A thin-walled blade laser shock peening deformation control method based on digital twinning technology

Abstract

The application discloses a thin-wall blade laser shock peening deformation control method based on a digital twinborn technology, and relates to the field of aero-engine blade machining technology.The method constructs a digital twinborn prior database through finite element simulation and laser shock peening experiments, realizes rapid simulation of a thin-wall blade laser shock peening process by using a simulation agent model, and thus expands the twinborn database.A digital twinborn body of the thin-wall blade is constructed by using machine learning based on physical entity information of the thin-wall blade and laser shock peening process parameters and data of the twinborn database.A deformation prediction model of the thin-wall blade laser shock peening in the digital twinborn body is used to realize deformation prediction in the thin-wall blade machining process and to give a warning when the deformation error is too large.Furthermore, feedback control is carried out according to target deformation requirements, actual machining laser parameters are automatically adjusted, and the deformation control effect is achieved.

Description

Technical Field

[0001] This invention relates to the field of aero-engine blade processing technology, specifically to a method for controlling the deformation of thin-walled blades by laser shock peening based on digital twin technology. Background Technology

[0002] As a core component of aero-engines, blades operate in extremely harsh environments and require very high fatigue performance. Laser shock peening (LSP) is one of the key methods to improve their reliability and extend their service life. However, these blades typically have complex structures, extremely thin walls (usually less than 2 mm), and extremely high surface precision requirements (usually at the micrometer level). During LSP, the enormous plasma shock wave pressure causes plastic deformation of the blade surface material, introducing beneficial residual compressive stress while also creating uneven stress distribution within the component, leading to blade deformation.

[0003] Traditional deformation control methods control the impact intensity by adjusting the core parameters of laser shock, thereby controlling deformation. Alternatively, they design impact strategies, employing alternating double-sided impacts and symmetrical path planning to make the generated residual stress as self-balancing as possible, thus offsetting deformation. However, these methods cannot achieve real-time monitoring and prediction of deformation, nor do they have the function of feedback adjustment of laser parameters, leading to the continuous accumulation of deformation errors. Summary of the Invention

[0004] The purpose of this invention is to provide a method for controlling the deformation of thin-walled blades by laser shock annealing based on digital twin technology. This method can monitor and predict the deformation of thin-walled blades in real time during the laser shock annealing process, thereby improving the processing accuracy.

[0005] To solve the above-mentioned technical problems, the technical solution adopted by the present invention is as follows: A method for controlling the deformation of thin-walled blades through laser shock peening based on digital twin technology, characterized by comprising the following steps: Step 1. Construct a digital twin prior database through finite element simulation and experiments: Perform finite element simulation of the deformation of thin-walled blades under laser shock strengthening using simulation software to obtain a large amount of sample data on laser shock strengthening parameters and thin-walled blade deformation, and verify it through experiments. During the experiment, DIC technology is used to collect real-time deformation information of thin-walled blades; then, the data generated by the finite element simulation and the experimental data are stored in the database as digital twin prior data. Step 2. Create a simulation proxy model based on the digital twin prior data in the digital twin prior database; Step 3. Improve the digital twin prior database using simulation proxy models: Reduce the order and speed up the simulation by using simulation proxy models to achieve rapid simulation of laser shock strengthening, thereby obtaining a large amount of deformation data under different laser parameters and different blade parameters. This data is used to expand the twin data under different working conditions, improve the digital twin prior database, and provide comprehensive data information for the training and testing of subsequent deformation prediction models. Step 4. Constructing a digital twin of the thin-walled blade: Based on the physical entity of the thin-walled blade and using the collected multimodal data and data from the digital twin prior database, a digital twin of the thin-walled blade is constructed using machine learning; the multimodal data includes the physical entity information, initial shape information, environmental information, and laser shock peening process parameters of the thin-walled blade. Step 5. The laser shock strengthening process of thin-walled blades is monitored in real time using a digital twin to predict deformation and to provide feedback control based on the target deformation requirements. The actual processing laser parameters are automatically adjusted to achieve deformation control.

