Multimodal anomaly detection in an industrial planer

Description

We are seeking a curious, self-driven, and motivated individual to pursue a master's degree in computer science as part of an applied research project in collaboration with Bois Daaquam, a major player in the lumber industry. This unique opportunity offers a multidisciplinary environment involving professors in computer science, business administration, and forestry. The goal is to develop deep learning models for anomaly detection using real-world data from various sensors (microphones, accelerometers, acoustic emission), transforming industrial machines into intelligent systems capable of identifying signs of malfunction or wear. The candidate will explore and structure a multi-sensor dataset collected in an industrial setting, design and adapt models to different operational contexts (ambient noise, machine types), and deploy prototypes to support operator decision-making.

The project will be based primarily at Université Laval within the Lab-Usine, with regular collaboration with Bois Daaquam and on-site validation in real conditions.

Research Field

- Machine learning
- Anomaly detection
- Predictive maintenance

Research Supervisors

Anthony Deschênes
Rémi Georges

Research Environment

Lab-Usine

Web Site

Financial Aid Available by Program of Study

Master's Degree in Computer Science with thesis

Program description

Financial Aid Available*

Financial Aid Related to Research Project

$25000 per year for 2 years.

Program-Specific Financial Aid

Graduate Studies Awards

Université Laval: Student Financial Aid

Sources de financement	Montant
Leadership and Comittment Scholarship (Canadians & permanent residents)	$10,000
Citizens of the World Scholarship (International students)	$20,000
Mobility Grant for Out-of-Province Internships or Research Visits (in French)	$1,500 to $3,000
Graduate Scholarships from Granting Agencies	$20,000 to $27,000
Online Directory of Graduate Scholarships (in French)	$500 to $50,000

_{* Amounts shown represent maximum financial aid available. Certain conditions apply. Subject to change without prior notice. For further information, contact sponsoring organizations directly.}

Desired Profile

- Forestry
- Computer Software
- Mathematics, Statistics and Actuarial Science
- Wood Engineering
- Computer Engineering
- Software Engineering
- Data science
- Statistic
- Artificial intelligence

Requirements and Conditions

- Strong programming skills in Python and experience in deep learning are required, with PyTorch knowledge considered a significant asset.
- Additional strengths include experience in signal processing or time series analysis, interest in industrial environments and embedded systems, and the ability to work with imperfect, noisy data.

Required Documentation

- Cover letter
- Curriculum vitæ
- Student transcript

Find Out More

Anthony Deschênes
Département d'informatique et de génie logiciel
anthony.deschenes@ift.ulaval.ca