QEC maintenance safety supervision method and system based on AR

Abstract

The invention relates to a QEC (Quality Error Correction) maintenance safety supervision method and system based on AR (Augmented Reality). According to the method, after a maintenance general task is generated, the maintenance general task is decomposed into a plurality of sub-tasks and sent to pre-obtained online AR equipment, and a maintenance piece where each sub-task is located and a target model are obtained; obtaining an associated sub-task set according to the maintenance piece associated sub-tasks; when the current sub-task is executed, acquiring a marked sub-task from the associated sub-task set of the current sub-task; acquiring a real-time model of a maintenance piece where the marked sub-task is located, and executing the next sub-task if the real-time model meets a first preset condition before and after the current sub-task is executed; if the real-time models of the maintenance pieces where all the sub-tasks are located in the current associated sub-task set meet a second preset condition, the associated sub-task set is qualified; and when the completion time of all the sub-tasks and the total task real-time model meet a third preset condition, the maintenance total task is qualified. Compared with the prior art, the method has the advantages of improving data analysis efficiency and accuracy in QEC maintenance work and the like.

Description

Technical Field

[0001] This invention relates to the fields of infrastructure and IT support technology, and in particular to an AR-based QEC aircraft maintenance safety supervision method and system. Background Technology

[0002] With the rapid development of aerospace technology, the demands for passenger capacity and safety in aviation are increasing. Aircraft maintenance personnel need to frequently inspect and maintain aircraft, making airport maintenance work increasingly demanding. Among these, QEC (Quick Engine Change) is a particularly complex frontline aviation operation performed on the core aircraft component, the engine. It is characterized by numerous parts to be disassembled and reassembled, high frequency of disassembly and assembly, and significant safety risks. Taking the CFM56-7B engine as an example, each operation requires the installation of over 300 types (nearly 1000) of parts. For a long time, aircraft maintenance work has been extremely demanding, requiring compliance at every step and close coordination between different procedures.

[0003] Therefore, maintenance auxiliary equipment or systems are needed to assist and guide aircraft maintenance personnel in their operations. For example, Chinese patent CN111553499A discloses a tablet-type personal maintenance auxiliary device. This device includes a ruggedized laptop computer and an installed portable maintenance auxiliary system. The portable maintenance auxiliary system adopts a modular design, including a data management and display module, a data offloading module, a fault diagnosis module, an in-situ equipment monitoring and management module, a control module for the portable maintenance diagnostic instrument, an integrated launch module, a maintenance operation management module, an interactive electronic manual, and a user management module.

[0004] However, because maintenance personnel still need to manually consult auxiliary equipment and fill out forms during operations, and because the connectivity between auxiliary equipment used by different personnel is insufficient—the equipment only retrieves aircraft maintenance data and provides feedback, without access to the current status of other personnel—the verification and inspection methods are limited, and information aggregation still relies on manual methods, resulting in low data analysis efficiency and significant bias. Therefore, improving the efficiency and accuracy of data analysis in QEC (Quality Control and Emergency Management) maintenance work, and consequently enhancing the intelligence level of QEC maintenance safety supervision, has become a problem that needs to be solved in this field. Summary of the Invention

[0005] The purpose of this invention is to overcome the shortcomings of existing technologies, such as low data analysis efficiency and large deviations, by providing an AR-based QEC (Quality Engineering Control) safety supervision method and system. This method applies Augmented Reality (AR) technology to aircraft maintenance work, aiming to create intelligent engine workshops and aviation front-line processes. It transforms some inefficient manual operations into efficient intelligent automated operations, freeing employees from inefficient tasks and allowing them to devote more energy to safe production. At the same time, AR technology assists employees in inspecting or verifying the actions of each link, effectively avoiding basic errors caused by human factors and effectively improving the safety level.

