AI-empowered, low-cost and portable optical fiber sensor system for distributed monitoring and shape reconstruction in UAV structures
This paper presents the development and application of a low-cost distributed optical fiber sensor for the continuous monitoring of force and shape in Unmanned Aerial Vehicles (UAVs) wings. The sensor system includes nanoparticle-doped optical fibers with enhanced backscattering, which lead to higher sensitivity and spatial resolution in transmission–reflection analysis (TRA) systems. The acquired optical signals are
fed into a neural network that provides the force distribution along the wing surface area. The results indicated the feasibility of the proposed system in which the RMSEs of 0.46 N, 13.1 mm and 5.2 mm were found for the estimation of force amplitude, location in x-axis and y-axis, respectively. Then, the distributed displacement sensing for wing shape reconstruction is evaluated and demonstrated a high accuracy in the 3D
shape reconstruction with relative errors as small as 0.21%. Thus, the proposed system is a solution with the combination of low-cost, high resolution and high accuracy for the first time in aircraft monitoring distributed systems. Therefore, the proposed AI-enabled sensor system provides a low-cost distributed optical fiber sensor that can be directly integrated into the control unit of UAV due to the simplicity of the signal acquisition process.
Integrated Photonic Neural Networks for Equalizing Optical Communication Signals: A Review
The demand for high-capacity communication systems has grown exponentially in recent decades, constituting a technological field in constant change. Data transmission at high rates, reaching tens of Gb/s, and over distances that can reach hundreds of kilometers, still faces barriers to improvement, such as distortions in the transmitted signals. Such distortions include chromatic dispersion, which causes a broadening of the transmitted pulse. Therefore, the development of solutions for the adequate recovery of such signals distorted by the complex dynamics of the transmission channel currently constitutes an open problem since, despite the existence of well-known and efficient equalization techniques, these have limitations in terms of processing time, hardware complexity, and especially energy consumption. In this scenario, this paper discusses the emergence of photonic neural networks as a promising alternative for equalizing optical communication signals. Thus, this review focuses on the applications, challenges, and opportunities of implementing integrated photonic neural networks for the scenario of optical signal equalization. The main work carried out, ongoing investigations, and possibilities for new research directions are also addressed. From this review, it can be concluded that perceptron photonic neural networks perform slightly better in equalizing signals transmitted over greater distances than reservoir computing photonic neural networks, but with signals at lower data rates. It is important to emphasize that photonics research has been growing exponentially in recent years, so it is beyond the scope of this review to address all existing applications of integrated photonic neural networks.
Polymer optical fiber Bragg gratings for multiparameter analysis in UAV wings: an AI-integrated approach
This paper presents the development of a polymer optical fiber Bragg grating (POFBG)-based sensor system for measurement of vibration, force amplitude and position for fixed-wing unmanned aerial vehicle (UAV). The POFBG is positioned along the wing structure, where forces amplitude and locations resulted in spectral changes in the POFBG. Then, predefined spectral features are used as input of a Generative Adversarial Network (GAN) for data augmentation, which increased the dataset to 1000 different force amplitude and locations. The accuracy of 1.9 Hz was obtained for vibration analysis. In the force amplitude and location analysis, the feed forward neural network (FFNN) resulted in relative errors of 3.30% and 3.51% for force amplitude and position, such errors are related to root mean squared errors (RMSE) and standard deviations of 0.33 N±0.05 N and 35.18 mm±2.3 mm for force amplitude and location, respectively. If the number of input features is reduced to only 3 predefined spectral features the RMSE without GAN increases to 1.23 N ± 0.15 N and 75.34 mm ± 9.20 mm for force amplitude and position, respectively. The FFNN with data augmentation resulted in relative errors of 7.8% for force amplitude and 2.4% for force location (RMSE of 0.78 N±0.10 N and 24.90 mm±2.1 mm, respectively), using 3 input features. The data augmentation resulted in accuracy increase with almost twofold reduction in the RMSE for the force amplitude and more than 3 times reduction of the RMSE for position estimation. Therefore, the POFBG sensor is a feasible option for shape reconstruction in UAV structures.
The Role of Photonics in Neuromorphic Computing for Augmenting the von Neumann Paradigm
The rapid expansion of Big Data and Artificial Intelligence has exposed fundamental inefficiencies in conventional von Neumann computing architectures, thus necessitating a search for alternative solutions. Neuromorphic computing, inspired by biological neural systems, has emerged as a promising route toward faster and more energy-efficient information processing approaches. Optical neuromorphic computing exploits light as a signal modality for stimulation, data delivery, information processing, and signal readout, offering intrinsic advantages in speed, parallelism, and power consumption. This review outlines the core principles of neuromorphic computing and examines recent advances in its optical implementations, with a particular focus on optical artificial synapses, photonic layers integrated into hybrid photonic-digital architectures, and optical neural networks. These emerging approaches define a coherent framework for advancing computing systems that offer clear advantages over purely von Neumann systems.
Tunable multicomponent emission from carbon nanomaterials for neuromorphic optical synaptic functions
Multi-component luminescent materials provide an effective route to engineer complex optical responses and temporal emission dynamics for neuromorphic photonics. In this work, we present a neuromorphic photonic layer based on a multi-component carbon-based nanomaterial (THR@BA) composed of a rigid boron oxide matrix derived from the calcination of boric acid (BA), which embeds three organic molecules, terephthalic acid (TPA), 1-hydroxy-2-naphthoic acid (HNA) and rhodamine B (RhB), forming a confined host-guest system with enhanced intermolecular interactions. The rigid matrix promotes energy transfer and excited-state coupling between the molecular components. The multi-component nanomaterial exhibits dual emission of fluorescence and long-lived phosphorescence and simultaneously provides complex responses upon multi-wavelength excitation. These responses result from the superposition of the optical properties of each single-component nanomaterial functionalized with the respective organic molecule, namely TPA@BA, HNA@BA, and RhB@BA. By tuning the excitation parameters, THR@BA reproduces key synaptic functions, including short- and long-term memory as well as potentiation involved in synaptic plasticity, deriving from the dynamic balance between fluorescence and phosphorescence emission with lifetimes ranging from nanoseconds to seconds. This work demonstrates that multi-component molecular systems confined within simple inorganic matrices can serve as versatile platforms for engineering programmable luminescence dynamics, making them ideal candidates for artificial optical synapses and neuromorphic computing.