Capacitor appearance detection device and method based on artificial intelligence technology

Abstract

The invention discloses a capacitor appearance detection device and method based on artificial intelligence technology. The lower part of a first combined frame is provided with an electric control box, and the upper surface of the electric control box is provided with a feeding module, a rotary table and a discharging module in sequence along the capacitor transfer direction; a feeding vibrationdisc is installed on the upper surface of a second combined frame, and a discharging port of the feeding vibration disc is located below the feeding end of the feeding module; an unqualified product discharging belt line feeding end and a qualified product discharging belt line feeding end are arranged below the discharging end of the discharging module; a vertical image collector is arranged above the rotary table, and a horizontal image collector is arranged in the horizontal direction; and a detection capacitor is placed on the rotary table through the feeding module, a high-definition image of the surface of the capacitor is transmitted to an upper computer through the image collector, whether defects exist or not is judged through the artificial neural network, sorting is conducted, and detection is completed. The automation level of the capacitance detection device is improved, and the detection precision is enhanced in combination with the artificial intelligence technology.

Description

technical field [0001] The invention relates to the field of image processing, in particular to a device and method for detecting capacitor appearance based on artificial intelligence technology. Background technique [0002] With the rapid development of artificial intelligence, machine vision inspection is increasingly used in various fields of industry. In the traditional capacitor industry, the detection methods of capacitor appearance are divided into two categories, one is completed by people, the detection efficiency is low, and the cost of quality control is high; the other is machine detection based on vision, as follows: [0003] Chinese patent CN105004731A is a column-type capacitor appearance automatic detection device and its detection method, including a combined cabinet under the detection table, the combined cabinet includes a system control cabinet, a first unqualified capacitor recovery box and a second unqualified capacitor recovery box , the first unqual...

AI Technical Summary

Problems solved by technology

This technical solution adopts a continuous detection method, combined with the combination of turntable + electromagnet, which greatly improves the detection efficiency, but also lacks the corresponding feeding mechanism, and the number of side cameras is large. Distortion, there is also the problem of poor image resolution, which affects the detection accuracy

[0005] Chinese patent CN108459023A discloses a double-reference capacitor appearance image detection method. The technical solution adopts a combination detection method of a deep-density reference image and a shallow-density reference image. The specific judgment standard is compared with a preset threshold, and the actual detection is still a classic algorithm. In the same way, the Chinese patent CN111008960A also uses a similar common algorithm. The actual accuracy on the market is 90% to 95%, which still needs to be improved; Does not provide a good detection rate

[0006] Chinese patent CN210294084U discloses a post-welding quality inspection equipment for lithium battery poles. It adopts two transmission guide rails combined with 3D and 2D cameras to take pictures. It also belongs to the field of image inspection, but its technical solution lacks the ability of comprehensive inspection. Not suitable for capacitance detection field

Images