A processing method and device for sorting aeroengine blades

Abstract

An embodiment of the present invention discloses a processing method and device for sorting blades of an aeroengine. The method includes: obtaining an image of a blade tenon of the aeroengine, and preprocessing the image of the blade tenon to obtain a target image; identifying a plaintext character in the target image, obtaining the assembly information of a corresponding target blade from a database according to the recognition result, and visually guiding the blade position of the target blade through text and / or highlighting display; obtaining an image of the blade state during the blade sorting process, and detecting the blade position of the target blade according to the image of the blade state to obtain a detection result. By means of the present invention, the problems of redundant information in paper process documents, time-consuming and laborious blade selection and sorting by workers, high labor intensity, heavy mental burden and easy errors in manual detection during the blade sorting process of the aeroengine are solved, and the technical effects of greatly shortening the working time, reducing the number of errors and improving the working efficiency and quality are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and particularly to a processing method and device for sorting aero-engine blades. Background Art

[0002] An aero-engine is a highly complex and precise thermal machine. By continuously rotating the blades at high speed, air is introduced from the air inlet into the compressor. The air is compressed in the compressor to increase the air pressure and supply the compressed air required for the engine to operate. The high-pressure air is mixed with fuel and burned in the combustion chamber to convert chemical energy into heat energy, forming high-temperature and high-pressure gas. The gas flow continuously accelerates and expands in the nozzle, fully converting the heat energy in the gas into kinetic energy and discharging it at high speed from the tail nozzle. The increase in gas momentum causes the engine to generate a powerful reaction thrust to drive the aircraft to fly. During the operation of an aero-engine, the vibration generated by the high-speed rotation of the blades has a great impact on the balance of the aero-engine rotor and the vibration response of the whole machine. Therefore, the assembly of the blades plays a very important role in the manufacture of aero-engines.

[0003] In the assembly of an aero-engine, the fan rotor blades are core components, and their matching and assembly results will greatly affect the assembly quality of the aero-engine. The theoretical parameter values such as the size and mass of the fan rotor blades of the same level in an aero-engine are the same. However, due to factors such as materials and processing errors, there are differences between each blade. Therefore, before the blades are assembled with the disk hub, they need to be strictly selected and tested according to characteristic parameters such as weight moment and natural frequency to meet the assembly requirements. Due to the consistent shape of the blades, during the process of selecting the blades, the operator can only distinguish them by the clear codes on the blade tenons. After the blades are produced, the worker needs to manually input the clear code data of the blades. The coding rules of the clear codes mainly include information such as the model, group, serial number, and furnace batch of the blades. There is a great similarity between the clear codes. Before assembly, the operator can only select the blade group according to the paper documents generated by optimal selection and matching, and then sort the grouped blades in the assembly order. The entire selection process has a large workload, is time-consuming and laborious, and requires multiple manual checks, which is mentally exhausting and prone to errors.

[0004] It can be seen that in the existing technology, during the blade sorting process, the worker needs to find and distinguish the blades according to the clear codes on the blade tenons. There is a great similarity between the clear codes of each blade. The sorting operation of the blades requires multiple checks to ensure the correctness of the blade order. The entire blade sorting process requires a large amount of human resources. The worker needs to perform multiple visual and thinking conversions between the paper documents and the blade groups, and rely on multiple manual checks and inspections, which requires a high level of care and patience from the worker, increases the mental burden of the worker, and is very prone to errors.

[0005] For the above problems, no effective solutions have been proposed yet. Summary of the Invention

[0006] An embodiment of the present invention provides a method and device for processing the sorting of aero-engine blades, so as to at least solve the technical problems of redundant information in paper process documents, time-consuming and laborious selection and sorting by workers, high labor intensity, heavy mental burden, and easy errors in manual detection during the sorting process of aero-engine blades.

[0007] According to one aspect of the embodiments of the present invention, a method for processing the sorting of aero-engine blades is provided, including: obtaining an image of the blade tenon of an aero-engine, and preprocessing the image of the blade tenon to obtain a target image; recognizing the clear-code characters in the target image, obtaining the assembly information of the corresponding target blade from a database according to the recognition result, and visually guiding the blade position of the target blade through text and / or highlighting display; obtaining an image of the blade state during the blade sorting process, and detecting the blade position of the target blade according to the image of the blade state to obtain a detection result.

