Method, device and equipment for predicting service life of high-pressure turbine blade of engine and medium
By performing simulation analysis and data optimization on high-pressure turbine blades, a damage coefficient matrix is generated. Combined with historical flight data, life prediction is performed, which solves the problem of high-pressure turbine blade condition detection and achieves accurate life prediction and improved safety.
Patent Information
- Application Number
- CN202510995373.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-07-18
- Publication Date
- 2025-11-14
AI Technical Summary
Existing technologies cannot effectively detect the root condition of high-pressure turbine blades in civil aircraft engines, resulting in an inability to accurately control their lifespan and increasing the risk of serious accidents such as in-flight engine failure due to sudden malfunctions.
By performing simulation analysis on the component to be predicted, an initial damage coefficient matrix is generated. Combined with historical flight data, data is supplemented and optimized to construct a QAR data matrix, calculate the cumulative fatigue damage value, and achieve life prediction.
Accurately predict fatigue damage to high-pressure turbine blades, provide early warnings when they are approaching their lifespan threshold, reduce the risk of in-flight engine shutdowns due to sudden failures, and improve the operational safety of aero engines.
Smart Images
Figure CN120951641A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of risk detection technology, and in particular to a method, device, equipment and medium for predicting the life of high-pressure turbine blades for engines. Background Technology
[0002] Civil aircraft engines consist of components such as a fan, low-pressure compressor, high-pressure compressor, combustion chamber, high-pressure turbine, and low-pressure turbine. After the gas mixes and burns with fuel in the combustion chamber, it first flows through the high-pressure turbine (HPTB), driving the high-pressure compressor at the front end. Then it enters the low-pressure turbine, driving the low-pressure compressor and fan. As the most critical core power component of the engine, the performance of the high-pressure turbine directly determines the engine's operating status. Once it is damaged, the high-pressure compressor will not work, the engine will completely lose power, and this can lead to serious accidents such as in-flight engine failure. Therefore, the condition monitoring of the high-pressure turbine blades is crucial.
[0003] Currently, the conventional inspection method for civil aviation engines is borescope inspection, which involves inserting an industrial endoscope into the engine and transmitting images via a camera, allowing professional engineers to assess the condition of the components. However, the critical part of the high-pressure turbine blade is the bottom connecting tenon, which cannot be directly observed through borescope. As a result, there is no effective technology to inspect the condition of the high-pressure turbine blade root when the engine is in the airfoil state, and it is also impossible to accurately control the lifespan of this component. Summary of the Invention
[0004] This invention provides a method for predicting the lifespan of high-pressure turbine blades in an engine. This method can provide early warnings of components approaching their lifespan threshold, reducing the risk of serious accidents such as in-flight engine shutdowns due to sudden malfunctions and improving the safety of civil aviation engine operation.
[0005] In a first aspect, embodiments of the present invention provide a method for predicting the lifespan of high-pressure turbine blades in an engine, comprising:
[0006] Simulation analysis was performed on the component to be predicted to obtain key parameters related to the damage; these key parameters included engine exhaust temperature and high-pressure turbine speed.
[0007] Based on the key parameters, an initial damage coefficient matrix is generated; the initial damage coefficient matrix is used to represent the damage coefficient values corresponding to different combinations of key parameter values.
[0008] Obtain the historical flight data of the component to be predicted, and supplement the historical flight data;
[0009] The maximum value of the key parameters for each flight is extracted from the supplemented historical flight data, and a QAR data matrix is constructed based on the maximum value.
[0010] The initial damage coefficient matrix is optimized based on the QAR data matrix;
[0011] Based on the optimized damage coefficient matrix, the cumulative fatigue damage value of the component to be predicted is calculated, and the life prediction is performed based on the cumulative fatigue damage value.
[0012] Furthermore, the component to be predicted undergoes simulation analysis to obtain key parameters related to damage, including:
[0013] Material simulation analysis and stress simulation analysis are performed on the component to be predicted to determine the key parameters that lead to fatigue damage, including engine exhaust temperature and high-pressure turbine speed.
[0014] Finite element analysis was performed on the component to be predicted to obtain the first fatigue life curve of the engine exhaust temperature and fatigue damage and the second fatigue life curve of the high-pressure turbine speed and fatigue damage.
[0015] Furthermore, generating the initial damage coefficient matrix based on the key parameters includes:
[0016] Construct an empty damage coefficient matrix; wherein the horizontal axis of the damage coefficient matrix represents the high-pressure turbine speed, the vertical axis represents the engine exhaust temperature, the matrix value represents the damage coefficient value, and the damage coefficient value represents the severity of the damage;
[0017] Obtain the exhaust temperature and high-pressure turbine speed of the engine that caused it to stop during the simulation analysis.
[0018] The exhaust temperature of the engine that stopped in mid-air and the high-pressure turbine speed that stopped in mid-air are used as reference values and filled into the damage coefficient matrix.
