Electric connector pin defect visual identification system

Abstract

A portable electrical connector pin defect visual identification system belongs to the technical field of automatic detection and comprises an industrial camera, a lens, an LED light source, low-reflection high-transmittance glass, an electric focusing mechanism, a display system, an embedded development board, a power supply module, an equipment structure, a software module and the like. The software module is developed and realized based on Python and OPENCV, can acquire and store an electric connector plug image shot by the industrial camera in real time, and can quickly identify position coordinates of electric connector pin characteristics; and the software module carries out defect discrimination by using an identification algorithm and a standard template database based on the position coordinates of the characteristics of the electric connector pin obtained in real time, so that the defect detection and discrimination of the electric connector pin are realized. The problems of difficulty, low efficiency, poor accuracy and the like of electrical connector pin defect detection are solved.

Description

TECHNICAL FIELD

[0001] The application relates to a visual identification system for defects of an electric connector pin, in particular to a portable visual identification system for defects of an electric connector pin, and belongs to the technical field of automatic detection. BACKGROUND

[0002] The electric connector is a key component in aerospace manufacturing, and the quality of the electric connector pin is directly related to the transmission efficiency of the control signal. The reason for the inclination of the electric connector pin may be related to improper operation of the operator, and the inclination of the electric connector pin cannot be found and corrected in time, which may cause the electric connector pin to be damaged under stress. Therefore, it is crucial to quickly and accurately find the inclination of the electric connector pin in the product assembly stage, which is the key to preventing the electric connector pin from being bent or retracted and ensuring the normal operation of the electric connector.

[0003] Due to the large variety, large quantity and small size of the electric connector pins, they are usually densely arranged in a limited space, which makes it very difficult to check the quality by the naked eye. When checking the electric connector manually, the reliability of the check is significantly affected by the experience of the personnel and the environmental conditions (such as light). Due to the diversity of the electric connector models and the layout of the pins, long-time visual inspection may cause visual fatigue or even dizziness, increasing the risk of judgment errors. In addition, the shadow of the pin may also interfere with the inspection, leading to misjudgment. In addition, manual detection is not only labor-intensive, but also prone to detection errors, especially when evaluating the slight inclination of the pin.

[0004] In order to improve the accuracy and reliability of the detection, it is urgent to develop effective automated detection means. SUMMARY

[0005] The technical problem to be solved by the application is to overcome the shortcomings of the prior art and solve the problems of difficult detection, low efficiency and poor accuracy of the electric connector pin defects.

[0006] The purpose of the application is achieved by the following technical solutions:

[0007] In a first aspect, the application provides a visual identification system for defects of an electric connector pin, comprising an industrial camera, a lens, low-reflection high-transparency glass, an electric focusing mechanism, a display system, an embedded development board and a software module.

[0008] The industrial camera is used for image acquisition, processing and analysis.

[0009] The lens is used for image acquisition, focusing and projection of the object to be photographed on the sensor of the industrial camera.

[0010] The low-reflection high-transparency glass is used for image acquisition. The electric connector pin is closely attached to one side of the low-reflection high-transparency glass, and the other side is spaced apart from the lens by a certain distance.

[0011] Electric focusing mechanism, connecting the aperture control ring and focusing control ring of the lens, for adjusting the lens to the best position to obtain a clear image;

[0012] Display system, connected with the embedded development board, for human-computer interaction and control, image display;

[0013] Embedded development board, controlling the industrial camera to collect images, and controlling the software module to perform image recognition, pin feature position calculation, save original images and detection result images; and controlling the display system to display images;

[0014] Software module, for realizing human-computer UI interaction, driving and control of the industrial camera, defect algorithm, database access and other functions.

[0015] Based on the first aspect, an embodiment of the present application further includes an LED light source for providing a stable non-flickering light environment in an indoor environment.

[0016] Based on the first aspect, an embodiment of the present application further includes a power module for providing stable power input for the industrial camera, light source, electric focusing mechanism, display system, and embedded development board.

[0017] Based on the first aspect, an embodiment of the present application further includes a device structure for fixing and accommodating all other modules.

[0018] Based on the first aspect, an embodiment of the present application, the low-reflection high-transmission glass surface has a coating for improving the wear resistance of the low-reflection high-transmission glass and ensuring the imaging quality.

