Signal processing using artificial neural network for BOTDA sensor system

Azad, Abul Kalam; Wang, Liang; Guo, Nan; Tam, Hwa Yaw; Lu, Chao

doi:10.1364/oe.24.006769

Cited by 135 publications

(57 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [10], a modified version of XCM was implemented on FPGA to speed up the processing time. Artificial neural network (ANN) is also proposed for BOTDA system to improve the sensing accuracy and processing speed [11]. However, the training of ANN is difficult due to numerous hyperparameters.…”

Section: Introductionmentioning

confidence: 99%

BOTDA Fiber Sensor System Based on FPGA Accelerated Support Vector Regression

Wang

Shu

et al. 2020

IEEE Trans. Instrum. Meas.

Self Cite

View full text Add to dashboard Cite

Brillouin optical time domain analyzer (BOTDA) fiber sensors have shown strong capability in static long haul distributed temperature/strain sensing. However, in applications such as structural health monitoring and leakage detection, realtime measurement is quite necessary. The measurement time of temperature/strain in a BOTDA system includes data acquisition time and post-processing time. In this work, we propose to use hardware accelerated support vector regression (SVR) for the post-processing of the collected BOTDA data. Ideal Lorentzian curves under different temperatures with different linewidths are used to train the SVR model to determine the linear SVR decision function. The performance of SVR is evaluated under different signal-to-noise ratios (SNRs) experimentally. After the model coefficients are determined, algorithm-specific hardware accelerators based on field programmable gate arrays (FPGAs) are used to realize SVR decision function. During the implementation, hardware optimization techniques based on loop dependence analysis and batch processing are proposed to reduce the execution latency. Our FPGA implementations can achieve up to 42x speedup compared with software implementation on an i7-5960x computer. The post-processing time for 96,100 BGSs along 38.44-km FUT is only 0.46 seconds with FPGA board ZCU104, making the post-processing time no longer a limiting factor for dynamic sensing. Moreover, the energy efficiency of our FPGA implementation can reach up to 226.1x higher than software implementation based on CPU. Index Terms-Brillouin optical time domain analyzer (BOTDA), fiber optics sensors, digital signal processing, support vector machine (SVM), field programmable gate arrays (FPGA), hardware implementation.

show abstract

Section: Introductionmentioning

confidence: 99%

BOTDA Fiber Sensor System Based on FPGA Accelerated Support Vector Regression

Wang

Shu

et al. 2020

IEEE Trans. Instrum. Meas.

Self Cite

View full text Add to dashboard Cite

show abstract

“…On the other hand, artificial neural networks(ANNs) have been applied in BOTDA [20]- [22]. As a special type of ANN, 1 the feedforward neural network (FNN) can be used to replace the traditional LCF method and improve the processing speed.…”

Section: Introductionmentioning

confidence: 99%

“…As a special type of ANN, 1 the feedforward neural network (FNN) can be used to replace the traditional LCF method and improve the processing speed. Ideal BGSs are used for FNN training [20]. During FNN testing process, the noise in the measured BGS needs to be reduced as much as possible, which means that the filtering operation cannot be omitted.…”

Section: Introductionmentioning

confidence: 99%

Optimized Feedforward Neural Network Training for Efficient Brillouin Frequency Shift Retrieval in Fiber

et al. 2019

View full text Add to dashboard Cite

Artificial neural networks (ANNs) can be used to replace traditional methods in various fields, making signal processing more efficient and meeting the real-time processing requirements of the Internet of Things (IoT). As a special type of ANN, recently the feedforward neural network (FNN) has been used to replace the time-consuming Lorentzian curve fitting (LCF) method in Brillouin optical time-domain analysis (BOTDA) to retrieve the Brillouin frequency shift (BFS), which could be used as the indicator in temperature/strain sensing, etc. However, FNN needs to be re-trained if the generalization ability is not satisfactory, or the frequency scanning step is changing in the experiment. This is a cumbersome and inefficient process. In this paper, FNN only needs to be trained once with the proposed method. 150.62 km BOTDA is built to verify the performance of the trained FNN. Simulation and experimental results show that the proposed method is promising in BOTDA because of its high computational efficiency and wide adaptability.

show abstract

“…In recent years, to enhance the SNR of BOTDA systems, various techniques and schemes have been established [6,7,8,9,10,11,12,13,14,15,16,17,18,19]. Coherent detection has been applied for Brillouin signal detection to improve the SNR [7,8] and to obtain additional Brillouin phase information for reduction of the non-local effects [9].…”

Section: Introductionmentioning

confidence: 99%

“…Further works have combined the coding technique with Raman amplification in BOTDAs to extend the sensing range with less system performance degradation [14,15,16]. More recently, different kinds of offline signal processing techniques such as image processing [17] and artificial neural networks [18] have been deployed to significantly enhance the sensor performance.…”

Section: Introductionmentioning

confidence: 99%

Bi-Directional Brillouin Optical Time Domain Analyzer System for Long Range Distributed Sensing

Guo

Wang

et al. 2016

Sensors

Self Cite

View full text Add to dashboard Cite

We propose and experimentally demonstrate a novel scheme of bi-directional Brillouin time domain analyzer (BD-BOTDA) to extend the sensing range. By deploying two pump-probe pairs at two different wavelengths, the Brillouin frequency shift (BFS) distribution over each half of the whole fiber can be obtained with the simultaneous detection of Brillouin signals in both channels. Compared to the conventional unidirectional BOTDA system of the same sensing range, the proposed BD-BOTDA scheme enables distributed sensing with a performance level comparable to the conventional one with half of the sensing range and a spatial resolution of 2 m, while maintaining the Brillouin signal-to-noise ratio (SNR) and the BFS uncertainty. Based on this technique, we have achieved distributed temperature sensing with a measurement range of 81.9 km fiber at a spatial resolution of 2 m and BFS uncertainty of ~0.44 MHz without introducing any complicated components or schemes.

show abstract

Signal processing using artificial neural network for BOTDA sensor system

Cited by 135 publications

References 27 publications

BOTDA Fiber Sensor System Based on FPGA Accelerated Support Vector Regression

BOTDA Fiber Sensor System Based on FPGA Accelerated Support Vector Regression

Optimized Feedforward Neural Network Training for Efficient Brillouin Frequency Shift Retrieval in Fiber

Bi-Directional Brillouin Optical Time Domain Analyzer System for Long Range Distributed Sensing

Contact Info

Product

Resources

About