Support Vector Machine based Differential Pulse-width Pair Brillouin Optical Time Domain Analyzer

Distributed fiber-optic sensors employ the conventional fiber as the sensing medium and allow all locations along the optical fiber to be measured simultaneously. Thus the sensing scheme provides an efficient way of simultaneously achieving multi-points sensing with a convenient and low-cost configuration. One of the most popular technologies that enables distributed sensing is based on Brillouin scattering. Characteristics of Brillouin scattering are determined mostly by the material properties of the optical fiber and the Brillouin Frequency Shift (BFS) has linear dependence on both the temperature and strain of the fiber under test (FUT). Based on this principle, intensive research efforts have been made in distributed Brillouin fiber sensors during the past two decades. Among them, Brillouin Optical Time-Domain Analysis (BOTDA) has attracted intensive research interest due to its promising properties for temperature and strain monitoring. In BOTDA the local Brillouin Gain Spectrum (BGS) is reconstructed by scanning the frequency offset of a continuous wave and an optical pulse around BFS when they are counter-propagating inside FUT, and the local BFS and hence the temperature and/ or strain information are retrieved accordingly. Usually curve fitting techniques are employed in determining the BFSs of the measured BGSs along the FUT, in which the measured BGS is fitted using an ideal curve and the BFS is found to be the frequency with the peak gain on the fitted curve. Fitting techniques using different lineshape for ideal curves, e.g. Lorentzian curve fitting (LCF), Gaussian curve fitting (GCF), pseudo-Voigt curve fitting (pVCF), and quadratic curve fitting (QCF) have been used to find the BFS distribution along FUT. However, the curve fitting techniques require careful initialization of model parameters and as many data points as possible collected on the measured BGS to ensure the fitting accuracy, otherwise the accuracy in BFS determination will degrade significantly. In addition, long processing time is needed for the iteration of fitting algorithms to find the BFS, especially when the sensing distance is long with a large number of BGSs collected and processed. Recently we have utilized the nonlinear mapping capability of Artificial Neural Network (ANN) in a BOTDA system and has successfully extracted temperature distribution from the measured BGSs along the FUT. Before temperature extraction ANN is trained to acquire the knowledge about the BGS patterns under different temperatures, thus it allows better accuracy even if the data points on the collected BGS become fewer when large frequency scanning step is adopted during the acquisition of BGSs. Moreover, the processing speed of ANN for temperature extraction is much faster than that of curving fitting techniques. In this presentation, we will review our work on using ANN for temperature extraction in a BOTDA system. Different idea spectrum profiles are used for training ANN, and the corresponding performances are compared with those using conventional curve fitting techniques. Some potential applications using ANN in BOTDA are also discussed. We believe that ANN can be an attractive tool for direct temperature or strain extraction in BOTDA system at high accuracy and fast speed.

Structural damage generally initiates in the form of structural cracks. Thus, developing efficient crack detection techniques is of great importance for the structural health monitoring. In this paper, a new crack identification method is proposed, which is based on the differential pulse-width pair Brillouin optical time domain analysis (DPP-BOTDA) technology and the irregular features of Brillouin gain spectrum (BGS) in the fiber due to structural cracks. The proposed method provides a new way to detect and quantify structural cracks without knowing the strain in the structure. First, the working mechanism of DPP-BOTDA is introduced to illustrate the reason that the DPP-BOTDA, compared to traditional BOTDA technique, can significantly improve the spatial resolution of distributed strain sensing, which is critical for structural crack detection. Then, the BGSs in the fiber with the presence of structural cracks, measured by the DPP-BOTDA, are numerically simulated, from which the crack-induced irregular features of the BGS are summarized. Based these irregular features, new structural crack detection and quantification methods are proposed, which are found to be independent of structural stain. Finally, an experiment is conducted on a simple supported reinforced concrete (RC) beam. The results demonstrate that by using the BGS measured by the DPP-BOTDA, the proposed structural crack identification method successfully detects the occurrence of structural cracks and relatively accurately predicts the crack widths.

