相关参考文献
注意：仅列出部分参考文献，下载原文获取全部文献信息。
Article
Optics
Huajian Zhong et al.
Summary: This study proposes a high-spatial-resolution optical frequency domain reflectometry method with a single interferometer, using a self-compensation technique to successfully eliminate phase noise and obtain a compensated signal with high signal-to-noise ratio. The high spatial resolution is achieved by analyzing the length of the delay fiber at different measurement distances. This method has great potential in the field of distributed measurement.
OPTICS AND LASERS IN ENGINEERING
(2023)
Article
Optics
Jacynthe Francoeur et al.
Summary: This study demonstrates the asynchronous and real-time sensing of bends with different curvatures and lengths using optical frequency domain reflectometry (OFDR) and a polymer extruded optical fiber triplet with enhanced backscattering properties. Simulations on digital phantoms show that the reconstruction accuracy is on the order of the interrogator's spatial resolution (millimeters) with sensing lengths of less than 1 m and a high SNR.
Article
Optics
Ming Wang et al.
Summary: We propose a pattern recognition strategy using LSTM and CNN, with phi-OTDR for vibration sensing and data acquisition. The LSTM-CNN trained on time domain curves, discrete wavelet transform (DWT), and short-time Fourier transform (STFT) inputs can effectively identify six target signals, aiding users in taking appropriate measures. LSTM shows significant improvement in classification performance compared to ANN and CNN, providing an application example for LSTM and optical fiber sensing integration.
Article
Optics
Mingxuan LIu et al.
Summary: An end-to-end deep learning model based on DBN and GRU is proposed for recognizing single and composite disturbance events in 9-OTDR. The model achieves high recognition accuracy (96.72% for single events and 90.94% for composite events) with short recognition time (0.079 s for single events and 0.084 s for composite events). This model is more effective in a high sensitivity, real-time 9-OTDR system.
Article
Engineering, Electrical & Electronic
Yuting Hu et al.
Summary: A method based on generative adversarial network (GAN) is proposed to reconstruct super-resolution Brillouin gain spectra (BGS) from its low-resolution counterpart, reducing acquisition time and improving measurement accuracy and resolution.
IEEE SENSORS JOURNAL
(2022)
Article
Engineering, Electrical & Electronic
Andrea Madaschi et al.
Summary: Two Neural Network-based solutions are proposed to recover the distributed temperature profile of a sensing fiber, showing a significant advantage in processing speed compared to classical fitting techniques, with slightly better accuracy in estimating temperature profiles.
IEEE SENSORS JOURNAL
(2022)
Article
Engineering, Electrical & Electronic
Hua Zheng et al.
Summary: In this paper, a scheme of deep learning enhanced long-range fast Brillouin optical time-domain analysis (BOTDA) is proposed and experimentally demonstrated. The deep learning algorithms are utilized to denoise and demodulate the volumetric data from fast BOTDA, leading to an extended sensing range of 10 km. Experimental results show that this method enables real-time vibration measurement in fast BOTDA.
JOURNAL OF LIGHTWAVE TECHNOLOGY
(2022)
Article
Engineering, Electrical & Electronic
Ahmed Sabri Kadhim Almoosa et al.
Summary: We propose using an artificial neural network (ANN) model to improve the Brillouin frequency shift (BFS) resolution of the differential cross-spectrum Brillouin optical time domain reflectometry (DCS-BOTDR) fiber sensor. The ANN model offers more flexibility in estimating BFS and significantly improves the resolution.
OPTICAL FIBER TECHNOLOGY
(2022)
Article
Optics
Chen Chen et al.
Summary: The distributed temperature profile of a hydrogen flame was experimentally demonstrated for the first time using optical frequency-domain reflectometry (OFDR). The monitoring was done through a telecom fiber inside the flame, and the highest temperature was found to be on the sides of the center flame. The uniformity of temperature was studied by varying the distance between the fiber and tube entrance, and the largest uniform region was obtained. The durability of single-mode fiber under the flame was also investigated. The findings have important implications for high-temperature measurement using telecom fiber and OFDR.
Article
Optics
Bei Chen et al.
