scholarly journals Dual-Kernel-Based Aggregated Residual Network for Surface Defect Inspection in Injection Molding Processes

2020 ◽  
Vol 10 (22) ◽  
pp. 8171
Author(s):  
Hwaseop Lee ◽  
Kwangyeol Ryu
Keyword(s):  
Injection Molding ◽  
Surface Defect ◽  
Defect Inspection ◽  
Residual Network ◽  
Cycle Times ◽  
Optical Inspection ◽  
Quality Product ◽  
Weakly Supervised

Automated quality inspection has been receiving increasing attention in manufacturing processes. Since the introduction of convolutional neural networks (CNNs), many researchers have attempted to apply CNNs to classification and detection of defect images. However, injection molding processes have not received much attention in this field of research because of product diversity, difficulty in obtaining uniform-quality product images, and short cycle times. In this study, two types of dual-kernel-based aggregated residual networks are proposed by utilizing a fixed kernel and a deformable kernel to detect surface and shape defects of molded products. The aggregated residual network is selected as a backbone, and a fixed-size, deformable kernel is applied for extracting surface and geometric features simultaneously. Comparative studies are conducted by including the existing research using the Weakly Supervised Learning for Industrial Optical Inspection dataset, which is a DAGM dataset. A case study reveals that the proposed method is applicable for inspecting the quality of injection molding products with excellent performance.

Automated Surface Inspection Using 3D Point Cloud Data in Manufacturing: A Case Study

2018 ◽  
Author(s):  
Romina Dastoorian ◽  
Ahmad E. Elhabashy ◽  
Wenmeng Tian ◽  
Lee J. Wells ◽  
Jaime A. Camelio
Keyword(s):  
Point Cloud ◽  
Surface Defect ◽  
Fault Location ◽  
Three Dimensional ◽  
Practical Case ◽  
3D Point Cloud ◽  
Point Cloud Data ◽  
Defect Inspection ◽  
Cloud Data

With the latest advancements in three-dimensional (3D) measurement technologies, obtaining 3D point cloud data for inspection purposes in manufacturing is becoming more common. While 3D point cloud data allows for better inspection capabilities, their analysis is typically challenging. Especially with unstructured 3D point cloud data, containing coordinates at random locations, the challenges increase with higher levels of noise and larger volumes of data. Hence, the objective of this paper is to extend the previously developed Adaptive Generalized Likelihood Ratio (AGLR) approach to handle unstructured 3D point cloud data used for automated surface defect inspection in manufacturing. More specifically, the AGLR approach was implemented in a practical case study to inspect twenty-seven samples, each with a unique fault. These faults were designed to cover an array of possible faults having three different sizes, three different magnitudes, and located in three different locations. The results show that the AGLR approach can indeed differentiate between non-faulty and a varying range of faulty surfaces while being able to pinpoint the fault location. This work also serves as a validation for the previously developed AGLR approach in a practical scenario.

A robust weakly supervised learning of deep Conv-Nets for surface defect inspection

2020 ◽  
Vol 32 (15) ◽  
pp. 11229-11244
Author(s):  
Haiyong Chen ◽  
Qidi Hu ◽  
Baoshuo Zhai ◽  
He Chen ◽  
Kun Liu
Keyword(s):  
Supervised Learning ◽  
Surface Defect ◽  
Defect Inspection ◽  
Weakly Supervised Learning ◽  
Weakly Supervised

scholarly journals CNN-Based Defect Inspection for Injection Molding Using Edge Computing and Industrial IoT Systems

2021 ◽  
Vol 11 (14) ◽  
pp. 6378
Author(s):  
Hyeonjong Ha ◽  
Jongpil Jeong
Keyword(s):  
Injection Molding ◽  
Data Augmentation ◽  
Smart Factory ◽  
Inspection System ◽  
Defect Inspection ◽  
Cycle Times ◽  
Injection Process ◽  
Imbalance Problem ◽  
Industrial Iot ◽  
Using Data

Currently, the development of automated quality inspection is drawing attention as a major component of the smart factory. However, injection molding processes have not received much attention in this area of research because of product diversity, difficulty in obtaining uniform quality product images, and short cycle times. In this study, we proposed a defect inspection system for injection molding in edge intelligence. Using data augmentation, we solved the data shortage and imbalance problem of small and medium-sized enterprises (SMEs), introduced the actual smart factory method of the injection process, and measured the performance of the developed artificial intelligence model. The accuracy of the proposed model was more than 90%, proving that the system can be applied in the field.

