基于WOA优化神经网络的BOTDA传感信息提取

计算机与现代化 ›› 2021, Vol. 0 ›› Issue (12): 19-26.

基于WOA优化神经网络的BOTDA传感信息提取

（1.北京交通大学信息科学研究所，北京100044；2.现代信息科学与网络技术北京市重点实验室，北京100044；
3.重庆大学光纤光子器件及系统研究室，重庆400044；4.中国长征火箭有限公司，北京100070）

出版日期:2021-12-24 发布日期:2021-12-24
作者简介:刘亚南（1994—），男，安徽亳州人，硕士研究生，研究方向：基于信息处理技术的传感信息提取，E-mail: 2425214399@qq.com；郭南（1989—），男，助理研究员，博士，研究方向：光纤分布式传感系统，E-mail： guonan@cqu.edu.cn；赵阳（1977—），男，工程师，硕士，研究方向：光纤通信，卫星通信及目标识别，E-mail： yzhao@chinarocket.cn；余贶琭（1986—），男，副教授，博士，研究方向：光纤传感以及基于信息处理技术的光纤传感信息提取，E-mail： klyu@bjtu.edu.cn。
基金资助:
国家自然科学基金资助项目（61805008）；中央高校基本科研业务费专项资金资助项目（2020JBM024）

BOTDA Sensing Information Extraction Based on Artificial Neural Network Using Whale Optimization Algorithm

(1. Institute of Information Science, Beijing Jiaotong University, Beijing 100044, China;
2. Beijing Key Laboratory of Modern Information Science and Network Technology, Beijing 100044, China;
3. Research Group of Fiber Photonic Devices and Systems, Chongqing University, Chongqing 400044, China;
4. China Rocket Co. Ltd., Beijing 100070, China)

Online:2021-12-24 Published:2021-12-24

摘要/Abstract

摘要： 人工神经网络（ANN）已被应用于获取布里渊光时域分析仪（BOTDA）所测的布里渊频移信息（BFS），然而其存在易陷入局部最优和收敛速度慢等缺点。为了克服上述缺点，本文提出一种基于WOA优化人工神经网络（WOA-NN）快速获取布里渊光纤传感器BFS的方法；随后通过设计非线性收敛因子a，进一步构建基于非线性WOA优化的神经网络（NWOA-NN）用来提取BFS。将提出的2种网络与经典ANN、粒子群优化神经网络（PSO-NN）、遗传算法优化神经网络（GA-NN）等模型进行比较，实验结果表明，本文所提出的WOA-NN模型在提取BOTDA中的温度信息时的性能优于其他3个网络,其所获取的温度的平均RMSE分别低于ANN、PSO-NN和GA-NN约42.66%、52.51%以及45.93%，NWOA-NN模型所获取的平均RMSE进一步优于WOA-NN 19.08%。同时，使用ANN、PSO-NN、GA-NN、WOA-NN和NWOA-NN进行训练所花费的平均时间分别为929.71 s、889.49 s、699.36 s、580.06 s和549.12 s，所提出的2个网络训练时间表现亦较好。

关键词: 布里渊光时域分析仪, 鲸鱼优化算法, 非线性收敛因子, 人工神经网络

Abstract: Artificial neural networks (ANNs) have been employed to acquire Brillouin frequency shift (BFS) information measured by Brillouin optical time domain analyzer (BOTDA), however, it suffers from drawbacks such as easy entrapment in local optima and a slow convergence rate. To overcome the above shortcomings, an artificial neural network using whale optimization algorithm (WOA) for rapid BFS acquisition for Brillouin fiber sensors is proposed in this manuscript. And then a modified nonlinear WOA neural network (NWOA-NN) with a designed nonlinear convergence factor a was put forward to better extract BFS. We compared the proposed networks with ANN, particle swarm optimized neural network (PSO-NN), and genetic algorithm optimized neural network (GA-NN) models. Experimental results show that the performance of the WOA-NN model is better than the latter three, and the average RMSE of temperature obtained by WOA-NN is lower than those of ANN, PSO-NN and GA-NN by approximately 42.66%, 52.51% and 45. 93%, respectively. The average RMSE by the NWOA-NN model further outperformed the WOA-NN by 19.08%. The average time spent training the ANN, PSO-NN, GA-NN, WOA-NN and NWOA-NN networks were respectively 929.71 s, 889.49 s, 699.36 s, 580.06 s and 549.12 s, our proposed networks illustrated better performance.

