A pre-flight detection method, device and equipment based on aircraft component status recognition

Abstract

The present application provides a pre-flight inspection method, device, and equipment based on aircraft component status recognition, the method comprising: obtaining observation results obtained by looking around the aircraft at a preset first distance in a preset first detection time period and observing the aircraft's components to be detected; then, obtaining a picture of the aircraft's components to be detected photographed by a photographing device at a preset second distance in a preset second detection time period; then, determining the image recognition result for the components to be detected based on the color and position of the components to be detected contained in the target detection area of ​​the picture to be detected; then, combining the observation results and the image recognition results to determine whether the aircraft meets the take-off standard. The present application combines the observation results and the image recognition results, and the identification of aircraft safety is more accurate.

Description

Technical Field

[0001] The present application relates to the field of safety detection technology, and in particular to a pre-flight detection method, device, and equipment based on aircraft component status identification. Background Art

[0002] The existing safety inspection scheme is basically carried out manually. After the aircraft lands at the airport, it is necessary to maintain many items such as the pitot tube, refueling cover, front and rear service covers, and landing gear latches within the set time. Improper operation will cause serious consequences. Taking the pitot tube as an example, the function of the aircraft pitot tube is to measure the total pressure and static pressure of the airflow through the pitot tube. The aircraft's airspeed and altitude are calculated and displayed on the primary flight display for the pilot's reference. The current maintenance method is to use a leather cover to protect the pitot tube when the aircraft completes the post-flight work after the flight to prevent dust, small insects and rain from entering the pitot tube and affecting the normal air pressure measurement. Before the aircraft takes off, the ground crew will remove the pitot tube protective cover. However, the service personnel have heavy inspection tasks, and the pre-flight personnel are exhausted and busy with work, so it is easy for them to forget to remove the pitot tube protective cover, which will cause certain consequences. If the pitot tube is heated, the protective cover will melt, causing aircraft malfunction. If the protective cover is not melted, the protective cover blocks the airflow, causing the aircraft to be unable to measure the airspeed and altitude normally. Based on the above situation, the aircraft may return to the airport for an emergency landing at the very least, or even cause an accident at the worst. Summary of the invention

[0003] In view of this, the purpose of the present application is to provide a pre-flight detection method, device, and equipment based on aircraft component status recognition, which combines observation results and image recognition results to more accurately identify aircraft safety.

[0004] In a first aspect, an embodiment of the present application provides a pre-flight detection method based on aircraft component status recognition, the method comprising:

[0005] Obtaining observation results obtained by observing the aircraft component to be inspected at a preset first distance during a preset first inspection time period;

[0006] Acquire a picture of the aircraft component to be inspected, taken by a photographing device at a preset second distance during a preset second inspection time period;

[0007] Determine an image recognition result for the component to be detected according to the color to be detected and the position to be detected of the component to be detected contained in the target detection area in the picture to be detected;

[0008] The observation result and the image recognition result are combined to determine whether the aircraft meets the take-off standard.

[0009] In some technical solutions of the present application, the target detection area in the to-be-detected picture is determined in the following manner:

[0010] Dense sampling is performed evenly at different positions to be detected on the image to be detected to obtain a plurality of sampling areas to be selected with different scales and aspect ratios;

[0011] Based on the image features of each of the to-be-selected sampling areas, screening out a target sampling area from the to-be-selected sampling areas;

[0012] The target sampling areas are combined to obtain a target detection area.

[0013] In some technical solutions of the present application, the above-mentioned determining the image recognition result for the component to be detected according to the target detection area in the picture to be detected containing the color to be detected and the position to be detected of the component to be detected includes:

[0014] Determining whether the part to be detected contains an appendage by comparing the color to be detected of the part to be detected with the original color of the part to be detected;

[0015] By comparing the to-be-detected position of the to-be-detected component with the safe position of the to-be-detected component, it is determined whether the to-be-detected component is in a safe state.