[0006] Furthermore, in step 1, the simulation software used is ABAQUS simulation software.

[0007] Furthermore, in step 1, the specific method for acquiring real-time deformation information of thin-walled blades using DIC technology is as follows: a high-contrast speckle pattern is coated on the back of the thin-walled blade subjected to laser impact, a high-speed camera is used to capture images of the blade during the laser impact process, and the displacement and strain distribution on the surface of the thin-walled blade after laser impact strengthening are calculated based on the images to obtain real-time deformation information of the thin-walled blade.

[0008] Furthermore, in step 2, the simulation proxy model is based on the support vector regression algorithm, and a low-dimensional and efficient simulation proxy model is obtained by extracting and training historical simulation data.

[0009] Furthermore, the expression for the support vector regression algorithm is: ; ; in, , These represent the constraints at the upper and lower boundaries, respectively. For kernel function, For bias terms, , This represents a single laser parameter vector. This represents the Euclidean distance between two vectors. This represents the bandwidth hyperparameter.

[0010] Furthermore, in step 3, during the simulation process, the simulation proxy model takes the simulated laser power density, spot size, and overlap rate as inputs and outputs the deformation of the thin-walled blade. It also extracts the node information and data from the simulation data and inputs them into the twin space to expand the twin database of the mapping relationship between laser shock strengthening parameters and deformation.

[0011] Furthermore, in step 4, the physical entity information of the thin-walled blade includes the type of sheet metal, thickness, and material properties; the environmental information is the position and temperature information of the thin-walled blade collected by position sensors and temperature sensors; the laser shock peening process parameters include laser power density, laser pulse width, number of shocks, scanning path, spot size, spot overlap rate, constraint layer, and absorption layer.

[0012] Further, in step 4, the digital twin includes four modules: a thin-walled blade 3D model construction module, a thin-walled blade processing environment simulation module, a thin-walled blade deformation prediction module, and a thin-walled blade processing visualization module. The thin-walled blade 3D model construction module is used to construct a corresponding thin-walled blade 3D model based on the physical entity of the thin-walled blade, virtually creating the physical model and assembly relationship of the corresponding object entity. The thin-walled blade processing environment simulation module is used to establish a virtual processing environment and realize the correct motion logic of the virtual entity. Based on the obtained thin-walled blade position data, laser scanning path data, and ambient temperature data, it uses modeling software to visualize the thin-walled blade... The system uses a 3D model to simulate the environment, enabling correct motion control and processing path of the virtual laser machine tool. The thin-walled blade deformation prediction module uses machine learning algorithms to establish a laser shock strengthening deformation prediction model based on real-time acquired multimodal data of the thin-walled blade. This model allows for real-time prediction of the thin-walled blade deformation, and provides timely warnings when the predicted deformation deviates significantly from the target deformation. The thin-walled blade processing visualization module allows users to observe the physical state and various processing information during the laser shock strengthening process of the thin-walled blade. It can display deformation cloud maps in real time, support online adjustment of laser parameters, and facilitate human-machine collaboration.

[0013] Furthermore, the machine learning algorithm is based on the gradient boosting regression tree algorithm. It combines data obtained from finite element simulation data, experimental data, and simulation proxy models to train and test the deformation prediction model, thereby improving prediction accuracy and real-time performance. In the actual processing, the real-time collected data such as laser power density, spot size, and overlap rate are used as inputs to the thin-walled blade deformation prediction module, and the deformation value is used as the output of the prediction model.

[0014] Furthermore, the gradient boosting regression tree algorithm is expressed as follows: ; ; In the above formula, Let be the predicted deformation of the t-th sample. For the i-th tree pair input The output (weak learner) is used to fit the residuals. Let be the input feature vector of the t-th sample, containing the key parameters of laser shock enhancement. For laser power density, The pulse width. The diameter of the light spot. For the number of impacts, For overlap rate .

