CN-121998606-A - AR-based QEC detection method and system

CN121998606ACN 121998606 ACN121998606 ACN 121998606ACN-121998606-A

Abstract

The invention relates to a QEC detection method and system based on AR. The method comprises the steps of disassembling a pre-constructed engine standard model into part units, obtaining three-dimensional model groups in the installation process of all the part units, obtaining an engine real-time model based on AR equipment, obtaining a first part unit with the largest difference degree when the difference degree between the engine real-time model and the standard model is higher than a first threshold value, judging whether the corresponding real-time model is matched with the three-dimensional model groups, maintaining the first part unit to the corresponding standard model state if the corresponding real-time model is matched with the three-dimensional model groups, and re-obtaining the engine real-time model to continue to execute when all the part units contacted with the first part unit synchronously change to the corresponding standard model state, otherwise, sending a QEC request. Compared with the prior art, the invention has the advantages of improving the safety and efficiency of the whole operation checking and checking process of QEC work and the like.

Inventors

ZHANG HAILIN
ZENG XIAOWEN
HUANG YANQING
LIU YADONG
XU MINYAN
YUE TING
ZHOU ZUOCHENG
DAI GUOHONG
Bai Minjian
Jiang Minxu
XUE WEI
KONG LINGXIN

Assignees

东方航空技术有限公司
中移物联网有限公司

Dates

Publication Date: 20260508
Application Date: 20241105

Claims (10)

1. The AR-based QEC detection method is characterized by comprising the following steps of: S1, disassembling a pre-constructed engine standard model into part units, and obtaining a three-dimensional model group in the installation process of all the part units, wherein the three-dimensional model at the end of the installation of each part unit is a corresponding part unit standard model; S2, acquiring an engine real-time model based on the AR equipment acquired in advance; S3, judging whether the difference degree of the real-time engine model and the standard engine model is higher than a first preset threshold, if so, acquiring a first part unit with the largest difference degree, and executing S4, otherwise, not executing; S4, judging whether the real-time model corresponding to the first part unit is matched with the three-dimensional model group corresponding to the first part unit, if so, executing S5, otherwise, sending a QEC request; And S5, maintaining the first part unit to the corresponding part unit standard model state, judging whether all the part units contacted with the first part unit synchronously change to the corresponding part unit standard model state, if so, returning to S2 for continuous execution, and otherwise, sending a QEC request.
2. The AR-based QEC detection method of claim 1, wherein the specific construction process of the engine standard model comprises: Acquiring engine part information and constructing an independent model of each part; Assembling to obtain an engine preliminary model based on the independent model of each part, the pre-acquired part assembly information and the assembly joint model; acquiring engine flight data, and correcting the engine preliminary model by utilizing the flight data to obtain an engine correction model; and acquiring historical disassembly and assembly information of the engine, and checking with the engine correction model to obtain an engine standard model.
3. The AR-based QEC detection method of claim 1, wherein the process of obtaining the three-dimensional model set of the individual part units specifically comprises: Monitoring an installation process by using pre-acquired AR equipment; acquiring all installation nodes of the current part unit from the beginning of installation to the end of installation; and acquiring all three-dimensional models of the current part unit relative to the whole engine based on all the installation nodes to obtain a corresponding three-dimensional model group.
4. The AR-based QEC detection method of claim 1, wherein S2 specifically comprises: AR equipment is obtained, and a target object is determined; Based on the AR equipment and a ranging principle, acquiring the distance between the AR equipment and the target object under a preset angle, and constructing a three-dimensional coordinate; And obtaining line, surface and volume distribution data by utilizing three-dimensional coordinates under at least three groups of preset angles, and establishing an engine real-time model.
5. The AR-based QEC detection method of claim 1, wherein determining whether the degree of difference between the real-time engine model and the standard engine model is higher than a first preset threshold comprises: The method comprises the steps of performing point integration on structural surfaces in the real-time engine model and the standard engine model to obtain data of a minimum unit; overlapping the engine real-time model and the engine standard model based on the data of the minimum unit, and acquiring and comparing positions of all part units in the overlapped three-dimensional model; When the second part unit and the third part unit are positioned at the same position, comparing the second part unit with the third part unit and obtaining a difference value; after shielding the second part unit and the third part unit, comparing the real-time engine model with the standard engine model again until all the part units are traversed; and integrating all the obtained difference values, and calculating a final difference degree value according to a preset weight coefficient.
6. The AR-based QEC detecting method of claim 5, wherein when the structural surface is a curved surface, the data of each point in the structural surface is sequentially compared according to a X, Y, Z direction, and the data of the minimum unit is obtained by point aggregation.
7. The AR-based QEC detection method according to claim 1, wherein S3 further comprises, when the degree of difference between the engine real-time model and the engine standard model is higher than a first preset threshold, Positioning a differentiation area of the engine real-time model and the engine standard model; and displaying an explosion diagram of the engine standard model corresponding to the differentiation area and an explosion diagram of the engine real-time model.
8. The AR-based QEC detection method of claim 1, wherein determining whether the real-time model corresponding to the first part unit matches the three-dimensional model set corresponding to the first part unit comprises: acquiring a real-time model corresponding to the first part unit; Comparing the real-time model with each three-dimensional model in the three-dimensional model group corresponding to the first part unit; And judging whether the matching degree between the real-time model and any three-dimensional model in the three-dimensional model group is higher than a second preset threshold value.
9. The AR-based QEC detection method of claim 1, wherein the execution procedure of the QEC request specifically comprises: Acquiring the corresponding relation among the part numbers according to the engine standard model; acquiring the position of the part unit with the deviation, and generating a maintenance task; Generating a corresponding explosion diagram, a flow diagram and a guide diagram according to the maintenance task, and acquiring a plurality of branch steps; according to the corresponding relation among the component numbers, taking the branch steps as a prepositive step, and establishing a corresponding node step; And establishing a maintenance task tree according to the node step and the corresponding branch step.
10. An AR-based QEC detection system for implementing the method of any of claims 1 to 9, said system comprising a standard setup module, a real-time acquisition module, a first judgment module, a second judgment module, a verification module and a QEC request module: The standard building module is used for disassembling a pre-built engine standard model into part units, and obtaining a three-dimensional model group in the installation process of all the part units, wherein the three-dimensional model at the end of the installation of each part unit is a corresponding part unit standard model; The real-time acquisition module is used for acquiring an engine real-time model based on the pre-acquired AR equipment; The first judging module is used for judging whether the difference degree of the real-time engine model and the standard engine model is higher than a first preset threshold value, if so, a first part unit with the largest difference degree is obtained, and the second judging module is started, otherwise, the first part unit is not executed; The second judging module is used for judging whether the real-time model corresponding to the first part unit is matched with the three-dimensional model group corresponding to the first part unit, if yes, the checking module is started, and otherwise, the QEC request module is started to send a QEC request; The inspection module is used for maintaining the first part unit to the corresponding part unit standard model state, judging whether all the part units contacted with the first part unit synchronously change to the corresponding part unit standard model state, if so, returning to the real-time acquisition module to continue execution, otherwise, starting the QEC request module to send a QEC request.