[0006] The objective of this invention can be achieved through the following technical solutions:

[0007] According to a first aspect of the present invention, an AR-based QEC (Quality, Emergency, and Control) aircraft maintenance safety supervision method is provided, comprising the following steps: acquiring maintenance aircraft parameters and maintenance objectives, and generating a total maintenance task; decomposing the total maintenance task into multiple sub-tasks and sending them to a pre-acquired online AR device, and acquiring the maintenance part and target model of each sub-task, wherein the online AR device is used to acquire the work progress of the sub-tasks in real time; associating the multiple sub-tasks according to the acquired maintenance parts to obtain a set of associated sub-tasks for each sub-task; when executing the current sub-task, acquiring the completed sub-tasks from the set of associated sub-tasks of the current sub-task. The task is denoted as a marked subtask; the real-time model of the repair part where the marked subtask is located is obtained, and it is determined whether the real-time model meets the first preset condition before and after the current subtask is executed. If it does, the next subtask is executed; otherwise, an alarm is issued. After the current set of associated subtasks is completed, it is determined whether the real-time model of the repair part where all subtasks in the current set of associated subtasks meet the second preset condition. If it does, the current set of associated subtasks is considered to be completed successfully; otherwise, an alarm is issued. When the completion time of all subtasks and the real-time model of the total task corresponding to all associated subtask sets meet the third preset condition, the total repair task is considered to be completed successfully.

[0008] As a preferred technical solution, the process of obtaining the target model includes: constructing a standard model of the engine after the aircraft is repaired based on the aircraft parameters and the repair objectives; and obtaining the target model of the repair component for each sub-task based on the engine standard model.

[0009] As a preferred technical solution, the method of decomposing and generating multiple sub-tasks specifically includes: listing multiple sub-steps of the total maintenance task, and splitting each sub-step to obtain multiple unit tasks; obtaining the operation time, tools used, and maintenance method of each unit task, and dividing multiple unit tasks with adjacent operation times, the same tools used, and the same maintenance method into a sub-task to obtain multiple sub-tasks.

[0010] As a preferred technical solution, when decomposing and generating multiple sub-tasks, the specific process includes: adding step tags corresponding to online AR devices to multiple sub-steps, and calculating the weighted proportion and weighted time of the sub-steps to obtain the sub-step time weight; generating the sub-task based on the sub-step time weight, and using the step tags as the task name of the sub-task, while uploading it to the server.

[0011] As a preferred technical solution, the multiple subtasks are associated based on the acquired repair parts. The specific process includes: acquiring the repair part where each subtask is located, and determining whether there is a connection relationship between two repair parts: if yes, all subtasks on the two repair parts are in the same associated subtask set; if no, no execution is performed; traversing all repair parts to generate at least one associated subtask set.

[0012] As a preferred technical solution, the first preset condition specifically includes: the second matching degree is higher than the first matching degree, wherein the first matching degree is the matching degree between the real-time model and the corresponding target model before the current subtask is executed, and the second matching degree is the matching degree between the real-time model and the corresponding target model after the current subtask is completed.

[0013] As a preferred technical solution, the second preset condition specifically includes: the matching degree between the real-time model of the repair part of all subtasks in the current associated subtask set and the corresponding target model is higher than a predetermined threshold.

[0014] As a preferred technical solution, the third preset condition specifically includes: the subtask is completed successfully, the error between the completion time of the subtask and the total time of the total task is lower than a predetermined error threshold, and the matching degree between the real-time model of the total task and the pre-built standard model is higher than a predetermined completion threshold.

[0015] As a preferred technical solution, the online AR device includes a camera, a display screen, a processor, and a human-computer interaction terminal. The online AR device is used to obtain the work progress of sub-tasks in real time. The specific process includes: receiving a sub-task processing request and obtaining a corresponding unique identifier; obtaining task permissions and task standard execution guidelines based on the unique identifier and displaying them on the display screen; using the camera to obtain real-time operation video, using the processor to compare the real-time operation video with the task standard execution guidelines to obtain the sub-task work progress; and using the human-computer interaction terminal to record the sub-task work progress to a sub-task form.

