电子测量与仪器学报

金姝,罗家童,高雅,俞本立,张书金,甄胜来.基于深度学习的光纤微震信号分类识别的研究[J].电子测量与仪器学报,2024,38(6):135-142

基于深度学习的光纤微震信号分类识别的研究

Deep learning-based classification and identificationof fiber optic microseismic signals

DOI：

英文关键词:fiber optic microseismic signal convolutional neural network attention mechanism classification and identification energy estimation

基金项目:安徽省重点研发计划（202104a05020059）、安徽省优秀科研创新团队（2022AH010003）、合肥综合性国家科学中心、贵州省科技支撑（黔科合支撑【2022】一般005）项目资助

作者	单位
金姝	1.安徽大学光电信息获取与控制教育部重点实验室合肥230601；2.安徽大学信息材料与智能感知安徽省实验室合肥230601
罗家童	安徽至博光电科技股份有限公司合肥230601
高雅	1.安徽大学光电信息获取与控制教育部重点实验室合肥230601；2.安徽大学信息材料与智能感知安徽省实验室合肥230601
俞本立	1.安徽大学光电信息获取与控制教育部重点实验室合肥230601；2.安徽大学信息材料与智能感知安徽省实验室合肥230601
张书金	贵州省矿山安全科学研究院有限公司贵阳550025
甄胜来	1.安徽大学光电信息获取与控制教育部重点实验室合肥230601；2.安徽大学信息材料与智能感知安徽省实验室合肥230601

Author	Institution
Jin Shu	1.Key Laboratory of OptoElectronic Information Acquisition and Manipulation, Ministry of Education, Anhui University, Hefei 230601,China; 2.Information Materials and Intelligent Sensing Laboratory of Anhui Province, Anhui University, Hefei 230601,China
Luo Jiatong	IDETECK CO., LTD., Chuangxin Avenue, Hefei 230601,China
Gao Ya	1.Key Laboratory of OptoElectronic Information Acquisition and Manipulation, Ministry of Education, Anhui University, Hefei 230601,China; 2.Information Materials and Intelligent Sensing Laboratory of Anhui Province, Anhui University, Hefei 230601,China
Yu Benli	1.Key Laboratory of OptoElectronic Information Acquisition and Manipulation, Ministry of Education, Anhui University, Hefei 230601,China; 2.Information Materials and Intelligent Sensing Laboratory of Anhui Province, Anhui University, Hefei 230601,China
Zhang Shujin	Guizhou Mining Safety Science Research Institute Co., Ltd, Guiyang 550025,China
Zhen Shenglai	1.Key Laboratory of OptoElectronic Information Acquisition and Manipulation, Ministry of Education, Anhui University, Hefei 230601,China; 2.Information Materials and Intelligent Sensing Laboratory of Anhui Province, Anhui University, Hefei 230601,China

摘要点击次数: 50

全文下载次数: 1324

中文摘要:

微震监测技术可实时、精确给出岩体破裂或失稳的空间位置，已成为煤与瓦斯突出、隧道岩爆等灾害预警的重要手段之一。针对地下工程中环境复杂，信号微弱难以有效辨别的问题，提出了一种将卷积神经网络与Transformer结合（T_CNN）的微震信号识别方法。利用光纤加速度传感器采集西部某隧道工程中的6种信号，将信号经过带通滤波降噪和傅里叶变换后输入模型进行训练和验证。利用模型中的卷积神经网络进行特征提取，基于Transformer对重点信息进行聚焦，通过多层感知机得出最终多分类结果。结果表明，基于T_CNN模型分类准确率达到98.09%，且收敛速度更快。相较于目前先进的残差神经网络来说，其准确率提高了6.2%，精确率、召回率、F1分数分别提高了0.036、0.023和0.033，证实了该算法在实际工程应用中的优越性。此外，将光纤微震信号经过特征变换后输入到模型中，光纤微震信号的能量也能得到较为准确的估算，进一步验证了该模型具有良好的应用前景。

英文摘要:

Microseismic monitoring technology can give the spatial location of rock body rupture or instability in real time and accurately, and has become one of the important means of early warning for disasters such as coal and gas herniation and tunnel rock explosion. Aiming at the problem of complex environment and weak signals difficult to be recognized effectively in underground engineering, a microseismic signal recognition method combining convolutional neural network and Transformer (T_CNN) is proposed. Six kinds of signals in tunnel engineering in a western region are collected by using fiber-optic acceleration sensors, and the signals are input into the model for training and verification after band-pass filtering for noise reduction and Fourier transform. Convolutional neural network in the model is utilized for feature extraction, focusing on the key information based on Transformer, and the final multi-classification results are derived by multilayer perceptron. The results show that the classification accuracy of the T_CNN-based model reaches 98.09% and converges faster. Compared with the current state-of-the-art residual neural network, the accuracy is improved by 6.2%, and the precision, recall, and F1 score are improved by 0.036, 0.023, and 0.033, respectively, which confirms the superiority of the algorithm in practical engineering applications. In addition, the energy of the fiber microseismic signal can also be estimated more accurately after the fiber microseismic signal is input into the model after the feature transformation, which further verifies that the model has good application prospects.

查看全文查看/发表评论下载PDF阅读器