Description

Today’s firefighting and emergency response system, mainly, relies on fire-fighters’ experience and intuition. In some cases, this human dependent approach results in catastrophic tragedies[1-4]. Even though firefighting technologies have drastically improved in last 100 years, there is almost no technology sufficiently developed to contribute to a firefighter’s decision making and forecasting capabilities. Current forecasting technologies use various sensing devices, including smoke alarms, CCTV cameras, temperature sensors, etc., as a data source for prediction models[4-9]. However, these devices are very expensive, battery dependent, and they cannot be installed everywhere[10-11]. For this reason, they are always placed at designated areas, which makes them only capable to provide information from a limited space and ranges. They cannot deliver the whole picture and almost always fail on erratic and not isolated events. We have designed zero-power nanostructured flexible antennas (ZNFA). These antennas are printable, tape like, simple, smart antennas with a very high temperature resistance. They can transmit data entirely on their own, without needing any power source or requiring any electronics. They simply absorb and reflect ambient wireless signals to produce a 0 or a 1 when they are stimulated by heat, vibration, or stretching. These signals can be picked up by any ambient wireless receiver, i.e Smartphone, Bluetooth, Wi-Fi receiver, etc., and used as an input for artificial intelligence (AI) platforms. These antennas can be produced for less than a dollar and can be placed anywhere that a wireless signal reaches, even in closed spaces. This antennas are printable antennas that can easily be printed by an inject printing system. The technology uses a revolutionary slurry material, that is constructed by a propriety combination of various nano-fillers, such as carbon nanotubes, quantum dots, other nanoparticles, etc. These nanostructured antenna geometries are carefully designed to absorb and reflect ambient wireless signals by two local phases of conductivity, low and high. For example, when these antennas are in a normal operating stage, low conductive mode, they provide weak signal that can be indexed as “0” by AI. But when they are at an irregular stage, i.e. heat presented or antenna stretched, they transmit a strong signal that can be indexed as “1” by AI. Training and implementation of AI algorithms to manage these novel antenna inputs helps to enable a rich ecosystem of talking components which can be used to form small local brains almost everywhere. Thus, a reliable sensor network for real-time fire monitoring, firefighter decision support system, and prediction can be immediately established. With the help of this elaborate sensor network, firefighters can easily access more information to double check their intuition and determine various key parameters, such as “how fires will spread?”, “who is in the building?”, “where is the origin of the fire?”, “which fire extinguisher or springer system can automatically be activated to contain fire?”, “where is the best place that a firefighter should enter the area?”, etc. This approach is extremely unique and innovative in many ways that have never been acknowledged before. It will greatly help firefighters to tackle the fire more systematically, considering all the options, unnecessary risks, expenses, and damages, in a glance. This technology will encourage a new way of thinking and will also produce a great impact on sensors and data collection.

References

1. Cooter, Roger, and Bill Luckin, eds. Accidents in history: injuries, fatalities and social relations. Vol. 41. Rodopi, 1997. 2. Weiger, Pamela R., and John Nicholson. "Learning from 9-11." NFPA JOURNAL (2002): 100-105. 3. Dyrks, Tobias, et al. "Designing for firefighters—building empathy through live action role-playing." International Conference on Information Systems for Crisis Response and Management. 2009. 4. Cowlard, Adam, et al. "Sensor assisted fire fighting." Fire Technology 46.3 (2010): 719-741. 5. Han, Liangxiu, et al. "FireGrid: An e-infrastructure for next-generation emergency response support." Journal of Parallel and Distributed Computing 70.11 (2010): 1128-1141. 6. Kumar, Vijay, Daniela Rus, and Sanjiv Singh. "Robot and sensor networks for first responders." (2005). 7. Koo, Sung-Han, Jeremy Fraser-Mitchell, and Stephen Welch. "Sensor steered fire simulation." Fire Safety Journal 45.3 (2010): 193-205. 8. Beji, Tarek, et al. "On the use of real-time video to forecast fire growth in enclosures." Fire Technology 50.4 (2014): 1021-1040. 9. Dyrks, Tobias, et al. "Designing for firefighters—building empathy through live action role-playing." International Conference on Information Systems for Crisis Response and Management. 2009. 10. Repenning, Nelson P. "Understanding fire fighting in new product development⋆." Journal of Product Innovation Management: AN INTERNATIONAL PUBLICATION OF THE PRODUCT DEVELOPMENT & MANAGEMENT ASSOCIATION 18.5 (2001): 285-300. 11. Fixr, “ Fire protection cost”, (2016), Retrived from https://www.fixr.com/costs/fire-protection

Attachments