Summary: The paper introduces a novel wavelet convolutional neural network (WNN) for temperature measurement in a Brillouin optical time domain reflectometry (BOTDR) system, which combines a one-dimensional convolutional neural network and a self-adaptive wavelet neural network. The WNN shows better robustness and flexibility compared to other techniques, providing a feasible and faster solution for temperature measurement.
Article
Optics
Youfu Geng et al.
Summary: In this paper, high spatial-resolution distributed temperature sensing is achieved based on a femtosecond laser written ultra-weak Fabry-Perot Array. The proposed ultra-weak FPA presents both higher spatial resolution and lower temperature sensing uncertainty, making it suitable for high-resolution temperature measurement of miniature devices.
Article
Optics
Manling Tian et al.
Summary: We propose a hybrid model named ATCN-SA-BiLSTM for phase sensitive optical time domain reflectometry signal recognition. The model combines channel attention based temporal convolutional network, spatial attention, and bidirectional long short-term memory network. Experimental results show that our method achieves better classification performance.
Article
Chemistry, Analytical
Zhanerke Katrenova et al.
Summary: This study presents the construction and investigation of a 2D sensing carpet based on a distributed fiber sensing technique for mapping local pressure. The results show that fully embedding the fiber inside the silicone carpet achieves the best pressure sensitivity coefficient.
Article
Optics
Yi Shi et al.
Summary: This paper presents a few-shot learning classification method based on time series transfer and CycleGAN data augmentation for Phi-OTDR system intrusion event recognition. By expanding rare samples and using data augmentation, the network training can meet the requirements, and the experimental results show that the proposed method achieves high classification accuracy even with few samples.
Article
Engineering, Electrical & Electronic
Qirui Wang et al.
Summary: This article enhances the Rayleigh backscattering profile of optical fibers using a femtosecond laser direct writing technique to improve the signal-to-noise ratio for optical frequency domain reflectometry. The enhanced backscattering signals enable effectively distributed strain measurements using a low-cost tunable laser, demonstrating potential and limitations for OFDR-based distributed fiber sensors.
IEEE SENSORS JOURNAL
(2022)
Article
Engineering, Electrical & Electronic
Sichen Li et al.
Summary: In this study, a trained convolutional neural network (CNN) based image denoising model is proposed to eliminate unwanted noises in the Phi-OTDR-based sensing system. Experimental results demonstrate that the proposed denoising scheme achieves significant improvement in signal-to-noise ratio (SNR), showing characteristics of robustness, well spatial resolution reservation, and high efficiency. The trained CNN model has great potential to be deployed on the Phi-OTDR system for real-time denoising.
IEEE SENSORS JOURNAL
(2022)
Article
Computer Science, Artificial Intelligence
Zheng Fang et al.
Summary: Effective and efficient semantic segmentation of 3D point cloud data is crucial. Existing methods have high computational costs and cannot handle large-scale point clouds in real-time. To address these issues, we propose SPVAN, a point-voxel-based network architecture that achieves a good balance between efficiency and performance.
IET COMPUTER VISION
(2022)
Article
Engineering, Electrical & Electronic
Pierre Travers et al.
Summary: This paper investigates the strain distribution in a 1 km fiber coil under a 500 Hz vibration using a phase-sensitive optical frequency domain reflectometry system. The system accurately detects the vibrations and mechanical responses of the coil packaging. A qualitative comparison is also made between experimental results and a mechanical simulation of the coil.
JOURNAL OF LIGHTWAVE TECHNOLOGY
(2022)
Article
Optics
Sheng Li et al.
Summary: In this paper, a reconstruction error model for distributed shape sensing in optical frequency domain reflectometry (OFDR) is proposed. The model is based on the Frenet-Serret frame and the error delivering theory, and it illustrates the relationship between the reconstruction error and parameters such as curvature, torsion, fiber length, and strain measurement error. The feasibility and applicability of the model are experimentally verified using an OFDR-based distributed optical fiber shape sensing system. The proposed model can predict the maximal reconstruction error when the estimated range of curvature, torsion, fiber length, and strain measurement errors are known, which is useful for judging whether the shape reconstruction error meets the requirement.
Article
Optics
Guijiang Yang et al.
Summary: A denoising and extraction convolutional neural network (DECNN) is proposed and demonstrated for simultaneous temperature and strain extraction in a BOTDA system. DECNN shows large noise tolerance and robustness over a wide range of temperature/strain and signal-to-noise ratio conditions, enabling reliable information extraction.
