CONFERENCE AGENDA
CONFERENCE AGENDA
Agenda
Key Information:
- Day 1: 8:00 to 18:00, Welcome Reception: 18:30
- Day 2: 8:45 to 17:30, Gala Dinner: 19:00
- Day 3: 9:00 to 14:00, NCC and Isambard AI Visit: 14:30
* Preliminary Programme, might be subject to minor changes
AICOMP25 - Monday, 1st of September 2025
| Monday, 1st of September 2025 | ||||||
| 08:00 | Registration and coffee | |||||
| 09:00 | Opening Ceremony | |||||
| 09:15 |
Plenary Lecture: Professor Adam Sobey Programme Director for Data-Centric Engineering at The Alan Turing Institute, UK Title TBC |
|||||
| Session 1 | Session 2 | |||||
| AI-Driven Process Modelling and Simulation in Composites | Mechanical Behaviour and Failure Prediction with AI | |||||
| Time | Type of presentation | Authors | Title | Type of presentation | Authors | Title |
|---|---|---|---|---|---|---|
| 10:10 | Keynote |
Arghyanil Bhattacharjee¹, Kamyar Gordnian³, Reza Vaziri¹, Trevor C Campbell² and Anoush Poursartip¹³ ¹ Composites Research Network, Departments of Materials Engineering and Civil Engineering, The University of British Columbia, Vancouver, BC, Canada ² Department of Statistics, The University of British Columbia, Vancouver, BC, Canada ³ Convergent Manufacturing Technologies, Vancouver, BC, Canada |
AN UNCERTAINTY QUANTIFICATION FRAMEWORK FOR THERMAL MANAGEMENT IN COMPOSITES MANUFACTURING | Keynote |
Wenbin Yu¹, Banghua Zhao¹ and R. Byron Pipes² ¹ School of Aeronautics and Astronautics, Purdue University, USA ² College of Engineering, Purdue University, USA |
ADVANCING MULTISCALE MODELING OF COMPOSITES THROUGH ARTIFICIAL INTELLIGENCE |
| 10:40 | Oral |
Salman Zafar¹'², Mustafa Unel¹'² and Hatice S. Sas¹'²'³ ¹ Faculty of Engineering and Natural Sciences, Sabanci University, Orhanli-Tuzla, Istanbul, Turkey ² Integrated Manufacturing Technologies Research and Application Center, Sabanci University, Orhanli-Tuzla, Istanbul, Turkey ³ School of Mechanical, Aerospace and Civil Engineering, The University of Sheffield, UK |
DETECTING DEFECTS AND DISSIMILAR REGIONS IN LIQUID COMPOSITE MOLDING: A DEEP LEARNING BASED APPROACH TO RESIN FLOW MONITORING | Oral |
Luca Patrignani, Silvestre T. Pinho Department of Aeronautics, Imperial College London, London, UK |
Graph Neural Networks for Efficient Prediction of Mechanical Response in Composite Structures with Models using Unstructured Meshes |
| 11:00 | Oral |
Jimmy G. Jean, Guillaume Broggi and Baris Caglar Aerospace Structures and Materials Department, Faculty of Aerospace Engineering, Delft University of Technology, Delft, the Netherlands |
IMAGE-BASED AI MODEL FOR PREDICTION OF MICROFLOW IN PROCESSING OF COMPOSITES | Oral |
Jacintha Y.Y. Loh, Vincent B.C. Tan and Tong-Earn Tay Department of Mechanical Engineering, National University of Singapore, Singapore |
OPEN-HOLE TENSION STRENGTH PREDICTION WITH MACHINE LEARNING |
| 11:20 | Coffee Break | |||||
| 11:50 | Oral |
S. Fernández-León¹'², D. Mocerino², J. Fernández-León¹, R. Valle¹, L. Baumela¹ and C. González²'³ ¹ Departamento de Inteligencia Artificial, Universidad Politécnica de Madrid, E.T.S. de Ingenieros Informáticos, Madrid, Spain ² IMDEA Materiales, Madrid, Spain ³ Departamento de Ciencia de Materiales, Universidad Politécnica de Madrid, Madrid, Spain |
Reinforcement Learning for Resilient Manufacturing of Structural Composites by Liquid Moulding | Oral |
