Search results

The purpose of this paper is to incorporate prior knowledge in the artificial neural network (ANN) model for the prediction of continuous cooling transformation (CCT) diagram of steel, so that the model predictions become valid from materials engineering point of view.

Genetic algorithm (GA) is used in different ways for incorporating system knowledge during training the ANN. In case of training, the ANN in multi-objective optimization mode, with prediction error minimization as one objective and the system knowledge incorporation as the other, the generated Pareto solutions are different ANN models with better performance in at least one objective. To choose a single model for the prediction of steel transformation, different multi-criteria decision-making (MCDM) concepts are employed. To avoid the problem of choosing a single model from the non-dominated Pareto solutions, the training scheme also converted into a single objective optimization problem.

The prediction results of the models trained in multi and single objective optimization schemes are compared. It is seen that though conversion of the problem to a single objective optimization problem reduces the complexity, the models trained using multi-objective optimization are found to be better for predicting metallurgically justifiable result.

ANN is being used extensively in the complex materials systems like steel. Several works have been done to develop ANN models for the prediction of CCT diagram. But the present work proposes some methods to overcome the inherent problem of data-driven model, and make the prediction viable from the system knowledge.

This study presents finite element (FE) and generalized regression neural network (GRNN) approaches for modeling multiple crack growth problems and predicting crack-growth directions under the influence of multiple crack parameters.

To determine the crack-growth direction in aluminum specimens, multiple crack parameters representing some degree of crack propagation complexity, including crack length, inclination angle, offset and distance, were examined. FE method models were developed for multiple crack growth simulations. To capture the complex relationships among multiple crack-growth variables, GRNN models were developed as nonlinear regression models. Six input variables and one output variable comprising 65 training and 20 test datasets were established.

The FE model could conveniently simulate the crack-growth directions. However, several multiple crack parameters could affect the simulation accuracy. The GRNN offers a reliable method for modeling the growth of multiple cracks. Using 76% of the total dataset, the NN model attained an R2 value of 0.985.

The models are presented for static multiple crack growth problems. No material anisotropy is observed.

In practical crack-growth analyses, the NN approach provides significant benefits and savings.

The proposed GRNN model is simple to develop and accurate. Its performance was superior to that of other NN models. This model is also suitable for modeling multiple crack growths with arbitrary geometries. The proposed GRNN model demonstrates its prediction capability with a simpler learning process, thus producing efficient multiple crack growth predictions and assessments.