Aircraft engine blade profile detection equipment
By using image acquisition and convolutional neural network algorithms in the blade surface detection equipment of aero engine and combining with three-dimensional scanners, the problem of difficulty in detecting blade surface defects in the prior art is solved, and comprehensive detection and defect recognition of blade surfaces are achieved , improves manufacturing quality and blade service life.
Patent Information
- Application Number
- CN202410960120.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-17
- Publication Date
- 2024-11-12
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The prior art is difficult to detect whether there are defects on the surface of aircraft engine blades, which makes it difficult to ensure manufacturing quality, affects engine performance and reliability, and may reduce the service life of the blades.
Using an aero engine blade surface detection device including image acquisition module, data processing and analysis module, comparison and evaluation module, and display and reporting module, defects are identified through image acquisition and convolutional neural network algorithms, and combined with a three-dimensional scanner for comprehensive results. Test.
The comprehensive inspection of the blade surface is achieved, which can accurately identify and quantify defects, determine the type and severity of defects, facilitate improving manufacturing quality and extending the service life of the blade.
Smart Images

Figure CN118937333A_ABST
Abstract
Description
Technical Field
[0001] The invention relates to the technical field of blade profile detection, and in particular to a device for detecting the blade profile of an aero-engine. Background Art
[0002] Aircraft engine blades are key parts of the engine, and their geometric shape characteristics have a vital impact on the engine's power performance. Blade profiles are usually designed based on fluid dynamics principles, and are mostly characterized by bending, twisting and rising. There are many of them and they come in various shapes. Therefore, accurate measurement of blade profiles is a key link in ensuring stable and improved engine performance.
[0003] After searching, the Chinese patent number CN113176085B is a patent for a hollow blade profile detection device for the hot end turbine of an aircraft engine, which relates to the technical field of automated detection equipment, including a frame, a drum mounting part, a dust removal mechanism and a detection mechanism. The present invention sets a mounting part to achieve the removal of dust and other impurities that may be attached to the inner flow channel of the blade to be inspected without disassembly, and sets a detection mechanism to cooperate with the driving motor to drive the moving seat to accurately position on the threaded end face of the drum mounting part, and in the process of the sleeve and the tenon fitting of the blade, the sleeve is filled with ultrapure water, and the sleeve is driven by the output end of the hydraulic cylinder to separate from the water level of the water tank, further achieving non-destructive and rapid quality detection of each blade without disassembly; by reading the water storage reading inside the vertical counterweight cylinder, it is accurately judged whether there are quality problems such as material missing and carbon deposition in the inner flow channel structure of the blade to be inspected, and the cost of the detection equipment is greatly reduced.
[0004] However, in actual use, it is difficult to detect whether there are defects on the blade surface, that is, it is difficult to ensure the manufacturing quality of the blade, and it is difficult to improve the performance and reliability of the engine. At the same time, it may affect the service life of the blade. Therefore, it is necessary to propose an aircraft engine blade profile detection device. Summary of the invention
[0005] The purpose of the present invention is to solve the shortcomings in the prior art that it is difficult to detect whether there are defects on the blade surface, that is, it is difficult to ensure the manufacturing quality of the blade, it is difficult to improve the performance and reliability of the engine, and it may affect the service life of the blade, and propose an aircraft engine blade profile detection device.
[0006] In order to achieve the above object, the present invention adopts the following technical solutions:
[0007] An aircraft engine blade profile detection device, comprising:
[0008] Image acquisition module: responsible for capturing image data of the blade surface in real time;
[0009] Data processing and analysis module: responsible for processing and analyzing the collected images, identifying and quantifying the defects on the surface of the blade body;
[0010] Comparison and evaluation module: responsible for comparing the collected data with the design requirements or standards, and evaluating the shape and quality of the blade surface;
[0011] Display and reporting module: responsible for displaying the analyzed data results to the user and generating a test report;
[0012] The image acquisition module is arranged on the outside of the fixed block, and a lifting control motor is fixedly installed on the outside of the fixed block. A second rotating shaft is provided at the output end of the lifting control motor, and a first bevel gear is fixedly connected to the outside of the second rotating shaft, and a second bevel gear is meshedly connected to the outside of the first bevel gear, and a threaded rod is fixedly connected to the outside of the second bevel gear, and a threaded sleeve is threadedly connected to the outside of the threaded rod, and a fixed platform is rotatably connected to the outside of the threaded sleeve, and a three-dimensional scanner is arranged on the outside of the fixed platform, and a telescopic rod is symmetrically fixedly connected to the outside of the fixed platform, and a second rotating wheel is fixedly connected to the outside of the telescopic rod away from the fixed platform, the second rotating wheel is rotatably connected to the fixed block, and the second rotating wheel is rotatably connected to the threaded rod.