[0019] The damage coefficient matrix is expanded in both the horizontal and vertical directions to obtain the expanded initial damage coefficient matrix.
[0020] Furthermore, the process of supplementing the historical flight data includes:
[0021] For historical flight data missing throughout the year, the data is gradually supplemented according to pre-set priority rules;
[0022] The priority rule is as follows: for any flight with missing data, data is first filtered from the same month of adjacent years, and the departure and arrival stations must be the same. One data point is randomly selected from the filtering results as supplementary data.
[0023] If there is no data for the same departure and arrival locations in the same month of adjacent years, the scope is expanded to all data of the engine, and data with the same departure and arrival locations in the same month are filtered. If there are multiple records, they are sorted and the first one is selected as the supplementary data.
[0024] If the above data is not available, filter data with the same departure point from adjacent years of the missing data, and determine whether there are any data with similar flight routes. If so, use the data as supplementary data.
[0025] If no data meets the criteria, search for data with the same departure point but different arrival points in the second year of the missing data, and select that data as supplementary data.
[0026] If none of the above conditions are met, filter data from all data that are from the same month and the same departure point as supplementary data.
[0027] If none of the above conditions are met, then all flight data from the same day in the following year will be used, and the first data entry will be selected as the supplementary data after being shuffled.
[0028] Furthermore, the optimization of the initial damage coefficient matrix based on the QAR data matrix includes:
[0029] Using the initial damage coefficient matrix and the QAR data matrix as input, a binary classifier is used to calculate each corresponding point group of the initial damage coefficient matrix and the QAR data matrix;
[0030] The calculated value is compared with a preset threshold. When the calculated value is greater than the threshold, the value of that point in the initial damage coefficient matrix is discarded. When the calculated value is less than or equal to the threshold, the value of that point in the initial damage coefficient matrix is retained, thus obtaining the optimized damage coefficient matrix.
[0031] Furthermore, the step of calculating the cumulative fatigue damage of the component to be predicted based on the optimized damage coefficient matrix includes:
[0032] The Hadamard product of the optimized damage coefficient matrix and the QAR data matrix is calculated, and the result is used as the cumulative fatigue damage value of the component to be predicted.
[0033] Secondly, embodiments of the present invention provide an engine high-pressure turbine blade life prediction device, comprising:
[0034] The damage simulation analysis module is used to perform simulation analysis on the component to be predicted and to obtain key parameters related to the damage; the key parameters include engine exhaust temperature and high-pressure turbine speed.
[0035] The damage coefficient matrix construction module is used to generate an initial damage coefficient matrix based on the key parameters; the initial damage coefficient matrix is used to represent the damage coefficient values corresponding to different combinations of key parameter values.
[0036] The data preprocessing module is used to acquire the historical flight data of the component to be predicted and to supplement the historical flight data.
[0037] The QAR data matrix construction module is used to extract the maximum value of the key parameters for each flight from the supplemented historical flight data, and construct the QAR data matrix based on the maximum value.
[0038] The damage coefficient matrix optimization module is used to optimize the initial damage coefficient matrix based on the QAR data matrix.
[0039] The life prediction module is used to calculate the cumulative fatigue damage value of the component to be predicted based on the optimized damage coefficient matrix, and to predict the life based on the cumulative fatigue damage value.
[0040] Thirdly, embodiments of the present invention provide an electronic device, comprising:
[0041] Memory, used to store computer programs;
[0042] A processor for executing the computer program;
[0043] Wherein, when the processor executes the computer program, it implements the engine high-pressure turbine blade life prediction method described in any of the first aspects above.
[0044] Fourthly, embodiments of the present invention provide a computer-readable storage medium storing a computer program that, when executed, implements the engine high-pressure turbine blade life prediction method described in any of the first aspects above.
[0045] Fifthly, embodiments of the present invention provide a computer program product, including computer instructions, which, when executed by a processor, implement the engine high-pressure turbine blade life prediction method described in any of the first aspects above.
[0046] Compared with existing technologies, the present invention provides a method for predicting the lifespan of high-pressure turbine blades in engines, which has the following advantages: Simulation analysis is performed on the component to be predicted to obtain key parameters related to damage; these key parameters include engine exhaust temperature and high-pressure turbine speed; an initial damage coefficient matrix is generated based on these key parameters; the initial damage coefficient matrix represents the damage coefficient values corresponding to different combinations of key parameter values; historical flight data of the component to be predicted is acquired and supplemented; the maximum value of the key parameters for each flight is extracted from the supplemented historical flight data, and a QAR data matrix is constructed based on the maximum value; the initial damage coefficient matrix is optimized based on the QAR data matrix; based on the optimized damage coefficient matrix, the cumulative fatigue damage value of the component to be predicted is calculated, and lifespan is predicted based on the cumulative fatigue damage value; the present invention can provide early warning of components approaching their lifespan threshold, reducing the risk of serious accidents such as in-flight engine shutdowns due to sudden failures and improving the safety of civil aviation engine operation. Attached Figure Description
[0047] To more clearly illustrate the technical features of the embodiments of the present invention, the drawings used in the embodiments of the present invention will be briefly introduced below. Obviously, the 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.
