In a recent study published in Engineering Structures, a team of researchers from the University of Technology Sydney have developed a novel machine-learning technique to better evaluate road conditions. This study holds the potential for better road construction and maintenance, along with reduced maintenance costs and fewer accidents.
"We have developed an advanced computer model that incorporates machine-learning and big data from construction sites to predict the stiffness of compacted soil with a high degree of accuracy in a fraction of second, so roller operators can make adjustments," said Dr. Behzad Fatahi who is the head of geotechnical and transport engineering at the University of Technology Sydney, and a co-author on the study.
For the study, the researchers utilized the Goldilocks principle to determine the appropriate amount of compaction for roads to maintain their structural integrity, which consists of several layers made of up soil, crushed rock, and asphalt and/or concrete to finish it off. However, sometimes the proper combination doesn’t always lead to structurally-sound roads.
"Like Goldilocks, the compaction needs to be 'just right' to provide the correct structural integrity and strength. Over-compaction can break down the material and change its composition, and under-compaction can lead to uneven settlement," said Dr. Fatahi. "A well-compacted multi-layer road base provides a stable foundation and increases the capacity of a road to bear heavy loads. Trucks can weigh up to 40 tons, so a poor-quality base can quickly lead to cracks and weak spots in the asphalt surface."
The next phase for the researchers is to measure both the moisture content and density of the compaction in real-time during the construction phase.
Sources: Engineering Structures
As always, keep doing science & keep looking up!