[0016] According to a second aspect of the present invention, an AR-based QEC (Quality, Emergency, and Control) aircraft maintenance safety monitoring system is provided. The system is used to implement the method described above, specifically comprising: a total task generation module, used to acquire maintenance aircraft parameters and maintenance objectives, and generate a total maintenance task; a sub-task generation module, used to acquire the maintenance parts for each sub-task, and according to the total maintenance task, decompose and generate multiple sub-tasks and send them to a pre-acquired online AR device, while simultaneously acquiring a target model for each maintenance part, the online AR device being used to acquire the work progress of the sub-tasks in real time; a sub-task association module, used to associate the multiple sub-tasks according to the acquired maintenance parts, obtaining a set of associated sub-tasks for each sub-task; and a marking module, used to mark the current sub-task when executing the current sub-task. The system retrieves completed subtasks from the associated subtask set and marks them as "marked subtasks". A first judgment module retrieves the real-time model of the repair part where the marked subtask is located and judges whether the real-time model meets a first preset condition before and after the execution of the current subtask. If yes, it continues to execute the next subtask; otherwise, it issues an alarm. A second judgment module, after the current associated subtask set is completed, judges whether the real-time models of all repair parts where all subtasks in the current associated subtask set are located meet a second preset condition. If yes, the current associated subtask set is considered complete; otherwise, it issues an alarm. A third judgment module, when all subtasks are completed and the real-time model of the total task corresponding to all associated subtask sets meets a third preset condition, then the total repair task is considered complete.

[0017] Compared with the prior art, the present invention has the following beneficial effects:

[0018] 1. The QEC aircraft maintenance safety supervision method provided by this invention can intelligently generate total tasks and sub-tasks, automatically allocate tasks, and provide real-time guidance and recording on AR devices to monitor the progress of sub-tasks. Workers can view task details through AR devices and perform operations according to the guidance without having to manually look up information or fill out forms. This effectively avoids low-level errors caused by human factors, effectively improves the safety level, and can improve the efficiency and accuracy of data analysis in QEC aircraft maintenance work, thereby improving the intelligence level of QEC aircraft maintenance safety supervision.

[0019] 2. Based on the acquired repair parts, the present invention associates the multiple sub-tasks. When there is a connection between two repair parts, all sub-tasks on the two repair parts are in the same associated sub-task set, realizing mutual cooperation between associated sub-tasks, making it easier for workers to know the task progress and the status of cooperation with other tasks more efficiently.

[0020] 3. This invention achieves automatic verification of the completion rate of sub-tasks, related sub-tasks, and the overall maintenance task through three judgment steps. In particular, in the judgment of the third preset condition, the invention judges whether the overall maintenance task is completed on schedule and efficiently by considering both time and completion rate. The time judgment not only determines whether the sub-task is executed qualifiedly, but also judges the error value of the sub-task completion time and the total time error value of the overall task, so as to dynamically correct the overall task progress and data summary, effectively improving the intelligence level of QEC aircraft maintenance safety supervision. The completion rate judgment ensures that the matching degree between the real-time model and the standard model of the overall task of all related sub-task sets is higher than the completion threshold, thereby eliminating the interference of the execution of one related sub-task set on other related sub-task sets, and ensuring the stability, safety and reliability of the overall structure. Attached Figure Description

[0021] Figure 1 A flowchart illustrating the method of this invention;

[0022] Figure 2 A schematic diagram of the system structure is provided for this invention;

[0023] Among them: 100, overall task generation module; 200, subtask generation module; 300, subtask association module; 400, marking module; 500, first judgment module; 600, second judgment module; 700, third judgment module. Detailed Implementation

[0024] The present invention will now be described in detail with reference to the accompanying drawings and specific embodiments. These embodiments are based on the technical solution of the present invention and provide detailed implementation methods and specific operating procedures. However, the scope of protection of the present invention is not limited to the following embodiments.

[0025] Example

[0026] like Figure 1 As shown, this embodiment provides an AR-based QEC aircraft maintenance safety supervision method, including the following steps:

[0027] Step S1: Obtain the aircraft parameters and maintenance objectives, and generate the overall maintenance task.

[0028] Specifically, the method for generating the overall maintenance task is as follows: upon receiving an aircraft maintenance request, obtain the aircraft parameters and maintenance objectives, and then generate the overall maintenance task.

