Method and system for predicting fatigue crack initiation of runner

Abstract

The invention relates to a wheel fatigue crack initiation prediction method and system, and the method comprises the steps: achieving the dynamic calculation and accumulation of fatigue damage through the dynamic stress time series data under the integrated point group working condition, switching working condition and start-stop working condition of a stress concentration region, employing a linear accumulation damage theory, and combining the real-time collected operation parameters of a unit, and achieving the prediction of the fatigue crack initiation of a wheel. The problem that traditional static evaluation cannot reflect real-time working condition influences is solved. The contribution ratio of various working conditions to the total damage of the runner can be accurately calculated, so that a high-precision comprehensive fatigue damage value is obtained. According to fatigue crack initiation prediction based on the value, an early warning signal can be sent in advance, traditional passive first-aid repair is converted into active prevention and control, the service cycle of the runner is remarkably prolonged, and the operation and maintenance cost is reduced.

Description

Technical Field

[0001] This application relates to the field of hydropower generation, and in particular to a method, system, computer equipment, and computer-readable storage medium for predicting the initiation of fatigue cracks in a turbine runner. Background Technology

[0002] During its service life, the turbine runner not only bears enormous static loads but also faces complex hydraulic vibrations and centrifugal force fluctuations. With increasing grid demands for peak and frequency regulation, the operating conditions of the turbine unit are becoming increasingly complex. Frequent load adjustments and start-up / shutdown operations exacerbate the accumulation of fatigue damage in the runner. The initiation of fatigue cracks is an early stage of runner failure; once fatigue cracks initiate and propagate, they seriously threaten the safe operation of the power plant.

[0003] In related technologies, fatigue life assessment of turbine runners often employs theoretical calculations based on design conditions or passive maintenance based on periodic offline flaw detection. Theoretical calculations typically assume the runner operates under ideal stable conditions, using simplified stress amplitudes and Miner's rule for estimation. This fails to reflect the diversity of "point group conditions" and the nonlinear damage accumulation caused by the impact of "transient processes" in actual operation. Offline flaw detection, on the other hand, exhibits significant lag, often only detecting cracks after they have formed or even expanded to a certain extent, thus missing the optimal opportunity for preventative maintenance. Summary of the Invention

[0004] This application provides a method, apparatus, system, computer equipment, and computer-readable storage medium for predicting the initiation of fatigue cracks in a turbine, in order to at least solve the problem of insufficient accuracy in predicting fatigue cracks in turbines in related technologies.

[0005] In a first aspect, embodiments of this application provide a method for predicting the initiation of fatigue cracks in a rotary drum, the method comprising: Under various typical operating conditions, dynamic stress time series data of the turbine runner at a preset target position are obtained. The various typical operating conditions include point group operating conditions, switching operating conditions and start-up and shutdown operating conditions. The preset target position includes stress concentration area and stress maximum point position. Based on the dynamic stress time series data and the stress amplitude-cycle number curve of the impeller, fatigue damage values ​​under various typical working conditions are calculated using the linear cumulative damage theory. Based on the contribution ratio of the point group working conditions, the switching working conditions, and the start-stop working conditions to the total damage of the runner, the fatigue damage values ​​under various typical working conditions are weighted and integrated to obtain the comprehensive fatigue damage value of the runner. Fatigue crack initiation is predicted based on the comprehensive fatigue damage value.

[0006] In some embodiments, under point group operation conditions, acquiring the dynamic stress time series data of the impeller at a preset target position includes: The flow field simulation data of the impeller under point group operation condition is mapped to the impeller structure model, and the impeller stiffness is calculated by the one-way fluid-structure coupling method to determine the target position of the impeller. The target position includes: stress concentration area and the position of maximum stress point. Based on the steady flow field simulation data of the turbine unit under point group operating conditions, pressure pulsation calculation is performed on the turbine unit, and during the pressure pulsation calculation, dynamic water pressure detection data corresponding to the target position is obtained, and pressure load curves under the operating conditions of each point group of water are generated according to the dynamic water pressure detection data. The hydrodynamic pressure load curves under the operating conditions of each point group are input into the impeller structure model for transient dynamic calculation to obtain the dynamic stress time series data of the target location.

