CN106897505B - 一种考虑时-空相关性的结构监测数据异常识别方法 - Google Patents

一种考虑时-空相关性的结构监测数据异常识别方法 Download PDF

Info

Publication number
CN106897505B
CN106897505B CN201710070354.7A CN201710070354A CN106897505B CN 106897505 B CN106897505 B CN 106897505B CN 201710070354 A CN201710070354 A CN 201710070354A CN 106897505 B CN106897505 B CN 106897505B
Authority
CN
China
Prior art keywords
monitoring data
data
correlation
statistics
formula
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Expired - Fee Related
Application number
CN201710070354.7A
Other languages
English (en)
Other versions
CN106897505A (zh
Inventor
伊廷华
黄海宾
李宏男
马树伟
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Dalian Lailibai Information Technology Co ltd
Dalian University of Technology
Original Assignee
Dalian Lailibai Information Technology Co ltd
Dalian University of Technology
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Dalian Lailibai Information Technology Co ltd, Dalian University of Technology filed Critical Dalian Lailibai Information Technology Co ltd
Priority to CN201710070354.7A priority Critical patent/CN106897505B/zh
Publication of CN106897505A publication Critical patent/CN106897505A/zh
Priority to PCT/CN2018/076574 priority patent/WO2018145662A1/zh
Priority to US16/090,744 priority patent/US10943174B2/en
Application granted granted Critical
Publication of CN106897505B publication Critical patent/CN106897505B/zh
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00Computer-aided design [CAD]
    • G06F30/20Design optimisation, verification or simulation
    • G06F30/23Design optimisation, verification or simulation using finite element methods [FEM] or finite difference methods [FDM]
    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05BCONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B23/00Testing or monitoring of control systems or parts thereof
    • G05B23/02Electric testing or monitoring
    • G05B23/0205Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
    • G05B23/0218Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
    • G05B23/0224Process history based detection method, e.g. whereby history implies the availability of large amounts of data
    • G05B23/024Quantitative history assessment, e.g. mathematical relationships between available data; Functions therefor; Principal component analysis [PCA]; Partial least square [PLS]; Statistical classifiers, e.g. Bayesian networks, linear regression or correlation analysis; Neural networks
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00Error detection; Error correction; Monitoring
    • G06F11/07Responding to the occurrence of a fault, e.g. fault tolerance
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10Complex mathematical operations
    • G06F17/11Complex mathematical operations for solving equations, e.g. nonlinear equations, general mathematical optimization problems
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10Complex mathematical operations
    • G06F17/15Correlation function computation including computation of convolution operations
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10Complex mathematical operations
    • G06F17/16Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00Pattern recognition
    • G06F18/20Analysing
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00Computing arrangements using knowledge-based models
    • G06N5/04Inference or reasoning models
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N7/00Computing arrangements based on specific mathematical models
    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05BCONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B2219/00Program-control systems
    • G05B2219/30Nc systems
    • G05B2219/35Nc in input of data, input till input file format
    • G05B2219/35017Finite elements analysis, finite elements method FEM
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00Pattern recognition
    • G06F18/20Analysing
    • G06F18/21Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/213Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
    • G06F18/2135Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F2111/00Details relating to CAD techniques
    • G06F2111/10Numerical modelling
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00Machine learning

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Mathematical Physics (AREA)
  • General Engineering & Computer Science (AREA)
  • Pure & Applied Mathematics (AREA)
  • Computational Mathematics (AREA)
  • Mathematical Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Evolutionary Computation (AREA)
  • Software Systems (AREA)
  • Artificial Intelligence (AREA)
  • Algebra (AREA)
  • Computing Systems (AREA)
  • Databases & Information Systems (AREA)
  • Geometry (AREA)
  • Computer Hardware Design (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Computational Linguistics (AREA)
  • Automation & Control Theory (AREA)
  • Testing And Monitoring For Control Systems (AREA)
  • Testing Or Calibration Of Command Recording Devices (AREA)