Kasper Foss Hansen, Dimitrios Bikos, and Soraia Pimenta Department of Mechanical Engineering, Imperial College London, London, United Kingdom |
CONVOLUTIONAL NEURAL NETWORKS FOR FAILURE PREDICTION IN TOW-BASED DISCONTINUOUS COMPOSITES |
| 12:10 | Oral |
Ashish Hegde, Dimitrios Zarouchas, Baris Caglar Aerospace Structures and Materials Department, Faculty of Aerospace Engineering, Delft University of Technology, Delft, the Netherlands |
Graph Neural Network based surrogate for cure simulation of composites | Oral |
S.Hasebe¹, R.Higuchi², T.Yokozeki² and S.Takeda ¹'² Department of Aeronautics and Astronautics, The University of Tokyo, Japan ³ Aviation Technology Directorate, Japan Aerospace Exploration Agency (JAXA), Tokyo, Japan |
MACHINE LEARNING-BASED LOW-VELOCITY IMPACT DAMAGE PREDICTION FOR CARBON FIBER REINFORCED PLASTICS |
| 12:30 | Oral |
Siyuan Chen¹, Adam J. Thompson¹, Tim J. Dodwell²'³, Stephen R. Hallett¹ and Jonathan P.-H. Belnoue¹'⁴ ¹ Bristol Composites Institute, University of Bristol, UK ² Department of Engineering, University of Exeter, UK ³ digiLab, The Innovation Centre, Exeter, UK ⁴ National Composites Centre, Bristol, UK |
PROBABILISTIC AI FOR IMPROVED PROCESS ROBUSTNESS IN NON-CRIMP FABRIC FORMING | Oral |
Luan Trinh¹, Quaiyum M. Ansari² and Paul Weaver³ ¹ Faculty of Engineering and Technology, Technological University of the Shannon, Midlands Midwest, Ireland ² Department of Aerospace and Mechanical Engineering, South East Technological University, Carlow, Ireland ³ Bernal Institute, School of Engineering, University of Limerick, Ireland |
MACHINE LEARNING-AIDED CLASSIFICATION OF BUCKLING BEHAVIOUR IN STIFFENED COMPOSITE CYLINDRICAL SHELLS WITH GEOMETRIC AND MATERIAL UNCERTAINTIES |
| 12:50 | Oral |
Julian Greif, Nils Meyer Data-driven Product Engineering and Design, University of Augsburg, Germany |
Fast prediction of warpage in injection-molded short fiber reinforced composites by coupling machine learning and differentiable FEM to incorporate real data | Oral |
Christian Düreth¹, Andreas Hornig¹'², and Maik Gude¹ ¹ Institute of Lightweight Engineering and Polymer Technology (TUD Dresden University of Technology, Germany) ² Center for Scalable Data Analytics and Artificial Intelligence Dresden/Leipzig (ScaDS.AI, TUD Dresden University of Technology, Germany) |
Gaussian Process Regression for Multi-Modal Fatigue Crack Growth Identification in Textile-Reinforced Composites |
| 13:10 | Lunch | |||||
| 14:10 |
Plenary Lecture: Professor Francisco Chinesta Professor of computational physics at Arts et Métiers Institute of Technology, Paris, France Hybrid AI to enhance composites science, engineering and technology |
|||||
| 15:00 | Flash talks | |||||
|
D. Gray¹, Y. Chen¹, A. Rhead¹, R. Butler¹ ¹ Department of Mechanical Engineering, University of Bath, UK FOURIER NEURAL OPERATOR TO PREDICT MICROSCALE STRESS AND DAMAGE FIELDS IN COMPOSITES |
||||||
|
Joseph Kirchhoff¹, Thomas O'Leary-Roseberry¹, John Yao¹, Dingcheng Luo¹, Yohannes Bekele¹, Tom Seidl², Tyler Hudson³, Andy Newman³, Wesley Tayon³, Mehran Tehrani⁴, Omar Ghattas¹ ¹ The University of Texas at Austin, USA ² Sandia National Labs, USA ³ NASA Langley Research Center, USA ⁴ The University of California at San Diego, USA MICRON-SCALE HETEROGENEOUS CHARACTERIZATION OF THERMOPLASTIC COMPOSITES VIA SEM-DIC, FINITE ELEMENTS & NEURAL OPERATORS |