[0008] Optionally, preprocessing the image of the blade tenon to obtain a target image includes: performing a smoothing filtering process on the image of the blade tenon to obtain a filtered image; performing a grayscale process on the filtered image to obtain a grayscale image; performing a binarization process on the grayscale image to obtain a binarized image, where the clear-code characters included in the binarized image are set to black, and the background within the character area is set to white; performing an inclination correction process on the binarized image to obtain the target image.

[0009] Optionally, performing an inclination correction process on the binarized image to obtain the target image includes: performing a rotation transformation on the binarized image according to the angle value obtained by the Hough line detection, and performing cropping according to the size of the image of the blade tenon, and rotating the clear-code characters to a horizontal position to obtain the target image.

[0010] Optionally, recognizing the clear-code characters in the target image includes: calling an Optical Character Recognition (OCR) engine interface; recognizing the clear-code characters in the target image according to the OCR engine interface.

[0011] Optionally, detecting the blade position of the target blade according to the image of the blade state to obtain a detection result includes: determining the position coordinates and the blade storage area of the target blade according to the image of the blade state; judging whether the blade position of the target blade is correct according to the position coordinates of the target blade and the blade storage area, and feeding back guiding information.

[0012] Optionally, determining the position coordinates and the blade storage area of the target blade according to the blade state image includes: performing extraction and correction on the blade state image according to perspective transformation to obtain a projection image; processing the projection image according to Hue Saturation Value (HSV) color segmentation to segment the blade sorting guide area from the image background of the projection image, and then using edge detection to obtain the coordinate values corresponding to the rectangular edges of each blade storage area to obtain the blade storage area; setting the region of interest of the projection image, using the inter-frame difference method to compare two video frames to obtain a difference image, and then determining the target blade according to the difference image and obtaining the position coordinates of the target blade.

[0013] Optionally, after detecting the blade position according to the blade state image and obtaining a detection result, the method further includes: in the case where the guiding information in the detection result indicates that the blade position of the target blade is incorrect, performing error correction guidance, where the error correction guidance includes displaying the recognition result and / or the blade position of the target blade in the text guidance area, and triggering the text input box in the text guidance area after receiving an operation instruction, and the text input box is used to input or modify the recognition result and / or the blade position of the target blade.

[0014] According to another aspect of the embodiments of the present invention, there is also provided a processing device for sorting blades of an aeroengine, including: a first processing module, configured to obtain a blade tenon image of the aeroengine and perform preprocessing on the blade tenon image to obtain a target image; a second processing module, configured to identify the clear text characters in the target image, obtain the assembly information of the corresponding target blade from a database according to the recognition result, and perform visual guidance on the blade position of the target blade through text and / or highlighting; a third processing module, configured to obtain the blade state image during the blade sorting process and detect the blade position of the target blade according to the blade state image to obtain a detection result.

[0015] According to another aspect of the embodiments of the present invention, there is also provided a computer-readable storage medium, where the computer-readable storage medium includes a stored program, and when the program runs, it controls the device where the computer-readable storage medium is located to execute the method steps described in any one of the above.

[0016] According to another aspect of the embodiments of the present invention, there is also provided a processor, where the processor is used to run a program, and when the program runs, it executes the method steps described in any one of the above.

[0017] In an embodiment of the present invention, a blade tenon image of an aeroengine is acquired, and the blade tenon image is preprocessed to obtain a target image. The target image is subjected to recognition of plain code characters, and according to the recognition result, the assembly information of the corresponding target blade is acquired from a database, and the blade position of the target blade is visually guided by means of text and / or highlighting display. A blade state image during the blade sorting process is acquired, and the blade position of the target blade is detected according to the blade state image to obtain a detection result. That is to say, in the embodiment of the present invention, by acquiring the blade tenon image, processing the image, recognizing the plain code characters in the image, directly searching for the corresponding assembly information from the database according to the recognition result, indicating the correct position of the blade by means of text and / or highlighting display, and performing real-time detection on the blade sorting process and timely feeding back the detection result to the operator, the technical problems existing in the blade sorting process of the aeroengine, such as redundant information in paper process documents, time-consuming and laborious selection and sorting by workers, high labor intensity, heavy mental burden, and easy occurrence of errors in manual detection, are solved, and the technical effects of greatly shortening the working time, reducing the number of errors, and improving the work efficiency and quality are achieved. Description of the Drawings

