Full-automatic hole-probe detection device for aero-engine rotor blade
The fully automated borehole inspection device utilizes an integrated probe unit and an AI computing chip to automatically plan the guidance and acquire three-dimensional images in real time, solving the problems of low efficiency and insufficient accuracy in the inspection of aero-engine rotor blades, and achieving efficient and accurate blade damage detection.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Utility models(China)
- Current Assignee / Owner
- EASTERN AIRLINES TECHNIC CO LTD
- Filing Date
- 2025-07-31
- Publication Date
- 2026-07-21
AI Technical Summary
Existing aero-engine rotor blade inspection technologies suffer from low inspection efficiency, insufficient accuracy, and reliance on manual judgment, making it difficult to achieve rapid and accurate result analysis.
The fully automated borehole inspection device includes an integrated probe unit, a non-guideable rigid rod probe, a guideable flexible shaft probe, and dual objective lenses. Combined with a stepper motor and an AI computing chip, it automatically plans the guiding path, acquires and analyzes 3D images in real time, and achieves accurate inspection.
It significantly improves detection efficiency and accuracy, enabling rapid and accurate identification of blade damage in complex environments. It features high integration, strong adaptability, and supports both manual and automatic operation modes.
Smart Images
Figure CN224535825U_ABST
Abstract
Description
Technical Field
[0001] This utility model relates to the field of aero-engine testing technology, and in particular to a fully automatic borehole inspection device for aero-engine rotor blades. Background Technology
[0002] The operational safety and efficiency of aero-engines directly depend on the integrity of their components. Aero-engine rotor blades are among the most critical components; cracks, corrosion, and other damage on their surfaces directly affect engine performance and safety. Traditional borehole inspection relies primarily on manual operation, which is time-consuming, labor-intensive, prone to human error, and suffers from low efficiency and limited accuracy. While existing aero-engine rotor blade inspection technologies have incorporated some automation, they still have the following shortcomings in probe guidance, image analysis, and result output:
[0003] 1) Damage detection relies on manual judgment, making it difficult to achieve rapid and accurate result analysis.
[0004] 2) The detection efficiency is low and cannot meet the needs of large-scale rapid detection of complex structures such as engine rotor blades.
[0005] A search revealed Chinese Utility Model Patent Publication No. CN115507896A, which discloses a method and apparatus for detecting blade clearance and tip damage in turbine engines. This method combines and analyzes data from individual sensors in an array-type eddy current sensor array to assess blade defects and potential hazards. The specific steps are as follows: a. Actual detection: The array-type eddy current sensor array is placed on the outer shell of the turbine engine rotor blade under test. Each eddy current sensor is operated by a multi-channel array-type eddy current detector, which acquires the detection signal data from each sensor; b. Data analysis: The signal values detected by different eddy current sensors are compared and analyzed to assess the condition of the blade and determine its defects and potential hazards. This existing patent suffers from the problem that the sensors are placed on the outer shell, resulting in indirect data acquisition and potentially inaccurate detection.
[0006] How to achieve fully automated inspection of aero-engine rotor blades to improve inspection efficiency and accuracy has become a technical problem that needs to be solved. Utility Model Content
[0007] The purpose of this invention is to overcome the defects of the existing technology and provide a fully automatic borehole inspection device for aero-engine rotor blades.
[0008] The objective of this utility model can be achieved through the following technical solutions:
[0009] According to one aspect of the present invention, a fully automatic borehole inspection device for aero-engine rotor blades is provided. The device includes a probe integrated host and a borehole probe connected in sequence. The borehole probe includes a non-guideable rigid rod probe, a guideable flexible shaft probe, and a dual objective lens for acquiring three-dimensional image data of the target to be inspected, connected in sequence.
[0010] The dual objective lens is mounted at one end of the guideable flexible shaft probe;
[0011] The probe integrated unit has a stepper motor integrated inside its main unit;
[0012] The probe integrated machine host automatically plans the guiding path according to the preset detection target. The stepper motor is connected to the non-guideable rigid rod probe. The stepper motor drives the guideable flexible shaft probe to automatically adjust the direction and position of the dual objective lenses to align with the detection target.
[0013] The integrated probe unit is also connected to an external operation and control terminal.
[0014] Preferably, the guideable flexible shaft probe includes a steel wire assembly inside, and the stepper motor controls the guideable flexible shaft probe to complete the guidance control through the steel wire assembly.
[0015] More preferably, the wire assembly consists of four wires, which are respectively connected to the four corners of the guideable flexible shaft probe.
