Deep Learning-Based Defect Detection for Sustainable Smart Manufacturing

Park, Sang-Hyun; Lee, Kang-Hee; Park, JiSu; Shin, Youn-Soon

doi:10.3390/su14052697

Cited by 17 publications

(8 citation statements)

References 13 publications

(16 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In binary classification and in the multi-class scenario, they achieve very high accuracy of defect detection. To inspect the gas lighter manufacturing process, researchers in [ 37 ] develop a DL model based on YOLOv4. Results show good performance in detecting defects with changing illuminance and distance.…”

Section: Deep Learning For Quality Inspectionmentioning

confidence: 99%

Artificial Intelligence-Based Smart Quality Inspection for Manufacturing

Sundaram

Zeid

2023

Micromachines

View full text Add to dashboard Cite

In today’s era, monitoring the health of the manufacturing environment has become essential in order to prevent unforeseen repairs, shutdowns, and to be able to detect defective products that could incur big losses. Data-driven techniques and advancements in sensor technology with Internet of the Things (IoT) have made real-time tracking of systems a reality. The health of a product can also be continuously assessed throughout the manufacturing lifecycle by using Quality Control (QC) measures. Quality inspection is one of the critical processes in which the product is evaluated and deemed acceptable or rejected. The visual inspection or final inspection process involves a human operator sensorily examining the product to ascertain its status. However, there are several factors that impact the visual inspection process resulting in an overall inspection accuracy of around 80% in the industry. With the goal of 100% inspection in advanced manufacturing systems, manual visual inspection is both time-consuming and costly. Computer Vision (CV) based algorithms have helped in automating parts of the visual inspection process, but there are still unaddressed challenges. This paper presents an Artificial Intelligence (AI) based approach to the visual inspection process by using Deep Learning (DL). The approach includes a custom Convolutional Neural Network (CNN) for inspection and a computer application that can be deployed on the shop floor to make the inspection process user-friendly. The inspection accuracy for the proposed model is 99.86% on image data of casting products.

show abstract

Section: Deep Learning For Quality Inspectionmentioning

confidence: 99%

Artificial Intelligence-Based Smart Quality Inspection for Manufacturing

Sundaram

Zeid

2023

Micromachines

View full text Add to dashboard Cite

show abstract

“…With respect to the above, in this article these tools were used to carry out a diagnosis and analysis of the causes that lead to the problem of defects in screws, taking as a starting point a sample of 200 screws, it is observed that most of these defects can result in the manufacturing stage, In order to reduce them and increase the efficiency of the process, a reliable method of inspection is deep learning, which implies a faster detection of defects, this methodology involves the classification of defective or non-defective in relation to the types of defects recorded [5]. According to this case there are several applications in the industry regarding the problem or how to minimize its impact, among these is the application of an intelligent manufacturing process that records defects through automated visual inspection, in this these faults or variations in the standard model are easily detected, and human costs are reduced thus reflecting sustainable growth, this model is also designed under real-time validation using open sources [6]. In general, this is known as machine learning by processing images that identify unknown parts on a visual basis requiring less hardware time [7].…”

Section: Literature Reviewmentioning

confidence: 99%

Quality Control Analysis to Detect Defects in Drywall Fastener Screws

Assan-Barrios

Castro-García²,

Fontalvo-Altamiranda³

et al. 2023

BILO

View full text Add to dashboard Cite

Screws are pieces designed to join two or more elements, they are composed of three parts that are thread, neck, and head. Depending on the type of material they are made of their size and functionality can acquire different characteristics. This article describes the way in which a sample of 200 2-inch screws used for drywall were evaluated to detect potential failures in their manufacturing, through the application of quality tools, with which the main factors that intervene to achieve the best quality of these products were determined. In addition, the study of a real case allowed us to demonstrate feasible improvements that can be applied not only in a certain area, but in the whole industry, since the quality of a product also determines the potential growth of a company. The results obtained showed the degree of affectation of each defect, being advisable for the company to focus on bent screws, screws with deformed tips and screws with incorrect measurements, as these represent greater losses. In conclusion, in the industry it is necessary to use and manage tools to increase the productivity and quality of the processes, thus having a significant impact on all areas of production, achieving the best possible final product.

show abstract

“…Furthermore, integrating the IIoT and deep learning technique can deliver automatic real-time defect detection with high performance. [22][23][24][25] The deep learning (DL) approach has been considered for manufacturing defect detection during the past ten years. The number of research publications on DL-based defect detection has also steadily increased.…”

Section: Literature Reviewmentioning

confidence: 99%

“…29 Furthermore, when a model generates a restricted range of similar images to fool the discriminator easily, mode collapse is a challenge many models encounter. 24,41,42 The models also need a large dataset to adequately reflect the variety and complexity of the original images effectively. However, the quality of synthetic data depends upon the quality of the training dataset.…”

Section: Literature Reviewmentioning

confidence: 99%

“…In addition, the computational resources, both in terms of time and hardware, that are required to train GAN models come at a high cost 29 . Furthermore, when a model generates a restricted range of similar images to fool the discriminator easily, mode collapse is a challenge many models encounter 24,41,42 . The models also need a large dataset to adequately reflect the variety and complexity of the original images effectively.…”

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

Intelligent IoT framework with GAN‐synthesized images for enhanced defect detection in manufacturing

Aramkul,

Sugunnasil

2023

Computational Intelligence

View full text Add to dashboard Cite

The manufacturing industry is always exploring techniques to optimize processes, increase product quality, and more accurately identify defects. The technique of deep learning is the strategy that will be used to handle the issues presented. However, the challenge of using AI in this domain is the small and imbalanced dataset for training affected by the severe shortage of defective data. Moreover, data acquisition requires significant labor, time, and resources. In response to these demands, this research presents an intelligent internet of things (IoT) framework enriched by generative adversarial network (GAN). This framework was developed in response to the needs outlined above. The framework applies the IoT for real‐time data collection and communication, while GAN are utilized to synthesize high‐fidelity images of manufacturing defects. The quality of the GAN‐synthesized image is quantified by the average FID score of 8.312 for non‐defective images and 7.459 for defective images. As evidenced by the similarity between the distributions of synthetic and real images, the proposed generative model can generate visually authentic and high‐fidelity images. As demonstrated by the results of the defect detection experiments, the accuracy can be enhanced to the maximum of 96.5% by integrating the GAN‐synthesized images with the real images. Concurrently, this integration reduces the occurrence of false alarms.

show abstract

Deep Learning-Based Defect Detection for Sustainable Smart Manufacturing

Cited by 17 publications

References 13 publications

Artificial Intelligence-Based Smart Quality Inspection for Manufacturing

Artificial Intelligence-Based Smart Quality Inspection for Manufacturing

Quality Control Analysis to Detect Defects in Drywall Fastener Screws

Intelligent IoT framework with GAN‐synthesized images for enhanced defect detection in manufacturing

Contact Info

Product

Resources

About