[0013] The above technical solution further includes:
[0014] The data processing and analysis module uses a threshold processing method for defect detection, and its specific formula is:
[0015] Where, (I(x,y)) represents the grayscale value of the image at ((x,y));
[0016] (T) is the set threshold.
[0017] The comparison and evaluation module uses a convolutional neural network algorithm to assist in comparison and evaluation, and the specific steps are as follows:
[0018] Data preparation and preprocessing: Collect a large amount of aero-engine blade surface image data, including normal blades and blades with various defects, and annotate the collected image data to identify whether there are defects in each image and the type and location of the defects;
[0019] Network model construction: Design a suitable CNN architecture according to task requirements, including the configuration and combination of convolutional layers, pooling layers, activation functions, and fully connected layer components, and set the initial values of weights and bias parameters in the network;
[0020] Network training: Set training parameters, input preprocessed image data into CNN, calculate prediction results through forward propagation process, compare prediction results with real annotations, calculate loss value, and update parameters in the network through back propagation algorithm to reduce loss value, repeat forward propagation and back propagation process until the predetermined number of iterations no longer decreases significantly;
[0021] Model evaluation and optimization: Use independent validation set data to evaluate the trained model and tune the model based on the evaluation results;
[0022] Comparison and evaluation: The surface image of the aircraft engine blade to be inspected is input into the trained CNN model for defect detection. The detected defects are compared with the preset defect standards to determine the type and severity of the defects.
[0023] An angle control motor is fixedly installed on the outside of the fixed block, and a first rotating wheel is provided at the output end of the angle control motor. The first rotating wheel is rotationally connected to the fixed block, and a belt is externally connected to the first rotating wheel for transmission, and the belt is transmission-connected to the second rotating wheel.
[0024] The outside of the fixed block is fixedly connected with a rotating ring, the outside of the rotating ring is rotatably connected with a detection platform, and the outside of the rotating ring is fixedly connected with an annular rack.
[0025] A position control motor is fixedly installed on the outside of the detection platform, and a first rotating shaft is provided at the output end of the position control motor. The first rotating shaft is rotationally connected to the detection platform, and a first gear is fixedly installed on the outside of the first rotating shaft. The first gear is meshingly connected to the annular rack.
[0026] The outside of the detection platform is symmetrically fixedly connected with a fixing column, the outside of the fixing column is provided with a blade body, and the outside of the fixing column is symmetrically fixedly installed with a blade fixing control motor.
[0027] The output end of the blade fixing control motor is provided with a third rotating shaft, the third rotating shaft is rotationally connected to the fixing column, and the outside of the third rotating shaft is fixedly connected with a blade fixing plate.
[0028] The present invention has the following beneficial effects:
[0029] 1. In the present invention, when inspecting the outside of the blade body, the height of the three-dimensional scanner can be changed by rotating the second bevel gear, and the telescopic rod can drive the three-dimensional scanner to rotate by driving the second rotating wheel to rotate, so that the position and angle of the three-dimensional scanner can be adjusted, and the outside of the blade body can be fully scanned to ensure the manufacturing quality of the blade.
[0030] 2. In the present invention, the image acquisition module can be used to comprehensively acquire the surface of the blade body, and the comparison and evaluation module can be used to detect defects in the acquired surface image of the blade body, and the detected defects can be compared with the preset defect standards to determine the type and severity of the defects, thereby facilitating subsequent processing of the blade body. BRIEF DESCRIPTION OF THE DRAWINGS
[0031] Figure 1 A schematic diagram of the structure of an aircraft engine blade profile detection device proposed by the present invention;
[0032] Figure 2 It is a schematic diagram of the first structure of the present invention;
[0033] Figure 3 It is a second structural schematic diagram of the present invention;
[0034] Figure 4 It is a schematic diagram of the third structure of the present invention;
[0035] Figure 5 for Figure 1 A schematic diagram of the structure enlargement in the middle;
[0036] Figure 6 for Figure 2 A magnified schematic diagram of the structure at B in the middle;
[0037] Figure 7 for Figure 4 A magnified schematic diagram of the structure at C in the middle;
[0038] Figure 8 It is a system block diagram of the present invention.
