WO2018145662A1 - 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 PDFInfo
- Publication number
- WO2018145662A1 WO2018145662A1 PCT/CN2018/076574 CN2018076574W WO2018145662A1 WO 2018145662 A1 WO2018145662 A1 WO 2018145662A1 CN 2018076574 W CN2018076574 W CN 2018076574W WO 2018145662 A1 WO2018145662 A1 WO 2018145662A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- monitoring data
- correlation
- statistical
- represent
- data
- 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.)
- Ceased
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/23—Design optimisation, verification or simulation using finite element methods [FEM] or finite difference methods [FDM]
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0218—Electric 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
- G05B23/0224—Process history based detection method, e.g. whereby history implies the availability of large amounts of data
- G05B23/024—Quantitative 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
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/11—Complex mathematical operations for solving equations, e.g. nonlinear equations, general mathematical optimization problems
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/15—Correlation function computation including computation of convolution operations
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/04—Inference or reasoning models
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N7/00—Computing arrangements based on specific mathematical models
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/35—Nc in input of data, input till input file format
- G05B2219/35017—Finite elements analysis, finite elements method FEM
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/10—Numerical modelling
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Definitions
- An abnormality identification method for structural monitoring data considering time-space correlation is an abnormality identification method for structural monitoring data considering time-space correlation
- the invention belongs to the field of civil engineering structural health monitoring, and proposes an abnormality identification method for structural monitoring data considering time-space correlation.
- the anomaly identification of structural monitoring data is mainly realized by statistical methods, which are generally divided into two categories: 1) single variable control charts, such as Shewhart control charts, accumulation and control charts, etc., for each type of measurement point The monitoring data respectively establish control charts to identify anomalies in the monitoring data; 2) multivariate statistical analysis, such as principal component analysis, independent component analysis, etc., which uses a correlation between multiple measurement points to establish a statistical model. And define the corresponding statistics to identify the anomalies in the monitoring data.
- the present invention aims to propose a statistical modeling method that simultaneously considers the time-space correlation, and on this basis defines a statistic to identify anomalies in the structure monitoring data.
- the technical solution is: First, the monitoring data Define current and past observation vectors and pre-whiten them; Secondly, establish a statistical correlation model for the current and past observation vectors after whitening to simultaneously consider the time-space correlation in the monitoring data; then, divide the model into systems The correlation and the system are independent of the two parts, and define two corresponding statistics; Finally, determine the control limit of the statistic, when the statistic exceeds its control limit, it can be judged that there is an abnormality in the monitoring data.
- a structural monitoring data anomaly identification method considering time-space correlation the steps are as follows:
- Step 1 Monitoring data preprocessing
- jy( )e9T represents the sample of the corresponding time ⁇ in the normal monitoring data
- m is the number of measured variables
- ( ) and : ⁇ ( ⁇ ) respectively represent the current and past observation vectors defined at time ⁇ ;
- Step 2 Time-space correlation modeling
- Step 4 Determine the control limit (9) If the monitoring data follows a normal distribution, the two statistics 13 ⁇ 4 and 13 ⁇ 4 are theoretically subject to the F distribution, and the theoretical limits of the control limits are: Where: and lim represent the statistic and control limits respectively; "representing the level of significance, generally taking 0.01;
- the structure monitoring data has the feature of time-space correlation, and the statistic based on this definition can effectively identify the abnormality in the monitoring data.
- a two-span highway bridge model with a length of 5.5 m and a width of 1.8 m was selected.
- a finite element model was established to simulate the structural response, and the responses of 16 measuring points were collected as monitoring data.
- a total of two data sets are generated: a training data set and a test data set; wherein, the training data set is a normal monitoring data set, and a part of the test data set is used to simulate abnormal monitoring data; both data sets last for 80s, and the sampling frequency is 256Hz.
