CN-121998391-A - Artificial intelligence avionics equipment quality inspection device and method

CN121998391ACN 121998391 ACN121998391 ACN 121998391ACN-121998391-A

Abstract

The invention belongs to the technical field of equipment quality inspection, and provides an artificial intelligent avionics equipment quality inspection device and method, wherein the device comprises a plurality of cameras, an AI quality inspection server, a model training platform and a handheld terminal; the system comprises a camera, a test device, a tested device, an operator, an AI quality inspection server, a model training platform, a handheld terminal and a handheld terminal, wherein the camera is positioned and installed according to the delimited areas of the test device and the tested device, video images of the test device, the tested device and the operator are respectively acquired in a test environment, the AI quality inspection server comprises a video image recognition system, a flow management system, a quality inspection table generation system, a man-machine interaction system and an inquiry callback system, AI detection of quality inspection flow procedures is achieved, the model training platform comprises a calculation center, the calculation center comprises a graphic processor and a neural network processor, the calculation center is used for quality inspection model training and algorithm deployment migration, and the handheld terminal comprises a quality inspection application program of each product and is used for automatically or manually intervening the quality inspection flow of the product. The invention solves the problems that the traditional quality inspection process consumes a great deal of labor and the inspection process can not be restored and traced back.

Inventors

WANG MINGHUA
MA ZHAOJUN
KONG WEN
ZHOU QI
SONG HAITONG
JIA XUEQI
GUO QIANG
LIU XUANRUI
QIN SIJUN

Assignees

山东盖特航空科技有限公司

Dates

Publication Date: 20260508
Application Date: 20251128

Claims (10)

1. The quality inspection device of the artificial intelligent avionics equipment is characterized by comprising a plurality of cameras, an AI quality inspection server, a model training platform and a handheld terminal; The AI quality inspection server comprises a video image recognition system, a flow management system, a quality inspection form generation system, a man-machine interaction system and an inquiry callback system, and is used for realizing AI detection of quality inspection flow procedures, wherein the flow management system is respectively in instruction interaction with the video image recognition system, the quality inspection form generation system, the man-machine interaction system and the inquiry callback system, the model training platform comprises a calculation center, the calculation center comprises a graphic processor and a neural network processor, the calculation center is used for quality inspection model training and algorithm deployment migration, and the handheld terminal comprises a quality inspection application program of each type of product, and is used for automatically or manually interfering with the quality inspection flow of the product.
2. An artificial intelligence avionics equipment quality inspection device in accordance with claim 1, The video image recognition system is provided with an image processing recognition algorithm related to the tested equipment, and is configured to recognize corresponding video image results according to the product attribute and the quality inspection flow; the identification process specifically comprises the following steps: Receiving real-time video image data from a camera, wherein the real-time video image data comprises an input signal of a testing device, an output state of the tested device and an operator operation action image; the video image result is the relation among the input signals of the testing equipment, the output state of the tested equipment and the operation action of an operator in the image, which is identified and determined according to each step of the quality inspection process, and is used as the basis for judging whether the step is qualified or not.
3. An artificial intelligence avionics equipment quality inspection device in accordance with claim 1, The flow management system comprises a data layer, a control layer and an execution and interaction layer, and is configured to process the quality inspection flow of each type of product and realize AI detection of the quality inspection flow.
4. An artificial intelligence avionics equipment quality control device according to claim 3, The data layer is configured to comprise an information importing interface and a constructed product quality inspection basic database, wherein the information importing interface is used for importing quality inspection processes in a product specified format, a product quality inspection form template, basic information of a tested product and information related to a testing environment; The control layer comprises a flow controller and a control layer, wherein the flow controller is configured to provide a product quality inspection flow management service, acquire the quality inspection flow of the current product from the data layer and convert the quality inspection flow into a procedure instruction; The execution and interaction layer is configured to automatically call the camera and the image processing and identifying algorithm to finish quality inspection according to the working procedure instruction of the control layer, and give an instruction or push the working procedure to an operator through the handheld terminal for carrying out the condition.
5. An artificial intelligence avionics equipment quality inspection device in accordance with claim 1, The quality inspection form generation system is configured to generate a quality inspection form according to information integrated in the flow management system in the quality inspection process, fill in data and associate evidence, and comprises the following specific processes: Collecting information before quality inspection, including operator basic information, inspector basic information, time, product model, part number and dispatching number; Extracting key data in the quality inspection process, including identifying the input and output images of an operator action, test equipment and a tested piece in each step by utilizing a video image identification system according to the quality inspection process, extracting corresponding data in an image identification result and filling the corresponding data in a quality inspection form; And after the quality inspection is finished, generating a functional performance inspection report form to form a quality inspection record.
6. An artificial intelligence avionics equipment quality inspection device in accordance with claim 1, The man-machine interaction system is configured to provide man-machine interaction service, an operator operates a man-machine interaction interface of the handheld terminal to start or pause a quality inspection flow of a product, and an automatic mode or a manual intervention mode is selected.
7. An artificial intelligence avionics equipment quality inspection device in accordance with claim 1, The inquiry callback system is configured to store a recording quality inspection process, wherein the recording quality inspection process comprises information collection before the recording quality inspection is started, operation and result of each procedure, key image data and global video, and provides global, test equipment, tested equipment and related images of operators for operators to trace back to obtain evidence.
8. The quality inspection method for the artificial intelligent avionics equipment is characterized by comprising the following steps of: the background imports the product data in a specified format, constructs a product quality inspection basic database, configures camera parameters and deploys avionics image recognition algorithms; logging in an application program at a handheld terminal, selecting a product model to be detected, inputting product information and inspector information, calling a product process flow and displaying all process nodes; after triggering the starting instruction, the flow management system advances the working procedure in sequence and prompts the current operation requirement through the application program, and the flow management system sends out the instruction according to the working procedure confirmation, and the camera shoots the image of the target area; After all the procedures are finished, authorized personnel inquire the history record, play back the video and trace the quality inspection process through the handheld terminal or the background.
9. A computer readable storage medium having stored thereon a program which when executed by a processor performs the steps of a method for quality control of an artificial intelligence avionics device according to claim 8.
10. An electronic device comprising a memory, a processor, and a program stored on the memory and executable on the processor, wherein the processor performs the steps of a method for quality control of an artificial intelligence avionics device in accordance with claim 8.