[0015] Beneficial technical effects This application constructs a digital twin of a thin-walled blade using machine learning, based on the physical entity information of the thin-walled blade and the laser shock strengthening process parameters, and using data from a twin database. By utilizing the deformation prediction model of the thin-walled blade in the digital twin for laser shock strengthening, deformation prediction during the processing of the thin-walled blade is achieved, and an early warning is issued when the deformation error is too large. Feedback control is performed according to the target deformation requirements, and the actual processing laser parameters are automatically adjusted to achieve deformation control and improve processing accuracy. Attached Figure Description

[0016] The present invention will be further described with reference to the accompanying drawings, but the embodiments in the drawings do not constitute any limitation on the present invention. For those skilled in the art, other drawings can be obtained based on the following drawings without creative effort: Figure 1 This is a flowchart of the deformation control method of the present invention. Detailed Implementation

[0017] To enable those skilled in the art to better understand the technical solutions of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of this application can be combined with each other.

[0018] like Figure 1 As shown, this embodiment of the invention provides a method for controlling the deformation of thin-walled blades through laser shock peening based on digital twin technology, comprising the following steps: Step 1. Construct a digital twin prior database through finite element simulation and experiments. Specifically, the finite element simulation is established using ABAQUS simulation software. The deformation simulation of thin-walled blades under laser shock strengthening is performed using an explicit-implicit analysis method to obtain a large amount of sample data on laser shock strengthening parameters and thin-walled blade deformation. The data is then verified through experiments. Finally, the data generated by the finite element simulation and the experimental data are stored in a database as "prior knowledge" for the digital twin.

[0019] The finite element simulation process is as follows: First, a three-dimensional model of the thin-walled blade is established and imported into the ABAQUS simulation software. Corresponding material properties are assigned, and corresponding constraints are applied. Then, loads with corresponding laser shock strengthening parameters are applied according to the planned impact path. The calculation is submitted to complete explicit dynamic analysis. Finally, implicit static analysis is performed based on this to obtain the final deformation data of the thin-walled blade after laser shock strengthening. In the experiment, the same laser shock strengthening parameters and blade as in the finite element simulation are used. Real-time deformation information of the thin-walled blade is acquired using DIC technology to verify the finite element simulation results throughout the entire process, thereby obtaining high-fidelity simulation and experimental data. Specifically, the DIC technology involves coating the back of the thin-walled blade subjected to laser shock with a high-contrast speckle pattern, capturing images of the blade during the laser shock process using a high-speed camera, and calculating the displacement and strain distribution on the surface of the thin-walled blade after laser shock strengthening using digital image correlation algorithms to obtain real-time deformation information of the thin-walled blade.

[0020] Step 2. Create a simulation proxy model based on the digital twin prior data in the digital twin prior database; the simulation proxy model is based on the support vector regression algorithm, and a low-dimensional and efficient simulation proxy model is obtained by extracting and training historical simulation data.

[0021] The expression for the support vector regression algorithm is as follows: ; ; in, , These represent the constraints at the upper and lower boundaries, respectively. For kernel function, This is a bias term used to improve the overall fit; , This represents a single laser parameter vector; This represents the Euclidean distance between two vectors; the smaller the value, the more similar the process combinations. This represents the bandwidth hyperparameter, used to control the degree of "locality sensitivity".

[0022] Step 3. Improve the digital twin prior database using simulation proxy models: Reduce the order and speed up the simulation by using simulation proxy models to achieve rapid simulation of laser shock reinforcement. This will obtain a large amount of deformation data under different laser parameters and different blade parameters, which will be used to expand the twin data under different working conditions, improve the digital twin prior database, and provide comprehensive data information for the training and testing of subsequent deformation prediction models.

