An aircraft engine defect identification system based on real-time analysis of borehole exploration images

Abstract

The application provides an aircraft engine defect identification system based on borehole exploration image real-time analysis. It is characterized by including: a borehole video acquisition module that acquires video images of the internal structure of aircraft engine equipment components and transmits them to an image processing engine in real time; the image processing engine automatically identifies cracks, pits, burns, notches, deformations, corrosion, material loss and other defects in the aircraft engine equipment components in each frame of video image through a neural network image recognition analysis algorithm, and transmits the defect identification analysis results to a data background; the data background is used to match the defect identification results found by the image processing engine with the records in the aircraft engine defect index database, confirm and record the defects and trends; the system realizes real-time tracking and monitoring of the defect state of aircraft components, automatically learns and accumulates a defect feature database, accurately identifies and quickly verifies defects, and promotes the application and development of intelligent maintenance and inspection technology in the field of aircraft operation and maintenance.

Description

TECHNICAL FIELD

[0001] The present application relates to the aircraft route operation and maintenance industry, in particular to a kind of aircraft engine defect identification system based on hole detection image real-time analysis. BACKGROUND

[0002] At present, aircraft engine maintenance inspection adopts hole detector endoscope camera and display screen, and the whole process is observed by artificial visual observation, and the equipment components in different regions of aircraft engine, such as combustion chamber, compressor, high and low pressure turbine, etc., are checked one by one to check whether there are defects such as cracks, pits, burns, notches, deformations, corrosion, material loss, etc. Since the appearance of the equipment components to be checked is similar, some defects are not obvious, therefore, the visual artificial inspection method has the problems of missed detection and inability to track the trend of defects in real time, thereby there are flight safety risk hidden dangers.

[0003] The aircraft engine defect identification system based on hole detection image real-time analysis of the present application provides hole detection image real-time analysis and automatic defect identification of the internal structural components of aircraft engine for maintenance inspection personnel, and voice broadcast reminds to avoid human missed detection; can integrate aircraft engine basic database and defect classification feature database, realize rapid positioning, label recording and classification determination of defects through neural network recognition analysis algorithm, improve work efficiency and quality, reduce safety risk hidden dangers, and improve the comprehensive management ability of aircraft engine operation and maintenance data. SUMMARY

[0004] In order to overcome the above problems or at least partially solve the above problems, the embodiment of the present application provides an aircraft engine defect identification system based on hole detection image real-time analysis.

[0005] The embodiment of the present application is implemented as follows:

[0006] An aircraft engine defect identification system based on hole detection image real-time analysis, comprising: a hole detection video acquisition module, which is used to acquire video images of internal equipment component structures of aircraft engine in real time during hole detection maintenance inspection operation of aircraft engine, and transmit the video images to image processing engine in real time; an image processing engine, which is used to process, store and analyze the video images transmitted by the hole detection video acquisition module, automatically identify defects such as cracks, pits, burns, notches, deformations, corrosion, material loss, etc. in the video images of internal equipment component structures of aircraft engine in real time, voice broadcast reminds, and transmit the defect identification results to data background in real time; a data background, which is used to match the defect identification results found by the image processing engine with the records in aircraft engine defect index database, confirm and record the identified defects and change trend.

[0007] In some embodiments of the present application, an aircraft engine defect identification system based on borehole exploration image real-time analysis, the borehole video acquisition module is used to obtain the real-time video stream image of the aircraft engine endoscopic maintenance inspection, the video image is compressed and encoded in real time and format converted, and each frame of video screenshot is extracted and transmitted to the image processing engine.

[0008] In some embodiments of the present application, an aircraft engine defect identification system based on borehole exploration image real-time analysis, the image processing engine is based on neural network image recognition analysis algorithm, and a pre-trained neural network model is used for feature matching identification and judgment of the input video stream MJEPG continuous frame screenshot, and real-time output of defect identification result.

[0009] In some embodiments of the present application, an aircraft engine defect identification system based on borehole exploration image real-time analysis, the pre-trained neural network model at least includes a component classification identification model and a defect target detection model, the component classification identification model at least includes type identification of aircraft engine components such as combustion chamber, compressor, high and low pressure turbine, and the defect target detection model at least includes detection and positioning of defects such as cracks, pits, burns, notches, deformations, corrosion and material loss.

[0010] In some embodiments of the present application, an aircraft engine defect identification system based on borehole exploration image real-time analysis, the defect identification result in the image processing engine at least includes aircraft engine number, engine equipment component name, defect classification name, defect position, video screenshot image with defect positioning label, timestamp and text annotation information.

