CN114104334B - Airplane inspection method based on automatic image recognition mode of moving trolley - Google Patents
Airplane inspection method based on automatic image recognition mode of moving trolley Download PDFInfo
- Publication number
- CN114104334B CN114104334B CN202111499113.7A CN202111499113A CN114104334B CN 114104334 B CN114104334 B CN 114104334B CN 202111499113 A CN202111499113 A CN 202111499113A CN 114104334 B CN114104334 B CN 114104334B
- Authority
- CN
- China
- Prior art keywords
- management platform
- data acquisition
- aircraft
- trolley
- inspection
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000007689 inspection Methods 0.000 title claims abstract description 89
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000012423 maintenance Methods 0.000 claims abstract description 56
- 238000007726 management method Methods 0.000 claims description 60
- 238000005516 engineering process Methods 0.000 abstract description 8
- 238000007405 data analysis Methods 0.000 abstract description 4
- 230000002159 abnormal effect Effects 0.000 abstract description 3
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 238000013024 troubleshooting Methods 0.000 abstract 1
- 238000004458 analytical method Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 3
- 230000000630 rising effect Effects 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 239000013078 crystal Substances 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B64—AIRCRAFT; AVIATION; COSMONAUTICS
- B64F—GROUND OR AIRCRAFT-CARRIER-DECK INSTALLATIONS SPECIALLY ADAPTED FOR USE IN CONNECTION WITH AIRCRAFT; DESIGNING, MANUFACTURING, ASSEMBLING, CLEANING, MAINTAINING OR REPAIRING AIRCRAFT, NOT OTHERWISE PROVIDED FOR; HANDLING, TRANSPORTING, TESTING OR INSPECTING AIRCRAFT COMPONENTS, NOT OTHERWISE PROVIDED FOR
- B64F5/00—Designing, manufacturing, assembling, cleaning, maintaining or repairing aircraft, not otherwise provided for; Handling, transporting, testing or inspecting aircraft components, not otherwise provided for
- B64F5/60—Testing or inspecting aircraft components or systems
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B62—LAND VEHICLES FOR TRAVELLING OTHERWISE THAN ON RAILS
- B62D—MOTOR VEHICLES; TRAILERS
- B62D63/00—Motor vehicles or trailers not otherwise provided for
- B62D63/02—Motor vehicles
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B62—LAND VEHICLES FOR TRAVELLING OTHERWISE THAN ON RAILS
- B62D—MOTOR VEHICLES; TRAILERS
- B62D63/00—Motor vehicles or trailers not otherwise provided for
- B62D63/02—Motor vehicles
- B62D63/04—Component parts or accessories
Landscapes
- Engineering & Computer Science (AREA)
- Transportation (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- Manufacturing & Machinery (AREA)
- Aviation & Aerospace Engineering (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
- Machines For Laying And Maintaining Railways (AREA)
Abstract
An airplane inspection method based on an automatic image recognition mode of a moving trolley. It includes constructing an aircraft inspection system; the motion trolley moves 360 degrees around the plane to be detected; determining a data acquisition point position; collecting point location image information sources; troubleshooting or safety hazards; until all data acquisition points are inspected, and the like. The aircraft inspection method based on the automatic image recognition mode of the moving trolley has the following beneficial effects: the moving trolley has stronger loading capacity, can bear required airborne inspection equipment and has lower required cost. Therefore, the requirements of airport clearance protection areas can be met, and the required aircraft inspection tasks can be completed from the ground. The automatic image recognition technology and the big data analysis technology are combined, so that the level of the abnormal problems of the equipment found and analyzed by maintenance patrols can be improved.
Description
Technical Field
The invention belongs to the technical field of aircraft maintenance inspection and repair inspection, and particularly relates to an aircraft inspection method based on an automatic image recognition mode of a moving trolley.
Background
With the high-speed development of the aviation industry, the aircraft maintenance inspection and repair inspection method is increasingly perfect, the specialized and automatic level of inspection equipment is gradually improved, the traditional manual operation mode is gradually replaced by automation, and the intelligent and convenient automatic maintenance inspection and repair inspection method becomes the current main development direction. The intelligent inspection is carried out from early information extraction and manual analysis and judgment, and the intelligent inspection is gradually carried out to the stage of assisting the manual judgment by the intelligent system analysis, so that inspection personnel can be helped to make more timely, accurate and systematic judgment by means of a large amount of data analysis and deep learning. Among them, the automatic image recognition technology is a very convenient and effective means, and is an important field of artificial intelligence.
