The application of artificial intelligence in Webuild’s construction sites, a new frontier of innovation

The Only Limit is Imagination. The application of artificial intelligence to the construction of large-scale projects, and specifically to construction site activities, are still largely unexplored. However, ongoing innovations in experimentation promise to revolutionize the industry. The use of robotics, the connection and integration of machines, sensors, and devices on site that “communicate” with each other, predictive maintenance driven by data collection and analysis, and augmented reality for staff training are just some examples of what artificial intelligence can do and how it can help transform the construction world. Starting with safety—one of the strategic sectors where innovations can enhance productivity while also saving lives. In this regard, Webuild’s construction sites around the world represent a new frontier of artificial intelligence, where innovative solutions are tested to minimize workers’ exposure to risk.

«Globally, explains Dr. Giampiero Astuti, Head of Innovation Program Management at Webuild, there is a hierarchy of safety controls ranging from the cultural factors, so anything that is linked to human behaviors, to the technical-organizational controls, including the technological one, which aim to intervene to the source of hazard. This is where artificial intelligence comes into play.»

The application of artificial intelligence in Webuild’s construction sites is being tested precisely where the risks are highest: in the movements of large construction machinery, in workers’ behavior inside tunnels, and in the operations of TBMs, the massive tunnel boring machines that dig tunnels.

«The potential is immense, continues Astuti, and we have begun testing these new AI applications in some sites and on certain models, starting from Paris and extending to Australia».

One of the first applications of artificial intelligence was tested in the construction of the Grand Paris Express, the new metro network in Paris that will connect the towns of Île-de-France. Webuild is involved in building several sections that require underground excavations. AI was used to ensure worker safety through the installation of cameras, whose configuration varies with the track, and the setup of AI-managed software. The cameras are designed to record any potential risk situations, such as the non-use of required PPE or pedestrian corridors, or machine-human interfaces.

When the cameras detect one of these anomalies, an alarm is triggered, and the dangerous situation is photographed, generating a text message that explains the irregularities. All this information feeds into a database that grows daily, allowing the AI to improve over time. The software learns to distinguish between real and apparent risks, filtering out superfluous inputs and signaling only the actual dangers. All this occurs while protecting workers’ privacy, with their faces pixelated in camera footage to safeguard their identity.

In the Australian Snowy Mountains, Webuild is developing one of the most ambitious hydroelectric projects in the country’s history: Snowy 2.0, a pumped storage plant capable of generating clean energy and storing it, releasing it only when energy demand rises.

The construction of the plant requires tunnels running under the mountains using TBMs. An innovative AI application was tested on these TBMs, which reduces the risk associated with the transportation of concrete segments—prefabricated elements that line the inside of the tunnels—to zero. Within these mechanical TBMs, there is a 30-meter platform where the segments are moved and transported to the front of the TBM, where they are positioned to form the complete ring of the tunnel.

«This area, comments John Joseph Supple, Technical Safety Manager at Webuild, is called the feeding area, the part that supplies the TBM but also presents potential dangers in the interface between the operator and the machine moving the segments. That’s why we’ve installed AI software and systems in this area that identify these interferences and automatically stop the machine without triggering alarms».

The software, connected to a network of cameras, recognizes if a person is too close to the segment handling point and halts the machine. These images, captured by the cameras, are instantly relayed to the TBM control cabin, where they contribute to the historical data that continually enhances the AI’s performance.

Webuild is also testing new AI systems in the vast Melbourne construction site, where hundreds of workers are building the North East Link, twin three-lane tunnels stretching 6.5 kilometers to fix a missing link in the city’s traffic network.

Here, new technologies have been applied to machinery like excavators, trucks, and cement mixers. These machines are equipped with micro-cameras that function like eyes, analyzing the operational area in real-time and triggering an alarm when human presence encroaches on the machine’s range. «The software, Supple explains, has been trained to recognize human biometric parameters, teaching it what a human is.»

The driver is alerted by an acoustic and visual alarm through a display inside the cab. The detection zones can be configured and can reach 7 mt away from the vehicle and the driver alerted only if a worker is nearby.