scholarly journals R-CNN-Based Large-Scale Object-Defect Inspection System for Laser Cutting in the Automotive Industry

Processes ◽  
2021 ◽  
Vol 9 (11) ◽  
pp. 2043
Author(s):  
Donggyun Im ◽  
Jongpil Jeong
Keyword(s):  
Object Detection ◽  
Laser Cutting ◽  
Large Scale ◽  
Metal Cutting ◽  
Vision System ◽  
Model Development ◽  
Inspection System ◽  
Defect Inspection ◽  
Molding Process ◽  
Inspection Method

A car side-outer is an iron mold that is applied in the design and safety of the side of a vehicle, and is subjected to a complicated and detailed molding process. The side-outer has three features that make its quality inspection difficult to automate: (1) it is large; (2) there are many objects to inspect; and (3) it must fulfil high-quality requirements. Given these characteristics, the industrial vision system for the side-outer is nearly impossible to apply, and indeed there is no reference for an automated defect-inspection system for the side-outer. Manual inspection of the side-outer worsens the quality and cost competitiveness of the metal-cutting companies. To address these problems, we propose a large-scale Object-Defect Inspection System based on Regional Convolutional Neural Network (R-CNN; RODIS) using Artificial Intelligence (AI) technology. In this paper, we introduce the framework, including the hardware composition and the inspection method of RODIS. We mainly focus on creating the proper dataset on-site, which should be prepared for data analysis and model development. Additionally, we share the trial-and-error experiences gained from the actual installation of RODIS on-site. We explored and compared various R-CNN backbone networks for object detection using actual data provided by a laser-cutting company. The Mask R-CNN models using Res-net-50-FPN show Average Precision (AP) of 71.63 (Object Detection) and 86.21 (Object Seg-mentation), which indicates a better performance than that of other models.

Automatic Inspection System of Small Plastic Gears Based on Machine Vision

2012 ◽  
Vol 522 ◽  
pp. 628-633 ◽  
Author(s):  
Jian Zhe Chen ◽  
Gui Tang Wang ◽  
Jian Qiang Chen ◽  
Xin Liang Yin
Keyword(s):  
Machine Vision ◽  
Template Matching ◽  
Vision System ◽  
Inspection System ◽  
Injection Molding Process ◽  
Automatic Inspection ◽  
Machine Vision System ◽  
Molding Process ◽  
Small Plastic ◽  
Plastic Gears

Small plastic gear is generally made by injection molding.But the injection molding process and mold have problems with missing tooth, shrink, more material, less material and inaccurate roundness and so on. Furthermore, using manual inspection will appear phenomenon of low efficiency, false detection and leak detection. To solve these problems, this paper introduces an automatic inspection system of small plastic gears based on machine vision. The system consists of feeding and sorting machine control system and machine vision inspection system of the gear defects. Mechanical control use digital servo control technology to achieve automatic nesting, feeding, positioning of gear workpiece, and depend on the inspection result of machine vision system to sort. After acquired gear image through a camera, Machine vision system uses median filtering, binarization, edge detection algorithms to process image. Then the system adopts template matching algorithm to obtain the inspection result and send the result to the sorting controller, which achieve automatic smart inspection of gear. The automatic inspection system has accurate, efficient, intelligent and other advantages.

The System Research on Automatic Defect Detection of Glasses

2013 ◽  
Vol 437 ◽  
pp. 362-365
Author(s):  
Hong Bing Yao ◽  
Jie Ping ◽  
Gui Dian Ma ◽  
Liang Wan Li ◽  
Ji Nan Gu
Keyword(s):  
Image Processing ◽  
Processing Speed ◽  
Detection System ◽  
Parallel Structure ◽  
Inspection System ◽  
Defect Inspection ◽  
Inspection Method ◽  
High Processing Speed ◽  
High Processing

