Search
13 articles for “physics-informed neural networks”
-
A Physics-Informed Graph Neural Network Framework for Real- Time Thermal-Aware Fault Prediction and Adaptive Power Optimization in Heterogeneous System-on-Chip Architectures
Abstract: Heterogeneous System-on-Chip (SoC) architectures are increasingly adopted in edge computing, artificial intelligence, autonomous systems, and high-performance embedded platforms due to their superior computational efficiency and flexibility. However, increasing integration density and workload diversity introduce severe thermal hotspots, accelerated device degradation, and unexpected hardware faults that adversely affect system reliability and energy efficiency. This study proposes a Physics-Informed Graph Neural Network (PI-GNN) framework for real-time thermal- aware fault prediction and adaptive …
Published in Journal of VLSI Design Tools and Technology · Vol. 16, Issue 2, 2026 Read article
-
AI-Based Discovery of High-Performance Energy Storage Polymer Composites: A Comprehensive Review
Abstract: The accelerating global demand for high-performance energy storage systems has stimulated significant research into advanced polymer composites as next-generation electrolytes, electrode binders, and functional membranes for batteries, supercapacitors, and photovoltaic devices. However, the vast compositional and structural design space of polymer materials presents formidable challenges for conventional trial-and-error discovery strategies, which remain slow, costly, and biased by prior expert knowledge. Machine learning (ML) and artificial intelligence (AI) have emerged as …
Published in Journal of Polymer & Composites · Vol. 14, Issue 3, 2026 · pp. 1083–1097 Read article
-
Quasar: Quantum-Accelerated Sustainable Anomaly Recognition in Climate Systems
Abstract: Accurate detection of climate anomalies is vital for disaster alleviation and policy making in a sustainable manner, but customary detection methods face the challenges of computational inefficiency and physical inconsistency. In this study, we propose a novel approach called Quantum-Optimized Fuzzy Physics-Informed Neural Networks (QFuzzy-PINNs), which integrates quantum computing, fuzzy logic, and physics-informed deep learning. As a first step, we employ quantum annealing for conventional optimization to adjust multiple Gaussian …
Published in International Journal of Climate Conditions · Vol. 2, Issue 2, 2025 · pp. 18–27 Read article
-
Autonomous Agentic AI for Adaptive Cure Optimization and Defect Prevention in Thermoset Polymer Composite Manufacturing
Abstract: Thermoset polymer composites occupy a central position in modern structural manufacturing, from aircraft fuselages to wind-turbine blades. Despite progress in resin chemistry and fiber architecture, the “cure process” that transforms compliant preforms into load-bearing structures remains difficult to manage. Manufacturers encounter ‘voids’, “interlaminar delaminations”, and “spring-back distortion” when curing complex or thick-section parts. The cause is not ignorance of the relevant physics, but rather that ‘temperature’, ‘chemistry’, ‘rheology’, and ‘mechanics’ …
Published in Journal of Polymer & Composites · Vol. 14, Issue 2, 2026 · pp. 301–320 Read article
-
Integrating AI and ML in Tribology: A Review of Current Trends and Future Prospects
Abstract: This review paper explores the growing integration of artificial intelligence (AI) and machine learning (ML) within the field of tribology. Tribology, the study of friction, wear, and lubrication, is crucial for Improving the performance and longevity of mechanical systems. This review explores the role of AI and machine learning techniques, including artificial neural networks (ANNs), support vector machines (SVMs), and physics-informed machine learning (PIML)can be used to solve difficult tribological …
Published in Recent Trends in Fluid Mechanics · Vol. 12, Issue 3, 2025 · pp. 56–60 Read article
-
The Convergence of AI and Composites - A Review Anchored in Patent Trends
Abstract: The integration of artificial intelligence (AI) and machine learning (ML) techniques is revolutionizing the design, analysis, and optimization of polymer (PC/FRP), metal (MC), and ceramic matrix composites (CC). Techniques such as artificial neural networks (ANN), deep learning (DL), genetic algorithms (GA), and physics-informed machine learning (PIML) are employed to enhance property estimation, process optimization, and predictive modeling. These AI-driven frameworks enable virtual testing, application-specific material design, and real-time decision-making, while …
Published in Journal of Polymer & Composites · Vol. 13, Issue 6, 2025 · pp. 182–198 Read article
-
Machine Learning Assisted Optimization of Nanoscale MOSFET Parameters Using TCAD Simulation
Abstract: This paper presents a machine learning (ML) assisted framework for the multi-objective optimization of nanoscale bulk n-channel metal-oxide-semiconductor field-effect transistors (nMOSFETs) with a 10 nm physical gate length, high-k HfO₂ gate dielectric, and TiN metal gate. Technology computer-aided design (TCAD) simulations employing drift-diffusion transport, Shockley-Read-Hall recombination, Lombardi mobility degradation, and density- gradient quantum correction models are used to generate a parametric dataset of 2,400 device configurations spanning gate length (L), …
