Search
14 articles for “Surrogate modelling”
-
Bayesian Optimization–Driven Operating Parameter Tuning for Maximizing Methane Yield in Anaerobic Digestion
Abstract: To achieve maximum methane production in an anaerobic digestion (AD) process, a combination of various operational parameters must be tuned nonlinearly in the digestion ecosystem. The conventional trial and error optimization methods are slow, resource consuming, and in most instances, cannot model the intricate parameter interaction in biogas production. The current work introduces a Bayesian Optimization-based model to optimize the set of conditions to maximize the level of methane produced …
Published in International Journal of Energy and Thermal Applications · Vol. 4, Issue 1, 2026 · pp. 1–8 Read article
-
Machine Learning Optimization for VARTM Carbon Polymer Laminates
Abstract: Vacuum-assisted resin transfer moulding (VARTM) is a key low-cost, out-of-autoclave process for manufacturing large-scale carbon-fibre reinforced polymer (CFRP) laminates crucial to aerospace wings, wind-turbine blades, marine hulls, and automotive structures. Unpredictable resin flow often leads to voids, dry spots, and race-tracking defects, resulting in 27.9% scrap rates and lengthy, costly trial-and-error design cycles. Although surrogate models provide rapid impregnation predictions for simple flat-plate geometries, vision-based monitoring is limited to idealized …
Published in Journal of Polymer & Composites · Vol. 14, Issue 3, 2026 · pp. 229–245 Read article
-
AI-Driven Topology Optimization of Woven Fiber-Reinforced Composite Chassis Structures for Electric Vehicles Under Crash Loading
Abstract: The structural design of an electric vehicle (EV) chassis represents a unique engineering challenge to achieve minimal weight while meeting occupants' safety requirements during high-energy crash conditions without compromise to the battery housing's integrity or the geometrical constraints of the electric powertrain package. In this paper, a single framework is proposed to integrate physics-based artificial intelligence (AI) surrogate models using PINNs, CNN-accelerated topology optimization, and FEA to design woven fiber-reinforced …
Published in Journal of Polymer & Composites · Vol. 14, Issue 2, 2026 · pp. 72–89 Read article
-
AI-Assisted Optimization of Supersonic Airfoil Shapes Using CFD Coupling
Abstract: This paper presents a novel framework for optimizing supersonic airfoil geometries through integrated artificial intelligence and computational fluid dynamics coupling. Traditional gradient-based optimization methods for high-speed aerodynamic shapes suffer from computational expense and convergence difficulties in non-convex design spaces. The proposed methodology employs a deep neural network surrogate model trained on high-fidelity Reynolds-Averaged Navier-Stokes solutions to approximate aerodynamic performance metrics across the design space. A hybrid particle swarm-genetic algorithm searches …
Published in Journal of Aerospace Engineering & Technology · Vol. 16, Issue 1, 2026 Read article
-
Intelligent Design Approaches in Microwave Engineering Using Machine Learning Techniques
Abstract: In microwave engineering, machine learning (ML) has become a potent technology allowing quicker design cycles, improved modelling accuracy, and automatic optimisation of complicated systems. Recent developments in the use of ML methods to microwave components and systems, including antennas, filters, and high-frequency circuits, are summarised in this study. In the framework of electromagnetic simulation, surrogate modelling, and parameter extraction, supervised and unsupervised learning algorithms are addressed. Moreover, the study looked …
Published in Journal of Microwave Engineering and Technologies · Vol. 12, Issue 2, 2025 · pp. 31–38 Read article
-
AI-Accelerated Development of Gradient Polymer Nanocomposite Thin Films
Abstract: Gradient polymer nanocomposite thin films are an active field of materials research due to the fact that it enables scientists to de-facto regulate the optical, electrical, and mechanical properties of a film by merely altering its composition on a layer-by-layer basis. This type of control opens the gate to the improved flexible electronics, long lasting protective coats, and the new smart gadgets. The problem is, though, that it is a …
Published in Journal of Polymer & Composites · Vol. 14, Issue 2, 2026 · pp. 456–469 Read article
-
Design and Optimization of Radial Turbines for Waste Heat Recovery Applications
Abstract: Waste heat recovery (WHR) offers a compelling way to improve sustainability and energy efficiency in several different industrial sectors. In waste heat recovery (WHR) systems, radial turbines are essential because they capture waste heat and transform it into useful mechanical or electrical energy. A thorough summary of the design and optimization concepts guiding radial turbines for WHR applications is given in this review article. After outlining the basic concepts of …