Abstract

本发明属于土木工程结构健康监测领域,提出了一种考虑时‑空相关性的结构监测数据异常识别方法。首先,对监测数据定义当前和过去观测向量,并对它们进行预白化;其次,对白化后的当前和过去观测向量建立统计相关模型,以同时考虑监测数据中的时‑空相关性;接着,将模型划分为系统相关和系统无关两部分,并定义两个相应的统计量;最后,确定统计量的控制限,当统计量超过其控制限时可判断监测数据中存在异常。

Description

一种考虑时-空相关性的结构监测数据异常识别方法
技术领域
本发明属于土木工程结构健康监测领域,提出了一种考虑时-空相关性的结构监测数据异常识别方法。
背景技术
土木工程结构在长期荷载、环境侵蚀和疲劳效应等因素的共同作用下,其服役性能的退化不可避免。深入分析结构监测数据,可以及时发现结构的异常状态并提供准确的安全预警,对确保土木工程结构的安全运营具有重要的现实意义。目前,结构监测数据的异常识别主要通过统计方法实现,一般分为两大类:1)单变量控制图,如休哈特控制图、累积和控制图等,该类方法对每个测点的监测数据分别建立控制图,以识别监测数据中的异常;2)多变量统计分析,如主成分分析、独立分量分析等,该类方法利用多测点监测数据之间的相关性建立统计模型,并定义相应的统计量以识别监测数据中的异常。
由于结构变形的连续性,结构相邻测点的响应数据之间也具有一定的相关性(即互相关性或空间相关性)。实际工程应用中,能够考虑这种相关性的多变量统计分析方法更具优越性。此外,该类方法仅需定义1~2个统计量,即可判别监测数据中是否存在异常,这对包含众多传感器的结构健康监测系统而言,非常便捷。除了互相关性外,结构响应数据中也存在自相关性(即时间相关性)。若能在统计建模过程中同时考虑自相关性和互相关性(即时-空相关性),则可提升多变量统计分析方法的异常识别能力,使其在工程应用中更具实用价值。
发明内容
本发明旨在提出一种同时考虑时-空相关性的统计建模方法,并在此基础上定义统计量以识别结构监测数据中的异常。其技术方案是:首先,对监测数据定义当前和过去观测向量,并对它们进行预白化;其次,对白化后的当前和过去观测向量建立统计相关模型,以同时考虑监测数据中的时-空相关性;接着,将模型划分为系统相关和系统无关两部分,并定义两个相应的统计量;最后,确定统计量的控制限,当统计量超过其控制限时可判断监测数据中存在异常。
一种考虑时-空相关性的结构监测数据异常识别方法,步骤如下:
步骤一:监测数据预处理
(1)对正常监测数据定义当前和过去观测向量:
yc(t)=y(t)
yp(t)=[yT(t-1),yT(t-2),...,yT(t-l)]T
式中:
Figure BDA0001223918200000021
表示正常监测数据中对应时刻t的样本,m为测量变量的个数;yc(t)和yp(t)分别表示定义在时刻t的当前和过去观测向量;l表示时延;
(2)对当前观测向量yc(t)和过去观测向量yp(t)进行预白化:
Figure BDA0001223918200000022
Figure BDA0001223918200000023
式中:Rc和Rp分别表示yc(t)和yp(t)的白化矩阵;
Figure BDA0001223918200000024
Figure BDA0001223918200000025
分别表示白化后的当前观测向量和过去观测向量;
步骤二:时-空相关性建模
(3)对正常监测数据进行时-空相关性建模,即建立
Figure BDA0001223918200000026
Figure BDA0001223918200000027
之间的统计相关模型如下:
Figure BDA0001223918200000028
Figure BDA0001223918200000029
式中:
Figure BDA00012239182000000210
Figure BDA00012239182000000211
分别表示
Figure BDA00012239182000000212
Figure BDA00012239182000000213
的自协方差矩阵;
Figure BDA00012239182000000214
Figure BDA00012239182000000215
分别表示
Figure BDA00012239182000000216
Figure BDA00012239182000000217
的互协方差矩阵;
(4)由于
Figure BDA0001223918200000031
Figure BDA0001223918200000032
是白化后的数据,则
Figure BDA0001223918200000033
Figure BDA0001223918200000034
均为单位矩阵;又由于
Figure BDA0001223918200000035
Figure BDA0001223918200000036
Figure BDA0001223918200000037
Figure BDA0001223918200000038
之间的统计相关模型可简化为:
Figure BDA0001223918200000039
Figure BDA00012239182000000310
