Static test method and system for overall drive generator of airplane, medium and equipment

Abstract

The present application discloses a static test method and system, medium, and device for an aircraft integrated drive generator. The method includes: immersing the aircraft integrated drive generator in a cleaning agent container filled with a cleaning agent, and then collecting in real time the image of the cleaning agent liquid level in the cleaning agent container to identify whether there are bubbles in the image of the cleaning agent liquid level. When there are no bubbles in the image of the cleaning agent liquid level, the static test result of the aircraft integrated drive generator is qualified; when there are bubbles in the image of the cleaning agent liquid level, combining the time interval between the generation of bubbles and the initial position points where the bubbles are generated to obtain the static test result of the aircraft integrated drive generator. Among them, the static test result includes qualified and unqualified. When the static test result is unqualified, the static test result also includes the parts of the unqualified aircraft integrated drive generator. It can achieve efficient and accurate detection of the sealing performance in the static test of the integrated drive generator, providing a reliable basis for the quality assurance of the equipment.

Description

Technical Field

[0001] This application relates to the field of civil aviation technology, and in particular to a static testing method, system, medium, and equipment for an aircraft integral drive generator. Background Technology

[0002] As a core power supply device in aviation, the sealing performance of the Integrated Drive Generator (IDG) directly determines the reliability, safety, and service life of the equipment. In the IDG maintenance and assembly process, static testing is a crucial step in verifying its sealing performance before delivery. The core purpose of this test is to simulate the static operating conditions of the IDG after installation (i.e., a closed environment in a non-operating state). By testing the isolation effect between its internal and external environments, the effectiveness of the following key sealing components is determined, specifically: 1. Dynamic sealing between the input shaft and the housing (achieved by sealing components; due to relative movement between the input shaft and the housing, sealing performance under movement must be ensured); 2. Assembly quality of static sealing rings at points such as electrical connectors and pipe interfaces (static sealing is achieved through fixed sealing rings; verification of the integrity and proper assembly of the sealing rings is required); 3. Integrity of the housing body and welded / connected parts (detecting for defects such as cracks and pinholes that could lead to media leakage). Traditional integrated drive generator sealing tests rely heavily on manual visual inspection, resulting in low accuracy. Summary of the Invention

[0003] In view of this, this application provides a static testing method, system, medium, and equipment for an aircraft integral drive generator, which can achieve efficient and accurate testing of the sealing performance in the static testing of the integral drive generator, providing a reliable basis for equipment quality assurance.

[0004] According to one aspect of this application, a static testing method for an aircraft integral drive generator is provided, the method comprising:

[0005] After immersing the aircraft's entire drive generator into a cleaning agent container, images of the cleaning agent level in the container are captured in real time.

[0006] Based on the cleaning agent liquid surface images collected within a preset time period, it is determined whether there are air bubbles in the cleaning agent liquid surface images. When there are no air bubbles in the cleaning agent liquid surface images, the static test result of the aircraft's overall drive generator is qualified.

[0007] When there are bubbles in the cleaning agent liquid surface image, the interval time of bubble generation and the initial position point of bubble generation are extracted. Combining the interval time of bubble generation and the initial position point of bubble generation, the static test result of the aircraft's overall drive generator is obtained. The static test result includes qualified and unqualified. When the static test result is unqualified, the static test result also includes the unqualified parts of the aircraft's overall drive generator.

[0008] According to another aspect of this application, a static testing system for an aircraft integral drive generator is provided, the system comprising:

[0009] The image acquisition module is used to acquire images of the cleaning agent level in the container in real time after the aircraft's overall drive generator is immersed in a cleaning agent container containing cleaning agent.

[0010] The bubble detection module is used to identify whether there are bubbles in the cleaning agent liquid surface image based on the cleaning agent liquid surface image collected within a preset time period. When there are no bubbles in the cleaning agent liquid surface image, the static test result of the aircraft's overall drive generator is qualified.

[0011] The bubble and position joint judgment module is used to extract the interval time of bubble generation and locate the initial position point of bubble generation when there are bubbles in the cleaning agent liquid surface image. Combining the interval time of bubble generation and the initial position point of bubble generation, the static test result of the aircraft's overall drive generator is obtained. The static test result includes qualified and unqualified. When the static test result is unqualified, the static test result also includes the unqualified parts of the aircraft's overall drive generator.

[0012] According to another aspect of this application, a medium is provided having a computer program stored thereon, which, when executed by a processor, implements the above-described static test method for the overall aircraft drive generator.

[0013] According to another aspect of this application, an apparatus is provided, including a medium, a processor, and a computer program stored on the medium and executable on the processor, wherein the processor executes the program to implement the above-described static test method for the overall aircraft drive generator.

[0014] With the above technical solution, a static test method, system, medium, and device for an aircraft integrated drive generator provided by this application immerse the aircraft integrated drive generator into a cleaning agent container filled with a cleaning agent, and then collect real-time images of the cleaning agent liquid level in the cleaning agent container to identify whether there are bubbles in the cleaning agent liquid level image. When there are no bubbles in the cleaning agent liquid level image, the static test result of the aircraft integrated drive generator is qualified; when there are bubbles in the cleaning agent liquid level image, the static test result of the aircraft integrated drive generator is obtained by combining the time interval between the generation of bubbles and the initial position points where the bubbles are generated. The static test result includes qualified and unqualified. When the static test result is unqualified, the static test result also includes the parts of the unqualified aircraft integrated drive generator. It can achieve efficient and accurate detection of the sealing performance in the static test of the integrated drive generator, providing a reliable basis for the quality assurance of the equipment.

[0015] The above description is only an overview of the technical solution of this application. In order to be able to understand the technical means of this application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features, and advantages of this application more obvious and understandable, the specific embodiments of this application are specifically listed below. Brief Description of the Drawings

[0016] The drawings described herein are used to provide a further understanding of this application and constitute a part of this application. The schematic embodiments of this application and their descriptions are used to explain this application and do not constitute an improper limitation to this application. In the drawings:

[0017] Figure 1 It shows a schematic flow chart of a static test method for an aircraft integrated drive generator provided by an embodiment of this application;

[0018] Figure 2 It shows a schematic flow chart of a combined judgment method for bubbles and positions in the static test of an aircraft integrated drive generator provided by an embodiment of this application;

[0019] Figure 3 It shows a schematic flow chart of another static test method for an aircraft integrated drive generator provided by an embodiment of this application;

[0020] Figure 4 It shows a schematic structural diagram of a static test system for an aircraft integrated drive generator provided by an embodiment of this application. Detailed Description of the Embodiments

[0021] In the following, this application will be described in detail with reference to the drawings and in combination with embodiments. It should be noted that, without conflict, the embodiments in this application and the features in the embodiments can be combined with each other.

[0022] This embodiment provides a static testing method for an aircraft's overall drive generator, such as... Figure 1 As shown, the method includes:

[0023] Step 101: After immersing the aircraft's overall drive generator into a cleaning agent container, a real-time image of the cleaning agent level in the container is acquired.

[0024] In existing technologies, the specific implementation process of IDG static testing is as follows:

[0025] 1. Test preparation: Connect the assembled IDG to the compressed air source and use the adjustment device to maintain the internal air pressure at the preset value of the simulated installation conditions (usually a specific pressure that matches the actual operating environment of the aircraft) to simulate its working pressure environment on the equipment.

