Equipment state detection method and device

Abstract

The invention discloses an equipment state detection method and device. The method comprises the following steps: acquiring an image of each to-be-detected area on flight equipment; performing target detection on the image to obtain the category, the position and the size of a target object; in a process variable module of the human-computer interaction interface, receiving a statistical operation for the number of target objects of each category and a summation operation for the number; the logic judgment module is used for carrying out logic judgment according to the total number, the positions and / or the sizes of the target objects and a preset logic judgment rule, and determining whether the to-be-detected area is in a normal state or not; and determining whether the state of the to-be-detected equipment is normal or not according to the judgment result of each to-be-detected area. According to the scheme, the process variable calculation function and the logic judgment rule are set, the process of processing the image data by using the target detection model is divided into calculation of a plurality of process variables, and a plurality of groups of judgment logics are set, so that cross-scene multiplexing can be realized only by adjusting the logic rule, and the requirements on the data volume and the calculation power are reduced.

Description

Technical Field

[0001] This solution relates to the field of civil aviation maintenance technology, and in particular to a method and device for equipment condition detection. Background Technology

[0002] In the field of civil aviation maintenance, there are a large number of photos of work sites. Manual reviewers need to check each photo of the project, content, and target status to ensure that the target is in the correct working condition.

[0003] Before the rise of deep learning, object detection mainly relied on carefully designed handcrafted features (such as HOG and SIFT) and classifiers (such as SVM). The most representative are Deformable Part-based Models. These methods first extract key points or region features from the image, and then use a classifier to determine whether an object exists and its location (usually by traversing the image through a sliding window).

[0004] Two-stage detectors are an early and highly influential deep learning method. Their core idea is: the first stage (Region Proposal) generates a large number of candidate regions (Region Proposals) that may contain the target; the second stage (Region Classification & Regression) performs accurate target classification and bounding box regression for each candidate region. To achieve faster detection speeds, one-stage detectors were proposed. These abandon the separate candidate region generation stage and directly predict the target's class probability and bounding box offset simultaneously at various locations on the image grid or on predefined anchor boxes.

[0005] The output of the object detection model is an array consisting of the class_name, bounding box coordinates, confidence score, and other information for all detected objects. These model outputs cannot be directly used for business decisions.

[0006] Users of the model must develop complex result processing and logical judgment code based on the type of target detection model used and the manual judgment rules. If there are a large number of different business scenarios and judgment logics, there will be a lot of code development work, and the work of checking and correcting a large number of similar logic codes can easily cause developers to become mentally exhausted. Summary of the Invention

[0007] This solution aims to at least address the technical problems existing in the prior art. Therefore, the first aspect of this invention proposes a method for detecting equipment status, the method comprising: Acquire images of each area to be detected on the flight equipment to be inspected; The image is used to detect objects using an object detection model to obtain the category, location, and size of the target objects included in the image. In the process variable module of the human-computer interaction interface, at the position corresponding to the area to be detected, a statistical operation on the number of target objects for each category and a summation operation on the number are received to obtain the total number of target objects; The logic judgment module of the human-computer interaction interface performs logical judgment based on the total number of target objects, their positions and / or sizes, and preset logical judgment rules to determine whether the area to be detected is in a normal state. The status of the device under test is determined based on the judgment results of each of the areas to be tested.

[0008] Optionally, before receiving the statistical operation on the number of the target objects for each category and the summation operation on the number, the method further includes: The system receives input operations for logical judgment rules for each of the regions to be detected. The logical judgment rules include the category, total number, and location of the target objects in the region to be detected under normal conditions.

[0009] Optionally, the area to be detected is the toilet service panel area, and the categories of target objects included in the image are: locked latches, unlocked latches, and service text; the logical judgment based on the total number of target objects, their positions and / or sizes, and preset logical judgment rules includes: Determine whether the number of locked latches and the number of unlocked latches are a first quantity and 0 respectively, and whether the number of service texts is a second quantity.