[0029] Step S2: Based on the overall maintenance task, multiple sub-tasks are generated and sent to a pre-acquired online AR device. The device then acquires the maintenance part and its target model for each sub-task. The online AR device is used to monitor the real-time progress of the sub-tasks. Specifically:

[0030] The target model for each subtask's maintenance component is obtained based on the overall maintenance standard model. The specific acquisition process includes: upon receiving an aircraft maintenance request, acquiring the aircraft maintenance parameters and maintenance objectives, constructing a standard model of the engine after aircraft maintenance (i.e., the overall maintenance standard model), which is a model that allows for standard operations after aircraft engine maintenance and is the target model for the entire engine; and then, based on the engine standard model, obtaining the model of each subtask's maintenance component, which is the target model.

[0031] In this embodiment, the tasks, from largest to smallest, are "Overall Task - Sub-Step - Sub-Task": The overall task is the entire QEC maintenance task, which is further divided into multiple sub-steps. Each sub-step contains multiple unit tasks, and several unit tasks within a sub-step are collectively classified into one sub-task. Therefore, the specific methods for decomposing and generating multiple sub-tasks include:

[0032] The overall maintenance task is broken down into multiple sub-steps, and each sub-step is further divided into multiple unit tasks. Then, the operation time, tools used, and maintenance methods of each unit task are obtained. Multiple unit tasks with adjacent operation times, the same tools used, and the same maintenance methods are divided into a sub-task, resulting in multiple sub-task sets.

[0033] It should be noted that multiple unit tasks with adjacent operation times and the same tools and maintenance methods refer to multiple steps completed consecutively using the same tools and techniques, such as tightening four bolts of the same type in succession.

[0034] After being broken down into multiple sub-tasks, these sub-tasks are sent to pre-acquired online AR devices, and a unique identifier for the corresponding sub-task data request, i.e., the AR device identifier, is obtained. The online AR device obtains task permissions through the unique identifier, retrieves the maintenance tools, and enters the maintenance area.

[0035] Therefore, when decomposing and generating multiple subtasks, the specific process should include:

[0036] Add step labels corresponding to online AR devices to multiple sub-steps, and calculate the weight and weighted time of each sub-step to obtain the time weight of the sub-step.

[0037] Subtasks are generated based on the time weights of the sub-steps, and the step labels are used as the task names of the subtasks, which are then uploaded to the server.

[0038] The weighted proportion is the percentage of the total engine repair area in the total task that each sub-step repairs (the weighted proportions of all sub-steps are summed to 1); the weighted time is the percentage of the total engine repair time in the total task that each sub-step repairs (the weighted time of all sub-steps is summed to 1).

[0039] It is important to note that the higher the weight of a sub-step, the more sub-tasks there are. Therefore, in practical applications, it is necessary to ensure that the workload of each sub-task in all sub-steps does not differ too much.

[0040] Step S3: Based on the acquired repair parts, associate multiple subtasks to obtain a set of associated subtasks for each subtask. Specifically:

[0041] First, obtain the repair part where each subtask is located, and determine whether there is a connection relationship between two repair parts: if yes, all subtasks on the two repair parts are in the same associated subtask set; if no, do not execute; second, traverse all repair parts and generate at least one associated subtask set.

[0042] Generally, the following situations exist:

[0043] The first type is a maintenance task for a single aircraft maintenance part, in which all subtasks are performed on that maintenance part. In this case, all subtasks are located in the same set of associated subtasks.

[0044] The second type is a maintenance task composed of multiple maintenance parts, where all maintenance parts are interconnected, and all subtasks are located in the same set of associated subtasks.

[0045] The third type is a maintenance task composed of multiple maintenance parts. Only some of the maintenance parts are interconnected. In this case, the subtasks on the partially connected maintenance parts are located in the same associated subtask set, while the other subtasks are located in one or more associated subtask sets.

[0046] Step S4: When executing the current subtask, retrieve the completed subtasks from the set of associated subtasks of the current subtask and mark them as marked subtasks. Specifically:

[0047] When executing the current subtask, retrieve the completed subtasks in the associated subtask set of the current subtask, and mark them as marked subtasks. Specifically: when executing a subtask, retrieve all subtasks in the same associated subtask set, obtain the completed subtasks among these subtasks, and mark these completed subtasks to obtain marked subtasks. It should be noted that when a subtask is executed, if the subtask is the first subtask executed in the corresponding associated subtask set, then only check whether the subtask is completed before executing the next subtask.

