Gas turbine blade platform optimization method based on rotor creep

Abstract

A gas turbine blade platform optimization method based on rotor creep belongs to the field of gas turbines, and comprises the following steps: step 1, acquiring data of a gas turbine of a corresponding model; 2, constructing a calculation model and a three-dimensional model; 3, training the calculation model obtained in the step 2; 4, combining the calculation model trained in the step 3 with the three-dimensional model to obtain change data; 5, the calculation model calculates the change rate to judge whether adjustment is needed or not; 6, if the change rate exceeds a specified threshold value, it is judged that the change rate needs to be adjusted; and 7, related maintenance personnel process the corresponding adjacent turbine blade platform according to a corresponding processing scheme given on the three-dimensional model. According to the method, the rotor creep data and the turbine blade platform gap change data are deeply coupled, and the collaborative analysis of the calculation model and the three-dimensional model is combined, so that the turbine blade platform gap change is accurately predicted and dynamically optimized.

Description

Technical Field

[0001] This invention belongs to the field of gas turbines, specifically a method for optimizing gas turbine blade platforms based on rotor creep. Background Technology

[0002] As the operating cycle of a gas turbine increases, stress changes or deformations occur in the hot channel components. Based on historical data analysis, the turbine rotor exhibits significant creep shortening at both ends due to its hollow shaft design. The blade root is the point of minimum clearance between the turbine blades. As the unit's operating time increases, the blade root clearance changes, leading to larger or smaller gaps between adjacent turbine blade platforms. This can cause gas leakage or blade friction during operation, severely affecting the gas turbine's operational safety and efficiency. Traditional methods for adjusting turbine blade platform clearance rely heavily on experience or periodic shutdowns for disassembly and measurement, which suffer from low adjustment accuracy, long downtime, and high costs, making them unsuitable for the long-term stable operation requirements of modern gas turbines. Summary of the Invention

[0003] This invention provides a method for optimizing gas turbine blade platforms based on rotor creep, in order to overcome the deficiencies in the prior art.

[0004] This invention is achieved through the following technical solution: A method for optimizing gas turbine blade platforms based on rotor creep includes the following steps: Step 1: Obtain the structural drawings of the corresponding gas turbine model, as well as the rotor creep displacement and the gap change between adjacent turbine blade platforms during a fixed-duration operating cycle in actual operation. Step 2: Based on the data obtained in Step 1, construct a calculation model of the rotor creep and the gap change data between adjacent turbine blade platforms for the corresponding gas turbine model, as well as a three-dimensional model of the corresponding gas turbine model; Step 3: Train the computational model obtained in Step 2; Step 4: Combine the computational model trained in Step 3 with the 3D model to obtain the data on the change in gap between adjacent turbine blade platforms within the corresponding service life; Step 5: After obtaining the gap change data between adjacent turbine blade platforms from the calculation model, calculate the rate of change to determine whether adjustments are needed; Step 6: If the rate of change exceeds the specified threshold, it is determined that adjustment is required. The structure of the corresponding adjacent turbine blade platform in the 3D model is analyzed and the corresponding processing solution is given on the 3D model. Step 7: The relevant maintenance personnel will process the corresponding adjacent turbine blade platforms according to the corresponding processing plan given on the 3D model.

[0005] The gas turbine blade platform optimization method based on rotor creep described above includes, in step one, the data collected also includes equivalent operating hours, start-stop times, load spectrum, and temperature field; the data collection cycle is 10,000 hours.

[0006] As described above, the optimization method for a gas turbine blade platform based on rotor creep involves the construction of a three-dimensional model in step two, which is based on the obtained gas turbine structural drawings. During the modeling process, it is necessary to ensure that the geometric dimensions, relative positions, and assembly relationship between the turbine blade platform and the rotor are consistent with the actual structure. At the same time, the rotor creep displacement data obtained in step one is incorporated into the three-dimensional model as boundary conditions to reflect the impact of actual operating conditions on the structure. After the model is constructed, it needs to be discretized using mesh generation technology. The size of the mesh cells after division should meet the calculation accuracy requirements, and the mesh should be refined in the key areas of the turbine blade platform.

