S.Mohanty¹, A. Chattopadhyay², J. Wei³, P. Peralta⁴

Structural Durability & Health Monitoring, Vol.5, No.1, pp. 33-56, 2009, DOI:10.3970/sdhm.2009.005.033

Abstract The current state of the art in the area of real time structural health monitoring techniques offers adaptive damage state prediction and residual useful life assessment. The present paper discusses the use of an integrated prognosis model, which combines an on-line state estimation model with an off-line predictive model to adaptively estimate the residual useful life of an Al-6061 cruciform specimen under biaxial loading. The overall fatigue process is assumed to be a slow time scale process compared to the time scale at which, the sensor signals were acquired for on-line state estimation. The on-line state estimation model was based… More >

Fuyao Yan^{1, #}, Yu hin Chan^2,#, Abhinav Saboo³ , Jiten Shah⁴, Gregory B. Olson^{1, 3}, Wei Chen^{2, *}

CMES-Computer Modeling in Engineering & Sciences, Vol.117, No.3, pp. 343-366, 2018, DOI:10.31614/cmes.2018.04452

Abstract Predicting the mechanical properties of additively manufactured parts is often a tedious process, requiring the integration of multiple stand-alone and expensive simulations. Furthermore, as properties are highly location-dependent due to repeated heating and cooling cycles, the properties prediction models must be run for multiple locations before the part-level performance can be analyzed for certification, compounding the computational expense. This work has proposed a rapid prediction framework that replaces the physics-based mechanistic models with Gaussian process metamodels, a type of machine learning model for statistical inference with limited data. The metamodels can predict the varying properties within an entire part in… More >

V. Romero¹, S. Kanaun²

The International Conference on Computational & Experimental Engineering and Sciences, Vol.3, No.4, pp. 233-242, 2007, DOI:10.3970/icces.2007.003.233

Abstract In this work Gaussian approximating functions proposed in the works of V. Maz'ya are used for the solution of the integral equations of elasto-plasticity for isotropic bodies. The use of this functions esentially simplify the calculation of the elements of the final matrix of the linear algebraic equations of the discretized problem. The elements of this matrix turn to be a combination of simple elementary functions. The method is applied to a 2D rectangular body that has a cut on a border and is subjected to axial tension. The convergence of the method is studied on this example. More >

S. Gopalakrishnan^{1, *}, A. Kandaswamy²

CMES-Computer Modeling in Engineering & Sciences, Vol.114, No.2, pp. 141-152, 2018, DOI:10.3970/cmes.2018.114.141

Abstract Delineation of the lung parenchyma in the thoracic Computed Tomography (CT) is an important processing step for most of the pulmonary image analysis such as lung volume extraction, lung nodule detection and pulmonary vessel segmentation. An automatic method for accurate delineation of lung parenchyma in thoracic Computed Tomography images is presented in this paper. The proposed method involves a segmentation phase followed by a lung boundary correction technique. The tissues in the thoracic Computed Tomography can be represented by a number of Gaussians. We propose a histogram utilized Adaptive Multilevel Thresholding (AMT) for estimating the total number of Gaussians and… More >

Shurong Li^1,*, Yulei Ge², Renlin Zang²

CMES-Computer Modeling in Engineering & Sciences, Vol.114, No.1, pp. 95-116, 2018, DOI:10.3970/cmes.2018.114.095

Abstract In this paper, an interacting multiple-model (IMM) method based on data-driven identification model is proposed for the prediction of nonlinear dynamic systems. Firstly, two basic models are selected as combination components due to their proved effectiveness. One is Gaussian process (GP) model, which can provide the predictive variance of the predicted output and only has several optimizing parameters. The other is regularized extreme learning machine (RELM) model, which can improve the over-fitting problem resulted by empirical risk minimization principle and enhances the overall generalization performance. Then both of the models are updated continually using meaningful new data selected by data… More >