||||||
|
Kailun Deng¹, Hasan Caglar², Yifan Zhao¹ and David Ayre² ¹ Centre for Life-cycle Engineering and Management, Cranfield University, UK ² Composites and Advanced Materials Centre, Cranfield University, UK Artificial Intelligence-Assisted Stacking Sequence Design in Composite Laminates |
||||||
|
Kieran Guoite¹'², Chris Dighton¹, Cristian Lira¹, Ole T. Thomsen², Jonathan P.-H. Belnoue¹'² ¹ National Composites Centre, Feynman Way, Bristol, United Kingdom ² Bristol Composites Institute, University of Bristol, Queens Building, University Walk, Bristol, United Kingdom Implementation of Gaussian Process Machine Learning for Resin Infusion Simulations |
||||||
|
Yan Shen¹, Tianyou Yuan¹, Jun Zhou², Cheng Qiu³, Jinglei Yang¹'⁴ ¹ Department of Mechanical and Aerospace Engineering, The Hong Kong University of Science and Technology ² School of Nursing, Center of Smart Health, The Hong Kong Polytechnic University, HKSAR, China ³ Institute of Mechanics, Chinese Academy of Sciences, China ⁴ HKUST Shenzhen-Hong Kong Collaborative Innovation Research Institute, China Multimodal Fusion Learning for Sustainable Composite Manufacturing: Integrating Microstructural Imaging and Multi-Objective Process Optimization |
||||||
|
Kuthan Çelebi¹, Oleksandr G. Kravchenko² and Sergii G. Kravchenko¹ ¹ Department of Materials Engineering, The University of British Columbia ² Department of Mechanical and Aerospace Engineering, Old Dominion University, U.S.A A DATA-DRIVEN SURROGATE MODELLING FRAMEWORK FOR MULTI-SCALE ANALYSIS OF MORPHOLOGICALLY COMPLEX COMPOSITES |
||||||
|
Xin Lu¹, Ryo Higuchi¹ and Tomohiro Yokozeki¹ ¹ Department of Aeronautics and Astronautics, The University of Tokyo, Japan Open-source C++ user subroutines for scalable and data-driven fracture analysis of composite materials using Abaqus |
||||||
|
Xiaohui Zhang¹, Ning Dong² and Gerhard Ziegmann³ ¹ Institute for Polymer Materials and Plastics Technology, Clausthal University of Technology, Germany ² Institute for Informatics, Clausthal University of Technology, Germany ³ Institute for Polymer Materials and Plastics Technology, Clausthal University of Technology, Germany Deep Learning-Based Flow Front Detection for In-Plane 1D Permeability Measurement |
||||||
|
Dhiraj Biswas¹'⁴, Rajesh Nakka², Sathiskumar A. Ponnusami², Ganapathi A. Sengodan³ ¹ Department of Materials, University of Oxford, United Kingdom ² Department of Engineering, City St George's, University of London, United Kingdom ³ School of Science, Engineering and Environment, University of Salford, United Kingdom Microscale tensile-compressive response and fracture prediction of composites using multi-output CNN model |
||||||
|
J. Seiffert¹, M. Ertl¹ and K. Drechsler¹ ¹ Chair of Carbon Composites, Technical University of Munich, Germany DEEP LEARNING TECHNIQUES FOR IN-SITU MISALIGNMENT QUANTIFICATION IN CONTINUOUS FIBER ADDITIVE MANUFACTURING |
||||||
|
Mohammad N. Saquib¹, Richard Larson¹, Jiang Li², Sergii G. Kravchenko³ and Oleksandr G. Kravchenko¹ ¹ Mechanical and Aerospace Engineering Department, Old Dominion University, USA ² Electrical and Computer Engineering Department, Old Dominion University, USA ³ Department of Materials Engineering, The University of British Columbia, Canada RECONSTRUCTION OF FIBER ORIENTATION MORPHOLOGY IN MOLDED DISCONTINUOUS FIBER COMPOSITES USING RESIDUAL STRESS-BASED DEEP LEARNING |