[0007] As described above, the optimization method for gas turbine blade platforms based on rotor creep includes the following steps: the training operation of the calculation model in step three is as follows: the equivalent operating hours, start-stop times, load spectrum, and temperature field collected in step one are used as input variables, and the rotor creep displacement and the change data of the gap between adjacent turbine blade platforms are used as output targets. The relationship between the rotor creep displacement and the change data of the gap between adjacent turbine blade platforms is fitted by constructing a nonlinear mapping function to obtain the calculation relationship between the two.

[0008] As described above, in the optimization method for gas turbine blade platforms based on rotor creep, step three involves iteratively training the computational model, using cross-validation to divide the training and validation sets, and continuously adjusting the model parameters to minimize the error between the predicted clearance change and the actual clearance change, until the model's prediction accuracy meets the requirement of an error rate of less than 0.1%.

[0009] As described above, in the method for optimizing gas turbine blade platforms based on rotor creep, step four involves coupling the trained computational model with a three-dimensional model. Predicted parameters such as the equivalent operating hours, start-stop frequency, load spectrum, and temperature field of the gas turbine within a complete operating cycle are input. The computational model outputs the creep displacement of the rotor within that operating cycle in real time, and calculates the gap change data between adjacent turbine blade platforms using the creep displacement. Simultaneously, the three-dimensional model is driven to dynamically simulate the relative position changes of adjacent turbine blade platforms, thereby accurately obtaining the specific values ​​and trend curves of the platform gap under different operating stages.

[0010] As described above, in the method for optimizing gas turbine blade platforms based on rotor creep, step five involves storing the initial gap between adjacent turbine blade platforms in the calculation model and comparing it with the gap change data between adjacent turbine blade platforms output by the calculation model. If the change rate is ≤ ±10%, no processing is required; if the change rate is > ±10%, processing is required during the corresponding maintenance period.

[0011] As described above, in the optimization method for gas turbine blade platforms based on rotor creep, step six involves analyzing the structure of adjacent turbine blade platforms on a three-dimensional model. The focus is on examining the chamfer dimensions of the platform edges, the roughness of the contact surfaces, and the transition area between the platform and the blade body. Based on the specific values ​​and distribution characteristics of the gap variation, the processing solutions include locally grinding the platform edges to adjust the contact area or structurally strengthening the transition area to reduce the impact of creep deformation on the gap.

[0012] As described above, in the optimization method for gas turbine blade platforms based on rotor creep, in step seven, before processing adjacent turbine blade platforms, relevant maintenance personnel need to review the processing plan displayed on the three-dimensional model to confirm the consistency between the key parameters of the grinding area and the strengthening position involved in the plan and the actual blade platform structure.

[0013] As described above, in the gas turbine blade platform optimization method based on rotor creep, during the processing of relevant maintenance personnel in step seven, high-precision measuring tools are used to monitor the grinding position and grinding thickness of the corresponding turbine blade platform in real time to ensure that the gap between adjacent turbine blade platforms after processing meets the design requirements. After processing, the actual processing data is fed back to the calculation model and the three-dimensional model for data update.

[0014] The advantages of this invention are: by deeply coupling rotor creep data with turbine blade platform clearance change data, and combining the collaborative analysis of the computational model and the three-dimensional model, this invention achieves accurate prediction and dynamic optimization of turbine blade platform clearance changes; this invention not only improves the accuracy and efficiency of clearance adjustment and reduces errors caused by experience judgment, but also effectively reduces the risk of gas leakage and blade friction through real-time data feedback and model iterative updates, effectively ensuring the long-term safe and stable operation of the gas turbine. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 This is one of the schematic diagrams of the gas turbine blade platform processing operation of the present invention; Figure 2 This is the second schematic diagram of the gas turbine blade platform processing operation of the present invention; Figure 3 This is the third schematic diagram of the gas turbine blade platform processing operation of the present invention; Figure 4 This is the fourth schematic diagram of the gas turbine blade platform processing operation of the present invention. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, 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, 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.

