Prisma Analysis of Innovative Technologies on Advancement of Optimisation of Manufacturing Industry DOI

Ndala Yves Mulongo,

Mahtlatse Matlala,

Khathutshelo Mushavhanamadi

et al.

Published: July 25, 2023

The swift advancement of modern innovation has created a significant change within various sectors, particularly in manufacturing industry. Consequently, several companies have started to investigate for innovative administrative configuration and policy order implement artificial intelligence technologies into their production routes. Hence, the tool such as, Computer Aided Manufacturing is considered as key player optimizing industry mostly smart manufacturing. advent 4.0 resulted novel business patterns, which are more adopted sector. To this end, present research paper sought use Prisma approach critically review existing literature field demonstrates outlines its role on optimising processes goods process that ability significantly improve productivity, flexibility, efficiency whilst enabling decision-making operations related supply chain. study offer clear idea company organization wishes provide roadmap digitizing techniques. It also expected by presenting review, both academics industrial practitioners will gain access hands-on library information impact new technology Artificial Intelligence. In assuring credibility approach, each search term or keyword was separately examined.

Language: Английский

Anomaly detection for industrial quality assurance: A comparative evaluation of unsupervised deep learning models DOI Creative Commons

Justus Zipfel,

Felix Verworner,

Marco Fischer

et al.

Computers & Industrial Engineering, Journal Year: 2023, Volume and Issue: 177, P. 109045 - 109045

Published: Jan. 31, 2023

Across many industries, visual quality assurance has transitioned from a manual, labor-intensive, and error-prone task to fully automated precise assessment of industrial quality. This transition been made possible due advances in machine learning general, supervised particular. However, the majority approaches only allow identify pre-defined categories, such as certain error types on manufactured objects. New, unseen are unlikely be detected by models. As remedy, this work studies unsupervised models based deep neural networks which not limited fixed set categories but can generally assess overall More specifically, we use inspection case European car manufacturer detection performance three (i.e., Skip-GANomaly, PaDiM, PatchCore). Based an in-depth evaluation study, demonstrate that reliable results achieved with even competitive those counterpart.

Language: Английский

Citations

50
Unsupervised fabric defects detection based on spatial domain saliency and features clustering DOI
Shuxuan Zhao, Ray Y. Zhong, Junliang Wang

et al.

Computers & Industrial Engineering, Journal Year: 2023, Volume and Issue: 185, P. 109681 - 109681

Published: Oct. 14, 2023

Language: Английский

Citations

23
AI-Driven Real-time Quality Monitoring and Process Optimization for Enhanced Manufacturing Performance DOI Open Access

Olanrewaju Okuyelu,

Ojima Adaji

Journal of Advances in Mathematics and Computer Science, Journal Year: 2024, Volume and Issue: 39(4), P. 81 - 89

Published: March 27, 2024

The integration of artificial intelligence (AI) into manufacturing processes has revolutionized quality control and process optimization. This paper focuses on AI-driven real-time monitoring optimization, exploring its potential to enhance performance. study reviews recent advancements in AI technologies, emphasizing their application environments. Utilizing machine learning algorithms, sensor data, IoT connectivity, the proposed system facilitates continuous production parameters. framework enables early fault prognosis, minimizing disruptions likelihood substandard output. further explores AI's role dynamically optimizing through analytics, adaptive control, predictive maintenance, intelligent decision-making, enhancing efficiency, resource utilization, product quality. Drawing a comprehensive review literature, case studies, experimental results by Wan et al. (2021), Kleven Maritime AS, Ekornes collectively demonstrate how AI-assisted Computer-aided Manufacturing (CM) enhances efficiency customization data analysis, modularization, ERP implementation, Industry 4.0 readiness, thereby enabling concurrent processing multiple tasks tailored customer preferences. provides valuable for researchers, practitioners, industry professionals aiming harness full propel performance new heights.

Language: Английский

Citations

15
Micro defect characterization of micro-CT images of PBX using deep learning and image processing method DOI Creative Commons
Liangliang Lv, Weibin Zhang, Xiaodong Pan

et al.

Energetic Materials Frontiers, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 1, 2025

Language: Английский

Citations

1
Developing a semi-supervised learning and ordinal classification framework for quality level prediction in manufacturing DOI
Gyeongho Kim, Jae Gyeong Choi, Minjoo Ku

et al.

