Researchers have developed a new machine-learning technique that applies the Goldilocks principle to road compaction quality.
Researchers have developed new “intelligent compaction” technology, which integrates into a road roller and can assess in real-time the quality of road base compaction. Improved road construction can reduce potholes and maintenance costs, and lead to safer, more resilient roads.
Months of heavy rain and floods (see our story about subsurface importance on roads here) have highlighted the importance of road quality, with poor construction leading to potholes and road subsidence. This not only causes tyre blowouts and structural damage to cars and trucks, but also increases the chance of serious accidents.
The innovative machine-learning technique, which processes data from a sensor attached to a construction roller, was developed by a research team from the University of Technology Sydney. The study was led by Associate Professor Behzad Fatahi, head of geotechnical and transport engineering, together with Professor Hadi Kahbbaz, Dr Di Wu and PhD student Zhengheng Xu.
“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 Associate Professor Fatahi.
For the non-Geotechs reading, roads are made up of three or more layers, which are rolled and compacted. The subgrade layer is usually soil, followed by natural materials such as crushed rock, and then asphalt or concrete on top. The variable nature of soil and moisture conditions can result in under or over-compacted material.