Enhancing weld line visibility prediction in injection molding using physics-informed neural networks DOI Creative Commons
Andrea Pieressa,

Giacomo Baruffa,

Marco Sorgato

et al.

Journal of Intelligent Manufacturing, Journal Year: 2024, Volume and Issue: unknown

Published: July 13, 2024

Abstract This study introduces a novel approach using Physics-Informed Neural Networks (PINN) to predict weld line visibility in injection-molded components based on process parameters. Leveraging PINNs, the research aims minimize experimental tests and numerical simulations, thus reducing computational efforts, make classification models for surface defects more easily implementable an industrial environment. By correlating with Frozen Layer Ratio (FLR) threshold, identified through limited data generates synthetic datasets pre-training neural networks. demonstrates that quality model pre-trained PINN-generated achieves comparable performance randomly initialized network terms of Recall Area Under Curve (AUC) metrics, substantial reduction 78% need points. Furthermore, it similar accuracy levels 74% fewer The results demonstrate robustness networks PINNs predicting visibility, offering promising minimizing efforts resources.

Language: Английский

A novel discrete learning-based intelligent methodology for breast cancer classification purposes DOI
Mehdi Khashei, Negar Bakhtiarvand

Artificial Intelligence in Medicine, Journal Year: 2023, Volume and Issue: 139, P. 102492 - 102492

Published: Jan. 19, 2023

Language: Английский

Citations

10
Analysis of energy management in a hybrid renewable power system using MOA technique DOI

K. A. Indu Sailaja,

K. Rahimunnisa

Environment Development and Sustainability, Journal Year: 2024, Volume and Issue: 26(7), P. 18989 - 19011

Published: May 10, 2024

Language: Английский

Citations

3
Predicting Offshore Oil Slick Formation: A Machine Learning Approach Integrating Meteoceanographic Variables DOI Open Access
Simone Carneiro Streitenberger, Estevão Luiz Romão, Fabrício Alves de Almeida

et al.

Water, Journal Year: 2025, Volume and Issue: 17(7), P. 939 - 939

Published: March 24, 2025

The presence of oil slicks in the ocean presents significant environmental and regulatory challenges for offshore processing operations. During primary oil–water separation, produced water is discharged into ocean, carrying residual oil, which measured using total grease (TOG) method. formation spread are influenced by metoceanographic variables, including wind direction (WD), speed (WS), current (CD), (CS), wave (WWD), peak period (PP). In Brazil, limits impose sanctions on companies when exceed 500 m length, making accurate prediction their occurrence extent crucial operators. This study follows three main stages. First, performance five machine learning classification algorithms evaluated, selecting most efficient method based metrics from a Brazilian company’s slick database. Second, best-performing model used to analyze influence variables TOG levels detection probability. Finally, third stage examines detected identify key contributing factors. results enhance decision-support frameworks, improving monitoring mitigation strategies discharges.

Language: Английский

Citations

0
A review of asset management using artificial intelligence‐based machine learning models: Applications for the electric power and energy system DOI Creative Commons
Gopal Lal Rajora, Miguel Á. Sanz-Bobi, Lina Bertling Tjernberg

et al.

IET Generation Transmission & Distribution, Journal Year: 2024, Volume and Issue: 18(12), P. 2155 - 2170

Published: June 1, 2024

Abstract Power system protection and asset management present persistent technical challenges, particularly in the context of smart grid renewable energy sectors. This paper aims to address these challenges by providing a comprehensive assessment machine learning applications for effective power systems. The study focuses on increasing demand production while maintaining environmental sustainability efficiency. By harnessing modern technologies such as artificial intelligence (AI), (ML), deep (DL), this research explores how ML techniques can be leveraged powerful tools industry. showcasing practical success stories, demonstrates growing acceptance significant technology current future business needs sector. Additionally, examines barriers difficulties large‐scale deployment settings exploring potential opportunities tactics. Through overview, insights into transformative shaping are provided.

Language: Английский

Citations

2
Enhancing weld line visibility prediction in injection molding using physics-informed neural networks DOI Creative Commons
Andrea Pieressa,

Giacomo Baruffa,

Marco Sorgato

et al.

Journal of Intelligent Manufacturing, Journal Year: 2024, Volume and Issue: unknown

Published: July 13, 2024

Abstract This study introduces a novel approach using Physics-Informed Neural Networks (PINN) to predict weld line visibility in injection-molded components based on process parameters. Leveraging PINNs, the research aims minimize experimental tests and numerical simulations, thus reducing computational efforts, make classification models for surface defects more easily implementable an industrial environment. By correlating with Frozen Layer Ratio (FLR) threshold, identified through limited data generates synthetic datasets pre-training neural networks. demonstrates that quality model pre-trained PINN-generated achieves comparable performance randomly initialized network terms of Recall Area Under Curve (AUC) metrics, substantial reduction 78% need points. Furthermore, it similar accuracy levels 74% fewer The results demonstrate robustness networks PINNs predicting visibility, offering promising minimizing efforts resources.

Language: Английский

Citations

2