[0007] In some embodiments, acquiring dynamic stress timing data of the impeller at the location of concentrated stress region and maximum stress point during switching and start-stop operations includes: By combining the time constraints of operating condition transitions and the standard time procedures for unit start-up and shutdown, a dynamic load time series is constructed. The dynamic load time series, the transient hydraulic loads under the switching and start-up / shutdown conditions, and the structural inertial loads generated by the speed change are used to establish a dynamic stress calculation model for the runner during the transition process. The transient dynamic structure algorithm is used to calculate the dynamic stress of the impeller in the transition process, and the dynamic stress time series data of the preset target position under switching and start-stop conditions are obtained.

[0008] In some embodiments, based on the dynamic stress time series data and the stress amplitude-cycle count curve of the impeller, fatigue damage values ​​under various typical working conditions are calculated using linear cumulative damage theory, including: The dynamic stress time series data is processed to determine multiple stress cycles corresponding to various typical working conditions, and the stress amplitude of each stress cycle is statistically analyzed, as well as the number of cycles under the stress amplitude is determined. Based on the stress amplitude-cycle number curve of the rotor, the fatigue limit cycle number corresponding to each stress amplitude is obtained; Based on the number of cycles and the corresponding fatigue limit cycle number, the damage contribution value of each stress cycle is calculated; The damage contribution values ​​of effective stress cycles under each typical working condition are summed to obtain the fatigue damage value under each typical working condition.

[0009] In some embodiments, for the point group working condition, the damage contribution values ​​of each effective stress cycle are summed to obtain the fatigue damage values ​​under each typical working condition, including: Based on the unit operating parameters of the turbine generator, update the cumulative running time of each point group operating condition interval, and calculate the running time ratio of each point group operating condition interval in real time. The fatigue damage value under the operating conditions of each point group is obtained by weighting the damage contribution value corresponding to each point group's operating condition interval using the proportion of operating time in each point group as a weighting factor.

[0010] In some embodiments, the cumulative runtime of each point group operating condition interval is updated based on the real-time unit operating parameters of the turbine units, including: The turbine unit's operating parameters are collected at a preset time frequency, including: head parameters, output parameters, and guide vane opening parameters. Based on a pre-constructed head-output-time coupled turbine operating condition model, the point group operating condition interval corresponding to the unit operating parameters is determined, and the corresponding interval duration counter is triggered to update the cumulative running time of the point group operating condition interval, wherein: The turbine unit operating condition model includes: dividing the normal operating head range and the abnormal operating head range according to the distribution characteristics of the historical operating data of the turbine unit, and further refining the normal operating head range into segments; Based on the division of the head interval, the output interval of the turbine unit is divided simultaneously; Based on the division results of the head interval, the division results of the output interval, and the running time corresponding to each division result, the operating condition model of the turbine unit is constructed.

[0011] In some embodiments, for the switching condition and the start-stop condition, the damage contribution values ​​of the effective stress cycles are accumulated to obtain the fatigue damage values ​​under each typical condition, including: The frequency of switching events and start / stop events within the calculation time of the statistical unit; The fatigue damage value per unit time for the switching condition and the start-stop condition is obtained by multiplying the occurrence frequency of the switching condition and the start-stop condition by the damage contribution value of the corresponding single event.

[0012] In some embodiments, predicting fatigue crack initiation based on the comprehensive fatigue damage value includes: Based on Miner's linear cumulative damage theory, the remaining fatigue life of the rotor under the current operating strategy is calculated using the comprehensive fatigue damage value and the historical cumulative damage of the rotor. The remaining fatigue life is compared with the preset fatigue crack initiation early warning threshold to determine whether a fatigue crack initiation early warning signal should be generated. If so, the predicted fatigue crack initiation time point and the damage contribution ratio of each typical working condition are displayed through a visualization platform.