[0010] Optionally, the area to be detected is the cabin door area, and the categories of target objects included in the image are: covered handles, uncovered handles, support rods, windows, and cabin doors; the logical judgment based on the total number of target objects, their positions and / or sizes, and preset logical judgment rules includes: Determine whether the number of covered handles, the number of uncovered handles, the number of support rods, and the number of windows are respectively a third quantity, 0, a fourth quantity, and a fifth quantity; Determine whether the location of the support rod is included in the area of ​​the cabin door.

[0011] Optionally, the area to be detected is the engine oil cover area, and the step of performing target detection on the image using a target detection model includes: The object detection model is used to obtain the categories of target objects included in the image; the categories of target objects include: locked engine oil cover latch, unlocked engine oil cover latch, engine cover text, and engine oil cover. Obtain the area or width percentage of the engine oil cover in the image.

[0012] Optionally, the step of performing logical judgment based on the total number of target objects, their positions and / or their sizes, and preset logical judgment rules includes: Determine whether the area ratio is greater than or equal to a preset first ratio, or whether the width ratio is greater than or equal to a preset second ratio; If so, determine whether the number of the locked engine oil cover latch, the unlocked engine oil cover latch, the engine cover text, and the number of the engine oil cover are the sixth quantity, 0, the seventh quantity, and 1, respectively.

[0013] A second aspect of the present invention provides a device for detecting the status of an equipment, the device comprising: The image acquisition module is used to acquire images of each area to be detected on the flight equipment to be inspected; The object detection module is used to perform object detection on the image using an object detection model to obtain the category, location, and size of the target objects included in the image; The statistics module is used in the process variable module of the human-computer interaction interface to receive statistical operations on the number of target objects of each category and summation operations on the number of objects at the position corresponding to the area to be detected, so as to obtain the total number of target objects. The judgment module is used in the human-computer interaction interface to make a logical judgment based on the total number of target objects, the position and / or the size, and the preset logical judgment rules to determine whether the area to be detected is in a normal state. The status determination module is used to determine whether the status of the device under test is normal based on the judgment results of each of the areas to be tested.

[0014] Optionally, the device further includes: The receiving module is used to receive input operations for the logical judgment rules of each of the regions to be detected, wherein the logical judgment rules include the category, total number and location of the target objects in the region to be detected under normal conditions.

[0015] A third aspect of the present invention provides an electronic device comprising a processor and a memory, wherein the memory stores at least one instruction, at least one program, a code set, or an instruction set, wherein the at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by the processor to implement the device status detection method as described in the first aspect.

[0016] A fourth aspect of the present invention provides a computer-readable storage medium storing at least one instruction, at least one program, a code set, or an instruction set, wherein the at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by a processor to implement the device status detection method as described in the first aspect.

[0017] The embodiments of the present invention have the following beneficial effects: The device status detection method provided in this invention acquires images of various detection areas on a flight device to be detected; performs target detection on the images using a target detection model to obtain the category, location, and size of the target objects included in the images; in the process variable module of the human-computer interaction interface, at the location corresponding to the detection area, it receives statistical operations on the number of target objects of each category and summation operations on the number to obtain the total number of target objects; in the logic judgment module of the human-computer interaction interface, it performs logical judgment based on the total number of target objects, the location and / or the size, and preset logical judgment rules to determine whether the detection area is in a normal state; and determines whether the status of the device to be detected is normal based on the judgment results of each detection area. This solution develops a process variable module and a logic judgment module for the human-computer interaction interface, sets process variable calculation functions and logical judgment rules, and breaks down the process of image data processing using the target detection model into the calculation of multiple process variables. By setting multiple sets of judgment logic, it realizes multiple logical judgments on image content using the target detection model and effective error prompts when detection fails. Only the logic rules need to be adjusted to reuse it across scenarios, reducing the demand for data volume and computing power. Attached Figure Description

[0018] Figure 1 A flowchart illustrating the steps of a device status detection method provided in an embodiment of the present invention; Figure 2 This is a schematic diagram of a toilet service panel area provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of a cabin door area provided in an embodiment of the present invention; Figure 4 This is a schematic diagram of an engine oil cover area provided in an embodiment of the present invention; Figure 5This is a structural block diagram of a device status detection device provided in an embodiment of the present invention. Detailed Implementation

[0019] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present solution, and not all embodiments. Based on the embodiments of the present solution, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present solution.