[0018] A method for optimizing gas turbine blade platforms based on rotor creep includes the following steps: Step 1: Obtain the structural drawings of the corresponding gas turbine model, as well as the rotor creep displacement and the gap change between adjacent turbine blade platforms during a fixed-duration operating cycle in actual operation. Step 2: Based on the data obtained in Step 1, construct a calculation model of the rotor creep and the gap change data between adjacent turbine blade platforms for the corresponding gas turbine model, as well as a three-dimensional model of the corresponding gas turbine model; Step 3: Train the computational model obtained in Step 2; Step 4: Combine the computational model trained in Step 3 with the 3D model to obtain the data on the change in gap between adjacent turbine blade platforms within the corresponding service life; Step 5: After obtaining the gap change data between adjacent turbine blade platforms from the calculation model, calculate the rate of change to determine whether adjustments are needed; Step 6: If the rate of change exceeds the specified threshold, it is determined that adjustment is required. The structure of the corresponding adjacent turbine blade platform in the 3D model is analyzed and the corresponding processing solution is given on the 3D model. Step 7: The relevant maintenance personnel will process the corresponding adjacent turbine blade platforms according to the corresponding processing plan given on the 3D model.

[0019] Specifically, the data collected in step one of this embodiment also includes equivalent operating hours, number of start-stop cycles, load spectrum, and temperature field; the data collection operation cycle is 10,000 hours.

[0020] Specifically, in step two of this embodiment, the construction of the three-dimensional model is based on the obtained gas turbine structural drawings. During the modeling process, it is necessary to ensure that the geometric dimensions, relative positions, and assembly relationship between the turbine blade platform and the rotor are consistent with the actual structure. At the same time, the rotor creep displacement data obtained in step one is incorporated into the three-dimensional model as boundary conditions to reflect the impact of actual operating conditions on the structure. After the model is built, it needs to be discretized using mesh generation technology. The size of the mesh elements after generation should meet the calculation accuracy requirements, and the mesh should be refined in the key areas of the turbine blade platform. The refined mesh areas include the connection transition fillets between the platform and the blade body, the chamfered edges, and the surfaces where contact friction may occur. The mesh density in these areas needs to be 2-3 times that of other areas to ensure that the subtle features of local stress concentration and deformation can be captured. At the same time, during the model construction process, the material property parameters of the turbine blade and rotor, such as elastic modulus, Poisson's ratio, and creep curve, also need to be imported so that the three-dimensional model can realistically reflect the mechanical behavior of the material under high temperature and high pressure, providing a reliable physical basis for subsequent gap change simulation.

[0021] More specifically, the training operation of the calculation model in step three of this embodiment is as follows: The equivalent operating hours, start-stop times, load spectrum, and temperature field collected in step one are used as input variables, and the rotor creep displacement and adjacent turbine blade platform clearance change data are used as output targets. The relationship between the rotor creep displacement and adjacent turbine blade platform clearance change data is fitted by constructing a nonlinear mapping function to obtain their calculation relationship. This nonlinear mapping function can be constructed using a regression model. By introducing extreme operating condition samples from historical operating data (such as over-temperature operation, frequent start-stop, etc.) as a special training set, the model's ability to predict clearance change trends under complex operating conditions is improved. During model training, the input variables need to be normalized to eliminate the influence of dimensional differences on fitting accuracy, and a penalty factor is set to avoid overfitting, ensuring that the model maintains stable predictive performance under different operating cycles and conditions.

