Method for detecting cleanliness of aero-engine liquid carrying part
Through the combination of extract liquid rinsing, filter membrane filtration, and image recognition model, the problem of inaccurate cleanliness evaluation of carrier liquid parts is solved, quantitative evaluation is achieved, and the engine safety and detection efficiency are improved.
Patent Information
- Application Number
- CN202510545826.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-04-28
- Publication Date
- 2025-07-11
AI Technical Summary
In the prior art, the cleanliness assessment of the liquid carrier system parts of aero engine lacks quantitative means, resulting in the residue of tiny particulate matter affecting engine performance and safety.
The parts were rinsed with extract solution and filtered with filter membrane to collect particulate matter. After drying, the photos were taken under the image amplification equipment. The particle size and quantity were identified in combination with the particle image recognition model, and the grade was evaluated according to the aircraft engine cleanliness standards.
实现了对载液零件清洁度的定量评价,提高了发动机的使用安全性和检测效率,确保了发动机的安全运行与长寿命。
Smart Images
Figure CN120293792A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of aero - engines, and particularly relates to a method for detecting the cleanliness of liquid - carrying parts of aero - engines. Background Art
[0002] As the core power device of an aircraft, an aero - engine needs to achieve long - term high - reliability operation under extreme working conditions (such as high temperature, high pressure, high speed, high load, etc.). The cleanliness of its liquid - carrying system (including subsystems such as fuel, lubricating oil, and hydraulic pressure) has a decisive impact on the safety and life of the engine. During the manufacturing, assembly, and maintenance processes of liquid - carrying system parts, the problem of particulate residue caused by insufficient cleanliness control means has long existed, becoming a key factor restricting the engine performance.
[0003] In traditional processes, liquid - carrying system parts are only judged as qualified by visually inspecting that there are no obvious contaminants on the surface, lacking quantitative evaluation means for cleanliness. Research shows that tiny particles that are not visible to the naked eye may remain on the surface of parts or in the system pipelines. During the operation of the engine, these particles will flow into key friction pairs (such as bearings, gears, pump bodies, etc.) along with the liquid - carrying medium, causing abnormal wear, local overheating, and even part failure. Summary of the Invention
[0004] Aiming at the problems existing in the prior art, the present invention provides a method for detecting the cleanliness of liquid - carrying parts of aero - engines, which can effectively and quantitatively evaluate whether the cleanliness of liquid - carrying parts meets the cleanliness level specified in relevant technical documents.
[0005] In order to solve the above - mentioned technical problems, the present invention is realized through the following technical solutions: A method for detecting the cleanliness of liquid - carrying parts of aero - engines, comprising: Placing the part to be detected in a particulate - free extraction device, flushing the part to be detected with an extraction liquid, and collecting the particulate matter on the part to be detected by filtration using a filter membrane to obtain a particulate - matter filter membrane of the part to be detected; Drying the particulate - matter filter membrane of the part to be detected, and taking a photo of the dried particulate - matter filter membrane of the part to be detected under an image magnification device to obtain an image of the particulate - matter filter membrane of the part to be detected; Identifying the particle size and the corresponding quantity of the particulate matter on the image of the particulate - matter filter membrane of the part to be detected; Evaluating the cleanliness level of the part to be detected according to the identified particle size and the corresponding quantity in combination with the cleanliness technical standard of liquid - carrying parts of aero - engines.
[0006] Further, before placing the part to be detected in a particulate - free extraction device, it further includes: Rinse the extraction equipment for placing the parts to be tested with the extraction liquid until a filter membrane free of particulate matter contamination is obtained.
[0007] Furthermore, the filter membrane used when rinsing the extraction equipment for placing the parts to be tested with the extraction liquid is the same as the filter membrane used for collecting the particulate matter on the parts to be tested.
[0008] Furthermore, identify the particle size and corresponding quantity of the particulate matter on the filter membrane image of the parts to be tested, specifically: Input the filter membrane image of the particulate matter of the parts to be tested into a pre-trained particulate matter image recognition model to output the particle size and corresponding quantity; the particulate matter image recognition model is obtained by training a neural network model with training data, and the training data includes a number of particulate matter filter membrane images marked with particle size and corresponding quantity labels.
[0009] Furthermore, the pore diameter of the filter membrane is not greater than 5 μm, and the filter membrane is compatible with the extraction liquid.