[0016] In some technical solutions of the present application, the above-mentioned determining whether the part to be detected contains an appendage by comparing the color to be detected of the part to be detected with the original color of the part to be detected includes:

[0017] If the color to be detected of the component to be detected is the same as the original color of the component to be detected, the component to be detected does not contain any attachments;

[0018] If the color to be detected of the component to be detected is different from the original color of the component to be detected, the component to be detected includes an appendage;

[0019] Determine the specific type and impact degree of the appendage according to the comparison between the color to be detected of the component to be detected and a preset reference color;

[0020] According to the specific type and impact degree of the attachment, an early warning prompt corresponding to the specific type and impact degree of the attachment is issued.

[0021] In some technical solutions of the present application, the above-mentioned determining whether the component to be detected is in a safe state based on comparing the position to be detected of the component to be detected with the safe position of the component to be detected includes:

[0022] If the deviation between the to-be-detected position of the to-be-detected component and the safe position of the to-be-detected component is within a safe interval, the to-be-detected component is in a safe state;

[0023] If the deviation between the to-be-detected position of the to-be-detected component and the safe position of the to-be-detected component is not within a safe interval, a corresponding early warning prompt is determined according to the deviation.

[0024] In some technical solutions of the present application, the above-mentioned combination of the observation result and the image recognition result to determine whether the aircraft meets the take-off standard includes:

[0025] Determining a target detection result with high accuracy from the observation result and the image recognition result according to the influencing factors during the observation and the image attributes of the image to be detected;

[0026] Based on the condition that the component to be detected includes attachments and the safety status in the target detection result, it is determined whether the aircraft meets the take-off standard.

[0027] In some technical solutions of the present application, the above-mentioned determining a more accurate target detection result from the observation result and the image recognition result according to the influencing factors during the observation and the image attributes of the image to be detected includes:

[0028] Determining a first accuracy of the observation result according to the influence degree of the influencing factor;

[0029] Determining a second accuracy of the image recognition result according to the image attribute of the image to be detected;

[0030] According to the first accuracy and the second accuracy, a recognition result with a higher accuracy is selected from the observation result and the image recognition result as the target recognition result.

[0031] In a second aspect, an embodiment of the present application provides a pre-flight detection device based on aircraft component status recognition, the device comprising:

[0032] A first acquisition module is used to acquire an observation result obtained by observing the aircraft component to be inspected at a preset first distance during a preset first detection time period;

[0033] A second acquisition module is used to acquire a picture of the aircraft component to be inspected, which is taken by a photographing device at a preset second distance during a preset second inspection time period;

[0034] A determination module, used to determine the image recognition result for the part to be detected according to the color to be detected and the position to be detected of the part to be detected contained in the target detection area in the picture to be detected;

[0035] A combining module is used to combine the observation result and the image recognition result to determine whether the aircraft meets the take-off standard.

[0036] In a third aspect, an embodiment of the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned pre-flight inspection method based on aircraft component status identification when executing the computer program.

[0037] The technical solution provided by the embodiments of the present application may have the following beneficial effects:

[0038] The present application obtains observation results obtained by observing the parts to be detected of the aircraft by looking around the aircraft at a preset first distance during a preset first detection time period; then, obtains a picture of the parts to be detected of the aircraft taken by a camera at a preset second distance during a preset second detection time period; then, according to the color and position of the parts to be detected contained in the target detection area of ​​the pictures to be detected, the image recognition results for the parts to be detected are determined; then, combining the observation results and the image recognition results, it is determined whether the aircraft meets the standards for takeoff. The present application combines the observation results and the image recognition results, and the identification of aircraft safety is more accurate.

[0039] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0041] Figure 1 A schematic flow chart of a pre-flight detection method based on aircraft component status identification provided in an embodiment of the present application is shown;

[0042] Figure 2 A schematic diagram of a process for combining observation results and image recognition results provided in an embodiment of the present application is shown;

[0043] Figure 3 A schematic diagram of a pre-flight detection device based on aircraft component status recognition provided by an embodiment of the present application is shown;

[0044] Figure 4A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0045] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the drawings in the present application only serve the purpose of explanation and description and are not used to limit the scope of protection of the present application. In addition, it should be understood that the schematic drawings are not drawn in real proportion. The flowchart used in this application shows the operations implemented according to some embodiments of the present application. It should be understood that the operations of the flowchart can be implemented out of sequence, and the steps without logical context can be reversed in order or implemented simultaneously. In addition, those skilled in the art can add one or more other operations to the flowchart under the guidance of the content of the present application, or remove one or more operations from the flowchart.

