Wildfires could be detected using 3D printing and machine learning – 3DPrint.com

Wildfires in the United States are becoming more frequent, with several experts indicating that climate change is the main reason. Last year in the United States there were 58,985 wildfires that burned more than 7.1 million acres. Over the past decade, wildfires have destroyed more than 82.3 million acres across the country (that’s about the size of Montana and nearly 4% of the country’s total size). Additionally, according to the National Interagency Fire Center, in the first two months of 2022, the number of wildfires and acres burned were above the 10-year average. As wildfires escalate, new technological resources can help suppress them or even control small fires to keep them from turning into a huge, out-of-control wildfire like the rapid fires in Dixie last year in California, which consumed 963,309 acres.

To help detect wildfires early, a team of 3D printing technicians from nonprofit education provider New Collar Network received an International Hardware Grant for Audio Innovations from Knowles Corporation (NYSE: KN) , a manufacturer of advanced micro-acoustic microphones. and speakers. The winning idea is an audio monitoring-enabled sensor encased in a 3D-printed enclosure that will use machine learning (ML) to distinguish between random forest sounds and the sound of a fire reigniting to notify authorities of a potential fire.

New Collar Network Knowles AISonic Hardware Grant winning team at the 3D Printing Lab: Filip Perez, Jed Beddo and Alec Kerr. Image courtesy of New Collar Network.

Using Knowles’ advanced hardware, the device can identify fire ignition and re-ignition, as well as arcing from power lines to indicate a possible fire hazard. Additionally, any device can relay a signal to other devices, such as field cameras, to provide immediate wildfire awareness to forest service firefighters.

To demonstrate a proof of concept and prototype of a forest fire early warning system, the team will use the winning prize, Knowles’ AISonic IA8201 Raspberry Pi development kit. This all-in-one package brings voice processing, audio edge, and ML listening capabilities to devices and systems for a range of new applications. Launched in September 2021, the latest development kit brings together all the hardware, complementary open source software and algorithms needed to test, prototype and debug voice and audio functionality and integration into new applications for the smart home, large technology public, industry and beyond.

Knowles designed this new kit to be the easiest and fastest way for product designers to prototype new innovations to address emerging use cases, including contextual voice, ML listening, and audio processing. in real time that requires flexible development tools to speed up the design process. development costs and take advantage of new technological advances.

Since the Knowles development kit has a small footprint, the team said it could be easily turned into a product to guard against wildfires. Additionally, they decided to 3D print a case for the device with a strap for easy attachment to a tree trunk. Alternatively, they could 3D print other enclosures, such as one with a magnet that would be useful on metal surfaces. Finally, as a complement, the team hopes to make the “always-on sensor units of the IA8201” solar-powered.

Rendering of the New Collar Network Wildfire Early Warning Sensor. Image courtesy of New Collar Network.

The team includes Filip Perez, Jed Beddo and Alec Kerr. All three are currently registered with the U.S. Department of Labor and are working in a 3D printing apprenticeship program for New Collar Network’s sister company, Fab Lab Hub, an America Makes member and hands-on digital fabrication skills training center. . According to the trio, the goal is to have a small product footprint to maintain “the nature of a beautiful forest but still noticeable for forestry staff to maintain the product”.

“We first start with emergency personnel or park rangers to prove how well the product and material would perform in outdoor conditions. Eventually, there would be a civilian version for people who live in arid, fire-prone regions; and a camp version so campers always know where the nearest wildfire is relative to their site, for advance warning or even to monitor the campsite,” the winners revealed.

Early warning projects like this could save more acres of forest land and provide more opportunities for safer exit from communities as well as reduce response times for firefighters with more precise location details. Additionally, as more people choose a career in 3D printing and are encouraged by non-profits to learn the craft, many more initiatives will be available sooner, moving from prototype more quickly. to production.

The New Collar Network team is one of five recipients of the Knowles International AI Sonic Hardware Grant for Audio Innovations. From the sheer number of high-quality submissions around the world, the judges chose a handful of innovative projects, like a group from Malawi that wants to build small, low-cost wind turbines using locally available materials or a Spanish team that hopes to solve sleep apnea. .

Sherry J. Basler