[0019] Based on the first aspect, an embodiment of the present application, the total frame rate of the industrial camera is greater than 150 frames / s, the resolution is greater than 1 million pixels, and the frame size can be arbitrarily changed.

[0020] Based on the first aspect, an embodiment of the present application, the software module is developed based on Python and OPENCV, the software module can acquire and save the images of the electrical connector plug captured by the industrial camera in real time, and can quickly identify the position coordinates of the electrical connector pin features, the software module uses the recognition algorithm and the standard template database based on the real-time acquired position coordinates of the electrical connector pin features to perform defect discrimination, thereby realizing electrical connector pin defect detection and discrimination.

[0021] Based on the first aspect, an embodiment of the present application, the display system mainly displays the UI interface, the collected images, and the detection result images.

[0022] Based on the first aspect, an embodiment of the present application, the software module uses a multi-threaded mode, and places the image collection and recognition display work in two threads respectively, to improve the system processing speed.

[0023] A recognition method of the electrical connector pin defect visual recognition system according to the first aspect, comprising:

[0024] The electrical connector pin defect visual recognition system is started and initialized;

[0025] Adjust the aperture parameter of the industrial camera;

[0026] Adjust the height and field of view of the industrial camera from the detected part according to the requirement through the electric focusing mechanism;

[0027] The image data is stored in the cache area by the reading image thread of the software module, the display image data thread is started, and the image data in the cache area is taken out and displayed by the display system;

[0028] The collected image is preprocessed and saved;

[0029] Each pin feature of the electrical connector is identified by the image recognition algorithm, and the position coordinates of each pin feature are calculated;

[0030] The standard template database is called to compare and calculate the deviation of each pin feature coordinate from the standard template;

[0031] Each pin feature is labeled and displayed on the image, the deviation value of each pin feature is labeled and displayed on the image, whether it is qualified is judged according to the error allowable range, and the qualified pin feature and deviation value are labeled on the image with a certain color, and the unqualified pin feature and deviation value are labeled on the image with another color.

[0032] Compared with the prior art, the present application has the following beneficial effects:

[0033] (1) The present application adopts visual nondestructive testing of electrical connector pin defects based on machine vision and image recognition technology, realizes acquisition, transmission, reading, display, identification and calculation of the position information of the pin through software, realizes recognition and marking of the detected pin defects, and has important significance and wide application prospect in the field of visual detection of space electrical connector pin defects.

[0034] (2) The present application is based on the camera to shoot the position of the electrical connector pin, and through software, the image is transmitted, read, displayed, identified and calculated to obtain the position information of the pin feature. Compared with the existing automatic detection system, the structure of the present application is compact and small, and can be handheld and operated offline.

[0035] (3) The recognition system of the present application has wide applicability and strong practicability. The recognition system is of detachable structure, facilitating installation and use in different occasions and saving work site. In the detection process, the interface of the recognition system is simple, operation is simple and convenient, and the reliability is high. The recognition system realizes rapid detection of the defects of the electrical connector pin, the detection resolution is 0.1 mm, and the detection effect is good.

[0036] (4) The present application can overcome the limitations of manual detection, provide a more reliable and efficient detection means, and minimize the interference of human factors, effectively improving the quality and efficiency of the product development and production process in the assembly site.

[0037] (5) The present application can be compatible with a variety of host computer devices (Android devices, Windows devices, Linux devices), and the software interface is rich, which can be integrated with other application systems, integrated into the product assembly development process, improve the image acquisition and detection efficiency, and improve the detection quality. BRIEF DESCRIPTION OF DRAWINGS

[0038] Figure 1 The figure is a schematic diagram of the electrical connector pin defect visual recognition system.

[0039] Figure 2 The figure is a visual recognition process of the electrical connector pin defect. DETAILED DESCRIPTION

[0040] In order to make the purpose, technical scheme and advantages of the present application clearer, the embodiments of the present application will be further described in detail below with reference to the drawings.

[0041] A portable electrical connector pin defect visual recognition system, as shown in Figure 1 The system includes an industrial camera, a lens, an LED light source, a low-reflective high-transparency glass, an electric focusing mechanism, a display system, an embedded development board, a power module, a device structure, a software module, etc. The software module is developed based on Python and OPENCV, and can acquire and save the images of the electrical connector plug taken by the industrial camera in real time, and quickly identify the position coordinates of the electrical connector pin features. Based on the real-time acquired position coordinates of the electrical connector pin features, the software module uses recognition algorithms and a standard template database to make defect judgment, thereby realizing electrical connector pin defect detection and judgment.