[0026] 2. Immersion test: Immerse the entire IDG in the specified cleaning agent (which has both cleaning and visual inspection functions; the liquid transparency must meet the requirements for bubble observation) and keep it in a static state;

[0027] 3. Manual observation and judgment: The tester shines a flashlight on the immersion area and continuously observes whether air bubbles rise to the surface during the 20-minute settling period. If air bubbles are found, it is determined that there is a sealing defect, and the IDG needs to be disassembled, re-inspected and reassembled, and then the above test procedure is repeated; if no air bubbles are generated within 20 minutes, it is determined that the static seal is qualified.

[0028] However, existing technologies have the following significant limitations:

[0029] 1. Unclear leak location: Manual inspection can only observe the bubbles rising to the surface, and it is impossible to accurately trace the initial location of the bubbles (such as being unable to distinguish whether the bubbles come from the input shaft seal, the electrical plug seal, or the housing crack). This results in the need to check multiple parts one by one during subsequent repairs, increasing the cost of ineffective disassembly.

[0030] 2. Minor defects are easily missed: For parts with minor sealing problems, the intervals between bubble formation are long (it may take several minutes for one bubble to appear) and the bubble size is small. During long-term manual observation, it is easy to miss the test due to fatigue and distraction of the test personnel. Such minor leaks may expand in a short period of time after IDG installation, causing equipment failure or return to the factory for repair.

[0031] 3. Subjectivity of judgment criteria: Different testers have different experiences in judging whether "bubbles constitute effective leakage" and "whether the number of bubbles meets the standard", lacking a unified quantitative standard, resulting in poor consistency of test results;

[0032] 4. Low efficiency: Testers need to be on duty for 20 minutes at a time, and cannot carry out other work at the same time. This results in high labor costs and a high frequency of repeated testing (due to missed detections or misjudgments), which prolongs the overall production cycle.

[0033] Therefore, the existing IDG static testing method, which relies on manual observation, can hardly meet the requirements of aviation maintenance companies for testing accuracy, efficiency and standardization. There is an urgent need for an automated and intelligent testing solution to overcome the above-mentioned technical bottlenecks.

[0034] In the above embodiments of this application, the liquid surface state of IDG after immersion in cleaning agent can be monitored in real time using a high-definition image acquisition device (such as an underwater camera). Combined with image recognition algorithms (such as dynamic target detection and edge feature extraction), the instant of bubble generation can be captured, and the data can be classified according to two key dimensions:

[0035] Time pattern dimension: based on the interval time of bubble generation (e.g., periodic occurrence is "regular", random occurrence is "irregular");

[0036] Spatial location dimension: The initial point of bubble generation is located by image coordinates and matched with the structural model of IDG (such as the input shaft sealing area, electrical plug installation area, shell welding area, etc.) to achieve "precise part correspondence".

[0037] Specifically, when acquiring images of the cleaning agent liquid surface using high-definition image acquisition equipment, noise reduction processing can be performed to address interference factors such as turbidity and bubble reflection that may occur during image acquisition, thereby improving the accuracy of subsequent extraction. Specifically, a transparent tempered glass container can be used, with dimensions such as 2m × 1.5m × 1m (length × width × height). An anti-surge baffle is installed inside the transparent tempered glass container to stabilize the liquid surface. A removable acrylic observation window is designed on one side of the transparent tempered glass container for easy camera maintenance. The inner wall of the transparent tempered glass container can be coated with an acid and alkali resistant coating (such as polytetrafluoroethylene) to adapt to the chemical properties of the cleaning agent. Then, the IDG is slowly and vertically immersed using a robotic arm to avoid violent disturbance; after immersion, it can be left to stand for 30 seconds to allow the liquid surface to stabilize.

[0038] Next, an image acquisition system can be built, with hardware configurations such as:

[0039] Industrial camera: A 20-megapixel CMOS camera (such as Baslerac A2440-75uc) can be selected, with a frame rate of 75fps, and a wide-angle lens (focal length 8mm) to cover the entire liquid surface.

[0040] Light source: A surround LED cold light source (wavelength 450nm blue light) can be installed, tilted at 30° to enhance the contrast of the bubble edge (the bubble will form a dark ring due to refraction).

[0041] Fixed bracket: The camera (high-definition image acquisition device) can be vertically installed 50cm directly above the container, and the position can be calibrated by adjusting the bracket with a three-axis to ensure that the field of view covers the entire liquid surface.

[0042] Set a trigger synchronization action: that is, trigger the camera to start shooting when IDG is immersed to ensure that the timestamp is synchronized with the cleaning process.

[0043] Next, real-time image processing and bubble detection begin. Specifically, after acquiring the image of the cleaning agent surface, preprocessing can be performed, including:

[0044] 1. Filtering and noise reduction: Use Gaussian filtering to smooth the ripples on the liquid surface.

[0045] 2. Dynamic threshold segmentation: Adaptive Otsu algorithm is used to segment the bubble region, eliminating interference from uneven lighting.

[0046] 3. Morphological operation: The expansion-corrosion combination closes the bubble edge and eliminates misjudgment of fine cracks.

[0047] Next, bubbles can be extracted from the cleaning agent surface image. Specifically, OpenCV's findContours function can be used to detect connected components and filter candidate bubbles with an area greater than 5 pixels². Impurities (such as oil stains) are then excluded based on the bubble's roundness (formula: 4π·area / perimeter²) and edge gradient direction. The bubble's position and size are then marked on the UI, and its quantity variation curve is statistically analyzed.

[0048] Furthermore, a combination of polarizing filters and blue light sources can be used to suppress specular reflections, thereby reducing interference from liquid surface reflections. In cases where tiny bubbles (<0.2mm) are missed, super-resolution reconstruction (SRGAN model) can be used to enhance image details.

[0049] Therefore, by following the steps described above, accurate real-time monitoring of air bubbles on the liquid surface during IDG cleaning can be achieved, thereby improving cleaning quality and automation levels.

[0050] Optionally, the aircraft integral drive generator includes an oil vent and a vent. In step 101, immersing the aircraft integral drive generator in a cleaning agent container includes:

[0051] Step 1011: After assembling the aircraft integral drive generator, seal the oil passage of the aircraft integral drive generator, connect the vent to the air source, and adjust the air source pressure to the preset range.

[0052] In the above embodiments of this application, the oil passage of the assembled IDG is sealed, leaving only the vent hole connected to an air source. The air pressure is adjusted to 16-18 psi. Subsequently, the IDG is immersed in the cleaning agent and left to stand for 20 minutes. During the standing period, image recognition technology is used to capture real-time images of the instantaneous bubble formation, recording the location and timing of bubble formation. Alternatively, the entire drive generator is fully assembled, and the oil passage of the generator is sealed with a plug, leaving only a vent hole for connecting to a pressurized air source. The air source is connected to the IDG, and the pressure applied by the air source is maintained between 16-18 psi before the IDG is placed in the cleaning agent. The IDG is then immersed in the cleaning agent for 20 minutes.

[0053] Furthermore, to ensure consistent testing conditions, the following two key parameters can also be controlled:

[0054] Air source pressure stability: The air pressure input to IDG is strictly controlled at 16-18 psi through a pressure regulating valve, with a fluctuation range not exceeding ±0.5 psi, simulating the actual operating conditions of the aircraft.

[0055] Cleaning agent environment: Standardize the concentration, temperature (e.g., 25±2℃) and settling depth of the cleaning agent to avoid changes in bubble characteristics due to environmental differences (e.g., excessively high temperature may generate additional bubbles).