[0011] In some embodiments of the present application, an aircraft engine defect identification system based on borehole exploration image real-time analysis, the data background integrates data uniformly, establishes an aircraft engine basic database and a defect index database, and the defect index database at least includes aircraft engine number, defect classification and grade, defect belonging to aircraft engine equipment component name and position, defect positioning image, defect mark start and end time, etc.

[0012] Some embodiments of the present application have at least the following advantages or beneficial effects:

[0013] 1. The system of the present application uses neural network image recognition technology to realize automatic real-time identification of defects and faults in the process of aircraft engine borehole maintenance inspection, and full-process voice real-time reminding, which improves the identification rate of aircraft engine component defects and greatly reduces the error rate and missed detection rate of manual identification.

[0014] 2. The system realizes retrieval and query of video image data of defects of aircraft engine equipment components, can quickly view historical records of fault defects, timely distinguishes new and old defects, avoids repeated checking and confirmation of defects, saves a large amount of working hours, and greatly improves the work efficiency of maintenance and inspection.

[0015] 3. The system improves data management capability, uniformly integrates aircraft engine operation and maintenance data, establishes an aircraft engine basic database and a defect index database, realizes big data tracking analysis of line operation and maintenance, and greatly reduces flight safety accident risks.

[0016] 4. The system realizes real-time tracking and monitoring of the defect state of aircraft engine components, automatically learns and accumulates a defect feature database, accurately identifies and quickly verifies defects, and promotes the application and development of intelligent maintenance technology in the field of line operation and maintenance. BRIEF DESCRIPTION OF DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments. It should be understood that the following drawings only identify some embodiments of the present application, and therefore should not be considered as a limitation to the scope. For those skilled in the art, other drawings can also be obtained without creative labor.

[0018] Figure 1 is a structural diagram of an aircraft engine defect identification system based on real-time analysis of hole exploration images; DETAILED DESCRIPTION

[0019] In order to make the purpose, technical scheme and advantages of the embodiments of the present application more clear, the following will combine the drawings in the embodiments of the present application to clearly and completely describe the technical scheme in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all the embodiments. The components of the embodiments of the present application described and shown in the drawings can be arranged and designed in various different configurations.

[0020] Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed present application, but only represents selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of the present application.

[0021] The following will combine the drawings to make a detailed description of some embodiments of the present application. In the case of no conflict, the following embodiments and features in the embodiments can be combined with each other.

[0022] EMBODIMENT

[0023] Please refer toFigure 1 The embodiment provides an aircraft engine defect identification system based on bore scope image real-time analysis, comprising:

[0024] A bore scope video acquisition module is used for acquiring video images of equipment components such as a combustion chamber, a compressor, a high-pressure turbine and a low-pressure turbine in an aircraft engine bore scope inspection operation in real time, compressing and encoding each frame of screenshot picture data of the video images into high-definition video with a resolution of 1920*1080 and 60 frames through a bore scope DP data interface, and transmitting the continuous frame screenshots to an image processing engine in real time according to an OTG transmission protocol format.

[0025] An image processing engine is connected to the bore scope video acquisition module to acquire real-time video stream MJEPG continuous frame screenshots, and based on a neural network image recognition analysis algorithm, a pre-trained neural network model is used to recognize and determine input image information; wherein the pre-trained neural network model comprises a component classification recognition model and a defect target detection model, the component classification recognition model at least comprises type recognition of aircraft engine components such as a combustion chamber, a compressor, a high-pressure turbine and a low-pressure turbine, and the recognition and determination is performed through a mode that an average classification recognition rate of no less than 100 continuous image frames exceeds 0.95, to determine a type and a region position of an aircraft engine equipment component being inspected; the defect target detection model at least comprises detection and positioning of defects such as cracks, pits, burns, notches, deformations, corrosion and material loss, and the recognition and determination is performed by scanning an image region of an aircraft engine equipment component in each image frame, to identify possible defects, and when a probability of detecting a target defect in 10 continuous image frames exceeds 0.95, the image is marked with a red frame for target defect positioning; a defect recognition result is output in combination with identified aircraft engine equipment component classification information, instant voice broadcast is reminded, and the defect recognition result is transmitted to a data background in real time; the defect recognition result at least comprises an aircraft engine number, an aircraft engine equipment component name, a defect classification name, a defect position, a video screenshot image with a defect positioning label, a timestamp and text annotation information; a notebook computer with a high-specification graphics card is used to realize neural network recognition analysis algorithm and GPU real-time image processing calculation.