The daily inspection can timely and accurately master the running condition of the equipment, discover faults and potential safety hazards existing in the equipment as soon as possible, and effectively ensure the safe and reliable running of the equipment.
At present, most of the equipment used in the existing maintenance inspection and repair inspection methods are unmanned aerial vehicles, technicians plan inspection routes according to experience, enable the unmanned aerial vehicles to inspect according to the planned inspection routes through the airborne inspection equipment, solve the inspection discovery problem in time, and synchronously upload the inspection discovery problem to a background server or a data terminal for backup.
However, the above technology has the following technical problems:
unmanned aerial vehicles generally have weak load capacity and have excessive cost for carrying the overload on-board inspection equipment. And the limit area is near the airport, the extension line of each end of the airport runway is 15 km, and the range of 6 km at each side of the airport runway is a clearance protection area, and the aircraft with low speed and small speed is strictly forbidden to ascend and descend, so that the unmanned aerial vehicle and other aircraft type equipment are not suitable to be used when the aircraft is overhauled.
Disclosure of Invention
In order to solve the problems, an object of the present invention is to provide an aircraft inspection method based on an automatic image recognition system of a moving trolley.
In order to achieve the above object, the method for inspecting an aircraft based on an automatic image recognition method of a moving trolley provided by the invention comprises the following steps in sequence:
1) An aircraft inspection system is constructed, and the aircraft inspection system comprises a management platform for aircraft maintenance inspection and repair inspection, a motion trolley, an automatic lifting guide rail, a two-degree-of-freedom cradle head, a motion track recorder and an image recorder; wherein the lower end of the automatic lifting guide rail is fixed on the moving trolley; the two-degree-of-freedom cradle head is arranged at the upper end of the automatic lifting guide rail; the motion trail recorder and the image recorder are respectively arranged on the motion trolley and the two-degree-of-freedom cradle head; the management platform is respectively connected with the motion trolley, the automatic lifting guide rail, the two-degree-of-freedom cradle head, the motion track recorder and the image recorder in a wireless manner;
2) Under the control of the management platform, the movement trolley moves 360 degrees around the outer contour of the airplane to be detected, and the movement is performed while the running track of the movement trolley is recorded in real time by using the movement track recorder and is uploaded to the management platform;
3) A technician determines a plurality of data acquisition points for maintenance/maintenance inspection on the running track according to task requirements on a management platform, and then the management platform automatically plans the movement track of the movement trolley and sends movement track instructions to the movement trolley;
4) The motion trolley moves to an initial data acquisition point according to the motion track instruction, then the height and the angle of the image recorder are adjusted through the automatic lifting guide rail and the two-degree-of-freedom cradle head, then the image recorder is used for acquiring images of the aircraft to be detected from different heights and angles, and an image information source of the initial data acquisition point is obtained and uploaded to the management platform;
5) The management platform automatically or manually checks faults or potential safety hazards on the aircraft to be detected, which are observed from the initial data acquisition point according to the image information source of the initial data acquisition point;
6) And (3) the movement trolley sequentially moves to the residual data acquisition points according to the planned movement track, and then the steps (4) -5) are repeated to obtain the image information source of the residual data acquisition points until all the data acquisition points are inspected.
In step 1), the management platform adopts an AT89C52 singlechip as a control chip, and the circuit mainly comprises: the device comprises a singlechip power supply circuit, a clock circuit, a reset circuit, a voltage reducing module and a stepping motor driver.
In the step 3), the method for automatically planning the motion trail of the motion trolley by the management platform is as follows:
and storing the aircraft inspection maintenance data on the driving track into a database of a management platform, establishing an individual aircraft maintenance inspection and maintenance inspection model, inputting the aircraft inspection maintenance data into the maintenance inspection and maintenance inspection model, outputting the maintenance inspection and maintenance inspection model, namely, the maintenance points and important parts with high failure and potential safety hazards, and finally taking the maintenance points and important parts as data acquisition points.