(5)上述统计相关模型的解可通过如下奇异值分解求得:
Figure BDA00012239182000000311
式中:
Figure BDA00012239182000000312
Figure BDA00012239182000000313
为酉矩阵;
Figure BDA00012239182000000314
为奇异值矩阵,其包含的m个非零奇异值即是
Figure BDA00012239182000000315
Figure BDA00012239182000000316
之间的相关系数;
(6)定义
Figure BDA00012239182000000317
在Φ上的投影为z(t),z(t)可通过下式求得:
Figure BDA00012239182000000318
式中:Q=ΦTRp
步骤三:定义统计量
(7)由于仅有m个非零相关系数,则可将变量z(t)划分为两部分:
zs(t)=Qsyp(t)
zn(t)=Qnyp(t)
式中:zs(t)和zn(t)分别表示z(t)的系统相关部分和系统无关部分;Qs和Qn分别为Q的前m行和后m(l-1)行;
(8)为了识别监测数据中的异常,可对zs(t)和zn(t)定义两个统计量:
Figure BDA00012239182000000319
Figure BDA00012239182000000320
对于新采集到的监测数据,先构造过去观测向量yp;再分别计算其对应的两个统计量
Figure BDA00012239182000000321
Figure BDA00012239182000000322
当统计量超过控制限时判断监测数据中存在异常;
步骤四:确定控制限
(9)若监测数据服从正态分布,则两个统计量
Figure BDA0001223918200000041
Figure BDA0001223918200000042
在理论上服从F分布,其控制限的理论值分别为:
Figure BDA0001223918200000043
Figure BDA0001223918200000044
式中:
Figure BDA0001223918200000045
Figure BDA0001223918200000046
分别表示统计量
Figure BDA0001223918200000047
Figure BDA0001223918200000048
的控制限;α表示显著性水平,一般取0.01;
(10)若监测数据不服从正态分布,则通过其它方法分别估计两个统计量
Figure BDA0001223918200000049
Figure BDA00012239182000000410
的概率密度分布,再通过设定的显著性水平α确定其控制限。
本发明的有益效果:在统计建模过程中考虑了结构监测数据具有时-空相关性这一特征,基于此定义的统计量可有效识别监测数据中的异常。
附图说明
图1是结构监测数据的时-空相关性建模示意图。
具体实施方式
以下结合附图和技术方案,进一步说明本发明的具体实施方式。
选取一座两跨公路桥模型,其长度为5.5m、宽度为1.8m。对其建立有限元模型以模拟结构响应,采集16个测点的响应作为监测数据。共生成两个数据集:训练数据集和测试数据集;其中,训练数据集为正常监测数据集,测试数据集中的一部分用于模拟异常监测数据;两个数据集均持续80s,采样频率为256Hz。本发明的关键在于结构监测数据的时-空相关性建模(见图1),具体实施方式如下:
(1)对训练数据集中的每一个数据点构造当前观测向量yc(t)和过去观测向量yp(t);并对所有的yc(t)和yp(t)进行预白化,得到白化矩阵Rc和Rp以及白化后的数据
Figure BDA0001223918200000051
Figure BDA0001223918200000052
(2)对训练数据集进行时-空相关性建模,即对
Figure BDA0001223918200000053
Figure BDA0001223918200000054
进行统计相关性建模,得到模型参数Q=ΦTRp和Λ;由于Λ中仅有16个非零相关系数,则矩阵Q的前16行组成Qs,其余部分组成Qn
(3)确定统计量
Figure BDA0001223918200000055
Figure BDA0001223918200000056
的控制限
Figure BDA0001223918200000057
Figure BDA0001223918200000058
采集到新的监测数据后,首先对其构造过去观测向量yp,然后计算两个统计量
Figure BDA0001223918200000059
Figure BDA00012239182000000510
当统计量超过控制限时判断监测数据中存在异常。
(4)在测试数据集中模拟异常监测数据,即3号传感器在40~80s期间发生异常;利用本发明提出的两个统计量
Figure BDA00012239182000000511
Figure BDA00012239182000000512
对异常监测数据进行识别,结果表明
Figure BDA00012239182000000513
Figure BDA00012239182000000514
均能成功识别出监测数据中的异常。