||||||
|
Ji Dong¹, Ali Kandemir², Ian Hamerton² ¹ School of Engineering Mathematics and Technology, University of Bristol, UK ² Bristol Composites Institute, School of Civil, Aerospace and Design Engineering, University of Bristol, UK BEYOND PIXELS: NEURAL IMPLICIT REPRESENTATIONS FOR ACCURATE FIBRE ALIGNMENT IN COMPOSITES |
||||||
| 15:40 | Poster Session Followed by Coffee Break | |||||
| Session 1 | Session 2 | |||||
| AI-Driven Process Modelling and Simulation in Composites | Mechanical Behaviour and Failure Prediction with AI | |||||
| 16:20 | Oral |
Tim Newman¹, Cristian Lira¹, Jamie Hartley², Mindaugas Max Sasnauskas², Arjen Koorevaar³ ¹ National Composites Centre, Engineering Development, Bristol, UK ² National Composites Centre, Manufacturing Development, Composite Moulding, Bristol, UK ³ Polyworx BV, Advanced Computing, Nijverdal, The Netherlands |
Deep multi-agent reinforcement learning for vent and inlet positioning and quantity in resin transfer moulding | Oral |
Chaeyoug Hong¹ and Wooseok Ji² Department of Mechanical Engineering, Ulsan National Institute of Science and Technology, Republic of Korea |
EFFICIENT TRAINING STRATEGY FOR A SCALABLE MICROMECHANICS MODEL PREDICTING LOCALIZED STRESSES BETWEEN FIBRES |
| 16:40 | Oral |
Liam D. Burns, Fadi El Kalach, Saeed Faharani, and Ramy Harik Clemson Composites Center, Clemson University, Greenville, SC, USA |
A Machine Learning Approach to Process Parameter Optimization of High-Pressure Resin Transfer Molding (HP-RTM) Systems | Oral |
Mohammad N. Saquib¹, Richard Larson¹, Jiang Li², Sergii G. Kravchenko³ and Oleksandr G. Kravchenko¹ ¹ Mechanical and Aerospace Engineering Department, Old Dominion University, USA ² Electrical and Computer Engineering Department, Old Dominion University, USA ³ Department of Materials Engineering, The University of British Columbia, Canada |
FAILURE PREDICTION IN MOLDED COMPOSITES USING RESIDUAL STRESS AND DEEP LEARNING DRIVEN MICROSTRUCTURE RECONSTRUCTION |
| 17:00 | Oral |
Nuri Ersoy¹, Mehmet Can Engül, Pınar Acar² ¹ Boazici University, TURKEY ² Virginia Tech University, USA |
A NEURAL NETWORK APPROACH TO COMPOSITES PROCESS SIMULATIONS | Oral |
J. Gerritsen¹, A. Hornig¹'²'³ and M. Gude³ ¹ Institute of Lightweight Engineering and Polymer Technology, TUD Dresden University of Technology, Germany ² Center for Scalable Data Analytics and Artificial Intelligence Dresden/Leipzig (ScaDS.AI), TUD Dresden University of Technology, Germany ³ Department of Engineering Science, Solid Mechanics and Materials Engineering, University of Oxford, OX1 3PJ, Oxford, United Kingdom |
Influence of the sampling strategy for training data on edge case performance of data driven failure criterion for FRP |
| 17:20 | Oral |
Suplal Tudu and R. Velmurugan Aerospace Engineering, Indian Institute of Technology Madras, India |
Modelling of Curing Process of Fiber Reinforced Polymer Composites in Autoclave using AI | Oral |
Runze Li, Mário Miranda and Silvestre T. Pinho Department of Aeronautics, Imperial College London, London, UK |
The uncertainty quantification of composite failure predictions based on Bayesian neural networks |
| 17:40 | Oral | Oral |