In step 4), the motion trolley moves to an initial data acquisition point according to the motion track instruction, then the height and the angle of the image recorder are adjusted through the automatic lifting guide rail and the two-degree-of-freedom cradle head, then the image recorder is used for acquiring images of the aircraft to be detected from different heights and angles, and the method for obtaining the image information source of the initial data acquisition point comprises the following steps:
4.1 According to the motion trail instruction, the motion trolley moves to the initial data acquisition point by utilizing the self-contained navigation motion function of the motion trail recorder, and stops moving;
4.2 Under the control of the management platform, the automatic lifting guide rail moves up and down until the image recorder reaches a certain height position among the preset low position, the preset middle position and the preset high position, and the operation of the automatic lifting guide rail is stopped;
4.3 Under the control of the management platform, the two-degree-of-freedom cradle head horizontally rotates and vertically overturns, when the image recorder is in a low position, a middle position and a high position, the two-degree-of-freedom cradle head rotates to a bottom view, a head view and a top view state respectively, and a lens on the image recorder is aligned with an airplane to be detected, so that the operation of the two-degree-of-freedom cradle head is stopped;
4.4 Collecting a plurality of low-level upward shooting, middle-level downward shooting or high-level downward shooting images of the airplane to be detected from the height and the angle by using an image recorder, and transmitting the images to a management platform;
4.5 Under the control of the management platform, the automatic lifting guide rail performs lifting movement until the image recorder reaches another height position, and the steps 4.3) -4.4) are repeated;
4.6 Under the control of the management platform, the automatic lifting guide rail performs lifting movement until the image recorder reaches the last height position, and the steps 4.3) -4.4) are repeated;
4.7 All the low-position upward shooting, the middle-position horizontal shooting and the high-position downward shooting images form an image information source of a starting data acquisition point.
In step 5), the method for the management platform to automatically or manually check the faults or potential safety hazards on the aircraft to be detected observed from the initial data acquisition point according to the image information source of the point comprises the following steps:
5.1 The management platform automatically or manually analyzes the reliability and the correctness of the information contained in the image information source of the initial data acquisition point to judge the reliability and the correctness of the image information source;
5.2 Comparing the related parameters in the image information source with a preset threshold value, if the related parameters exceed the threshold value, judging that the fault or potential safety hazard exists in the aircraft parts observed from the point location, and timely reporting to a crew for overhaul through a management platform;
5.3 If no fault or potential safety hazard exists, the point inspection maintenance work is completed.
The aircraft inspection method based on the automatic image recognition mode of the moving trolley has the following beneficial effects: the moving trolley has stronger loading capacity, can bear required airborne inspection equipment and has lower required cost. Therefore, the requirements of airport clearance protection areas can be met, and the required aircraft inspection tasks can be completed from the ground. The automatic image recognition technology and the big data analysis technology are combined, so that the level of the abnormal problems of the equipment found and analyzed by maintenance patrols can be improved.
Drawings
Fig. 1 is a flowchart of an aircraft inspection method based on an automatic image recognition mode of a moving trolley.
FIG. 2 is a schematic diagram of the workflow of an aircraft inspection method based on the automatic image recognition method of the moving trolley;
fig. 3 is a schematic diagram of the effect of low-level elevation shooting, middle-level elevation shooting and high-level depression shooting of a certain data acquisition point in the aircraft inspection method based on the automatic image recognition mode of the moving trolley.
Detailed Description
The invention will now be described in detail with reference to the drawings and specific examples.
As shown in fig. 1 to 3, the aircraft inspection method based on the automatic image recognition mode of the moving trolley provided by the invention comprises the following steps in sequence:
1) An aircraft inspection system is constructed, and the aircraft inspection system comprises a management platform for aircraft maintenance inspection and repair inspection, a moving trolley 1, an automatic lifting guide rail 2, a two-degree-of-freedom cradle head 3, a motion trail recorder 4 and an image recorder 5; wherein the lower end of the automatic lifting guide rail 2 is fixed on the moving trolley 1; the two-degree-of-freedom cradle head 3 is arranged at the upper end of the automatic lifting guide rail 2; the motion trail recorder 4 and the image recorder 5 are respectively arranged on the motion trolley 1 and the two-degree-of-freedom cradle head 3; the management platform is respectively connected with the moving trolley 1, the automatic lifting guide rail 2, the two-degree-of-freedom cradle head 3, the moving track recorder 4 and the image recorder 5 in a wireless way.
