Patent
Micro part quality detection system based on convolutional neural network
Li Dongjie,Liu Cong +1 more
TLDR
In this article, a micro part quality detection system based on a convolutional neural network (CNN) is presented. But the system is not suitable for the detection of micro parts and can improve the automation degree and the efficiency of detection, and reduce the influence of human factors on the detection process.Abstract:
The invention discloses a micro part quality detection system based on a convolutional neural network. The micro part quality detection system comprises: A, collecting the surface image information ofa micro part by an image acquisition module formed by microscopic vision; B, detecting the image collected by the microscopic vision by using a convolutional neural network model, and classifying thedetected defect images; C, transmitting the classifying result into a main controller, and sending a control signal to a terminal actuator; and D, carrying out picking and classifying on the corresponding micro part by the terminal mechanical arm actuator according to the control signal transmitted by the controller so as to convey the part into the corresponding receiving box, such that the whole system completes the detection and defect classification on the surface quality of the micro part. According to the present invention, the system can effectively used for the detection of micro parts, and can improve the automation degree and the efficiency of detection, and reduce the influence of human factors on the detection process and the labor intensity of workers.read more
Citations
More filters
Patent
Tool wear state automatic detection method based on image processing
TL;DR: In this paper, a tool image is acquired through a simple image acquisition equipment microscope, so that the wear state can be detected without detaching the tool; high detection speed is achieved; the machining process is not influenced; and the production cost is lowered.
Patent
Size sorting system and method
TL;DR: In this paper, a size sorting system consisting of a controller, a camera, and a grabbing mechanism is described, where objects of different sizes are stored in different storage baskets, and manpower is greatly saved.
Patent
Color sorting system and color sorting method
TL;DR: In this paper, a color sorting system consisting of a controller and a grasping mechanism is described, and a mature color neural network is established to accurately correspond to the return path of the grabbing mechanism.
Patent
Shape sorting system and method
TL;DR: In this article, a shape sorting system consisting of a controller and a grabbing mechanism is presented. But the controller is not connected with a camera and a grasping mechanism, and the sorting system also comprises a plurality of containing baskets.
Patent
Material distribution decision-making method and device based on machine learning model and storage medium
TL;DR: In this article, a machine learning model and a storage medium are used to determine a material distribution decision result corresponding to the to-be-distributed part, which can improve the detection and material distribution efficiency.
References
More filters
Patent
Method for detecting mobile phone case profile degree defects
TL;DR: In this article, a method for detecting the mobile phone case profile degree defects was proposed, which comprises the following steps of 1) putting the mobile case onto the test platform; 2) using a semiconductor line structure optical laser with the blue wavelength being 405nm for illuminating mobile phone structure element; 3) collecting laser line images by the first and second CMOS image pickup modules; 4) selecting the camera optic axis and laser line optical plane included angle to be 45 degrees; 5) setting the sensor sampling line number being n pixels; determining the sampling pixel line numbers and the
Patent
Defect detection and classification method based on FCNs (fully convolutional networks) and applied to galvanized stamping parts
TL;DR: In this article, a defect detection and classification method based on FCNs was applied to galvanized stamping parts and the method comprises steps as follows: collecting samples with various types of defects; performing preliminary binary classification according to image gray standard deviation, and distinguishing qualified workpieces and defective workpieces;preprocessing the preliminarily screened samples to improve contrast, and extracting region of interests to serve as improved FCN inputs for training; calculating pixel values of output workpiece images, and setting a threshold value to judge the types of the workpiece defects and performing classification
Patent
Wooden board sorting method and system based on machine learning
TL;DR: In this paper, an automatic sorting method and a system based on machine learning was proposed for wooden board sorting, which is able to rapidly adapt to continuously changing product classification demands, the changeable disposition environment, high-difference timber materials and the paint spray process.
Patent
Industrial appearance inspection method based on smart vision
TL;DR: Zhang et al. as discussed by the authors proposed an industrial appearance inspection method based on smart vision, which comprises the following steps: 1) obtaining a plurality of product appearance flaw samples, wherein multiple samples having the same flaw are images shot at different angles or positions; 2) labeling the flaw images in the product appearance flaws samples and determining categories of flaws in the images; 3) according to the product appearances flaws and the categories of the flaws in images, carrying out deep learning network training to obtain a product appearance deep learning model; 4) obtaining appearance images of a detected product in real