[0048] Step S5: Obtain the real-time model of the repair part where the marked subtask is located, and determine whether the real-time model of the repair part where the marked subtask is located meets the first preset condition before and after the current subtask is executed. If it does, continue to execute the next subtask; otherwise, issue an alarm.

[0049] The first precondition is that the second matching degree is higher than the first matching degree, meaning that the matching degree between the models has improved. The first matching degree is the matching degree between the real-time model of the repair part where the current subtask is located and the corresponding target model before the current subtask is executed; the second matching degree is the matching degree between the real-time model of the repair part where the current subtask is located and the corresponding target model after the current subtask is completed.

[0050] In this embodiment, the matching degree refers to "similarity", that is, the degree of similarity between two models. By modeling the model and using existing similarity calculation methods, the similarity between the two models can be obtained.

[0051] Here, it is necessary to determine whether the execution of a subtask will promote the further completion of related subtasks. If so, the subtask is considered to have been completed reasonably and the next subtask can proceed. Otherwise, if the subtask hinders the completion of its related subtasks, it indicates an error in the execution of the subtask or a process abnormality, requiring an alarm to be issued and a job check to be performed. This usually involves re-executing the set of related subtasks containing the subtask.

[0052] In this process, to determine whether the current operation is before or after the execution of a subtask, it is also necessary to obtain the subtask's progress. Specifically, this involves using an online AR device to obtain the subtask's progress, and when the AR device detects the maintenance image or video corresponding to the step label, uploading the current maintenance image / video, the current time, and the AR device identifier (unique identifier) ​​to the server.

[0053] In fact, AR monitoring is performed when each subtask is completed. When each subtask is completed, the AR device needs to acquire images of the maintenance area. After acquiring multiple sets of images, a real-time 3D map of the maintenance area is constructed and matched with the target 3D map of the maintenance area to obtain the matching degree. If the matching degree increases, the subtask is considered to be successfully completed and the next maintenance subtask is executed. Otherwise, the maintenance subtask needs to be performed again until the maintenance subtask is successfully completed.

[0054] Step S6: After the current associated subtask set is completed, determine whether the real-time model of the repair part where all subtasks in the current associated subtask set are located meets the second preset condition. If yes, the current associated subtask set is considered to have been completed successfully; otherwise, an alarm is issued.

[0055] The second preset condition is as follows: the matching degree between the real-time model and the corresponding target model of all subtasks in the current associated subtask set is higher than a predetermined threshold. Specifically, all subtasks in the associated subtask set are extracted, and the real-time model of the overall structure composed of these subtasks is matched with the target model of the overall structure to obtain a matching value. If the matching value is higher than the predetermined threshold, then the current associated subtask set is considered to have been successfully completed; otherwise, an alarm is issued.

[0056] Generally, the predetermined threshold is no less than 99% (actually 99.99%, depending on the nature of the repair parts). That is, after completing the associated sub-tasks, if the real-time model of this batch of interrelated repair parts is more than 99.99% identical to the target model, that is, the completion error is less than one ten-thousandth, then the associated sub-task set is considered to have been successfully completed; otherwise, the associated sub-task set is considered to have been unsuccessfully completed, an alarm needs to be issued, and the associated sub-task set needs to be re-executed.

[0057] Step S7: When the completion time of all subtasks and the real-time model of the total task corresponding to all associated subtask sets meet the third preset condition, the total maintenance task is considered successfully completed.

[0058] The third preset condition specifically includes: the sub-task is completed satisfactorily, the error between the completion time of the sub-task and the total time of the overall task is lower than a predetermined error threshold, and the matching degree between the real-time model of the overall task and the pre-built standard model is higher than a predetermined completion threshold. This step mainly aims to determine whether the overall maintenance task is completed on schedule and efficiently, including the judgment of time and completion degree. Specifically:

[0059] To determine whether the overall maintenance task is complete, the time-based judgment method is as follows: In the subtask work progress, one subtask corresponds to one maintenance work card, and one maintenance work card corresponds to one actual task time bar; the planned time bar is compared with the actual time bar to monitor the overall task progress; when a subtask is generated, the total allowable error value for the completion of each subtask is generated based on the subtask weight and operation time; after the subtask is completed, not only is it determined whether the subtask was executed successfully, but also the subtask completion time error value and the total time error value of the overall task are compared, and the overall task execution process is dynamically adjusted.