The management platform adopts an AT89C52 singlechip as a control chip, and the circuit mainly comprises: the device comprises a singlechip power supply circuit, a clock circuit, a reset circuit, a voltage reducing module and a stepping motor driver. Wherein the functions of each part are as follows: (1) a singlechip power supply circuit: providing a 5V power supply for the singlechip and providing logic voltage for the circuit; (2) a clock circuit: providing a 12.0592MHz crystal oscillator for the singlechip; (3) a reset circuit: for manual reset; (4) a step-down module: 24V to 6V provides voltage for the steering engine; (5) stepper motor driver: the stepper motor is driven 57. The driving mode of the steering engine is PWM, the singlechip outputs PWM signals with different pulse widths to control the position of the steering engine, the DS3230 steering engine has a pulse width range of 0.5 ms-2.5 ms, and when the input pulse width is 0.5ms, 1.5ms and 2.5ms, the steering engine positions are respectively 0, 90 and 180 degrees. The singlechip outputs PWM signals through ports P0.6 and PO.7, and the PWM signals are respectively used for controlling a steering engine 1 (horizontal rotation steering engine), and a steering engine 2 turns up and down. The 57-phase four-wire stepper motor is driven by a DM542 driver. P2.3 of the singlechip provides pulse signals, duty ratio is 50%, and frequency is 1000Hz. P2.4 provides direction signals, and the high level and the low level respectively correspond to positive and negative directions.
2) Under the control of the management platform, the motion trolley 1 moves 360 degrees around the outer contour of the airplane 6 to be detected, and the motion track recorder 4 is used for recording the running track of the motion trolley 1 in real time and uploading the running track to the management platform;
as shown in fig. 2, in the present invention, the aircraft 6 to be detected is a boeing 747 aircraft.
3) A technician determines a plurality of data acquisition points for maintenance/maintenance inspection on the running track according to task requirements on a management platform, and then the management platform automatically plans the movement track of the movement trolley 1 and sends movement track instructions to the movement trolley 1;
the method for automatically planning the motion trail of the motion trolley 1 by the management platform comprises the following steps:
and storing a large amount of aircraft inspection maintenance data into a database of a management platform, establishing an individual aircraft maintenance inspection and maintenance inspection model, constructing the maintenance inspection and maintenance inspection model based on a neural network, training by using the aircraft inspection maintenance data, inputting the aircraft inspection maintenance data on a running track into the trained maintenance inspection and maintenance inspection model, outputting the maintenance inspection and maintenance inspection model as maintenance points and important parts with high failure and potential safety hazards, and finally taking the maintenance points and the important parts as data acquisition points.
The number of the data acquisition points is variable, six data acquisition points are selected in the invention, and the number of the data acquisition points is 1 to 6.
4) The motion trolley 1 moves to an initial data acquisition point according to the motion trail instruction, then the height and the angle of the image recorder 5 are adjusted through the automatic lifting guide rail 2 and the two-degree-of-freedom cradle head 3, then the image recorder 5 is used for acquiring images of the aircraft 6 to be detected from different heights and angles, and an image information source of the initial data acquisition point is obtained and uploaded to the management platform;
in the invention, the data acquisition point position 1 is used as the initial data acquisition point position. The dark arrows in fig. 2 indicate the moving direction of the moving trolley 1 along the moving track, and the light arrows indicate the image effect of the moving trolley 1 collected at the corresponding data collection points.
The specific method comprises the following steps:
4.1 According to the motion track instruction, the motion trolley 1 moves to the initial data acquisition point by utilizing the self-contained navigation motion function of the motion track recorder 4, and stops the motion of the motion trolley 1;
4.2 As shown in fig. 3, under the control of the management platform, the automatic lifting guide rail 2 performs lifting movement until the image recorder 5 reaches a certain height position among the preset low position, middle position and high position, and the operation of the automatic lifting guide rail 2 is stopped;
in fig. 3, the automatic lifting guide rail 2 on the upper side is in a low position, the automatic lifting guide rail 2 on the middle is in a middle position, and the automatic lifting guide rail 2 on the lower side is in a high position;
4.3 Under the control of the management platform, the two-degree-of-freedom cradle head 3 horizontally rotates and vertically overturns, when the image recorder 5 is in a low position, a middle position and a high position, the two-degree-of-freedom cradle head 3 rotates to a bottom view, a head up view and a top view state respectively, and a lens on the image recorder 5 is aligned with the plane 6 to be detected, so that the operation of the two-degree-of-freedom cradle head 3 is stopped;
in fig. 3, the upper automatic rising rail 2 is in a bottom view state, the middle automatic rising rail 2 is in a top view state, and the lower automatic rising rail 2 is in a top view state.
