Abstract
This article presents an experimental study on verification of the applicability of Gaussian mixture modelling (GMM) algorithm of acoustic emissions for damage identification in reinforced concrete (RC) structures. Eight RC-flanged beam specimens with different properties were tested subjected to flexural loading. An incremental cyclic load was applied on RC-flanged beam specimens till failure, and simultaneously, the released acoustic emissions (AE) were recorded. It may be required to study crack classification in RC structures, because crack classification studies are useful to predict the structural performance and subsequently to implement the appropriate structural rehabilitation methods. AE belonging to tensile cracking and shear cracking can be studied by a probabilistic approach. It was observed that the line separating the AE clusters belonging to tensile and shear cracks was shifting towards a higher rise angle as the specimen is reaching collapse stage. This observation indicates dominance of shear cracks near the collapse stage. At the loading cycle where yielding occurred in the test specimen obtained by using GMM algorithm for AE, the load cycle entered into heavy damage zone is almost same as per NDIS-2421 damage assessment chart. The results obtained by both GMM algorithms for AE and NDIS-2421 criterion to evaluate the damage in the RC-flanged beams were compared and discussed.
Similar content being viewed by others
References
Aggelis DG (2011) Classification of cracking mode in concrete by acoustic emission parameters. Mech Res Commun 38(3):153–157
Ohno K, Ohtsu M (2010) Crack classification in concrete based on acoustic emission. Const Build Mat 24(12):2339–2346
Farhidzadeh A, Singla P, Salamone S (2013) A probabilistic approach for damage identification and crack mode classification in reinforced concrete structures. J Intell Mater Syst Struct 24(14):1722–1735
Grosse C, Reinhardt H, Dahm T (1997) Localization and classification of fracture types in concrete with quantitative acoustic emission measurement techniques. NDT E Int 30(4):223–230
Grosse CU, Ohtsu M (2008) Acoustic emission testing. Springer, Berlin
Holford KM (2000) Acoustic emission—basic principles and future directions. Strain 36(2):51–54
Aggelis DG, Matikas T, Shiotani T (2012) Advanced acoustic techniques of health monitoring of concrete structures. In: Kim S (eds) The Song’s handbook of concrete durability. Middleton Publishing, London
Behnia A, Chaia HK, Shiotani T (2014) Advanced structural health monitoring of concrete structures with the aid of acoustic emission. Cons Build Mater 65(8):282–302
RILEM TC 212-ACD (2010) Acoustic emission and related NDE techniques for crack detection and damage evaluation in concrete. Measurement method for acoustic emission signals in concrete. Mater Struct 43(9):1177–1181
RILEM TC 212-ACD (2010) Acoustic emission and related NDE techniques for crack detection and damage evaluation in concrete. Test Method for damage qualification of reinforced concrete beams by AE. Mater Struct 43(9):1183–1186
RILEM TC 212-ACD (2010) Acoustic emission and related NDE techniques for crack detection and damage evaluation in concrete. Test method for classification of active cracks in concrete structures by acoustic emission. Mater Struct 43(9):1187–1189
NDIS-2421 (2000) Recommended practice for in-situ monitoring of concrete structures by acoustic emission. Japanese Society for Nondestructive Inspection, Tokyo
Ohtsu M, Uchida M, Okamoto T, Yuyama S (2002) Damage assessment of reinforced concrete beams qualified by acoustic emission. ACI Struct J 417:411–417
Beck P, Lark RJ, Holford KM (2003) Moment tensor analysis of acoustic emission in concrete specimens failed in four-point bending. Key Eng Mater 245–246:443–450
Shahidan S, Noorshuhada MN, Bunnori NM (2011) Overview of moment tensor analysis of acoustic emission signal in evaluation of concrete structures. In: 7th IEEE intl colloquium on signal processing and its applications, March 4–6., Penang, Malaysia, pp 20–23
Shigeishi M, Ohtsu M (2001) Acoustic emission moment tensor analysis: development for crack identification in concrete materials. Const Build Mater 15(5):311–319
Yuyama S, Li Z, Ito Y (1999) Quantitative analysis of fracture process in RC column foundation by moment tensor analysis of acoustic emission. Const Build Mater 13(1):87–97
Beck P, Lark R, Holford M (2003) Moment tensor analysis of acoustic emission in concrete specimens failed in four bending. Key Eng Mater 245:443–450
Ohtsu M, Okamoto T, Yuyama S (1998) Moment tensor analysis of acoustic emission for cracking mechanisms in concrete. ACI Struct J 99:411–417
JCMS-III B5706 (2003) Monitoring method for active cracks in concrete by acoustic emission. Federation of Construction Material Industries, Tokyo, pp 23–28
Aggelis DG, Shiotani T, Momoki S, Hirama A (2009) Acoustic emission and ultrasound for damage characterization of concrete elements. ACI Mater J 2009:1–6
Reynolds DA, Rose RC (1995) Robust text-independent speaker identification using Gaussian mixture speaker models. IEEE Trans Speech Audio Process 3:72–83
Reynolds DA, Quatieri TF, Dunn RB (2000) Speaker verification using adapted Gaussian mixture models. Dig Signal Process 10:19–41
Dempster AP, Laird NM, Rubin DB (1977) Maximum likelihood from incomplete data via the EM algorithm. J R Stat Soc Ser B Methodol 39:1–38