[0013] Secondly, embodiments of this application provide a fatigue crack initiation prediction system for a rotary drum, the system comprising: an acquisition module, a damage calculation module, and a prediction module, wherein: The acquisition module is used to acquire dynamic stress time series data of the turbine runner at a preset target position under multiple typical operating conditions. The multiple typical operating conditions include point group operating conditions, switching operating conditions and start-up and shutdown operating conditions. The preset target position includes stress concentration area and stress maximum point position. The damage calculation module is used to calculate fatigue damage values ​​under various typical working conditions based on the dynamic stress time series data and the stress amplitude-cycle number curve of the impeller, using the linear cumulative damage theory. The prediction module is used to weight and integrate the fatigue damage values ​​under various typical working conditions according to the contribution ratio of the point group working conditions, the switching working conditions and the start-stop working conditions to the total damage of the rotor, to obtain the comprehensive fatigue damage value of the rotor, and to predict the initiation of fatigue cracks based on the comprehensive fatigue damage value.

[0014] Thirdly, embodiments of this application provide a computer device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method described in the first aspect above.

[0015] Fourthly, embodiments of this application provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in the first aspect above.

[0016] Compared to related technologies, the fatigue crack initiation prediction method and system for turbine runners provided in this application integrates dynamic stress time-series data based on stress concentration area point group conditions, switching conditions, and start-up / shutdown conditions. It utilizes linear cumulative damage theory combined with real-time acquired unit operating parameters to achieve dynamic calculation and accumulation of fatigue damage, solving the problems of high cost and poor accuracy associated with traditional static assessments. It can accurately calculate the contribution ratio of various operating conditions to the total damage of the turbine runner, thereby obtaining a high-precision comprehensive fatigue damage value. Based on this value, fatigue crack initiation prediction can issue early warning signals, transforming traditional passive repairs into proactive prevention, significantly extending the service life of the turbine runner and reducing operation and maintenance costs. Attached Figure Description

[0017] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings: Figure 1 This is a flowchart of a method for predicting the initiation of fatigue cracks in a rotary drum according to an embodiment of this application; Figure 2 This is a schematic diagram of the unit operating condition zoning system in the embodiments of this application; Figure 3 This is a structural block diagram of a wheel fatigue crack initiation prediction system according to this application; Figure 4 This is a schematic diagram of the internal structure of an electronic device according to an embodiment of this application. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of this application clearer, the application is described and illustrated below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application. All other embodiments obtained by those skilled in the art based on the embodiments provided in this application without inventive effort are within the scope of protection of this application.

[0019] Obviously, the accompanying drawings described below are merely some examples or embodiments of this application. Those skilled in the art can apply this application to other similar scenarios based on these drawings without any inventive effort. Furthermore, it is understood that although the efforts made in this development process may be complex and lengthy, for those skilled in the art related to the content disclosed in this application, any changes to design, manufacturing, or production based on the technical content disclosed in this application are merely conventional technical means and should not be construed as insufficient disclosure of the content of this application.

[0020] In this application, the reference to "embodiment" means that a specific feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment that is mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described in this application may be combined with other embodiments without conflict.

[0021] Unless otherwise defined, the technical or scientific terms used in this application shall have the ordinary meaning understood by one of ordinary skill in the art to which this application pertains. The terms “a,” “an,” “an,” “the,” and similar words used in this application do not indicate quantity limitation and may indicate singular or plural. The terms “comprising,” “including,” “having,” and any variations thereof used in this application are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or device that comprises a series of steps or modules (units) is not limited to the listed steps or units, but may also include steps or units not listed, or may include other steps or units inherent to these processes, methods, products, or devices. The terms “connected,” “linked,” “coupled,” and similar words used in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. “Multiple” used in this application refers to two or more. “And / or” describes the relationship between related objects, indicating that three relationships may exist; for example, “A and / or B” can represent: A alone, A and B simultaneously, and B alone. The character " / " generally indicates that the preceding and following objects are in an "or" relationship. The terms "first," "second," and "third" used in this application are merely to distinguish similar objects and do not represent a specific ordering of the objects.

[0022] Figure 1 This is a flowchart of the fatigue crack initiation prediction method for a turbine according to an embodiment of this application, as shown below. Figure 1 As shown, the method includes the following steps: S101, under various typical working conditions, acquire dynamic stress time series data of the runner at a preset target position. The various typical working conditions include point group working conditions, switching working conditions and start-stop working conditions. The preset target position includes stress concentration area and stress maximum point position.

