automatically outputs a warning signal to prompt the operator to adjust the power regulation strategy.

[0062] It is foreseeable that this invention uses the turbine rotor expansion difference as a core safety constraint parameter. By constructing a predictive model based on inertial elements, it achieves accurate prediction of the expansion difference, solving the deficiency of existing technologies in lacking forward-looking safety assessment. This allows for the early avoidance of expansion difference exceeding limits caused by power regulation, significantly improving the unit's peak-shaving safety. The model adopts an inertial element combination structure, which can effectively simulate the dynamic hysteresis effect of various input parameters on the expansion difference, adapting to the complex characteristics of the expansion difference. It has high prediction accuracy, strong robustness, and is applicable to different operating conditions and different types of thermal power units, with a wide range of applications.

[0063] Compared to traditional passive control methods that rely solely on real-time monitoring, this invention can proactively predict the expansion difference changes under different power regulation schemes, quantify the safe regulation range and rate, provide scientific guidance for the flexible operation of the unit, fully tap the peak-shaving potential while ensuring safety, and improve the unit's flexible operation capability.

[0064] Example 3 is an embodiment of the present invention. The above is an illustrative scheme of a method for evaluating the flexibility of operation based on the prediction of turbine rotor expansion difference. It should be noted that the technical solution of a system for evaluating the flexibility of operation based on the prediction of turbine rotor expansion difference belongs to the same concept as the above-described method for evaluating the flexibility of operation based on the prediction of turbine rotor expansion difference. Details not described in detail in the technical solution of the system for evaluating the flexibility of operation based on the prediction of turbine rotor expansion difference in this embodiment can be found in the description of the above-described method for evaluating the flexibility of operation based on the prediction of turbine rotor expansion difference.

[0065] This embodiment provides a flexible operation capability assessment system based on turbine rotor expansion difference prediction, including: expansion difference prediction module, correction module, capability assessment module, and quantification module; The expansion difference prediction module constructs a real-time prediction model for turbine expansion difference based on collected multi-dimensional operating data, configures inertial elements and performs weighting to form the expansion difference prediction value; The correction module sets a future target power value to determine the power change trend, and performs expansion difference prediction on the parameters corresponding to the power change trend, and calculates the expansion difference prediction value sequence under the current target power. The capability assessment module compares the predicted expansion difference value sequence corresponding to each target power with a preset threshold to determine whether the target power is allowed to be safely adjusted under the current state. The quantification module, in response to being deemed permissible for safe adjustments, statistically analyzes and calculates quantitative indicators characterizing the unit's current flexible operating capability.

[0066] This embodiment also provides an electronic device applicable to a method for evaluating the flexibility of operation based on turbine rotor expansion difference prediction, comprising: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the method for evaluating the flexibility of operation based on turbine rotor expansion difference prediction as proposed in the above embodiment.

[0067] This embodiment also provides a storage medium storing a computer program that, when executed by a processor, implements a flexible operation capability assessment method based on turbine rotor differential expansion prediction as proposed in the above embodiment.

[0068] The storage medium proposed in this embodiment belongs to the same inventive concept as the method for evaluating the flexible operation capability based on the prediction of turbine rotor expansion difference proposed in the above embodiments. Technical details not described in detail in this embodiment can be found in the above embodiments, and this embodiment has the same beneficial effects as the above embodiments.

[0069] Based on the above description of the implementation methods, those skilled in the art can clearly understand that the present invention can be implemented using software and necessary general-purpose hardware, and of course, it can also be implemented using hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk, or optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods of the various embodiments of the present invention.

[0070] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for evaluating the flexible operation capability based on the prediction of turbine rotor expansion difference, characterized in that: include, Based on the collected multi-dimensional operational data, a real-time prediction model for turbine expansion difference is constructed, inertial elements are configured and weighted to form the predicted expansion difference value; Set a future target power value to determine the power change trend, and predict the expansion difference of the parameters corresponding to the power change trend. Calculate the expansion difference prediction value sequence under the current target power. The predicted value sequence of expansion difference corresponding to each target power is compared with the preset alarm threshold to determine whether the target power is allowed to be safely adjusted in the current state. In response to being deemed permissible for safe adjustments, quantitative indicators characterizing the unit's current flexible operating capability are statistically analyzed and calculated.

2. The method for evaluating the flexible operation capability based on turbine rotor expansion difference prediction as described in claim 1, characterized in that, The construction of the real-time prediction model for turbine expansion difference includes: Three-dimensional unsteady-state thermal conduction control equations were established for the turbine rotor and cylinder respectively. Based on the preset axial and radial boundary conditions, the temperature distribution at the rotor position and the temperature distribution at the cylinder position at different times were calculated. Based on the temperature distribution, the thermal deformation field is simulated and solved to obtain the axial elongation of the rotor and the axial elongation of the cylinder, which are then input into the expansion difference prediction algorithm.