Richiardi J, Drygajlo A (2003) Gaussian mixture models for on-line signature verification. In: Proceedings of the 2003 ACM SIGMM workshop on biometrics methods and applications—WBMA, Berkeley, CA, 115–122
Permuter H, Francos J, Jermyn I (2006) A study of Gaussian mixture models of color and texture features for image classification and segmentation. Pattern Recogn 39:695–706
Povinelli RJ, Johnson MT, Lindgren AC (2004) Time series classification using Gaussian mixture models of reconstructed phase spaces. IEEE Trans Knowl Data Eng 16:779–783
Stauffer C, Grimson WEL (1999) Adaptive background mixture models for real-time tracking. In: Proceedings of the 1999 IEEE computer society conference on computer vision and pattern recognition. Fort Collins, CO, 23–25 June, 1999, pp 246–252
Terejanu G, Singla P, Singh T (2008) Uncertainty propagation for nonlinear dynamic systems using Gaussian mixture models. J Guide Cont Dyn 31:1623–1633
Bilmes JA (1998) A gentle tutorial of the EM algorithm and its application to parameter estimation for Gaussian mixture and hidden markov models. International Computer Science Institute, Berkeley
Colombo S, Forde MC, Main IG (2005) AE energy analysis on concrete bridge beams. Mater Struct 38(9):851–856
Vidya Sagar R (2016) A parallel between earthquake sequences and acoustic emissions released during fracture process in reinforced concrete structures under flexural loading. Const Build Mater 114(7):772–793
Vidya Sagar R, Rao MVMS (2014) An experimental study on loading rate effect on acoustic emission based b-values related to reinforced concrete fracture. Const Build Mater 70(5):460–472
Calabrese L, Campanella G, Proverbio E (2013) Use of acoustic emission data clustering to identify damage mode in concrete structures. In: Güneş O, Akkaya Y (eds) Nondestructive testing of materials and structures. RILEM Book series, vol. 6, pp 329–334 Springer, Dordrecht
Nair A, Cai C (2010) Acoustic emission monitoring of bridges: review and case studies. Eng Struct 32(6):1704–1714
Abouhussien AA, Hassan AAA (2015) Evaluation of damage progression in concrete structures due to reinforcing steel corrosion using acoustic emission monitoring. J Civil Struct Health Monit 5(5):751–765
Vidya Sagar R, Raghu Prasad BK (2013) Laboratory investigations on cracking in reinforced concrete beams using on-line acoustic emission monitoring technique. J Civil Struct Health Monit 3(3):169–186
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendix A
Appendix A
The Gaussian mixture modelling (a multivariate probabilistic analysis) allows the user to sort large quantity of data into different clusters (sub-population or first mixture and second mixture) using the expectation (derivation of posterior probability or mixture weights)—maximization algorithm (we compute µ, ∑, and \( \pi_{k} ) \). The GMM (or the linear superposition of Gaussians) is given in Eq. (A1) [23]:
where K is the number of Gaussians (or number clusters, tensile, or shear cluster) and k = 1,…K, \( N(x|\mu_{k, } \mathop \sum \nolimits_{k} ) \) is the normal multivariate Gaussian distribution for class K, and \( \pi_{k} \) is the mixing coefficient (or weightage) for kth Gaussian distribution. A D-variate Gaussian distribution function is given in Eq. (A2):
where \( \mu_{k } \) is the vector form of mean for the kth Gaussian and \( \mathop \sum \nolimits_{k} \) is the covariance matrix for the kth Gaussian. The mixing coefficient (or weightage) satisfies the constraint 0 ≤ \( \pi_{k} \) ≤ 1 and is given in Eq. (A3):
For a univariate Gaussian distribution, the probability density function [F(x)] is given in Eq. (A4):
where − ∞ ≤ x ≤ ∞, µ is the mean, and \( \sigma \) is the standard deviation of the data [30, 31]. Standard deviation (σ) can be thought of measuring how far the data values lie from the mean (µ). Assuming that the variables are independent with probability density function’s \( N\left( {\mu_{1} , \sigma_{1}^{2} } \right) \), \( N\left( {\mu_{2} , \sigma_{2}^{2} } \right) \), …. \( N\left( {\mu_{P} , \sigma_{P}^{2} } \right) \), respectively. The joint densities are given by Eq. (A5). The variance and standard deviation describes how spread out the data is. If the data all lie close to the mean, then the standard deviation is small, while if the data are spread out over large range of values, σ is large:
Solving Eq. (A5), we get
1.1 Implementing GMM algorithm to study crack classification in RC structures
In the present study, the first mixture is the population (or AE hits) which belongs to tensile cracks and the second mixture is the population (or AE hits) which belongs to shear cracks. To use GMM algorithm to classify crack mode in RC test specimens under flexural loading, the input data is a 2-D vector, i.e. RA and AF, are considered:
In addition, the hidden classes are I = {1, 2}, which represent the tensile and shear mode, respectively. In the present experimental data, there are only two clusters (or Gaussians). Therefore, from Eq. (5):
where \( \sigma_{1}^{2} \) is the variance of tensile clusters, \( \sigma_{2 }^{2} \) is the variance of shear clusters, and \( \sigma_{12} = \sigma_{21} \) = 0. Since tensile and shear clusters are independent, the exponent part of Eq. (A10) represents an ellipse. To find the constant part of Eq. (A10), calculate determinant of covariance matrix.