[0010] Furthermore, when drying the filter membrane of the particulate matter of the parts to be tested, dry the filter membrane in a non-blowing air oven.
[0011] Furthermore, the drying temperature of the non-blowing air oven is 60 °C to 90 °C, the temperature control accuracy is ±5 °C, and the drying time is 10 minutes to 15 minutes.
[0012] Furthermore, before drying the filter membrane in the non-blowing air oven, it also includes: Place the filter membrane in a pollution-free petri dish; Put the petri dish into the non-blowing air oven.
[0013] Furthermore, the image magnifying device is a microscope.
[0014] Furthermore, according to the identified particle size and corresponding quantity, combine with the cleanliness technical standard of the liquid-carrying parts of the aero-engine to evaluate the cleanliness level of the parts to be tested, specifically: The cleanliness technical standard of the liquid-carrying system parts of the aero-engine stipulates the particle size and corresponding quantity corresponding to different cleanliness levels under a set surface area; After converting the surface area of the parts to be tested to the set surface area, use the identified particle size and corresponding quantity for cleanliness level evaluation.
[0015] Compared with the prior art, the present invention has at least the following beneficial effects: A method for detecting the cleanliness of liquid-carrying parts of an aeroengine provided by the present invention places the parts to be detected in an extraction device free of particulate matter contamination, flushes the parts to be detected with an extraction liquid, and filters and collects the particulate matter on the parts to be detected using a filter membrane to obtain a particulate matter filter membrane of the parts to be detected; dries the particulate matter filter membrane of the parts to be detected, and takes a photo of the dried particulate matter filter membrane of the parts to be detected under an image magnification device to obtain an image of the particulate matter filter membrane of the parts to be detected; identifies the particle size and corresponding quantity of the particulate matter on the image of the particulate matter filter membrane of the parts to be detected; and evaluates the cleanliness level of the parts to be detected based on the identified particle size and corresponding quantity in combination with the cleanliness technical standard of the liquid-carrying parts of the aeroengine. Through the steps of extraction, filtration, drying, photographing, and image recognition, the particle size and corresponding quantity of the particulate matter on the parts to be detected can be accurately identified and counted, thereby realizing the quantitative evaluation of the cleanliness of the liquid-carrying parts, overcoming the problem of inaccurate cleanliness evaluation caused by only relying on visual inspection in the traditional process, and greatly improving the use safety of the aeroengine.
[0016] To make the above objects, features, and advantages of the present invention more obvious and understandable, the following specifically enumerates preferred embodiments and, in conjunction with the accompanying drawings, provides a detailed description as follows. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] To more clearly illustrate the technical solutions in the specific embodiments of the present invention, the following will briefly introduce the drawings required for use in the description of the specific embodiments. Obviously, the drawings in the following description are some embodiments of the present invention, and those of ordinary skill in the art can also obtain other drawings based on these drawings without creative efforts.
[0018] Figure 1 It is a flowchart of a method for detecting the cleanliness of liquid-carrying parts of an aeroengine according to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS
[0019] To make the objects, technical solutions, and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention.
[0020] As Figure 1 shown, the embodiments of the present invention provide a method for detecting the cleanliness of liquid-carrying parts of an aeroengine, mainly to achieve the quantitative evaluation of the cleanliness of the liquid-carrying parts and ensure the safe operation and long life of the engine. The method specifically includes the following steps: Step 1: Place the part to be inspected in an extraction device free of particulate contamination. Use the extraction liquid to rinse the part to be inspected, and filter and collect the particulates on the part to be inspected using a filter membrane to obtain a filter membrane of the particulates on the part to be inspected.
[0021] Specifically, first, ensure that the inside of the extraction device is in a state free of particulate contamination, which can be achieved by pre-cleaning the inside of the device with a high-purity solvent and drying it. At the same time, select a suitable extraction liquid, which should have good carrying capacity for particulates and should not cause corrosion or adverse effects on the part material. Then, place the liquid-carrying part of the aeroengine to be inspected in the extraction device to ensure that the part can fully contact the extraction liquid. Next, turn on the extraction device so that the extraction liquid flushes the surface and internal channels of the part at a certain flow rate and pressure to effectively remove the particulates attached to the part. It should be noted that parameters such as extraction time, flow rate, and pressure need to be adjusted according to the structure, material of the part, and the expected cleanliness requirements. After extraction, filter the extraction liquid containing particulates through a filter membrane. The selection of the filter membrane should ensure that its pore size can intercept all particulates that may affect the engine performance. During the filtration process, keep the surface of the filter membrane flat to avoid damage to the filter membrane or uneven distribution of particulates on the filter membrane.