[0048] Figure 1 This is a flowchart illustrating an embodiment of a method for predicting the life of high-pressure turbine blades in an engine provided by the present invention.
[0049] Figure 2 This is a schematic diagram of an embodiment of an engine high-pressure turbine blade life prediction device provided by the present invention;
[0050] Figure 3 This is a schematic diagram of the structure of one embodiment of an electronic device provided by the present invention. Detailed Implementation
[0051] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0052] It should be noted that although functional modules are divided in the device schematic diagram and a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first," "second," etc., in the specification, claims, and the aforementioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.
[0053] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein is for the purpose of describing embodiments of the invention only and is not intended to limit the invention.
[0054] In a first aspect, embodiments of the present invention provide a method for predicting the lifespan of high-pressure turbine blades in an engine, see [link to previous document]. Figure 1 This is a flowchart illustrating an embodiment of a method for predicting the lifespan of high-pressure turbine blades in an engine, provided by the present invention.
[0055] like Figure 1 As shown, the method includes the following steps:
[0056] S1: Perform simulation analysis on the component to be predicted to obtain key parameters related to the damage; the key parameters include engine exhaust temperature and high-pressure turbine speed.
[0057] S2: Based on the key parameters, generate an initial damage coefficient matrix; the initial damage coefficient matrix is used to represent the damage coefficient values corresponding to different combinations of key parameter values;
[0058] S3: Obtain the historical flight data of the component to be predicted, and complete the historical flight data;
[0059] S4: Extract the maximum value of the key parameters for each flight from the supplemented historical flight data, and construct a QAR data matrix based on the maximum value;
[0060] S5: Optimize the initial damage coefficient matrix based on the QAR data matrix;
[0061] S6: Based on the optimized damage coefficient matrix, calculate the cumulative fatigue damage value of the component to be predicted, and predict its lifespan based on the cumulative fatigue damage value.
[0062] In practice, the first step is to perform simulation analysis on the component to be predicted. Through simulation analysis, the two key parameters driving fatigue damage are identified: engine exhaust temperature (EGT) and high-pressure turbine speed (N2). The values of the key parameters are then correlated with the damage coefficient to construct an initial damage coefficient matrix, achieving preliminary quantitative modeling of the damage. Historical flight data of the component to be predicted is obtained and supplemented to address the issue of missing historical data and ensure data integrity. The maximum values of the key parameters are then extracted to construct a QAR data matrix. The initial matrix is then optimized using the QAR data matrix, eliminating invalid areas and focusing on overload-related critical damage, making the matrix more closely reflect actual operating conditions. Based on the optimized damage coefficient matrix, the cumulative fatigue damage value of the component to be predicted is calculated. The cumulative fatigue damage value is directly related to the actual wear state of the component to be predicted and can serve as a core indicator for determining the lifespan threshold. Compared to traditional experience-based lifespan assessments, this method is more accurate and traceable.
[0063] In summary, this invention performs simulation analysis on the component to be predicted, and obtains key parameters related to damage. These key parameters include engine exhaust temperature and high-pressure turbine speed. Based on these key parameters, an initial damage coefficient matrix is generated, representing the damage coefficient values corresponding to different combinations of key parameter values. Historical flight data of the component to be predicted is acquired and supplemented. The maximum value of the key parameters for each flight is extracted from the supplemented historical flight data, and a QAR data matrix is constructed based on this maximum value. The initial damage coefficient matrix is optimized based on the QAR data matrix. Based on the optimized damage coefficient matrix, the cumulative fatigue damage value of the component to be predicted is calculated, and lifespan is predicted based on this cumulative fatigue damage value. This invention achieves a transformation from experience-driven data and mechanism-driven approaches to fatigue life prediction, ensuring both theoretical rigor and engineering practicality. Its accurate cumulative damage value and lifespan prediction results can provide early warnings of components approaching their lifespan threshold, reducing the risk of serious accidents such as in-flight engine shutdowns due to sudden malfunctions and improving the safety of civil aviation engine operation.
[0064] In one optional implementation, the simulation analysis of the component to be predicted, and the analysis to obtain key parameters related to damage, include:
[0065] Material simulation analysis and stress simulation analysis are performed on the component to be predicted to determine the key parameters that lead to fatigue damage, including engine exhaust temperature and high-pressure turbine speed.
[0066] Finite element analysis was performed on the component to be predicted to obtain the first fatigue life curve of the engine exhaust temperature and fatigue damage and the second fatigue life curve of the high-pressure turbine speed and fatigue damage.