[0018] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The illustrative embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation to the present invention. In the drawings:

[0019] Figure 1 It is a flowchart of a processing method for aeroengine blade sorting provided by an embodiment of the present invention;

[0020] Figure 2 It is a schematic diagram of an overall solution of a guiding method and system for aeroengine blade sorting based on projection enhancement provided by an embodiment of the present invention;

[0021] Figure 3 It is an effect diagram of plain code recognition image processing provided by an embodiment of the present invention;

[0022] Figure 4 It is a flowchart of blade sorting detection provided by an embodiment of the present invention;

[0023] Figure 5 It is an effect diagram of blade sorting detection provided by an embodiment of the present invention;

[0024] Figure 6 It is an effect diagram of a blade sorting guiding system provided by an embodiment of the present invention;

[0025] Figure 7 It is a schematic diagram of a processing device for aeroengine blade sorting provided by an embodiment of the present invention. Detailed Embodiments

[0026] To enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without making creative efforts shall fall within the protection scope of the present invention.

[0027] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the accompanying drawings are used to distinguish different objects, rather than to limit a specific order.

[0028] According to one aspect of the embodiments of the present invention, a method for processing the sorting of aero-engine blades is provided. Figure 1 The flowchart of the method for processing the sorting of aero-engine blades provided by the embodiments of the present invention is as Figure 1 shown, and the method includes the following steps:

[0029] Step S102, obtain the image of the blade tenon of the aero-engine, and preprocess the image of the blade tenon to obtain a target image;

[0030] Optionally, a camera can be called to obtain the image of the blade tenon, and the image is preprocessed to increase the contrast between the clear code characters and the background, and ensure that the angle of the characters can meet the recognition requirements.

[0031] Step S104, recognize the clear code characters in the target image, obtain the assembly information of the corresponding target blade from the database according to the recognition result, and visually guide the blade position of the target blade through text and / or highlighting;

[0032] The above assembly information includes but is not limited to information such as the model, group, serial number, furnace batch, etc. of the blade; optionally, the recognition of clear code characters can be realized by calling the OCR engine interface, and the assembly information of the corresponding target blade is obtained from the database according to the recognition result, and then the blade sorting is visually guided through text and highlighting.

[0033] Step S106, obtain the blade state image during the blade sorting process, and detect the blade position of the target blade according to the blade state image to obtain a detection result.

[0034] Optionally, the industrial camera is used to collect the blade sorting image, and image processing algorithms such as perspective transformation, image segmentation, edge detection, and inter-frame difference are used to realize the detection and judgment of the blade position.

[0035] It should be noted that the present invention uses projection enhancement technology for visual guidance in the blade sorting process, and uses image processing technology to detect the blade sorting result to ensure the correctness of blade sorting.

[0036] In an embodiment of the present invention, a tenon image of an aeroengine blade is acquired, and the tenon image of the blade is preprocessed to obtain a target image; the clear code characters in the target image are recognized, and according to the recognition result, the assembly information of the corresponding target blade is obtained from the database, and the blade position of the target blade is visually guided by text and / or highlighting; the blade state image during the blade sorting process is acquired, and the blade position of the target blade is detected according to the blade state image to obtain a detection result. That is to say, in the embodiment of the present invention, by acquiring the tenon image of the blade, processing the image, recognizing the clear code characters in the image, directly searching for the corresponding assembly information from the database according to the recognition result, indicating the correct position of the blade by text and / or highlighting, and performing real-time detection on the blade sorting process, and timely feedback the detection result to the operator, thereby solving the technical problems of redundant information in paper process documents, time-consuming and laborious for workers to select and sort, heavy labor intensity, heavy mental burden, and easy errors in manual detection during the blade sorting process of aeroengines, and achieving the technical effects of greatly shortening the working time, reducing the number of errors, and improving the efficiency and quality of work.

