2025年7月26日 星期六
岩石力学与工程学报  2024, Vol. 43 Issue (1): 206-215    DOI: 10.13722/j.cnki.jrme.2023.0291
  学术论文 本期目录 | 过刊浏览 | 高级检索 |
滑坡裂缝计时序数据实时异常检测分析
张  磊1,巨能攀1,何朝阳1,解明礼1,张成强1,刘  洋2
(1. 成都理工大学 地质灾害防治与地质环境保护国家重点实验室,四川 成都  610059;2. 四川省自然资源厅,四川 成都  610072)
Real-time anomaly detection and analysis of time series data for crack gauge in landslides
ZHANG Lei1,JU Nengpan1,HE Chaoyang1,XIE Mingli1,ZHANG Chengqiang1,LIU Yang2
(1. State Key Laboratory of Geohazard Prevention and Geoenvironment Protection,Chengdu University of Technology,Chengdu,Sichuan 610059,China;2. Sichuan Provincial Natural Resources Department,Chengdu,Sichuan 610072,China)
全文: PDF (1953 KB)   HTML (1 KB) 
输出: BibTeX | EndNote (RIS)      
摘要 针对滑坡裂缝实时监测中异常数据难以有效识别这一问题,基于滑坡不同变形阶段建立偶然异常阈值,提出基于区间预测的时序数据实时异常检测方法,该方法考虑了数据间时序逻辑关系以及滑坡变形阶段关联信息。首先,通过差分自回归移动平均模型(autoregressive integrated moving average,ARIMA),提取裂缝计累计位移的时序特征,构建区间预测模型,并使用滑动窗口算法对其分割子序列进行预测;其次,利用预测值修正置信区间(? = 0.05)来确定拟异常点,并为滑坡不同变形阶段设立偶然异常阈值;最后,通过组合异常识别得到异常信息。研究结果表明,该方法能准确识别数据异常值,且在时序数据实时异常检测上具有一定的普适性。将模型预测区间与异常值进行对比分析获得数据异常的实时可能性,可为滑坡监测预警智能化决策提供数据参考价值。
服务
把本文推荐给朋友
加入我的书架
加入引用管理器
E-mail Alert
RSS
作者相关文章
张 磊1
巨能攀1
何朝阳1
解明礼1
张成强1
刘 洋2
关键词 边坡工程滑坡时序模型实时异常检测监测预警    
Abstract:In order to address the issue of effectively identifying abnormal data in real-time monitoring of landslide cracks,occasional abnormal thresholds based on the various deformation stages of landslides are established. Additionally,a real-time anomaly detection method for time series data,utilizing interval prediction,is proposed. This method takes into consideration the temporal logic relationship between data and the correlated information of landslide deformation stages. Firstly,the time series characteristics of cumulative displacement of crack gauge are extracted using the autoregressive integrated moving average(ARIMA) model. Subsequently,an interval prediction model is constructed,and the sliding window algorithm is employed to predict sub-sequences. Secondly,to determine prospective abnormal points,a modified confidence interval(with ? = 0.05) is utilized,and occasional abnormal thresholds are established for different deformation stages of landslides. Finally,exceptional information is obtained through combined anomaly recognition. The research results indicate that this method accurately identifies abnormal data values and demonstrates universal applicability in real-time anomaly detection of time series data. By comparing the predicted interval of the model with the abnormal values,the real-time possibility of data abnormalities can be obtained. Furthermore,this method provides valuable data reference for intelligent decision-making in landslide monitoring and early warning.
Key wordsslope engineering    landslide    time series model    real-time anomaly detection    monitoring and early warning
    
引用本文:   
张 磊1,巨能攀1,何朝阳1,解明礼1,张成强1,刘 洋2. 滑坡裂缝计时序数据实时异常检测分析[J]. 岩石力学与工程学报, 2024, 43(1): 206-215.
ZHANG Lei1,JU Nengpan1,HE Chaoyang1,XIE Mingli1,ZHANG Chengqiang1,LIU Yang2. Real-time anomaly detection and analysis of time series data for crack gauge in landslides. , 2024, 43(1): 206-215.
链接本文:  
https://rockmech.whrsm.ac.cn/CN/10.13722/j.cnki.jrme.2023.0291      或      https://rockmech.whrsm.ac.cn/CN/Y2024/V43/I1/206
版权所有 © 2005-2016 《岩石力学与工程学报》编辑部
   主办单位:中国岩石力学与工程学会 出版单位:科学出版社
地址:湖北省武汉市武昌小洪山(邮编:430071) 电话:(027)87199250 传真:(027)87199250 E-mail: rock@whrsm.ac.cn
本系统由北京玛格泰克科技发展有限公司设计开发  技术支持:010-82358270,E-mail: support@magtech.com.cn
鄂公网安备 42010602003581号