4.4 Collecting a plurality of low-level upward shooting, middle-level downward shooting or high-level downward shooting images of the airplane 6 to be detected at the height position by using an image recorder 5, and transmitting the images to a management platform;
4.5 Under the control of the management platform, the automatic lifting guide rail 2 performs lifting movement until the image recorder 5 reaches another height position, and the steps 4.3) -4.4) are repeated;
4.6 Under the control of the management platform, the automatic lifting guide rail 2 performs lifting movement until the image recorder 5 reaches the last height position, and the steps 4.3) -4.4) are repeated;
4.7 All the low-position upward shooting, the middle-position horizontal shooting and the high-position downward shooting images form an image information source of a starting data acquisition point.
5) The management platform automatically or manually checks faults or potential safety hazards on the aircraft 6 to be detected, which are observed from the initial data acquisition point according to the image information source of the initial data acquisition point;
the specific method comprises the following steps:
5.1 The management platform automatically or manually analyzes the reliability and the correctness of the information contained in the image information source of the initial data acquisition point to judge the reliability and the correctness of the image information source;
the confidence is a value that detects whether the collected sample is within a range of a predetermined requirement for the sample, i.e., it reflects the reliability, credibility of the collected sample. The validity refers to the accuracy of the acquired sample, namely the error between the measured value and the actual value. And setting a preset credibility and effectiveness threshold according to the requirement of the management platform on the required image, and evaluating the credibility and effectiveness of the image information source acquired by the initial data acquisition point to obtain the credibility and effectiveness information of the image information source.
When the judgment standard of the credibility and the validity comprises the brightness of the image, a preset brightness threshold is set, and when the brightness of the image acquired by the image recorder 5 cannot meet the preset brightness threshold, the credibility and the validity information of the image information source of the initial data acquisition point position cannot meet the preset threshold, and the image acquisition needs to be carried out again. When the reliability and effectiveness information of the image information source of the initial data acquisition point is larger than the preset threshold, the image sample can be used as an image for further judging the equipment, and the inspection maintenance detection is continued on the image information source. The reliability and the effectiveness of the images are detected, so that the information effectiveness of the acquired images is ensured, and a solid foundation is laid for the accuracy of the analysis processing of the subsequent images. When the reliability and the effectiveness of the image information source of the initial data acquisition point are smaller than or equal to the preset threshold, the acquired image is indicated to have a certain problem, the acquired image cannot be used as a sample image for judging the initial data acquisition point, an acquisition instruction is required to be acquired at the moment, the acquisition parameters which do not accord with the sample acquisition confidence coefficient are adjusted, and the initial data acquisition point is subjected to image acquisition again, so that the accurate analysis of the initial data acquisition point is ensured.
5.2 Comparing the related parameters in the image information source with a preset threshold value, if the related parameters exceed the threshold value, judging that the fault or potential safety hazard exists in the aircraft parts observed from the point location, and timely reporting to a crew for overhaul through a management platform;
judging whether faults or potential safety hazards exist or not, extracting relevant inspection condition information obtained by the image recorder 5 at an initial data acquisition point, judging and checking the conditions in the condition information by means of the artificial intelligent functions such as machine learning and the like of the management platform, and transferring the screened suspicious targets to the artificial work sequence to further judge. The management platform is characterized in that a user of the management platform takes past maintenance content stored by the platform as reference data, takes a processing result calculated by platform artificial intelligence according to big data as reference opinion, performs manual inspection on a suspicious target, performs hidden trouble investigation and maintenance on an initial data acquisition point position by a machine-assisted inspection personnel, reports a confirmed fault position to a maintenance center, and assigns professional crews to maintain by the maintenance center. The efficiency and the accuracy of aircraft maintenance inspection and repair inspection can be improved by combining the image recognition technology with the big data analysis processing technology, and the capability of inspection maintenance personnel to find and solve abnormal problems is improved.