[0037] In an optional implementation manner, preprocessing the tenon image of the blade to obtain a target image includes: performing smoothing filtering on the tenon image of the blade to obtain a filtered image; performing grayscale processing on the filtered image to obtain a grayscale image; performing binarization processing on the grayscale image to obtain a binarized image, wherein the clear code characters included in the binarized image are set to black, and the background within the character area is set to white; performing skew correction processing on the binarized image to obtain a target image. Further, performing skew correction processing on the binarized image to obtain a target image includes: performing a rotation transformation on the binarized image according to the angle value obtained by the Hough line detection, and performing cropping according to the size of the tenon image of the blade to rotate the clear code characters to a horizontal position to obtain a target image.

[0038] In the above implementation manner of the present invention, the clear code image of the blade can be captured by a camera, and image processing technologies such as smoothing filtering, grayscale processing, and binarization processing are used to detect the clear code area of the blade from a complex background, and the image is skew-corrected according to the Hough line detection algorithm, so as to obtain a more accurate target image.

[0039] In an optional implementation manner, recognizing the clear code characters in the target image includes: calling the optical character recognition OCR engine interface; recognizing the clear code characters in the target image according to the OCR engine interface.

[0040] In the specific implementation process, the OCR engine interface can be called to identify the clear-code characters, integrated into the boot system through the DLL file, and the assembly information of the corresponding target blade is obtained from the database according to the recognition result, and sorting guidance is carried out in a visual manner with text prompts and highlighting.

[0041] In the above embodiment of the present invention, the OCR engine interface can be called to quickly identify the clear-code characters in the target image.

[0042] In an alternative embodiment, the blade position of the target blade is detected according to the blade status image, and the detection result is obtained, including: determining the position coordinates and the blade storage area of the target blade according to the blade status image; judging whether the blade position of the target blade is correct according to the position coordinates and the blade storage area of the target blade, and feedbacking the guidance information.

[0043] In the above embodiment of the present invention, by using the position coordinates and the blade storage area of the target blade obtained from the blade status image to judge whether the blade position of the target blade is correct and feedbacking the guidance information, the accuracy and reliability of the blade sorting process can be effectively improved.

[0044] In an alternative embodiment, determining the position coordinates and the blade storage area of the target blade according to the blade status image includes: performing extraction and correction on the blade status image according to perspective transformation to obtain a projection image; processing the projection graph by hue saturation value (HSV) color segmentation to separate the blade sorting guidance area from the image background of the projection graph, and then obtaining the coordinate values corresponding to the rectangular edges of each blade storage area by using edge detection to obtain the blade storage area; setting the region of interest of the projection image, comparing two video frames by using the inter-frame difference method to obtain a difference image, and then determining the target blade according to the difference image and obtaining the position coordinates of the target blade.

[0045] In the specific implementation process, the blade status image of the assembly site can be collected by an industrial camera, and the extraction and correction of the projection image are realized by using perspective transformation; the rectangular blocks in the blade sorting guidance area are segmented by HSV color segmentation, and the positioning of each rectangular block is realized according to edge detection; according to the difference operation result of the video frames, the position of the current blade is obtained, and it is analyzed and judged whether the blade sorting is correct, and error warning information and error correction solutions are timely feedbacked.

[0046] In the above embodiment of the present invention, the image of the blade sorting operation is collected by an industrial camera, and image extraction and correction, image segmentation, and image comparison are performed by using image processing algorithms to detect the correctness of the blade sorting in real time and feedback the detection result.

[0047] In an alternative embodiment, after detecting the blade position based on the blade state image and obtaining the detection result, the above method further includes: when the guiding information in the detection result indicates that the blade position of the target blade is incorrect, error correction guidance is performed, where the error correction guidance includes displaying the recognition result and / or the blade position of the target blade in the text guidance area, and triggering the text input box in the text guidance area after receiving an operation instruction, and the text input box is used to input or modify the recognition result and / or the blade position of the target blade.

[0048] In the above embodiment of the present invention, if the guiding information in the detection result indicates that the blade position of the target blade is incorrect, error correction guidance can be performed. It should be noted that the error correction guidance can not only display the recognition result and / or the blade position of the target blade in the text guidance area, but also trigger the text input box in the text guidance area after receiving an operation instruction, and input or modify the recognition result and / or the blade position of the target blade through the text input box, so as to adjust the relevant parameters in the blade sorting process in a timely manner, effectively shorten the working time, reduce the number of errors, and improve the work efficiency and quality.

