University of Electronic Science and Technology of China

Sichuan Guangsheng Iot Technology Co., Ltd.

Jiangsu Zhongtian Technology Co., Ltd.

Zhongtian Power Optical Cable Co., Ltd.

Yunjiang Rao

Zinan Wang

Yun Fu

Bing Han

Huijuan Wu

Zengling Ran

Jiaqi Li

Xiangrong Liu

Wei Jun Zhang

Ming Li

Qiang Li

Yao Xiao

Kang Li

Bo Hu

Ji Xiong

Jiping Xue

Lianlian Xie

Ya Qian

Hanyu Li

Jiping Chen

Hongjian Guan

Shuhong Xie

Han Wu

Mengjiao Wang

Bo Tang

Mingru Yang

Cangping He

Haoyu Qiu

Rui Ma

Weili Zhang

Jingfeng Long

The present invention relates to an intelligent fiber optical distributed acoustic sensing (FODAS) system and method based on an artificial intelligence (AI) chip, belonging to the field of distributed optical fiber sensing technologies. The system comprises a light source, a modulator, an optical amplifier, a sensing part, a data processor, a photoelectric detector, and an alarm unit, where the data processor is specifically an AI chip; the light source, the modulator, the optical amplifier and port a of a circulator are connected in sequence, port b of the circulator is connected to an optical fiber, port c of the circulator is connected to the photoelectric detector, an output end of a detector is connected to the data processor, an output end of the data processor is connected to the alarm unit; and the data processor receives external acoustic signals and extracts amplitude and frequency features of the external acoustic signals to identify the type. The present invention can collect the external acoustic signals and identify the signal type thereof, and has important application value in the fields of perimeter security, disaster warning, geological exploration, and the like.

Intelligent FODAS system and method based on AI chip

A 1D-CNN-based ((one-dimensional convolutional neural network)-based) distributed optical fiber sensing signal feature learning and classification method is provided, which solves a problem that an existing distributed optical fiber sensing system has poor adaptive ability to a complex and changing environment and consumes time and effort due to adoption of manually extracted distinguishable event features. The method includes steps of: segmenting time sequences of distributed optical fiber sensing acoustic and vibration signals acquired at all spatial points, and building a typical event signal dataset; constructing a 1D-CNN model, conducting iterative update training of the network through typical event signals in a training dataset to obtain optimal network parameters, and learning and extracting 1D-CNN distinguishable features of different types of events through an optimal network to obtain typical event signal feature sets; and after training different types of classifiers through the typical event signal feature sets, screening out an optimal classifier.

1D-CNN-based distributed optical fiber sensing signal feature learning and classification method

A fully distributed magnetic adsorption multi-parameter sensing cable, which is configured to be installed on the wall of a metal pipeline, includes an outer sheath, a sensing component arranged in the outer sheath, and a fully distributed magnetic adsorption reinforcement (FDMAR) arranged in the outer sheath and on a peripheral side of the sensing component. The outer sheath is attached to the wall of the metal pipeline by the FDMAR. A magnetic adsorption force between the FDMAR and the wall of the metal pipeline is able to be adjusted by changing the size of the FDMAR and the distance between the FDMAR reinforcement and the wall of the metal pipeline. The fully distributed magnetic adsorption multi-parameter sensing cable has the advantages of good adsorption effect and high sensitivity.

Fully distributed magnetic adsorption multi-parameter sensing cable

A distributed acoustic sensing (DAS) system based on space-division multiplexing with multi-core fiber (MCF) is proposed. It relates to a technical field of distributed optical fiber sensing. The present invention maintains the advantage of single-ended measurement in the standard DAS system, and realizes the intensity accumulation of the Rayleigh backscattering light within each core of the MCF, which can greatly improve the strain resolution of DAS systems. Moreover, the introduction of optical switch can make different code sequences transmit in the different core of the MCF simultaneously, which can make the single-pulse response with coding gain demodulated without sacrificing the frequency responding bandwidth. Furthermore, the utilization of space-division multiplexing can make multiple pulses with precious time delay transmit in the MCF simultaneously, which can greatly improve the frequency responding bandwidth of DAS system.

Distributed acoustic sensing system based on space-division multiplexing with multi-core fiber

A long-distance FODAS amplification system includes a distributed amplification unit, which includes a LEAF, a pump, and a WDM; wherein the pump light passes through the WDM into the LEAF, so as to realize distributed amplification. A long-distance FODAS amplification method includes steps of: 1) modulating and amplifying a light source to obtain the probe pulse light; 2) guiding the pump light and the probe pulse light into LEAF; 3) combining the probe pulse light with the pump light to perform distributed amplification, so as to generate power-raised Rayleigh backscattered light; and 4) converting and demodulating the Rayleigh backscattered light after being output through the circulator, so as to complete distributed sensing.

Long-distance fiber optic distributed acoustic sensing amplification system and method thereof

A random distributed Rayleigh feedback fiber laser based on a double-cladding weakly ytterbium-doped fiber includes: a pump laser source, a pump combiner, a cladding power stripper, and a double-cladding weakly ytterbium-doped fiber for simultaneously achieving distributed active gain and random distributed Rayleigh feedback. An output end of the pump combiner is connected with one end of the double-cladding weakly ytterbium-doped fiber, the other end of the double-cladding weakly ytterbium-doped fiber is connected with an input end of the cladding power stripper, and a concentration of ytterbium ions in the double-cladding weakly ytterbium-doped fiber is in a range of 0.5&#xd7;10to 1&#xd7;10/m. The laser provided by the present invention solves the problem that the existing random fiber lasers cannot simultaneously utilize distributed active gain and random distributed Rayleigh feedback with a single type of fiber.