5.3 If no fault or potential safety hazard exists, the point inspection maintenance work is completed.
6) And (3) the motion trolley 1 sequentially moves to the residual data acquisition points according to the planned motion trail, and then the steps (4) -5) are repeated to obtain the image information source of the residual data acquisition points until all the data acquisition points are inspected.
Claims (2)
1. An aircraft inspection method based on an automatic image recognition mode of a moving trolley is characterized by comprising the following steps of: the aircraft inspection method comprises the following steps in sequence:
1) constructing an aircraft inspection system, wherein the aircraft inspection system comprises a management platform for aircraft maintenance inspection and repair inspection, a moving trolley (1), an automatic lifting guide rail (2), a two-degree-of-freedom cradle head (3), a motion track recorder (4) and an image recorder (5); wherein the lower end of the automatic lifting guide rail (2) is fixed on the moving trolley (1); the two-degree-of-freedom cradle head (3) is arranged at the upper end of the automatic lifting guide rail (2); the motion trail recorder (4) and the image recorder (5) are respectively arranged on the motion trolley (1) and the two-degree-of-freedom cradle head (3); the management platform is respectively connected with the moving trolley (1), the automatic lifting guide rail (2), the two-degree-of-freedom cradle head (3), the moving track recorder (4) and the image recorder (5) in a wireless manner;
2) Under the control of a management platform, the movement trolley (1) moves 360 degrees around the outer contour of the airplane (6) to be detected, and the movement of the movement trolley simultaneously records the running track of the movement trolley (1) in real time by using a movement track recorder (4) and uploads the running track to the management platform;
3) A technician determines a plurality of data acquisition points for maintenance/maintenance inspection on the running track according to task requirements on a management platform, and then the management platform automatically plans the movement track of the movement trolley (1) and sends a movement track instruction to the movement trolley (1);
4) The motion trolley (1) moves to an initial data acquisition point according to the motion track instruction, then the height and the angle of the image recorder (5) are adjusted through the automatic lifting guide rail (2) and the two-degree-of-freedom cradle head (3), then the image recorder (5) is used for acquiring images of the aircraft (6) to be detected from different heights and angles, and an image information source of the initial data acquisition point is obtained and uploaded to the management platform;
5) The management platform automatically or manually checks faults or potential safety hazards on the aircraft (6) to be detected, which are observed from the initial data acquisition point according to the image information source of the initial data acquisition point;
6) The motion trolley (1) sequentially moves to the residual data acquisition points according to the planned motion track, and then the step 4) -the step 5) are repeated to obtain an image information source of the residual data acquisition points until all the data acquisition points are inspected;
in the step 3), the method for automatically planning the motion trail of the motion trolley (1) by the management platform is as follows:
storing the aircraft inspection maintenance data on the running track into a database of a management platform, establishing an individual aircraft maintenance inspection and maintenance inspection model, inputting the aircraft inspection maintenance data into the maintenance inspection and maintenance inspection model, outputting the maintenance inspection and maintenance inspection model, namely, the maintenance points and important parts with high failure and potential safety hazards, and finally taking the maintenance points and important parts as data acquisition points;
in step 4), the motion trolley (1) moves to an initial data acquisition point according to the motion track instruction, then the height and the angle of the image recorder (5) are adjusted through the automatic lifting guide rail (2) and the two-degree-of-freedom cradle head (3), and then the image recorder (5) is used for acquiring images of the aircraft (6) to be detected from different heights and angles, so that an image information source of the initial data acquisition point is obtained, wherein the method comprises the following steps:
4.1 The motion trolley (1) moves to an initial data acquisition point position by utilizing the self-contained navigation motion function of the motion track recorder (4) according to the motion track instruction, and the motion of the motion trolley (1) is stopped;