[0067] Specifically, material simulation analysis of the component to be predicted can provide a deeper understanding of the performance characteristics of the materials used in the component. Through multi-field coupled simulation, it can be confirmed that during engine operation, when the temperature changes, the thermal expansion mismatch between the depleted layer and the matrix material leads to an aggravation of the temperature-stress hysteresis effect. This hysteresis effect causes the material to bear greater stress fluctuations during temperature cycling, thereby accelerating the generation of fatigue damage and reducing the fatigue life by 40% compared to the theoretical value. Using an anisotropic constitutive model can accurately describe the deformation and failure behavior of single-crystal materials under complex stress states. By simulating and reproducing the crack propagation path along the crystal plane through this model, it is possible to gain a deeper understanding of the crack propagation mechanism in the microstructure of the material.
[0068] Stress simulation analysis of the components to be predicted is performed. Based on the principles of engine aero-thermodynamics, a three-dimensional transient temperature field model is constructed to accurately simulate the temperature distribution and changes of the engine's high-pressure turbine under different operating conditions. Under typical flight envelopes, the engine's operating state is constantly changing, causing the high-pressure turbine to bear unsteady thermal loads. Simulation can reproduce these thermal loads and analyze their impact on component stress. The blade leading edge bears extreme temperature gradients because the airflow velocity and temperature change drastically at the blade leading edge. At the same time, centrifugal loads are generated by the rotation of the high-pressure turbine. The synergistic effect of temperature gradients and centrifugal loads causes the blade leading edge to bear a complex stress state, increasing the risk of fatigue damage. Through multi-physics coupling simulation, the interaction of multiple physical fields such as temperature field and stress field is comprehensively considered. This simulation can verify that there is significant stress concentration in the tenon R-angle region. Through engine aerodynamic characteristic analysis, it is known that the high-pressure turbine speed changes drastically during takeoff / reverse thrust phases. This change causes the components to bear large cyclic stresses, thereby inducing low-cycle fatigue.
[0069] Finite element analysis was performed on the component to be predicted. A precise finite element model was established for the HPTB tenon of the engine. This model needed to accurately reflect the geometry, material properties, and connection relationship with surrounding components at the tenon. For actual flights where the engine was shut down, corresponding finite element analysis scenarios were constructed based on the actual operating conditions of the engine, including loads and temperatures at different flight stages. In the analysis, engine exhaust temperature (EGT) and high-pressure turbine speed (N2) were applied to the model as key load parameters. EGT reflects the temperature of the high-pressure turbine during operation, and its changes will cause thermal stress at the tenon. The N2 speed determines the magnitude of the centrifugal force on the blades. At the same time, the influence of vibration values on material fatigue life was considered and incorporated into the load system. Using the fatigue analysis module in the finite element software, combined with the fatigue performance data of the material, the fatigue life of the model was calculated. By simulating stress-strain cycles under different combinations of EGT and N2, the first fatigue life curve of EGT and fatigue damage and the second fatigue life curve of N2 and fatigue damage were obtained.
[0070] The embodiments of the present invention determine the key parameters that lead to damage through material simulation analysis and stress simulation analysis, and obtain fatigue life curves by combining finite element analysis. This enables a comprehensive and in-depth understanding of the fatigue damage mechanism and life characteristics of engine components, providing strong support for the safe operation and reliability improvement of engines.
[0071] In one optional implementation, generating the initial damage coefficient matrix based on the key parameters includes:
[0072] Construct an empty damage coefficient matrix; wherein the horizontal axis of the damage coefficient matrix represents the high-pressure turbine speed, the vertical axis represents the engine exhaust temperature, the matrix value represents the damage coefficient value, and the damage coefficient value represents the severity of the damage;
[0073] Obtain the exhaust temperature and high-pressure turbine speed of the engine that caused it to stop during the simulation analysis.
[0074] The exhaust temperature of the engine that stopped in mid-air and the high-pressure turbine speed that stopped in mid-air are used as reference values and filled into the damage coefficient matrix.
[0075] The damage coefficient matrix is expanded in both the horizontal and vertical directions to obtain the expanded initial damage coefficient matrix.
[0076] Specifically, first, a blank two-dimensional matrix is created, with the horizontal axis representing the high-pressure turbine speed (N2) and the vertical axis representing the engine exhaust temperature (EGT). The values in the matrix are damage coefficients, used to quantify the severity of damage under the corresponding operating conditions. Three pairs of EGT and N2 values for an in-flight engine used for fatigue curve simulation are selected, and the corresponding coordinate points are found in the matrix. The damage coefficient values of these points are used as the baseline values and set to 1. For example, assuming N2 = 98 and EGT = 770℃ as the baseline point, its damage coefficient is filled with 1.