3. The method for evaluating the flexible operation capability based on turbine rotor expansion difference prediction as described in claim 2, characterized in that, The configuration and weighted combination of inertial elements for input parameters includes: The multi-dimensional operational data is used as input parameters to establish first-order inertial links for dynamic processing. The inertial time constant of the input parameter is set in the first-order inertial element to simulate the time lag required for the current parameter change to be transmitted to the expansion difference; Simultaneously, corresponding weighting coefficients are assigned to the first-order inertial element, and all dynamically processed parameter output values ​​and weighting coefficients are linearly superimposed to form the expansion difference prediction value.

4. The method for evaluating the flexible operation capability based on turbine rotor differential expansion prediction as described in claim 3, characterized in that, The step of setting a future target power value to determine the power change trend includes: Based on the difference between the target power and the current power, the magnitude and direction of the power change are determined, and the initial power change rate is set according to the magnitude and direction of the power change. The parameter change trend is determined through the power change, and the design characteristic curve of the unit is constructed. Based on the unit's design characteristic curve, the theoretical optimal parameters under the current power change range are obtained, and the theoretical range of parameter changes is determined based on the theoretical optimal parameters to obtain the theoretical change trajectory. By combining the statistical patterns of the same operating conditions in historical operating data, the correlation strength between parameters and power is quantified through correlation analysis to determine key influencing parameters. In conjunction with the initial power change rate, the theoretical change trajectory is corrected to generate a parameter change sequence. Substitute the parameter change sequence into the turbine expansion difference real-time prediction model, and calculate the expansion difference prediction curve for the future time period under each target power. Meanwhile, real-time stress state feedback of the steam turbine is introduced during the prediction process. In response to the real-time stress being greater than or equal to the allowable stress threshold of the material, the rate of change of the expansion difference is reduced.

5. The method for evaluating the flexible operation capability based on the prediction of turbine rotor expansion difference as described in claim 4, characterized in that, The determination of whether the target power is permissible for safe adjustment under the current state includes: The expansion difference prediction curve is compared with the current unit's preset alarm threshold, wherein the alarm threshold includes an upper limit value for expansion difference alarm and a lower limit value for expansion difference alarm; If all predicted values ​​in the current expansion difference prediction curve are less than the lower limit of the expansion difference alarm, then it is determined that adjusting the current target power is feasible and safe adjustment is allowed. If any predicted value in the current expansion difference prediction curve is greater than or equal to the expansion difference alarm upper limit, it is determined that adjusting the current target power under the current set power change trend poses a risk of exceeding the expansion difference limit, which is not feasible and safe adjustment is not allowed.

6. The method for evaluating the flexible operation capability based on turbine rotor differential expansion prediction as described in claim 5, characterized in that, The quantitative indicators used to calculate the current flexible operating capability of the unit include: Among all the target power adjustments deemed feasible, the closed interval formed by the minimum power value and the maximum power value is taken as the safe adjustment range at the current moment. Within the safe adjustment range at the current moment, the conditions under which the predicted value of the expansion difference does not exceed the limit are tested under different power change rates. The maximum allowable power change per unit time is found and quantified as the maximum safe adjustment rate at the current moment. Based on the maximum safe adjustment rate and the safe adjustment range, the time required for the turbine unit to adjust from the current power to the boundary of the safe adjustment range at the current maximum safe adjustment rate is calculated and recorded as the continuous adjustment duration.

7. The method for evaluating the flexible operation capability based on turbine rotor differential expansion prediction as described in claim 6, characterized in that, After obtaining the predicted expansion difference value sequence, an early warning step is performed, and the predicted expansion difference value is compared with the expansion difference alarm threshold in real time. When the predicted value fails to reach the differential expansion alarm threshold, an early warning signal is automatically generated and issued to prompt the operator to adjust the currently implemented power regulation strategy.

8. A flexible operation capability assessment system based on turbine rotor expansion difference prediction, employing the flexible operation capability assessment method based on turbine rotor expansion difference prediction as described in any one of claims 1 to 7, characterized in that, include: Inflation difference prediction module, correction module, capacity assessment module, and quantification module; The expansion difference prediction module constructs a real-time prediction model for turbine expansion difference based on collected multi-dimensional operating data, configures inertial elements and performs weighting to form the expansion difference prediction value; The correction module sets a future target power value to determine the power change trend, and performs expansion difference prediction on the parameters corresponding to the power change trend, and calculates the expansion difference prediction value sequence under the current target power. The capability assessment module compares the predicted expansion difference value sequence corresponding to each target power with a preset threshold to determine whether the target power is allowed to be safely adjusted under the current state. The quantification module, in response to being deemed permissible for safe adjustments, statistically analyzes and calculates quantitative indicators characterizing the unit's current flexible operating capability.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the flexible operation capability assessment method based on turbine rotor expansion difference prediction as described in any one of claims 1 to 7.

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 implements the steps of the flexible operation capability assessment method based on turbine rotor expansion difference prediction as described in any one of claims 1 to 7.

Images