Description

AR-based QEC detection method and system Technical Field The invention relates to the technical field of infrastructure and IT support, in particular to a QEC detection method and system based on AR. Background Aviation maintenance refers to maintenance and repair of an aircraft and technical equipment on the aircraft, and ensures the safety of the aircraft, and is a precondition and a necessary condition for the use of the aircraft and an important component of the aviation industry. The aero-engine is a heart of an aircraft, the aero-engine maintenance is a part of the aircraft maintenance and is an important component of the aviation duty work, and the areas where the aero-engine is most prone to faults are a high-pressure gas compressor, a combustion chamber and a high-pressure turbine. At present, the aero-engine is maintained, QEC (Quick ENGINE CHANGE, quick change engine) work is a major issue, and QEC work is an aviation first-line work implemented on an aircraft core component engine, and has the characteristics of more assembly and disassembly components, high assembly and disassembly frequency and high safety risk. At present, QEC work mainly depends on manual work, and staff still need to manually read auxiliary equipment and manually fill in forms on the auxiliary equipment in the process of work. In addition, because QEC work is very tedious, need a large amount of staff to carry out a large amount of operation steps, but the relativity between the operation of different staff is still insufficient, auxiliary assembly just obtains the aircraft maintenance data and feeds back yet, neither QEC maintenance is guided in real time, nor QEC work multi-step associated analysis, can only rely on maintenance personnel experience real-time operation, and whole operation inspection verification process security is difficult to be ensured. Disclosure of Invention The invention aims to overcome the defects of the prior art and provide an AR-based QEC detection method and an AR-based QEC detection system, wherein the method applies an augmented reality (Augmented Reality, AR) technology to maintenance work of a machine, so that high automation of QEC detection is realized, workers are free from complicated manual operation, and the safety of the whole operation checking and checking process of QEC work can be effectively improved. The aim of the invention can be achieved by the following technical scheme: According to the first aspect of the invention, the AR-based QEC detection method comprises the following steps of S1, disassembling a pre-built engine standard model into part units, obtaining a three-dimensional model group in the installation process of all the part units, wherein the three-dimensional model at the end of installation of each part unit is a corresponding part unit standard model, S2, obtaining an engine real-time model based on pre-obtained AR equipment, S3, judging whether the difference degree between the engine real-time model and the engine standard model is higher than a first preset threshold value, obtaining a first part unit with the largest difference degree and executing S4 if the difference degree is higher than the first preset threshold value, otherwise not executing the first part unit, S4, judging whether a real-time model corresponding to the first part unit is matched with the three-dimensional model group corresponding to the first part unit, if the real-time model is matched with the three-dimensional model group corresponding to the first part unit, executing S5, otherwise, maintaining the first part unit to the corresponding part unit standard model state, judging whether all the part units contacted with the first part unit synchronously change to the corresponding part unit standard model state, if the first part unit is higher than the first part unit standard state, and executing the QEC request if the corresponding part unit is not synchronously, and executing the QEC request if the QEC request is continuously sent. The method comprises the steps of obtaining engine part information and building an independent model of each part, assembling to obtain an engine preliminary model based on the independent model of each part, the pre-obtained part assembly information and the assembly joint model, obtaining engine flight data, correcting the engine preliminary model by utilizing the flight data to obtain an engine correction model, obtaining engine historical disassembly and assembly information, and correcting with the engine correction model to obtain the engine standard model. The method comprises the steps of monitoring an installation process by using pre-acquired AR equipment, acquiring all installation nodes from the beginning of installation to the end of installation of a current part unit, and acquiring all three-dimensional models of the current part unit relative to the whole engine based on all the installation nodes to obtain a corresponding three-dim