Attada Phanendra Kumar¹, Shailesh Garg², Souvik Chakraborty², Dineshkumar Harursampath¹ and Sathiskumar Anusuya Ponnusami³ ¹ Department of Aerospace Engineering, Indian Institute of Science, Bengaluru, India ² Department of Applied Mechanics, Indian Institute of Technology Delhi, Delhi, India ³ Department of Engineering, City St George's, University of London, London, United Kingdom |
Conformal prediction for uncertainty quantification of composite thermomechanical properties using randomised prior wavelet neural operators | ||
| 18:00 | End of the day 1 | |||||
| 18:30 | Welcome reception: Wills Memorial Hall | |||||
AICOMP25 - Tuesday, 2nd of September 2025
| Tuesday, 2nd of September 2025 | ||||||||||
| 08:45 | Registration and coffee | |||||||||
| 09:15 |
Plenary Lecture: Dr Pierre-Yves Mechin Composites structural analyst & materials specialist, PlyNow FROM MOLECULE TO STRUCTURE, COMPOSITES BEHAVIOUR AND PERFORMANCE ENHANCED BY AI |
|||||||||
| Session 3 | Session 4 | |||||||||
| AI for Intelligent Composite Manufacturing and Control | Data-Driven Surrogate Models and Accelerated Simulations | |||||||||
| Time | Type of presentation | Authors | Title | Type of presentation | Authors | Title | ||||
|---|---|---|---|---|---|---|---|---|---|---|
| 10:10 | Keynote |
Ramy Harik Clemson Composites Center, Clemson University |
Towards Smart Automated Fiber Placement | Keynote |
Pavana Prabhakar¹, Haotian Feng², Sabarinathan P Subramaniyan³, and Hridyesh Tewani⁴ ¹ Department of Mechanical Engineering, University of Wisconsin-Madison, USA ² Department of Civil & Environmental Engineering, University of Wisconsin-Madison, USA |
AI FOR THE ANALYSIS, DESIGN, AND OPTIMIZATION OF COMPOSITES | ||||
| 10:40 | Oral |
Anatoly Koptelov, Hanna Beketova, Jonathan P.-H. Belnoue, Stephen R. Hallett, Iryna Tretiak and Bassam El Said Bristol Composites Institute, University of Bristol, Bristol, BS8 1TR, United Kingdom |
Aspects of spatial time series forecasting for composite manufacturing problems of various dimensionality | Oral |
M. Petrolo¹, M. Santori¹, K. Johnson², E. Zappino¹ and N. Zobeiry² ¹ MUL2 LAB, Department of Mechanical and Aerospace Engineering, Politecnico di Torino, Italy ² Department of Materials Science and Engineering, University of Washington, Seattle, WA, USA |
ASSESSMENT OF MULTI-FIDELITY STRUCTURAL THEORIES TO TRAIN PROBABILISTIC MACHINE LEARNING FOR PROCESS-INDUCED DEFECTS | ||||
| 11:00 | Oral |
Marcello Laurenti, Irene Bavasso, Erika Palazzi, Jacopo Tirillò, Fabrizio Sarasini and Filippo Berto University of Rome "La Sapienza", Department of Chemical Engineering Materials Environment |
AI-Driven Computational Framework for Optimizing FDM Process Parameters and Enhancing Mechanical Performance | Oral |
S. Fernández-León¹'², D. Mocerino², R. Valle¹, L. Baumela¹ and C. González²'³ ¹ Departamento de Inteligencia Artificial, Universidad Politécnica de Madrid, Spain ² IMDEA Materiales, Madrid, Spain ³ Departamento de Ciencia de Materiales, Universidad Politécnica de Madrid, Spain |
A deep surrogate model for accelerating LCM mould-filling simulations in unstructured and three-dimensional meshes | ||||
| 11:20 | Coffee Break | |||||||||
| 11:50 | Oral |