[0023] To overcome the shortcomings of traditional methods that rely solely on design condition estimations, this step introduces full-channel fluid-structure interaction simulation technology to obtain high-fidelity data. Specifically, it includes the following sub-steps: S1, Dynamic Stress Calculation of Fluid-Structure Coupling under Point Group Operating Conditions: First, a head-output-time coupled model is constructed based on the historical operating data of the turbine unit, and representative point group operating conditions are extracted. For each point group operating condition, a steady flow field simulation of the entire flow channel is performed, and the runner stiffness is calculated through unidirectional fluid-structure coupling to accurately locate the stress concentration area (such as the connection between the blade outlet edge and the lower ring) and the location of the maximum stress point.

[0024] Specifically, based on the distribution characteristics of historical data (such as frequency histograms and probability density curves), the normal operating head range and the abnormal operating head range are first divided.

[0025] For regularly operating head ranges (e.g., areas with data concentration exceeding 80%), the data is further subdivided (e.g., every 2 meters of head is a sub-range); for non-operating ranges, the segmentation step size can be appropriately relaxed. Based on the head range division results, the unit output range is simultaneously divided (e.g., segmented with a step size of 10% of rated output). By distinguishing between regularly operating and non-operating ranges and performing differentiated subdivisions, this step ensures both extremely high resolution for high-frequency operating conditions and coverage for low-frequency operating conditions, achieving an optimal balance between computational accuracy and computational cost.

[0026] The historical data on the running time falling within each "head-output" two-dimensional grid is statistically analyzed, and a model containing three-dimensional information (head, output, and cumulative duration) is constructed. Based on this model, the operating conditions of the point group can be quickly obtained.

[0027] Next, for each point group operating condition extracted from S101, corresponding boundary conditions (inlet total pressure, outlet static pressure, impeller speed, etc.) were set, and steady flow field calculations were performed using CFD (Computational Fluid Dynamics) software. The pressure distribution, velocity vector, and streamline distribution within the flow field were obtained. Furthermore, a finite element model (FEM) of the impeller's solid structure was established. Through a fluid-structure interaction interface, the fluid surface pressure loads under each point group operating condition obtained from the CFD calculation were mapped onto the corresponding surface mesh of the impeller structure model. Notably, the unidirectional fluid-structure interaction technique was used to achieve a lossless mapping of fluid pressure loads from the fluid domain to the solid domain, significantly improving the boundary accuracy of structural stress calculations.

[0028] Finally, after mapping onto the corresponding surface mesh of the runner structure model, centrifugal force (determined by rotational speed) and gravity load under the corresponding point group operating conditions are applied to the runner structure model, and correct displacement constraints are set. Static solutions are performed using a structural mechanics solver to obtain the stress cloud map and displacement distribution map of the runner. The region with the largest stress gradient change is identified as the "stress concentration region"; simultaneously, the node with the highest equivalent stress value is marked as the "maximum stress point location". In this embodiment, these two types of locations are collectively referred to as "target locations".

[0029] Furthermore, using a steady flow field as the initial value, an unsteady calculation is performed using a transient turbulence model (such as SSTk-ω). A virtual monitoring probe is set at a preset target location to record the pressure fluctuation sequence over time, generating a hydrodynamic pressure-load curve containing time-domain pulsation characteristics.

[0030] Finally, the hydrodynamic pressure load curve is applied as a boundary condition to the impeller structure model, and the centrifugal force and gravity at the corresponding rotational speed are superimposed. The dynamic stress time series data of the preset target position under the working conditions of each stable point group are calculated by a transient dynamic algorithm (such as the Newmark-β method).

[0031] Specifically, using the results of steady-state calculations as the initial flow field, a transient turbulence model adapted to large-scale separated flows (such as the SSTk-ω or DES model) is employed, and an appropriate time step is set to perform unsteady flow field calculations. By embedding a virtual probe into the numerical model and performing transient turbulence calculations, this step can capture millisecond-level unsteady flow details in the flow field, successfully simulating the complex flow regime inside the impeller that is difficult for actual sensors to access, and obtaining high-time-resolution raw data.

[0032] During the calculation process, the pressure fluctuation data sequence at the virtual monitoring probe is recorded in real time over time. The calculation is performed for a sufficient time period (e.g., 5-10 rotations of the impeller). Time-domain analysis is performed on the recorded data sequence to remove data from the initial stage of numerical oscillation, generating hydrodynamic pressure-load curves containing time-domain pulsation characteristics for each point group's operating conditions.