[0039] In the figure: 1. detection table; 2. fixed column; 3. blade body; 4. annular rack; 5. rotating ring; 6. fixed block; 7. three-dimensional scanner; 8. angle control motor; 9. telescopic rod; 10. threaded sleeve; 11. fixed table; 12. first rotating wheel; 13. belt; 14. second rotating wheel; 15. position control motor; 16. first rotating shaft; 17. first gear; 18. lifting control motor; 19. second rotating shaft; 20. first bevel gear; 21. second bevel gear; 22. threaded rod; 23. blade fixing control motor; 24. third rotating shaft; 25. blade fixing plate. DETAILED DESCRIPTION
[0040] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0041] like Figure 1-Figure 8 As shown, an aircraft engine blade surface detection device comprises:
[0042] Image acquisition module: responsible for capturing image data of the surface of the blade body 3 in real time;
[0043] Data processing and analysis module: responsible for processing and analyzing the collected images, identifying and quantifying the defects on the surface of the blade body 3;
[0044] Comparison and evaluation module: responsible for comparing the collected data with the design requirements or standards, and evaluating the shape and quality of the surface of the blade body 3;
[0045] Display and reporting module: responsible for displaying the analyzed data results to the user and generating a test report;
[0046] The image acquisition module is arranged on the outside of the fixed block 6, and a lifting control motor 18 is fixedly installed on the outside of the fixed block 6. A second rotating shaft 19 is provided at the output end of the lifting control motor 18. The outside of the second rotating shaft 19 is fixedly connected with a first bevel gear 20, and the outside of the first bevel gear 20 is meshedly connected with a second bevel gear 21, and the outside of the second bevel gear 21 is fixedly connected with a threaded rod 22, and the outside of the threaded rod 22 is threadedly connected with a threaded sleeve 10, and the outside of the threaded sleeve 10 is rotatably connected with a fixed platform 11. A three-dimensional scanner 7 is arranged on the outside of the fixed platform 11, and a telescopic rod 9 is symmetrically fixedly connected to the outside of the fixed platform 11. The telescopic rod 9 is fixedly connected to the outside of the fixed platform 11 away from the fixed platform 11. The second rotating wheel 14 is rotatably connected to the fixed block 6, and the second rotating wheel 14 is rotatably connected to the threaded rod 22.
[0047] The working principle of an aircraft engine blade profile detection device proposed by the present invention is that when it is necessary to detect the surface of the blade body 3, the lifting control motor 18 is started, and the lifting control motor 18 causes the second rotating shaft 19 set at the output end to rotate, and the second rotating shaft 19 drives the first bevel gear 20 fixedly connected to the outside to rotate, and the first bevel gear 20 causes the second bevel gear 21 meshingly connected to the outside to rotate, and the second bevel gear 21 drives the threaded rod 22 fixedly connected to the outside to rotate, and the threaded rod 22 causes the threaded sleeve 10 connected to the outside to drive the fixed platform 11 to rise and fall, that is, the three-dimensional scanner 7 set outside the fixed platform 11 can be adjusted to a suitable height, and at this time, the second rotating wheel 14 is rotated, and the second rotating wheel 14 causes the telescopic rod 9 symmetrically fixedly connected to the outside to drive the fixed platform 11 to rotate, so that the acquisition angle of the three-dimensional scanner 7 is adjusted, so as to facilitate more comprehensive acquisition of image data of the blade body 3.
[0048] In one embodiment, for the above data processing and analysis module, the data processing and analysis module uses a threshold processing method for defect detection, and its specific formula is:
[0049] Where, (I(x,y)) represents the grayscale value of the image at ((x,y));
[0050] (T) is the set threshold.