Key words: Brillouin optical time domain analyzer, whale optimization algorithm, nonlinear convergence factor, artificial neural networks

刘亚南, 郭南, 赵阳, 余贶琭, . 基于WOA优化神经网络的BOTDA传感信息提取[J]. 计算机与现代化, 2021, 0(12): 19-26.

LIU Ya-nan, GUO Nan, ZHAO Yang, YU Kuang-lu, . BOTDA Sensing Information Extraction Based on Artificial Neural Network Using Whale Optimization Algorithm[J]. Computer and Modernization, 2021, 0(12): 19-26.

参考文献［27］

［1］	GALINDEZ-JAMIOY C A, LOPEZ-HIGUERA J M. Brillouin distributed fiber sensors: An overview and applications［J］. Journal of Sensors, 2012. DOI:10.1155/2012/204121.
［2］	MIZUNO Y, ZOU W W, HE Z Y, et al. Operation of Brillouin optical correlation-domain reflectometry: Theoretical analysis and experimental validation［J］. Journal of Lightwave Technology, 2010,28(22):3300-3306.
［3］	BAO X Y, CHEN L. Recent progress in distributed fiber optic sensors［J］. Sensors, 2012,12(7):8601-8639.
［4］	DONG Y K, CHEN L, BAO X Y. Time-division multiplexing-based BOTDA over 100km sensing length［J］. Optics Letters, 2011,36(2):277-279.
［5］	GALINDEZ-JAMIOY C A, QUINTELA A, QUINTELA M A, et al. 30cm of spatial resolution using pre-excitation pulse BOTDA technique［C］// The 21st International Conference on Optical Fiber Sensors. 2011,7753.DOI:10.1117/12.884996.
［6］	LALAM N, NG W P. Recent development in artificial neural network based distributed fiber optic sensors［C］// 2020 12th International Symposium on Communication Systems, Networks and Digital Signal Processing(CSNDSP). 2020.DOI:10.1109/CSNDSP49049.2020.9249588.
［7］	PANNELL C N, DHLIWAYO J, WEBB D J. The accuracy of parameter estimation from noisy data, with application to resonance peak estimation in distributed Brillouin sensing［J］. Measurement Science and Technology, 1998,9(1):50-57.
［8］	FARAHANI M A, CASTILLO-GUERRA E, COLPITTS B G. Accurate estimation of Brillouin frequency shift in Brillouin optical time domain analysis sensors using cross correlation［J］. Optics Letters, 2011,36(21):4275-4277.
［9］	FARAHANI M A, CASTILLO-GUERRA E, COLPITTS B G. A detailed evaluation of the correlation-based method used for estimation of the Brillouin frequency shift in BOTDA sensors［J］. IEEE Sensors Journal, 2013,13(12):4589-4598.
［10］	ALEM M， SOTO M A， TUR M, et al. Analytical expression and experimental validation of the Brillouin gain spectral broadening at any sensing spatial resolution［C］// 2017 25th Optical Fiber Sensors Conference(OFS). 2017. DOI: 10.1117/12.2267639.
［11］	MCCULLOCH W S, PITTS W. A logical calculus of the ideas immanent in nervous activity［J］. The Bulletin of Mathematical Biophysics, 1943,5(4):115-133.
［12］	AZAD A K, WANG L, GUO N, et al. Signal processing using artificial neural network for BOTDA sensor system［J］. Optics Express, 2016,24(6):6769-6782.
［13］	RUIZ-LOMBERA R, SERRANO J M, LOPEZ-HIGUERA J M. Automatic strain detection in a Brillouin optical time domain sensor using principal component analysis and artificial neural networks［C］// SENSORS, 2014 IEEE. 2014:1539-1542.
［14］	WANG L, ZENG Y, CHEN T. Back propagation neural network with adaptive differential evolution algorithm for time series forecasting［J］. Expert Systems with Applications, 2015,42(2):855-863.
［15］	KIM J S, JUNG S. Implementation of the RBF neural chip with the back-propagation algorithm for on-line learning［J］. Applied Soft Computing, 2015,29:233-244.
［16］	MIRJALILI S. How effective is the Grey Wolf optimizer in training multi-layer perceptrons［J］. Applied Intelligence, 2015,43(1):150-161.
［17］	DEVIKANNIGA D, VETRIVEL K, BADRINATH N . Review of meta-heuristic optimization based artificial neural networks and its applications［J］. Journal of Physics: Conference Series, 2019,1362(1).DOI: 10.1088/1742-6596/1362/1/012074.
［18］	LAMBIOTTE R, DELVENNE J C, BARAHONA M. Random walks, Markov processes and the multiscale modular organization of complex networks［J］. IEEE Transactions on Network Science and Engineering, 2014,1(2):76-90.
［19］	ZHANG Y J, XU J R， FU X H， et al. Hybrid algorithm combining genetic algorithm with back propagation neural network for extracting the characteristics of multi-peak Brillouin scattering spectrum［J］. Frontiers of Optoelectronics, 2017,10(1):62-69.
［20］	张燕君,徐金睿,付兴虎. 基于GA-QPSO混合算法的Brillouin 散射谱特征提取方法［J］. 中国激光, 2016,43(2):138-147.
［21］	KANG W X, LI H, HAN Y. Genetic optimization of general regression neural network applied to feature extraction of Brillouin scattering spectrum in BOTDA sensors［C］// 2018 12th International Symposium on Antennas, Propagation and EM Theory(ISAPE). 2018.DOI:10.1109/ISAPE.2018.8634093.
［22］	MIRJALILI S, LEWIS A. The whale optimization algorithm［J］. Advances in Engineering Software, 2016,95:51-67.
［23］	Virupakshappa, AMARAPUR B. Computer-aided diagnosis applied to MRI images of brain tumor using cognition based modified level set and optimized ANN classifier［J］. Multimedia Tools and Applications, 2020,79(5-6):3571-3599.
［24］	PARAMBANCHARY D, MALLESWARA RAO V. WOA-NN: A decision algorithm for vertical handover in heterogeneous networks［J］. Wireless Networks, 2020,26(1):165-180.
［25］	ALJARAH I, FARIS H, MIRJALILI S. Optimizing connection weights in neural networks using the whale optimization algorithm［J］. Soft Computing, 2018,22(1):1-15.
［26］	WU X Y, ZHANG S， XIAO W D, et al. The exploration/exploitation tradeoff in whale optimization algorithm［J］. IEEE Access, 2019,7:125919-125928.
［27］	SUN Y J, WANG X L, CHEN Y H, et al. A modified whale optimization algorithm for large-scale global optimization problems［J］. Expert Systems with Applications, 2018,114:563-577.