[0033] S2, Construction and Calculation of Dynamic Load Sequence for Transient Processes: For switching conditions (such as load adjustment and interval transitions caused by head fluctuations) and start-up / shutdown conditions, a dynamic load time sequence describing the changes in guide vane opening, rotational speed, and flow rate over time is constructed, based on the actual time schedule of the unit's guide vane opening / closing. This sequence and transient hydraulic loads are applied to the model to calculate the dynamic stress time series data at the preset target location under drastic changes in rotational speed and water hammer effect.

[0034] This step involves constructing a dynamic load sequence that matches the operating rhythm of the actual machine to capture the transient impact stresses experienced by the runner during start-up, shutdown, and switching. This effectively compensates for the blind spots in steady-state analysis and ensures comprehensive coverage of low-cycle large-amplitude fatigue damage.

[0035] In summary, step S101 utilizes advanced numerical simulation techniques to construct a full-condition dynamic stress database covering steady-state point groups and transient transition processes. By capturing the nonlinear characteristics of fluid pulsation and structural response, it obtains time-series data containing complete amplitude, frequency, and phase information, thereby solving the core technical challenges of inaccurate load input sources and excessive computational load in fatigue prediction. This lays a solid, high-precision data foundation for subsequent cumulative damage calculations.

[0036] S102, based on dynamic stress time series data and the stress amplitude-cycle number curve of the impeller, calculates the fatigue damage value under various typical working conditions using the linear cumulative damage theory.

[0037] Specifically, the dynamic stress time series data is processed to determine multiple stress cycles, and the number of stress amplitude cycles (e.g., σ) for each stress cycle is counted. a When '=30MPa, Nf=1×10 6 Next, σ a When '=60MPa, Nf=5×10 4 (times), according to formula Di =n i / Nf i Calculate the damage value (D) for a single stress cycle. i (For the damage contribution of the i-th cycle); further, according to the stress amplitude-cycle number curve of the impeller, the fatigue limit cycle number corresponding to each stress amplitude is obtained; and based on the cycle number and its corresponding fatigue limit cycle number, the damage contribution value of each stress cycle is calculated; the damage contribution values ​​of the effective stress cycles under each typical working condition are accumulated to obtain the fatigue damage value under each typical working condition.

[0038] S1, for point group working conditions, the damage contribution values ​​of each effective stress cycle are summed to obtain the fatigue damage values ​​under each typical working condition, including: Based on the unit operating parameters of the turbine, the cumulative running time of each point group operating condition interval is updated, and the running time ratio of each point group operating condition interval is calculated in real time. Using the running time ratio of each point group operating condition interval as a weighting factor, the damage contribution value corresponding to each point group operating condition interval is weighted and calculated to obtain the fatigue damage value under the point group operating condition.

[0039] It should also be noted that, for point group operating conditions, this implementation provides an online runtime statistics mechanism to update the cumulative runtime of each point group operating condition interval, specifically including: The turbine unit's operating parameters are collected at a preset time frequency. These operating parameters include: head parameters, output parameters, and guide vane opening parameters. Based on the pre-constructed turbine operating condition model that couples head, output, and time, the operating condition intervals of the point group corresponding to the unit operating parameters are determined, and the corresponding interval duration counter is triggered to update the cumulative running time of the operating condition interval of the point group. The turbine operating condition model includes: dividing the normal operating head interval and the abnormal operating head interval according to the distribution characteristics of the historical operating data of the turbine, and further refining the segmentation of the normal operating head interval.

[0040] S2, for switching and start-stop conditions, calculating fatigue damage values ​​includes: statistically analyzing the frequency of switching and start-stop events within a unit calculation time; multiplying the frequency of each switching and start-stop condition within a unit time by the damage contribution value of the corresponding single event to obtain the fatigue damage value per unit time for the switching and start-stop conditions.

[0041] Step S102 extracts effective cycles through rainflow counting and combines this with a modified SN curve for damage mapping, integrating microscopic material fatigue characteristics with macroscopic structural stress response. This not only calculates minute damage during stable operation but also keenly captures significant damage caused by transient impacts, thus solving the problem of difficulty in quantifying and assessing damage to turbines under complex alternating stress.