[0046] In addition, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various configurations. 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 application claimed for protection, but merely represents the 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 making creative work belong to the scope of protection of the present application.

[0047] It should be noted that the term "comprising" will be used in the embodiments of the present application to indicate the existence of the features declared thereafter, but does not exclude the addition of other features.

[0048] The existing safety inspection scheme is basically carried out manually. After the aircraft lands at the airport, it is necessary to maintain many items such as the pitot tube, refueling cover, front and rear service covers, and landing gear latches within the set time. Improper operation will cause serious consequences. Taking the pitot tube as an example, the function of the aircraft pitot tube is to measure the total pressure and static pressure of the airflow through the pitot tube. The aircraft's airspeed and altitude are calculated and displayed on the primary flight display for the pilot's reference. The current maintenance method is to use a leather cover to protect the pitot tube when the aircraft completes the post-flight work after the flight to prevent dust, small insects and rain from entering the pitot tube and affecting the normal air pressure measurement. Before the aircraft takes off, the ground crew will remove the pitot tube protective cover. However, the service personnel have heavy inspection tasks, and the pre-flight personnel are exhausted and busy with work, so it is easy for them to forget to remove the pitot tube protective cover, which will cause certain consequences. If the pitot tube is heated, the protective cover will melt, causing aircraft malfunction. If the protective cover is not melted, the protective cover blocks the airflow, causing the aircraft to be unable to measure the airspeed and altitude normally. Based on the above situation, the aircraft may return to the airport for an emergency landing at the very least, or even cause an accident at the worst.

[0049] The embodiments of the present application provide a pre-flight detection method, device, and equipment based on aircraft component status identification, which are described below through embodiments.

[0050] Figure 1 A flow chart of a pre-flight detection method based on aircraft component status recognition provided by an embodiment of the present application is shown, wherein the method includes steps S101-S104; specifically:

[0051] S101, obtaining observation results obtained by observing the aircraft components to be inspected at a preset first distance during a preset first inspection time period;

[0052] S102, obtaining a picture of the aircraft component to be inspected, taken by a photographing device at a preset second distance during a preset second inspection time period;

[0053] S103, determining an image recognition result for the part to be detected according to the color to be detected and the position to be detected of the part to be detected contained in the target detection area in the picture to be detected;

[0054] S104: Determine whether the aircraft meets the take-off criteria by combining the observation results and the image recognition results.

[0055] This application combines observation results and image recognition results to more accurately identify aircraft safety.

[0056] Some embodiments of the present application are described in detail below. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0057] S101, obtaining observation results obtained by observing a component to be inspected of the aircraft by looking around the aircraft at a preset first distance during a preset first inspection time period.

[0058] The components to be tested in this application include pitot tubes, cover plates, and landing gear.

[0059] Pitot tube: Function: The total pressure and static pressure of the airflow are measured through the pitot tube, and the aircraft's airspeed and altitude are calculated and displayed on the primary flight display for the pilot's reference. Current maintenance method: Post-flight: When the aircraft completes post-flight work, a leather cover will be used to protect the pitot tube to prevent dust, insects and rain from entering the pitot tube, thereby affecting the normal pressure measurement. Pre-flight: The pitot tube protective cover will be removed before the aircraft takes off. Problems: Before the flight, the personnel are exhausted and busy, and it is easy to forget to remove the pitot tube protective cover. Consequences: After the pitot tube is heated, the protective cover melts, causing aircraft failure. If the protective cover is not melted, the protective cover blocks the airflow, causing the aircraft to be unable to measure the airspeed and altitude normally. Based on the above two situations, the aircraft may return to the airport for an alternate landing at the least, or an accident may occur at the worst.