[0049] A detailed description of an alternative embodiment of the present invention will be given below.

[0050] To solve the technical problems mentioned in the present invention, an alternative embodiment of the present invention realizes a method and system for guiding the sorting of aero-engine blades based on projection enhancement through technologies such as augmented reality and image processing. First, a camera is called to obtain the blade tenon image, and image preprocessing such as smoothing filtering, grayscale processing, binarization processing, and Hough line detection is performed using image processing technologies. The OCR interface is called to identify the clear code information of the blade, and the corresponding optimal matching result of the blade is obtained by searching in the database. The blade position is visually guided using text and highlighted icons; the image of the blade sorting operation is collected by an industrial camera, and image extraction and correction, image segmentation, and image comparison are performed using image processing algorithms to detect the correctness of the blade sorting in real time and feedback the detection result.

[0051] Figure 2 It is a schematic diagram of the overall solution of the method and system for guiding the sorting of aero-engine blades based on projection enhancement provided by the embodiment of the present invention. As Figure 2 shown, the overall solution includes the guidance and detection of the blade sorting process. Visual guidance is performed on the blade sorting operation through projection enhancement, and text prompts and highlighted indications of the blade position are given according to the database information and clear code characters. The UI interface is interacted with the system by clicking the mouse and keyboard; the blade sorting process is detected in real time, the sorting position of the blade is judged, error warning information is feedback, and error correction guidance is performed to form a closed-loop system of guidance-detection-feedback-guidance.

[0052] Figure 3 This is the effect diagram of the clear code recognition image processing provided by the embodiment of the present invention, as Figure 3 shown. The specific steps are as follows:

[0053] Step 1: Use bilateral filtering to process the original image (corresponding to the above blade tenon image). On the basis of retaining the character edge feature details, the removal of noise is well achieved.

[0054] Step 2: Convert the color image into a grayscale image through weighted average grayscale processing, which greatly reduces the amount of data and makes subsequent processing more convenient and fast.

[0055] Step 3: Through binarization processing, the clear code characters can be set to black, and the background within the character area can be set to white, increasing the contrast of the clear code characters, reducing the difficulty of subsequent character recognition, and improving the recognition accuracy at the same time.

[0056] Step 4: Rotate the binarized image according to the angle value obtained by Hough line detection, and crop it according to the size of the original image. The clear code characters are rotated to the horizontal position, which can greatly reduce the errors caused by the angle during character recognition and improve the success rate of clear code recognition.

[0057] Step 5: After the image processing of the blade clear code, not only can the contrast between the clear code characters and the background be increased, making it easy to recognize, but also the angle of the characters can be ensured to meet the recognition requirements, improving the recognition accuracy. The characters are recognized by calling the API interface of the Baidu AI open platform.

[0058] Figure 4 This is the flow chart of the blade sorting detection provided by the embodiment of the present invention, as Figure 4 shown; Figure 5 This is the effect diagram of the blade sorting detection provided by the embodiment of the present invention. The detection effect is as Figure 5 shown. The specific steps are as follows:

[0059] Step 1: Collect the blade state images at the assembly site through an industrial camera. Since the images captured by the camera not only include the projection images, but also contain part of the surrounding environment, and there may also be deviations in the angles of the captured images. In order to ensure that the blade sorting state can be fully obtained, first, perspective transformation is required to extract and correct the projection images, and then the blade storage area and the current blade are located respectively.

[0060] Step 2: For the positioning of the blade storage area, first, the HSV color segmentation technology is used to process the projection graphics to distinguish the blade sorting guide area from the image background, and then the edge detection technology is used to obtain the coordinate values corresponding to the rectangular edges of each blade storage area, realizing the precise positioning of the blade storage area.

[0061] Step 3: The positioning of the current blade refers to detecting the position of the blade completed in the current operation. First, it is necessary to set the region of interest (ROI) for the image to exclude background interference during the blade positioning process. Then, the inter-frame difference method is used to compare two video frames to obtain a difference image, and the difference image is utilized to find the current blade and obtain its position coordinates.

