PhD Thesis - Classification of acoustic signals created during the rapid deformation of microsamples by Machine Learning (M/F)

Job Description

Thesis Subject

By analyzing sound—specifically acoustic emission (AE)—it is possible to detect various atomic-scale processes (such as fracture, defect movement, and structural transformation) occurring within a material during deformation. But can we categorize these different types of processes based on sound? Can we also predict the crystal structure itself from the induced sound, anticipate micro-deformation, or even extrapolate the behavior of other materials? The project aims to use artificial intelligence (machine learning, or ML) to classify AE signals captured from microscopic samples during deformation. CASCADE-RAPIDE will employ micromechanical experiments to systematically study AE signal properties under various conditions. ML algorithms and perception tests will be used to analyze and classify the experimental data.

Your Work Environment

The goal of this doctoral project is to investigate extreme strain rates, analyze experimental acoustic emission (AE) signals based on wave properties using machine learning (ML), and provide insights into rapid, small-scale deformation mechanisms. To achieve this, CASCADE-RAPIDE will utilize a unique in situ setup that combines micromechanical testing and AE signal detection across a wide strain-rate range (spanning more than eight orders of magnitude). This setup operates inside a scanning electron microscope (SEM), allowing the surface and microstructure of small pillars to be observed during deformation. The collected AE data will be processed using advanced ML algorithms and human perception tests for classification. The project involves collaboration with ELTE Budapest (P. D. Ispánovity) and JUNIA Lille (A. Paté).

Summary of work:
1. Compression tests will be performed on focused ion beam (FIB)-fabricated micropillars at various strain rates, using different materials.
2. Artificial intelligence techniques will be employed to learn long-term dependencies in the time domain, incorporating information regarding the deformation.
3. Application of human perception tests to classify AE signals.

Constraints and risks

What we offer: Cutting-edge training in mechanics and materials science; a stimulating and rewarding research and teaching program; and an extensive international network comprising leading scientists in the field (in France, Switzerland, Germany, etc.). The student will have access to state-of-the-art micromechanical testing equipment (such as the Alemnis ultra-high-speed deformation system) combined with versatile characterization techniques (including in situ high-resolution EBSD and in situ acoustic emission).

Requirements:
- Master's degree (or near completion) in experimental physics or materials science
- Proficiency in the mechanics of materials and mechanical testing; experience with electron microscopy characterization is an asset
- Aptitude for programming and an interest in data science
- Good command of English (French is an asset)
- Ability to work in a team
Candidates must submit a detailed CV, a cover letter, a Master's degree certificate (or the expected date of completion), their Master's thesis (or other relevant research work such as papers, student competition entries, etc.), and the contact details of their thesis supervisor.

Compensation and benefits

Compensation

2300 € gross monthly

Annual leave and RTT

44 jours

Remote Working practice and compensation

Pratique et indemnisation du TT

Transport

Prise en charge à 75% du coût et forfait mobilité durable jusqu’à 300€

About the offer

About the CNRS

The CNRS is a major player in fundamental research on a global scale. The CNRS is the only French organization active in all scientific fields. Its unique position as a multi-specialist allows it to bring together different disciplines to address the most important challenges of the contemporary world, in connection with the actors of change.

CNRS

The research professions