[0077] Furthermore, based on the numerical relationship of the N2-fatigue life curve, the damage coefficients corresponding to different N2 values under the same EGT are derived. If, under a certain EGT, the N2-fatigue life curve value corresponding to the baseline N2 (e.g., 98) is A (e.g., 0.87), and the curve value corresponding to the target N2 (e.g., 99) is B (e.g., 0.90), then the damage coefficient of the target point (N2 = 99, EGT = 770℃) = baseline value (1) × B / A (i.e., 1 × 0.90 / 0.87). And so on, completing the calculation for all N2 values under the same EGT. The corresponding damage coefficients are filled to achieve lateral expansion. Based on the three known reference points (different combinations of EGT and N2), the vertical axis (EGT direction) is filled using a linear distribution principle. The linear relationship in the EGT direction is fitted through the damage coefficients of the three reference points, and then the damage coefficients corresponding to different EGTs under any N2 are calculated to complete the vertical expansion. After lateral (N2 direction) and vertical (EGT direction) expansion, all calculation results are integrated to obtain an initial damage coefficient matrix covering the full range of EGT and N2.
[0078] The damage coefficient matrix of this invention integrates two independent but synergistic key parameters, engine exhaust temperature (EGT) and high-pressure turbine speed (N2), into a two-dimensional matrix. This avoids the limitations of single-parameter evaluation and can accurately reflect the degree of damage under the combined effect of temperature and speed. It achieves the accuracy, efficiency and practicality of damage quantification, and provides key technical support for fatigue life assessment of engine components.
[0079] In one optional implementation, the step of supplementing the historical flight data includes:
[0080] For historical flight data missing throughout the year, the data is gradually supplemented according to pre-set priority rules;
[0081] The priority rule is as follows: for any flight with missing data, data is first filtered from the same month of adjacent years, and the departure and arrival stations must be the same. One data point is randomly selected from the filtering results as supplementary data.
[0082] If there is no data for the same departure and arrival locations in the same month of adjacent years, the scope is expanded to all data of the engine, and data with the same departure and arrival locations in the same month are filtered. If there are multiple records, they are sorted and the first one is selected as the supplementary data.
[0083] If the above data is not available, filter data with the same departure point from adjacent years of the missing data, and determine whether there are any data with similar flight routes. If so, use the data as supplementary data.
[0084] If no data meets the criteria, search for data with the same departure point but different arrival points in the second year of the missing data, and select that data as supplementary data.
[0085] If none of the above conditions are met, filter data from all data that are from the same month and the same departure point as supplementary data.
[0086] If none of the above conditions are met, then all flight data from the same day in the following year will be used, and the first data entry will be selected as the supplementary data after being shuffled.
[0087] Specifically, the operational parameters involved in supplementing historical flight data include departure station, arrival station, flight time, and actual takeoff / arrival time. The flight time of an aircraft reflects the amount of fuel it carries. More fuel leads to a higher takeoff weight, which in turn affects the N2 speed and EGT temperature the most. When supplementing data, it is necessary to prioritize matching the route characteristics to ensure that the load-related parameters of the supplemented data are consistent with those of the missing flights, thereby reducing N2 / EGT deviations caused by load differences. In addition, engine performance deteriorates with increasing operating time. Under the same N2 conditions, EGT temperature will increase with increasing operating time. When supplementing data, it is necessary to select data from the two flights with the closest time intervals to minimize parameter deviations caused by changes in engine performance and ensure the timeliness and consistency of the supplemented data.
[0088] The supplementary rules achieve accurate matching of missing data through multi-dimensional condition priority ranking. The first condition, "same month in adjacent years," takes into account the impact of seasons on flight operations (such as different fuel loads and atmospheric temperatures in different seasons). The climate and operational characteristics of the same month are more similar, reducing interference from environmental factors. The second condition, "same departure / arrival station," directly locks in route characteristics, ensuring that core parameters such as load and range are consistent, avoiding N2 / EGT distortion due to route differences. Subsequently, by gradually relaxing the conditions while retaining key characteristics (same month, same route; same departure point, similar range; same departure point, different destination; same month, same departure point; same day of the following year), the most similar substitute data can still be found when data is missing, balancing the feasibility and accuracy of the supplement.
[0089] It should be noted that the data supplementation method of this invention has been verified to meet the accuracy requirements of fatigue life assessment. The verification method can simulate a data-deficient environment, such as deleting a whole year's data from existing data and using the remaining year's data and that year's data as the data source, or not using the deleted data as the data source, and then using the above-mentioned data supplementation method to supplement the data. The deviation between the fatigue cumulative life calculated by the supplemented data and the actual fatigue cumulative life can be analyzed. If the deviation is within an acceptable range, it can be proven that the method can meet the accuracy requirements of fatigue life assessment in engineering practice, providing empirical support for the reliability of data supplementation.
[0090] In one optional implementation, optimizing the initial damage coefficient matrix based on the QAR data matrix includes:
[0091] Using the initial damage coefficient matrix and the QAR data matrix as input, a binary classifier is used to calculate each corresponding point group of the initial damage coefficient matrix and the QAR data matrix;
[0092] The calculated value is compared with a preset threshold. When the calculated value is greater than the threshold, the value of that point in the initial damage coefficient matrix is discarded. When the calculated value is less than or equal to the threshold, the value of that point in the initial damage coefficient matrix is retained, thus obtaining the optimized damage coefficient matrix.