[1]	李茹, 范冰冰. 基于混合策略改进的鲸鱼优化算法[J]. 计算机与现代化, 2022, 0(06): 13-20.
[2]	凌文通, 倪建军, 陈颜, 唐广翼. 基于改进鲸鱼优化算法的多无人机围捕[J]. 计算机与现代化, 2021, 0(06): 1-5.
[3]	李梓龙, 吕勇, 谭国平, 严勤, . 基于纹理特征的超声图像乳腺肿块识别[J]. 计算机与现代化, 2021, 0(02): 1-6.
[4]	潘卫军, 刘皓晨, 王润东, 胡博文. 基于ANN的改进Spark系统在空管大数据处理中的应用[J]. 计算机与现代化, 2020, 0(12): 78-82.
[5]	唐丽晴, 应忠于, 罗云. 基于鲸鱼优化改进算法的基站选址[J]. 计算机与现代化, 2020, 0(09): 100-105.
[6]	杨永娇，邱宇，占力超. 基于宽度学习的智能电网数据服务器流量异常检测算法[J]. 计算机与现代化, 2019, 0(09): 77-.
[7]	许智彪. 基于代价敏感主动学习算法的2型糖尿病诊断[J]. 计算机与现代化, 2018, 0(06): 84-.
[8]	王典;蔡琼. 最优加权组合法在电能短期负荷预测中的应用[J]. 计算机与现代化, 2012, 203(7): 188-191.
[9]	靳建彬王元钦陈源. 基于遗传算法的BP神经网络优化策略研究[J]. 计算机与现代化, 2010, 1(9): 88-91.