Accurately and quickly detecting defects on the surface of a part directly affects the quality of the product. Failure to remove non-conforming products in time will bring about quality problems. However, in industries such as automobiles, motorcycles, and internal combustion engines that are characterized by mass production methods, the surface defects in the key parts of the identification and detection of important parts have to date been dominated by manual visual inspection. Due to the complexity of the process implementation (especially after the use of advanced disconnection heads for connecting rod breaking process), it is also necessary to put forward a standardized evaluation standard. For example, for the possible damage to the coupling surface of the connecting rod, there are the following specific provisions: the area of ​​the breach is less than 3mm2; the linear length of any direction of the break is less than 2.5mm. As long as one of the conditions is met, it is judged as unqualified and rejected. According to the characteristics of the parts, the area where the break may appear is outside of the bonding surface (line), and the range is "eight". Under this circumstance, depending on the way of artificial visual inspection and estimation, it is not only inefficient but also labor-intensive, and it cannot accurately implement the provisions of the above standards. On the other hand, it is difficult to achieve the above object even if other conventional measurement methods are used. The principle of image processing technology for surface defect detection Image processing technology, also known as "machine vision," is to use the image of the measured object as a carrier for information, and extract useful information from it to achieve the purpose of measurement. It has advantages such as non-contact, high speed, large measurement range, and rich information. Through the combination of a CCD (Charge Coupled Device) camera with an optical system and a processing system, different detection requirements can be achieved. For the above-mentioned workpiece surface defects can be identified by the reflection shown in Figure 1. FlagKing Flags Manufacturing Co.,Limited , https://www.cnflagkings.com
As shown in the figure, the system uses a square LED diffuse light source to illuminate the break area to be detected. After the light hits the surface of the object, the photoelectrically coupled CCD component reflected in the camera is converted into a corresponding electrical signal. The CCD component can be understood as a dot matrix composed of photosensitive pixels. Each pixel of the CCD corresponds to the two-dimensional image characteristics of the measured object one-to-one. That is, by analyzing the “pixel imaging resultsâ€, the object can be indirectly analyzed. Image features, such as the length and area values ​​of the corresponding object can be obtained by calculating the number of imaged pixels in the binarized image. The image processing system performs binarization processing on the obtained image according to the electric quantity signal, and performs further calculation and analysis on the binary image as an object.
In practical use, the image processing system uses the method of comparison for setting the gray level binarization threshold and the light source. The specific method of comparison: using a known sample as a reference for calibration (comparison), dividing the measured value of a known reference by the pixel value corresponding to the reference, the correspondence between the pixel and the actual value can be obtained Proportional value. By adjusting the brightness of the light source and the binarization threshold of the system, the gray level binarization threshold is optimized to ensure that the system has a relatively high resolution to the object boundary, ie, the optimized binarization threshold and the light source can make the boundary Changes produce as large a pixel value change as possible.
As a novel and practical sensing technology, the image detection unit has been productized in recent years. Some well-known manufacturers, such as Japan's Panasonic Corporation, Germany's Siemens Corporation, have introduced series of products with complete specifications, including light sources. , cameras, image processors, etc., which create very favorable conditions for the promotion and application of image detection technology. At the same time, the relevant corporate standards promulgated not only regulate the production, but also provide the basis for users to select suitable detection units in different situations and to perform system design faster and better.
According to the characteristics of the measured object (workpiece, measured part), referring to relevant standards, an appropriate image detection unit can be conveniently selected. Taking the connecting rod as an example, since the area of ​​the joint defect can not be larger than 15×15 m 2 , it is appropriate to take the “field of view†of 20×21.4 m 2 from the corresponding standard. For each field of view and depth of field, the user can select cameras with different focal lengths, such as 8, 16, 25 and 50 models, each focal length corresponding to the distance from the lens to the surface to be measured and the lens to be measured. CCD photosensitive surface distance ba and other two parameters. According to the situation of the tested workpiece, the camera with the focal length f=25mm is selected. At this time, the above two parameters are 137mm and 9mm, respectively. This example uses Panasonic's small image detection unit, in which the core component CCD sensor pixel is 512 × 480, in the case of the determination of the field of vision, according to which the measurement resolution of the selected detection unit can be found:
July 06, 2023