[0093] Specifically, the original damage matrix is generated based on simulation data, but the failure of an actual engine is the result of fatigue sources caused by overload. Not all EGT and N2 combinations will cause damage. Only the overload region beyond a certain failure boundary is the key cause of cracks. Using the initial damage coefficient matrix and QAR data matrix as input, a binary classifier is used to learn and find a decision boundary. Regions are divided in the matrix. Points above the boundary are determined to be normal working regions. The damage coefficients of these points have no significant impact on cracks and are directly discarded and not included in subsequent damage calculations. Points below the boundary are determined to be overload damage regions. These points are the key to causing cracks and their damage coefficients are retained for subsequent cumulative calculations, finally obtaining the optimized damage coefficient matrix.
[0094] This invention optimizes the initial damage coefficient matrix by dividing the normal working area and the overload damage area from a mechanistic perspective. Only the damage data of the overload area is retained, while irrelevant normal data is removed, making the damage assessment more accurate and more in line with the actual failure causes.
[0095] In one optional implementation, calculating the cumulative fatigue damage of the component to be predicted based on the optimized damage coefficient matrix includes:
[0096] The Hadamard product of the optimized damage coefficient matrix and the QAR data matrix is calculated, and the result is used as the cumulative fatigue damage value of the component to be predicted.
[0097] Specifically, in the optimized damage coefficient matrix, each element represents the unit damage amount under a specific EGTN2 combination. In the QAR data matrix, the element at the corresponding position represents the actual running time or frequency of the engine experiencing the EGT-N2 combination during a certain flight, i.e., the actual occurrence of the operating condition. The Hadamard product of the two is calculated, and the result can be directly correlated to the cumulative fatigue damage value of a single engine. It can reflect the total damage of the engine throughout its entire life cycle and trace the specific contribution of different flights and operating conditions to the damage, providing accurate data for the life assessment and maintenance decision of the component to be predicted.
[0098] Secondly, embodiments of the present invention provide an engine high-pressure turbine blade life prediction device, see [link to relevant documentation]. Figure 2 This is a schematic diagram of an embodiment of an engine high-pressure turbine blade life prediction device provided by the present invention.
[0099] like Figure 2 As shown, the device includes:
[0100] Damage simulation analysis module 21 is used to perform simulation analysis on the component to be predicted and to obtain key parameters related to damage; the key parameters include engine exhaust temperature and high-pressure turbine speed.
[0101] The damage coefficient matrix construction module 22 is used to generate an initial damage coefficient matrix based on the key parameters; the initial damage coefficient matrix is used to represent the damage coefficient values corresponding to different combinations of key parameter values.
[0102] Data preprocessing module 23 is used to acquire historical flight data of the component to be predicted and to supplement the historical flight data;
[0103] QAR data matrix construction module 24 is used to extract the maximum value of the key parameters of each flight from the supplemented historical flight data, and construct a QAR data matrix based on the maximum value;
[0104] The damage coefficient matrix optimization module 25 is used to optimize the initial damage coefficient matrix based on the QAR data matrix;
[0105] The life prediction module 26 is used to calculate the cumulative fatigue damage value of the component to be predicted based on the optimized damage coefficient matrix, and to predict the life based on the cumulative fatigue damage value.
[0106] In an optional implementation, the damage simulation analysis module 21 is further configured to:
[0107] Material simulation analysis and stress simulation analysis are performed on the component to be predicted to determine the key parameters that lead to fatigue damage, including engine exhaust temperature and high-pressure turbine speed.
[0108] Finite element analysis was performed on the component to be predicted to obtain the first fatigue life curve of the engine exhaust temperature and fatigue damage and the second fatigue life curve of the high-pressure turbine speed and fatigue damage.
[0109] In an optional implementation, the damage coefficient matrix construction module 22 is further configured to:
[0110] Construct an empty damage coefficient matrix; wherein the horizontal axis of the damage coefficient matrix represents the high-pressure turbine speed, the vertical axis represents the engine exhaust temperature, the matrix value represents the damage coefficient value, and the damage coefficient value represents the severity of the damage;
[0111] Obtain the exhaust temperature and high-pressure turbine speed of the engine that caused it to stop during the simulation analysis.
[0112] The exhaust temperature of the engine that stopped in mid-air and the high-pressure turbine speed that stopped in mid-air are used as reference values and filled into the damage coefficient matrix.
[0113] The damage coefficient matrix is expanded in both the horizontal and vertical directions to obtain the expanded initial damage coefficient matrix.
