AI insights could help reduce craft injuries
Artificial intelligence (AI) research is revealing ways to reduce physical injuries and boost the productivity of skilled craft workers.
Craft labor is demanding, often requiring constant and repetitive physical motions that can lead to fatigue, wear and tear, and musculoskeletal injury. Those injuries represent billions of dollars in healthcare costs each year, and the physical toll can lead to young workers leaving the profession or experts retiring early.
While retaining and recruiting craft labor continues to be a significant issue and cost for today’s mega projects, construction continues to be one of the most dangerous industries in the United States.
Despite efforts to reduce the risk of occupational injuries and illnesses in construction, the industry continues to account for a disproportionate share of work-related injuries, illnesses and deaths. In 2016, construction workers were 7% of the U.S. workforce, but suffered 19% (991) of the nation’s 5,190 reported fatal work injuries, according to a U.S. Bureau of Labor Statistics Report released in 2017.
Data: U.S. Bureau of Labor Statistics
Meanwhile, construction labor in the U.S. Gulf Coast is expected to be in short supply and base wages rates for all trades and per diems for travelers will increase in 2018, according to Compass International.
Pipefitters, welders, electricians and instrumentation installers are in the highest demand and shortest supply right now.
Insulators, carpenters, roofers, masons and painters will also be in demand for the next six to twelve months to meet the construction repair effort from natural disaster damage.
A team of researchers at University of Waterloo in Ontario, Canada, believe that AI can help mitigate risks and retain valuable craft, not by replacing people with technology, but by training the craft to work smarter and safer.
Studies using motion sensors and AI software have revealed how construction workers use previously unidentified techniques to limit the loads on their joints, knowledge that can now be passed on to apprentices in training programs.
Dr. Carl Haas, a professor of civil and environmental engineering, is taking lessons learned from studies on bricklaying, for example, to inform a system that can give trainees immediate feedback so they can modify their movements to reduce the physical stresses of their demanding work.
Led by Haas and Eihab Abdel-Rahman, a systems design engineering professor at Waterloo, research involves the use of now-inexpensive motion sensor suits and sophisticated AI software.
A motion sensor suit in the University of Waterloo study.
Masonry and construction are demanding fields, requiring constant and repetitive motions that can lead to fatigue, wear and tear, and musculoskeletal injury.
“The people in skilled trades learn or acquire a kind of physical wisdom that they can’t even articulate,” Haas said. “It’s pretty amazing and pretty important.”
The research shows master masons don’t follow the standard ergonomic rules taught to novices. Instead, they develop their own ways of working quickly and safely.
Examples include more swinging than lifting of blocks and less bending of their backs.
“They’re basically doing the work twice as fast with half the effort – and they’re doing it with higher quality,” Haas said. “It’s really intriguing.”
In their first study, the researchers analyzed data from bricklayers of various experience levels who wore sensor suits while building a wall with concrete blocks. The data showed experts put less stress on their bodies, but were able to do much more work.
A follow-up study was done to determine how master masons work so efficiently. It involved the use of sensors to record their movements and AI computer programs to identify patterns of body positions.
The researchers now plan to do more in-depth study of how the experts move on the job.
“Skilled masons work in ways we can show are safer, but we don’t quite understand yet how they manage to do that,” said Hass, who compares their skill to a professional golf swing. “Now we need to understand the dynamics.”
Image: University of Waterloo
Sensor Suit Lessons
As part of their work, the researchers are now developing a system that uses sensor suits to give trainees immediate feedback so they can modify their movements to reduce stress on their bodies.
Musculoskeletal injuries are a significant problem in construction, causing many apprentices to drop out and many experienced workers to prematurely wear out.
“There is an unseen problem with craft workers who are just wearing out their bodies,” he said. “It’s not humane and it’s not good for our economy for skilled tradespeople to be done when they’re 50.”
Haas hopes lessons learned from the experts – in bricklaying and other construction trades as well – can be passed on during training to increase productivity and keep more skilled workers on the job longer.
Data collected from the research could also be used to justify the adoption of tools such as self-leveling palates, or block holders, that have the potential to increase productivity and reduce wear and tear on workers as well.
By Heather Doyle