We experimentally demonstrate the use of artificial neural network (ANN) to process sensing signals obtained from Brillouin optical time domain analyzer (BOTDA). The distributed temperature information is extracted directly from the local Brillouin gain spectra (BGSs) along the fiber under test without the process of determination of Brillouin frequency shift (BFS) and hence conversion from BFS to temperature. Unlike our previous work for short sensing distance where ANN is trained by measured BGSs, here we employ ideal BGSs with different linewidths to train the ANN in order to take the linewidth variation due to different conditions from the training and testing phases into account, making it feasible for long distance sensing. Moreover, the performance of ANN is compared with other two techniques, Lorentzian curve fitting and cross-correlation method, and our results show that ANN has higher accuracy and larger tolerance to measurement error, especially at large frequency scanning step. We also show that the temperature extraction from BOTDA measurements employing ANN is significantly faster than the other two approaches. Hence ANN can be an excellent alternative tool to process BGSs measured by BOTDA and obtain temperature distribution along the fiber, especially when large frequency scanning step is adopted to significantly reduce the measurement time but without sacrifice of sensing accuracy.

We propose and demonstrate a novel differential pulse-width pair Brillouin optical time domain analysis (DPP-BOTDA) system with a pulsed-probe wave for online distributed strain measurement of fiber Michelson hydrophones (FMHs). Different from the conventional DPP-BOTDA using a continuous probe wave, a pulsed-probe wave is used in our scheme to avoid the interferences between the reflected lights from the sensor arm and reference arm of the FMH, where the probe pulse width should be adjusting precisely equal to the time delay between the two arms. The Brillouin frequency shift (BFS) containing the strain and/or temperature information is measured by sweeping the frequency difference of the probe pulse and the pump pulse. In the experiment, an optimized 8/8.5 ns pump pulse pair is applied to realize a 5-cm spatial resolution, and the probe pulses of 624.5 ns and 1269 ns are applied to measure the strain distribution of the sensor arms of two FMHs. We have successfully measured the temperature-induced strain of a FMH with an arm length difference of 62.45 m as temperature increases from -40°C to 80°C and the distributed strain variation of the other FMH with the arm length difference of 126.91 m as the hydrostatic pressure increases from 0.1 MPa to 10 MPa. The results indicate that the proposed scheme can provide a desirable solution for online distributed strain measurement of the FMHs.

We propose and experimentally demonstrate the use of principal component analysis (PCA) based pattern recognition to extract temperature distribution from the measured Brillouin gain spectra (BGSs) along the fiber under test (FUT) obtained by Brillouin optical time domain analysis (BOTDA) system. The proposed scheme employs a reference database consisting of relevant ideal BGSs with known temperature attributes. PCA is then applied to the BGSs in the reference database as well as to the measured BGSs so as to reduce their size by extracting their most significant features. Now, for each feature vector of the measured BGS, we determine its best match in the reference database comprised of numerous reduced-size feature vectors of the ideal BGSs. The known temperature attribute corresponding to the best-matched BGS in the reference database is then taken as the extracted temperature of the measured BGS. We analyzed the performance of PCA-based pattern recognition algorithm in detail and compared it with that of curve fitting method. The experimental results validate that the proposed technique can provide better accuracy, faster processing speed and larger noise tolerance for the measured BGSs. Therefore, the proposed PCA-based pattern recognition algorithm can be considered as an attractive method for extracting temperature distributions along the fiber in BOTDA sensors.

The key operation of traditional Brillouin optical time-domain analysis (BOTDA) is the frequency-sweeping process to get the distributed Brillouin gain spectrum (BGS) whose central frequency (i.e. Brillouin frequency shift, BFS) has a linear relationship with the environmental information (e.g. temperature or strain) over the sensing fiber. However, this time-consuming process has limited the sampling rate of BOTDA. In this paper, we summarize several fast BOTDA systems for dynamic strain measurement which is developed by our team and refers to frequency-agile technique, slope-assisted methods and optical chirp chain technique.

