This letter presents a novel learning-based method called extreme learning machine (ELM) to solve the Bragg wavelength detection problem in the fiber Bragg grating (FBG) sensor network. Based on building up a regression model, the proposed approach is divided into two phases: 1) offline training phase and 2) online detection phase. Due to the good generalization capability of ELM, the well-trained detection model can directly and accurately determine the Bragg wavelengths of the sensors even when the spectra of FBGs are completely overlapped. The results demonstrate that the proposed method is efficient and stable. It has shown competitive advantages in terms of the detection accuracy, the offline training speed, as well as the real-time detection efficiency.Index Terms-Fiber Bragg grating (FBG), fiber-optic sensors, wavelength division multiplexing (WDM), extreme learning machine (ELM).
A wavelength detection method for a wavelength division multiplexing (WDM) FBG sensor network is proposed based on least squares support vector regression (LS-SVR). As a kind of promising machine learning technique, LS-SVR is employed to approximate the inverse function of the reflection spectrum. The LS-SVR detection model is established from the training samples, and then the Bragg wavelength of each FBG can be directly identified by inputting the measured spectrum into the well-trained model. We also discuss the impact of the sample size and the pre-process of the input spectrum on the performance of the training effectiveness. The results demonstrate that our approach is effective in improving the accuracy for sensor networks with a large number of FBGs.
The structures and surface adsorption sites of Pd-Ir nanoalloys are crucial to the understanding of their catalytic performance because they can affect the activity and selectivity of nanocatalysts. In this article, density functional theory (DFT) calculations are performed on bare Pd-Ir nanoalloys to systematically explore their stability and chemical ordering properties, before studying the adsorption of CO on the nanoalloys. First, the structural stability of 38-atom and 79-atom truncated octahedral (TO) Pd-Ir nanoalloys are investigated. Then the adsorption properties and preferred adsorption sites of CO on 38-atom Pd-Ir nanoalloys are considered. The PdIr structure, which has the lowest energy of all the considered isomers, exhibits the highest structural stability, while the PdIr configuration is the least stable. In addition, the adsorption strength of CO on Ir atoms is found to be greater than on Pd for Pd-Ir nanoclusters. The preferred adsorption sites of CO on pure Pd and Ir clusters are in agreement with calculations and experiments on extended Pd and Ir surfaces. In addition, d-band center and charge effects on CO adsorption strength on Pd-Ir nanoalloys are analyzed by comparison with pure clusters. The study provides a valuable theoretical insight into catalytically active Pd-Ir nanoalloys.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.