[0020] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of embodiments of this disclosure, unless otherwise stated, "a plurality of" means two or more. Furthermore, the use of "based on" or "according to" implies openness and inclusiveness, because processes, steps, calculations, or other actions "based on" or "according to" one or more of the stated conditions or values ​​may in practice be based on additional conditions or beyond the stated values.

[0021] Figure 1 The flowchart illustrates the steps of a device status detection method provided in an embodiment of the present invention.

[0022] like Figure 1 As shown, the method includes the following steps: Step 101: Acquire images of each area to be detected on the flight equipment to be inspected.

[0023] In the field of civil aviation maintenance, there are a large number of photos taken at work sites. It is necessary to check the shooting items, shooting content, and target status one by one to ensure that the shooting targets are in the correct working state.

[0024] Specifically, the areas to be inspected may include: the lavatory service panel, cabin doors, engine oil filler caps, etc. Images of each area to be inspected should be taken, ensuring clear images, sufficient lighting, and standard angles, covering the entire area to be inspected.

[0025] Detailed shooting specifications can be defined for each area to be inspected, such as angle, distance, and required reference objects, to ensure the consistency of input images. When uploading images, the system can automatically detect sharpness, brightness, occlusion, etc., and immediately prompt for reshooting of unqualified images.

[0026] Step 102: Use an object detection model to perform object detection on the image to obtain the category, location, and size of the target objects included in the image.

[0027] The object detection model is used to identify the category of all objects of interest in an image, such as latches, windows, support rods, and text, and outputs their category, location, and size. The location is usually represented by a bounding box, and the size is the dimensions of the bounding box.

[0028] The output is typically an array of model results, where each array element contains the target object's class_name, bounding box, confidence score, size, etc.

[0029] As an optional embodiment, prior to step 103, the method further includes: The system receives input operations for logical judgment rules for each of the regions to be detected. The logical judgment rules include the category, total number, and location of the target objects in the region to be detected under normal conditions.

[0030] The system provides a rule configuration interface, which can be considered the configuration interface for the "logic judgment module." Users can set unique logic judgment rules for each "area to be detected" (such as the "toilet service panel" or "cabin door"). This "input operation" specifically includes: Define the category of the target object: Select the objects that need to be inspected in this specific area from all the categories that the object detection model can recognize.

[0031] For example, for the lavatory service panel area, check [Service Lock - Locked, Service Lock - Not Locked, Service Text]. For the cabin door area, check [Cabin Door, Window, Support Bar].

[0032] Set the total number under normal conditions: Set the normal quantity standard for each target object category.

[0033] For example, for the toilet service panel area, the settings are: "Service Lock - Locked" = 4, "Service Lock - Not Locked" = 0, "Service Text" = 1.

[0034] This gives us a logical rule for determining the area of ​​the toilet service panel.

[0035] Step 103: In the process variable module of the human-computer interaction interface, at the position corresponding to the area to be detected, receive the statistical operation of the number of the target objects for each category and the summation operation of the number to obtain the total number of the target objects.

[0036] The process variable module in the human-computer interaction interface can be a dynamic form or interface that lists the detected target objects at the corresponding positions on the image based on the detection results of step 102. This step allows maintenance personnel to confirm, correct, and supplement the detection results.

[0037] If the model misidentifies "Type A latch" as "Type B latch", the user can correct the category. Users can manually add targets that the model missed or delete falsely detected targets.

[0038] After confirming that the test results are correct, the maintenance personnel manually trigger the corresponding position on the human-machine interface to count the number of target objects in each category. After the count is completed, the count is summed to obtain the total number of target objects.

[0039] For example, the function that might be used in step 103 is as follows: a) COUNT(class_name) counts the target data volume for the specified label within the [model results array]. b) MAX_WIDTH(class_name) calculates the maximum width percentage of the specified label within the model result array. c) MAX_AREA(class_name) calculates the maximum area percentage of a specified label within the model result array. d) SUM(value_a, value_b, ...) sums the process variables such as value_a and value_b.