A comparison of two metamodel-based methodologies for multiple criteria simulation optimization using an injection molding case study

2013 ◽  
Vol 33 (3) ◽  
pp. 193-209 ◽  
Author(s):  
María G. Villarreal-Marroquín ◽  
Joshua D. Svenson ◽  
Fangfang Sun ◽  
Thomas J. Santner ◽  
Angela Dean ◽  
...  
Keyword(s):  
Injection Molding ◽  
Pareto Front ◽  
Simulation Optimization ◽  
Expected Improvement ◽  
Data Envelopment ◽  
Pareto Solutions ◽  
Advantages And Disadvantages ◽  
Hypervolume Indicator

Abstract This paper compares two metamodel-based methodologies for multi-criteria simulation optimization (SO), using the injection molding of a disposable camera front housing as a case study. The first methodology uses linear regression metamodels and data envelopment analysis (DEA) to iteratively identify potential Pareto solutions, while the second one uses a Gaussian process metamodel and calculates an expected improvement to determine the new input runs sequentially. A one-to-one comparison of the approaches is presented using two optimization examples. The first example involves two process outputs and the second involves three. The approaches are evaluated using the same number of simulations, and are compared in terms of the quality of the obtained Pareto front, based on the hypervolume indicator. Advantages and disadvantages of both methods are discussed.

AOI Techniques for Surface Defect Inspection

2010 ◽  
Vol 36 ◽  
pp. 297-302 ◽  
Author(s):  
Rong Sheng Lu ◽  
Yan Qiong Shi ◽  
Qi Li ◽  
Qing Ping Yu
Keyword(s):  
Rapid Development ◽  
Light Illumination ◽  
Defect Inspection ◽  
Emerging Industries ◽  
Optical Inspection ◽  
Textile Printing ◽  
Automobile Steel ◽  
Automated Optical Inspection ◽  
Key Techniques

Recent years, automated optical inspection (AOI) is developed very fast along with the rapid development of the emerging industries of semiconductor, LCD, PCB, optical communication and precision assembly, and also widely used in the industries of robot, automobile, steel, textile, printing, medicine, etc. In this paper, we will take a review of the AOI techniques, which are used for defect inspection on a large surface, such as inspecting the quality of TFT-LCD glass substrate and filter. The AOI system architecture having high inspection speed is illustrated. Some key techniques of light illumination, distributed image processing and convey mechanism, are explained.

Process Control of Injection Molding Based on Multiscale Visualization Methodology - A Case Study

2010 ◽  
Vol 154-155 ◽  
pp. 1839-1845
Author(s):  
Jin Cheng ◽  
Jian Rong Tan ◽  
Jia Hong Yu
Keyword(s):  
Injection Molding ◽  
Optimal Process ◽  
Part Quality ◽  
Statistical Mathematics ◽  
Injection Molded ◽  
Plastic Parts ◽  
Injection Molded Plastic ◽  
Optimal Process Parameter

Multiscale visualization approaches are proposed to efficiently assist designers not familiar with statistical mathematics in determining the optimal process parameter schemes for achieving desired part quality in injection molding, based on which the parameters’ relative importance to part quality and their influence on either single quality index or comprehensive part quality can be visually described by the map of the sum of squared deviations, response surface diagram and distribution map of comprehensive part quality. The proposed visualization approaches are universal for analyzing the effects of process parameters on the quality of any injection-molded plastic parts although the mobile phone cover is utilized as an example in the presentation of our work.

Review of Vision Inspection Technology for Surface Defect of Steel Bar

2015 ◽  
Vol 740 ◽  
pp. 543-546
Author(s):  
Wu Bin Li ◽  
Quan Zhong Zhang ◽  
Jun Long Sun ◽  
Lu Liu ◽  
Shi Long He
Keyword(s):  
Surface Defect ◽  
Raw Materials ◽  
Research Development ◽  
Defect Inspection ◽  
Vision Inspection ◽  
Detection Technology ◽  
Steel Bar ◽  
Key Issues ◽  
Working Principle

With the increase of requirement for the quality of raw materials in industry, surface defect inspection of steel bar has been an essential part of industrial production. The characteristics of vision-based detection technology for steel bar surface defect and the newest research development were introduced. The working principle of vision inspection technology and key issues were analyzed. Finally, the current domestic research emphases and development trends were proposed.

scholarly journals Pengendalian Kualitas Part Trim Rear Quarter Right APV Arena dengan Menggunakan Metode Six Sigma di PT. Suzuki Indomobil Motor

2016 ◽  
Vol 13 (1) ◽  
pp. 486
Author(s):  
Fatimah Zahara
Keyword(s):  
Injection Molding ◽  
Production Process ◽  
Six Sigma ◽  
Risk Priority Number ◽  
Noisy Environments ◽  
Molding Machine ◽  
Five Factors ◽  
Set Up