[0042] S103. Based on the contribution ratio of point group working conditions, switching working conditions and start-stop working conditions to the total damage of the runner, the fatigue damage values ​​under various typical working conditions are weighted and integrated to obtain the comprehensive fatigue damage value of the runner. The fatigue crack initiation is predicted based on the comprehensive fatigue damage value.

[0043] This step is the core of online real-time prediction, driving model updates through real-time operational data. Real-time statistics of unit group operating conditions: Real-time head H and output P of the units are collected at a rate of seconds via the power plant's SCADA interface. Based on a pre-constructed "unit operating condition interval system," it is determined which unit group interval the current state falls into.

[0044] Figure 2 This is a schematic diagram of the unit operating condition zoning system in an embodiment of this application. For example... Figure 2 As shown, the table divides head and output into several grid intervals. Using this graph as a real-time criterion, when a real-time parameter falls into a certain grid, the corresponding counter is triggered to accumulate the running time. This graph is the logical foundation for achieving "automatic operating condition identification" and "accurate duration statistics." Based on the statistical results, the running time percentage of each group of operating conditions is calculated. By matching the operating condition partition table in real time and accumulating the count, this step achieves a digital reconstruction of the unit's operating history, accurately capturing the dwell time of each operating condition and solving the problem that traditional assessments cannot reflect the actual operating distribution characteristics of the unit.

[0045] Transient operating condition frequency statistics and damage rate calculation: The frequency of switching events and start-up / shutdown events is statistically analyzed within a unit calculation time. Combined with the single-event damage value calculated in S102, the average damage rate of the transient process is calculated. This step transforms discrete transient operations into an average damage contribution per unit time, enabling quantitative assessment of non-steady-state processes such as start-up / shutdown and load adjustments, thus overcoming the technical shortcoming of focusing only on steady-state operation while neglecting operational losses.

[0046] Finally, this embodiment introduces the concept of contribution ratio, and integrates the damage values ​​of the three types of working conditions (point group, switching, start and stop) with weight to obtain the comprehensive damage rate; and further predicts the remaining fatigue life based on Miner's theory (failure when total damage D=1) and the historical cumulative damage of the impeller. The calculation results are compared with preset thresholds. If an early warning is triggered, the predicted fatigue crack initiation time and the damage contribution ratio of each operating condition are displayed on a visualization platform. By weighted integration of the damage contributions of the three types of operating conditions, this step constructs a comprehensive damage model that reflects the stress characteristics of the unit throughout its entire life cycle. This model can not only calculate the remaining life in real time, but also quantify the damage-causing weights of various operating conditions, achieving a leap from passive estimation to proactive prediction.

[0047] This step involves collecting real-time unit operating data and dynamically updating the weighting coefficients of various operating conditions to synthesize a comprehensive fatigue damage value that closely matches the current operating strategy. This enables accurate prediction of fatigue crack initiation time and, through damage contribution ratio analysis, provides power plant operation and maintenance personnel with data support for optimizing operating strategies (such as reducing time spent in high-damage conditions), significantly improving the intelligent operation and maintenance level and equipment safety of hydropower stations.

[0048] Through the steps described above, compared to related technologies, this application integrates dynamic stress data under point group, switching transition, and start-up / shutdown conditions, combined with real-time unit operating parameters and linear cumulative damage theory, to achieve dynamic calculation of fatigue damage. It accurately calculates the damage contribution under each operating condition, obtaining high-precision comprehensive fatigue damage values ​​while ensuring low computational overhead. This method enables early warning, shifting from reactive emergency repairs to proactive prevention, extending the turbine runner's service life, and reducing operation and maintenance costs.

[0049] Secondly, embodiments of this application also provide a fatigue crack initiation prediction system for a rotary wheel. Figure 3 This is a structural block diagram of a fatigue crack initiation prediction system for a rotary wheel according to this application, as shown below. Figure 3 As shown, the system includes: an acquisition module 30, a damage calculation module 31, and a prediction module 32, wherein: The acquisition module 30 is used to acquire dynamic stress time series data of the impeller at a preset target position under various typical working conditions. The various typical working conditions include point group working conditions, switching working conditions and start-stop working conditions. The preset target position includes stress concentration area and stress maximum point position. The damage calculation module 31 is used to calculate the fatigue damage value under various typical working conditions based on dynamic stress time series data and the stress amplitude-cycle number curve of the wheel, using the linear cumulative damage theory. The prediction module 32 is used to weight and integrate the fatigue damage values ​​under various typical working conditions according to the contribution ratio of point group working conditions, switching working conditions and start-stop working conditions to the total damage of the runner, to obtain the comprehensive fatigue damage value of the runner, and to predict the initiation of fatigue cracks based on the comprehensive fatigue damage value.