[0022] More specifically, in step three of this embodiment, the computational model is iteratively trained. Cross-validation is used to divide the training and validation sets. Model parameters are continuously adjusted to minimize the error between predicted and actual gap changes until the model's prediction accuracy meets the requirement of an error rate below 0.1%. Simultaneously, a dynamic database is established to categorize and store processing data from each iteration, including key parameters such as gap change rate under different operating cycles, grinding thickness, and actual gap values ​​after processing. Data mining techniques are used to analyze the correlation between processing effects and operating conditions, providing data support for subsequent optimization of the computational model's prediction algorithm and the structural analysis logic of the 3D model, further improving the method's adaptability and optimization accuracy. Furthermore, after data updates, the computational model needs to be retrained, incorporating the latest processed data as new samples into the training set. This allows the model to continuously learn from feedback information during actual processing, gradually reducing the deviation between theoretical predictions and actual operating conditions.

[0023] More specifically, in step four of this embodiment, the trained computational model is coupled with the 3D model. Predicted parameters such as the equivalent operating hours, start-stop frequency, load spectrum, and temperature field of the gas turbine within a complete operating cycle are input. The computational model outputs the creep displacement of the rotor within that operating cycle in real time, and calculates the gap change data between adjacent turbine blade platforms using the creep displacement. Simultaneously, the 3D model dynamically simulates the relative position changes of adjacent turbine blade platforms, thereby accurately obtaining the specific values ​​and trend curves of the platform gap at different operating stages. During the dynamic simulation, the 3D model can display the distribution cloud map of the platform gap at each time point in real time, intuitively presenting areas with excessively large or small gaps, providing a visual basis for subsequent adjustments. Furthermore, in step five of this embodiment, the computational model stores the initial gap between adjacent turbine blade platforms and compares it with the gap change data between adjacent turbine blade platforms output by the computational model. If the change rate is ≤ ±10%, no processing is required; if the change rate is > ±10%, processing is required during the corresponding maintenance period.

[0024] Furthermore, in step six of this embodiment, when analyzing the structure of adjacent turbine blade platforms on a three-dimensional model, the focus is on examining the chamfer dimensions of the platform edges, the roughness of the contact surfaces, and the transition area connecting the platform and the blade body. Based on the specific values ​​and distribution characteristics of the gap variation, the processing solution includes local grinding of the platform edges (the actual operation is as follows). Figure 1-4As shown, adjusting the contact area or strengthening the transition area can reduce the impact of creep deformation on the clearance. The 3D model will simultaneously display the clearance simulation results before and after adjustment and the structural stress distribution cloud map, allowing maintenance personnel to evaluate the feasibility of the solution. During the solution formulation process, the operating years of the gas turbine, cumulative creep damage, and future operating plans must be comprehensively considered. If the blade platform is nearing the end of its design life, a temporary grinding solution can be selected in conjunction with the replacement plan to meet short-term operating needs. If it is a blade in the medium-term operation, a structural strengthening solution is preferred to fundamentally slow down the clearance change rate.

[0025] Furthermore, in step seven of this embodiment, before processing the adjacent turbine blade platform, the relevant maintenance personnel must first review the processing plan displayed on the 3D model to confirm the consistency between the key parameters of the grinding area and the reinforcement location involved in the plan and the actual blade platform structure. The review includes whether the coordinate deviation of the grinding path is controlled within ±0.05mm, whether the material thickness of the reinforcement area meets the design specifications, and whether the flatness of the platform surface after processing meets the aerodynamic performance requirements of the gas turbine during operation. If any discrepancies are found between the 3D model and the actual structure, immediate feedback is required, and corrections should be made by updating the geometric parameters or material properties of the 3D model to ensure the accuracy and safety of the processing plan. During the processing implementation phase, the maintenance personnel... Personnel must strictly follow the process parameters marked on the 3D model. During the process, operation must be paused after every 10% of the work is completed. The current platform gap must be re-measured using a laser tracker, and the measured data must be compared with the predicted value of the 3D model. If the deviation exceeds ±0.02mm, the tool path must be recalibrated or the process parameters adjusted until the requirements are met. After processing, maintenance personnel must use a white light interferometer to inspect the micro-morphology of the platform surface to ensure that the surface roughness Ra≤0.8μm. The actual gap value, grinding amount, cladding layer thickness, and other data after processing must be entered into a dedicated database and uploaded to the update module of the calculation model to trigger automatic iterative training of the model, so that subsequent predictions can fully reflect the impact of this processing on the gap change. In addition, a 200-hour trial operation monitoring of the processed turbine blade platform is required. Vibration frequency, temperature distribution, and gap change data during operation are collected and compared with the baseline data before processing to verify the persistence of the optimization effect. If the gap change rate is stably controlled within ±5% during the trial operation, the processing is considered qualified; otherwise, a new optimization plan must be formulated based on the new operating data.