[0016] More preferably, there are two stepper motors, and the two diagonally opposite steel wires of the guideable flexible shaft probe are connected to the same stepper motor.
[0017] Preferably, the device further includes a probe fixing mechanism, through which the borehole probe is fixedly connected to the engine casing.
[0018] Preferably, the probe fixing mechanism is a rotary thread.
[0019] Preferably, both the non-guideable rigid probe and the guideable flexible shaft probe are no more than 6 mm.
[0020] Preferably, the probe integrated host includes a network card for data interaction with an external server.
[0021] Preferably, the device further includes a battery module, which is connected to the probe integrated machine host and the borehole probe.
[0022] More preferably, the probe integrated machine host and the operation and control terminal are connected via WIFI.
[0023] Compared with the prior art, the present invention has the following beneficial effects:
[0024] 1) The probe integrated machine host of this utility model automatically plans the guiding path, perceives the position and attitude of the probe inside the engine through the image information acquired by the probe in real time, and drives the probe to accurately align with the target of interest through the stepper motor, and automatically completes the acquisition of three-dimensional images of the blade, which significantly improves the detection efficiency and accuracy.
[0025] 2) The probe integrated machine of this utility model has built-in functional modules such as light source, stepper motor and AI computing chip. It can complete the inspection task independently without relying on external equipment. It has a high degree of integration, is easy to carry, and is flexible and convenient to operate on site.
[0026] 3) This utility model uses a stepper motor to control and adaptively adjust the direction of the dual objective lenses in real time to align with the target for image capture, and performs real-time intelligent analysis for damage detection, thereby improving the accuracy of detection.
[0027] 4) The device of this utility model transmits the real-time acquired images and detection results to an external operation and control terminal. The operation and control terminal can manually control the orientation and position of the probe. By combining automatic detection with manual control, the accuracy of acquisition and detection can be better guaranteed. Attached Figure Description
[0028] Figure 1 This is a schematic diagram of the structure of the detection device of this utility model;
[0029] Figure 2 This is a schematic diagram showing the connection between the detection device and the operation and control terminal of this utility model;
[0030] Figure 3 This is a schematic diagram of the detection process of the detection device of this utility model;
[0031] Figure 4 This is a schematic diagram illustrating the process of adjusting the orientation of the dual objective lenses to align with the detection target according to this utility model.
[0032] In the attached diagram, 1 is a dual objective lens, 2 is a directional flexible shaft probe, 3 is a non-directional rigid rod probe, 4 is a probe fixing mechanism, 5 is a stepper motor, 6 is the probe integrated unit main unit, 7 is a battery module, and 8 is an operation and control terminal. Detailed Implementation
[0033] The technical solutions of the present utility model will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some, not all, of the embodiments of the present utility model. Based on the embodiments of the present utility model, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present utility model.
[0034] This embodiment relates to a fully automated borehole inspection device for aero-engine rotor blades, such as... Figure 1 The device includes a battery module 7, a probe integrated unit 6, a stepper motor 5, and a borehole probe connected in sequence. The device also includes a probe fixing mechanism 4, which fixes the borehole probe to the engine casing. Optionally, the device is connected to the engine casing via a rotary thread.
[0035] The probe all-in-one main unit 6 integrates an AI computing chip, two stepper motors 5, a light source, a network card, etc., enabling independent operation without the need for additional external equipment. The borehole probe also connects to the probe all-in-one main unit 6 via a data cable. Images acquired by the borehole probe are output to the probe all-in-one main unit 6 in real time for analysis by the AI computing chip, automatically identifying damage characteristics and outputting detection results. For example... Figure 2 The probe-integrated main unit 6 interacts with an external operation and control terminal (such as a tablet computer) 8 via WiFi. For example, it can transmit the analysis results of images acquired by the borehole probe to the external operation and control terminal (such as a tablet computer) 8 for viewing. The operation and control terminal 8 serves as the user interface, allowing users to set detection targets, control commands, display real-time transmitted images, and view, store, and export detection results. The operation and control terminal 8 also provides a manual probe control function, allowing users to intervene at any time during automatic detection and switch to manual mode to complete specific operations. In manual mode, users send control commands for the orientation and position of the probe to the probe-integrated main unit 6 via the operation interface. The probe-integrated main unit 6 then controls the orientation and position of the guideable flexible shaft probe 2 according to the control commands.
[0036] The all-in-one host 6 also interacts with external servers (cloud servers) via network cards, such as data transmission and remote system maintenance, including remote upgrades and updates to damage recognition models.
