Expensive models and experiments
PIML can reduce repeated simulation or experimental cost while retaining the governing knowledge used in Carpet and Textile Technology.
Physics-Informed Machine Learning Society
FDP: 25 September 2026
Annual Meeting: 08–09 July 2027
Andhra Pradesh, India
pimlsociety@gmail.com
Carpet and Textile Technology covers fibre selection, yarn formation, weaving, knitting, tufting, nonwovens, dyeing, finishing, coating, backing, testing, quality and recycling. Carpet production adds pile geometry, tuft bind, backing adhesion, dimensional stability, wear, acoustics and floor-interface performance.
PIML can connect process settings and multi-scale textile structure to permeability, deformation, dye transport, thermal/acoustic behaviour and durability. Exact carpet-labelled PIML is scarce, so adjacent fibre/fabric studies must be identified as methodological evidence rather than carpet validation.
This page presents ten focused research areas, degree-level project pathways, selected publications and direct support through the PIMLS biweekly members meeting.
This Carpet and Textile Technology guide covers Physics-Informed Neural Networks (PINNs), physics-guided machine learning, scientific machine learning, neural operators, hybrid models and engineering digital twins. Explore the research and project pathways below, then join the Physics-Informed Machine Learning Society to connect with the international PIMLS community.
Use available scientific knowledge to make limited data more useful, transparent and testable.
PIML can reduce repeated simulation or experimental cost while retaining the governing knowledge used in Carpet and Textile Technology.
Learn uncertain parameters, closures or discrepancies around an inspectable mechanistic foundation.
Test whether structured models generalize across geometries, materials, assets, operating regimes or sites.
Use physical residuals, independent measurements, uncertainty and conventional engineering baselines before deployment.
Each card connects a meaningful Carpet and Textile Technology question with suitable scientific knowledge, modelling choices and evidence needed to test it.
Fibre geometry, chemistry and variability determine downstream behaviour. PIML opportunities: Use dimensional and material priors for small-data blend/property models.
Draft, twist and tension affect evenness, strength and hairiness. PIML opportunities: Combine mass/twist relationships and machine dynamics with sensor data.
Tension, loop/interlacement geometry and speed influence defects. PIML opportunities: Use kinematic and tension constraints for monitoring and parameter optimization.
Gauge, stitch rate, pile height and yarn feed determine surface structure. PIML opportunities: Develop geometry/mass-conserving quality and defect models.
Adhesive flow, curing and interfaces control tuft bind and stability. PIML opportunities: Fuse rheology, heat/curing and adhesion tests with learned residuals.
Dye transport and fixation depend on chemistry, time and temperature. PIML opportunities: Embed kinetic/mass-balance features in dyeability and recipe models.
Application, drying and curing determine hand and function. PIML opportunities: Use fluid/thermal balances for pickup, thickness and energy estimation.
Flow depends on fibre, yarn and fabric pore scales. PIML opportunities: Use porous-flow PINNs and scale bridging with measured pressure/flow.
Anisotropy, large deformation and hysteresis complicate constitutive laws. PIML opportunities: Infer objective, stable material response from full-field and cyclic tests.
Repeated loads cause nonlinear recovery and residual deformation. PIML opportunities: Use viscoelastic/contact-informed sequence models for durability.
Start with a scope that matches your time, mathematical background, experimental access and expected research contribution.
Learn the foundations with a bounded, measurable system.
A reproducible implementation, clear baselines, a manageable dataset and physically meaningful validation.
Combine an engineering model, substantial data and rigorous comparison.
A thesis-quality study with held-out regimes, mechanistic and data-only baselines, ablation and uncertainty.
Address a publishable methodological, multiscale or deployment research gap.
New methodology or validated engineering insight, multi-regime evidence, reproducible software and journal publications.
Choose one Carpet and Textile Technology question and a measurable engineering output.
State the governing relationships, constraints or validated domain knowledge you will retain.
Build mechanistic and data-only baselines before the hybrid model.
Hold out experiments, conditions, assets, sites or regimes at the deployment level.
Report uncertainty, ablation, limitations, data lineage and reproducible code.
Use this focused reading list to understand the general PIML framework, direct Carpet and Textile Technology evidence and suitable hybrid modelling methods.
Do not list papers only. Compare the engineering question, incorporated knowledge, data, split strategy, baselines, uncertainty and evidence level.
This source is included in the Carpet and Textile Technology literature guide because it demonstrates or reviews a relevant physics-informed, hybrid, inverse, surrogate or scientific-machine-learning approach. Read the methods, data split, baselines and validation evidence—not only the reported accuracy.
This source is included in the Carpet and Textile Technology literature guide because it demonstrates or reviews a relevant physics-informed, hybrid, inverse, surrogate or scientific-machine-learning approach. Read the methods, data split, baselines and validation evidence—not only the reported accuracy.
This source is included in the Carpet and Textile Technology literature guide because it demonstrates or reviews a relevant physics-informed, hybrid, inverse, surrogate or scientific-machine-learning approach. Read the methods, data split, baselines and validation evidence—not only the reported accuracy.
This source is included in the Carpet and Textile Technology literature guide because it demonstrates or reviews a relevant physics-informed, hybrid, inverse, surrogate or scientific-machine-learning approach. Read the methods, data split, baselines and validation evidence—not only the reported accuracy.
This source is included in the Carpet and Textile Technology literature guide because it demonstrates or reviews a relevant physics-informed, hybrid, inverse, surrogate or scientific-machine-learning approach. Read the methods, data split, baselines and validation evidence—not only the reported accuracy.
This source is included in the Carpet and Textile Technology literature guide because it demonstrates or reviews a relevant physics-informed, hybrid, inverse, surrogate or scientific-machine-learning approach. Read the methods, data split, baselines and validation evidence—not only the reported accuracy.
Scientific ML, optimization, trustworthy AI and reproducible research software.
Differential equations, numerical methods, inverse problems and uncertainty.
Instrumentation, data acquisition, state estimation and responsible deployment.
Experiments, calibration, validation evidence and practical expertise for Carpet and Textile Technology.
These answers help students avoid common scope, terminology and validation mistakes.
Use the biweekly meeting form for research guidance.
Request accessNo. Carpet and Textile Technology projects may use physics-guided features, hybrid residual models, differentiable simulators, neural operators, constrained architectures or data assimilation. State exactly what knowledge is incorporated.
Choose one engineering question, a measurable output and a defensible mechanistic baseline. Add learning only where data can identify an uncertainty or discrepancy.
A meaningful question, justified prior knowledge, deployment-level holdouts, strong baselines, ablation, uncertainty, reproducibility and honest limitations.
Simulation can broaden coverage, but simulation-only evidence cannot establish real-system accuracy. Use calibrated experiments, field measurements or trusted independent references appropriate to the claim.
Submit the biweekly members meeting form to discuss your project level, branch, data, model, validation plan and possible collaborators.
Join the biweekly members meeting for project guidance, collaboration and publication planning—or contact the Society directly.
Meeting participation is requested through the Google form. Complete it carefully so the Society can understand your research interest.