[0060] The method for judging the completion rate is as follows: the engine model after QEC repair is compared with the standard engine model again. Only when the matching degree between the overall task structure model, which includes all related sub-task sets, and the standard model is higher than the completion threshold is the overall task execution completion rate considered qualified. This can eliminate the interference of the execution of one related sub-task set on other related sub-task sets, and ensure that the overall structure is completed stably, safely and reliably.

[0061] In this embodiment, the server determines whether the sub-task has been completed based on the maintenance images / videos, and calculates the total task progress based on the weighted proportion of all currently completed sub-tasks.

[0062] The online AR device introduced in this embodiment includes a camera, a display screen, a processor, and a human-computer interaction terminal. The online AR device is used to obtain the work progress of sub-tasks in real time and assists in the execution of steps S1 to S7 throughout the process. The specific application process includes:

[0063] (1) When a maintenance request is received, a general maintenance task is generated.

[0064] When generating the overall maintenance task, a list of required maintenance tools is generated, and it is determined whether the required maintenance tools are complete. If so, the maintenance tool requisition number is obtained; otherwise, a maintenance tool requisition message is issued.

[0065] (2) Obtain the online AR device, decompose the maintenance task into sub-tasks, and send them to the online AR device. The online AR device receives the sub-task processing request and obtains the corresponding unique identifier.

[0066] Specifically, the process involves acquiring online AR devices, generating sub-tasks corresponding to the AR devices based on their work card data and location, and sending these sub-tasks to the AR devices. Specifically, this involves sending the corresponding maintenance tool requisition code to the AR device. Furthermore, after sending the sub-tasks to the AR devices, the associated AR devices are linked. The work card data includes worker level, work duration, work direction, and historical work records.

[0067] (3) Issue task permissions and task standard execution guidelines to the online AR device. The online AR device obtains the task permissions and task standard execution guidelines based on its unique identifier and displays them on the screen. The task standard execution guidelines include route guidance, tool usage, and operation information. The operation information includes text, images, and videos. After issuing task permissions to the AR device, grant the AR device the permission to apply for maintenance tools.

[0068] In practice, authentication is required with the AR device. If authentication is successful, task permissions are granted to the AR device; otherwise, no operation is performed. Task permissions include: access to view, edit, revise, and upload task data.

[0069] (4) Online AR devices obtain the progress of sub-tasks in real time and execute sub-tasks.

[0070] Specifically, the AR device acquires real-time operation video through a camera, compares the real-time operation video with the task standard execution guidelines through a processor to obtain the sub-task work progress, and records the sub-task work progress to the sub-task form through the human-computer interaction terminal to provide feedback to the worker.

[0071] (5) When a subtask is completed, the associated subtask set is executed.

[0072] (6) Determine whether the overall maintenance task is completed. If yes, collect all AR device forms and summarize the task; otherwise, continue to execute (2).