- the key to the invention lies in the structure-air correlation modeling, see the following formula:
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)
- Automation & Control Theory (AREA)
- Computational Linguistics (AREA)
- Testing And Monitoring For Control Systems (AREA)
- Testing Or Calibration Of Command Recording Devices (AREA)
Abstract
一种考虑时-空相关性的结构监测数据异常识别方法,属于土木工程结构健康监测领域,具体包括: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: ) = [ (卜 1), (卜 2),..., (卜 /)—
式中: jy( )e9T表示正常监测数据中对应时刻 ί的样本, m为测量变量的个数; ( )和:^ (ί)分别表示定义在时刻 ί的当前和过去观测向量; /表示时延;
(2)对当前观测向量 ^ (ί)和过去观测向量:^ (ί)进行预白化:
p{t) = R p{t)
式中: 和/ r分别表示 (ί)和 的白化矩阵; ( 和 w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 和 之间的统计 相关模型如下:
式中: =E^ ^和^ =Ε 分别表示 j^W和 的自协方差矩阵; Cpc = Ε ^ τ}和 P = E{ T}分别表示 (t)和 (t)的互协方差矩阵;
(4)由于 和 是白化后的数据, 则 (? 和 (^均为单位矩阵; 又由于 ; = ccp且 = cpc, 则 (ή和 ( )之间的统计相关模型可简化为:
(5)上述统计相关模型的解可通过如下奇异值分解求得:
Cpc=E{ypycT} = ^AWT 式中: <^ = [^^..,^]£ "^和^ = [^,^...,¾^]£ ^为酉矩阵; Ε9Γ^为 奇异值矩阵, 其包含的 m个非零奇异值即是 和 之间的相关系数;
(6)定义 在 Φ上的投影为 φ;), ζ(ί)可通过下式求得:
ζ ( = 0Ty~p it) = TR yp {t) = Qyp (t)
式中: ρ = φτ/^; 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 ζ(ί)划分为两部分: zs{t) = Qsyp{t)
式中: 和 分别表示 ζ(ί)的系统相关部分和系统无关部分; ^和 |2„分别 为 β的前 m行和后 m(/-l)行;
对于新采集到的监测数据, 先构造过去观测向量 再分别计算其对应的 两个统计量 和 H^, 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 1¾和1¾在理论上服从 F分布, 其控制限的理论值分别为:
式中: 和 ,lim分别表示统计量 和 的控制限; "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 ί¾ 和1¾的概率密度分布, 再通过设定的显著性水平 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。
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 -空相关性建模, 见如下公式:
(2) 对训练数据集进行时-空相关性建模, 即对 和 进行统计相关 性建模, 得到模型参数 β = Φτ ^和 ; 由于 中仅有 16个非零相关系数, 则矩 阵 β的前 16行组成 , 其余部分组成 。
(3) 确定统计量 和 的控制限 Un^n ,Um; 采集到新的监测数据后, 首先对其构造过去观测向量 Jp, 然后计算两个统计量 Η^= ^τ((2 ) ^和 = ypT{Q Qn)yp^ 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 1¾和1¾对异常监测数据进行识别, 结果表 明 和 H 均能成功识别出监测数据中的异常。
Claims
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:
步骤一: 监测数据预处理
式中: j( )e9T表示正常监测数据中对应时刻 的样本, m为测量变量的个数; (ί)和: 分别表示定义在时刻 的当前和过去观测向量; /表示时延;
(2)对当前观测向量 (ί)和过去观测向量:^ (ί)进行预白化:
yp{t) = Rpyp{t)
式中: 和/ T分别表示 (ί)和 的白化矩阵; 和 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 (t)和 (ή之间的统计 相关模型如下:
C C C C )φ = λ2φ
[c;' cpc;-pcpc) = 2
式中: έρρ: E^ 和 dcc = E{ycycT}分别表示 (ή和 ( 的自协方差矩阵;
= Ε ^ 和 = 分别表示 W和 W的互协方差矩阵;
(4) 由于 和 ( 是白化后的数据, 则 <? 和 均为单位矩阵; 又由于 c]c = ^且 = cpc, 则 ^ (ή和 ( 之间的统计相关模型简化为:
(5)上述统计相关模型的解通过如下奇异值分解求得: 式中: ( ^^^.^Jef^和 ^: ^,^…,^^ 为酉矩阵; >1£9^ 为 奇异值矩阵, 其包含的 m个非零奇异值即是 和 (f)之间的相关系数;
(6) 定义 在 Φ上的投影为 ζ(ί), ζ(ί)通过下式求得:
ζ (ή = Φ (ή = 0TR' y' (t) = Qyp (t)
式中: ρ = φτ/^;
步骤三: 定义统计量
式中: 和 Ζ„(ί)分别表示 ζ(ί)的系统相关部分和系统无关部分; ^和 ^分别 为 β的前 m行和后 (Z-l)行;
(8)为了识别监测数据中的异常, 对 ^ (?)和 zn (t)定义两个统计量:
^n =zn Tzn =ypT(Qn TQn)yp
对于新采集到的监测数据, 先构造过去观测向量 再分别计算其对应的 两个统计量 和 H , 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 和 在理论上服从 F分布, 其控制限的理论值分别为:
m(m2/2-l)
式中: H 和 lim分别表示统计量 和 的控制限; "表示显著性 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 和 的概率密度分布, 再通过设定的显著性水平 确定其控制限。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| 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 (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710070354.7 | 2017-02-13 | ||
| 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 (1)
| Publication Number | Publication Date |
|---|---|
| WO2018145662A1 true WO2018145662A1 (zh) | 2018-08-16 |
Family
ID=59198025
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2018/076574 Ceased 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 |
Country Status (3)
| Country | Link |
|---|---|
| US (1) | US10943174B2 (zh) |
| CN (1) | CN106897505B (zh) |
| WO (1) | WO2018145662A1 (zh) |
Families Citing this family (6)
| 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 |