[0056] Step 102: Based on the cleaning agent liquid surface images collected within a preset time period, identify whether there are air bubbles in the cleaning agent liquid surface images. When there are no air bubbles in the cleaning agent liquid surface images, the static test result of the aircraft's overall drive generator is qualified.

[0057] Step 103: When there are bubbles in the cleaning agent liquid surface image, extract the interval time of bubble generation and locate the initial position point of bubble generation. Combine the interval time of bubble generation and the initial position point of bubble generation to obtain the static test result of the aircraft overall drive generator. The static test result includes qualified and unqualified. When the static test result is unqualified, the static test result also includes the unqualified parts of the aircraft overall drive generator.

[0058] Next, if no bubbles are generated, the static test result of the aircraft's overall drive generator is qualified. If there are bubbles, the specific static test result is further determined by combining the time pattern of bubble generation and the initial position electricity. Specifically, if the bubble interval time is uniform and the initial position points meet the preset range, it indicates that the generator has stable ventilation and normal structure, and the static test result is qualified. On the contrary, if the bubble interval time is chaotic or the initial position points deviate from the preset range, the result is unqualified. At this time, by analyzing the position where the bubbles abnormally occur, the internal fault location of the generator can be accurately positioned, such as blockage of the ventilation pipeline, loose sealing or structural damage, etc., providing a clear direction for subsequent maintenance, effectively improving the maintenance efficiency and accuracy, and reducing the maintenance cost. By extracting the interval time of bubble generation and the initial position points in the cleaning agent liquid level image within a preset time period, the generation pattern of bubbles and the fault source can be accurately tracked. Interval time analysis can reveal the chemical reaction rate between the cleaning agent and the component surface or the mechanical friction frequency, assisting in judging whether the cleaning process meets the standard; initial position positioning can quickly lock the high-pollution areas or structural defect positions of the components, such as the aging position of the sealing ring or the gap with oil stain accumulation, guiding targeted maintenance. This technology realizes the transformation from passive cleaning to active quality control, reduces the error of manual visual inspection, improves the cleaning efficiency and component reliability, and provides data support for cleaning process optimization.

[0059] Optionally, in step 103, extracting the interval time of bubble generation and positioning the initial position point of bubble generation specifically includes:

[0060] Step 1031, perform Gaussian filtering on the collected cleaning agent liquid level image, and use the improved YOLOv11 network to locate bubbles in the Gaussian-filtered cleaning agent liquid level image.

[0061] Step 1032, continuously track the bubbles in each frame of the cleaning agent liquid level image through the ByteTrack tracking network, and associate the same bubble in adjacent frames according to the continuous tracking bubble movement trajectory to obtain the independent bubble sequence of the bubbles.

[0062] Step 1033, for multiple independent bubble sequences, determine the bubbles corresponding to the first-occurring independent bubble sequence, and locate the generation position of the bubbles as the initial position point of bubble generation.

[0063] Step 1034, record the interval time between the bubbles corresponding to the previous independent bubble sequence and the bubbles corresponding to the adjacent next independent bubble sequence as the interval time of bubble generation.

[0064] In the above embodiments of this application, the acquired raw cleaning agent liquid surface image may contain liquid surface ripples or noise interference. Gaussian filtering can be used to perform weighted smoothing of the image using a convolution kernel (such as 5×5) to suppress high-frequency noise (such as small fluctuations in the liquid surface) while preserving bubble edge features. Specific steps include:

[0065] 1. Filter parameter settings: A Gaussian kernel with σ=1.5 can be selected to balance the noise reduction and edge preservation effects. In the processed image, bubbles appear as bright circular areas, and background noise is significantly reduced.

[0066] Based on the Gaussian filtered image, an improved YOLOv11 network (such as adding the attention mechanism CBAM) can be used to locate bubbles. The network input size can be 640×640, and the output includes the bounding box (x,y,w,h) of the bubble and the confidence score.

[0067] For example, to improve the training process of YOLOv11 networks:

[0068] 1. Data labeling: The positions of bubbles in 500 images are manually labeled to form a training set.

[0069] 2. Model optimization: Embed the CBAM module in the YOLOv11 Backbone to improve the detection accuracy of tiny bubbles (diameter < 5 pixels).

[0070] 3. Inference results: The model outputs the coordinates of the bubbles in each frame of the image, such as bubble A (120,80,10,10) detected in frame 1.

[0071] Next, ByteTrack is used for bubble tracking and trajectory association, specifically:

[0072] Input consecutive frames (e.g., 30fps) into ByteTrack, and use Kalman filtering to predict bubble positions. The IOU matching threshold can be set to 0.3 to associate the same bubble in adjacent frames. An example output is shown below.

[0073] The trajectory of bubble A in frames 1 to 5 is [(120,80),(125,82),(130,85),...].

[0074] Next, based on the trajectory ID, independent bubble sequences (such as bubble A sequence, bubble B sequence) are generated. For each independent sequence (such as bubble A), the coordinates of its first appearance (such as (120, 80) in frame 1) are taken as the initial position point. The time difference of the first appearance of adjacent bubbles is recorded (such as bubble A at t1 = 0.1s, bubble B at t2 = 0.3s, with an interval Δt = 0.2s), and the time difference of all independent sequences is calculated.

[0075] To address this, Gaussian filtering for noise reduction and improved YOLOv11's precise positioning, combined with ByteTrack's trajectory correlation, can accurately track the bubble generation pattern. For example, during a cleaning operation, the system located a region in the gearbox sealing ring area (initial position point) where dense bubbles were continuously generated, with the average interval shortened to 0.15 seconds, indicating the presence of stubborn oil stains in this area, requiring an extended cleaning time or adjustment of the cleaning agent concentration.

[0076] Optionally, the aircraft's overall drive generator includes a vent, which is connected to an air source. In step 1033, for multiple independent bubble sequences, the bubble corresponding to the first occurrence of the independent bubble sequence is determined, and the location of the bubble's generation is positioned as the initial location point of bubble generation. Specifically, this includes:

[0077] Step 10331: Determine whether the bubble motion trajectory corresponding to the independent bubble sequence conforms to the liquid flow law.

[0078] Step 10332: If the bubble movement trajectory conforms to the liquid flow law, then for multiple independent bubble sequences, determine the bubble corresponding to the first independent bubble sequence and locate the bubble generation position as the initial position point of bubble generation.

[0079] Step 10333: If the bubble movement trajectory does not conform to the liquid flow law, after stabilizing the pressure of the gas source, the aircraft's overall drive generator is immersed in the cleaning agent container containing the cleaning agent again, and the step of re-collecting the cleaning agent liquid level image of the cleaning agent container in real time is performed.

[0080] In the above embodiments of this application, when the aircraft's overall drive generator is immersed in a container filled with cleaning agent and ventilated through it by a stable air source, the cleaning agent will form a certain flow pattern. Typically, the flow of liquid is influenced by various factors, such as the shape of the container, the viscosity of the liquid, the location of the vent, and the gas flow rate. Generally, under the influence of gravity and gas disturbance, the liquid will diffuse from near the vent outwards, forming a general flow direction.

[0081] Specifically, for example, the cleaning agent container is rectangular in shape, and the aircraft's overall drive generator vents air from the center of the container's bottom. Based on the fundamental principles of liquid flow, it can be predicted that the bubbles generally move upwards from the center of the container's bottom and then diffuse outwards.