[0023] During the simulation, the simulated laser power density, spot size, and overlap rate are used as inputs to the surrogate model, and the output is the deformation of the thin-walled blade. The node information and data of the simulation data are extracted and input into the twin space to expand the database of the mapping relationship between laser shock strengthening parameters and deformation.

[0024] Step 4. Construct a digital twin of the thin-walled blade. Based on the physical entity of thin-walled blades and utilizing acquired multimodal data and digital twin technology... The data from the verification database is used to construct a digital twin of the thin-walled blade using machine learning; the multimodal data includes the physical entity information, initial shape information, environmental information, and laser shock strengthening process parameters of the thin-walled blade.

[0025] The physical entity information of the thin-walled blade, such as the type of sheet metal, thickness and material properties, is collected, and the initial shape information of the thin-walled blade is acquired using a structured light scanner.

[0026] The laser shock peening process parameters include: laser power density, laser pulse width, number of shocks, scanning path, spot size, spot overlap rate, constraint layer, absorption layer, etc.

[0027] The environmental information of the thin-walled blade includes, for example, motion patterns, machine tool temperature, laser position, thin plate position, clamping method, and strengthening path direction. This environmental information is collected using position sensors, temperature sensors, etc., and all information is preprocessed to obtain a preprocessed dataset.

[0028] The digital twin includes a thin-walled blade 3D model construction module, a thin-walled blade processing environment simulation module, a thin-walled blade deformation prediction module, and a thin-walled blade processing visualization module.

[0029] The thin-walled blade 3D model building module is used to build a corresponding thin-walled blade 3D model based on the physical entity of the thin-walled blade, and to virtually generate the physical model and assembly relationship of the corresponding object entity. The thin-walled blade 3D model is modeled using SolidWorks, and the 3D model is rendered using 3DS Max. Finally, the rendered model is imported into Unity 3D software to obtain a virtual entity that matches the physical entity.

[0030] The thin-walled blade processing environment simulation module is used to establish a virtual processing environment and realize the correct motion logic of the virtual entity. Based on the obtained thin-walled blade position data, laser scanning path data, and ambient temperature data, the modeling software is used to simulate the environment of the three-dimensional model of the thin-walled blade, so as to realize the correct motion control and processing path of the virtual laser machine tool. The thin-walled blade deformation prediction module is used to establish a laser shock strengthening deformation prediction model based on real-time acquired multimodal data of thin-walled blades and machine learning algorithms. The laser shock strengthening deformation prediction model enables real-time prediction of thin-walled blade deformation. When the predicted thin-walled blade deformation deviates too much from the target deformation, it can issue an early warning in a timely manner.

[0031] The machine learning algorithm is based on the gradient boosting regression tree algorithm. It combines data obtained from finite element simulation data, experimental data, and simulation proxy models to train and test the deformation prediction model, thereby improving prediction accuracy and real-time performance. In the actual processing, the real-time collected data such as laser power density, spot size, and overlap rate are used as inputs to the thin-walled blade deformation prediction module, and the deformation value is used as the output of the prediction model.

[0032] The gradient boosting regression tree algorithm is expressed as follows: ; ; In the above formula, Let be the predicted deformation of the t-th sample. For the i-th tree pair input The output (weak learner) is used to fit the residuals. Let be the input feature vector of the t-th sample, containing the key parameters of laser shock enhancement. For laser power density, The pulse width. The diameter of the light spot. For the number of impacts, For overlap rate .

[0033] Furthermore, the loss function of the gradient boosting regression tree algorithm is the Huber loss function: ; In the above formula, Let be the actual deformation of the t-th sample. The residual is the absolute value of the difference between the predicted deformation of the t-th sample and the predicted deformation. It is the Huber threshold, used to distinguish between "small errors" and "large errors".