[0022] Step 2: Dry the filter membrane of the particulates on the part to be inspected, and take a photo of the dried filter membrane of the particulates on the part to be inspected under an image magnification device to obtain an image of the filter membrane of the particulates on the part to be inspected.
[0023] Specifically, place the filtered filter membrane in an oven and dry it at an appropriate temperature (to avoid deformation of the filter membrane or change in the morphology of particulates caused by too high a temperature) until the filter membrane is completely dry and all residual extraction liquid is removed. Place the dried filter membrane under an image magnification device, adjust the magnification to be able to clearly display all particulates without distortion. Use a high-resolution camera to take a photo of the filter membrane to ensure that the image is clear and has a moderate contrast for subsequent particulate identification.
[0024] Step 3: Identify the particle size and corresponding quantity of the particulates on the image of the filter membrane of the particulates on the part to be inspected.
[0025] Specifically, use image processing software to process the taken filter membrane image, including removing background noise and enhancing contrast to accurately identify the particulates in the image. Through image analysis algorithms, automatically measure the particle size of each particulate and classify the particulates according to the preset particle size classification standard. At the same time, count the quantity of particulates of each particle size category.
[0026] Step 4: Evaluate the cleanliness level of the part to be inspected based on the identified particle size and corresponding quantity of the particulates, in combination with the cleanliness technical standard of the liquid-carrying part of the aeroengine.
[0027] Specifically, the identified particle sizes and corresponding quantities are compared with the cleanliness technical standard of the liquid-carrying parts of the aero-engine. It should be understood that the standard is usually formulated according to the engine type, usage conditions and performance requirements, and includes the particle quantity and particle size limits corresponding to different cleanliness levels.
[0028] According to the comparison result, the cleanliness level of the part to be detected is evaluated. If the particle content of the part is lower than or equal to the limit value of the corresponding cleanliness level, it is determined to be qualified; otherwise, further cleaning treatment or re-evaluation is required.
[0029] In one implementable manner, before placing the part to be detected in the extraction equipment without particle contamination, it further includes: rinsing the extraction equipment for placing the part to be detected with the extraction liquid until a filter membrane without particle contamination is obtained.
[0030] That is to say, before officially detecting the cleanliness of the part to be detected, it must be ensured that the extraction equipment itself is in a state without particle contamination. This is because any particles remaining inside the equipment may affect the accuracy of the final detection result. First, thoroughly rinse the extraction equipment with the same extraction liquid as used in the subsequent extraction process. During the rinsing process, it should be ensured that the extraction liquid can fully contact every corner of the equipment, including the inner wall, joints, filters and other parts where particles may be hidden. After rinsing, use a new filter membrane to filter the outlet of the extraction equipment to check the rinsing effect. The purpose is to capture and check the possible remaining particles. If any particles are observed on the filter membrane, it means that the inside of the equipment still does not meet the standard of no particle contamination, and the rinsing step needs to be repeated until a filter membrane without particle contamination is obtained.
[0031] It should be understood that after ensuring that there is no particle contamination inside the extraction equipment, the equipment should be dried to avoid the interference of the remaining moisture on the subsequent detection process.
[0032] Preferably, the filter membrane used when rinsing the extraction equipment for placing the part to be detected with the extraction liquid is the same as the filter membrane used for collecting the particles on the part to be detected, effectively avoiding the influence of the remaining particles inside the equipment and the filter membrane difference on the detection result.
[0033] In one implementable manner, the identification of the particle sizes and corresponding quantities on the particle filter membrane image of the part to be detected is specifically as follows: input the particle filter membrane image of the part to be detected into a pre-trained particle image recognition model, and output the particle sizes and corresponding quantities; the particle image recognition model is obtained by training a neural network model with training data, and the training data includes several particle filter membrane images marked with particle size and corresponding quantity labels.
[0034] Specifically, before particulate matter recognition, a pre-trained particulate matter image recognition model needs to be prepared. This model is trained using a neural network model in deep learning technology. To train the model, a large amount of training data needs to be collected. The training data includes a number of particulate matter filter membrane images marked with the particle size of particulate matter and the corresponding quantity labels. The training data images should cover particulate matter with different particle sizes, different quantities, and different distribution situations to ensure the generalization ability of the model.