Computers & Industrial Engineering, Journal Year: 2023, Volume and Issue: 181, P. 109286 - 109286

Published: May 9, 2023

Language: Английский

Citations

22
Intelligent approach for the industrialization of deep learning solutions applied to fault detection DOI
Ivo Perez Colo, Carolina Saavedra Sueldo, Mariano De Paula

et al.

Expert Systems with Applications, Journal Year: 2023, Volume and Issue: 233, P. 120959 - 120959

Published: July 11, 2023

Language: Английский

Citations

17
A Novel GAN-Based Anomaly Detection and Localization Method for Aerial Video Surveillance at Low Altitude DOI Creative Commons
Danilo Avola, Irene Cannistraci, Marco Cascio

et al.

Remote Sensing, Journal Year: 2022, Volume and Issue: 14(16), P. 4110 - 4110

Published: Aug. 22, 2022

The last two decades have seen an incessant growth in the use of Unmanned Aerial Vehicles (UAVs) equipped with HD cameras for developing aerial vision-based systems to support civilian and military tasks, including land monitoring, change detection, object classification. To perform most these artificial intelligence algorithms usually need know, a priori, what look for, identify. or recognize. Actually, operational scenarios, such as war zones post-disaster situations, areas objects interest are not decidable priori since their shape visual features may been altered by events even intentionally disguised (e.g., improvised explosive devices (IEDs)). For reasons, recent years, more research groups investigating design original anomaly detection methods, which, short, focused on detecting samples that differ from others terms appearance occurrences respect given environment. In this paper, we present novel two-branch Generative Adversarial Network (GAN)-based method low-altitude RGB video surveillance detect localize anomalies. We chosen focus sequences interested complex scenarios where small device can represent reason danger attention. proposed model was tested UAV Mosaicking Change Detection (UMCD) dataset, one-of-a-kind collection challenging videos whose were acquired between 6 15 m above sea level three types ground (i.e., urban, dirt, countryside). Results demonstrated effectiveness Area Under Receiving Operating Curve (AUROC) Structural Similarity Index (SSIM), achieving average 97.2% 95.7%, respectively, thus suggesting system be deployed real-world applications.

Language: Английский

Citations

23
Data-driven intelligent computational design for products: method, techniques, and applications DOI Creative Commons
Maolin Yang, Pingyu Jiang,

Tianshuo Zang

et al.

Journal of Computational Design and Engineering, Journal Year: 2023, Volume and Issue: 10(4), P. 1561 - 1578

Published: July 4, 2023

Abstract Data-driven intelligent computational design (DICD) is a research hotspot that emerged under fast-developing artificial intelligence. It emphasizes utilizing deep learning algorithms to extract and represent the features hidden in historical or fabricated process data then learn combination mapping patterns of these for solution retrieval, generation, optimization, evaluation, etc. Due its capability automatically efficiently generating solutions thus supporting human-in-the-loop innovative activities, DICD has drawn attention both academic industrial fields. However, as an emerging subject, many unexplored issues still limit development application DICD, such specific dataset building, engineering design-related feature engineering, systematic methods techniques implementation entire product process, In this regard, operable road map from full-process perspective established, including general workflow project planning, overall framework implementation, common mechanisms calculation principles during key enabling technologies detailed three case scenarios application. The can help researchers locate their directions further provide guidance engineers applications.

Language: Английский

Citations

13
Defect detection of printed circuit board based on adaptive key-points localization network DOI
Jianbo Yu, Lixiang Zhao,

Wang Yan-shu

et al.

Computers & Industrial Engineering, Journal Year: 2024, Volume and Issue: 193, P. 110258 - 110258

Published: May 31, 2024

Language: Английский

Citations

4
Modelo basado en YOLOv8 para la detección automática de daños en tejados residenciales DOI Creative Commons
Alisson Clay Rios da Silva,

Antonio Gilson Barbosa Azevedo,

Fernando Humberto de Almeida Moraes Neto

et al.

Revista ALCONPAT, Journal Year: 2025, Volume and Issue: 15(1)

Published: Jan. 1, 2025

This study developed an automated image recognition model for inspecting residential roofs using the YOLOv8 architecture to identify three types of damage. The methodology involved images from 167 buildings captured by drones and annotated in CVAT, which were used train test model. was applied anomaly detection classification, achieving 79% precision. limitations small dataset limited variety capture angles. originality work lies innovative use roof inspection. Future research will focus on developing YOLOv9 YOLOv10 architectures expanding damage classes.

Language: Английский

Citations

0