A novel optical fiber displacement sensor of wider measurement range based on neural network

2006 ◽  
Author(s):  
Yuan Guo ◽  
Xue Feng Dai ◽  
Yu Tian Wang
Keyword(s):  
Neural Network ◽  
Optical Fiber ◽  
Measurement Range ◽  
Displacement Sensor

Artificial Neural Network Compensation for an Optical Fiber Micro-Displacement Sensor in Positioning System

2012 ◽  
Vol 496 ◽  
pp. 449-452 ◽  
Author(s):  
Lu Jun Cui ◽  
Hui Chao Shang ◽  
Gang Zhang ◽  
You Ping Chen ◽  
Yong Li
Keyword(s):  
Neural Network ◽  
Numerical Simulation ◽  
Artificial Neural Network ◽  
Optical Fiber ◽  
Compensation Method ◽  
Experimental Results ◽  
Displacement Sensor ◽  
Positioning System ◽  
Nonlinear Correction ◽  
Artificial Neural

The present work investigates an optical fiber micro-displacement sensor based on artificial neural network. Owing to the micro-displacement sensor was affected by the variations and noises seriously, the artificial neural network was introduced to the micro-displacement sensor as compensation method, experimental results and numerical simulation indicated that the micro-micro-displacement sensor with artificial neural network could enhance the nonlinear correction for sensor and decrease the interferences effectively. Simultaneously, by way of the contrast test of the different neural network, experimental results showed that the linearity of full scope could reach 0.2% for micro-micro-displacement sensor based on BRF network, and concluded the BRF network was more suitable for compensation of optical micro-displacement sensor.

scholarly journals In-Process Diameter Measurement Technique for Micro-Optical Fiber with Standing Wave Illumination

2021 ◽  
Author(s):  
Masaki Michihata ◽  
Zhao Zheng ◽  
Daiki Funaiwa ◽  
Sojiro Murakami ◽  
Shotaro Kadoya ◽  
...  
Keyword(s):  
Optical Fiber ◽  
Standing Wave ◽  
Dynamic Range ◽  
Scattered Light ◽  
High Dynamic Range ◽  
Measurement Range ◽  
Diameter Distribution ◽  
Process Measurement ◽  
Air Turbulence ◽  
Tapered Optical Fiber

AbstractIn this paper, we propose an in-process measurement method of the diameter of micro-optical fiber such as a tapered optical fiber. The proposed technique is based on analyzing optically scattered light generated by standing wave illumination. The proposed method is significant in that it requires an only limited measurement range and does not require a high dynamic range sensor. These properties are suitable for in-process measurement. This experiment verified that the proposed method could measure a fiber diameter as stable as ± 0.01 μm under an air turbulence environment. As a result of comparing the measured diameter distribution with those by scanning electron microscopy, it was confirmed that the proposed method has a measurement accuracy better than several hundred nanometers.

An enlarge polymer optical fiber linear-displacement sensor based on constructive interference

2021 ◽  
Vol 63 ◽  
pp. 102481
Author(s):  
Abdul Ghaffar ◽  
Mujahid Mehdi ◽  
YanYun Hu ◽  
Arnaldo G. Leal-Junior ◽  
Abdul Basit ◽  
...  
Keyword(s):  
Optical Fiber ◽  
Linear Displacement ◽  
Displacement Sensor ◽  
Polymer Optical Fiber ◽  
Constructive Interference

An Optical Fiber Sensing Network Supporting Weak Optical Signal Detection and a Neural Network Method for Information Collection

2021 ◽  
Vol 16 (2) ◽  
pp. 188-195
Author(s):  
Keyuan Liu ◽  
Haibin Li ◽  
Ya Wang
Keyword(s):  
Neural Network ◽  
Optical Fiber ◽  
Signal Detection ◽  
Mobile Phone ◽  
Optical Power ◽  
Information Collection ◽  
Identification System ◽  
Power Meter ◽  
Fiber Sensing ◽  
Optical Fiber Sensing

The weak direct current (DC) signals detected and converted by the photodetector are output to the mobile phone by voltage/frequency switching, and the signals are processed by the mobile phone APP and audio conversion module. The photodetector is equipped with the automatic switching function to design an optical power meter and detect weak signals. Meanwhile, the optical cable identification system is analyzed and combined with the optical power meter to generate an optical fiber sensing network to improve the weak alternating current (AC) signal detection. This network needs data fusion in sensor nodes’ data collection. The cluster routing protocol is introduced and combined with the back propagation neural network (BPNN) to propose a method suitable for this photoelectric transmission and improve the information fusion and accuracy. In the experiment, the optical power meter is output in gears first, and the output waveforms are normal. The photodiode’s optical power is adjusted to obtain different frequencies on the oscilloscope. In the proposed optical fiber sensing network, weak AC signals are amplified significantly, and different optical fiber lines can be distinguished in the optical cables. The proposed information collection method can reduce network communication and node energy consumption.

scholarly journals Fast Measurement of Brillouin Frequency Shift in Optical Fiber Based on a Novel Feedforward Neural Network

Photonics ◽  
2021 ◽  
Vol 8 (11) ◽  
pp. 474
Author(s):  
Fen Xiao ◽  
Mingxing Lv ◽  
Xinwan Li
Keyword(s):  
Neural Network ◽  
Optical Fiber ◽  
Frequency Shift ◽  
Brillouin Scattering ◽  
Principal Component ◽  
Feedforward Neural Network ◽  
Gain Spectrum ◽  
Fiber Sensors ◽  
Brillouin Gain ◽  
Distributed Optical Fiber

Brillouin scattering-based distributed optical fiber sensors have been successfully employed in various applications in recent decades, because of benefits such as small size, light weight, electromagnetic immunity, and continuous monitoring of temperature and strain. However, the data processing requirements for the Brillouin Gain Spectrum (BGS) restrict further improvement of monitoring performance and limit the application of real-time measurements. Studies using Feedforward Neural Network (FNN) to measure Brillouin Frequency Shift (BFS) have been performed in recent years to validate the possibility of improving measurement performance. In this work, a novel FNN that is 3 times faster than previous FNNs is proposed to improve BFS measurement performance. More specifically, after the original Brillouin Gain Spectrum (BGS) is preprocessed by Principal Component Analysis (PCA), the data are fed into the Feedforward Neural Network (FNN) to predict BFS.

Sign in / Sign up

Export Citation Format

Share Document