Random distributed Rayleigh feedback fiber laser based on double-cladding weakly ytterbium-doped fiber

A distributed optical fiber sensing signal processing method for safety monitoring of underground pipe network, which belongs to infrastructure safety monitoring field, which is aimed to improve the intelligent ability of detection and identification of the existing distributed optical fiber sound/vibration sensing system under complex application conditions. The present invention utilizes the distributed optical fiber sound/vibration sensing system to pick up the sound or vibration signal of the whole line along the detection cable; and the customized short time feature and long time feature are respectively extracted from the relative quantity of the sound or the vibration signal at each spatial point in the whole monitoring range. The Bayesian identification and classification network at each spatial point is constructed and trained based on the prior knowledge of the collected signal features and their different background noises.

Distributed optical fiber sensing signal processing method for safety monitoring of underground pipe network

A speckle-free imaging light source based on a random fiber laser (RFL) using a strong-coupling multi-core optical fiber, relating to a field of optical fiber laser illumination light source, is provided, mainly including a pumping source and an optical fiber loop mirror, and further including the strong-coupling multi-core optical fiber with/without a single-mode optical fiber. Through directly adopting the strong-coupling multi-core optical fiber or combining the single-mode optical fiber with the strong-coupling multi-core optical fiber to serve as a main device in the RFL-based illumination light source, the generated RFL has multiple transvers modes and low spatial coherence which prevent speckle formation during illumination, which provides an ideal illumination light source for high-speed full-field speckle-free imaging technology.

Speckle-free imaging light source based on random fiber laser using strong-coupling multi-core optical fiber

A method of improving measurement speed of distributed optical fiber sensors by adopting orthogonal signals and the system thereof is disclosed, which is related to the optical fiber sensor field and solves the problems that conventional technology will increasing the bandwidth of the received signal, reducing the signal-to-noise ratio of the received signal or distortion the spatial resolution of the system. The method comprises steps of generating N periodic orthogonal optical pulse sequence; injecting the N periodic orthogonal optical pulse sequence into the optical fiber under test(); collecting the scattered light signal; demodulating the scattered light signal with the local oscillating light and then converting into digital signals; extracting the scatter information of the orthogonal optical pulses from the collected digital signals; and arranging the scattered information in order of precedence of the infusion. The measurement speed of the distributed optical fiber sensors is improved by N&#x2212;1 times.

Method of improving measurement speed of distributed optical fiber sensor by adopting orthogonal signals and system thereof

A hybrid distributed amplification method based on a random fiber laser generated within erbium fiber with low doping concentration, i.e. weak erbium-doped fiber (WEDF), which includes: Step 1. constructing a fiber link via WEDF; Step 2. generating the random fiber laser based on the fiber link, the pump source, the wavelength division multiplexer and the strong feedback module; Step 3. constructing the spatial equalized gain based on hybrid gain of the erbium fiber and random fiber laser; Step 4. the signal is amplified by the hybrid spatial equalized gain. The present invention solves the typical problem of high laser threshold and low pump conversion efficiency when conventional fiber is used to generate random fiber laser for distributed amplification.

Hybrid random fiber laser distributed amplification method based on erbium fiber with low doping concentration

A method for distributedly measuring polarization transmission matrices of an optical fiber includes steps of: inputting a fully polarized pulse into the optical fiber with linear birefringence only; and demodulating polarization states of Rayleigh backscattered light at different points on the optical fiber from a pulse input end; after demodulating, dividing the polarization states of the Rayleigh backscattered light into Q groups in sequence, wherein every three polarization states are divided into one group; calculating a transmission matrix of Group N; and solving the equation set using a numerical analysis method for obtaining multiple solutions, and screening the multiple solutions according to characteristics of the polarization transmission matrix, wherein each time of screening provides a unique solution M(N) of the equation set; continually updating Mvalues for iteration, so as to obtain the distribution of polarization transmission matrices of the optical fiber.

Method for distributedly measuring polarization transmission matrices of optical fiber and system thereof

An online traffic volume monitoring system based on a phase-sensitive optical time domain reflectometry and its monitoring method are related to a field of intelligent transportation and an application of distributed fiber sensing. A vehicle moving temporal-spatial response graph is generated by accumulating differentiated Optical Time-Domain Reflectometry tracks at different moments in one unit monitoring period for traffic volume statistics, and then converted into a vehicle moving trajectory image through binarization and image pre-processing. Parameters of the moving vehicles are detected by utilizing a search-match method. A traffic volume, moving speeds, moving directions and locations are obtained respectively from detected trajectory number, and a tilt angle and pixel positions. The monitoring method is helpful to solve traffic congestion problem and informing drivers of real-time traffic volume, and contributes to realize an intelligent city traffic regulation.

Online traffic volume monitoring system and method based on phase-sensitive optical time domain reflectometry

A long-distance polarization and phase-sensitive reflectometry based on random laser amplification for extending a sensing distance includes a long-distance polarization and phase-sensitive reflectometry of a distributed Raman amplification based on optical fiber random lasers generated by unilateral pumps, a long-distance polarization and phase-sensitive reflectometry of a distributed Raman amplification based on optical fiber random lasers generated by bilateral pumps, and a long-distance polarization and phase-sensitive reflectometry of a Raman amplification based on a combination of optical fiber random lasers generated by unilateral pumps and a common Raman pump source, which are applied in optical fiber perturbation sensing and have a capability of greatly improving a working distance of a sensing system and a high practicability.

Growing community of inventors

Sichuan, China

Yunjiang Rao