Claims (1)

1.一种考虑时-空相关性的结构监测数据异常识别方法,其特征在于:
选取一座两跨公路桥模型,已知其长度、宽度;对其建立有限元模型以模拟结构响应,采集测点的响应作为监测数据;共生成两个数据集:训练数据集和测试数据集;其中,训练数据集为正常监测数据集,测试数据集中的一部分用于模拟异常监测数据;具体方法步骤如下:
步骤一:监测数据预处理
(1)对正常监测数据定义当前和过去观测向量:
yc(t)=y(t)
yp(t)=[yT(t-1),yT(t-2),...,yT(t-l)]T
式中:
Figure FDA00024871936400000117
表示正常监测数据中对应时刻t的样本,m为测量变量的个数;yc(t)和yp(t)分别表示定义在时刻t的当前和过去观测向量;l表示时延;
(2)对当前观测向量yc(t)和过去观测向量yp(t)进行预白化:
Figure FDA0002487193640000011
Figure FDA0002487193640000012
式中:Rc和Rp分别表示yc(t)和yp(t)的白化矩阵;
Figure FDA0002487193640000013
Figure FDA0002487193640000014
分别表示白化后的当前观测向量和过去观测向量;
步骤二:时-空相关性建模
(3)对正常监测数据进行时-空相关性建模,即建立
Figure FDA0002487193640000015
Figure FDA0002487193640000016
之间的统计相关模型如下:
Figure FDA0002487193640000017
Figure FDA0002487193640000018
式中:
Figure FDA0002487193640000019
Figure FDA00024871936400000110
分别表示
Figure FDA00024871936400000111
Figure FDA00024871936400000112
的自协方差矩阵;
Figure FDA00024871936400000113
Figure FDA00024871936400000114
分别表示
Figure FDA00024871936400000115
Figure FDA00024871936400000116
的互协方差矩阵;
(4)由于
Figure FDA0002487193640000021
Figure FDA0002487193640000022
是白化后的数据,则
Figure FDA0002487193640000023
Figure FDA0002487193640000024
均为单位矩阵;又由于
Figure FDA0002487193640000025
Figure FDA0002487193640000026
Figure FDA0002487193640000027
Figure FDA0002487193640000028
之间的统计相关模型简化为:
Figure FDA0002487193640000029
Figure FDA00024871936400000210
(5)上述统计相关模型的解通过如下奇异值分解求得:
Figure FDA00024871936400000211
式中:
Figure FDA00024871936400000212
Figure FDA00024871936400000213
为酉矩阵;
Figure FDA00024871936400000214
为奇异值矩阵,其包含的m个非零奇异值即是
Figure FDA00024871936400000215
Figure FDA00024871936400000216
之间的相关系数;
(6)定义
Figure FDA00024871936400000217
在Φ上的投影为z(t),z(t)通过下式求得:
Figure FDA00024871936400000218
式中:Q=ΦTRp
步骤三:定义统计量
(7)由于仅有m个非零相关系数,则将变量z(t)划分为两部分:
zs(t)=Qsyp(t)
zn(t)=Qnyp(t)
式中:zs(t)和zn(t)分别表示z(t)的系统相关部分和系统无关部分;Qs和Qn分别为Q的前m行和后m(l-1)行;
(8)为了识别监测数据中的异常,对zs(t)和zn(t)定义两个统计量:
Figure FDA00024871936400000219
Figure FDA00024871936400000220
对于新采集到的监测数据,先构造过去观测向量yp;再分别计算其对应的两个统计量
Figure FDA00024871936400000221
Figure FDA00024871936400000222
当统计量超过控制限时判断监测数据中存在异常;
步骤四:确定控制限
(9)若监测数据服从正态分布,则两个统计量
Figure FDA0002487193640000039
Figure FDA00024871936400000310
在理论上服从F分布,其控制限的理论值分别为:
Figure FDA0002487193640000031
Figure FDA0002487193640000032
式中:
Figure FDA0002487193640000033
Figure FDA0002487193640000034
分别表示统计量
Figure FDA0002487193640000035
Figure FDA0002487193640000036
的控制限;α表示显著性水平,一般取0.01;
(10)若监测数据不服从正态分布,则通过其它方法分别估计两个统计量
Figure FDA0002487193640000037
Figure FDA0002487193640000038
的概率密度分布,再通过设定的显著性水平α确定其控制限。
CN201710070354.7A 2017-02-13 2017-02-13 一种考虑时-空相关性的结构监测数据异常识别方法 Expired - Fee Related CN106897505B (zh)