[0082] High-speed cameras and other equipment are used to capture real-time images of the cleaning agent surface in the container. Image processing technology is used to identify the position of each bubble and record its coordinates at different times.

[0083] Analyze the position coordinates of each bubble and calculate the change in bubble position and direction between adjacent time points. For example, at time t1, the position coordinates of a bubble are (x1, y1), and at time t2, its position coordinates become (x2, y2). Then, the displacement vector of the bubble during this time is d = (x2 - x1, y2 - y1).

[0084] Based on the previously predicted liquid flow direction, determine whether the bubble displacement direction matches it. If the displacement direction of most bubbles is consistent with the expected liquid flow direction, and the displacement amount is within a reasonable range, then the continuous change in bubble position can be considered to conform to the laws of liquid flow.

[0085] For example, in the aforementioned cuboid container, if a bubble's displacement direction is consistently upward and outward from the bottom center of the container for several consecutive moments, and the amount of displacement does not change suddenly or drastically, then the bubble's trajectory conforms to the laws of liquid flow. Conversely, if a bubble's displacement direction is completely opposite to the expected liquid flow direction, or if the amount of displacement suddenly becomes very large, far exceeding the range that normal liquid flow can drive, then the bubble's trajectory does not conform to the laws of liquid flow.

[0086] If the bubble's trajectory shows a continuous change in position that conforms to the laws of liquid flow, it is considered a valid bubble. If the bubble's trajectory shows a continuous change in position that does not conform to the laws of liquid flow, the gas source pressure is re-stabilized. This may be because unstable gas source pressure causes abnormal gas flow in the liquid, thus affecting the bubble's trajectory. After re-stabilizing the gas source pressure, the aircraft's entire drive generator is re-immersed in a container of cleaning agent, and real-time images of the cleaning agent surface are acquired again. The above judgment process is repeated until a valid bubble conforming to the laws of liquid flow is found.

[0087] In summary, by analyzing the trajectory of bubble movement and comparing it with the expected direction of liquid flow, it is possible to determine whether the continuous change in bubble position conforms to the law of liquid flow, and to take appropriate action based on the judgment results.

[0088] Optionally, such as Figure 2 As shown, the cleaning agent container contains a pressure gauge. The aircraft's integrated drive generator includes assembled and unassembled parts. The assembled parts include the area between the input shaft and the seal, and the electrical plug and the sealing ring. In step 103, by combining the interval time of bubble generation and the initial position of bubble generation, the static test results of the aircraft's integrated drive generator are obtained, including:

[0089] Step 1035: Determine the time pattern of bubble generation based on the interval between bubble generation.

[0090] Step 1036: When the timing of bubble generation is regular and the initial location of bubble generation is an assembly part, the static test result of the aircraft's overall drive generator is unqualified.

[0091] Step 1037: When the timing of bubble generation is regular and the initial location of bubble generation is a non-assembly part, determine the static test result of the aircraft's overall drive generator based on the pressure gauge display.

[0092] Step 1038: When the timing of bubble generation is irregular, continue to determine whether bubbles are generated in the latter half of the preset time period. Based on the results of the continued determination and the display results of the pressure gauge, jointly determine the static test results of the aircraft's overall drive generator.

[0093] Step 1039: When the static test result is unqualified, the location of the unqualified aircraft overall drive generator is obtained by combining the initial position point of the bubble generation.

[0094] In the above embodiments of this application, the time pattern is determined based on the interval between bubble generation, that is, by observing whether the time interval between bubble emergence is stable. If the bubbles emerge continuously at a relatively fixed and predictable time interval, that is, the time interval fluctuates little and exhibits periodic characteristics, then it is regular; if the time interval between bubble emergence is irregular, sometimes dense and sometimes sparse, without a stable period, then it is irregular.

[0095] Next, by combining the time pattern and the location of the bubble, we can make a joint judgment. Specifically, based on the location of the bubble (between the input shaft and the seal, at the electrical plug / sealing ring, and non-assembly parts) and the time pattern (regular / irregular), the bubbles can be divided into six categories. Then, a "layered processing" mechanism can be designed for these six categories of bubbles to avoid blind disassembly. Specifically:

[0096] For bubbles that are "regular and located in moving parts (i.e. assembly parts, such as between the input shaft and the seal)," it proves that the static test result of the aircraft's overall drive generator is unqualified. At the same time, "non-disassembly repair" (such as rotary lubrication) should be tried first to reduce component wear.

[0097] For air bubbles that are "regular and located in static sealing parts (i.e. assembly parts, such as electrical plug sealing rings)," it proves that the static test result of the aircraft's overall drive generator is unqualified and is directly judged as "assembly or aging problem," and the disassembly process is initiated.

[0098] For bubbles that are "irregular or regular and located in non-assembly areas", a "time observation window" (the second half of 20 minutes) and "pressure-assisted judgment" can be introduced to eliminate false faults and avoid ineffective operations.

[0099] The core of this logic is the "principle of minimal intervention," which means that through a step-by-step process of "observation-verification-repair," the accuracy of detection is ensured while minimizing secondary damage to IDG components.

[0100] Furthermore, the bubble patterns can be categorized into six types, as follows:

[0101] The first type: Bubbles are generated regularly between the input shaft and the seal.

[0102] The second type: Bubbles that appear regularly at the time of the electrical plug or other sealing ring locations.

[0103] The third type: Bubbles that are generated in a time-regular manner in non-assembled parts (such as the outer shell).

[0104] The fourth type: Irregularly generated bubbles at the input shaft and the seal.

[0105] The fifth type: Bubbles that appear irregularly at different times are found at the plug or other sealing ring locations.

[0106] The sixth type: Bubbles that appear out of order in unassembled areas (such as the outer shell).

[0107] If the first scenario occurs for the first time: it is likely due to incomplete lubrication and misfitting of the input shaft and seal during assembly. First, use the IDG manual rocker arm to rotate the input shaft to ensure sufficient lubrication between the input shaft and the seal, then repeat the pressure soaking operation; if the first scenario occurs again, disassemble and inspect the seal, reassemble it, and then retest.

[0108] If the second situation occurs: it may be that the electrical plug or sealing ring at the location of the bubble is aging or has an assembly problem, and it needs to be disassembled and reassembled and tested again.

[0109] If a third situation occurs, it may be due to damage to the casing or gaps in certain areas that allow cleaning agent to seep in, creating the illusion of an unstable seal. In this case, a comprehensive judgment needs to be made in conjunction with subsequent digital pressure gauge readings.

[0110] If the fourth scenario occurs, there are three possibilities:

[0111] Possibility 1: The cleaning agent seeped into the gaps in non-essential areas, requiring further assessment using a digital pressure gauge.

[0112] Possible scenario 2: The input shaft and seal may not have been fully lubricated and properly fitted during assembly. First, use the IDG manual rocker arm to rotate the input shaft to ensure sufficient lubrication between the input shaft and the seal, and then repeat the pressure soaking operation. If the first situation occurs again, disassemble and inspect the seal and reassemble it, and then retest.

[0113] Possibility 3: If bubbles appear for a short period of time, but no bubbles appear in the latter half of the 20-minute period, then there is no problem.

[0114] If the fifth situation occurs: there may be an installation gap at the plug or other sealing ring locations. Continue to observe the situation. If no bubbles are generated in the second half of the 20-minute period, it can be determined that there is no problem; if bubbles are generated, it is necessary to make a comprehensive judgment in conjunction with the pressure gauge.