4.2 Under the control of the management platform, the automatic lifting guide rail (2) performs lifting movement until the image recorder (5) reaches a certain height position among a preset low position, a preset middle position and a preset high position, and the operation of the automatic lifting guide rail (2) is stopped;
4.3 Under the control of a management platform, the two-degree-of-freedom cradle head (3) horizontally rotates and vertically overturns, when the image recorder (5) is in a low position, a middle position and a high position, the two-degree-of-freedom cradle head (3) rotates to a bottom view, a top view and a top view state respectively, a lens on the image recorder (5) is aligned with an airplane (6) to be detected, and the operation of the two-degree-of-freedom cradle head (3) is stopped;
4.4 Collecting a plurality of low-level upward shooting, middle-level downward shooting or high-level downward shooting images of the airplane (6) to be detected from the height and the angle by using an image recorder (5), and transmitting the images to a management platform;
4.5 Under the control of the management platform, the automatic lifting guide rail (2) performs lifting movement until the image recorder (5) reaches another height position, and the steps 4.3) -4.4) are repeated;
4.6 Under the control of the management platform, the automatic lifting guide rail (2) performs lifting movement until the image recorder (5) reaches the last height position, and the steps 4.3) -4.4) are repeated;
4.7 All the low-position upward shooting, the middle-position downward shooting and the high-position downward shooting images form an image information source of a starting data acquisition point position;
in step 5), the method for the management platform to automatically or manually check the faults or potential safety hazards on the aircraft (6) to be detected observed from the initial data acquisition point according to the image information source of the point comprises the following steps:
5.1 The management platform automatically or manually analyzes the reliability and the correctness of the information contained in the image information source of the initial data acquisition point to judge the reliability and the correctness of the image information source;
5.2 Comparing the related parameters in the image information source with a preset threshold value, if the related parameters exceed the threshold value, judging that the fault or potential safety hazard exists in the aircraft parts observed from the point location, and timely reporting to a crew for overhaul through a management platform;
5.3 If no fault or potential safety hazard exists, the point inspection maintenance work is completed.
2. The method for inspecting an aircraft based on an automatic image recognition method for a moving trolley according to claim 1, wherein: in step 1), the management platform adopts an AT89C52 singlechip as a control chip, and the circuit mainly comprises: the device comprises a singlechip power supply circuit, a clock circuit, a reset circuit, a voltage reducing module and a stepping motor driver.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111499113.7A CN114104334B (en) | 2021-12-09 | 2021-12-09 | Airplane inspection method based on automatic image recognition mode of moving trolley |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111499113.7A CN114104334B (en) | 2021-12-09 | 2021-12-09 | Airplane inspection method based on automatic image recognition mode of moving trolley |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114104334A CN114104334A (en) | 2022-03-01 |
| CN114104334B true CN114104334B (en) | 2024-02-23 |
Family
ID=80363795
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111499113.7A Active CN114104334B (en) | 2021-12-09 | 2021-12-09 | Airplane inspection method based on automatic image recognition mode of moving trolley |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114104334B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117649213B (en) * | 2024-01-30 | 2024-04-19 | 四川宽窄智慧物流有限责任公司 | Front-end management method and system for transportation safety |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018103242A1 (en) * | 2016-12-09 | 2018-06-14 | 武汉科技大学 | Electric tower inspection method of using four-rotor unmanned aerial vehicle based on motor learning |
| CN110110112A (en) * | 2019-05-05 | 2019-08-09 | 中国民用航空飞行学院 | It is a kind of based on liftable trolley around machine check method and system |
| RU2734363C1 (en) * | 2020-02-28 | 2020-10-15 | Артур Георгиевич Арутюнов | Examination of aircraft surface using unmanned aerial vehicle |
| CN111780811A (en) * | 2020-07-27 | 2020-10-16 | 福州木鸡郎智能科技有限公司 | Chicken group state inspection monitoring system and method |
| CN112327906A (en) * | 2020-10-22 | 2021-02-05 | 华能阜新风力发电有限责任公司 | Intelligent automatic inspection system based on unmanned aerial vehicle |
