摘要
光纤预警系统已被广泛应用于油气管道的入侵检测预警中,目前的技术难点仍是如何提高光纤入侵信号多分类识别的准确率。采用梯度提升决策树(GBDT)算法训练光纤入侵信号多分类模型,并提出了一种基于傅里叶分解方法(FDM)及GBDT算法的特征提取与识别算法。该算法采用FDM对光纤入侵信号进行预处理,提取信号的近似熵、能量和谱熵特征。采用GBDT算法训练模型并对光纤入侵信号进行识别分类。为了检验该算法的性能,分别用支持向量机和AdaBoost算法训练模型并进行对比实验。结果表明,该算法能有效识别敲击、小跑、过车和镐刨四类光纤入侵信号,平均准确率为92.5%。
The optical fiber early warning system has been widely used in the intrusion detection and early warning of oil and gas pipelines.The current technical difficulty is still how to improve the accuracy of multi-class recognition of optical fiber intrusion signals.In this paper,gradient boosting decision tree(GBDT)algorithm is used to train the multiclassification model of fiber intrusion signal,and a feature extraction and recognition algorithm based on Fourier decomposition method(FDM)and GBDT algorithm is proposed.The algorithm uses FDM to preprocess the fiber intrusion signal,extracts the approximate entropy,energy and spectral entropy characteristics of the signal,and then uses the GBDT algorithm to train the model to identify and classify the fiber intrusion signal.In order to test the performance of the algorithm,use support vector machine and AdaBoost algorithms to train the models and conduct comparative experiments.The results show that the algorithm can effectively identify four types of optical fiber intrusion signals,namely,knocking,trotting,passing and picking,with an average accuracy of 92.5%.
作者
曲洪权
王征一
盛智勇
曲洪斌
王玲
Qu Hongquan;Wang Zhengyi;Sheng Zhiyong;Qu Hongbin;Wang Ling(School of Information Science and Technology,North China University of Technology,Beijing 100144,China;International Business Department,China Petroleum Pipeline Bureau Engineering Co.,Ltd.,Langfang 065000,Hebei,China;Asia Pacific Branch of China Petroleum Pipeline Bureau Engineering Co.,Ltd.,Langfang 065000,Hebei,China)
出处
《激光与光电子学进展》
CSCD
北大核心
2022年第23期98-105,共8页
Laser & Optoelectronics Progress
基金
国家自然科学基金(61571014)
北京市自然科学基金(4172017)。
关键词
光纤光学
光纤入侵信号
特征提取与识别
傅里叶分解
梯度提升决策树
fiber optics
fiber intrusion signal
feature extraction and recognition
fourier decomposition
gradient boosting decision tree
