Yushan Yin¹, Witold Pedrycz^1,2, Zhiwu Li^1,*

CMC-Computers, Materials & Continua, Vol.79, No.1, pp. 623-650, 2024, DOI:10.32604/cmc.2024.048787 - 25 April 2024

Abstract Utilizing granular computing to enhance artificial neural network architecture, a new type of network emerges—the granular neural network (GNN). GNNs offer distinct advantages over their traditional counterparts: The ability to process both numerical and granular data, leading to improved interpretability. This paper proposes a novel design method for constructing GNNs, drawing inspiration from existing interval-valued neural networks built upon NNNs. However, unlike the proposed algorithm in this work, which employs interval values or triangular fuzzy numbers for connections, existing methods rely on a pre-defined numerical network. This new method utilizes a uniform distribution of information More >

J.C. Tang¹, C.M. Fu^1,2

CMES-Computer Modeling in Engineering & Sciences, Vol.113, No.3, pp. 239-259, 2017, DOI:10.3970/cmes.2017.113.249

Abstract In this paper, an efficient interval analysis method called dimension-reduction interval analysis (DRIA) method is proposed to calculate the bounds of response functions with interval variables, which provides a kind of solution method for uncertainty analysis problems of complex structures and systems. First, multi-dimensional function is transformed into multiple one-dimensional functions by extending dimension reduction method to the interval analysis problem. Second, all the one-dimensional functions are transformed to standard quadratic form by second order Taylor expansion method. As a result, the multi-dimensional function is approximately represented by the functions that each interval variable occurs More >

Di Wu¹, Wei Gao^1,2, Chongmin Song¹, Zhen Luo³

CMES-Computer Modeling in Engineering & Sciences, Vol.108, No.5, pp. 331-373, 2015, DOI:10.3970/cmes.2015.108.331

Abstract Two novel mathematical programming approaches are proposed to separately assess non-deterministic behaviour and stability of engineering structures against disparate uncertainties. Within the proposed computational schemes, uncertainties attributed by the material properties, loading regimes, as well as environmental influences are simultaneously incorporated and modelled by the interval approach. The proposed mathematical programming approaches proficiently transform the uncertain structural analyses into deterministic mathematical programs. Two essential aspects of structural analysis, namely linear structural behaviour and bifurcation buckling, have been explicitly investigated. Diverse verifications have been implemented to justify the accuracy and computational efficiency of the proposed approaches More >

C. Jiang^1,2, S. Yu¹, H.C. Xie¹, B.C. Li¹

CMES-Computer Modeling in Engineering & Sciences, Vol.98, No.4, pp. 443-467, 2014, DOI:10.3970/cmes.2014.098.443

Abstract Based on the interval analysis method, this paper proposes an uncertain optimization model for the ride comfort in vehicles and achieves the optimal design of vehicle ride comfort under the condition of complicated uncertainty. The spring stiffness and shock absorber damping of suspension is regarded as the design parameters, while the root mean square (RMS) of the vehicle body acceleration is treated as the design objective and the corresponding constraints are composed of suspension stiffness, natural frequency and RMS of suspension dynamic deflection. Moreover, the uncertainties of key parameters, such as sprung mass, tire stiffness, More >

C. Wang¹, W. Gao¹, C.W. Yang¹, C.M. Song¹

CMC-Computers, Materials & Continua, Vol.25, No.1, pp. 19-46, 2011, DOI:10.3970/cmc.2011.025.019

Abstract The random interval response and probabilistic interval reliability of structures with a mixture of random and interval properties are studied in this paper. Structural stiffness matrix is a random interval matrix if some structural parameters and loads are modeled as random variables and the others are considered as interval variables. The perturbation-based stochastic finite element method and random interval moment method are employed to develop the expressions for the mean value and standard deviation of random interval structural displacement and stress responses. The lower bound and upper bound of the mean value and standard deviation More >

Wei Gao¹, Chongmin Song¹, Francis Tin-Loi¹

CMES-Computer Modeling in Engineering & Sciences, Vol.46, No.2, pp. 151-190, 2009, DOI:10.3970/cmes.2009.046.151

Abstract Static response and reliability of structures with a mixture of random and interval parameters under uncertain loads are investigated in this paper. Structural stiffness matrix is a random interval matrix when some structural parameters are modeled as random variables and others are considered as intervals. The structural displacement and stress responses are also random interval variables. From the static finite element governing equations, the random interval structural responses are obtained using the random interval perturbation method based on the first- and second-order perturbations. The expressions for mean value and standard deviation of random interval structural More >