[0026] Furthermore, in step seven of this embodiment, during the relevant maintenance personnel's handling process, high-precision measuring tools are used to monitor the grinding position and grinding thickness of the corresponding turbine blade platform in real time to ensure that the gap between adjacent turbine blade platforms after processing meets the design requirements. After processing, the actual processing data is fed back to the calculation model and 3D model for data update to improve the accuracy and reliability of subsequent turbine blade platform gap change prediction. At the same time, during the data update process, historical processing records need to be classified and archived to establish a case library containing different fault types, handling measures, and effect evaluations, providing a reference for rapid diagnosis and solution formulation of similar problems. In addition, data visualization technology can be used to graphically present the correlation between the gap change trend and the handling measures in long-term operation, helping technicians identify potential structural weaknesses and providing data support for the design improvement and operation and maintenance strategy optimization of the gas turbine blade platform.

[0027] The turbine blade platform processed by this invention during trial operation showed an average error between the predicted and actual measured values ​​of the clearance change rate within 0.08%, far lower than the 3.5% average error of traditional methods. Simultaneously, gas leakage was reduced by 28%, and the number of blade friction cycles decreased by 65%. Furthermore, by introducing a third-party testing agency to conduct random sampling inspections of the platform clearance during trial operation using a laser interferometer, the consistency between the sampled data and the dynamic simulation results of the three-dimensional model of this invention reached 99.9%, further confirming the high accuracy of the test results.

[0028] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for rotor creep based optimization of a gas turbine turbine blade platform, characterized by: The method comprises the following steps: Step one: obtaining the structural drawing of the corresponding type of gas turbine and the rotor creep displacement amount and the gap change data between adjacent turbine blade platforms in the fixed time length of the running cycle of the corresponding type of gas turbine in the actual running process; Step two: constructing a calculation model of the rotor creep and the gap change data between adjacent turbine blade platforms of the corresponding type of gas turbine and a three-dimensional model of the corresponding type of gas turbine according to the data obtained in step one; Step three: training the calculation model obtained in step two; Step four: combining the trained calculation model in step three with the three-dimensional model to obtain the gap change data between adjacent turbine blade platforms in the corresponding use cycle; Step five: calculating the change rate of the gap change data between adjacent turbine blade platforms obtained by the calculation model to determine whether adjustment is needed; Step six: if the change rate exceeds the specified threshold, it is determined that adjustment is needed, the structure of the corresponding adjacent turbine blade platforms in the three-dimensional model is analyzed, and the corresponding treatment scheme is given on the three-dimensional model; Step seven: the relevant maintenance personnel process the corresponding adjacent turbine blade platforms according to the corresponding treatment scheme given on the three-dimensional model.

2. A method of rotor creep based optimization of a gas turbine turbine blade platform according to claim 1, characterized in that: The data collected in step one also includes equivalent running hours, start-stop times, load spectrum, and temperature field; the data collection running cycle is 10,000 hours.