[0037] The light source is a high-brightness source (e.g., LED light source), providing uniform illumination to meet the image acquisition needs of the complex environment inside the engine. Battery module 7 powers the entire device and mainly includes the stepper motor and other components within the probe integrated unit 6 (network card, light source, etc.). Battery module 7 is removable and replaceable; a single battery module can power the device for 2 hours, and it can also be powered by an external power source.
[0038] The borehole probe includes a non-guideable rigid rod probe 3, a guideable flexible shaft probe 2, and a dual objective lens 1 mounted on one end of the guideable flexible shaft probe 2, connected in sequence. The guideable flexible shaft probe 2 has a built-in wire assembly with four steel wires, which are connected to the four corners of the probe. Two diagonally opposite wires are connected to the same stepper motor. The two stepper motors on the probe's main unit 6 drive the wire assembly to achieve multi-degree-of-freedom steering of the guideable flexible shaft probe 2, enabling precise physical guidance control. The dual objective lens 1 is used to acquire three-dimensional (3D) images of the rotor blades, sensing their three-dimensional position and shape information. Both the non-guideable rigid rod probe 3 and the guideable flexible shaft probe 2 have diameters not exceeding 6 mm, suitable for the confined inspection space of an engine. The non-guideable rigid rod probe 3 and the guideable probe 2 are essentially a single unit; the guideable probe 2 can be oriented via wire control, and its diameter of no more than 6 mm is suitable for most engine borehole inspection scenarios.
[0039] AI computing chip automatic positioning and guidance: The AI computing chip combines 3D image information and Simultaneous Localization and Mapping (SLAM) technology to identify key parts inside the engine in real time (such as high-pressure turbine rotor blades, stator blades, blade roots and blade tips, etc.) and control the borehole probe to accurately align with the target of interest.
[0040] The AI computing chip measures the three-dimensional image data acquired by the dual objective lens 1, generates three-dimensional parameters of the damage (axial length, radial length, and depth), and constructs a digital model.
[0041] AI computing chips run deep learning models (such as YOLO or Mask R-CNN) to analyze the acquired images in real time, automatically identify cracks, corrosion and other damage features, and realize intelligent analysis and automatic damage detection of the images measured by the probe. The detection results include panoramic 3D images of each blade, damage measurement data, location markings and a complete detection report.
[0042] This embodiment also relates to a fully automated borehole inspection method for aero-engine rotor blades, such as... Figure 3 The method includes:
[0043] Step S1, Install the device: Fix the fully automatic borehole detection device to the engine borehole using the probe fixing mechanism 4;
[0044] Step S2, Start the device: After the probe all-in-one machine host 6 is powered on, it starts up. The tablet computer connects to the all-in-one machine host 6 via WIFI and displays real-time images, with an average latency of less than 200 milliseconds.
[0045] Step S3, Navigation and Positioning: The borescope probe acquires initial image information inside the engine, confirms the initial position of the dual objective lens 1, and automatically plans the guiding path based on the preset 3D position information inside the engine and the preset detection target (such as HPT blade, HPC blade or other areas) and adjusts the direction of the dual objective lens 1 to align with the detection target.
[0046] Step S4, Image Acquisition and Analysis: After the dual objective lens 1 is aligned with the target, the borescope probe captures a 3D image of the rotor blade, ensuring that the acquired borescope image captures at least a complete 3D image of the blade. The borescope image is then transmitted to the AI computing chip of the probe integrated host 6 via wired transmission. The AI computing chip of the probe integrated host 6 detects damage and performs measurements in real time. The AI computing chip runs a deep learning model (such as YOLO or Mask R-CNN) to analyze the acquired images in real time, automatically identifying cracks, corrosion, and other damage features, extracting edge features of the damage, and realizing intelligent analysis and automatic damage detection of the probe-measured images based on the distance between feature points detected in the 3D image. The detection results include a panoramic 3D image of each blade, damage measurement data, location annotations, and a complete detection report.
[0047] Step S5, Report Generation: The probe integrated machine host 6 automatically records the inspection results and generates a digital report, which is transmitted to the operation and control terminal for user viewing.
[0048] In step S3, the process of automatically adjusting the orientation of the dual objective lens 1 to align with the detection target using a visual servo control method includes: analyzing the image data acquired by the probe and adjusting the X-axis and Y-axis deflection of the borehole probe in real time to align the borehole probe with the detection target. For example... Figure 4 The specific steps are as follows:
[0049] Step S3-1: Real-time acquisition of image data inside the engine using the dual objective lenses of the borescope probe;
[0050] Step S3-2: Extract feature points of the target to be detected (such as the leading and trailing edges of the guide, the corners of the rotor blades, and the cooling control) from the acquired image data, and calculate the image error between the current feature point and the expected feature point; wherein the feature points include the edges, corners or pre-marked markers of the target to be detected.