[0060] Service cover: Function: Mainly includes refueling cover, front and rear service cover. Under normal circumstances, the cover is closed to maintain the streamline of the aircraft and protect the refueling panel, refueling port and service port. Current maintenance method: Before flight: Airport service personnel open the service panel, add clean water, and then close the service panel; Airport service personnel open the refueling cover, add fuel, and then close the refueling cover. Stopover: Airport service personnel open the service panel, add clean water, discharge sewage, and then close the service panel; Airport service personnel open the refueling cover, add fuel, and then close the refueling cover. After flight: Airport service personnel open the service panel, discharge clean water, discharge sewage, and then close the service panel. Problems: Airport service personnel tend to forget to close the corresponding cover. Consequences: Under high-speed flight, the unclosed cover is easy to fall off, causing damage to the aircraft, posing a threat to flight safety, and in severe cases, it will constitute an accident symptom.

[0061] Landing gear latch: Function: Front landing gear safety pin: prevents the landing gear from being accidentally retracted while the aircraft is parked on the ground; the front wheel turning pin mainly releases the hydraulic pressure of the aircraft's front wheel turning, so that the tractor can control the direction of the front wheel. Main landing gear safety pin: a locking device that ensures that the aircraft's main landing gear will not be accidentally retracted when it is parked or taxiing on the ground. Current maintenance method: After the aircraft lands, the maintenance personnel will plug in the front landing gear and main landing gear latches respectively, and remove the latches before the aircraft takes off; the front wheel turning pin is inserted when the aircraft is pushed out of the parking position and removed before the aircraft taxis. Existing problems: Maintenance personnel often forget to remove the landing gear latch. Consequences: The main (front) landing gear latch is not removed: the aircraft landing gear cannot be retracted, and the aircraft makes an alternate landing or returns. The front landing gear turning pin is not removed: the pilot cannot control the aircraft to turn, causing an unsafe situation when the aircraft taxis.

[0062] The first detection time period preset here is before the aircraft takes off or during the aircraft transit. During the above-mentioned first detection time period, the observation distance between the relevant staff and the aircraft is between 1-3 meters, and the inspection around the aircraft is completed in 15 minutes, the above-mentioned components to be detected are detected, and the observation results for the above-mentioned components to be detected are recorded, and the observation results are input to the server. The requirements for observation in this application are that there must be a change in the pitch angle, and the detection route is a preset prescribed route. The observation results here include whether the above-mentioned components to be detected contain attachments and whether the above-mentioned components to be detected are in a safe state.

[0063] S102: obtaining a picture of the aircraft component to be inspected by taking the picture at a preset second distance by using a photographing device in a preset second inspection time period.

[0064] The present application not only considers the observation results, but also collects images of the aircraft parts to be inspected, that is, the images of the aircraft parts to be inspected are taken by a shooting device at a preset second distance, and the image recognition results are obtained by analyzing and processing the images to be inspected.

[0065] The second detection time period in the embodiment of the present application can be the same time period as the second detection time period described above, or the two can be different time periods. If the first detection time period coincides with the second time period, during observation, the present application provides a portable camera for the staff to take pictures of the aircraft components to be inspected through the portable camera while observing. If the first detection time period does not coincide with the second time period, the present application can set a fixed camera at a preset position around the aircraft, and take pictures of the aircraft components to be inspected before or after observation through the fixed camera.

[0066] For example, the inspector wears AR glasses for inspection and completes the flight around the aircraft in 15 minutes. The personnel's recognition distance is 1-3 meters. There are changes in pitch angles. According to the route, the prescribed inspection is completed and the pitot tube, cover, and landing gear on the route are identified. The hardware used is GLXSS SEAR glasses. Fixed cameras can also be considered. The recognition distance of the camera is 50-100 meters.

[0067] S103 , determining an image recognition result for the component to be detected according to the color to be detected and the position to be detected of the component to be detected contained in the target detection area in the image to be detected.