[0042] Industrial camera: the camera requires a full frame rate of more than 150 frames / s, a resolution of more than 1 million pixels, and can change the frame size at will;

[0043] Lens: used for collecting, focusing and projecting the image of the object being photographed on the sensor of the industrial camera, facilitating image collection, processing and analysis of the industrial camera, etc.

[0044] LED light source: for providing a stable light environment without flicker in an indoor environment;

[0045] Low reflection high transmission glass: the low reflection high transmission glass is fixed on the device structure and is spaced apart from the lens to ensure that the image at the end of the low reflection high transmission glass can be clearly imaged. The electrical connector plug section is tightly attached to one side of the low reflection high transmission glass during image acquisition. The surface of the low reflection high transmission glass has a special coating that can improve the wear resistance of the low reflection high transmission glass and ensure the imaging quality.

[0046] Electric focusing mechanism: for connecting the aperture control ring and the focusing control ring of the lens and adjusting the lens to the best position to obtain a clear image.

[0047] Display system: the display system is a touch control display screen connected to the embedded development board for human-computer interaction and control and image display. It mainly displays the relevant UI interface and the image obtained by industrial camera acquisition and calculation.

[0048] Embedded development board: quickly receives the high-speed image transmitted by the industrial camera and sends it to the software module to quickly identify and calculate the position coordinates of the pin features from the image. The software module compares the identified position coordinates of the pin features with the standard template database based on the recognition algorithm to obtain the recognition result.

[0049] Power module: for providing stable power input for each module (industrial camera, light source, electric focusing mechanism, display system, embedded development board).

[0050] Device structure: for fixing and storing other modules.

[0051] Software module: the software module is the software control part of the electrical connector pin defect visual recognition system, which includes human-computer UI interaction, industrial camera driving and control, defect algorithm implementation, database access and other functions.

[0052] Further, the industrial camera is fixed on the device structure through the camera support, the lens is connected with the industrial camera, the electric focusing mechanism is connected with the two adjusting rings of the lens, the industrial camera is electrically connected with the embedded development board through the USB3.0 interface, and the LED light source is placed on the device structure.

[0053] Further, the embedded development board controls the industrial camera to perform image acquisition, controls the software module to perform image recognition, pin feature position calculation, saves original images and detection result images, and performs other work; controls the display system to perform image display, and the software module is developed based on Python and OPENCV2.4.13 platform and can run cross-platform.

[0054] Further, the software module is a software control part of the electrical connector pin defect visual recognition system, and contains functions such as human-computer UI interaction, control of a camera and a driving module, defect algorithm implementation, database access, and the like.

[0055] Further, the software module adopts a multi-thread mode, and places image acquisition and recognition display work in two threads respectively, so as to improve system processing speed.

[0056] A portable electrical connector pin defect visual recognition method, as shown in the figure, based on the above-mentioned recognition system, comprises the following steps. Figure 2

[0057] Step one, system power-on.

[0058] Step two, industrial camera initialization and initialization of other modules.

[0059] Step three, adjustment of the aperture parameter of the industrial camera.

[0060] Step four, adjustment of the height and field of view of the industrial camera from the detected piece according to requirements through an electric focusing mechanism, and usually, default parameters are adopted.

[0061] Step five, starting of the reading image thread of the software module and storage of image data in a cache area, starting of the display image data thread, taking out of the image data in the cache area, and display of the image by a display system.

[0062] Step six, pre-processing of the collected image based on OpenCV and saving.

[0063] Step seven, detection of the detected piece, recognition of the electrical connector pin features through an image recognition algorithm, and calculation of the position coordinates of each pin feature.

[0064] Step eight, calling of a standard template database, comparison and recognition, and calculation of the deviation of each pin feature coordinate from the standard template.

[0065] Step nine, marking and display of each pin feature on the image, marking and display of the deviation value of each pin feature on the image, determination of whether it is qualified or not according to the error allowable range, marking of the qualified pin feature and deviation value on the image with green color, and marking of the unqualified pin feature and deviation value on the image with red color.