Jan Wolf¹, Aaron Vogel², Mathias Morgenstern², Christian Prescher³, Ulrich Burgbacher⁴, Manuel Prätorius⁴, Luis Garcia⁵, Benjamin Risse⁵, Thomas Behnisch¹ and Maik Gude¹ ¹ Institute for Lightweight Engineering and Polymer Technology, TUD Dresden University of Technology, Germany ² SURAGUS GmbH, Germany ³ STRUCNAMICS Engineering GmbH, Germany ⁴ tapdo technologies GmbH, Germany |
Tailoring carbon fibers combining novel inline sensors and machine learning | Oral |
Aewis K.W. Hii, Stephen R. Hallett and Bassam El Said Bristol Composites Institute, University of Bristol, UK |
Modelling defects and progressive 3D failure in large composite components with shell elements: a data-driven, multi-scale approach | ||||
| 12:10 | Oral |
Simone Bancora¹, Tim Newman¹, Paris Mulye² ¹ National Composites Centre, United Kingdom ² Quantiflex Simulations SAS, France |
Use of Deep Reinforcement Learning to achieve Real-time Control of a Resin Infusion Process | Oral |
Jens Wiegand¹ and Giuseppe Zumpano ¹ COMPACT Composite Impact Engineering LTD, UK ² Rolls Royce PLC, UK |
Accelerating composite impact simulations by the use of neural network based surrogate models | ||||
| 12:30 | Oral |
Patrick Flore, Fabian Röder, Kevin Chen, Andreas Gebhard Leibniz-Institut für Verbundwerkstoffe, Germany |
Geometry-Based Synthetic Data and Deep Learning for Online Surface Inspection of Fiber-Reinforced Composites | Oral |
Shuang Yan¹, Mikhail Matveev¹, Michael Causon², Marco Iglesias², Andreas Endruweit¹, and Michael Tretyakov² ¹ Composites Research Group, Faculty of Engineering, University of Nottingham, Nottingham, UK ² School of Mathematical Sciences, Faculty of Science, University of Nottingham, Nottingham, UK |
A SURROGATE MODEL FOR INVERSE PARAMETER ESTIMATION IN RESIN TRANSFER MOULDING PROCESSES | ||||
| 12:50 | Lunch | |||||||||
| Session 5 | Session 6 | |||||||||
| AI in Non-Destructive Testing and Structural Health Monitoring | AI-Driven Design and Industrial Applications in Composites | |||||||||
| 13:50 | Oral |
A. Tabatabaeian¹, B. Jerkovic², P. Harrison¹, E. Marchiori² and M. Fotouhi³ ¹ James Watt School of Engineering, University of Glasgow, UK ² Institute of Computing and Information Sciences, Radboud University, the Netherlands ³ Faculty of Civil Engineering and Geosciences, Delft University of Technology, the Netherlands |
Detection of Barely Visible Impact Damage in CFRP Composite Panels Using Deep Learning Models and Hybrid Glass/Carbon Sensors | Oral |
R.Zammit-Mangion¹, T.Ainsworth², C.Fallon¹, E.G.Loukaides¹ and F.Pinto¹ ¹ Department of Mechanical Engineering, University of Bath, United Kingdom ² GKN Aerospace, Isle of White, United Kingdom |
ENHANCING THE RELIABILITY OF ADHESIVELY BONDED AIRCRAFT JOINTS USING MACHINE LEARNING METHODS | ||||
| 14:10 | Oral |
Fabing Emmanuel¹'², Méchin Pierre-Yves¹ and Keryvin Vincent² ¹ Dassault Systèmes, France ² Université Bretagne Sud, IRDL, France |
AI BASED FIBRE MISALIGNMENT MEASUREMENT | Oral |
Göran Fernlund¹'², Alireza Forghani¹, Anthony Floyd¹, and Anoush Poursartip¹'² ¹ Convergent Manufacturing Technologies, Canada ² The University of British Columbia, Materials Engineering, Canada |
A structured approach to merging AI and ML into established composites process simulation and process analytics | ||||
| 14:30 | Oral |
Jonas Naumann¹'², Jonas P. Appels¹, Philipp Sämann¹, Timo de Wolff² and Christoph Brauer¹ ¹ Institute of Lightweight Systems, German Aerospace Center (DLR) Stade, Germany ² Institute of Analysis and Algebra, Technische Universität Braunschweig, Braunschweig, Germany |