[0068] After obtaining the image to be detected of the component to be detected, the present application analyzes the image to be detected to obtain an image recognition result for the component to be detected included in the image to be detected.

[0069] The image to be detected includes a target detection area containing the parts to be detected and an impurity area containing other parts of the aircraft or the background. When analyzing the image to be detected, it is first necessary to determine the target detection area in the image to be detected from the image to be detected. The present application obtains a plurality of selected sampling areas of different scales and aspect ratios by uniformly and densely sampling different positions to be detected on the image to be detected; then, based on the image features of each sampling area to be selected, the target sampling area is screened out from the sampling area to be selected; finally, the target sampling areas are combined to obtain the target detection area.

[0070] The above process can be implemented in a pre-trained target detection region recognition model. The training process of the target detection region recognition model is as follows: the algorithm uses the yolo5 network structure to detect the components to be detected. First, nearly a hundred pictures are labeled to form data in XML format, and then converted into the data set style required for training and sent to the yolo5 network for training. Dense sampling is performed evenly at different positions on the picture. Different scales and aspect ratios can be used for sampling, and then classification and regression are performed directly after extracting features using CNN. The whole process only requires one step, so the advantage is that it is fast. After non-maximum suppression screening, the final detection result is obtained, and it is compared with the observation result to obtain the classification loss and regression loss, which are then returned to the network. Each bounding box has a confidence score, which is used to identify the probability of the component to be detected.

[0071] After determining the target detection area containing the component to be detected from the image to be detected, it is necessary to analyze the component to be detected contained in the target detection area to determine whether the component to be detected contains any attachments and is in a safe state.

[0072] When identifying whether the part to be detected contains an appendage, the present application mainly compares the color to be detected of the part to be detected with the original color of the part to be detected. If the color to be detected of the part to be detected is the same as the original color of the part to be detected, the part to be detected does not contain an appendage; if the color to be detected of the part to be detected is different from the original color of the part to be detected, the part to be detected contains an appendage. If the part to be detected does not contain an appendage, it is considered that the part to be detected does not need to be processed. If the part to be detected contains an appendage, the present application also determines the specific type of the appendage. After determining the specific type of the appendage, it is also necessary to determine whether the appendage has an impact on the normal operation of the aircraft, and if it has an impact, what is the extent of the impact. For example, the part to be detected is a landing gear. Through image recognition, it is determined that the landing gear contains an appendage landing gear latch. If the landing gear latch is not removed in time, it will have serious consequences for the normal flight of the aircraft. In this case, a corresponding early warning prompt is required. For another example, the component to be inspected is a landing gear. Through image recognition, it is determined that the landing gear contains an attachment, a leaf. The leaf will fall when the aircraft takes off and will not affect the normal flight of the aircraft. At this time, no early warning is required.

[0073] When detecting whether the component to be detected is in a safe state, the present application mainly compares the position to be detected of the component to be detected and the safe position of the component to be detected. If the deviation between the position to be detected and the safe position of the component to be detected is within a safe interval, the component to be detected is in a safe state; if the deviation between the position to be detected and the safe position of the component to be detected is not within the safe interval, a corresponding early warning prompt is determined according to the deviation.

[0074] The early warning prompts in this application include different early warning methods and early warning times. For example, if the appendages contained in the part to be detected have a strong impact or the position to be detected of the part to be detected is significantly different from the safe position of the part to be detected (not in the safe range), a flash plus a high-decibel, high-frequency prompt sound is used to continuously prompt for three minutes. If the appendages contained in the part to be detected have a weak impact or the position to be detected of the part to be detected is not significantly different from the safe position of the part to be detected (not in the safe range), a lower-decibel, lower-frequency prompt sound is used to intermittently prompt for two minutes.

[0075] S104: Determine whether the aircraft meets the take-off criteria by combining the observation results and the image recognition results.

[0076] There are many influencing factors when conducting observations, including environmental factors and human factors of the staff during the test. For example, environmental factors include the intensity of the light when the staff is looking around, weather conditions, etc.; human factors include the staff's work experience, test time, physical condition, etc.