Description

Artificial intelligence avionics equipment quality inspection device and method Technical Field The invention belongs to the technical field of equipment quality inspection, and particularly relates to an artificial intelligent avionics equipment quality inspection device and method. Background The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art. In the field of avionics equipment maintenance, a quality inspection link is important after the traditional avionics equipment is repaired. The device is not only concerned with whether the device can be normally put into use, but also influences the safety and stability of subsequent flight. The quality inspection system mainly comprises test equipment, a tested piece and a connecting cable. The testing equipment is used for providing power supply for avionics equipment, inputting excitation signals, receiving and judging output responses and other key tasks, wherein the output responses comprise display equipment such as indicator lights, nixie tubes and the like on a panel of the avionics equipment, and also comprise display data on PC testing software. When the tested part with normal function receives the excitation input, the predicted value is output, and once a certain function is abnormal, the output deviates from the normal range. In the traditional quality inspection process, an operator needs to sequentially execute the works of setting input, judging whether output is normal, recording and the like according to the production inspection process requirement. Meanwhile, a quality inspector needs to monitor the quality inspector by side, so that misoperation or missed inspection can be prevented. However, there are a number of drawbacks to this quality inspection mode: The cost is increased due to the fact that a large amount of labor is consumed, and the reservation process is complicated and low in efficiency due to the requirement that at least two people are simultaneously present. And the whole process only depends on a paper record sheet, once a problem occurs, the inspection process cannot be restored and traced back, and great difficulty is brought to subsequent fault investigation. Disclosure of Invention In order to overcome the defects of the prior art, the invention provides an artificial intelligent avionics equipment quality inspection device and method, which step the quality inspection process step by step, identify the input and output states of an operator operation and test equipment and a tested piece, confirm whether the input and output relation is correct or not until the whole quality inspection process is finished, record the whole quality inspection process by video, and solve the problems that the traditional quality inspection process consumes a large amount of labor and the inspection process cannot be restored and traced back. To achieve the above object, one or more embodiments of the present invention provide the following technical solutions: The invention provides an artificial intelligent avionics equipment quality inspection device, which comprises a plurality of cameras, an AI quality inspection server, a model training platform and a handheld terminal, wherein the AI quality inspection server is connected with the model training platform; The AI quality inspection server comprises a video image recognition system, a flow management system, a quality inspection form generation system, a man-machine interaction system and an inquiry callback system, and is used for realizing AI detection of quality inspection flow procedures, wherein the flow management system is respectively in instruction interaction with the video image recognition system, the quality inspection form generation system, the man-machine interaction system and the inquiry callback system, the model training platform comprises a calculation center, the calculation center comprises a graphic processor and a neural network processor, the calculation center is used for quality inspection model training and algorithm deployment migration, and the handheld terminal comprises a quality inspection application program of each type of product, and is used for automatically or manually interfering with the quality inspection flow of the product. Further, an image processing recognition algorithm related to the tested equipment is deployed in the video image recognition system and is configured to recognize a corresponding video image result according to the product attribute and the quality inspection flow; the identification process specifically comprises the following steps: Receiving real-time video image data from a camera, wherein the real-time video image data comprises an input signal of a testing device, an output state of the tested device and an operator operation action image; the video image result is the relation among the input signals of the testing equi