Social Housing
Discover unique AI-powered fire risk tool FireAngel Predict®
After 10 years in development and patented in application, FireAngel Predict® runs a unique algorithm to pinpoint fire risk in our communities.
Social Housing
Introducing FireAngel Predict®, a step-change in the fire industry that protects residents, properties and communities from preventable fire risks using unrivalled insight.
Through a patented application, the AI-powered fire risk tool instantly spots trends of behaviours logged by smoke and heat alarms and highlights these properties, allowing for effective interventions.
Developed with support from the UK Fire and Rescue Service, Predict® gives visibility of previously hidden trends in social housing and domestic properties, such as alarms activating through the night, devices being removed and delays in silencing non-critical alarms, which are understood to be precursors to serious fires.
Predict® forms an integral part of FireAngel’s purpose-built solution for home safety, FireAngel Connected. With Connected, housing teams can remotely monitor safety and environmental sensors, access real-time status and compliance updates, and view instant diagnostics reports for a more efficient, intelligent way to manage properties and protect residents.
With the option to add third party Zigbee sensors to networks as needs or legislation evolves, and the ability to integrate the data and insight into existing asset management systems, Connected can fit seamlessly into your existing property management and resident safety processes.
In 2010, as an industry first, FireAngel introduced a battery powered smoke alarm with diagnostics capability which stored the last 10 device activations within its data centre. These alarms have since been regularly installed during Home Safety visits completed by Fire & Rescue Services across the country. If any of these devices were in properties where serious fires took place, they were sent to FireAngel’s head office for forensic investigation.
The data soon highlighted that in many cases there were multiple activations in the weeks or sometimes days before the larger, and in many cases fatal, fires had occurred. During these pre-cursor occurrences when a smoke or heat alarm was activated, the device would log events, including the time taken to silence alarm and the number of activations in a day, recording if a device had also been removed from its baseplate.
These indications reinforced both national statistics and anecdotal messages from Fire & Rescue services that many fires are caused by repeated behaviours. Fire Officers know the time taken to silence a sounding alarm could be longer due to reduced mobility, hoarding, or inebriation. They are also aware devices are regularly removed if residents are smokers or abuse drugs.
Fire & Rescue Services estimate that only 1 in 4 fires in the UK are known to them, so having a map of the missing fires could help prevent the 1 known fire from even occurring as an outcome of successful interventions. FireAngel created a patented application taking the data of these activations or ‘near misses’ and developed the accessible AI tool Predict®. This provides a real-time view of the active risk in a property in two simple outputs – either low risk, with no further action needed, or high risk, which requires urgent interventions to prevent the probability of a future fire.
If an alarm is sited correctly, is regularly maintained and continues to trigger Predict® alerts, by automatically highlighting potentially dangerous behaviours to social landlords it enables active resident‑centric intervention to mitigate risk.
This insight into the correlation between behaviour and increased risk is only valuable if the correct intervention is in place. As Predict® provides a real-time risk level, the success of these interventions by Fire & Rescue Services or Resident Safety Teams can be measured and monitored over time. The use of open APIs allows this data to be passed to third-party resources to complete an intervention. It can also be implemented into a current asset or resident management system that your team is already to using to support day-to-day activities and increase time efficiency.
Nick Rutter, FireAngel Co‑Founder & Chief Product Officer said: “All organisations are stretched, and systems that offer loads of data are not the answer. FireAngel’s AI-driven predictive technology gives housing associations a stratification of risks, so they know how to use their resources most effectively. Because they can pinpoint the most significant need, this technology allows them to work more cost-effectively.”
Devices that are incorrectly installed or sited in inappropriate areas can trigger multiple false alarms that result in a Predict® alert. It’s important to ensure the correct device is installed in the most appropriate place in the correct room to reduce the occurrence of unwanted alarms. View further details about best practice advice on alarm type and placement to reduce nuisance alarms in our guide.
Find out more information about FireAngel’s unique Predict® fire risk tool or explore our Connected solution.