[0077] When analyzing the image to be detected, the image attributes will also affect the image recognition results. The image attributes here include the angle at which the image was taken, the influence of the lighting when the image was taken, the cleanliness and completeness of the image, etc.

[0078] like Figure 2 As shown, the present application combines the above-obtained observation results and image recognition results to include:

[0079] S201, determining a target detection result with high accuracy from the observation results and the image recognition results according to the influencing factors during observation and the image attributes of the image to be detected;

[0080] S202: Determine whether the aircraft meets the take-off standard based on the situation that the component to be detected contains attachments and the safety status in the target detection result.

[0081] The specific process is as follows: determine the first accuracy of the observation result according to the degree of influence of the influencing factors; determine the second accuracy of the image recognition result according to the image attributes of the image to be detected; based on the first accuracy and the second accuracy, select the recognition result with higher accuracy from the observation results and the image recognition results as the target recognition result.

[0082] For example, the first accuracy includes a first basic value and a first additional value, the first basic value is determined by the human factors of the staff, and the first additional value is determined by environmental factors. The second accuracy includes a second basic value and a second additional value, the second basic value is determined by the clarity of the image to be detected, and the second additional value is determined by the integrity of the image to be detected. Here, the first additional value or the second additional value is zero or a negative number.

[0083] Figure 3 A schematic diagram of the structure of a pre-flight detection device based on aircraft component status recognition provided by an embodiment of the present application is shown, and the device includes:

[0084] A first acquisition module is used to acquire an observation result obtained by observing the aircraft component to be inspected at a preset first distance during a preset first detection time period;

[0085] A second acquisition module is used to acquire a picture of the aircraft component to be inspected by taking the picture at a preset second distance through a photographing device during a preset second inspection time period;

[0086] A determination module, used to determine the image recognition result for the part to be detected according to the color to be detected and the position to be detected of the part to be detected contained in the target detection area in the picture to be detected;

[0087] The combination module is used to combine the observation results and the image recognition results to determine whether the aircraft meets the take-off standards.

[0088] The determination module, when used to determine the image recognition result for the part to be detected according to the target detection area in the picture to be detected containing the color to be detected and the position to be detected of the part to be detected, includes:

[0089] Determine the target detection area in the image to be detected in the following way:

[0090] Dense sampling is performed evenly at different locations to be detected on the image to be detected, to obtain multiple sampling areas of different scales and aspect ratios;

[0091] Based on the image features of each sampling area to be selected, a target sampling area is screened out from the sampling areas to be selected;

[0092] The target sampling areas are combined to obtain the target detection area.

[0093] According to the target detection area in the image to be detected including the color to be detected and the position to be detected of the component to be detected, the image recognition result for the component to be detected is determined, including:

[0094] Determine whether the part to be detected contains an appendage by comparing the color to be detected of the part to be detected with the original color of the part to be detected;

[0095] By comparing the to-be-detected position of the to-be-detected component with the safe position of the to-be-detected component, it is determined whether the to-be-detected component is in a safe state.

[0096] Determining whether the part to be detected contains an appendage by comparing the color to be detected of the part to be detected with the original color of the part to be detected includes:

[0097] If the color to be detected of the part to be detected is the same as the original color of the part to be detected, the part to be detected does not contain any attachments;

[0098] If the color to be detected of the part to be detected is different from the original color of the part to be detected, the part to be detected contains an appendage;

[0099] According to the comparison between the color of the part to be inspected and the preset reference color, the specific type and impact degree of the attachment are determined;

[0100] Based on the specific type and impact level of the attachment, an early warning alert corresponding to the specific type and impact level of the attachment is issued.

[0101] Determining whether the component to be detected is in a safe state by comparing the position to be detected of the component to be detected with the safe position of the component to be detected, including:

[0102] If the deviation between the to-be-detected position of the to-be-detected component and the safe position of the to-be-detected component is within the safe range, the to-be-detected component is in a safe state;

[0103] If the deviation between the to-be-detected position of the to-be-detected component and the safe position of the to-be-detected component is not within the safe range, a corresponding early warning prompt is determined according to the deviation.

