Using a Machine Learning Algorithm Integrated with Data De-Noising Techniques to Optimize the Multipoint Sensor Network

Abstract

In this paper, for an intensity wavelength division multiplexing (IWDM)-based multipoint fiber Bragg grating (FBG) sensor network, an effective strain sensing signal measurement method, called a long short-term memory (LSTM) machine learning algorithm, integrated with data de-noising techniques is proposed. These are considered extremely accurate for the prediction of very complex problems. Four ports of an optical coupler with distinct output power ratios of 70%, 60%, 40%, and 30% have been used in the proposed distributed IWDM-based FBG sensor network to connect a number of FBG sensors for strain sensing. In an IWDM-based FBG sensor network, distinct power ratios of coupler ports can contain distinct powers or intensities. However, unstable output power in the sensor system due to random noise, harsh environments, aging of the equipment, or other environmental factors can introduce fluctuations and noise to the spectra of the FBGs, which makes it hard to distinguish the sensing signals of FBGs from the noise signals. As a result, noise reduction and signal processing methods play a significant role in enhancing the capability of strain sensing. Thus, to reduce the noise, to improve the signal-to-noise ratio, and to accurately measure the sensing signal of FBGs, we proposed a long short-term memory (LSTM) deep learning algorithm integrated with discrete waveform transform (DWT) data smoother (de-noising) techniques. The DWT data de-noising methods are important techniques for analyzing and de-noising the sensor signals, and it further improves the strain sensing signal measurement accuracy of the LSTM model. Thus, after de-noising the sensor data, these data are fed into the LSTM model to measure the sensing signal of each FBG. The experimental results prove that the integration of LSTM with the DWT data de-noising technique achieved better sensing signal measurement accuracy, even in noisy data or environments. Therefore, the proposed IWDM-based FBG sensor network can accurately sense the signal of strain, even in bad or noisy environments; can increase the number of FBG sensors multiplexed in the sensor system; and can enhance the capacity of the sensor system.

Simultaneous Temperature Estimation of Multiple Gratings Using a Multi-Layer Neural Network

“…But this method focusses on accuracy instead of speed, is only tested on four FBGs, and for optical spectrum analyzer (OSA) measurements. The method's error is given as a maximum absolute error (MAE) of 0.03-0.07 • C. Another method described in [12] focusses on solving the problem of spectrally overlapping FBGs with good accuracy (RMSE of 0.0095 • C) but with a processing time of 0.132 s/FBG. This method is also only tested on four FBGs and for OSA measurements.…”

Design Reliable Bus Structure Distributed Fiber Bragg Grating Sensor Network Using Gated Recurrent Unit Network

“…Recently, to resolve the problems of WDM and TDM, researchers have proposed intensity wavelength division multiplexing (IWDM) techniques. IWDM is used to increase the number of multiplexed FBG sensors, and it has a low-complexity advantage [ 3 , 15 , 16 , 17 , 18 ]. Several network topologies, such as tree, ring, mesh, star, and bus topologies, have been proposed in the FBG sensor network area [ 3 , 12 , 13 , 17 ] to implement different multiplexing techniques.…”

“…The IWDM approach allows the adjacent FBG reflection spectrum to overlap and crossover to each other without their identification being lost [ 3 , 15 , 16 , 17 , 18 ]. This realized that IWDM is used to improve the multiplexing capacity and capability of the FBG sensor system and is capable of increasing the interrogated number of sensors twice more than conventional WDM [ 15 , 16 , 17 , 18 ].…”

“…The IWDM approach allows the adjacent FBG reflection spectrum to overlap and crossover to each other without their identification being lost [ 3 , 15 , 16 , 17 , 18 ]. This realized that IWDM is used to improve the multiplexing capacity and capability of the FBG sensor system and is capable of increasing the interrogated number of sensors twice more than conventional WDM [ 15 , 16 , 17 , 18 ]. However, in an IWDM-based sensor system, an unmeasurable gap is created when the bandwidth of one FBG is slightly greater than the neighboring FBG, which induces crosstalk between FBGs and increasing errors in Bragg wavelength measurements [ 15 , 16 , 17 ].…”

“…However, these proposed algorithms have a lack of adaptability and a poor learning capacity for a greater number of FBG sensor systems, and during configuration changes, these algorithms also have reusability problems. In addition, in traditional machine learning techniques, features are manually extracted and consistency is limited, while deep learning ensures that data features and spectral features are automatically extracted via the multi-layer network structure [ 3 , 14 , 18 , 27 , 28 , 29 , 30 ]. More recently, to enhance the accuracy of Bragg wavelength detection, several deep learning techniques such as long short-term memory (LSTM) [ 27 ], convolutional neural networks (CNNs) [ 28 ], back-propagation neural networks (BPNNs) [ 29 ], a hybrid of discrete-wavelet transform (DWT) and LSTM [ 18 ] techniques, and MLP [ 14 , 30 ] techniques have been proposed.…”