[0040] In this step, by changing the function and adjusting the logic rules, the cross-scene reuse of target detection data can be achieved, reducing the demand for data volume and computing power.

[0041] Step 104: The logic judgment module of the human-computer interaction interface performs a logical judgment based on the total number of target objects, the position and / or the size, and the preset logical judgment rules to determine whether the area to be detected is in a normal state.

[0042] The structured data generated in step 103 is judged according to the preset logical judgment rules.

[0043] Specifically, the preset logical judgment rules can be based on quantity, position, or size. These rules can be used individually or in combination, depending on the actual situation.

[0044] As an optional embodiment, the area to be detected is the toilet service panel area, and the categories of target objects included in the image are: locked latches, unlocked latches, and service text; the logical judgment based on the total number of target objects, their positions and / or sizes, and preset logical judgment rules includes: Step 1041: Determine whether the number of locked latches and the number of unlocked latches are a first quantity and 0 respectively, and whether the number of service texts is a second quantity.

[0045] Figure 2 This is a schematic diagram of a toilet service panel area provided in an embodiment of the present invention.

[0046] like Figure 2 As shown, the left side is a standard image of the toilet service panel area, and the right side is an image to be inspected taken in that area. The standard image includes 4 locked latches, 0 unlocked latches, and 1 set of service text.

[0047] The object detection model identifies the image to be detected and obtains the object's class_name, bounding box (bbox), confidence level, and size. The object's class is categorized as follows: B777_LAVATORY_SERVICE_LOCK (B777 service lock - locked), B777_LAVATORY_SERVCIE_UNLOCK (B777 service lock - not locked), and B777_LAVATORY_SERVICE (B777 service text).

[0048] In the process variable module of the human-computer interaction interface, corresponding to the toilet service panel area, it receives statistical operations on the quantity of target objects for each category and summation operations on the quantities to obtain the total number of target objects. An example is shown below: SERVICE_LOCK_COUNT = COUNT(B777_LAVATORY_SERVICE_LOCK) SERVICE_UNLOCK_COUNT = COUNT(B777_LAVATORY_SERVCIE_UNLOCK) SERVICE_TEXT_COUNT = COUNT(B777_LAVATORY_SERVICE) The first line represents the number of locked latches, the second line represents the number of unlocked latches, and the third line represents the number of service documents.

[0049] In the logic judgment module, it determines whether the number of locked latches and the number of unlocked latches are a first quantity and 0 respectively, and whether the number of service texts is a second quantity. Specifically, the first quantity and the second quantity can be preset according to the actual situation.

[0050] Example as follows: SERVICE_LOCK_COUNT = 4 SERVICE_UNLOCK_COUNT = 0 SERVICE_TEXT_COUNT = 1 That is: determine whether the number of locked latches is 4, the number of unlocked latches is 0, and the number of service documents is 1.

[0051] As an optional embodiment, the area to be detected is the cabin door area, and the categories of target objects included in the image are: covered handles, uncovered handles, support rods, windows, and cabin doors; the logical judgment based on the total number of target objects, their positions and / or sizes, and preset logical judgment rules includes: Step 1042: Determine whether the number of covered handles, the number of uncovered handles, the number of support rods, and the number of windows are respectively the third quantity, 0, the fourth quantity, and the fifth quantity; Step 1043: Determine whether the position of the support rod is included in the area of ​​the cabin door.

[0052] Figure 3 This is a schematic image of a cabin door area provided in an embodiment of the present invention.

[0053] like Figure 3 As shown, the left side is a standard image of the cabin door area, and the right side is an image of the area to be inspected taken in that area. The standard image includes one covered handle, zero uncovered handles, one window, and one support rod.

[0054] The object detection model identifies the image to be detected and obtains the object's class_name, bounding box (bbox), confidence level, and size. The object's class is: B737_CABIN_DOOR_HANDLE (B737 cabin door - locked), B737_CABIN_DOOR_UNHANDLE (B737 cabin door - unlocked), B737_CABIN_DOOR_WINDOW (B737 cabin door - window), and B737_CABIN_DOOR_HINGE (B737 cabin door - support rod).