V. Vittaldev¹, R. P. Russell²

CMES-Computer Modeling in Engineering & Sciences, Vol.111, No.1, pp. 83-117, 2016, DOI:10.3970/cmes.2016.111.083

Abstract Monte Carlo simulations are an accurate but computationally expensive procedure for approximating the resultant non-Gaussian probability density function (PDF) after propagation of an initial Gaussian PDF through a nonlinear function. Univariate splitting libraries for Gaussian Mixture Models (GMMs) exist with up to five elements in the literature. The number of splits are extended in the present work by generating three homoscedastic univariate splitting libraries with up to 39 elements. Mulitvariate GMMs are typically handled with splits along a single direction. Instead, we generate a regular multidirectional grid over the initial multivariate Gaussian distribution by recursively applying the splitting library along… More >

K. Naveen Kumar¹, K. Srinivasa Rao², Y. Srinivas³, Ch. Satyanarayana⁴

CMES-Computer Modeling in Engineering & Sciences, Vol.107, No.3, pp. 201-221, 2015, DOI:10.3970/cmes.2015.107.201

Abstract Texture Analysis is one of the prime considerations for image analysis and processing. Texture segmentation gained lot of importance due to its ready applicability in automation of scene identification and computer vision. Several texture segmentation methods have been developed and analysed with the assumption that the feature vector associated with the texture of the image region is modelled as Gaussian mixture model. Due to the limitations of the Gaussian model being meso kurtic, it may not characterise the texture of all image regions accurately. Hence in this paper, a texture segmentation algorithm is developed and analysed with the assumption that… More >

H.T. Zhu ¹

CMES-Computer Modeling in Engineering & Sciences, Vol.97, No.3, pp. 281-298, 2014, DOI:10.3970/cmes.2014.097.281

Abstract This study is concerned with a solution procedure to obtain the probability density function (PDF) of a vibro-impact Duffing oscillator under fully correlated external and parametric Gaussian white noises. The proposed solution procedure consists of three steps. In the first step, the Zhuravlev non-smooth coordinate transformation is adopted to introduce an additional impulsive damping term, in which the original vibro-impact oscillator is converted into a new oscillator without any barrier. After that, the PDF of the new oscillator is obtained by solving the Fokker-Planck equation with the exponential-polynomial closure method. Last, the PDF of the original oscillator is formulated in… More >

S. Chakraverty^1,2, Smita Tapaswini¹

CMES-Computer Modeling in Engineering & Sciences, Vol.103, No.2, pp. 71-90, 2014, DOI:10.3970/cmes.2014.103.071

Abstract Fractional Fornberg-Whitham equation has a vast application in physics. There exist various investigations for the above problem by considering the variables and parameters as crisp/exact. In practice, we may not have these parameters exactly but those may be known in some uncertain form. In the present paper, these uncertainties are taken as interval/fuzzy and the authors proposed here a new method viz. that of the double parametric form of fuzzy numbers to handle the uncertain fractional Fornberg-Whitham equation. Using the single parametric form of fuzzy numbers, original fuzzy fractional Fornberg-Whitham equation is converted first to an interval based fuzzy differential… More >

Shantaram Parab¹, Shreya Srivastava², Pijush Samui³, A. Ramachandra Murthy⁴

CMES-Computer Modeling in Engineering & Sciences, Vol.101, No.2, pp. 139-158, 2014, DOI:10.3970/cmes.2014.101.139

Abstract This paper studies the applicability of Gaussian Process Regression (GPR) and Least Squares Support Vector Machines (LSSVM) to predict fracture parameters and failure load (P_max) of high strength and ultra-high strength concrete beams. Fracture characteristics include fracture energy (G_F), critical stress intensity factor (K_IC) and critical crack tip opening displacement (CTOD_C) Mathematical models have been developed in the form of relation between several input variables such as beam dimensions, water cement ratio, compressive strength, split tensile strength, notch depth, modulus of elasticity and output fracture parameters. Four GPR and four LSSVM models have been developed using MATLAB software for training… More >