Since it is assumed that the variables are independent. \( \sigma_{1P} \), \( \sigma_{2P} \) … = 0.
Here, \( \sigma_{11} \) is the standard deviation for only tensile clusters. \( \sigma_{22} \) is the standard deviation of only shear clusters; ∑ is the covariance matrix. \( \sigma_{21} \) is the covariance for both tensile and shear clusters. \( \sigma_{11}^{2} \) and \( \sigma_{22}^{2} \) are known as variance. If the tensile and shear clusters are independent each other, then their covariance is zero:
For the exponential part of Eq. (A4), in matrix multiplication, square term is equal to the term multiplied by its transpose, and therefore
Substituting Eqs. (A11) and (A12) into Eq. (A6), we get the general equation for a P variate Gaussian distribution:
Estimating the (∑, µ) of a distribution maximum-likelihood (ML) estimation is used.
Taking logarithm on both sides of Eq. (A13):
To maximize, take derivative of Eq. (A14) with respect to µ and equate it to zero:
Take derivative of Eq. (A14) with respect to ∑ and equate it to zero:
where N is the number of data points. Similarly, for a mixture of Gaussians also called as “Linear superposition of Gaussian’s”:
where K is the number of Gaussians (or clusters). When k equal to 1 indicates for tensile clusters and k equal to 2 for shear cluster, \( N(x|\mu_{k, } \mathop \sum \nolimits_{k} ) \) is the normal multivariate Gaussian distribution for class K; \( \pi_{k} \) is the mixing coefficient (or weightage) for each Gaussian distribution. \( \pi_{1} \) is the mixing coefficient (or weightage) for tensile cluster:
where N1 is the number of AE hits in tensile cluster. N is the total number of AE hits. \( \pi_{2} \) is the mixing coefficient (or weightage) for shear cluster:
Here, N2 is the number of AE hits in shear cluster and N is the total number of AE hits recorded. Taking logarithmic-likelihood on both sides of Eq. (A14), we get
where N indicates all data points (total number of AE hits recorded in the test) and n may equal to 1 and 2. Note that, inside the logarithm, there is a summation over K Gaussian’s, and outside, there is summation for N number of sample data points. The maximum-likelihood can be obtained iteratively using expectation–maximization (EM) method. EM algorithm is used to estimate a set of parameters which are the mixing coefficient (\( \pi_{k} \)), set of class means (\( \mu_{k} \)), and set of covariance (\( \mathop \sum \nolimits_{k} \)). EM algorithm method contains two steps: namely, estimation (or expectation) step and maximization step.
Step I: By applying Bayes’ rule for a given parameter, the expected values of a latent variable are computed:
where \( \pi_{k} = \frac{{N_{k} }}{N} \), \( N_{k} \) = Number of samples for kth class or it is the effective number of data points assigned to cluster k and N = total number of samples, \( \gamma_{k} \) is the latent variable, \( P\left( {k |X} \right) \) is the posterior probability, \( p\left( k \right) \) is the class prior, and \( p(x) \) is the unconditional prior.
For tensile cluster, k = 1.
For shear cluster, k = 2.
where the numerator corresponds to the kth Gaussian and the denominator is the sum of all Gaussians.
Step II: In this step, the parameters are re-estimated using the current latent variable:
where j = 1,2. In case of tensile clusters, j is equal to 1 and j is equal to 2 for shear clusters:
Here, n = a single AE hit. N = total number of AE hits recorded
The log-likelihood is estimated using Eq. (A22) for the above obtained parameters over a number of successive iterations and checked whether it truly represents the data sample or not. This process repeats until a convergence is obtained which is governed by the following criteria; in successive iterations, the parameters (µ, ∑, π) do change or over the last few iterations; second, when the log-likelihood itself does not change over a set of iterations [3].
Rights and permissions
About this article
Cite this article
Vidya Sagar, R. Verification of the applicability of the Gaussian mixture modelling for damage identification in reinforced concrete structures using acoustic emission testing. J Civil Struct Health Monit 8, 395–415 (2018). https://doi.org/10.1007/s13349-018-0284-5
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13349-018-0284-5