LOS ANGELES - s4story -- A team of researchers at the University of California, Los Angeles (UCLA) has introduced a novel framework for monitoring structural vibrations using diffractive optical processors. This new technology uses artificial intelligence to co-optimize a passive diffractive layer and a shallow neural network, allowing the system to encode time-varying mechanical vibrations into distinct spatio-temporal optical patterns.

Structural Health Monitoring (SHM) systems are vital for assessing the condition of civil infrastructure, such as buildings and bridges, particularly after exposure to natural hazards like earthquakes. Traditional vibration-based methods rely on sensor networks of accelerometers and strain gauges, which demand significant power, generate large datasets requiring complex digital signal processing, and can be expensive to install and maintain. Furthermore, achieving high spatial resolution for accurate damage localization often requires a costly, dense sensor deployment.

More on S For Story

• The First Great War Story Returns
• Limited Founder Editions of "Starfighters Defending Earth" Starts March 16th
• Lady D Releases Chiseled by Choices: Reflections on Empowerment, Growth, and Healing
• Hypnotherapy Finder Announces Official US Wide Launch After Successful Soft Launch
• Ayahuasca: The Mother Of All The Plants And The Voice Of Pachamama is now available for pre-order!

The new research, led by Professor Aydogan Ozcan of the UCLA Electrical and Computer Engineering Department, overcomes these challenges using a physical-digital co-integration. Instead of relying on traditional sensor networks that digitize raw physical signals, the new system uses a passive, optimized diffractive layer attached to the target structure. As the structure oscillates, this optimized diffractive surface moves, modulating an incoming illuminating wave to encode the structural displacements into light, which is then captured by a few optical detectors and rapidly decoded by a low-power neural network.

This approach marks a fundamental departure from conventional digital sensing paradigms by shifting a portion of the computational burden into the physical domain.

In collaboration with Professor Ertugrul Taciroglu's lab at UCLA's Civil and Environmental Engineering Department and Dr. Farid Ghahari of the California Geological Survey, Ozcan's team demonstrated the power of their platform through experimental validations using millimeter-wave illumination on a laboratory-scale building model with a programmable shake table. They successfully extracted 1D and 2D vibration spectra under various dynamic excitations, including seismic waveforms from an earthquake dataset. Additionally, they showcased a wavelength-multiplexed diffractive system capable of simultaneously monitoring multi-point structural vibrations using light sources with distinct wavelengths.

More on S For Story

• Melzi Job Coach Launches on iOS and Android: A Privacy-First AI Career Engine Built for Execution
• Children's Book Grayson, Come Back! Teaches Emotional Regulation Skills at School
• Technology Leader and Army Veteran Releases Memoir on Late Autism Diagnosis
• Northwest GA Author Jessica W. Bowman Turns Personal Loss Into Books Helping Readers Navigate Li
• MWA Prince George's County Hosts "From Shy to Sold" with Publishing Consultant Ally Machate

One of the significant advantages of this technology is its scalability and energy efficiency. The diffractive surface functions as a completely passive encoder and consumes no energy during its operation. Furthermore, a design optimized for millimeter waves can be physically scaled to operate in other parts of the electromagnetic spectrum, such as the visible or infrared, by adjusting the dimensions of the diffractive features in proportion to the illumination wavelength.

This research was conducted by an interdisciplinary team from UCLA's Electrical and Computer Engineering Department, California NanoSystems Institute (CNSI), Civil and Environmental Engineering Department, and the California Geological Survey.

Publication: https://doi.org/10.1126/sciadv.aea1712