ENHANCING COMPOSITE MICROGRAPH ANALYSIS WITH SEMANTIC SEGMENTATION | Oral |
J. Kucera National Composites Centre, UK |
CompoST – Composite Standard for composite data transfer and interoperability | ||||
| 14:50 | Oral |
Mahoor Mehdikhani, Rui Guo, Shailee Upadhyay, Christian Breite, and Yentl Swolfs Department of Materials Engineering, KU Leuven, Belgium |
Segmentation in X-ray computed tomography images using deep learning | Oral |
Hussain Abass¹'², Ross Allen¹, Andrew Corbett¹'³ and Ton Peijs² ¹ digiLab, UK ² WMG, University of Warwick ³ Alan Turing Institute, UK |
FASTER ANALYSIS AND OPTIMISATION OF DISCONTINUOUS COMPOSITES USING MACHINE LEARNING | ||||
| 15:10 | Coffee Break and Poster Session | |||||||||
| 15:50 | Oral |
Umeir Khan¹, Vincent K. Maes¹, Rob Hughes², Petar Zivkovic³, Jon Wright³, Turlough McMahon³, and James Kratz¹ ¹ Bristol Composites Institute, Department of Aerospace Engineering, University of Bristol, United Kingdom ² Department of Mechanical Engineering, University of Bristol, United Kingdom ³ Airbus UK, United Kingdom |
Transfer Learning for Efficient Photo-Inspection of In-plane Waviness | Oral |
J. Kucera, K. Angelov, P. Druiff National Composites Centre, UK |
National Composite Center upcoming projects | ||||
| 16:10 | Oral |
Rui Guo, Mahoor Mehdikhani, Christian Breite and Yentl Swolfs Materials Engineering, KU Leuven, Belgium |
A 2D packing generator for unidirectional fibre-reinforced composites based on a Generative Adversarial Network | Oral |
S. Psarras¹, G. Sotiriadis¹, M. Sergolle², T. Balutch², E. Billaudeau² and V. Kostopoulos¹ ¹ Department of Mechanical Engineering & Aeronautics, University of Patras, Greece ² Naval Group, Centre d'Expertise des Structures et Matériaux Navals Technocampus Océan, France |
ENHANCING REPAIR PATCH DESIGN FOR THICK COMPOSITE STRUCTURES IN NAVAL APPLICATION USING ARTIFICIAL INTELLIGENCE | ||||
| 16:30 | Oral |
A. Gazzola, M. Quaresimin and M. Zappalorto Department of Management and Engineering, University of Padova, Vicenza, Italy |
DEEP LEARNING APPROACH FOR STRUCTURAL HEALTH MONITORING OF MULTIDIRECTIONAL LAMINATES VIA ELECTRICAL MEASUREMENTS | Oral |
Yilun Dong¹, Zhong Zhang¹ ¹ School of Engineering Science, University of Science and Technology of China, China |
Artificial neural networks applied to polymer composites | ||||
| 16:50 | Oral |
Mengyue He¹'², Zhifang Zhang¹ and Karthik Ram Ramakrishnan³ ¹ Research Center for Wind Engineering and Engineering Vibration, Guangzhou University, Guangzhou, China ² College of Engineering, Shantou University, Shantou, China ³ Bristol Composites Institute, University of Bristol, United Kingdom |
SUPPORT VECTOR MACHINE ALGORITHMS FOR DELAMINATION ASSESSMENT IN VIBRATION BASED SHM | Oral |
Andrejs Krauklis¹ Latvia University of Life Sciences and Technologies, Faculty of Forest and Environmental Sciences, Institute of Civil Engineering and Woodworking, MEI Core Group, Latvia |
MODULAR MATERIALS INFORMATICS FRAMEWORK FOR ASSESSING COMPOSITE MATERIAL AGEING | ||||
| 17:10 | Oral |