Article
Optics
Ming Hai Wang et al.
Summary: The AIoT technology is applied to a temperature measurement system based on BGS test setup, where the training and testing stages of the neural network are divided into different layers to improve performance and reduce network traffic. The integration of curve fitting methods and a digital resampling filter enables accurate temperature extraction from BGS signals. Experimental results demonstrate the superior performance of the proposed approach in terms of temperature extraction accuracy and data compression.
Article
Engineering, Electrical & Electronic
Yihao Shao et al.
Summary: This paper proposes a novel spatial-spectral involution MLP network (SSIN) for HSI classification, which utilizes two paths to extract different types of information, improving spatial information extraction capability and incorporating global spatial distribution information. Experimental results demonstrate that SSIN outperforms some state-of-the-art methods.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2022)
Article
Engineering, Electrical & Electronic
Yanjie Meng et al.
Summary: A method using two outer cores of multicore fiber without calibration and OFDR, as well as a complement using three outer cores of multicore fiber, were proposed for three-dimensional shape sensing. By integrating all fiber shape from all cores combinations, a higher accuracy in reconstructed shape was obtained.
JOURNAL OF LIGHTWAVE TECHNOLOGY
(2021)
Article
Engineering, Electrical & Electronic
Shuai Qu et al.
Summary: The performance of optical frequency domain reflectometry (OFDR) has been experimentally analyzed and compared with image processing methods to extend the strain measurement range up to 7000 microstrain with a 4 mm spatial resolution, overcoming limitations of traditional processing methods. Wavelet transform is discussed in detail to determine the suitable decomposition level in OFDR data processing scheme, providing a new idea to achieve wide strain measurement range in OFDR system.
JOURNAL OF LIGHTWAVE TECHNOLOGY
(2021)
Article
Engineering, Civil
Gong-Yu Hou et al.
Summary: The paper proposes a method to estimate the continuous deformation of concrete beams using distributed optical fiber monitoring technology. By training a neural network with strain and deformation distribution curves, the method shows a very close match between trained network values and actual values, with a high goodness of fit.
KSCE JOURNAL OF CIVIL ENGINEERING
(2021)
Article
Engineering, Electrical & Electronic
Zeen Chen et al.
Summary: In this study, large curvature radius shape sensing was successfully achieved using optical frequency domain reflectometry (OFDR) in multi-core fibers, reconstructing two-dimensional circle shapes with curvature radii from 5 cm to 100 cm. The accuracy of three-dimensional shape reconstruction was validated with a root-mean-square error of 7.2 mm and a mean Euclidean distance of 3.4 mm.
IEEE PHOTONICS JOURNAL
(2021)
Article
Computer Science, Information Systems
Yi Shi et al.
Summary: This paper proposes a multi-radial-distance event classification method based on deep learning, using Phi-OTDR to determine the distance of target events on sensing fiber for the first time through deep learning approach. The passband of filters is selected by searching the maximum Euclidean distance in the frequency domain, and the method shows high accuracy in classification results and identifying event type and radial distance.
Article
Computer Science, Information Systems
Changshuo Liang et al.
Summary: OFDR is a type of DOFS that has high spatial resolution and large dynamic range, making it useful in a wide range of sensing scenarios such as temperature, strain, and vibration.
Article
Engineering, Electrical & Electronic
Riccardo Veronese et al.
JOURNAL OF LIGHTWAVE TECHNOLOGY
(2020)
Article
Computer Science, Information Systems
Huijuan Wu et al.
Article
Optics
Zhiyuan Cao et al.
Article
Engineering, Electrical & Electronic
Hao Wu et al.
JOURNAL OF LIGHTWAVE TECHNOLOGY
(2019)
Article
Physics, Applied
Cong Shao et al.
APPLIED PHYSICS EXPRESS
(2019)
Article
Optics
Aidana Beisenova et al.
Article
Engineering, Multidisciplinary
Wei-Qiang Feng et al.
Article
Optics
Jianjian Wang et al.
OPTICS COMMUNICATIONS
(2019)
Article
Engineering, Electrical & Electronic
Zhiyong Zhao et al.
JOURNAL OF LIGHTWAVE TECHNOLOGY
(2018)
Article
Optics
Huan Wu et al.
