Bridging the skills gap with AI on the factory floor

The challenge 

Bois Daaquam is an integrated forestry company and a leading player in Quebec’s lumber industry. Like many manufacturers, it faces a dual challenge: a shortage of skilled workers and the need to train new operators quickly while maintaining production quality. 

At the heart of its operations is the industrial planer, which is essential for finishing 2x3s, 2x4s and other lumber. When a problem occurs, such as a jam, an irregular board or a worn component, the operator typically has to stop the machine and intervene manually. This process is costly in terms of both time and resources, and does not meet the demands of modern production. Bois Daaquam wanted to automate anomaly detection in a non-invasive way, without interrupting operations, while also creating a training aid for new workers. 

The goal was to reduce reliance on experienced operators, many of whom are approaching retirement age, by simplifying onboarding for new hires and automating certain responses to anomalies, such as clearing jams. 

The solution 

Emmanuel Kona spent much of his Mitacs internship collecting and analyzing data on the shop floor at Bois Daaquam. Over several site visits, he installed sensing equipment, including microphones, accelerometers and acoustic emission sensors, on and around the planer. He then recorded the sounds produced by the machine during operation. 

This was followed by a rigorous data labeling process in which each audio segment was matched with the events that occurred during the recording, with jams being the most frequently observed anomaly. This step, which is often underestimated, proved critical to the quality of the resulting models. 

Using this well-structured dataset, Emmanuel developed machine learning models capable of automatically predicting whether an audio segment was normal or abnormal by drawing on signals from all three sensor types simultaneously. The aim was to detect machine problems in real time without stopping production. 

The internship was carried out through the Mitacs program, which is supported by Quebec’s ministère de l’Économie, de l’Innovation et de l’Énergie. 

The results: A tangible contribution to manufacturing 

Through his internship, Emmanuel enabled Bois Daaquam to: 

• Lay the groundwork for predictive maintenance: The models developed can detect anomalies without stopping the machine, helping to reduce unplanned downtime. 

• Support the training of new operators: By automatically detecting and responding to anomalies, for example by raising the rollers, reversing the bottom rollers to eject a jammed board and then resuming operations, the solution reduces reliance on experienced operators and streamlines onboarding for new hires. 

• Strengthen university-industry ties: The knowledge transfer that took place during the internship led to the acquisition of an accelerometer, which is now permanently installed on Bois Daaquam’s planer, a first for the company. 

• Produce publication-worthy results: A scientific article based on Emmanuel’s work is being finalized and will be submitted later this summer, a remarkable achievement for an undergraduate internship. 

Bois Daaquam now has a solid foundation on which to build a doctoral research project, with the potential to transform its operational practices over the long term. 

“By automating anomaly detection on an industrial planer, this project directly addresses the shortage of skilled labor and offers a solution developed with the help of a Mitacs intern, resulting in real productivity gains at Bois Daaquam.” 

Anthony Deschênes, Ph. D., Assistant Professor, Department of Computer Science and Software Engineering, Université Laval 

From theory to practice: A close connection to university training 

Emmanuel, who was a software engineering student at Université Laval at the time of the internship, had no prior research experience when he took on this project at Bois Daaquam. During the internship, he gained experience in every stage of a complete machine learning project, from field data collection and labeling to model training, results analysis and scientific writing. 

“This internship was a genuine learning experience for me academically, professionally and personally.It gave me an incredible opportunity to apply my knowledge to a real industrial problem.My sincere thanks to Bois Daaquam, Mitacs, MEIE and Université Laval for making this experience possible.” 

Emmanuel Kona, Computer Engineering student, Université Laval

This remarkable progression clearly illustrates how work-integrated learning can accelerate skill development far beyond what classroom learning alone can offer.  

About Mitacs

For over 25 years, Mitacs has helped grow the economy and develop the workforce of tomorrow, connecting industry with academia and global partners to solve real-world challenges. We support business-academic research collaboration through internships, co-funded with businesses, for undergraduate to graduate students and post-doctoral fellows.

As a national innovation connector, Mitacs takes a talent-first approach to strengthen innovation capacity and drive global competitiveness. We serve as an essential research-commercialization bridge, accelerating market entry and growth for new products and services.

This is a critical time for Canada to think big and take bold action. Mitacs is ready to help build a strong and resilient Canadian economy, powered by ideas, talent and innovation.

Mitacs is funded by the Government of Canada, the Government of Alberta, the Government of British Columbia, Research Manitoba, the Government of New Brunswick, the Government of Newfoundland and Labrador, the Government of Nova Scotia, the Government of Ontario, Innovation PEI, the Government of Quebec, the Government of Saskatchewan, and the Government of Yukon.