[0115] If the sixth situation occurs: it may be caused by external gaps. Continue to observe. If no bubbles are produced in the second half of the 20-minute period, it can be judged that there is no problem. If bubbles continue to emerge, it is necessary to make a comprehensive judgment in conjunction with the pressure gauge.

[0116] Optionally, the aircraft integral drive generator includes a vent, which is connected to an air source. In step 1037, the static test results of the aircraft integral drive generator are determined based on the pressure gauge readings, including:

[0117] Step 10371: If the pressure gauge reading is stable, the static test result of the aircraft's overall drive generator is qualified.

[0118] Step 10372: If the pressure gauge reading is unstable, then after stabilizing the pressure of the gas source, continue to collect images of the cleaning agent liquid level in the cleaning agent container in real time until the timing of bubble generation is regular and the initial location of bubble generation is a non-assembly part. Then, determine the static test result of the aircraft's overall drive generator based on the pressure gauge reading.

[0119] In the above embodiments of this application, such as Figure 3 As shown, the corresponding non-assembled parts (i.e. Figure 3 If the pressure gauge does not change when bubbles are generated in the non-warning zone (in the air supply area), that is, if the pressure is stable, then the static test result of the aircraft's overall drive generator is qualified. If the pressure gauge shows that the pressure is unstable, check whether the air source pressure is stable, and re-stabilize the air source pressure before making a judgment.

[0120] Optionally, in step 1038, based on the results of the continued assessment and the pressure gauge readings, the static test results of the aircraft's overall drive generator are jointly assessed, including:

[0121] Step 10381: When bubbles are generated in the latter half of the preset time period and the pressure gauge reading shows a downward trend, the static test result of the aircraft's overall drive generator is unqualified.

[0122] Step 10382: When no bubbles are generated in the second half of the preset time period and the display result of the pressure gauge is unstable, after stabilizing the pressure of the gas source again, continue to collect the image of the cleaning agent liquid level in the cleaning agent container in real time until the time pattern of bubble generation is irregular and no bubbles are generated in the second half of the preset time period, and the static test result of the aircraft integrated drive generator is qualified.

[0123] In the above embodiments of the present application, when bubbles are detected and the pressure gauge shows a pressure drop, it is determined that there is a leak in the IDG, and it needs to be disassembled and repaired and then retested, that is, the static test result of the aircraft integrated drive generator is unqualified. When no bubbles are detected but the pressure gauge shows pressure fluctuations (unstable), after stabilizing the gas source pressure again, continue to monitor. If there are no bubbles in the second half of 20 minutes, it is determined to be qualified.

[0124] Furthermore, a collaborative monitoring network of "gas source pressure sensor + image acquisition module + time timer" can be constructed. Specifically, the pressure sensor collects the internal air pressure of the IDG in real time (accuracy ±0.1 psi) and records the pressure change curve; the image module synchronously records the time, position and frequency of bubble generation; the control system correlates and analyzes the data of the three to form a three-dimensional data set of "pressure change trend - bubble characteristics - time node" to provide multi-dimensional basis for fault judgment. For example, when "irregular bubbles" are detected, if the pressure curve is stable and the bubbles disappear in the second half of 20 minutes, it is determined as "non-leakage"; if the pressure curve drops synchronously, it is directly determined as "seal failure". In particular, combined with the display result of the pressure gauge, it can be divided into three cases. For example:

[0125] The first case: Bubbles emerge and the pressure gauge changes. Immediately determine it as a leak, disassemble, reassemble and retest in combination with the photo of the leak point.

[0126] The second case: No bubbles emerge but the pressure gauge changes. It may be that the pressure of the gas supply source is unstable. After stabilizing the gas source pressure again, continue to monitor the bubbles. If no bubbles emerge in the second half of 20 minutes, it can be determined that the static test is qualified.

[0127] The third case: Bubbles emerge but the pressure gauge does not change. It needs to be judged in combination with time. If no bubbles emerge in the second half of 20 minutes, it can be determined that the static test is qualified.

[0128] That is, when bubbles are detected and the pressure gauge shows a pressure drop, it is determined that there is a leak in the IDG, and it needs to be disassembled and repaired and then retested; when no bubbles are detected but the pressure gauge shows pressure fluctuations, after stabilizing the gas source pressure again, continue to monitor. If there are no bubbles in the second half of 20 minutes, it is determined to be qualified; when bubbles are detected but the pressure gauge shows stable pressure, if the bubbles disappear in the second half of 20 minutes, it is determined to be qualified; if they continue to be generated, further judgment is made in combination with the bubble type.

[0129] Furthermore, during the test, pressure sensors collected real-time data on the internal air pressure of the aircraft's Integrated Drive Generator (IDG), while the image acquisition module simultaneously recorded the formation of air bubbles. When air bubbles were observed emerging, and the pressure gauge showed a change in pressure, this indicated a gas leak inside the IDG.

[0130] For example, the pressure sensor recorded a drop in internal air pressure from its normal value, while the image acquisition module showed bubbles emerging from specific locations (such as the input shaft and seal, electrical connector, or sealing ring) during the corresponding time period. This indicates that gas leaked from inside the IDG into the cleaning agent, forming bubbles. This simultaneous bubble formation and pressure change directly reflects a problem with the IDG's sealing performance, leading to gas leakage. Therefore, the static test result for the aircraft's integrated drive generator was deemed unqualified. After determining the specific leak location based on the leak photos, the IDG needs to be disassembled, reassembled, and retested to resolve the sealing issue.

[0131] If no bubbles are generated in the latter half of the preset time period, and the pressure gauge reading is unstable, the gas supply pressure is re-stabilized, and the static test results are evaluated. In other words, if no bubbles emerge during the test, but the pressure gauge shows pressure changes, this is likely due to unstable gas supply pressure. Normally, if the IDG seal is good and there is no gas leakage, no bubbles will be generated, and pressure changes may be caused by fluctuations in the gas supply pressure.

[0132] For example, the pressure sensor records a short-term rise or fall in the internal air pressure of the IDG, but the image acquisition module does not capture any bubbles. In this case, it is necessary to re-stabilize the air source pressure to restore it to a normal, stable state. After stabilizing the air source pressure, real-time images of the cleaning agent level in the cleaning agent container are continued, and the timing of bubble formation is again determined based on the interval between bubble formations. If the timing of bubble formation is irregular, it is further determined whether bubbles are formed in the latter half of a preset time period (e.g., 20 minutes). If no bubbles are formed in the latter half of the preset time period, it indicates that the previous pressure changes were caused by unstable air source pressure, not a leak in the IDG itself, and the static test result of the aircraft's overall drive generator is qualified.

[0133] If bubbles are generated in the latter half of the preset time period and the pressure gauge reading remains stable, the static test result should be determined in conjunction with the time interval. In other words, if bubbles emerge but the pressure gauge shows no change in pressure, further judgment based on the time interval is necessary. This is because no pressure change indicates relatively stable internal pressure within the IDG, suggesting that the bubble generation may be temporary or non-continuous.

[0134] For example, in the initial stage of the test, the image acquisition module shows that a small number of bubbles emerge from non-assembled parts (such as the external housing), but the internal air pressure of the IDG recorded by the pressure sensor always remains within the normal range. At this time, observe the latter half of the preset time period (such as 20 minutes). If no bubbles are generated in the latter half, it indicates that the bubble emergence may be transient, for example, due to changes in the surface tension of the cleaning agent or external interference, rather than a continuous leakage problem of the IDG. Then, the static test result of the aircraft's integrated drive generator is qualified.