[0114] In an optional implementation, the data preprocessing module 23 is further configured to:
[0115] For historical flight data missing throughout the year, the data is gradually supplemented according to pre-set priority rules;
[0116] The priority rule is as follows: for any flight with missing data, data is first filtered from the same month of adjacent years, and the departure and arrival stations must be the same. One data point is randomly selected from the filtering results as supplementary data.
[0117] If there is no data for the same departure and arrival locations in the same month of adjacent years, the scope is expanded to all data of the engine, and data with the same departure and arrival locations in the same month are filtered. If there are multiple records, they are sorted and the first one is selected as the supplementary data.
[0118] If the above data is not available, filter data with the same departure point from adjacent years of the missing data, and determine whether there are any data with similar flight routes. If so, use the data as supplementary data.
[0119] If no data meets the criteria, search for data with the same departure point but different arrival points in the second year of the missing data, and select that data as supplementary data.
[0120] If none of the above conditions are met, filter data from all data that are from the same month and the same departure point as supplementary data.
[0121] If none of the above conditions are met, then all flight data from the same day in the following year will be used, and the first data entry will be selected as the supplementary data after being shuffled.
[0122] In an optional implementation, the damage coefficient matrix optimization module 25 is further configured to:
[0123] Using the initial damage coefficient matrix and the QAR data matrix as input, a binary classifier is used to calculate each corresponding point group of the initial damage coefficient matrix and the QAR data matrix;
[0124] The calculated value is compared with a preset threshold. When the calculated value is greater than the threshold, the value of that point in the initial damage coefficient matrix is discarded. When the calculated value is less than or equal to the threshold, the value of that point in the initial damage coefficient matrix is retained, thus obtaining the optimized damage coefficient matrix.
[0125] In an optional implementation, the lifetime prediction module 26 is further configured to:
[0126] The Hadamard product of the optimized damage coefficient matrix and the QAR data matrix is calculated, and the result is used as the cumulative fatigue damage value of the component to be predicted.
[0127] Thirdly, embodiments of the present invention provide an electronic device, see [link to previous document]. Figure 3 The diagram shown is a structural schematic of an electronic device provided in an embodiment of the present invention.
[0128] like Figure 3 As shown, the device includes:
[0129] Memory 31 is used to store computer programs;
[0130] Processor 32 is used to execute the computer program;
[0131] When the processor 32 executes the computer program, it implements the engine high-pressure turbine blade life prediction method as described in any of the above embodiments.
[0132] For example, the computer program may be divided into one or more modules / units, which are stored in the memory 31 and executed by the processor 32 to complete the present invention. The one or more modules / units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in the electronic device.
[0133] The processor 32 can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.
[0134] The memory 31 can be used to store the computer programs and / or modules. The processor 32 implements various functions of the electronic device by running or executing the computer programs and / or modules stored in the memory 31 and calling the data stored in the memory 31. The memory 31 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the mobile phone (such as audio data, phonebook, etc.). In addition, the memory 31 may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital card (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.
[0135] It should be noted that the aforementioned electronic devices include, but are not limited to, processors and memory, as will be understood by those skilled in the art. Figure 3 The structural diagram is merely an example of the electronic device described above and does not constitute a limitation on the electronic device. It may include more components than shown in the diagram, or combine certain components, or use different components.
[0136] Fourthly, embodiments of the present invention also provide a computer-readable storage medium storing a computer program that, when executed, implements the engine high-pressure turbine blade life prediction method described in any of the above embodiments.
[0137] It should be understood that the present invention can implement all or part of the processes in the above-described method for predicting the life of high-pressure turbine blades of an engine, or it can be accomplished by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the above-described method for predicting the life of high-pressure turbine blades of an engine. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.
[0138] Fifthly, embodiments of this application also provide a computer program product, which is stored in a storage medium and executed by at least one processor to implement the engine high-pressure turbine blade life prediction method described in any of the above embodiments.
[0139] The above description is merely a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. It should be noted that, for those skilled in the art, several equivalent obvious modifications and / or equivalent substitutions can be made without departing from the technical principles of the present invention, and these obvious modifications and / or equivalent substitutions should also be considered within the scope of protection of the present invention.
Claims
1. A method for predicting the life of high-pressure turbine blades in an engine, characterized in that, include: Simulation analysis was performed on the component to be predicted to obtain key parameters related to the damage; these key parameters included engine exhaust temperature and high-pressure turbine speed. Based on the key parameters, an initial damage coefficient matrix is generated; the initial damage coefficient matrix is used to represent the damage coefficient values corresponding to different combinations of key parameter values. Obtain the historical flight data of the component to be predicted, and supplement the historical flight data; The maximum value of the key parameters for each flight is extracted from the supplemented historical flight data, and a QAR data matrix is constructed based on the maximum value. The initial damage coefficient matrix is optimized based on the QAR data matrix; Based on the optimized damage coefficient matrix, the cumulative fatigue damage value of the component to be predicted is calculated, and the life prediction is performed based on the cumulative fatigue damage value.