[0073] Furthermore, this embodiment also provides an AR-based QEC aircraft maintenance safety supervision system. The system implements the steps of the aforementioned method, including a total task generation module 100, a sub-task generation module 200, a sub-task association module 300, a marking module 400, a first judgment module 500, a second judgment module 600, and a third judgment module 700. Specifically, the total task generation module 100 acquires maintenance parameters and maintenance objectives of the aircraft to generate a total maintenance task; the sub-task generation module 200 acquires the maintenance parts for each sub-task, decomposes it into multiple sub-tasks based on the total maintenance task, and sends them to a pre-acquired online AR device, while simultaneously acquiring the target model of each maintenance part. The online AR device is used to acquire the real-time progress of the sub-tasks; the sub-task association module 300 associates multiple sub-tasks based on the acquired maintenance parts to obtain a set of associated sub-tasks for each sub-task; and the marking module 400, when executing the current sub-task, retrieves completed sub-tasks from the set of associated sub-tasks of the current sub-task and marks them as marks. The system comprises three subtasks: a first judgment module 500, which acquires the real-time model of the repair part where the subtask is located, and determines whether the real-time model meets the first preset condition before and after the execution of the current subtask. If yes, it continues to execute the next subtask; otherwise, it issues an alarm. A second judgment module 600, after the current associated subtask set is completed, determines whether the real-time models of all repair parts where subtasks in the current associated subtask set are located meet the second preset condition. If yes, the current associated subtask set is considered complete; otherwise, it issues an alarm. A third judgment module 700, when all subtasks are completed and the real-time model of the total task corresponding to all associated subtask sets meets the third preset condition, the overall repair task is considered complete. In addition, the system includes an AR association module and an authentication module. The AR association module associates subtasks with AR glasses and sends the subtasks to the AR device. The authentication module authenticates the AR device; upon successful authentication, the permission issuance module issues task permissions to the AR device. The specific execution steps of each module are the same as those of the aforementioned method and will not be repeated here.

[0074] In summary, the AR-based QEC (Quality, Emergency, and Completion) aircraft maintenance safety supervision method and system provided by this invention can intelligently generate overall tasks and sub-tasks. Utilizing the provided real-time response method, workers can view task details and execute tasks according to instructions via AR devices, and monitor sub-task progress through AR. Simultaneously, information is shared between related sub-tasks, automatically adjusting the overall task progress based on sub-task completion, and automatically collecting and summarizing data. Based on this, the solution provided by this invention can automatically allocate tasks and provide real-time guidance and recording on AR devices, eliminating the need for workers to manually consult documents and fill out forms. Furthermore, the interoperability between related sub-tasks allows workers to better understand task progress and coordination with other tasks, automatically verifying sub-task completion and correcting the overall task progress and data summary. This highly intelligent approach effectively avoids low-level errors caused by human error, significantly improving safety levels. In practical applications, this invention also facilitates coordination among staff in various positions and can be combined with technologies such as communication between multiple AR devices and control center intervention via AR device login to achieve more intelligent and efficient QEC aircraft maintenance safety supervision.

[0075] The preferred embodiments of the present invention have been described in detail above. It should be understood that those skilled in the art can make numerous modifications and variations based on the concept of the present invention without creative effort. Therefore, all technical solutions that can be obtained by those skilled in the art based on the concept of the present invention through logical analysis, reasoning, or limited experimentation on the basis of existing technology should be within the scope of protection defined by the claims.

Claims

1. An AR-based QEC (Quality, Emergency, and Existing) aircraft maintenance safety supervision method, characterized in that, Includes the following steps: Obtain aircraft maintenance parameters and maintenance objectives, and generate a comprehensive maintenance task; Based on the overall maintenance task, multiple sub-tasks are generated and sent to a pre-acquired online AR device. The repair part and target model of each sub-task are then obtained. The online AR device is used to obtain the work progress of the sub-tasks in real time. Based on the acquired repair parts, the multiple subtasks are associated to obtain a set of associated subtasks for each subtask; When executing the current subtask, retrieve the completed subtasks from the set of associated subtasks of the current subtask and mark them as marked subtasks; Obtain the real-time model of the repair part where the marked subtask is located, and determine whether the real-time model meets the first preset condition before and after the current subtask is executed. If it does, continue to execute the next subtask; otherwise, issue an alarm. After the current associated subtask set is completed, determine whether the real-time model of the repair part of all subtasks in the current associated subtask set meets the second preset condition. If yes, the current associated subtask set is considered to have been completed successfully; otherwise, an alarm is issued. The maintenance task is considered complete when the completion time of all subtasks and the real-time model of the total task corresponding to all associated subtask sets meet the third preset condition.

2. The AR-based QEC aircraft maintenance safety supervision method according to claim 1, characterized in that, The process of obtaining the target model includes: Based on the aircraft parameters and maintenance objectives, construct a standard model of the engine after aircraft maintenance; Based on the engine standard model, obtain the target model of the maintenance part for each sub-task.