[0050] This system integrates dynamic stress data from point clusters, switching transitions, and start-up / shutdown conditions. Combined with real-time unit operating parameters and linear cumulative damage theory, it achieves dynamic calculation of fatigue damage, accurately calculating the damage contribution under each operating condition and obtaining a high-precision comprehensive fatigue damage value. This method enables early warning, shifting from "passive emergency repair" to "proactive prevention," extending the turbine runner's service life, and reducing maintenance costs.

[0051] In one embodiment, Figure 4 This is a schematic diagram of the internal structure of an electronic device according to an embodiment of this application, such as... Figure 4 As shown, an electronic device is provided, which can be a server, and its internal structure diagram can be as follows. Figure 4 As shown, the electronic device includes a processor, a network interface, internal memory, and non-volatile memory connected via an internal bus. The non-volatile memory stores an operating system, computer programs, and a database. The processor provides computing and control capabilities, the network interface communicates with external terminals via a network, the internal memory provides an environment for the operating system, the computer programs are executed by the processor to implement a wheel fatigue crack initiation prediction system, and the database stores data.

[0052] Those skilled in the art will understand that Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the electronic device to which the present application is applied. The specific electronic device may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements.

[0053] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. This computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0054] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0055] The above embodiments are merely illustrative of several implementation methods of this application, and their descriptions are relatively specific and detailed. However, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A method for predicting the initiation of fatigue cracks in a rotary wheel, characterized in that, The method includes: Under various typical operating conditions, dynamic stress time series data of the turbine runner at a preset target position are obtained. The various typical operating conditions include point group operating conditions, switching operating conditions and start-up and shutdown operating conditions. The preset target position includes stress concentration area and stress maximum point position. Based on the dynamic stress time series data and the stress amplitude-cycle number curve of the impeller, fatigue damage values ​​under various typical working conditions are calculated using the linear cumulative damage theory. Based on the contribution ratio of the point group working conditions, the switching working conditions, and the start-stop working conditions to the total damage of the runner, the fatigue damage values ​​under various typical working conditions are weighted and integrated to obtain the comprehensive fatigue damage value of the runner. Fatigue crack initiation is predicted based on the comprehensive fatigue damage value.

2. The method according to claim 1, characterized in that, Under point group working conditions, the dynamic stress time series data of the impeller at the preset target position is obtained as follows: The flow field simulation data of the impeller under point group operation condition is mapped to the impeller structure model, and the impeller stiffness is calculated by the one-way fluid-structure coupling method to determine the target position of the impeller. The target position includes: stress concentration area and the position of maximum stress point. Based on the steady flow field simulation data of the turbine unit under point group operating conditions, pressure pulsation calculation is performed on the turbine unit, and during the pressure pulsation calculation, dynamic water pressure detection data corresponding to the target position is obtained, and pressure load curves under the operating conditions of each point group of water are generated according to the dynamic water pressure detection data. The hydrodynamic pressure load curves under the operating conditions of each point group are input into the impeller structure model for transient dynamic calculation to obtain the dynamic stress time series data of the target location.

3. The method according to claim 2, characterized in that, Under switching and start-stop conditions, the dynamic stress time series data of the runner at the concentrated stress region and the location of the maximum stress point are obtained, including: By combining the time constraints of operating condition transitions and the standard time procedures for unit start-up and shutdown, a dynamic load time series is constructed. The dynamic load time series, the transient hydraulic loads under the switching and start-up / shutdown conditions, and the structural inertial loads generated by the speed change are used to establish a dynamic stress calculation model for the runner during the transition process. The transient dynamic structure algorithm is used to calculate the dynamic stress of the impeller in the transition process, and the dynamic stress time series data of the preset target position under switching and start-stop conditions are obtained.