Quality is an important aspect in enhancing the competitiveness of the product. Quality's role is to give satisfaction to the customer and be able to compete with similar products. During of the production process there is a chance that the products are not produced in established standards. Products that not suitable with the specifications is a defect that would cause harm to the company. Trim Rear Quarter Right is a component of the APV Arena car which is each production of Trim Rear Quarter Right there are at least one or more defective products. This of course would lead to losses for the company. The method used in this case study is the six sigma method because this method has been proven effective. Defect in Trim Rear Quarter Right caused by five factors that is negligence of the operator in set up the machine, the age of the machine , the quality of the materials, the application of the method is not maximized and noisy environments. The set up process of injection molding machine is the most influential in causing the defect product with RPN (Risk Priority Number) value is 256.Keywords: Quality, Six Sigma,Trim Rear Quarter Right AbstrakKualitas merupakan aspek penting dalam meningkatkan daya saing produk. Perannya adalah memberikan kepuasan kepada pelanggan dan mampu bersaing dengan produk sejenis.Trim Rear Quarter Right merupakan komponen dari mobil APV Arena yangsetiap produksi Trim Rear Quarter Right ini setidaknya terdapat satu atau lebih produk cacat. Hal ini tentunya akan menyebabkan kerugian bagi perusahaan. Metode yang digunakan dalam studi kasus ini yaitu metode six sigma karena metode ini sudah terbukti efektif. acat pada produk Trim Rear Quarter Right disebabkan oleh lima faktor yaitu: kelalaian operator dalam set up mesin , umur mesin, kualitas material, penerapan metode yang belum maksimal dan lingkungan yang berisik. Proses set up molding injection machine adalah proses paling berpengaruh dalam menyebabkan defect produk dengan nilai RPN (Risk Priority Number) sebesar 256.Kata kunci: Kualitas,Six Sigma, Trim Rear Quarter Right

scholarly journals A Case Study in the Transformers and Household Appliances Factory

2017 ◽  
Vol 1 (2) ◽  
pp. 591-608
Author(s):  
Nada Saleh Mahdi ◽  
Hussein Reza Mahdi Reza Mahdi
Keyword(s):  
Product Quality ◽  
Poor Quality ◽  
Quality Level ◽  
Insulation Material ◽  
Household Appliances ◽  
Quality Product ◽  
The One

The research aims to identify the best way to evaluate the final product quality level, and through the comparison between the results of the value of demerits by using demerit system that depending on quadrant classification accredited by the researchers for defects with the method that used at the factory, that depending on three-classification of defects, and used cause and effect Diagram on the defects of the category (A) to identify the main and Secondary reasons that occurrence of this defect, Use the method case study to reach the goals of the research and was selected factory of transformers and household appliances Which represents the one of the formations of the General company for Electronic Industries spatial limits of the study, as were selected reflective product sample for the application of this study as it consists of 87 part which increases the probability of the emergence defects that different influence the reflective product quality, Search results showed that the use of demerit system, which depends on the quad classification for defects, that will lead to a devaluation of demerit value and thus improve the quality product reflective, In addition to identifying the main reasons and secondary that lead to emergence defects of class (A), It was identified four causes is (Touching the wires of body, Presence scratch in the connecting wires, Poor quality of connecting wires, A defect in the insulation material).

Misophonia: An Evidence-Based Case Report

2020 ◽  
Vol 29 (4) ◽  
pp. 685-690
Author(s):  
C. S. Vanaja ◽  
Miriam Soni Abigail
Keyword(s):  
Quality Of Life ◽  
Case Report ◽  
Case History ◽  
Pure Tone ◽  
Physiological Responses ◽  
Evidence Based ◽  
Management Option ◽  
Pure Tone Audiogram

Purpose Misophonia is a sound tolerance disorder condition in certain sounds that trigger intense emotional or physiological responses. While some persons may experience misophonia, a few patients suffer from misophonia. However, there is a dearth of literature on audiological assessment and management of persons with misophonia. The purpose of this report is to discuss the assessment of misophonia and highlight the management option that helped a patient with misophonia. Method A case study of a 26-year-old woman with the complaint of decreased tolerance to specific sounds affecting quality of life is reported. Audiological assessment differentiated misophonia from hyperacusis. Management included retraining counseling as well as desensitization and habituation therapy based on the principles described by P. J. Jastreboff and Jastreboff (2014). A misophonia questionnaire was administered at regular intervals to monitor the effectiveness of therapy. Results A detailed case history and audiological evaluations including pure-tone audiogram and Johnson Hyperacusis Index revealed the presence of misophonia. The patient benefitted from intervention, and the scores of the misophonia questionnaire indicated a decrease in the severity of the problem. Conclusions It is important to differentially diagnose misophonia and hyperacusis in persons with sound tolerance disorders. Retraining counseling as well as desensitization and habituation therapy can help patients who suffer from misophonia.

Sign in / Sign up

Export Citation Format

Share Document