[0104] The combination module, when used to combine the observation results and the image recognition results to determine whether the aircraft meets the take-off criteria, includes:

[0105] According to the influencing factors during observation and the image attributes of the image to be detected, a target detection result with high accuracy is determined from the observation results and the image recognition results;

[0106] Based on the condition that the parts to be inspected contain attachments and the safety status in the target inspection results, it is determined whether the aircraft meets the take-off standards.

[0107] According to the influencing factors during observation and the image attributes of the image to be detected, a more accurate target detection result is determined from the observation results and image recognition results, including:

[0108] Determine the first accuracy of the observation results according to the degree of influence of the influencing factors;

[0109] Determining a second accuracy of the image recognition result according to the image attribute of the image to be detected;

[0110] According to the first accuracy and the second accuracy, a recognition result with a higher accuracy is selected from the observation results and the image recognition results as the target recognition result.

[0111] like Figure 4 As shown, an embodiment of the present application provides an electronic device for executing the pre-flight detection method based on aircraft component status identification in the present application, the device includes a memory, a processor, a bus, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the pre-flight detection method based on aircraft component status identification when executing the computer program.

[0112] Specifically, the above-mentioned memory and processor may be general-purpose memory and processor, which are not specifically limited here. When the processor runs the computer program stored in the memory, the above-mentioned pre-flight detection method based on aircraft component status identification can be executed.

[0113] Corresponding to the pre-flight inspection method based on aircraft component status identification in the present application, an embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned pre-flight inspection method based on aircraft component status identification are executed.

[0114] Specifically, the storage medium can be a general storage medium, such as a mobile disk, a hard disk, etc. When the computer program on the storage medium is run, the above-mentioned pre-flight detection method based on aircraft component status identification can be executed.

[0115] In the embodiments provided in the present application, it should be understood that the disclosed systems and methods can be implemented in other ways. The system embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of the system or unit can be electrical, mechanical or other forms.

[0116] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0117] In addition, each functional unit in the embodiments provided in the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0118] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0119] It should be noted that similar numbers and letters represent similar items in the following figures. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. In addition, the terms "first", "second", "third", etc. are only used to distinguish the description and are not to be understood as indicating or implying relative importance.

[0120] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present application, which are used to illustrate the technical solutions of the present application, rather than to limit them. The protection scope of the present application is not limited thereto. Although the present application is described in detail with reference to the above-mentioned embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-mentioned embodiments within the technical scope disclosed in the present application, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application. They should all be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A pre-flight detection method based on aircraft component status recognition, characterized in that: The method comprises: Obtaining observation results obtained by observing the aircraft component to be inspected at a preset first distance during a preset first inspection time period; Acquire a picture of the aircraft component to be inspected taken by a photographing device at a preset second distance during a preset second inspection time period; wherein the second inspection time period is different from the first inspection time period; Determine an image recognition result for the component to be detected according to the target detection area in the picture to be detected including the color to be detected and the position to be detected of the component to be detected; Combining the observation result and the image recognition result, determining whether the aircraft meets the take-off criteria; The combining the observation result and the image recognition result to determine whether the aircraft meets the take-off standard includes: Determining a target detection result with high accuracy from the observation result and the image recognition result according to the influencing factors during the observation and the image attributes of the image to be detected; Determining whether the aircraft meets the take-off standard based on the condition that the part to be inspected includes an attachment and a safety status in the target inspection result; The determining a relatively accurate target detection result from the observation result and the image recognition result according to the influencing factors during the observation and the image attributes of the image to be detected includes: Determine the first accuracy of the observation result according to the influence degree of the influencing factor; wherein the first accuracy includes a first basic value and a first additional value, the first basic value is determined by the human factors of the staff, and the first additional value is determined by the environmental factors; Determine the second accuracy of the image recognition result according to the image attributes of the image to be detected; wherein the second accuracy includes a second basic value and a second additional value, the second basic value is determined by the clarity of the image to be detected, and the second additional value is determined by the completeness of the image to be detected; According to the first accuracy and the second accuracy, a recognition result with a higher accuracy is selected from the observation result and the image recognition result as the target recognition result.