[0066] Step ten, saving of data such as the original image, the marked image, and the determined result in the local storage or the host computer storage, and inclusion of the original image and the detection result image into the database.

[0067] The contents not described in detail in the specification of the present application are the known technology of those skilled in the art.

[0068] ​Although the present application has been disclosed with reference to the preferred embodiments, it is not intended to limit the present application, and any person skilled in the art can make possible changes and modifications to the technical solutions of the present application using the disclosed methods and technical contents without departing from the spirit and scope of the present application. Therefore, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present application without departing from the technical solutions of the present application shall fall within the protection scope of the technical solutions of the present application.

Claims

1. A visual recognition system for defects in electrical connector pins, characterized in that, This includes industrial cameras, lenses, low-reflection, high-transparency glass, electric focusing mechanisms, display systems, embedded development boards, and software modules; Industrial cameras are used for image acquisition, processing, and analysis. A lens is used to capture, focus, and project images of the object being photographed onto the sensor of an industrial camera. Low-reflection, high-transmittance glass is used. During image acquisition, the electrical connector plug is placed close to one side of the low-reflection, high-transmittance glass, while the other side is spaced a certain distance from the lens. The electric focusing mechanism, which connects the aperture control ring and focus control ring of the lens, is used to adjust the lens to the optimal position to obtain a clear image; The display system, connected to the embedded development board, is used for human-computer interaction and control, and image display. The embedded development board controls an industrial camera for image acquisition, controls software modules for image recognition, calculates pin feature positions, saves original images and detection result images, and also controls the display system for image display. The software module is used to implement functions such as human-machine interface interaction, driving and controlling industrial cameras, defect algorithms, and database access.

2. The visual recognition system for electrical connector pin defects according to claim 1, characterized in that, It also includes LED light sources to provide a flicker-free and stable lighting environment indoors.

3. The visual recognition system for electrical connector pin defects according to claim 1, characterized in that, It also includes a power module for providing stable power input to industrial cameras, light sources, motorized focusing mechanisms, display systems, and embedded development boards.

4. The visual recognition system for electrical connector pin defects according to claim 1, characterized in that, It also includes the equipment structure for securing and housing all other modules.

5. The visual recognition system for electrical connector pin defects according to claim 1, characterized in that, The surface of the low-reflection, high-transmittance glass has a coating to improve its abrasion resistance and ensure image quality.

6. The visual recognition system for electrical connector pin defects according to claim 1, characterized in that, Industrial cameras have a full-frame frame rate of more than 150 frames per second, a resolution of more than 1 million pixels, and can arbitrarily change the image size.

7. The visual recognition system for electrical connector pin defects according to claim 1, characterized in that, The software module is developed and implemented based on Python and OpenCV. It can acquire and save images of electrical connector plugs captured by industrial cameras in real time, and can quickly identify the position coordinates of electrical connector pin features. Based on the position coordinates of the electrical connector pin features acquired in real time, the software module uses recognition algorithms and a standard template database to identify defects, thereby realizing the detection and identification of electrical connector pin defects.

8. The visual recognition system for electrical connector pin defects according to claim 1, characterized in that, The display system mainly displays the UI interface, acquired images, and detection result images.

9. The visual recognition system for electrical connector pin defects according to claim 1, characterized in that, The software module adopts a multi-threaded approach, placing image acquisition and recognition / display tasks in two separate threads to improve system processing speed.

10. A method for identifying defects in electrical connector pins based on the visual recognition system of claim 1, characterized in that, include: The visual recognition system for defective electrical connector pins is activated and initialized. Adjust the aperture parameters of the industrial camera; The height and field of view of the industrial camera relative to the inspected workpiece can be adjusted using an electric focusing mechanism as needed. The software module's image reading thread stores image data in a buffer, starts the image data display thread, retrieves the image data from the buffer, and displays the image by the display system; The acquired images are preprocessed and saved. The image recognition algorithm identifies the features of each pin of the electrical connector and calculates the position coordinates of each pin feature. The system calls upon a standard template database to compare and identify the deviations between the coordinates of each pin feature and the standard template. Each pin feature is labeled and displayed on the image, and the deviation value of each pin feature is labeled and displayed on the image. The pass / fail status is determined according to the allowable error range. Passing pin features and deviation values ​​are marked on the image with one color, and unqualified pin features and deviation values ​​are marked on the image with another color.

Images