In recent years, many conventional image denoising techniques have been intensively studied to enhance the signal to noise ratio (SNR) of Brillouin optical time domain analyzer (BOTDA), due to their superior denoising performance to one-dimensional methods. However, in the case of low sampling rate, the details of the signal are smoothed out due to less useful information, resulting in a degradation of the spatial resolution. Moreover, these conventional denoising algorithms are quite time-consuming compared with the BOTDA measuring time. To overcome these drawbacks, we employ a feed-forward convolutional neural networks (CNN) based image denoising for BOTDA. A conventional BOTDA system with 15 ns pulse width is implemented to demonstrate the effectiveness of the exploited CNN-based denoising method. The actual electrical noise signals of the BOTDA at different sampling rates are collected to synthesize training samples. The CNN model is trained with the noise and simulated BOTDA signals. Experimental results show that SNR improvement of 13.43 dB, 13.57 dB, and 12.9 dB is achieved at a sampling rate of 500 MSa/s, 250 MSa/s, and 125 MSa/s, respectively, via the trained CNN denoiser. No spatial resolution distortion can be observed in the denoised BOTDA signals. Besides, the CNN denoiser only takes 0.045 s to process a 151 × 50000 image benefiting from GPU computing. This processing time is negligible compared with the acquisition time of BOTDA, which makes real-time denoising possible.

Appearance of micrometer size surface cracks is common in structural elements such as welded connections, beams, and gusset plates in bridges. Brillouin scattering-based sensors are capable of making distributed strain measurements. Pre-pump-pulse Brillouin optical time domain analysis (PPP-BOTDA) provides a centimeter-level spatial resolution, which facilitates detection and monitoring of the cracks. In the work described here, in addition to the shift in Brillouin frequency (distributed strains), change in the Brillouin gain spectrum (BGS) width is investigated for the detection and monitoring of surface micro-cracks. A theoretical analysis was undertaken in order to verify the rationality of the proposed method. The theoretical approach involved simulation of strain within a segment of the optical fiber traversing a crack and use of the simulated strain distribution in the opto-mechanical relations in order to numerically obtain the change in the BGS. Simulations revealed that the increase in crack opening displacements is associated with increase in BGS width and decrease in its peak power. Experimental results also indicated that the increases in crack opening displacements are accompanied with increases in BGS widths. However, it will be difficult to use the decrease in BGS power peak as another indicator due to practical difficulties in establishing generalized power amplitude in all the experiments. The study indicated that, in combination with the shift in Brillouin frequency, the increase in BGS width will provide a strong tool for detection and monitoring of surface micro-crack growths.

Near infrared spectroscopy was used in discrimination of intact bovine teeth in terms of animal sex, diet, tooth type and place of origin. Discriminant Analysis (DA) models were developed and tested using a stratified random 70:30 data split to calibration and test sets. Of the discriminant techniques of Soft Independent Modelling of Class Analogy (SIMCA), Partial Least Squares – DA, Artificial Neural Networks (ANN) and Support Vector Machine (SVM), SVM and PLS-DA models performed best in most instances, with pretreatment choice impacting technique success. For test set prediction of animal sex, an accuracy of 95% was achieved using a PLS-DA model, and similar performance achieved using a SVM model. SVM, ANN and SIMCA models predicted three categories of tooth type (deciduous, permanent unerupted and erupted) with similar accuracies (89, 79 and 82%, respectively), however, permanent unerupted teeth were conflated with permanent erupted teeth. Prediction accuracy for ANN, SVM and PLS-DA models were also similar for discrimination of teeth from animals on a grain versus grass diet (PLS-DA 82%). There was considerable variation between models in prediction of geographic origin. Of the seven locations, two were discriminated with true positive rate around 70% using SVM and ANN models. Potential applications of this technology are discussed.

