H. Braendle | Searcharxiv

arXiv2015

Distributed Temperature Sensing: Review of Technology and Applications

Distributed temperature sensors (DTS) measure temperatures by means of optical fibers. Those optoelectronic devices provide a continuous profile of the temperature distribution along the cable. Initiated in the 1980s, DTS systems have undergone significant improvements in the technology and the application scenario over the last decades. The main measuring principles are based on detecting the back-scattering of light, e.g., detecting via Rayleigh, Raman, Brillouin principles. The application domains span from traditional applications in the distributed temperature or strain sensing in the cables, to the latest smart grid initiative in the power systems, etc. In this paper, we present comparative reviews of the different DTS technologies, different applications, standard and upcoming, different manufacturers.

physics.ins-det↗

arXiv2015

Improved Calibration of Near-Infrared Spectra by Using Ensembles of Neural Network Models

IR or near-infrared (NIR) spectroscopy is a method used to identify a compound or to analyze the composition of a material. Calibration of NIR spectra refers to the use of the spectra as multivariate descriptors to predict concentrations of the constituents. To build a calibration model, state-of-the-art software predominantly uses linear regression techniques. For nonlinear calibration problems, neural network-based models have proved to be an interesting alternative. In this paper, we propose a novel extension of the conventional neural network-based approach, the use of an ensemble of neural network models. The individual neural networks are obtained by resampling the available training data with bootstrapping or cross-validation techniques. The results obtained for a realistic calibration example show that the ensemble-based approach produces a significantly more accurate and robust calibration model than conventional regression methods.

cs.NE↗