Automatic Vision Inspection Solution for the Manufacturing Process of Automotive Components Through Plastic Injection Molding

Muresan, Mircea Paul; Cireap, Dragos Gabriel; Giosan, Ion

doi:10.1109/iccp51029.2020.9266249

Cited by 9 publications

(7 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Machine vision is widely used in various fields [6]- [9]. Vision recognition and positioning technology is a typical application of machine vision in industrial automation, which is widely used in automatic assembly, moving objects on production lines and defect detection in products [10]- [12]. The use of visual sensors for object detection and attitude estimation is still an active research area, especially in the application of industrial robots.…”

Section: Related Workmentioning

confidence: 99%

Robot Target Location Based on the Difference in Monocular Vision Projection

Zheng

Deng

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Visual guidance is widely used in industrial robots. At present, the traditional method of template matching and positioning is often used in industrial robots under monocular vision guidance. However, for complex workpieces with height differences, if the angle and position of the workpiece are not consistent with the template, the projection will be different, and the positioning accuracy will be obviously reduced. A new method is proposed to solve this problem by dividing the whole contour of the workpiece and using the weighted method of the contour module to correct and match the workpiece image. First, the contour region of the template image is divided according to the position of the grasping points. Then the weight is assigned according to the distance from each contour region to the grasping points. Then, a fast feature point matching method is used to match the initial image of the workpiece to be measured. Finally, accurate contour matching is carried out for each weighted contour region so that the robot can grasp the object accurately. A large number of experiments show that the method has the design requirements of high stability and high accuracy.

show abstract

Section: Related Workmentioning

confidence: 99%

Robot Target Location Based on the Difference in Monocular Vision Projection

Zheng

Deng

et al. 2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…However, in the real eld, more speci c types of defects regarding injection molding products' shapes should be considered. There are some studies considering defects of the injection molding products detected by vision images (e.g., [22][23][24]); however, they only concentrated on detecting aws on the surface of the injection molding products, and the detected defects were not analyzed with the processing parameters. Third, previous studies have conducted experiments in the laboratory, not in the real eld.…”

Section: Related Workmentioning

confidence: 99%

Development of a Vision-Image-Based Quality Prediction Neural-Network Algorithm for an Injection Molding Machine Considering Cavity Sensor and Vibration Data

Kim

Lee²

2022

Preprint

View full text Add to dashboard Cite

This research develops a neural-network-based algorithm for predicting the quality levels of injection molding products to handle quality regarding problems caused by occurrences of low-quality products. With an assumption that vibration data and temperature and pressure data of the cavities in mold generated from the injection molding machine would be different according to the products’ quality, main objective of this research is to predict the quality grade for each product utilizing the vibration data of the machine and temperature and pressure data of each cavity collected during a product is processed. Among diverse features that can represent quality of injection molding products, we especially focus on the features that could be driven from vision images of the products. We firstly explain how the infrastructure is constructed for collecting the vibration data, cavity sensor data, and vision-image data. Then, for the vibration and cavity sensor data, statistical features that stand for specific patterns of each data utilized as independent variables are derived. Quality grades of each product are also distinguished by two indicators: flection of the product’s housing and alignment of pinholes derived from the vision images of products utilizing the Canny-Edge algorithm. Finally, utilizing statistical features of the vibration and cavity sensor data as independent variables and distinguished quality grades of each product as dependent variables, a neural-network-based quality prediction algorithm is developed, and the performance of the algorithm is evaluated.

show abstract

“…There can be found multiple application of artificial-intelligence-aided computer vision in a variety of automated manufacturing inspection cases, such as steel [ 20 , 21 , 22 ], wood [ 23 , 24 , 25 , 26 ], and resin/plastic [ 27 , 28 , 29 ]. The mentioned investigations utilize deep neural networks as an algorithm to distinguish defects.…”

Section: Related Workmentioning

confidence: 99%

Segmentation of Drilled Holes in Texture Wooden Furniture Panels Using Deep Neural Network

Augustauskas

Lipnickas

Surgailis³

2021

Sensors

View full text Add to dashboard Cite

Drilling operations are an essential part of furniture from MDF laminated boards required for product assembly. Faults in the process might introduce adverse effects to the furniture. Inspection of the drilling quality can be challenging due to a big variety of board surface textures, dust, or woodchips in the manufacturing process, milling cutouts, and other kinds of defects. Intelligent computer vision methods can be engaged for global contextual analysis with local information attention for automated object detection and segmentation. In this paper, we propose blind and through drilled holes segmentation on textured wooden furniture panel images using the UNet encoder-decoder modifications enhanced with residual connections, atrous spatial pyramid pooling, squeeze and excitation module, and CoordConv layers for better segmentation performance. We show that even a lightweight architecture is capable to perform on a range of complex textures and is able to distinguish the holes drilling operations’ semantical information from the rest of the furniture board and conveyor context. The proposed model configurations yield better results in more complex cases with a not significant or small bump in processing time. Experimental results demonstrate that our best-proposed solution achieves a Dice score of up to 97.89% compared to the baseline U-Net model’s Dice score of 94.50%. Statistical, visual, and computational properties of each convolutional neural network architecture are addressed.

show abstract

Automatic Vision Inspection Solution for the Manufacturing Process of Automotive Components Through Plastic Injection Molding

Cited by 9 publications

References 20 publications

Robot Target Location Based on the Difference in Monocular Vision Projection

Robot Target Location Based on the Difference in Monocular Vision Projection

Development of a Vision-Image-Based Quality Prediction Neural-Network Algorithm for an Injection Molding Machine Considering Cavity Sensor and Vibration Data

Segmentation of Drilled Holes in Texture Wooden Furniture Panels Using Deep Neural Network

Contact Info

Product

Resources

About