Converge launches AI machine learning program for concrete strength prediction
Converge has built the world’s first artificial intelligence (AI) concrete strength prediction engine. This was made possible by Converge’s unique access to a huge concrete performance data set, paving the way for the first commercial application of Machine Learning to monitor and predict material performance in a live project.
The strength prediction engine was developed in collaboration with BAM Nuttall, using funding from an Innovate UK grant awarded in 2018, and is already being utilised on BAM Nuttall’s London City Airport expansion project. Head of Innovation at BAM Nuttall, Colin Evison, says: “This advancement in construction technology is a game changer. The Converge prediction engine gives us insight into material performance we didn’t think possible. We are delighted to be Converge’s industry partner in bringing this exciting new tool to market.”
Since its inception in 2014, Converge has enabled leading construction companies to drive efficiencies onsite and shorten concrete cycles with real-time strength data. Whilst the alerts and live data generated by the Converge system bring significant project management benefits, an extensive customer survey revealed that resultant actions often weren’t happening until many hours after critical strengths were reached. Converge Product Lead, Sam Ellenby, says: “Our users were waiting for concrete to hit a critical strength before scheduling the next activity, but this often meant that the site teams needed to strike formwork or tension the slab were deployed in other areas when the time came to act. Thus, critical actions were frequently delayed.”
While such delays are small, when accumulated across hundreds of cycles they result in weeks of lost potential progress. When concrete sits on the critical path, the costs associated with these time lags costs the industry millions of pounds every year.
To combat this inefficiency, Converge used the Innovate UK grant to develop the industry’s first and most advanced AI strength prediction engine. Within hours of concrete being poured, Converge can predict the time a critical strength will be reached, several days in advance, by applying the latest in machine learning techniques.
The predictions engine combines local weather data, a database of historical concrete curing data, and the Converge concrete monitoring platform’s real-time measurements from the pour. This gives Converge the unique ability to predict the time the concrete will reach strength with an accuracy of +/- 5%, several days in advance.
The result of this immense predictive power is that teams can plan to act precisely when needed. This improved productivity keeps projects on track and, ultimately, can save millions of pounds.
Converge and BAM Nuttall are excited by the results at London City Airport and are securing other opportunities to use this technology on live projects. Of course, this is only the first of numerous cutting-edge capabilities that the Innovation UK grant has allowed Converge and BAM Nuttall to deliver. We look forward to building the future together. Watch this space.