[0051] In one embodiment, for the above comparison and evaluation module, the comparison and evaluation module uses a convolutional neural network algorithm to assist in comparison and evaluation, and the specific steps are as follows:
[0052] Data preparation and preprocessing: Collect a large amount of aero-engine blade surface image data, including normal blades and blades with various defects, and annotate the collected image data to identify whether there are defects in each image and the type and location of the defects;
[0053] Network model construction: Design a suitable CNN architecture according to task requirements, including the configuration and combination of convolutional layers, pooling layers, activation functions, and fully connected layer components, and set the initial values of weights and bias parameters in the network;
[0054] Network training: Set training parameters, input preprocessed image data into CNN, calculate prediction results through forward propagation process, compare prediction results with real annotations, calculate loss value, and update parameters in the network through back propagation algorithm to reduce loss value, repeat forward propagation and back propagation process until the predetermined number of iterations no longer decreases significantly;
[0055] Model evaluation and optimization: Use independent validation set data to evaluate the trained model and tune the model based on the evaluation results;
[0056] Comparison and evaluation: The surface image of the aircraft engine blade to be inspected is input into the trained CNN model for defect detection. The detected defects are compared with the preset defect standards to determine the type and severity of the defects.
[0057] In one embodiment, for the above-mentioned fixed block 6, an angle control motor 8 is fixedly installed on the outside of the fixed block 6, and a first rotating wheel 12 is provided at the output end of the angle control motor 8. The first rotating wheel 12 is rotationally connected to the fixed block 6, and the external transmission connection of the first rotating wheel 12 is connected with a belt 13, and the belt 13 is transmission connected to the second rotating wheel 14.
[0058] In one embodiment, for the above-mentioned fixed block 6 , the outside of the fixed block 6 is fixedly connected to the rotating ring 5 , the outside of the rotating ring 5 is rotatably connected to the detection platform 1 , and the outside of the rotating ring 5 is fixedly connected to the annular rack 4 .
[0059] In one embodiment, for the above-mentioned testing platform 1, a position control motor 15 is fixedly installed on the outside of the testing platform 1, and a first rotating shaft 16 is provided at the output end of the position control motor 15. The first rotating shaft 16 is rotationally connected to the testing platform 1, and a first gear 17 is fixedly installed on the outside of the first rotating shaft 16. The first gear 17 is meshingly connected to the annular rack 4.
[0060] The working principle of an aircraft engine blade profile detection device proposed by the present invention is to start the angle control motor 8, the angle control motor 8 will cause the first rotating wheel 12 set at the output end to rotate, the first rotating wheel 12 will drive the belt 13 connected to the external transmission to transmit, the belt 13 will cause the second rotating wheel 14 connected to the transmission to rotate, start the position control motor 15, the position control motor 15 will drive the first rotating shaft 16 set at the output end to rotate, the first rotating shaft 16 will cause the first gear 17 connected to the external meshing to rotate, the first gear 17 will cause the annular rack 4 connected to the external meshing to drive the rotating ring 5 to rotate outside the detection platform 1, so as to facilitate a comprehensive detection of the outside of the blade body 3.
[0061] In one embodiment, for the above-mentioned detection platform 1 , a fixing column 2 is symmetrically fixedly connected to the outside of the detection platform 1 , a blade body 3 is arranged outside the fixing column 2 , and a blade fixing control motor 23 is symmetrically fixedly installed outside the fixing column 2 .
[0062] In one embodiment, for the blade fixing control motor 23, the output end of the blade fixing control motor 23 is provided with a third rotating shaft 24, the third rotating shaft 24 is rotatably connected to the fixing column 2, and the outside of the third rotating shaft 24 is fixedly connected to the blade fixing plate 25.
[0063] The working principle of an aircraft engine blade profile detection device proposed by the present invention is that the fixing column 2 is convenient for fixing the blade body 3 through the blade fixing plate 25 arranged externally, so as to facilitate detection. The blade body 3 is placed in the middle of the blade fixing plate 25, and the blade fixing control motor 23 is started. The blade fixing control motor 23 will drive the third rotating shaft 24 arranged at the output end to rotate, and the third rotating shaft 24 will cause the blade fixing plate 25 to rotate. By independently controlling the rotation of the blade fixing plate 25, the fixing effect of the blade body 3 can be improved.
[0064] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.