[0062] Step 4: Analyze and compare the position coordinates of the current blade with the blade storage area to obtain the sorting position of the blade. Judge whether the position of the current blade is correct according to the database information, and give feedback guidance information in a timely manner.

[0063] Figure 6 The following is the effect diagram of the blade sorting guidance system provided by the embodiment of the present invention. As Figure 6 shown, the system mainly includes two parts: a main interface and a blade sorting guidance interface. Click the start button on the main interface to enter the blade sorting guidance interface. The guidance interface is divided into three parts: a blade sorting guidance area, a barcode scanning and recognition area, and an interaction area. The blade placement guidance area is composed of 6×3 rectangular blocks, corresponding to the positions of 18 blades respectively. By highlighting the rectangular blocks, it indicates the placement position of the current blade, guiding workers to complete the blade sorting work accurately and efficiently; the barcode scanning and recognition area mainly displays the image captured by the camera during barcode scanning, facilitating the judgment of the image range and quality to ensure the correctness of subsequent clear code recognition; the interaction area mainly includes a camera switching dropdown box, a barcode scanning and recognition button, an exit button, a text input box, and a text guidance area. The camera switching dropdown box is used to realize the selection and switching of cameras. The system can obtain the number and names of cameras in real time, and the operator can independently select the camera for clear code recognition of the blade according to the requirements; clicking the barcode scanning and recognition button can perform the clear code recognition operation of the blade. In the Windows system, the dynamic link library (DLL) file for image processing and the application program interface (API) for character recognition are directly called to detect and recognize the clear code characters of the blade tenon image, and obtain the corresponding blade information from the blade database. If an Android tablet or HoloLens2 platform is used, the Socket communication technology needs to be utilized to obtain the clear code recognition result and blade information, and then the clear code recognition result and blade position information are displayed in the text guidance area. The text input box can input or modify the clear code information of the blade. When the system fails to detect the camera or the clear code recognition is incorrect, the text input box can be opened by clicking the text guidance area, and the corresponding blade information can be obtained by manually inputting or modifying the clear code recognition result, ensuring the stability and reliability of the system.

[0064] According to another aspect of the embodiments of the present invention, there is also provided a processing device for sorting aero-engine blades. Figure 7 It is a schematic diagram of the processing device for sorting aero-engine blades provided by the embodiments of the present invention. As Figure 7 shown, the processing device for sorting aero-engine blades includes: a first processing module 702, a second processing module 704, and a third processing module 706. The processing device for sorting aero-engine blades will be described in detail below.

[0065] The first processing module 702 is configured to obtain an image of the blade tenon of the aero-engine, and preprocess the image of the blade tenon to obtain a target image.

[0066] The second processing module 704 is connected to the first processing module 702, and is configured to identify the plain code characters in the target image, obtain the assembly information of the corresponding target blade from the database according to the recognition result, and visually guide the blade position of the target blade through text and / or highlighting.

[0067] The third processing module 706 is connected to the second processing module 704, and is configured to obtain the blade state image during the blade sorting process, and detect the blade position of the target blade according to the blade state image to obtain a detection result.

[0068] In the embodiments of the present invention, the processing device for sorting aero-engine blades adopts the following steps: obtaining an image of the blade tenon of the aero-engine, preprocessing the image of the blade tenon to obtain a target image; identifying the plain code characters in the target image, obtaining the assembly information of the corresponding target blade from the database according to the recognition result, and visually guiding the blade position of the target blade through text and / or highlighting; obtaining the blade state image during the blade sorting process, and detecting the blade position of the target blade according to the blade state image to obtain a detection result. That is to say, in the embodiments of the present invention, by obtaining the image of the blade tenon, processing the image, identifying the plain code characters in the image, directly searching for the corresponding assembly information from the database according to the recognition result, indicating the correct position of the blade through text and / or highlighting, and performing real-time detection on the blade sorting process, and feeding back the detection result to the operator in a timely manner, the technical problems existing in the process of sorting aero-engine blades, such as the redundant information of paper process documents, the time-consuming and laborious process of workers' selection and sorting, the heavy labor intensity, the heavy mental burden, and the easy occurrence of errors in manual detection, are solved, and the technical effects of greatly shortening the working time, reducing the number of errors, and improving the efficiency and quality of work are achieved.

