Engineers at UNSW Sydney have developed a new fire detection system that monitors changes to Wi-Fi signals as they pass through the air to identify environmental changes when a fire is present. Their solution is purported to be more accurate than existing detection systems, which are primarily based on thermal imaging and can produce false alarms triggered by hot objects like radiators or faulty exhaust pipes. The system uses a series of low-cost Wi-Fi transmitters and receivers, driven by the Raspberry Pi and installed in a waterproof enclosure, which is deployed along the roadway to detect the change in signals caused by fire and smoke.
The system uses a series of transmitters and receivers placed at locations within an environment, such as traffic tunnels, hallways and other enclosed areas, and monitors the Wi-Fi signals as they pass through the air. When the air temperature changes, so does its density, which alters the signal's signature between the transmitter and receiver. AI is employed to monitor those changes, report any unusual activity associated with fire, and activate overhead sprinklers and other fire-retardant systems to gain control.
The Wi-Fi system is much cheaper than traditional camera-based systems and easier to install and maintain. "Existing specialized fire detection cameras can cost around $10,000 to buy, whereas our transmitters and receivers are $100 or even less," explains professor Aruna Seneviratne. "The other thing with cameras is that they need to be carefully maintained. The lenses need to be kept clean, and they often need to be properly aligned. With our system, the transmitters and receivers are just sending out a radio signal, and there is very little maintenance required. Therefore, there is also a much lower cost to operating the system."