3. The AR-based QEC aircraft maintenance safety supervision method according to claim 1, characterized in that, The specific methods for decomposing and generating multiple subtasks include: The overall maintenance task is divided into multiple sub-steps, and each sub-step is broken down to obtain multiple unit tasks; The operation time, tools used, and maintenance method of each unit task are obtained. Multiple unit tasks with adjacent operation times, the same tools used, and the same maintenance method are divided into a subtask to obtain multiple subtasks.

4. The AR-based QEC aircraft maintenance safety supervision method according to claim 3, characterized in that, When decomposing and generating multiple subtasks, the specific process includes: Add step labels corresponding to online AR devices to multiple sub-steps, and calculate the weight and weighted time of each sub-step to obtain the time weight of the sub-step. The subtask is generated based on the time weight of the sub-step, and the step label is used as the task name of the subtask, which is then uploaded to the server.

5. The AR-based QEC aircraft maintenance safety supervision method according to claim 1, characterized in that, Based on the acquired repair parts, the multiple sub-tasks are associated, and the specific process includes: Obtain the repair component for each subtask and determine whether there is a connection between two repair components: If yes, all subtasks on the two repair parts are in the same set of associated subtasks; if no, they are not executed. Iterate through all repair parts and generate at least one set of associated subtasks.

6. The AR-based QEC aircraft maintenance safety supervision method according to claim 1, characterized in that, The first preset condition specifically includes: the second matching degree is higher than the first matching degree, wherein the first matching degree is the matching degree between the real-time model and the corresponding target model before the current subtask is executed, and the second matching degree is the matching degree between the real-time model and the corresponding target model after the current subtask is completed.

7. The AR-based QEC aircraft maintenance safety supervision method according to claim 1, characterized in that, The second preset condition specifically includes: the matching degree between the real-time model of the repair part of all subtasks in the current associated subtask set and the corresponding target model is higher than a predetermined threshold.

8. The AR-based QEC aircraft maintenance safety supervision method according to claim 1, characterized in that, The third preset condition specifically includes: the subtask is completed successfully, the error between the completion time of the subtask and the total time of the total task is lower than a predetermined error threshold, and the matching degree between the real-time model of the total task and the pre-built standard model is higher than a predetermined completion threshold.

9. The AR-based QEC aircraft maintenance safety supervision method according to claim 1, characterized in that, The online AR device includes a camera, a display screen, a processor, and a human-computer interaction terminal. The online AR device is used to obtain the real-time progress of sub-tasks, and the specific process includes: Receive subtask processing requests and obtain the corresponding unique identifier; The task permissions and standard execution instructions are obtained based on the unique identifier and displayed on the screen. The real-time operation video is acquired using a camera, and the sub-task work progress is obtained by comparing the real-time operation video with the task standard execution guidance using a processor. Use the human-computer interaction terminal to record the progress of subtasks to the subtask form.

10. An AR-based QEC (Quality, Emergency, and Critical) aircraft maintenance safety monitoring system, characterized in that, The system is used to implement the method as described in any one of claims 1-9, specifically including: The overall task generation module is used to obtain the aircraft maintenance parameters and maintenance objectives, and generate the overall maintenance task. The subtask generation module is used to obtain the repair part of each subtask, and decompose and generate multiple subtasks according to the total repair task, and send them to the pre-acquired online AR device. At the same time, it obtains the target model of each repair part. The online AR device is used to obtain the work progress of the subtask in real time. The subtask association module associates the multiple subtasks based on the acquired repair parts to obtain a set of associated subtasks for each subtask. The marking module retrieves completed subtasks from the set of associated subtasks of the current subtask when executing the current subtask, and marks them as marked subtasks; The first judgment module obtains the real-time model of the repair part where the marked subtask is located, and judges whether the real-time model meets the first preset condition before and after the current subtask is executed. If it does, the next subtask is executed; otherwise, an alarm is issued. The second judgment module, after the current associated subtask set is completed, judges whether the real-time model of the repair part of all subtasks in the current associated subtask set meets the second preset condition. If it does, the current associated subtask set is considered to have been completed successfully; otherwise, an alarm is issued. The third judgment module determines that the maintenance task is considered complete when all subtasks have been executed and the real-time model of the total task corresponding to all associated subtask sets meets the third preset condition.

Images