| WO2021082644A1 (en) * | 2019-10-29 | 2021-05-06 | 北京海益同展信息科技有限公司 | Fault detection method and apparatus, and storage medium |
| CN112929613A (en) * | 2021-03-08 | 2021-06-08 | 华录智达科技股份有限公司 | Inspection method and system for equipment operation and maintenance based on image recognition |
| CN113264200A (en) * | 2021-04-14 | 2021-08-17 | 泛博科技(中山)有限公司 | Aviation intelligent self-checking multi-scene universal unmanned vehicle system |
| CN113506383A (en) * | 2021-07-09 | 2021-10-15 | 中国飞机强度研究所 | Airplane strength test inspection method and system |
-
2021
- 2021-12-09 CN CN202111499113.7A patent/CN114104334B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018103242A1 (en) * | 2016-12-09 | 2018-06-14 | 武汉科技大学 | Electric tower inspection method of using four-rotor unmanned aerial vehicle based on motor learning |
| CN110110112A (en) * | 2019-05-05 | 2019-08-09 | 中国民用航空飞行学院 | It is a kind of based on liftable trolley around machine check method and system |
| WO2021082644A1 (en) * | 2019-10-29 | 2021-05-06 | 北京海益同展信息科技有限公司 | Fault detection method and apparatus, and storage medium |
| RU2734363C1 (en) * | 2020-02-28 | 2020-10-15 | Артур Георгиевич Арутюнов | Examination of aircraft surface using unmanned aerial vehicle |
| CN111780811A (en) * | 2020-07-27 | 2020-10-16 | 福州木鸡郎智能科技有限公司 | Chicken group state inspection monitoring system and method |
| CN112327906A (en) * | 2020-10-22 | 2021-02-05 | 华能阜新风力发电有限责任公司 | Intelligent automatic inspection system based on unmanned aerial vehicle |
| CN112929613A (en) * | 2021-03-08 | 2021-06-08 | 华录智达科技股份有限公司 | Inspection method and system for equipment operation and maintenance based on image recognition |
| CN113264200A (en) * | 2021-04-14 | 2021-08-17 | 泛博科技(中山)有限公司 | Aviation intelligent self-checking multi-scene universal unmanned vehicle system |
| CN113506383A (en) * | 2021-07-09 | 2021-10-15 | 中国飞机强度研究所 | Airplane strength test inspection method and system |
Non-Patent Citations (1)
| Title |
|---|
| 旋翼无人机在特种设备巡检技术中的设计与应用;孙东晓;陈庆诚;文祥;董伟;;机电一体化(第05期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114104334A (en) | 2022-03-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108189043B (en) | Inspection method and inspection robot system applied to high-speed rail machine room | |
| CN1300750C (en) | Airplane berth plane type automatic identification and indication system | |
| WO2019158171A1 (en) | Systems and vehicles for managing wind turbine systems | |
| CN109815912B (en) | Highway safety inspection system based on artificial intelligence | |
| CN114104334B (en) | Airplane inspection method based on automatic image recognition mode of moving trolley | |
| CN114261528B (en) | Unmanned aerial vehicle nest self-checking system and method | |
| CN112698618A (en) | Server alarm recognition system based on machine vision technology | |
| CN112506214B (en) | Operation flow of unmanned aerial vehicle autonomous fan inspection system | |
| CN113111704A (en) | Airport pavement disease and foreign matter detection method and system based on deep learning | |
| CN114723271A (en) | Power transmission project quality detection method and system based on image recognition | |
| CN114115020A (en) | Intelligent control system and control method for height of unmanned aerial vehicle | |
| CN113762183A (en) | Intelligent checking and analyzing system for existing building safety and operation method | |
| CN114550334A (en) | Bridge robot inspection teaching training system, method and storage medium | |
| CN110445055A (en) | A kind of power transmission line unmanned cruising inspection system | |
| CN116740833A (en) | Line inspection and card punching method based on unmanned aerial vehicle | |
| CN111459190A (en) | Unmanned aerial vehicle for automatic inspection of large-scale centralized photovoltaic power station and inspection method | |
| CN114721432A (en) | Unmanned aerial vehicle intelligent inspection equipment based on big data and inspection image defect analysis method | |
| CN113050671A (en) | Unmanned aerial vehicle system for detecting natural gas leakage and detection method | |
| CN114937040B (en) | Train inspection method, device and system for rail transit vehicle section and storage medium | |
| CN116978139A (en) | Unmanned aerial vehicle intelligent inspection system and method based on Beidou technology | |
| CN115793682A (en) | Bridge intelligent inspection method and inspection system based on unmanned aerial vehicle | |
| CN112382190B (en) | Intelligent coal dressing simulation laboratory | |
| CN115421503A (en) | Unmanned aerial vehicle inspection system for bridge | |
| CN112417661B (en) | Data acquisition and analysis system for unmanned equipment packaging test | |
| CN113776783A (en) | Machine room server fault lamp detection method based on inspection robot |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |