Knowledge‐Based Modeling of Material Behavior with Neural Networks

Ghaboussi, Jamshid; Garrett, James H.; Wu, Xiaomin

doi:10.1061/(asce)0733-9399(1991)117:1(132)

Cited by 631 publications

(295 citation statements)

References 12 publications

Supporting

Mentioning

288

Contrasting

Unclassified

Order By: Relevance

“…Creation of the new type intelligent data base and a suitable, postprocessor and preprocessor can be proposed for all "difficult" material as for example -concrete. The concrete soft modeling was at the beginning (from chronological point of view, [5]) of the history of the application of the ANN in civil engineering. All constitutive doubts concerning existing, adapted or revitalized structures in civil engineering should be arbitrated using the proposed methodology.…”

Section: Example Of Determination Of Mechanical Propertiesmentioning

confidence: 99%

“…We mention for example the so called self-learning finite element procedure introduced first by Ghaboussi in [4][5][6] and developed then by Shin and Pande in [7,8] as a very promising technique of data acquisition for the ANN training process. Presentation of this method that was applied immediately to problems of diaphragma wall dimensioning would exceed the Some aspects of application of artificial neural network for numerical modeling in civil engineering frame of this paper.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Some aspects of application of artificial neural network for numerical modeling in civil engineering

Lefik¹

2013

Bulletin of the Polish Academy of Sciences: Technical Sciences

View full text Add to dashboard Cite

Abstract. In order to obtain reliable results of computations in civil engineering, the numerical procedures that are used at the stage of design should be calibrated by comparison of the theoretical results with an observed behavior of previously modeled and then executed structures. The hybrid Finite Element code with an Artificial Neural Network inserted as a representation of a constitutive law, offers a possibility to adjust not only parameters of the constitutive relationships but also its qualitative form. Because of this, the representation of constitutive law by the ANN is presented in this paper. The constitutive data should be calibrated to fit well the observable values, measured in experiments. If the constitutive law is expressed by ANN, the inverse problem can be reduce to a training of the ANN inserted into the Finite Element code. An example of a solution of the inverse problem in calibration of constitutive law is presented. An identification of parameters of flow of pollutant in soils is described as another example of application of ANN in engineering.

show abstract

Section: Example Of Determination Of Mechanical Propertiesmentioning

confidence: 99%

mentioning

confidence: 99%

Some aspects of application of artificial neural network for numerical modeling in civil engineering

Lefik¹

2013

Bulletin of the Polish Academy of Sciences: Technical Sciences

View full text Add to dashboard Cite

show abstract

“…The natural path of a solution of an existing condition is introduction of different heuristic procedures structural identification which considers features of a studied problem. They are grounded on an application of neural networks, intellectual and genetic technologies [6][7][8][9][10][11][12][13]. Application of these technologies is grounded on learning of their elements by means of search models-applicants and obtaining of total adequate model.…”

Section: Introductionmentioning

confidence: 99%

Structural Methods of Estimation Lyapunov Exponents Linear Dynamic System

Karabutov¹

2015

IJISA

View full text Add to dashboard Cite

Abstract-The problem of structural identification linear dynamic systems on the basis of the analysis Lyapunov exponent in the conditions of uncertainty is considered. The method of estimation the general solution system on the basis of application static model is developed. Definition of Lyapunov exponent (LE) on the analysis of a coefficient structural properties system is grounded. On the basis of a coefficient of structural properties the special structures reflecting change LE are introduced. The criterion of estimation an order system on the basis of the analysis behaviour these structures are offered. The decision-making method about type of roots dynamic system on the basis of the analysis of time series and the structures reflecting change LE is developed. Two approaches to an estimation of the largest LE and the Perron bottom indexes are offered. The first approach to identification of a change in a coefficient of structural properties with the help secant method for various classes of roots is grounded. The second approach is the structurally-frequency method grounded on definition of estimations LE by means of the analysis of local minima of structures offered in work. The frequency method which is a modification of a method a bar graph in the statistical theory is applied to a validation of the obtained estimations. Results of simulation confirm effectiveness of the offered methods, structures and procedures.

show abstract

“…Recently, a new programming paradigm, artificial neural networks (ANN) has been proposed to model complicated multiparameter material behavior (Ghaboussi et al, 1991;Mukherjee et al, 1995;Mukherjee and Rao, 1996). The basic advantage of artificial neural networks lies in the fact that it is able to automatically map a relationship from the supplied input and output parameters.…”

Section: Introductionmentioning

confidence: 99%