| CN116484213A (zh) * | 2022-12-13 | 2023-07-25 | 山东省交通规划设计院集团有限公司 | 基于投影重构与深度学习的公路结构健康预测方法及系统 |
| 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 |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100076756A1 (en) * | 2008-03-28 | 2010-03-25 | Southern Methodist University | Spatio-temporal speech enhancement technique based on generalized eigenvalue decomposition |
| CN102928514A (zh) * | 2012-10-14 | 2013-02-13 | 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 |
| CN104655425A (zh) * | 2015-03-06 | 2015-05-27 | 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 |
| CN106897505A (zh) * | 2017-02-13 | 2017-06-27 | 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 |
Family Cites Families (5)
| 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 |
| 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 |
| 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 |
-
2017
- 2017-02-13 CN CN201710070354.7A patent/CN106897505B/zh not_active Expired - Fee Related
-
2018
- 2018-02-12 US US16/090,744 patent/US10943174B2/en not_active Expired - Fee Related
- 2018-02-12 WO PCT/CN2018/076574 patent/WO2018145662A1/zh not_active Ceased
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100076756A1 (en) * | 2008-03-28 | 2010-03-25 | Southern Methodist University | Spatio-temporal speech enhancement technique based on generalized eigenvalue decomposition |
| CN102928514A (zh) * | 2012-10-14 | 2013-02-13 | 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 |
| CN104655425A (zh) * | 2015-03-06 | 2015-05-27 | 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 |
| CN106897505A (zh) * | 2017-02-13 | 2017-06-27 | 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 |
Non-Patent Citations (1)
| Title |
|---|
| MA, JIE ET AL.: "Blind Source Separation Method Based on Eigen Value and Singular Value", JOURNAL OF TIANJIN UNIVERSITY, vol. 38, no. 8, 31 August 2005 (2005-08-31), pages 740 - 743, ISSN: 0493-2137 * |
Also Published As
| Publication number | Publication date |
|---|---|
| US20190122131A1 (en) | 2019-04-25 |
| US10943174B2 (en) | 2021-03-09 |
| CN106897505B (zh) | 2020-10-13 |
| CN106897505A (zh) | 2017-06-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2018145662A1 (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 | |
| CN108960303B (zh) | 一种基于lstm的无人机飞行数据异常检测方法 | |
| CN108171142B (zh) | 一种确定复杂工业过程中关键变量因果关系的方法 | |
| WO2018001147A1 (zh) | 一种基于优化张紧弦模型的桥索监测方法及系统 | |
| CN103389472B (zh) | 一种基于nd-ar模型的锂离子电池循环寿命的预测方法 | |
| CN109829136B (zh) | 一种带随机跳变的退化设备的剩余寿命预测方法及系统 | |
| CN108304685A (zh) | 一种非线性退化设备剩余寿命预测方法及系统 | |
| CN110728089B (zh) | 基于botda技术的大跨桥梁斜拉索结构损伤诊断方法 | |
| CN106199267B (zh) | 一种电力设备故障特征分析方法 | |
| CN115015683B (zh) | 电缆生产的性能测试方法、装置、设备及存储介质 | |
| CN107885928A (zh) | 考虑测量误差的步进应力加速性能退化可靠性分析方法 | |
| CN108562821A (zh) | 一种基于Softmax确定配电网单相接地故障选线的方法及系统 | |
| CN115267409A (zh) | 一种电力设备故障检测方法、装置及设备 | |
| CN109779791A (zh) | 一种固体火箭发动机中异常数据智能诊断方法 | |
| CN117113068A (zh) | 一种桥梁支座纵向位移的模拟方法及系统 | |
| CN106407555A (zh) | 基于加速因子不变原则的加速退化数据分析方法 | |
| CN105674943A (zh) | 一种通用的多点非线性整体变形预测方法 | |
| CN111127242A (zh) | 一种基于小样本数据的电力系统可靠性动态实时评估方法 | |
| CN110414086B (zh) | 一种基于灵敏度的综合应力加速因子计算方法 | |
| CN119808606A (zh) | 一种考虑结构特征的机队数字孪生损伤诊断和预测方法 | |
| CN118861950B (zh) | 变压器多参数融合状态评估方法、装置、设备及介质 | |
| CN108170648A (zh) | 一种基于已知数据回归的非高斯过程监测方法 | |
| 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 | |
| CN119556067A (zh) | 一种基于多特征融合和迭代预测模型的电缆早期故障预警方法及系统 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 18750863 Country of ref document: EP Kind code of ref document: A1 |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 18750863 Country of ref document: EP Kind code of ref document: A1 |