[0035] The collected training data is input into the neural network model. By continuously adjusting the parameters and weights of the model, the model can accurately identify and count the particulate matter on the filter membrane image. After the model training is completed, an independent validation data set is needed to evaluate the performance of the model. By comparing the difference between the model prediction result and the true label, the accuracy of the model can be evaluated.
[0036] After the model validation and optimization are completed, the particulate matter filter membrane image of the part to be detected is input into the trained model. The model will automatically identify and count the particulate matter on the image, and output the results of the particle size of particulate matter and the corresponding quantity, realizing the rapid and accurate identification of the particle size and quantity of particulate matter, and greatly improving the detection efficiency and the accuracy of detection.
[0037] In this embodiment, the introduction and use of the particulate matter image recognition model ensure the accuracy of the cleanliness detection of the part to be detected, and also greatly improve the detection efficiency and automation degree, making the cleanliness detection of the liquid-carrying parts of aero-engines more efficient and accurate.
[0038] In an implementable manner, the pore size of the filter membrane is not greater than 5 μm, and the filter membrane is compatible with the extraction liquid.
[0039] Specifically, the pore size of the filter membrane is not greater than 5 μm to ensure that most of the tiny particulate matter that may affect the performance of aero-engines can be captured. At the same time, the filter membrane must be compatible with the extraction liquid, that is, the filter membrane material will not dissolve, expand or deform due to the chemical properties of the extraction liquid, thus affecting its filtering effect.
[0040] In an implementable manner, when drying the particulate matter filter membrane of the part to be detected, the filter membrane is dried in a non-blowing air oven.
[0041] Specifically, after extraction and filtration, the filter membrane is placed in a non-blowing air oven for drying. During the drying process of the non-blowing air oven, the air flow inside the oven is relatively stable, avoiding the problem of particulate matter falling off or redistributing on the filter membrane caused by air flow disturbance. At the same time, the non-blowing air oven can also provide a more uniform temperature distribution to ensure that the filter membrane is heated evenly during the drying process, avoiding damage or deformation of the filter membrane caused by local overheating.
[0042] Preferably, the drying temperature of the non-blast oven is 60°C to 90°C, and the temperature control accuracy is ±5°C. Within this temperature range, the filter membrane will not be damaged due to overheating, and at the same time, the moisture in the extraction liquid can volatilize rapidly. The temperature control accuracy of ±5°C ensures a stable temperature during the drying process, avoiding problems such as uneven drying of the filter membrane or changes in the morphology of the particulate matter caused by temperature fluctuations. The drying time is set to 10 minutes to 15 minutes. Within this time range, the residues on the filter membrane can volatilize sufficiently, while avoiding the aging or deformation of the filter membrane caused by too long drying time.
[0043] Preferably, before drying the filter membrane in the non-blast oven, it further includes: placing the filter membrane in a pollution-free petri dish and putting the petri dish into the non-blast oven.
[0044] In one implementable manner, the image magnification device is a microscope. Place the dried filter membrane on the stage of the microscope, adjust the magnification and focal length of the microscope so that the particulate matter on the filter membrane is clearly visible. Then, use the camera attached to the microscope or an external high-resolution camera to take a picture of the filter membrane to obtain a high-definition image of the particulate matter filter membrane of the part to be detected.
[0045] In one implementable manner, according to the identified particle size and corresponding quantity of the particulate matter, the cleanliness level of the part to be detected is evaluated in combination with the cleanliness technical standard of the liquid-carrying parts of the aero-engine. Specifically: the cleanliness technical standard of the liquid-carrying system parts of the aero-engine stipulates the particle size and corresponding quantity corresponding to different cleanliness levels under a set surface area; after converting the surface area of the part to be detected to the set surface area, the identified particle size and corresponding quantity are used for cleanliness level evaluation.
[0046] Specifically, the cleanliness technical standard of the liquid-carrying system parts of the aero-engine details the particle size range and corresponding quantity corresponding to different cleanliness levels, and these regulations are based on a set surface area. Since the surface area of the part to be detected may be different from the set surface area in the standard, it is necessary to convert the surface area of the part to be detected to the set surface area. According to the converted surface area, the identified particle size and corresponding quantity are adjusted accordingly, and the particle quantity is scaled according to the proportion of the surface area to ensure consistency when comparing with the data in the standard. Compare the adjusted particle size and corresponding quantity with the different cleanliness levels specified in the standard to determine the cleanliness level of the part to be detected.