Brillouin optical time-domain analysis (BOTDA) enables high-precision distributed sensing by extracting the Brillouin frequency shift (BFS). However, the BFS extraction based on traditional Lorentz curve fitting (LCF) suffers from limited accuracy and low efficiency. This work proposes a spatial-temporal feature fusion method integrating pseudo-video denoising (PVD) network and deep learning to improve the BFS extraction in BOTDA. In our proposal, a PVD network was introduced to improve the signal-to-noise ratio of temporal data by simulating video processing, utilizing multi-frame time redundancy to suppress noise while preserving Lorentz line-shape features. Furthermore, a spatial-temporal feature fusion network combining convolutional neural network (CNN), long short-term memory (LSTM), and multi-head attention (MHA) was constructed. After extracting local spectral features through CNN, LSTM was used to capture the long-term temporal dependence of Brillouin gain spectrum (BGS) signals along the fiber axis, and MHA was introduced to dynamically weight critical frequency points to suppress noise interference. Experiments on a BOTDA system with a sensing fiber of 1.02 km single-mode fibers (SMFs) demonstrated that the proposed method achieved a root mean square error (RMSE) of 0.333 MHz for the BFS extraction, benefiting a higher accuracy by 3.5% as well as 18 times faster processing speed with respect to that with the LCF method. This work provides a high-precision and time-efficient BFS extraction solution for distributed Brillouin sensing, especially for applications under complex noise conditions, exhibiting potentials in structural health monitoring for critical infrastructure such as energy pipeline monitoring, high voltage cable monitoring, and so on.

Frequency-comb-based Brillouin optical time-domain analysis (BOTDA) sensors were developed to achieve acquisition-time reduction and high-spatial-resolution/long-distance sensing simultaneously. We found that, for the standard frequency-comb-based BOTDA, the use of a double-sideband (DSB) pulse generates a series of pulse pairs that simultaneously propagate along the sensing fiber, leading to a nonlinear interaction between the two sidebands of each frequency comb pulse, and a significant splitting of the Brillouin gain spectrum (BGS). This problem prevents its application in high-spatial-resolution sensing due to the higher pulse power requirement. Thus, one of the sidebands of DSB pulse was proposed for greatly suppressing the BGS distortion. In combination with the phonon pre-excitation technique based on phase-shifted pulse, a sensor with a spatial-resolution approximately 60 cm along a fiber approximately 592 m in length was demonstrated. Furthermore, we explored the detailed performance of long-distance sensing by frequency- comb-based BOTDA. The use of a frequency comb for the probe wave can suppress the pulse distortion and non-local effect, which is helpful for extending the sensing distance. A spatial resolution of approximately 6 m along a sensing fiber approximately 74.2 km in length was successfully demonstrated.

The sudden collapse of sinkholes in the Dead Sea area represents a serious threat to infrastructure in the area. The formation of these sinkholes has been shown to be directly correlated with the drop in the Dead Sea water level which is accompanied by a corresponding lowering of the groundwater level and permits the penetration of low-salinity groundwater into coastal areas. This water causes dissolution of the salt layers which results in the formation of subsurface voids that develop into collapse sinkholes. Various tools and measurement methods have been investigated in order to attempt to detect the formation of sinkholes, but to date, there is no method capable of providing early warning of possible collapse. This paper investigates the use of fiber-optic Brillouin optical time-domain reflectometry (BOTDR) or Brillouin optical time-domain analysis (BOTDA) for such detection. Brillouin optical time-domain reflectometry or analysis (BOTDR/A) is an optical measurement technique that provides di...