[0055] In the process variable module of the human-computer interaction interface, at the location corresponding to the cabin door area, it receives statistical operations on the quantity of target objects for each category and summation operations on the quantities to obtain the total number of target objects. An example is shown below: DOOR_HANDLE = COUNT(B737_CABIN_DOOR_HANDLE) DOOR_UNHANDLE = COUNT(B737_CABIN_DOOR_UNHANDLE) DOOR_WINDOW = COUNT(B737_CABIN_DOOR_WINDOW) DOOR_HINGE = COUNT(B737_CABIN_DOOR_HINGE) The first line represents the number of locked cabin doors, the second line represents the number of unlocked cabin doors, the third line represents the number of windows, and the fourth line represents the number of support rods.

[0056] In the logic judgment module, it determines whether the number of covered handles, the number of uncovered handles, the number of support rods, and the number of windows are the third, zero, fourth, and fifth quantities, respectively. Specifically, the third, fourth, and fifth quantities can be preset according to the actual situation.

[0057] Example as follows: DOOR_HANDLE = 1 DOOR_UNHANDLE = 0 DOOR_WINDOW = 1 DOOR_HINGE = 1 That is: determine whether the number of covered handles is 1, the number of uncovered handles is 0, the number of windows is 1, and the number of support rods is 1.

[0058] As an optional embodiment, the area to be detected is the engine oil cover area, and step 102 includes: Step 1021: Use the object detection model to obtain the category of the target object included in the image; the category of the target object includes: locked engine oil cover latch, unlocked engine oil cover latch, engine cover text, and engine oil cover; Step 1022: Obtain the area or width percentage of the engine oil cover in the image.

[0059] Step 104 includes: Step 1044: Determine whether the area ratio is greater than or equal to a preset first ratio, or whether the width ratio is greater than or equal to a preset second ratio; Step 1045: If yes, then determine whether the locked engine oil cover latch, the unlocked engine oil cover latch, the engine cover text, and the number of engine oil covers are the sixth quantity, 0, the seventh quantity, and 1, respectively.

[0060] Figure 4 This is a schematic diagram of an engine oil cover area provided in an embodiment of the present invention.

[0061] like Figure 4 As shown, the left side is a standard image of the engine oil cover area, and the right side is an image of the area to be inspected taken in that area. The standard image includes 2 locked engine oil cover latches, 0 unlocked engine oil cover latches, 1 set of engine cover text, and 1 engine oil cover.

[0062] The object detection model identifies the image to be detected and obtains the target object's class_name, bounding box (bbox), confidence level, and size. The target object's class is: B737_ENG_OIL_PANEL_LATCH (B737 engine oil cover latch - locked), B737_ENG_OIL_PANEL_UNLATCH (B737 engine oil cover latch - not locked), B737_ENG_OIL_LABEL (B737 engine cover text), and B737_ENG_OIL_PANEL (B737 oil cover).

[0063] In addition, to ensure that the photos taken by maintenance personnel are not too far away, resulting in small targets and affecting recognition accuracy, the target detection model also outputs the detection box size of each target object. The area or width proportion of the engine oil cover in the image can be calculated by the detection box size.

[0064] Then, determine whether the area percentage is greater than or equal to a preset first percentage, or whether the width percentage is greater than or equal to a preset second percentage. The first and second percentages can be preset according to the actual situation. For example, the first percentage is 10%, and the second percentage is 20%.

[0065] Once the area or width proportions are confirmed to meet the requirements, the process variable module of the human-computer interaction interface, at the location corresponding to the cabin door area, receives statistical operations on the quantity of target objects for each category and summation operations on the quantity, obtaining the total number of target objects. An example is shown below: DOOR_HANDLE = COUNT(B737_CABIN_DOOR_HANDLE) DOOR_UNHANDLE = COUNT(B737_CABIN_DOOR_UNHANDLE) DOOR_WINDOW = COUNT(B737_CABIN_DOOR_WINDOW) DOOR_HINGE = COUNT(B737_CABIN_DOOR_HINGE) The first line represents the number of locked cabin doors, the second line represents the number of unlocked cabin doors, the third line represents the number of engine cover texts, and the fourth line represents the number of oil cover texts.

