AI in Mechanics of Nonwoven Materials (Ref: SF-ED-2025)

About the Project

In contrast to composites and woven fabrics, nonwoven materials have a unique web structure, which is composed of randomly oriented fibres bonded via mechanical, thermal or chemical techniques. Nonwoven materials are engineered fabrics, which could be disposable or durable, and the properties of these materials such as, strength, softness, filtration, flame retardancy, absorbency, stretch etc., could be designed according to their specific purposes (hygiene, filtering etc.). Nonwovens had a vital role during COVID’19 pandemic as they were utilized in fabrication of disposable masks, tissues, overalls, bonnets and hygiene products, since these products are mostly made of polymers-based nonwovens.

The main aim of the proposed project is to develop a novel artificial intelligence (AI) scheme for designing nonwoven materials considering required microstructure and mechanical performance. This novel scheme will analyse 3D orientation distribution function (ODF) of the nonwoven fibres and their corresponding manufacturing parameters (bond pattern, basis weight, speed, angle, stretch, temperature, etc.). The outcomes of the proposed project are vital for developing, prototyping and simulating real-life performance of the nonwoven materials (strength, filtration, absorption, wear, cost, basis weight, etc.), and will lead to design and manufacturing of innovative advanced nonwoven materials with minimum time and cost based on AI driven machine learning system. The AI based software tool will lead to various innovations in manufacturing of nonwovens with reduced basis weight, cost, waste, buckling and local damage associated with the traditional processes. The proposed scheme will forward-predict and optimise process parameters considering their short- and long-term effects, time influence, loading conditions and fibre-to-fibre interaction. This project will answer the following question: “What should be done to design a new nonwoven or improve an existing one at the design stage before manufacturing?”, and lead to more diverse and innovative advanced materials and efficient processes with improved sustainability, efficiency and fabric performance.

Major aims of this project are as follows:

1. Analysis of 3D microstructure of nonwovens experimentally (X-ray micro-CT and SEM) and numerically (3D ODF, 3D crimp), and develop an algorithm system (in MATLAB) to parametrically and mathematically capture, illustrate and mimic their fibrous microstructural composition before, during and after deformation.
2. Development and validation of multi-scale 3D parametric nonlinear finite element analysis (FEA) model (within MSC. Marc & Python) to simulate tension, compression, folding and recovery (spring-back) behaviour of nonwovens for various application-relevant scenarios.
3. Designing an AI software tool (with Python) based on machine learning for predicting and optimizing the microstructure and manufacturing parameters of nonwovens considering the desired / required real-life usage performance and behaviour. This novel AI software tool will incorporate FEA and 3D ODF software algorithms developed within this proposal and use them within the machine learning system for learning, storing, and providing designs and solutions.

Name of primary supervisor/CDT lead:

Dr Emrah Demirci E.Demirci@lboro.ac.uk

https://www.lboro.ac.uk/schools/meme/staff/emrah-demirci/

Entry requirements:

Undergraduate and MSc degrees in Mechanical Engineering or relevant fields.

English language requirements:

Applicants must meet the minimum English language requirements

Bench fees required: Yes

Bench fee value: 5000

Closing date of advert: 15 Jun 2026

Start date:01 April 2026; 01 July 2026, 01 Oct 2026

Full-time/part-time availability: Full-time 3 years

Fee band: 2025/26 Band RB (UK £5,006, International £28,600)

How to Apply:

All applications should be made online. Under Campus, please select *Loughborough* and select Programme ‘Mechanical and Manufacturing Engineering’. Please quote the advertised reference number ‘SF-ED-2025’ in your application under the ‘Finance’ section.

Applications must include a personal statement, up-to-date curriculum vitae (CV), details of two referees (one from your highest degree qualification), certified certificates and transcripts for all completed degree programmes, and a reference to the project ‘SF-ED-2025’.

To avoid delays in processing your application, please ensure that you submit the above supporting documents.

Project search terms:

artificial intelligence, materials science, mathematical modelling, mechanical engineering, solid mechanics, textiles, mechanics of textiles, finite element analysis, Python coding

Email address Wolfson:

ws.phdadmin@lboro.ac.uk