[0051] Step S3-3: Use the image Jacobian matrix to map the image error into the probe's deflection motion command;
[0052] The image Jacobian matrix is calculated using the following formula:
[0053]
[0054] in,f For the camera focal length, ( x , y ) represents the coordinates of the feature point in the image.
[0055] Step S3-4: Adjust the X-axis and Y-axis deflection of the borehole probe according to the deflection motion command to align the borehole probe with the detection target;
[0056] The deflection motion command is generated using the following formula:
[0057]
[0058]
[0059] in, v Let be the deflection velocity vector of the probe. λ To control the gain coefficient, J + The pseudo-inverse of the image Jacobian matrix is... e The image error vector, S The image coordinates of the current feature point. S The image coordinates of the desired feature points;
[0060] Step S3-5: Repeat steps S3-1 to S3-4 until the image error is less than the preset threshold, and complete the alignment of the borehole probe with the detection target.
[0061] This invention utilizes image feedback information to generate control commands in real time, ensuring rapid response of the probe in complex environments and strong real-time performance. It can adapt to minute changes in the engine's internal environment, such as blade position deviations or temporary obstacles, demonstrating strong adaptability. Through visual servo control, the borehole probe can adjust its X and Y axis deflections in real time, precisely aligning with the detection target, achieving high-precision target alignment and improving detection accuracy.
[0062] The above description is merely a specific embodiment of this utility model, but the protection scope of this utility model is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this utility model, and these modifications or substitutions should all be covered within the protection scope of this utility model. Therefore, the protection scope of this utility model should be determined by the scope of the claims.
Claims
1. A fully automated borehole inspection device for aero-engine rotor blades, characterized in that, The device includes a probe integrated host (6) and a borehole probe connected in sequence. The borehole probe includes a non-guideable rigid rod probe (3), a guideable flexible shaft probe (2), and a dual objective lens (1) for acquiring three-dimensional image data of the target to be detected, connected in sequence. The dual objective lens (1) is mounted at one end of the guideable flexible shaft probe (2); The probe integrated host (6) integrates a stepper motor (5). The probe integrated host (6) automatically plans the guiding path according to the preset detection target. The stepper motor (5) is connected to the non-guideable rigid rod probe (3). The stepper motor drives the guideable flexible shaft probe (2) to automatically adjust the direction and position of the dual objective lens (1) to align with the detection target. The probe integrated host (6) is also connected to an external operation and control terminal (8).
2. The fully automatic borehole inspection device for aero-engine rotor blades according to claim 1, characterized in that, The guideable flexible shaft probe (2) includes a steel wire assembly inside, and the stepper motor (5) controls the guideable flexible shaft probe (2) through the steel wire assembly to complete the guidance control.
3. The fully automatic borehole inspection device for aero-engine rotor blades according to claim 2, characterized in that, The wire assembly consists of four wires, which are connected to the four corners of the guideable flexible shaft probe (2).
4. The fully automatic borehole inspection device for aero-engine rotor blades according to claim 3, characterized in that, There are two stepper motors (5), and the two diagonally opposite steel wires of the guideable flexible shaft probe (2) are connected to the same stepper motor.
5. The fully automatic borehole inspection device for aero-engine rotor blades according to claim 1, characterized in that, The device also includes a probe fixing mechanism (4), through which the borehole probe is fixedly connected to the engine casing.
6. The fully automatic borehole inspection device for aero-engine rotor blades according to claim 5, characterized in that, The probe fixing mechanism (4) is a rotating thread.
7. The fully automatic borehole inspection device for aero-engine rotor blades according to claim 1, characterized in that, Both the non-guideable rigid rod probe (3) and the guideable flexible shaft probe (2) are no more than 6 mm.
8. The fully automatic borehole inspection device for aero-engine rotor blades according to claim 1, characterized in that, The probe integrated host (6) includes a network card for data interaction with an external server.
9. A fully automatic borehole inspection device for aero-engine rotor blades according to claim 1, characterized in that, The device also includes a battery module (7), which is connected to the probe integrated host (6) and the borehole probe.
10. A fully automatic borehole inspection device for aero-engine rotor blades according to claim 1, characterized in that, The probe integrated host (6) and the operation and control terminal (8) are connected via Wi-Fi.