[0034] Furthermore, the recursive formula for the gradient boosting regression tree algorithm is: ; In the above formula, This represents the model's predicted value for deformation before this update. This represents the updated model's total prediction of the deformation. Indicates the learning rate. This represents the output of the nth regression tree, which fits the current residual.

[0035] The thin-walled blade processing visualization module allows users to observe the physical state and various processing information of thin-walled blades during the laser shock strengthening process. It can display deformation cloud maps in real time and support online adjustment of laser parameters for human-machine collaboration.

[0036] Step 5: The laser shock strengthening process of thin-walled blades is monitored in real time using a digital twin to predict deformation. When the deformation error is too large, an early warning is issued. Feedback control is performed according to the target deformation requirements to automatically adjust the actual processing laser parameters and achieve deformation control.

[0037] When the predicted deformation of the thin-walled blade during laser shock peening deviates from the target shape, the digital twin generates a new set of laser process parameters and sends them in real time to the controller of the physical processing system via a communication interface. Upon receiving the instruction, the physical processing system immediately adjusts the corresponding parameters and executes subsequent laser shock peening according to the new settings. After implementing the new parameters, the system returns to the first step to perform real-time monitoring, prediction, and decision-making again, forming a continuous closed loop of "perception-analysis-decision-execution," achieving dynamic and adaptive process control.

[0038] This invention constructs a digital twin prior database through finite element simulation and laser shock strengthening experiments. A simulation proxy model is used to achieve rapid simulation of the laser shock strengthening process of thin-walled blades, thereby expanding the twin database. Based on the physical entity information of the thin-walled blades and the laser shock strengthening process parameters, and using data from the twin database, machine learning is employed to construct a digital twin of the thin-walled blades. Using a deformation prediction model for laser shock strengthening of thin-walled blades within the digital twin, deformation prediction during the thin-walled blade processing is achieved, and an early warning is issued when the deformation error is too large. Feedback control is implemented based on the target deformation requirements, automatically adjusting the actual processing laser parameters to achieve deformation control.

[0039] Furthermore, those skilled in the art can combine and integrate the different embodiments or examples described herein, as well as the features of those embodiments or examples, without contradiction. Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present invention.