[0069] It should be noted here that the above first processing module 702, second processing module 704, and third processing module 706 correspond to steps S102 to S106 in the method embodiment. The examples and application scenarios implemented by the above modules and the corresponding steps are the same, but are not limited to the content disclosed in the above method embodiment.

[0070] Optionally, the above first processing module 702 includes: a first processing unit for performing smoothing filtering on the blade tenon image to obtain a filtered image; a second processing unit for performing grayscale processing on the filtered image to obtain a grayscale image; a third processing unit for performing binarization processing on the grayscale image to obtain a binarized image, wherein the clear code characters included in the binarized image are set to black, and the background within the character area is set to white; a fourth processing unit for performing skew correction processing on the binarized image to obtain a target image.

[0071] Optionally, the above fourth processing unit includes: a first processing subunit for performing a rotation transformation on the binarized image according to the angle value obtained by the Hough line detection, and cropping according to the size of the blade tenon image to rotate the clear code characters to the horizontal position to obtain a target image.

[0072] Optionally, the above second processing module 704 includes: a calling unit for calling the optical character recognition OCR engine interface; an identifying unit for identifying the clear code characters in the target image according to the OCR engine interface.

[0073] Optionally, the above third processing module 706 includes: a determining unit for determining the position coordinates of the target blade and the blade storage area according to the blade state image; a judging unit for judging whether the blade position of the target blade is correct according to the position coordinates of the target blade and the blade storage area, and feeding back guiding information.

[0074] Optionally, the above determining unit includes: a second processing subunit for performing extraction correction on the blade state image according to perspective transformation to obtain a projection image; a third processing subunit for processing the projection pattern according to hue saturation value HSV color segmentation to segment the blade sorting guiding area from the image background of the projection pattern, and then using edge detection to obtain the coordinate values corresponding to the rectangular edges of each blade storage area to obtain the blade storage area; a fourth processing subunit for setting the region of interest of the projection image, comparing two video frames using the inter-frame difference method to obtain a difference image, and then determining the target blade according to the difference image and obtaining the position coordinates of the target blade.

[0075] Optionally, the above device further includes: a fourth processing module, configured to, after detecting the blade position according to the blade state image and obtaining a detection result, perform error correction guidance when the guidance information in the detection result indicates that the blade position of the target blade is incorrect, where the error correction guidance includes displaying the recognition result and / or the blade position of the target blade in the text guidance area, and triggering the text input box in the text guidance area after receiving an operation instruction, and the text input box is used to input or modify the recognition result and / or the blade position of the target blade.

[0076] According to another aspect of the embodiments of the present invention, there is also provided a computer-readable storage medium, which includes a stored program, where, when the program runs, it controls the device where the computer-readable storage medium is located to execute the method steps in any one of the above.

[0077] It should be noted that the above computer-readable storage medium may be located in any one of the computer terminals in the computer terminal group in the computer network, and / or in any one of the mobile terminals in the mobile terminal group, and the above computer-readable storage medium includes a stored program.

[0078] According to another aspect of the embodiments of the present invention, there is also provided a processor, which is used to run a program, where, when the program runs, it executes the method steps in any one of the above.

[0079] The above is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention.