[0026] The data background connects the image processing engine to obtain the defect identification result in real time, matches the record in the engine defect index database of the airplane, confirms and records the identified defect and change trend, and iteratively updates the data record in the engine defect index database of the airplane, so that the defect record, historical data retrieval and tracking analysis of the engine maintenance inspection of the airplane are realized; the defect index database at least includes the engine number of the airplane, the defect classification and grade, the name and position of the defect belonging to the engine equipment component of the airplane, the defect positioning image, the defect mark start and end time, etc.; the cloud server is adopted in the application, the network and the image processing engine are remotely connected, the defects found in the engine maintenance inspection process of the airplane are tracked in real time, the defect type is determined in time, the troubleshooting operation is assisted and guided, and the historical defect information data is analyzed by using big data.

[0027] Further, the system utilizes the neural network image recognition technology to realize automatic real-time recognition of the equipment component defect in the bore inspection maintenance operation process of the airplane engine, and realizes full-process voice instant reminding, improves the recognition rate of the airplane component defect, and greatly reduces the error rate and the missed detection rate of manual recognition.

[0028] Further, the system realizes the retrieval and query of the video image data of the equipment component defect of the airplane engine, can quickly view the historical record of the fault defect, timely distinguishes the new and old defects, avoids repeated checking and confirming of the defect, saves a large amount of working hours, and greatly improves the maintenance and inspection work efficiency.

[0029] Further, the system improves the data management capability, uniformly integrates the airplane engine operation and maintenance data, establishes the airplane engine basic database and the defect index database, realizes the big data tracking analysis of the line operation and maintenance, and greatly reduces the flight safety accident hidden danger.

[0030] Further, the system realizes real-time tracking and monitoring of the airplane engine component defect state, automatically learns and accumulates the defect feature database, accurately identifies and quickly verifies the defect, and promotes the application and development of intelligent maintenance technology in the line operation and maintenance field.

[0031] The above is only the preferred embodiment of the application and is not used to limit the application, for those skilled in the art, the application can have various changes and variations, any modification, equivalent replacement, improvement, etc. within the spirit and principle of the application should be included in the protection scope of the application.

[0032] It will be apparent to those skilled in the art that the application is not limited to the details of the above-exemplified embodiments and that the present application can be implemented in other particular forms without departing from the spirit or essential characteristics thereof. The presently disclosed embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the application being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. No reference herein to any prior art is to be taken as an admission that the application is not entitled to antedate such prior art by virtue of prior application. No reference to any prior art in this specification is intended to be, nor should it be taken as, an acknowledgement or any form of suggestion that such prior art is accepted as relevant prior art against the present application. Any citation of any prior art in this specification is solely provided on the basis of relevance to the disclosure of the application.

Claims

1. An aircraft engine defect identification system based on real-time analysis of bore-scope images, characterized by, The utility model relates to a kind of real-time monitoring system for aircraft engine crack, which comprises: A hole-probing video acquisition module is used to collect video images of the internal structure of aircraft engine components during the aircraft engine hole-probing maintenance inspection operation, compress and encode the video images in real time, and extract each frame of video screenshot and transmit it to the image processing engine in real time. An image processing engine is used to process, store and analyze the video images transmitted by the video acquisition module, automatically identify cracks, pits, burns, notches, deformations, corrosion and material loss defects in the video images in real time, timely voice broadcast reminders, and transmit the defect identification results to the data backend in real time. A data backend is used to match the defect identification results found by the image processing engine with the records in the aircraft engine defect index database, confirm and record the identified defects and trends, and iteratively update the data records in the aircraft engine defect index database. The image processing engine uses a pre-trained neural network model based on neural network image recognition analysis algorithm to perform feature matching identification and judgment on the input video stream MJEPG continuous frame screenshots, and outputs the defect identification results in real time. The defect identification results include at least aircraft engine number, aircraft engine component name, defect classification name, defect location, video screenshot image with defect positioning label, timestamp and text annotation information. The pre-trained neural network model includes at least component classification identification model and defect target detection model, and the component classification identification model includes at least type identification of combustion chamber, compressor, high and low pressure turbine aircraft engine components. The defect target detection model includes at least crack, pit, burn, notch, deformation, corrosion and material loss defect detection and positioning. The data backend automatically learns and accumulates defect feature database for real-time tracking and monitoring of aircraft engine component defect status, accurate identification and rapid verification of defects, unified integration of data, establishment of aircraft engine basic database and defect index database, and defect index database includes at least aircraft engine number, defect classification and grade, defect belonging to aircraft engine component name and location, defect positioning image, defect label start and end time.

Images