Claims

1. A method for controlling the deformation of thin-walled blades through laser shock peening based on digital twin technology, characterized in that, Includes the following steps: Step 1. Construct a digital twin prior database through finite element simulation and experiments: Perform finite element simulation of the deformation of thin-walled blades under laser shock strengthening using simulation software to obtain a large amount of sample data on laser shock strengthening parameters and thin-walled blade deformation, and verify it through experiments. During the experiment, DIC technology is used to collect real-time deformation information of thin-walled blades; then, the data generated by the finite element simulation and the experimental data are stored in the database as digital twin prior data. Step 2. Create a simulation proxy model based on the digital twin prior data in the digital twin prior database; Step 3. Improve the digital twin prior database using simulation proxy models: Reduce the order and speed up the simulation by using simulation proxy models to achieve rapid simulation of laser shock strengthening, thereby obtaining a large amount of deformation data under different laser parameters and different blade parameters. This data is used to expand the twin data under different working conditions, improve the digital twin prior database, and provide comprehensive data information for the training and testing of subsequent deformation prediction models. Step 4. Constructing a digital twin of the thin-walled blade: Based on the physical entity of the thin-walled blade and using the collected multimodal data and data from the digital twin prior database, a digital twin of the thin-walled blade is constructed using machine learning; the multimodal data includes the physical entity information, initial shape information, environmental information, and laser shock peening process parameters of the thin-walled blade. Step 5. The laser shock strengthening process of thin-walled blades is monitored in real time using a digital twin to predict deformation and to provide feedback control based on the target deformation requirements. The actual processing laser parameters are automatically adjusted to achieve deformation control. In step 4, the physical entity information of the thin-walled blade includes the type of sheet metal, thickness, and material properties; the environmental information is the position and temperature information of the thin-walled blade collected by position sensors and temperature sensors; the laser shock peening process parameters include laser power density, laser pulse width, number of shocks, scanning path, spot size, spot overlap rate, constraint layer, and absorption layer. In step 4, the digital twin comprises four modules: a thin-walled blade 3D model construction module, a thin-walled blade processing environment simulation module, a thin-walled blade deformation prediction module, and a thin-walled blade processing visualization module. The thin-walled blade 3D model construction module is used to construct a corresponding 3D model of the thin-walled blade based on its physical entity, virtually creating the physical model and assembly relationships of the corresponding object entity. The thin-walled blade processing environment simulation module is used to establish a virtual processing environment and realize the correct motion logic of the virtual entity. Based on the obtained thin-walled blade position data, laser scanning path data, and ambient temperature data, it uses modeling software to visualize the 3D model of the thin-walled blade. The model simulates the environment to achieve correct motion control and processing path of the virtual laser machine tool. The thin-walled blade deformation prediction module is used to establish a laser shock strengthening deformation prediction model based on real-time acquired multimodal data of thin-walled blades using machine learning algorithms. The laser shock strengthening deformation prediction model enables real-time prediction of thin-walled blade deformation. When the predicted thin-walled blade deformation deviates too much from the target deformation, it can issue an early warning in time. The thin-walled blade processing visualization module allows users to observe the physical state and various processing information of thin-walled blades during the laser shock strengthening process. It can display deformation cloud maps in real time and support online adjustment of laser parameters for human-machine collaboration. The machine learning algorithm is based on the gradient boosting regression tree algorithm. It combines data obtained from finite element simulation data, experimental data, and simulation surrogate models to train and test the deformation prediction model, thereby improving prediction accuracy and real-time performance. The expression for the gradient boosting regression tree algorithm is as follows: ； ； In the above formula, The predicted deformation of the t-th sample. For the i-th tree pair input The output is used to fit the residual. Let be the input feature vector of the t-th sample, containing the key parameters of laser shock enhancement. For laser power density, The pulse width. The diameter of the light spot. For the number of impacts, This refers to the overlap rate.

2. The method for controlling the deformation of thin-walled blades by laser shock peening based on digital twin technology according to claim 1, characterized in that: In step 1, the simulation software used is ABAQUS simulation software.

3. The method for controlling the deformation of thin-walled blades by laser shock peening based on digital twin technology according to claim 1, characterized in that: In step 1, the specific method for acquiring real-time deformation information of thin-walled blades using DIC technology is as follows: a high-contrast speckle pattern is coated on the back of the thin-walled blade subjected to laser impact, and a high-speed camera is used to capture images of the blade during the laser impact process. Based on the images, the displacement and strain distribution on the surface of the thin-walled blade after laser impact strengthening are calculated to obtain the real-time deformation information of the thin-walled blade.

4. The method for controlling the deformation of thin-walled blades by laser shock peening based on digital twin technology according to claim 1, characterized in that: In step 2, the simulation proxy model is based on the support vector regression algorithm. By extracting and training historical simulation data, a low-dimensional and efficient simulation proxy model is obtained.

5. The method for controlling the deformation of thin-walled blades using laser shock peening based on digital twin technology according to claim 4, characterized in that, The expression for the support vector regression algorithm is: ； ； in, , These represent the constraints at the upper and lower boundaries, respectively. For kernel function, For bias terms, , This represents a single laser parameter vector. This represents the Euclidean distance between two vectors. This represents the bandwidth hyperparameter.

6. The method for controlling the deformation of thin-walled blades by laser shock peening based on digital twin technology according to claim 1, characterized in that: In step 3, during the simulation process, the simulation proxy model takes the simulated laser power density, spot size and overlap rate as inputs and outputs the deformation of the thin-walled blade. It also extracts the node information and data of the simulation data and inputs them into the twin space to expand the twin database of the mapping relationship between laser shock strengthening parameters and deformation.

Images