The dependence of Brillouin linewidth and peak frequency on lightwave state of polarization (SOP) due to fiber inhomogeneity in single mode fiber (SMF) is investigated by using Brillouin optical time domain analysis (BOTDA) system. Theoretical analysis shows fiber inhomogeneity leads to fiber birefringence and sound velocity variation, both of which can cause the broadening and asymmetry of the Brillouin gain spectrum (BGS) and thus contribute to the variation of Brillouin linewidth and peak frequency with lightwave SOP. Due to fiber inhomogeneity both in lateral profile and longitudinal direction, the measured BGS is the superposition of several spectrum components with different peak frequencies within the interaction length. When pump or probe SOP changes, both the peak Brillouin gain and the overlapping area of the optical and acoustic mode profile that determine the peak efficiency of each spectrum component vary within the interaction length, which further changes the linewidth and peak frequency of the superimposed BGS. The SOP dependence of Brillouin linewidth and peak frequency was experimentally demonstrated and quantified by measuring the spectrum asymmetric factor and fitting obtained effective peak frequency respectively via BOTDA system on standard step-index SMF-28 fiber. Experimental results show that on this fiber the Brillouin spectrum asymmetric factor and effective peak frequency vary in the range of 2% and 0.06MHz respectively over distance with orthogonal probe input SOPs. Experimental results also show that in distributed fiber Brillouin sensing, polarization scrambler (PS) can be used to reduce the SOP dependence of Brillouin linewidth and peak frequency caused by fiber inhomogeneity in lateral profile, however it maintains the effects caused by fiber inhomogeneity in longitudinal direction. In the case of non-ideal polarization scrambling using practical PS, the fluctuation of effective Brillouin peak frequency caused by fiber inhomogeneity provides another limit of sensing frequency resolution of distributed fiber Brillouin sensor.

This study explores the effectiveness of various noise reduction filters in accurately measuring temperature distributions over a 38.2 km single-mode fiber (SMF). Brillouin optical time-domain analysis (BOTDA) sensor is utilized to gather Brillouin gain spectra (BGSs), which are denoised using bilateral filter (BF), guided filter (GF), adaptive Wiener filter (AWF), non-local means filter (NLMF), average filter (AF) and disc filter (DF). The temperature distributions over the SMF are then determined by applying least-squares curve fitting (LSCF). The study assesses the efficacy of noise reduction filters considering signal-to-noise ratio (SNR), uncertainty in temperature measurement (UTM), experimental spatial resolution (ESR) and signal processing speed (SPS). Among six different filters, NLMF outperforms other filters which can provide SNR improvement of 10.22 dB for which the UTM can be improved by 58.93% without deteriorating the ESR of the sensor. The noise reduction using such filter can also provide 6.2% faster SPS. Therefore, NLMF can be considered as an effective noise reduction filter for the precise temperature measurement using BOTDA sensors. DUJASE Vol. 8 (1) 42-50, 2023 (January)

기업의 부도를 예측하는 것은 회계나 재무 분야에서 중요한 연구주제이다. 지금까지 기업 부도예측을 위해 여러 가지 데이터마이닝 기법들이 적용되었으나 주로 단일 모형을 사용함으로서 복잡한 분류 문제에의 적용에 한계를 갖고 있었다. 본 논문에서는 최근에 각광받고 있는 SVM (support vector machine) 모형들을 결합한 앙상블 SVM 모형 (ensemble SVM model)을 부도예측에 사용하고자 한다. 제안된 앙상블 모형은 v-조각 교차 타당성 (v-fold cross-validation)에 의해 얻어진 여러 가지 모형 중에서 성능이 좋은 상위 k개의 단일 모형으로 구성하고 과반수 투표 방식 (majority voting)을 사용하여 미지의 클래스를 분류한다. 본 논문에서 제안된 앙상블 SVM 모형의 성능을 평가하기 위해 실제 기업의 재무비율 자료와 모의실험자료를 가지고 실험하였고, 실험결과 제안된 앙상블 모형이 여러 가지 평가척도 하에서 단일 SVM 모형들보다 좋은 성능을 보임을 알 수 있었다. Corporate bankruptcy prediction has been an important topic in the accounting and finance field for a long time. Several data mining techniques have been used for bankruptcy prediction. However, there are many limits for application to real classification problem with a single model. This study proposes ensemble SVM (support vector machine) model which assembles different SVM models with each different kernel functions. Our ensemble model is made and evaluated by v-fold cross-validation approach. The k top performing models are recruited into the ensemble. The classification is then carried out using the majority voting opinion of the ensemble. In this paper, we investigate the performance of ensemble SVM classifier in terms of accuracy, error rate, sensitivity, specificity, ROC curve, and AUC to compare with single SVM classifiers based on financial ratios dataset and simulation dataset. The results confirmed the advantages of our method: It is robust while providing good performance.