Priority Applications (3)

Application Number Priority Date Filing Date Title
CN201710070354.7A CN106897505B (zh) 2017-02-13 2017-02-13 一种考虑时-空相关性的结构监测数据异常识别方法
PCT/CN2018/076574 WO2018145662A1 (zh) 2017-02-13 2018-02-12 一种考虑时-空相关性的结构监测数据异常识别方法
US16/090,744 US10943174B2 (en) 2017-02-13 2018-02-12 Anomaly identification method for structural monitoring data considering spatial-temporal correlation

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710070354.7A CN106897505B (zh) 2017-02-13 2017-02-13 一种考虑时-空相关性的结构监测数据异常识别方法

Publications (2)

Publication Number Publication Date
CN106897505A CN106897505A (zh) 2017-06-27
CN106897505B true CN106897505B (zh) 2020-10-13

Family

ID=59198025

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710070354.7A Expired - Fee Related CN106897505B (zh) 2017-02-13 2017-02-13 一种考虑时-空相关性的结构监测数据异常识别方法

Country Status (3)

Country Link
US (1) US10943174B2 (zh)
CN (1) CN106897505B (zh)
WO (1) WO2018145662A1 (zh)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106897505B (zh) * 2017-02-13 2020-10-13 大连理工大学 一种考虑时-空相关性的结构监测数据异常识别方法
CN111008238B (zh) * 2019-11-15 2023-10-10 武汉楚誉科技股份有限公司 基于关联演化大数据的关键模式自动定位与预警方法
CN114638039B (zh) * 2022-03-24 2024-05-03 沈阳大学 一种基于低秩矩阵恢复的结构健康监测特征数据解释方法
CN116698323B (zh) * 2023-08-07 2023-10-13 四川华腾公路试验检测有限责任公司 一种基于pca和扩展卡尔曼滤波的桥梁健康监测方法及系统
CN117171604B (zh) * 2023-11-03 2024-01-19 城资泰诺(山东)新材料科技有限公司 基于传感器的保温板生产线异常监测系统

