An adaptive learning damage estimation method for structural health monitoring

被引:42
作者
Chakraborty, Debejyo [1 ]
Kovvali, Narayan [2 ]
Papandreou-Suppappola, Antonia [2 ]
Chattopadhyay, Aditi [3 ]
机构
[1] Gen Motors Corp, Global Res & Dev, Warren, MI 48090 USA
[2] Arizona State Univ, Sch Elect Comp & Energy Engn, Tempe, AZ USA
[3] Arizona State Univ, Sch Engn Matter Transport & Energy, Tempe, AZ USA
关键词
Structural health monitoring; damage estimation; time-frequency analysis; matching pursuit decomposition; probability density function; Kullback-Leibler divergence; active data selection; adaptive learning; Dirichlet process mixture; Markov chain Monte Carlo methods; Bayesian filtering; FATIGUE-CRACK GROWTH; WAVELET TRANSFORM; CLASSIFICATION; IDENTIFICATION;
D O I
10.1177/1045389X14522531
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
Structural health monitoring is an important problem of interest in many civil infrastructure and aerospace applications. In the last few decades, many techniques have been investigated to address the detection, estimation, and classification of damage in structural components. One of the key challenges in the development of real-world damage identification systems, however, is variability due to changing environmental and operational conditions. Conventional statistical methods based on static modeling frameworks can prove to be inadequate in a dynamic and fast changing environment, especially when a sufficient amount of data is not available. In this paper, a novel adaptive learning structural damage estimation method is proposed in which the stochastic models are allowed to perpetually change with the time-varying conditions. The adaptive learning framework is based on the use of Dirichlet process (DP) mixture models, which provide the capability of automatically adjusting to structure within the data. Specifically, time-frequency features are extracted from periodically collected structural data (measured sensor signals), that are responses to ultrasonic excitation of the material. These are then modeled using a DP mixture model that allows for a growing, possibly infinite, number of mixture components or latent clusters. Combined with input from physically based damage growth models, the adaptively identified clusters are used in a state-space setting to effectively estimate damage states within the structure under varying external conditions. Additionally, a data selection methodology is implemented to enable judicious selection of informative measurements for maximum performance. The utility of the proposed algorithm is demonstrated by application to the estimation of fatigue-induced damage in an aluminum compact tension sample subjected to variable-amplitude cyclic loading.
引用
收藏
页码:125 / 143
页数:19
相关论文
共 79 条
[1]  
Abramowitz M., 1965, Handbook of mathematical functions with formulas, graphs, and mathematical tables
[2]  
[Anonymous], 2008, A Wavelet Tour of Signal Processing: The Sparse Way
[3]  
[Anonymous], 1994, ASPECTS UNCERTAINTY
[4]  
[Anonymous], 2000, ASYMPTOTICS STAT SOM, DOI DOI 10.1534/genetics.112.147611
[5]  
[Anonymous], TECHNICAL REPORT
[6]   MIXTURES OF DIRICHLET PROCESSES WITH APPLICATIONS TO BAYESIAN NONPARAMETRIC PROBLEMS [J].
ANTONIAK, CE .
ANNALS OF STATISTICS, 1974, 2 (06) :1152-1174
[7]  
Bhattacharyya A., 1943, Bull Calcutta Math Soc, V35, P99
[8]   FERGUSON DISTRIBUTIONS VIA POLYA URN SCHEMES [J].
BLACKWELL, D ;
MACQUEEN, JB .
ANNALS OF STATISTICS, 1973, 1 (02) :353-355
[9]  
Boyd S., 2004, CONVEX OPTIMIZATION
[10]  
Chakraborty D., 2009, 2009 43rd Asilomar Conference on Signals, Systems and Computers, P1678, DOI 10.1109/ACSSC.2009.5469782