[0135] Specifically, when six types of bubbles are identified, the following operations can be performed respectively:

[0136] Type 1 (regular, between the input shaft and the seal): When it first appears, lubricate the input shaft by rotating it with the IDG manual rocker arm and then repeat the test; if it appears again, disassemble the seal for inspection and reassembly;

[0137] Type 2 (regular, at the electrical plug / seal ring): Directly disassemble the corresponding part, check the status of the seal ring and reassemble it before retesting;

[0138] Type 3 (regular, non-assembled parts): Make a comprehensive judgment by combining the pressure change data of the digital pressure gauge;

[0139] Type 4 (irregular, between the input shaft and the seal): If no bubbles appear in the latter half of 20 minutes, it is judged as qualified; if they continue to appear, refer to the handling of Type 1 or make a judgment in combination with the pressure gauge;

[0140] Type 5 (irregular, at the electrical plug / seal ring): If no bubbles appear in the latter half of 20 minutes, it is judged as qualified; if they continue to appear, make a judgment in combination with the pressure gauge;

[0141] Type 6 (irregular, non-assembled parts): If no bubbles appear in the latter half of 20 minutes, it is judged as qualified; if they continue to appear, make a judgment in combination with the pressure gauge.

[0142] Therefore, the existing operation method that relies on manual observation for the static test of the integrated drive generator (IDG) exposes the following significant drawbacks in practical applications:

[0143] 1. The leak point location accuracy is insufficient, increasing the maintenance cost. Manual observation can only detect the phenomenon of bubble floating, but cannot accurately lock the initial generation position of the bubbles. Due to the complex structure of the IDG, the bubbles will displace in the liquid due to buoyancy, and it is difficult for the test personnel to distinguish whether the bubbles come from the dynamic seal area between the input shaft and the seal, the static seal point of the electrical plug / seal ring, or the crack of the housing body. This ambiguity leads to the need to disassemble and check multiple parts one by one during subsequent maintenance, not only prolonging the maintenance cycle but also potentially causing secondary damage to the components due to repeated disassembly, increasing the ineffective cost.

[0144] 2. Minor leaks are easily missed, posing potential safety hazards. For areas with minor sealing defects (such as localized wear on the seal ring or micro-cracks in the casing), air bubbles may appear only every few minutes or even ten minutes, and their size may be tiny (less than 1mm in diameter). During a 20-minute continuous observation period, testers are prone to missing these leaks due to visual fatigue and fluctuations in attention. After installation in the IDG system, such minor leaks may gradually expand with changes in operating conditions (such as vibration or increased temperature), leading to malfunctions such as oil leaks and pressure imbalances, and even affecting the normal operation of the equipment, posing safety risks.

[0145] 3. Subjective judgment criteria lead to inconsistent test results. Current technology lacks unified quantitative judgment standards, and the "presence," "quantity," and "frequency" of bubbles rely entirely on the experience of testers. For example, some personnel believe that "one or two occasional bubbles are negligible," while others require "absolutely no bubbles," resulting in contradictory "pass" and "fail" judgments for the same IDG unit. This subjectivity reduces the authority of the test and may lead to misjudgments causing defective products to enter the spare parts warehouse or qualified products to be repeatedly disassembled, resulting in resource waste.

[0146] 4. High labor costs and low testing efficiency: During the testing process, personnel must be on duty at all times and focus on observing the liquid level, and cannot carry out other work within 20 minutes, resulting in low utilization of human resources. At the same time, the high rate of repeated testing due to missed detections or misjudgments further prolongs the IDG's production cycle, making it difficult to meet the efficiency requirements of large-scale maintenance or production.

[0147] 5. Poor environmental adaptability and highly susceptible to external interference. The accuracy of manual observation is affected by factors such as ambient light (e.g., uneven lighting in the workshop) and the transparency of the cleaning agent (e.g., turbidity or impurities in the liquid). For example, excessively strong light may cause bubbles to reflect light and be difficult to identify, while turbidity in the cleaning agent directly hinders bubble observation, further increasing the probability of misjudgment or missed detection.

[0148] The aforementioned shortcomings make it difficult for existing technologies to meet the high precision, high efficiency, and high reliability requirements of IDG sealing performance testing in high-end fields such as aviation, and urgently need to be addressed through technological innovation.

[0149] By applying the technical solution of this embodiment, the assembly of the overall drive generator is first completed, the oil passage is sealed and the air source is connected, and the pressure is adjusted to 16-18 psi. The IDG is immersed in the cleaning agent, and simultaneously the image recognition system is activated to detect bubbles and capture images in real time within 20 minutes. The images are preprocessed and classified, and operations are performed according to the corresponding processing scheme based on different bubble types. The static test results of the IDG are judged based on the changes in the digital pressure gauge readings and a joint judgment standard. Through the above method, efficient and accurate detection of the sealing performance in the static testing of the overall drive generator can be achieved, providing a reliable basis for equipment quality assurance.

[0150] In one specific embodiment, such as Figure 3 As shown, after IDG assembly, the oil vent should be plugged to ensure a sealed internal state. Gas is introduced through the vent to achieve a pressure of 15-18 psi, creating a stable pressure environment for subsequent testing. The IDG is then immersed in a cleaning agent for 20 minutes to allow for observation using image recognition technology. Image recognition technology is used to observe the IDG and monitor for the generation of air bubbles.

[0151] Bubble generation: The location of bubble generation is captured by the image. If the bubbles appear in areas prone to leakage, such as seals or oil windows, there is a high probability of a leak. If the bubbles appear in non-warning areas (possibly external gaps), further judgment is needed based on the pressure gauge readings.

[0152] No bubbles were generated: The static test results were initially deemed acceptable, but final confirmation was still required based on the changes in the pressure gauge.

[0153] When bubbles are generated and the test is in a non-warning zone, or when no bubbles are generated but the pressure gauge readings are necessary to ensure test accuracy, the results should be observed.

[0154] Unstable pressure: If the pressure gauge shows unstable pressure, it indicates a problem with the gas source pressure, which may affect the accuracy of the test results. In this case, the gas source needs to be checked. If the gas source pressure is unstable, the test should be repeated after stabilizing the gas source.

[0155] Stable pressure and no bubbles (or stable pressure combined with bubbles in non-warning zones): If the pressure gauge shows stable pressure and no bubbles are generated during the preset time period (such as the second half of 20 minutes), the static test result of the aircraft's overall drive generator can be judged as qualified.

[0156] If the static test result is unqualified, the IDG is reassembled according to the location of the leak shown in the image, and then the above test process is repeated until the test result is qualified.

[0157] By following the steps above, the static performance of the aircraft's overall drive generator can be tested relatively accurately, and it can be determined whether there are any problems such as leaks that affect normal operation.

[0158] By applying the technical solution of this embodiment, compared with the prior art, the following beneficial effects are achieved:

[0159] 1. Leak location is improved from "fuzzy" to "precise," achieving a breakthrough in fault tracing. In existing technologies, workers can only visually observe bubbles rising to the surface. However, these bubbles shift due to buoyancy in the cleaning agent, making it difficult to trace the original leak point (such as the specific location of the input shaft seal, electrical connector seal, or housing crack). This leads to inefficient subsequent disassembly requiring inspection of multiple parts one by one. This invention uses image recognition technology to capture the image the instant a bubble appears, directly locking its initial position (such as between the input shaft and the seal, or at the electrical connector). Combined with classification rules, it precisely associates the leak location with specific components, reducing leak location errors to the component level, minimizing unnecessary disassembly, and improving the targeted nature of repairs.