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7016825B1 (en) * 2000-10-26 2006-03-21 Vextec Corporation Method and apparatus for predicting the failure of a component
US20080188972A1 (en) * 2006-10-11 2008-08-07 Fisher-Rosemount Systems, Inc. Method and System for Detecting Faults in a Process Plant
US8374854B2 (en) 2008-03-28 2013-02-12 Southern Methodist University Spatio-temporal speech enhancement technique based on generalized eigenvalue decomposition
CN101403923A (zh) * 2008-10-31 2009-04-08 浙江大学 基于非高斯成分提取和支持向量描述的过程监控方法
CN102928514B (zh) * 2012-10-14 2014-12-24 浙江农林大学 一种基于频率特征的木材应力波无损检测方法
CN103942533A (zh) * 2014-03-24 2014-07-23 河海大学常州校区 一种基于视频监控系统的城市交通违规行为检测方法
TWI519987B (zh) * 2014-11-14 2016-02-01 財團法人工業技術研究院 結構拓樸最佳化設計方法
CN104655425B (zh) * 2015-03-06 2017-05-03 重庆大学 基于稀疏表示和大间隔分布学习的轴承故障分类诊断方法
CN106897505B (zh) * 2017-02-13 2020-10-13 大连理工大学 一种考虑时-空相关性的结构监测数据异常识别方法

Also Published As

Publication number Publication date
CN106897505A (zh) 2017-06-27
WO2018145662A1 (zh) 2018-08-16
US10943174B2 (en) 2021-03-09
US20190122131A1 (en) 2019-04-25

Similar Documents

Publication Publication Date Title
CN106897505B (zh) 一种考虑时-空相关性的结构监测数据异常识别方法
CN106897509B (zh) 一种动态非高斯结构监测数据异常识别方法
CN110303380B (zh) 一种数控机床刀具剩余寿命预测方法
CN106951695B (zh) 多工况下的机械设备剩余使用寿命计算方法及系统
CN107357275B (zh) 非高斯工业过程故障检测方法及系统
KR100867938B1 (ko) 종속변수 유사도와 커널 회귀법을 이용한 발전소 계측기성능감시용 예측방법
CN112132430B (zh) 一种配电主设备分布式状态传感器可靠性评估方法及系统
KR20170053692A (ko) 커널 회귀 모델의 앙상블을 위한 장치 및 방법
CN106647650B (zh) 基于变量加权pca模型的分散式工业过程监测方法
CN108956111B (zh) 一种机械部件的异常状态检测方法及检测系统
CN105138770A (zh) 基于间接可靠性特征量的航天产品可靠性仿真评估方法
CN111753776B (zh) 基于回声状态与多尺度卷积联合模型的结构损伤识别方法
CN103134433B (zh) 一种利用位移监测鉴别边坡失稳致滑因子的方法
CN110728089A (zh) 基于botda技术的大跨桥梁斜拉索结构损伤诊断方法
CN113988210A (zh) 结构监测传感网失真数据修复方法、装置及存储介质
CN111368428A (zh) 一种基于监控二阶统计量的传感器精度下降故障检测方法
CN104750926A (zh) 基于节点曲率和小波分析的变截面梁损伤识别方法
CN116698323B (zh) 一种基于pca和扩展卡尔曼滤波的桥梁健康监测方法及系统
CN108170648B (zh) 一种基于已知数据回归的非高斯过程监测方法
CN114091600A (zh) 一种数据驱动的卫星关联故障传播路径辨识方法及系统
CN105651537B (zh) 一种高损伤敏感性的桁架结构损伤实时监测系统
CN110598680A (zh) 一种机械设备健康状态评估方法、系统和可读存储介质
CN115034121A (zh) 一种基于组织性能智能预报模型的带钢工艺调控方法
CN115032502A (zh) 一种最大特征向量电网异常定位方法
CN113919224A (zh) 一种主蒸汽流量预测方法及其系统

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant
CF01 Termination of patent right due to non-payment of annual fee

Granted publication date: 20201013

Termination date: 20220213

CF01 Termination of patent right due to non-payment of annual fee