Claims

1. A processing method for sorting aeroengine blades, characterized in that Including: Obtain the blade tenon image of an aeroengine, and preprocess the blade tenon image to obtain a target image; Perform recognition on the clear code characters of the target image, obtain the assembly information of the corresponding target blade from a database according to the recognition result, and visually guide the blade position of the target blade through text and / or highlighting display; Performing recognition on the clear code characters of the target image includes: Invoke the optical character recognition OCR engine interface; Recognize the clear code characters in the target image according to the OCR engine interface; Obtain the blade state image during the blade sorting process, and detect the blade position of the target blade according to the blade state image to obtain a detection result; Detecting the blade position of the target blade according to the blade state image to obtain a detection result includes: Determine the position coordinates and blade storage area of the target blade according to the blade state image; Judge whether the blade position of the target blade is correct according to the position coordinates of the target blade and the blade storage area, and feedback guiding information; Determining the position coordinates and blade storage area of the target blade according to the blade state image includes: Perform extraction and correction on the blade state image according to perspective transformation to obtain a projection image; Process the projection image according to hue saturation value (HSV) color segmentation, segment the blade sorting guiding area from the image background of the projection image, and then use edge detection to obtain the coordinate values corresponding to the rectangular edges of each blade storage area to obtain the blade storage area; Set the region of interest of the projection image, compare two video frames using the inter-frame difference method to obtain a difference image, then determine the target blade according to the difference image, and obtain the position coordinates of the target blade; The judging whether the blade position of the target blade is correct and feedbacking guiding information includes: Analyze and compare the position coordinates of the current blade with the blade storage area, obtain the sorting position of the blade, judge whether the position of the current blade is correct according to the database information, and give feedback guiding information in a timely manner.

2. The method according to claim 1, wherein Preprocessing the blade tenon image to obtain a target image includes: Perform smoothing filtering processing on the blade tenon image to obtain a filtered image; Perform grayscale processing on the filtered image to obtain a grayscale image; Perform binarization processing on the grayscale image to obtain a binarized image, where the clear code characters included in the binarized image are set to black, and the background within the character area is set to white; Perform skew correction processing on the binarized image to obtain the target image.

3. The method according to claim 2, wherein Performing skew correction processing on the binarized image to obtain the target image includes: Perform rotation transformation on the binarized image according to the angle value obtained by Hough line detection, and perform cropping according to the size of the blade tenon image, rotate the clear code characters to a horizontal position to obtain the target image.

4. The method according to any one of claims 1 to 3, characterized in that, After detecting the blade position according to the blade state image to obtain a detection result, the method further includes: When the guiding information in the detection result indicates that the blade position of the target blade is incorrect, error correction guidance is performed. The error correction guidance includes displaying the recognition result and / or the blade position of the target blade in the text guidance area, and triggering the text input box in the text guidance area after receiving an operation instruction. The text input box is used to input or modify the recognition result and / or the blade position of the target blade.

5. A processing device for sorting aero-engine blades, characterized in that, It includes: A first processing module, configured to obtain an image of a blade tenon of an aeroengine, and preprocess the image of the blade tenon to obtain a target image; A second processing module, configured to recognize the clear text characters in the target image, obtain the assembly information of the corresponding target blade from a database according to the recognition result, and visually guide the blade position of the target blade through text and / or highlighting display; Recognizing the clear text characters in the target image includes: Invoking an optical character recognition (OCR) engine interface; Recognizing the clear text characters in the target image according to the OCR engine interface; A third processing module, configured to obtain an image of the blade state during the blade sorting process, and detect the blade position of the target blade according to the image of the blade state to obtain a detection result; Detecting the blade position of the target blade according to the image of the blade state to obtain a detection result includes: Determining the position coordinates and the blade storage area of the target blade according to the image of the blade state; Judging whether the blade position of the target blade is correct according to the position coordinates of the target blade and the blade storage area, and feedbacking guiding information; Determining the position coordinates and the blade storage area of the target blade according to the image of the blade state includes: Performing extraction and correction on the image of the blade state according to perspective transformation to obtain a projection image; Processing the projection image according to hue, saturation, value (HSV) color segmentation to segment the blade sorting guiding area from the image background of the projection image, and then using edge detection to obtain the coordinate values corresponding to the rectangular edges of each blade storage area to obtain the blade storage area; Setting a region of interest of the projection image, comparing two video frames using the inter-frame difference method to obtain a difference image, then determining the target blade according to the difference image, and obtaining the position coordinates of the target blade; Judging whether the blade position of the target blade is correct and feedbacking guiding information includes: Analyzing and comparing the position coordinates of the current blade with the blade storage area to obtain the sorting position of the blade, judging whether the position of the current blade is correct according to the database information, and timely giving feedback guiding information.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein when the program runs, it controls the device where the computer-readable storage medium is located to execute the method steps described in any one of claims 1 to 4.

7. A processor, characterized in that, The processor is used to run a program, wherein when the program runs, it executes the method steps described in any one of claims 1 to 4.

Images