[0160] 2. Microbubble detection shifts from "human oversight" to "intelligent capture," reducing quality risks. In existing technologies, the interval between microbubble formations can be several minutes or even more than ten minutes. During continuous observation for 20 minutes, workers are prone to missing these bubbles due to fatigue and distraction. Furthermore, such micro-leaks can expand rapidly after IDG installation, causing the equipment to be returned to the factory prematurely. The embodiments described in this application utilize image recognition algorithms for high-frequency scanning of the liquid surface, accurately capturing and recording even bubbles with long intervals and small volumes. This solves the "blind spot" problem of manual observation, reducing quality risks caused by missed detections from the source.

[0161] 3. The judgment criteria have shifted from "experience-based" to "standardized," avoiding human error. Existing technologies rely on the experience of staff, leading to inconsistent standards among personnel regarding whether bubbles constitute a leak and when disassembly is necessary (e.g., some consider a small number of bubbles negligible, while others require absolute absence of bubbles), resulting in poor test result stability. This invention categorizes bubbles into six types based on "time pattern" (regular / irregular) and "location of occurrence" (input shaft seal, electrical plug / sealing ring, housing, etc.), and establishes clear handling rules for each type of bubble (e.g., lubricate and retest the first occurrence of the first type, disassemble directly for the second type, etc.). This forms a quantifiable and reproducible standard process, reducing the impact of human experience differences on the results.

[0162] 4. The testing process shifts from "labor-intensive" to "automated collaboration," improving work efficiency. Existing technologies require staff to be on duty and observe the entire process for 20 minutes, during which time they cannot perform other work, resulting in high labor costs and low efficiency. The embodiments of this application use an image recognition system to automatically complete bubble detection, classification, and recording, issuing prompts only when manual intervention is needed (such as rotating the input shaft or disassembling components), allowing staff to perform multiple tasks simultaneously.

[0163] 5. Fault diagnosis shifts from "single-based" to "multi-dimensional collaboration," improving the reliability of conclusions. Existing technologies rely solely on the presence or absence of bubbles, failing to distinguish whether bubbles are caused by poor sealing, gas source fluctuations, or cleaning agent seepage into non-critical areas. This application innovatively combines two dimensions: "bubble type" and "pressure change." When bubbles are generated, the stability of the internal air pressure of the IDG is monitored simultaneously. By observing combinations such as "bubbling + pressure drop," "bubbling + stable pressure," and "no bubbling + pressure fluctuation," the nature of the fault (e.g., leakage, unstable gas source, or false bubbles) can be accurately determined. For example, in the case of "bubbling but no change in pressure gauge," combining the time dimension (whether it stops in the latter half of 20 minutes) can eliminate interference from "seepage into non-critical areas," improving accuracy.

[0164] Furthermore, as Figure 1 In terms of specific implementation, this application provides a static testing system for an aircraft's overall drive generator, such as... Figure 4 As shown, the system includes:

[0165] The image acquisition module 201 is used to acquire images of the cleaning agent level in the cleaning agent container in real time after the aircraft's overall drive generator is immersed in the cleaning agent container containing the cleaning agent.

[0166] The bubble detection module 202 is used to identify whether there are bubbles in the cleaning agent liquid surface image based on the cleaning agent liquid surface image collected within a preset time period. When there are no bubbles in the cleaning agent liquid surface image, the static test result of the aircraft's overall drive generator is qualified.

[0167] The bubble and position joint judgment module 203 is used to extract the interval time of bubble generation and locate the initial position point of bubble generation when there are bubbles in the cleaning agent liquid surface image. By combining the interval time of bubble generation and the initial position point of bubble generation, the static test result of the aircraft overall drive generator is obtained. The static test result includes qualified and unqualified. When the static test result is unqualified, the static test result also includes the unqualified parts of the aircraft overall drive generator.

[0168] It should be noted that other corresponding descriptions of the functional units involved in the static testing system for an integrated aircraft drive generator provided in this application embodiment can be found in the following references. Figures 1 to 2 The corresponding descriptions in the method will not be repeated here.

[0169] Based on the above, Figures 1 to 2 Accordingly, this application also provides a medium on which a computer program is stored, which, when executed by a processor, implements the above-described method. Figures 1 to 2 The static test method for the aircraft's overall drive generator is shown.

[0170] Based on this understanding, the technical solution of this application can be embodied in the form of a software product, which can be stored in a non-volatile medium (such as a CD-ROM, USB flash drive, or portable hard drive) and includes several instructions to cause a device (such as a personal computer, server, or network device) to execute the methods described in the various implementation scenarios of this application.

[0171] Based on the above, Figures 1 to 2 The method shown, and Figure 4 To achieve the above objectives, the virtual system embodiment shown in this application also provides a device, which may be a personal computer, server, network device, etc. This device includes a medium and a processor; the medium is used to store a computer program; the processor is used to execute the computer program to achieve the above-described objectives. Figures 1 to 2 The static test method for the aircraft's overall drive generator is shown.

[0172] Optionally, the device may also include a user interface, a network interface, a camera, radio frequency (RF) circuitry, sensors, audio circuitry, a Wi-Fi module, etc. The user interface may include a display screen, input units such as a keyboard, etc., and optional user interfaces may also include USB interfaces, card reader interfaces, etc. The network interface may optionally include standard wired interfaces, wireless interfaces (such as Bluetooth interfaces, Wi-Fi interfaces), etc.

[0173] Those skilled in the art will understand that the device structure provided in this embodiment does not constitute a limitation on the device, and may include more or fewer components, or combine certain components, or have different component arrangements.

[0174] The medium may also include an operating system and a network communication module. The operating system is a program that manages and stores the device's hardware and software resources, supporting the operation of information processing programs and other software and / or programs. The network communication module is used to enable communication between the various components within the medium, as well as communication with other hardware and software within the physical device.

[0175] Through the description of the above embodiments, those skilled in the art can clearly understand that the present application can be implemented by means of software plus a necessary general hardware platform, or can also be implemented by hardware. After immersing the aircraft integrated drive generator into a cleaning agent container filled with a cleaning agent, the cleaning agent liquid level image of the cleaning agent container is collected in real time, and whether there are bubbles in the cleaning agent liquid level image is identified. When there are no bubbles in the cleaning agent liquid level image, the static test result of the aircraft integrated drive generator is qualified; when there are bubbles in the cleaning agent liquid level image, combining the interval time of bubble generation and the initial position points of bubble generation, the static test result of the aircraft integrated drive generator is obtained. Among them, the static test result includes qualified and unqualified. When the static test result is unqualified, the static test result also includes the parts of the unqualified aircraft integrated drive generator. It can achieve efficient and accurate detection of the sealing performance in the static test of the integrated drive generator, providing a reliable basis for the quality guarantee of the equipment.

[0176] Those skilled in the art can understand that the attached drawings are only schematic diagrams of a preferred implementation scenario, and the modules or processes in the attached drawings are not necessarily required for implementing the present application. Those skilled in the art can understand that the modules in the system in the implementation scenario can be distributed in the system of the implementation scenario according to the description of the implementation scenario, or can be correspondingly changed and located in one or more systems different from the present implementation scenario. The modules in the above implementation scenario can be combined into one module, or can be further split into multiple sub-modules.