4. The method according to claim 1, characterized in that, Based on the dynamic stress time series data and the stress amplitude-cycle count curve of the impeller, fatigue damage values ​​under various typical working conditions are calculated using the linear cumulative damage theory, including: The dynamic stress time series data is processed to determine multiple stress cycles corresponding to various typical working conditions, and the stress amplitude of each stress cycle is statistically analyzed, as well as the number of cycles under the stress amplitude is determined. Based on the stress amplitude-cycle number curve of the rotor, the fatigue limit cycle number corresponding to each stress amplitude is obtained; Based on the number of cycles and the corresponding fatigue limit cycle number, the damage contribution value of each stress cycle is calculated; The damage contribution values ​​of effective stress cycles under each typical working condition are summed to obtain the fatigue damage value under each typical working condition.

5. The method according to claim 4, characterized in that, For the aforementioned point group working conditions, the damage contribution values ​​of each effective stress cycle are summed to obtain the fatigue damage values ​​under each typical working condition, including: Based on the unit operating parameters of the turbine generator, update the cumulative running time of each point group operating condition interval, and calculate the running time ratio of each point group operating condition interval in real time. The fatigue damage value under the operating conditions of each point group is obtained by weighting the damage contribution value corresponding to each point group's operating condition interval using the proportion of operating time in each point group as a weighting factor.

6. The method according to claim 5, characterized in that, Based on the real-time operating parameters of the turbine units, update the cumulative runtime of each point group's operating condition range, including: The turbine unit's operating parameters are collected at a preset time frequency, including: head parameters, output parameters, and guide vane opening parameters. Based on a pre-constructed head-output-time coupled turbine operating condition model, the point group operating condition interval corresponding to the unit operating parameters is determined, and the corresponding interval duration counter is triggered to update the cumulative running time of the point group operating condition interval, wherein: The turbine unit operating condition model includes: dividing the normal operating head range and the abnormal operating head range according to the distribution characteristics of the historical operating data of the turbine unit, and further refining the normal operating head range into segments; Based on the division of the head interval, the output interval of the turbine unit is divided simultaneously; Based on the division results of the head interval, the division results of the output interval, and the running time corresponding to each division result, the operating condition model of the turbine unit is constructed.

7. The method according to claim 4, characterized in that, For the switching condition and the start-stop condition, the damage contribution values ​​of the effective stress cycles are accumulated to obtain the fatigue damage values ​​under each typical condition, including: The frequency of switching events and start / stop events within the calculation time of the statistical unit; The fatigue damage value per unit time for the switching condition and the start-stop condition is obtained by multiplying the occurrence frequency of the switching condition and the start-stop condition by the damage contribution value of the corresponding single event.

8. The method according to claim 1, characterized in that, The prediction of fatigue crack initiation based on the comprehensive fatigue damage value includes: Based on Miner's linear cumulative damage theory, the remaining fatigue life of the rotor under the current operating strategy is calculated using the comprehensive fatigue damage value and the historical cumulative damage of the rotor. The remaining fatigue life is compared with the preset fatigue crack initiation early warning threshold to determine whether a fatigue crack initiation early warning signal should be generated. If so, the predicted fatigue crack initiation time point and the damage contribution ratio of each typical working condition are displayed through a visualization platform.

9. A fatigue crack initiation prediction system for a rotary wheel, characterized in that, The system includes: an acquisition module, a damage calculation module, and a prediction module, wherein: The acquisition module is used to acquire dynamic stress time series data of the turbine runner at a preset target position under multiple typical operating conditions. The multiple typical operating conditions include point group operating conditions, switching operating conditions and start-up and shutdown operating conditions. The preset target position includes stress concentration area and stress maximum point position. The damage calculation module is used to calculate fatigue damage values ​​under various typical working conditions based on the dynamic stress time series data and the stress amplitude-cycle number curve of the impeller, using the linear cumulative damage theory. The prediction module is used to weight and integrate the fatigue damage values ​​under various typical working conditions according to the contribution ratio of the point group working conditions, the switching working conditions and the start-stop working conditions to the total damage of the rotor, to obtain the comprehensive fatigue damage value of the rotor, and to predict the initiation of fatigue cracks based on the comprehensive fatigue damage value.

10. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method as described in any one of claims 1 to 8.

Images