Mihai M. Vasilache¹'², Iryna Tretiak³, Rostand B. Tayong¹ and Vladan Velisavljevic¹ ¹ Institute for Research in Engineering and Sustainable Environment (IRESE), School of Computer Science and Technology, University of Bedfordshire, Luton, United Kingdom ² GKN Aerospace Service Limited, London Luton Airport, Luton, Bedfordshire, United Kingdom ³ Bristol Composites Institute, University of Bristol, United Kingdom |
USING MACHINE LEARNING CONVOLUTION NEURAL NETWORK METHODS FOR THE ULTRASOUND CHARACTERISATION OF POROSITY ACROSS CARBON FIBRE REINFORCED POLYMER LAYERS | Oral | ||||||
| 17:30 | End of the day 2 | |||||||||
| 19:00 | GALA DINNER: The Sansovino Hall at Bristol Harbour Hotel | |||||||||
AICOMP25 - Wednesday, 3rd of September 2025
| Wednesday, 3rd of September 2025 | |||
| 09:00 | Coffee and Pastries | ||
| 09:30 |
Plenary Lecture: Dr Navid Zobeiry Associate Professor in the Materials Science & Engineering Department at the University of Washington in Seattle, USA Applied AI for Composites: From Accelerated Testing to Autonomous Certification and Smarter Engineering |
||
| Session 7 | |||
| Physics-Informed Neural Networks (PINNs) and Physics-Based AI | |||
| Time | Type of presentation | Authors | Title |
|---|---|---|---|
| 10:20 | Oral |
Ehsan Ghane¹, Marina Maia², Iuri Rocha², Martin Fagerström³, and Mohsen Mirkhalaf¹ ¹ Department of Physics, University of Gothenburg, Sweden ² Department, Delft University of Technology, The Netherlands ³ Department of Industrial and Materials Science, Chalmers University of Technology, Sweden |
HIERARCHICAL PHYSICALLY RECURRENT NEURAL NETWORKS FOR MULTI-SCALE MODELING OF WOVEN COMPOSITES |
| 10:40 | Oral |
Sahar Abouali, Anoush Poursartip, Reza Vaziri Composites Research Network, Departments of Civil Engineering and Materials Engineering, The University of British Columbia, Vancouver, BC, Canada |
A PHYSICS-INFORMED NEURAL NETWORK FOR INVERSE CHARACTERIZATION OF COMPOSITE DAMAGE MODELS USING FULL-FIELD EXPERIMENTAL DATA |
| 11:00 | Oral |
Bernabe Lorenzo Avila¹, Nils Meyer² and Dietmar Koch³ ¹ Materials Engineering, University of Augsburg, Germany ² Data-driven Product Engineering and Design, University of Augsburg, Germany ³ Materials Engineering, University of Augsburg, Germany |
Predicting Thermal Behaviour of C/C-SiC Fibre-Patched Structures Using Physics-Informed-Networks (PINNs) |
| 11:20 | Coffee break | ||
| 11:50 | Oral |
John M. Hanna¹'² ¹ Akhet solutions, Rennes, France ² Inria Rennes, France |
Applications of Physics-informed neural networks to Liquid composite molding |
| 12:10 | Oral |
Tobias Würth¹, Niklas Freymuth², Gerhard Neumann² and Luise Kärger¹ ¹ Institute of Vehicle System Technology, Karlsruhe Institute of Technology (KIT), Germany ² Autonomous Learning Robots, Karlsruhe Institute of Technology (KIT), Germany |
Physics-Informed MeshGraphNets (PI-MGNs) for ansiotropic materials |
| 12:30 | Oral |
Shady Adib¹, Ieva Misiunaite² ¹ School of Engineering, Newcastle University, Newcastle upon Tyne, United Kingdom ² Research Laboratory of Innovative Building Structures, Department of Aeronautical Engineering, Vilnius Gediminas Technical University, Vilnius, Lithuania |
AI-Enhanced Topology Optimisation of PLA Lattice Structures for Hybrid Composite Applications: Exploring Physics-Informed Approaches |
| 12:50 | Closing Ceremony | ||
| 13:00 | Farewell Lunch | ||
| 14:00 |
End of conference. Optional tour to the National Composite Centre and Isambard AI Start at 14:30 , estimated time return time 17:00 (TBC) |
||