Published in International Journal of Mechanical Dynamics and Systems Analysis · Vol. 1, Issue 2, 2023 · pp. 52–58 Read article
-
Machine Learning Based Optimization of Polymer Structure Property Relationships in Composite Material Systems
Abstract: In modern engineering applications, polymer-based composite materials have garnered a lot of attention because of their lightweight nature, high strength-to-weight ratio, and changing physical features. In order to maximize the relationships between polymer structure and properties in composite materials, this study suggests a strategy based on reinforcement learning (RL). The research utilized the Polymer Composite Properties Dataset, which contains 12,700 records associated with polymer matrices, reinforcement fillers, interfacial bonding characteristics, …
Published in Journal of Polymer & Composites · Vol. 14, Issue 3, 2026 · pp. 242–255 Read article
-
Experimental Validation and Implementation Framework for Optimized Methane Yield Prediction in Anaerobic Digestion
Abstract: The correct validation and realistic application of optimized anaerobic digestion (AD) models are essential steps in transferring biogas production systems to real-life. This paper outlines an experimental validation and deployment pipeline of an AI-optimized model of the methane yield prediction model based on the application of more advanced machine learning and Bayesian optimization methods. Others The validated surrogate-assisted optimization model was tested with controlled laboratory-scale AD experiments at optimized operating …
Published in International Journal of Environmental Noise and Pollution Control · Vol. 4, Issue 1, 2026 · pp. 25–32 Read article
-
Neuromorphic Spiking Neural Networks and Event-Driven Hardware: Architectures, Learning Paradigms, and Experimental Realizations
Abstract: With the current computational boom the research community is seeking for more sustainable energy efficient i.e. biologically inspired models of conventional Artificial Neural Networks (ANNs). Spiking Neural Networks (SNNs) known as the third generation of neural network models, provide a revolutionary approach by mimicking the asynchronized event-driven and temporally accurate signaling of the mammalian brain. Whereas conventional deep learning models operate with real-valued activations and dense matrix multiplications, SNNs use …
Published in Current Trends in Signal Processing · Vol. 16, Issue 2, 2026 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
-
Intuitionistic Fuzzy Hypergraph Laplacians and Dominating Transversals for Resilient Discrete Network Design
Abstract: This manuscript develops a discrete mathematical framework for resilience analysis on networks whose interactions are polyadic, uncertain, and partially conflicting. Classical graphs compress multi-way coordination into pairwise edges, while ordinary fuzzy graphs often ignore the non-membership information that becomes critical in emergency logistics, infrastructure interdependence, and cyberphysical coordination. We therefore formulate an intuitionistic fuzzy hypergraph in which each vertex hyperedge incidence carries membership, non-membership, and hesitation, and we construct a …
Published in Research & Reviews: Discrete Mathematical Structures · Vol. 13, Issue 2, 2026 · pp. 15–21 Read article
-
Smart Ways to Manage Waste with AI and IOT: A Review
Abstract: Rapid urban growth and population have led to exponential growth in municipal solid waste over traditional inefficient waste management systems (collection / segregation / disposal). This paper reviews the convergence of Internet-of- Things (IoT) and artificial intelligence (AI), seen as two potential smart techniques to launch smarter waste management. The research reports important applications for AI and IoT in waste classification, waste collection optimization, waste-to-energy as well as smart bin …
Published in International Journal of Advanced Control and System Engineering · Vol. 3, Issue 2, 2025 · pp. 26–31 Read article
-
Artificial Intelligence–Assisted Reduced-Order Modeling and Stability Control in Granular Couette Flow
Abstract: This study develops a reduced-order and stability-aware modeling framework for dense granular Couette flow by integrating continuum mechanics, bifurcation analysis, and data-driven stability estimation. Starting from coupled governing equations for momentum, granular temperature, and microstructural evolution, the system is nondimensionalized and reduced using a Galerkin projection consistent with shear-driven boundary conditions. This yields a low-dimensional nonlinear dynamical system that preserves the essential coupling between velocity, fluctuation energy, and structural relaxation. …
Published in Emerging Trends in Chemical Engineering · Vol. 13, Issue 3, 2026 Read article