Claims
1. An aircraft engine blade profile detection device, characterized in that: include: Image acquisition module: responsible for capturing image data of the surface of the blade body (3) in real time; Data processing and analysis module: responsible for processing and analyzing the collected images, identifying and quantifying the defects on the surface of the blade body (3); Comparison and evaluation module: responsible for comparing the collected data with the design requirements or standards, and evaluating the shape and quality of the surface of the blade body (3); Display and reporting module: responsible for displaying the analyzed data results to the user and generating a test report; The image acquisition module is arranged outside the fixed block (6); a lifting control motor (18) is fixedly installed outside the fixed block (6); a second rotating shaft (19) is arranged at the output end of the lifting control motor (18); a first bevel gear (20) is fixedly connected to the outside of the second rotating shaft (19); a second bevel gear (21) is meshingly connected to the outside of the first bevel gear (20); a threaded rod (22) is fixedly connected to the outside of the second bevel gear (21); and the threaded rod (22) is threaded on the outside of the threaded rod (22). A threaded sleeve (10) is connected to the threaded sleeve (10), the outside of the threaded sleeve (10) is rotatably connected to a fixed platform (11), a three-dimensional scanner (7) is arranged outside the fixed platform (11), a telescopic rod (9) is symmetrically fixedly connected to the outside of the fixed platform (11), the outside of the telescopic rod (9) away from the fixed platform (11) is fixedly connected to a second rotating wheel (14), the second rotating wheel (14) is rotatably connected to the fixed block (6), and the second rotating wheel (14) is rotatably connected to the threaded rod (22).
2. The aircraft engine blade profile detection device according to claim 1, characterized in that: The data processing and analysis module uses a threshold processing method for defect detection, and its specific formula is: Where, (I(x,y)) represents the grayscale value of the image at ((x,y)); (T) is the set threshold.
3. The aircraft engine blade profile detection device according to claim 1, characterized in that: The comparison and evaluation module uses a convolutional neural network algorithm to assist in comparison and evaluation, and the specific steps are as follows: Data preparation and preprocessing: Collect a large amount of aero-engine blade surface image data, including normal blades and blades with various defects, and annotate the collected image data to identify whether there are defects in each image and the type and location of the defects; Network model construction: Design a suitable CNN architecture according to task requirements, including the configuration and combination of convolutional layers, pooling layers, activation functions, and fully connected layer components, and set the initial values of weights and bias parameters in the network; Network training: Set training parameters, input preprocessed image data into CNN, calculate prediction results through forward propagation process, compare prediction results with real annotations, calculate loss value, and update parameters in the network through back propagation algorithm to reduce loss value, repeat forward propagation and back propagation process until the predetermined number of iterations no longer decreases significantly; Model evaluation and optimization: Use independent validation set data to evaluate the trained model and tune the model based on the evaluation results; Comparison and evaluation: The surface image of the aircraft engine blade to be inspected is input into the trained CNN model for defect detection. The detected defects are compared with the preset defect standards to determine the type and severity of the defects.
4. The aircraft engine blade profile detection device according to claim 1, characterized in that: An angle control motor (8) is fixedly mounted on the outside of the fixed block (6); a first rotating wheel (12) is provided at the output end of the angle control motor (8); the first rotating wheel (12) is rotationally connected to the fixed block (6); a belt (13) is externally transmission-connected to the first rotating wheel (12); and the belt (13) is transmission-connected to the second rotating wheel (14).
5. The aircraft engine blade profile detection device according to claim 1, characterized in that: The exterior of the fixed block (6) is fixedly connected to a rotating ring (5), the exterior of the rotating ring (5) is rotatably connected to a detection platform (1), and the exterior of the rotating ring (5) is fixedly connected to an annular rack (4).
6. The aircraft engine blade profile detection device according to claim 5, characterized in that: A position control motor (15) is fixedly mounted on the outside of the detection platform (1), and a first rotating shaft (16) is provided at the output end of the position control motor (15). The first rotating shaft (16) and the detection platform (1) are rotationally connected. A first gear (17) is fixedly mounted on the outside of the first rotating shaft (16), and the first gear (17) and the annular rack (4) are meshingly connected.
7. The aircraft engine blade profile detection device according to claim 5, characterized in that: The outside of the detection platform (1) is symmetrically fixedly connected with a fixing column (2), the outside of the fixing column (2) is provided with a blade body (3), and the outside of the fixing column (2) is symmetrically fixedly installed with a blade fixing control motor (23).
8. The aircraft engine blade profile detection device according to claim 7, characterized in that: The output end of the blade fixing control motor (23) is provided with a third rotating shaft (24), the third rotating shaft (24) is rotationally connected to the fixing column (2), and the outside of the third rotating shaft (24) is fixedly connected with a blade fixing plate (25).
Citation Information
Patent Citations
A device for detecting the profile of hollow blades of hot end turbine of aircraft engine
CN113176085B
Cited By
Aero-engine turbine surface defect detection equipment
CN119757667A