[0066] In the logic judgment module, it is determined whether the locked engine oil cover latch, the unlocked engine oil cover latch, the engine cover text, and the number of engine oil covers are the sixth quantity, 0, the seventh quantity, and 1, respectively. Specifically, the sixth and seventh quantities can be preset according to the actual situation.

[0067] Example as follows: PANEL_LATCH_COUNT = 2 PANEL_UNLATCH_COUNT = 0 PANEL_LABEL_COUNT = 1 PANEL_COUNT = 1 That is: determine whether the number of locked engine oil cover latches is 2, the number of unlocked engine oil cover latches is 0, the number of engine cover text is 1, and the number of engine oil cover plates is 1.

[0068] This step involves developing a model result data processing system, setting process variable calculation functions and logical judgment rules, and breaking down the image data processing process using the object detection model into the calculation of multiple process variables. By setting multiple sets of judgment logic, multiple logical judgments on image content using the object detection model are achieved.

[0069] Step 105: Determine whether the status of the device under test is normal based on the judgment results of each of the areas to be tested.

[0070] All areas to be tested must be judged as "normal" for the entire flight equipment to be considered "normal". If even one critical area (such as the cabin door) is abnormal, the overall status is "abnormal". After being judged as "abnormal", the system can issue an "error message".

[0071] Ultimately, a detailed inspection report can be generated, listing the inspection results, anomalies, and photographic evidence for each area to be inspected, making it easier for maintenance personnel to quickly locate and handle problems.

[0072] This step directly outputs the final decision result, such as "normal / abnormal" or "error message," instead of the intermediate "model result array," thus avoiding the need for business systems to repeatedly develop downstream logic.

[0073] In summary, the device status detection method provided by this invention acquires images of various areas to be detected on a flight device; performs target detection on the images using a target detection model to obtain the category, location, and size of the target objects included in the images; in the process variable module of the human-computer interaction interface, at the location corresponding to the area to be detected, it receives statistical operations on the number of the target objects of each category and summation operations on the number to obtain the total number of the target objects; in the logic judgment module of the human-computer interaction interface, it performs logical judgment based on the total number of the target objects, the location and / or the size, and preset logical judgment rules to determine whether the area to be detected is in a normal state; and determines whether the status of the device to be detected is normal based on the judgment results of each area to be detected. This solution, by developing a process variable module and a logic judgment module for the human-computer interaction interface, and setting process variable calculation functions and logical judgment rules, breaks down the process of image data processing using the target detection model into the calculation of multiple process variables. By setting multiple sets of judgment logic, it realizes multiple logical judgments of image content using the target detection model and effective error prompts when detection fails. Only the logic rules need to be adjusted to reuse it across scenarios, reducing the demand for data volume and computing power.

[0074] Figure 5 This is a structural block diagram of a device status detection device provided in an embodiment of the present invention.

[0075] like Figure 5 As shown, the device 200 includes: Image acquisition module 201 is used to acquire images of each area to be detected on the flight equipment to be detected; The target detection module 202 is used to perform target detection on the image using a target detection model to obtain the category, location and size of the target objects included in the image; The statistics module 203 is used in the process variable module of the human-computer interaction interface to receive statistical operations on the number of target objects of each category and summation operations on the number of objects at the position corresponding to the area to be detected, so as to obtain the total number of target objects. The judgment module 204 is used in the human-computer interaction interface to make a logical judgment based on the total number of target objects, the position and / or the size, and a preset logical judgment rule to determine whether the area to be detected is in a normal state. The status determination module 205 is used to determine whether the status of the device under test is normal based on the judgment results of each of the areas to be detected.

[0076] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0077] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state disk (SSD)).

[0078] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0079] The various embodiments in this specification are described in a related manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0080] The above description is merely a preferred embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention are included within the scope of protection of the present invention.