[0047] In the present invention, terms such as "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.
[0048] Finally, it should be noted that the above-described embodiments are only specific embodiments of the present invention, used to illustrate the technical solutions of the present invention, rather than limiting it. The protection scope of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: any person skilled in the art within the technical scope disclosed by the present invention can still modify the technical solutions recorded in the foregoing embodiments or can easily think of changes, or make equivalent replacements for some of the technical features; and these modifications, changes, or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.
Claims
1. A method for detecting the cleanliness of liquid-carrying parts of an aero-engine, characterized in that Including: Place the part to be detected in an extraction device free of particulate matter contamination, rinse the part to be detected with an extraction liquid, and filter and collect the particulate matter on the part to be detected using a filter membrane to obtain a filter membrane of the particulate matter on the part to be detected. Dry the filter membrane of the particulate matter on the part to be detected, and take a photo of the dried filter membrane of the particulate matter on the part to be detected under an image magnification device to obtain an image of the filter membrane of the particulate matter on the part to be detected. Identify the particle size and corresponding quantity of the particulate matter on the image of the filter membrane of the particulate matter on the part to be detected. According to the identified particle size and corresponding quantity, evaluate the cleanliness level of the part to be detected in combination with the cleanliness technical standard of the liquid-carrying parts of the aero-engine.
2. The method for detecting the cleanliness of a liquid-carrying part of an aero-engine according to claim 1, wherein Before placing the part to be detected in an extraction device free of particulate matter contamination, it further includes: Rinse the extraction device for placing the part to be detected with an extraction liquid until a filter membrane free of particulate matter contamination is obtained.
3. A method for detecting the cleanliness of liquid-carrying parts of an aeroengine according to claim 2, characterized in that, The filter membrane used for rinsing the extraction device for placing the part to be detected with an extraction liquid is the same as the filter membrane used for collecting the particulate matter on the part to be detected.
4. A method for detecting the cleanliness of a liquid-carrying part of an aeroengine according to claim 1, characterized in that, The identification of the particle size and corresponding quantity of the particulate matter on the image of the filter membrane of the particulate matter on the part to be detected is specifically: Input the image of the filter membrane of the particulate matter on the part to be detected into a pre-trained particulate matter image recognition model, and output the particle size and corresponding quantity; the particulate matter image recognition model is obtained by training a neural network model using training data, and the training data includes a number of particulate matter filter membrane images marked with particle size and corresponding quantity labels.
5. A method for detecting the cleanliness of a liquid-carrying part of an aero-engine according to claim 1, characterized in that, The pore diameter of the filter membrane is not greater than 5 μm, and the filter membrane is compatible with the extraction liquid.
6. A method for detecting the cleanliness of liquid-carrying parts of an aeroengine according to claim 1, characterized in that, When drying the filter membrane of the particulate matter on the part to be detected, dry the filter membrane in a non-blowing drying oven.
7. A method for detecting the cleanliness of a liquid-carrying part of an aero-engine according to claim 6, characterized in that, The drying temperature of the non-blowing drying oven is 60 °C to 90 °C, the temperature control accuracy is ±5 °C, and the drying time is 10 minutes to 15 minutes.
8. A method for detecting the cleanliness of a liquid-carrying part of an aero-engine according to claim 7, characterized in that Before drying the filter membrane in the non-blowing drying oven, it further includes: Place the filter membrane in a pollution-free petri dish. Put the petri dish into the non-blowing drying oven.
9. A method for detecting the cleanliness of liquid-carrying parts of an aero-engine according to claim 1, characterized in that, The image magnification device is a microscope.
10. A method for detecting the cleanliness of liquid-carrying parts of an aero-engine according to claim 1, characterized in that, The evaluation of the cleanliness level of the part to be detected in combination with the cleanliness technical standard of the liquid-carrying parts of the aero-engine according to the identified particle size and corresponding quantity is specifically: The cleanliness technical standard of the parts of the aero-engine liquid-carrying system stipulates the particle size and corresponding quantity corresponding to different cleanliness levels under a set surface area. After converting the surface area of the part to be detected to the set surface area, use the identified particle size and corresponding quantity to evaluate the cleanliness level.