Published in Journal of Microelectronics and Solid State Devices · Vol. 13, Issue 1, 2026 · pp. 10–19 Read article
-
A Technical Blueprint for AI-Driven Localization in 6G Mobile Networks
Abstract: The advent of sixth-generation (6G) wireless systems promises unprecedented spatial resolution, ultra-low-latency, and pervasive connectivity, turning mobile localization from a peripheral service into a core enabler of immersive extended reality (XR), autonomous logistics, and digital twins. Yet, the sheer scale of dense terahertz (THz) deployments, the stochastic nature of reconfigurable intelligent surfaces (RIS), and the dynamic interference landscape render traditional model-based positioning techniques inadequate. This work investigates how artificial intelligence …
Published in Journal of Mobile Computing, Communications & Mobile Networks · Vol. 13, Issue 1, 2026 · pp. 26–34 Read article
-
Application of Convolutional Neural Networks in Design of Efficient Pipe Flow System
Abstract: Convolutional Neural Networks exhibit remarkable capabilities in flow pattern recognition, pressure drop prediction, leak detection, and system optimization through their ability to process complex spatial and temporal data patterns. The study examines CNN architectures specifically adapted for fluid dynamics applications, including data preprocessing techniques, feature extraction methods, and performance optimization strategies. Key applications include real-time flow monitoring, predictive maintenance, design parameter optimization, and anomaly detection in pipe networks. Comparative analysis …
Published in Recent Trends in Fluid Mechanics · Vol. 12, Issue 3, 2025 · pp. 1–9 Read article
-
A Hybrid Multi-Physics Ensemble Deep Learning Framework for Simultaneous Prediction of Thermal and Electrical Conductivity in Functional Polymer-Based Nanocomposites
Abstract: Polymer-based nanocomposites have become promising materials for applications in energy storage, flexible electronics, biomedical devices, aerospace components, and advanced engineering because of their tunable thermal and electrical properties. Reliable prediction of these properties is essential for accelerating material design; however, existing analytical models and conventional machine learning techniques often fail to represent the complex interactions among filler characteristics, polymer matrices, processing conditions, and interfacial transport phenomena. This work presents HMEP-Net, …
Published in Journal of Polymer & Composites · Vol. 14, Issue 3, 2026 · pp. 1062–1082 Read article
-
Utilizing Artificial Intelligence and Remote Sensing to Predict Flooding in Real-Time and Address Climate Resilience Policy in South Asia
Abstract: South Asia, a region characterized by hydro-climatic instability, faces an intensifying risk from devastating flooding, aggravated by human-induced climate change and intricate river basin interactions. Traditional flood prediction systems, based on limited in-situ data and resource-intensive physical models, have serious delays and resolution problems that make it harder to reduce disaster risk. The combined applications of Artificial Intelligence (AI) and high-resolution remote sensing (RS) constitute a paradigm shift in real-time …
Published in Journal of Remote Sensing & GIS · Vol. 17, Issue 1, 2026 Read article
-
Identifying and Implementing a Machine Learning Model Suitable for Processing Visually Evoked Potential
Abstract: A Brain-Computer Interface (BCI) is a system that translates brain activity patterns into computer commands, bypassing physical movement. Electroencephalography (EEG) is commonly used to acquire signals in BCI research. Visual evoked potentials (VEPs) are brain responses in the visual cortex to visual stimuli. Recent studies show that exposing individuals to flickering at a consistent frequency generates EEG signals synchronized with the stimulation. Efficient extraction of VEP signals begins with preprocessing …
Published in Journal of Microwave Engineering and Technologies · Vol. 11, Issue 2, 2024 · pp. 1–8 Read article
-
A Survey of Several Machine Learning (ML) Algorithms for Security Solution in Internet of Things (IoT) Networks
Abstract: The Internet of Things (IoT) refers to the integration of physical objects with the Internet, allowing for connectivity and monitoring. This idea has garnered immense attention from researchers and users alike, driven by the widespread accessibility of the Internet. It spans a wide range of devices, including smart versions of conventional appliances, innovative tools tailored for Internet-enabled ecosystems, and sensors that leverage connectivity to revolutionize industries such as manufacturing, healthcare, …
Published in Journal of Artificial Intelligence Research & Advances · Vol. 12, Issue 1, 2025 · pp. 1–11 Read article