Claims

1. A method for detecting equipment status, characterized in that, The method includes: Acquire images of each area to be detected on the flight equipment to be inspected; The image is used to detect objects using an object detection model to obtain the category, location, and size of the target objects included in the image. In the process variable module of the human-computer interaction interface, at the position corresponding to the area to be detected, a statistical operation on the number of target objects for each category and a summation operation on the number are received to obtain the total number of target objects; The logic judgment module of the human-computer interaction interface performs logical judgment based on the total number of target objects, their positions and / or sizes, and preset logical judgment rules to determine whether the area to be detected is in a normal state. The status of the device under test is determined based on the judgment results of each of the areas to be tested.

2. The method according to claim 1, characterized in that, Before receiving the statistical operation on the number of the target objects for each category and the summation operation on the number, the method further includes: The system receives input operations for logical judgment rules for each of the regions to be detected. The logical judgment rules include the category, total number, and location of the target objects in the region to be detected under normal conditions.

3. The method according to claim 1, characterized in that, The area to be detected is the toilet service panel area, and the categories of target objects included in the image are: locked latches, unlocked latches, and service text. The step of performing logical judgment based on the total number of target objects, their positions and / or sizes, and preset logical judgment rules includes: Determine whether the number of locked latches and the number of unlocked latches are a first quantity and 0 respectively, and whether the number of service texts is a second quantity.

4. The method according to claim 1, characterized in that, The area to be detected is the cabin door area, and the categories of target objects included in the image are: covered handle, uncovered handle, support rod, window, and cabin door. The step of performing logical judgment based on the total number of target objects, their positions and / or sizes, and preset logical judgment rules includes: Determine whether the number of covered handles, the number of uncovered handles, the number of support rods, and the number of windows are respectively a third quantity, 0, a fourth quantity, and a fifth quantity; Determine whether the location of the support rod is included in the area of ​​the cabin door.

5. The method according to claim 1, characterized in that, The area to be detected is the engine oil cover area. The step of using a target detection model to perform target detection on the image includes: The object detection model is used to obtain the categories of target objects included in the image; the categories of target objects include: locked engine oil cover latch, unlocked engine oil cover latch, engine cover text, and engine oil cover. Obtain the area or width percentage of the engine oil cover in the image.

6. The method according to claim 5, characterized in that, The step of performing logical judgment based on the total number of target objects, their positions and / or sizes, and preset logical judgment rules includes: Determine whether the area ratio is greater than or equal to a preset first ratio, or whether the width ratio is greater than or equal to a preset second ratio; If so, determine whether the locked engine oil cover latch, the unlocked engine oil cover latch, the engine cover text, and the number of engine oil covers are the sixth quantity, 0, the seventh quantity, and 1, respectively.

7. A device for detecting equipment status, characterized in that, The device includes: The image acquisition module is used to acquire images of each area to be detected on the flight equipment to be inspected; The object detection module is used to perform object detection on the image using an object detection model to obtain the category, location, and size of the target objects included in the image; The statistics module is used in the process variable module of the human-computer interaction interface to receive statistical operations on the number of target objects of each category and summation operations on the number of objects at the position corresponding to the area to be detected, so as to obtain the total number of target objects. The judgment module is used in the human-computer interaction interface to make a logical judgment based on the total number of target objects, the position and / or the size, and a preset logical judgment rule to determine whether the area to be detected is in a normal state. The status determination module is used to determine whether the status of the device under test is normal based on the judgment results of each of the areas to be tested.

8. The apparatus according to claim 7, characterized in that, The device further includes: The receiving module is used to receive input operations for the logical judgment rules of each of the regions to be detected, wherein the logical judgment rules include the category, total number and location of the target objects in the region to be detected under normal conditions.

9. An electronic device, characterized in that, The electronic device includes a processor and a memory, wherein the memory stores at least one instruction, at least one program, a code set, or an instruction set, and the at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by the processor to implement the device status detection method as described in any one of claims 1-6.

10. A computer-readable storage medium, characterized in that, The storage medium stores at least one instruction, at least one program, code set, or instruction set, wherein the at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by a processor to implement the device status detection method as described in any one of claims 1-6.

Images