2. The method according to claim 1, characterized in that Determine the target detection area in the image to be detected by: Dense sampling is performed evenly at different positions to be detected on the image to be detected to obtain a plurality of sampling areas to be selected with different scales and aspect ratios; Based on the image features of each of the to-be-selected sampling areas, screening out a target sampling area from the to-be-selected sampling areas; The target sampling areas are combined to obtain a target detection area.

3. The method according to claim 1, characterized in that The step of determining the image recognition result for the component to be detected based on the target detection area in the picture to be detected including the color to be detected and the position to be detected of the component to be detected comprises: Determining whether the part to be detected contains an appendage by comparing the color to be detected of the part to be detected with the original color of the part to be detected; By comparing the to-be-detected position of the to-be-detected component with the safe position of the to-be-detected component, it is determined whether the to-be-detected component is in a safe state.

4. The method according to claim 3, characterized in that The step of determining whether the part to be detected contains an appendage by comparing the color to be detected of the part to be detected with the original color of the part to be detected comprises: If the color to be detected of the component to be detected is the same as the original color of the component to be detected, the component to be detected does not contain any attachments; If the color to be detected of the component to be detected is different from the original color of the component to be detected, the component to be detected includes an appendage; Determine the specific type and impact degree of the appendage according to the comparison between the color to be detected of the component to be detected and a preset reference color; According to the specific type and impact degree of the attachment, an early warning prompt corresponding to the specific type and impact degree of the attachment is issued.

5. The method according to claim 3, characterized in that: The step of determining whether the component to be detected is in a safe state by comparing the position to be detected of the component to be detected with the safe position of the component to be detected comprises: If the deviation between the to-be-detected position of the to-be-detected component and the safe position of the to-be-detected component is within a safe interval, the to-be-detected component is in a safe state; If the deviation between the to-be-detected position of the to-be-detected component and the safe position of the to-be-detected component is not within a safe range, a corresponding early warning prompt is determined according to the deviation.

6. A pre-flight detection device based on aircraft component status recognition, characterized in that: The device comprises: A first acquisition module is used to acquire an observation result obtained by observing the aircraft component to be inspected at a preset first distance during a preset first detection time period; A second acquisition module is used to acquire a picture of the aircraft component to be inspected taken by a photographing device at a preset second distance during a preset second inspection time period; wherein the second inspection time period is different from the first inspection time period; A determination module, used to determine the image recognition result for the part to be detected according to the color to be detected and the position to be detected of the part to be detected contained in the target detection area in the picture to be detected; A combining module, used to combine the observation result and the image recognition result to determine whether the aircraft meets the take-off standard; The combining the observation result and the image recognition result to determine whether the aircraft meets the take-off standard includes: Determining a target detection result with high accuracy from the observation result and the image recognition result according to the influencing factors during the observation and the image attributes of the image to be detected; Determining whether the aircraft meets the take-off standard based on the condition that the part to be inspected includes an attachment and a safety status in the target inspection result; The determining a relatively accurate target detection result from the observation result and the image recognition result according to the influencing factors during the observation and the image attributes of the image to be detected includes: Determine the first accuracy of the observation result according to the influence degree of the influencing factor; wherein the first accuracy includes a first basic value and a first additional value, the first basic value is determined by the human factors of the staff, and the first additional value is determined by the environmental factors; Determine the second accuracy of the image recognition result according to the image attributes of the image to be detected; wherein the second accuracy includes a second basic value and a second additional value, the second basic value is determined by the clarity of the image to be detected, and the second additional value is determined by the completeness of the image to be detected; According to the first accuracy and the second accuracy, a recognition result with a higher accuracy is selected from the observation result and the image recognition result as the target recognition result.

7. An electronic device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate via the bus, and when the machine-readable instructions are executed by the processor, the steps of the pre-flight inspection method based on aircraft component status identification as described in any one of claims 1 to 5 are performed.

Images