2. The method for predicting the life of high-pressure turbine blades in an engine as described in claim 1, characterized in that, The simulation analysis of the component to be predicted yields key parameters related to damage, including: Material simulation analysis and stress simulation analysis are performed on the component to be predicted to determine the key parameters that lead to fatigue damage, including engine exhaust temperature and high-pressure turbine speed. Finite element analysis was performed on the component to be predicted to obtain the first fatigue life curve of the engine exhaust temperature and fatigue damage and the second fatigue life curve of the high-pressure turbine speed and fatigue damage.
3. The method for predicting the life of high-pressure turbine blades in an engine as described in claim 1, characterized in that, The process of generating an initial damage coefficient matrix based on the key parameters includes: Construct an empty damage coefficient matrix; wherein the horizontal axis of the damage coefficient matrix represents the high-pressure turbine speed, the vertical axis represents the engine exhaust temperature, the matrix value represents the damage coefficient value, and the damage coefficient value represents the severity of the damage; Obtain the exhaust temperature and high-pressure turbine speed of the engine that caused it to stop during the simulation analysis. The exhaust temperature of the engine that stopped in mid-air and the high-pressure turbine speed that stopped in mid-air are used as reference values and filled into the damage coefficient matrix. The damage coefficient matrix is expanded in both the horizontal and vertical directions to obtain the expanded initial damage coefficient matrix.
4. The method for predicting the life of high-pressure turbine blades in an engine as described in claim 1, characterized in that, The process of supplementing the historical flight data includes: For historical flight data missing throughout the year, the data is gradually supplemented according to pre-set priority rules; The priority rule is as follows: for any flight with missing data, data is first filtered from the same month of adjacent years, and the departure and arrival stations must be the same. One data point is randomly selected from the filtering results as supplementary data. If there is no data for the same departure and arrival locations in the same month of adjacent years, the scope is expanded to all data of the engine, and data with the same departure and arrival locations in the same month are filtered. If there are multiple records, they are sorted and the first one is selected as the supplementary data. If the above data is not available, filter data with the same departure point from adjacent years of the missing data, and determine whether there are any data with similar flight routes. If so, use the data as supplementary data. If no data meets the criteria, search for data with the same departure point but different arrival points in the second year of the missing data, and select that data as supplementary data. If none of the above conditions are met, filter data from all data that are from the same month and the same departure point as supplementary data. If none of the above conditions are met, then all flight data from the same day in the following year will be used, and the first data entry will be selected as the supplementary data after being shuffled.
5. The method for predicting the life of high-pressure turbine blades in an engine as described in claim 1, characterized in that, The optimization of the initial damage coefficient matrix based on the QAR data matrix includes: Using the initial damage coefficient matrix and the QAR data matrix as input, a binary classifier is used to calculate each corresponding point group of the initial damage coefficient matrix and the QAR data matrix; The calculated value is compared with a preset threshold. When the calculated value is greater than the threshold, the value of that point in the initial damage coefficient matrix is discarded. When the calculated value is less than or equal to the threshold, the value of that point in the initial damage coefficient matrix is retained, thus obtaining the optimized damage coefficient matrix.
6. The method for predicting the life of high-pressure turbine blades in an engine as described in claim 1, characterized in that, The calculation of the cumulative fatigue damage value of the component to be predicted based on the optimized damage coefficient matrix includes: The Hadamard product of the optimized damage coefficient matrix and the QAR data matrix is calculated, and the result is used as the cumulative fatigue damage value of the component to be predicted.
7. A device for predicting the lifespan of high-pressure turbine blades for engines, characterized in that, include: The damage simulation analysis module is used to perform simulation analysis on the component to be predicted and to obtain key parameters related to the damage; the key parameters include engine exhaust temperature and high-pressure turbine speed. The damage coefficient matrix construction module is used to generate an initial damage coefficient matrix based on the key parameters; the initial damage coefficient matrix is used to represent the damage coefficient values corresponding to different combinations of key parameter values. The data preprocessing module is used to acquire the historical flight data of the component to be predicted and to supplement the historical flight data. The QAR data matrix construction module is used to extract the maximum value of the key parameters for each flight from the supplemented historical flight data, and construct the QAR data matrix based on the maximum value. The damage coefficient matrix optimization module is used to optimize the initial damage coefficient matrix based on the QAR data matrix. The life prediction module is used to calculate the cumulative fatigue damage value of the component to be predicted based on the optimized damage coefficient matrix, and to predict the life based on the cumulative fatigue damage value.
8. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor for executing the computer program; Wherein, when the processor executes the computer program, it implements the engine high-pressure turbine blade life prediction method as described in any one of claims 1 to 6.
9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed, implements the engine high-pressure turbine blade life prediction method as described in any one of claims 1 to 6.
10. A computer program product, characterized in that, It includes computer instructions that, when executed by a processor, implement the engine high-pressure turbine blade life prediction method as described in any one of claims 1 to 6.