[0177] The above serial numbers of the present application are only for description and do not represent the advantages or disadvantages of the implementation scenarios. The above-disclosed are only several specific implementation scenarios of the present application. However, the present application is not limited thereto, and any changes made by those skilled in the art should fall within the protection scope of the present application.

Claims

1. A static testing method for an aircraft's overall drive generator, characterized in that, The method includes: After immersing the aircraft's entire drive generator into a cleaning agent container, images of the cleaning agent level in the container are captured in real time. Based on the cleaning agent liquid surface images collected within a preset time period, it is determined whether there are air bubbles in the cleaning agent liquid surface images. When there are no air bubbles in the cleaning agent liquid surface images, the static test result of the aircraft's overall drive generator is qualified. When there are bubbles in the cleaning agent liquid surface image, extract the interval time of bubble generation and locate the initial position point of bubble generation. The cleaning agent container is equipped with a pressure gauge. The parts of the aircraft's overall drive generator include assembled parts and unassembled parts. The assembled parts include the electrical plug, the sealing ring, and the part between the input shaft and the sealing part. Based on the interval between bubble formation, determine the temporal pattern of bubble formation; When the timing of bubble generation is regular and the initial location of bubble generation is an assembly point, the static test result of the aircraft's overall drive generator is unqualified. When the timing of bubble generation is regular and the initial location of bubble generation is a non-assembly part, the static test results of the aircraft's overall drive generator can be judged based on the pressure gauge readings. When the timing of bubble generation is irregular, continue to determine whether bubbles are generated in the latter half of the preset time period. Based on the results of the continued determination and the pressure gauge readings, jointly determine the static test results of the aircraft's overall drive generator. When the static test result is unqualified, the unqualified part of the aircraft's overall drive generator is obtained by combining the initial position point of the bubble generation. The static test result includes qualified and unqualified parts. When the static test result is unqualified, the static test result also includes the unqualified part of the aircraft's overall drive generator.

2. The method according to claim 1, characterized in that, The aircraft integrated drive generator includes a vent, which is connected to an air source. The determination of the static test results of the aircraft integrated drive generator based on the pressure gauge readings includes: If the pressure gauge reading is stable, the static test result of the aircraft's overall drive generator is qualified. If the pressure gauge reading is unstable, the process continues to collect images of the cleaning agent level in the cleaning agent container in real time after the pressure of the gas source is stabilized. This continues until the timing of bubble generation becomes regular and the initial location of bubble generation is a non-assembly part. Based on the pressure gauge reading, the static test results of the aircraft's overall drive generator are then determined.

3. The method according to claim 1, characterized in that, The aircraft integral drive generator includes an oil vent and a vent. Immersing the aircraft integral drive generator in a cleaning agent container filled with cleaning agent includes: After assembling the aircraft's integrated drive generator, seal the oil passage of the integrated drive generator, connect the vent to the air source, and adjust the air source pressure to the preset range.

4. The method according to claim 3, characterized in that, The static test results of the aircraft's overall drive generator are jointly determined based on the results of the further assessment and the pressure gauge readings, including: When bubbles are generated in the latter half of the preset time period and the pressure gauge reading shows a downward trend, the static test result of the aircraft's overall drive generator is unqualified. When there are no bubbles generated in the second half of the preset time period and the display result of the pressure gauge is unstable, the step of continuously collecting the cleaning agent liquid level image of the cleaning agent container in real time after stabilizing the pressure of the gas source again is carried out until the time pattern of bubble generation is irregular and there are no bubbles generated in the second half of the preset time period, and the static test result of the aircraft integrated drive generator is qualified.

5. The method according to claim 1, characterized in that, The extraction of the interval time of bubble generation and the positioning of the initial position point of bubble generation include: Performing Gaussian filtering on the collected cleaning agent liquid level image, and using the improved YOLOv11 network to locate bubbles in the Gaussian-filtered cleaning agent liquid level image; Continuously tracking the bubbles in each frame of the cleaning agent liquid level image through the ByteTrack tracking network, and associating the same bubble in adjacent frames according to the continuous tracking bubble movement trajectory to obtain the independent bubble sequence of the bubbles; For multiple independent bubble sequences, determining the bubble corresponding to the first-occurring independent bubble sequence, and positioning the generation position of the bubble as the initial position point of bubble generation; Recording the interval time between the bubble corresponding to the previous independent bubble sequence and the bubble corresponding to the adjacent next independent bubble sequence as the interval time of bubble generation.

6. The method according to claim 5, characterized in that, The aircraft integrated drive generator includes a ventilation hole, and the ventilation hole is connected to a gas source. The determining the bubble corresponding to the first-occurring independent bubble sequence for multiple independent bubble sequences and positioning the generation position of the bubble as the initial position point of bubble generation includes: Judging whether the bubble movement trajectory corresponding to the independent bubble sequence conforms to the liquid flow law; If the bubble movement trajectory conforms to the liquid flow law, then for multiple independent bubble sequences, determining the bubble corresponding to the first-occurring independent bubble sequence, and positioning the generation position of the bubble as the initial position point of bubble generation; If the bubble movement trajectory does not conform to the liquid flow law, after stabilizing the pressure of the gas source again, the aircraft integrated drive generator is immersed in the cleaning agent container filled with cleaning agent again, and the step of re-real-time collecting the cleaning agent liquid level image of the cleaning agent container is performed.

7. A static testing system for an aircraft integral drive generator, characterized in that, The system includes: An image acquisition module, configured to immerse the aircraft integrated drive generator in the cleaning agent container filled with cleaning agent and then collect the cleaning agent liquid level image of the cleaning agent container in real time; A bubble judgment module, configured to identify whether there are bubbles in the cleaning agent liquid level image based on the cleaning agent liquid level image collected within the preset time period. When there are no bubbles in the cleaning agent liquid level image, the static test result of the aircraft integrated drive generator is qualified; The bubble and position joint judgment module is used to extract the interval time of bubble generation and locate the initial position point of bubble generation when bubbles are present in the cleaning agent liquid surface image. The cleaning agent container contains a pressure gauge. The aircraft's integrated drive generator includes assembled and unassembled parts. Assembled parts include the electrical plug, sealing ring, and the area between the input shaft and the seal. Based on the bubble generation interval time, the module judges the time pattern of bubble generation. When the bubble generation time pattern is regular and the initial position point of bubble generation is an assembled part, the static test result of the aircraft's integrated drive generator is unqualified. When the location point is a non-assembly part, the static test result of the aircraft's overall drive generator is determined based on the pressure gauge display. When the timing of bubble generation is irregular, it is further determined whether bubbles are generated in the latter half of the preset time period. Based on the results of this further determination and the pressure gauge display, the static test result of the aircraft's overall drive generator is jointly determined. When the static test result is unqualified, the location of the unqualified aircraft's overall drive generator is obtained by combining the initial location of bubble generation. The static test result includes both qualified and unqualified results. When the static test result is unqualified, the static test result also includes the location of the unqualified aircraft's overall drive generator.

8. A medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the method for static testing of the aircraft's overall drive generator as described in any one of claims 1 to 6.

9. An apparatus comprising a medium, a processor, and a computer program stored on the medium and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method for static testing of the aircraft integral drive generator as described in any one of claims 1 to 6.

Images