3. A method of rotor creep based optimization of a gas turbine turbine blade platform according to claim 1, characterized in that: The three-dimensional model in step two is constructed according to the obtained gas turbine structural drawing, and the geometric size, relative position, and assembly relationship with the rotor of the turbine blade platform are ensured to be consistent with the actual structure during the modeling process. At the same time, the rotor creep displacement data obtained in step one is integrated as a boundary condition into the three-dimensional model to reflect the influence of the actual running condition on the structure. After the model is constructed, the model needs to be discretized by grid division technology. The grid element size after division should meet the calculation accuracy requirement, and the grid should be refined in the key area of the turbine blade platform.

4. A method of rotor creep based optimization of a gas turbine turbine blade platform according to claim 1, characterized in that: The training operation of the calculation model in step three is as follows: the equivalent running hours, start-stop times, load spectrum, and temperature field collected in step one are used as input variables, the rotor creep displacement amount and the gap change data between adjacent turbine blade platforms are used as output targets, the relationship between the rotor creep displacement amount and the gap change data between adjacent turbine blade platforms is fitted through the construction of a nonlinear mapping function, and the calculation relationship between the two is obtained.

5. A method of rotor creep based optimization of a gas turbine turbine blade platform according to claim 4, characterized in that: In step three, the calculation model is iteratively trained, the training set and the validation set are divided by cross-validation method, the model parameters are continuously adjusted to minimize the error between the predicted gap change and the actual gap change, and the prediction accuracy of the model is required to be less than 0.1%.

6. A method of rotor creep based optimization of a gas turbine turbine blade platform according to claim 1, characterized in that: The step four is coupling the trained calculation model with the three-dimensional model, inputting the equivalent running hours, start-stop times, load spectrum, and temperature field prediction parameters of the gas turbine in a complete running cycle, and outputting the creep displacement of the rotor in the running cycle in real time through the calculation model, and calculating the gap change data between adjacent turbine blade platforms, and driving the three-dimensional model to dynamically simulate the relative position change of adjacent turbine blade platforms, so as to accurately obtain the specific value and change trend curve of the platform gap in different running stages.

7. A method of rotor creep based optimization of a gas turbine turbine blade platform according to claim 1, characterized in that: The step five is comparing the initial gap between adjacent turbine blade platforms stored in the calculation model with the gap change data between adjacent turbine blade platforms output by the calculation model, if the change rate is ≤±10%, no processing is needed, if the change rate is >±10%, the processing is needed during the corresponding maintenance period.

8. A method of rotor creep based optimization of a gas turbine turbine blade platform according to claim 1, characterized in that: The step six is analyzing the structure of adjacent turbine blade platforms on the three-dimensional model, focusing on the chamfer size of the platform edge, the roughness of the contact surface, and the connection transition area of the platform and the blade body, and according to the specific value and distribution characteristics of the gap change, the processing scheme includes locally polishing the platform edge to adjust the contact area or structurally strengthening the transition area to reduce the influence of creep deformation on the gap.

9. A method of rotor creep based optimization of a gas turbine turbine blade platform according to claim 1, characterized in that: The step seven is that the relevant maintenance personnel need to review the processing scheme displayed on the three-dimensional model before processing the adjacent turbine blade platforms, and confirm the consistency of the key parameters of the polishing area and the strengthening position involved in the scheme with the actual blade platform structure.

10. A method of rotor creep based optimization of a gas turbine turbine blade platform according to claim 1, characterized in that: The step seven is that the relevant maintenance personnel need to review the processing scheme displayed on the three-dimensional model before processing the adjacent turbine blade platforms, and confirm the consistency of the key parameters of the polishing area and the strengthening position involved in the scheme with the actual blade platform structure. The step seven is that the relevant maintenance personnel need to review the processing scheme displayed on the three-dimensional model before processing the adjacent turbine blade platforms, and confirm the consistency of the key parameters of the polishing area and the strengthening position involved in the scheme with the actual blade platform structure.

Images