A glasses defect inspection system is researched and developed according to the principle of light scattering and visual inspection method, which is based on the machine vision. In order to achieve the classification of glasses, the functions of image acquisition, simple image processing, grading and sorting of glasses are designed in this system. Operation of parallel structure is adopted in this system. Forwardlighting by low-angled-ring-LED is used to get the clear images of the defects in or on the surface of the glasses, such as speckles, impurities, feathers and so on. Image processing and glasses grading based on normalization algorithms are used to acquire the identifying information of various defects of glasses. Experiment results show that the detection system, which can detect all the kinds of defects of the glasses, has high processing speed and strong anti-interference capacity. The size of the smallest defect that can be detected by the system is 0.03mm, and the average detection time of each glass is less than 2s.

scholarly journals INDUSTRIAL VISION SYSTEM FOR OBJECT DETECTION

2021 ◽  
pp. 99-105
Author(s):  
Marek Vagas ◽  
Alena Galajdova
Keyword(s):  
Object Detection ◽  
Visual Inspection ◽  
Vision System ◽  
Robotic Arm ◽  
Reference Object ◽  
Inspection System ◽  
Technological Operation ◽  
Lighting Conditions ◽  
The Future ◽  
Automated Process

The article aimed to experimentally verify and detect the coordinates of a given reference object, which will be manipulated by an industrial robotic arm, type SCARA. It was necessary to identify and locate individual objects at the automated workplace using the OMRON F150-3 visual inspection system during the process. Therefore, the ultimate goal of the assigned task is to reliably grasp the detected reference object and move on to the next technological operation. In the future, it would be appropriate to ensure reliable lighting conditions to guarantee the continuity of the automated process. The article is a publication of scientific and methodical character.

Methodology to Correlate Defect Reduction Systems to Electrical Test Data via Artificially Manufactured Defects

2002 ◽  
Author(s):  
Mike Santana ◽  
Alfredo V. Herrera
Keyword(s):  
Test Data ◽  
Learning Opportunities ◽  
Inspection System ◽  
Navigation Systems ◽  
Defect Inspection ◽  
Defect Reduction ◽  
Electrical Test ◽  
Important System

Abstract This paper describes a methodology for correlating physical defect inspection/navigation systems with electrical bitmap data through the fabrication of artificial defects via reticle alterations or circuit modifications using an inline FIB. The methodology chosen consisted of altering decommissioned reticles to create defects resulting in both open and shorted circuits within areas of an AMD microprocessor cache. The reticles were subsequently scanned using a KLA SL300HR StarLight inspection system to confirm their location, while wafers processed on these reticles were scanned at several layers using standard inline metrology. Finally, the wafers were electrically tested, bitmapped, and physically deprocessed. All defect data was then analyzed and cross-correlated between each system, uncovering some important system deficiencies and learning opportunities. Data and images are included to support the significance and effectiveness of such a methodology.

Ultrasonic measurement of clamping force for injection molding machine

2019 ◽  
Vol 39 (4) ◽  
pp. 388-396 ◽  
Author(s):  
Peng Zhao ◽  
Yao Zhao ◽  
Jianfeng Zhang ◽  
Junye Huang ◽  
Neng Xia ◽  
...  
Keyword(s):  
Injection Molding ◽  
Measurement Method ◽  
Large Scale ◽  
Force Measurement ◽  
Low Cost ◽  
Ultrasonic Method ◽  
Injection Molding Process ◽  
Propagation Time ◽  
Clamping Force ◽  
Molding Process

AbstractAn online and feasible clamping force measurement method is important in the injection molding process and equipment. Based on the sono-elasticity theory, anin situclamping force measurement method using ultrasonic technology is proposed in this paper. A mathematical model is established to describe the relationship between the ultrasonic propagation time, mold thickness, and clamping force. A series of experiments are performed to verify the proposed method. Experimental findings show that the measurement results of the proposed method agree well with those of the magnetic enclosed-type clamping force tester method, with difference squares less than 2 (MPa)2and errors bars less than 0.7 MPa. The ultrasonic method can be applied in molds of different thickness, injection molding machines of different clamping scales, and large-scale injection cycles. The proposed method offers advantages of being highly accurate, highly stable, simple, feasible, non-destructive, and low-cost, providing significant application prospects in the injection molding industry.

Sign in / Sign up

Export Citation Format

Share Document