An artificial neural network approach to multiphase continua constitutive modeling

Lucon, Peter; Donovan, Richard P.

doi:10.1016/j.compositesb.2006.12.008

Cited by 41 publications

(20 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Validation is needed to calculate the error after each epoch (one cycle of training data). The testing dataset is used to check the ability of the network to predict new data at the end of the training process before the network can be used for predictions (Zhang and Friedrich, 2003;Samarasinghe, 2006;Lucon and Donovan, 2007).…”

Section: Method-artificial Neural Network Simulationmentioning

confidence: 99%

Incorporation of iodine into apatite structure: a crystal chemistry approach using Artificial Neural Network

Wang

2015

Front. Earth Sci.

View full text Add to dashboard Cite

Materials with apatite crystal structure have a great potential for incorporating the long-lived radioactive iodine isotope (129 I) in the form of iodide (I −) from nuclear waste streams. Because of its durability and potentially high iodine content, the apatite waste form can reduce iodine release rate and minimize the waste volume. Crystal structure and composition of apatite (A 5 (XO 4) 3 Z) was investigated for iodide incorporation into the channel of the structure using Artificial Neural Network. A total of 86 experimentally determined apatite crystal structures of different compositions were compiled from literature, and 44 of them were used to train the networks and 42 were used to test the performance of the trained networks. The results show that the performances of the networks are satisfactory for predictions of unit cell parameters a and c and channel size of the structure. The trained and tested networks were then used to predict unknown compositions of apatite that incorporates iodide. With a crystal chemistry consideration, chemical compositions that lead to matching the size of the structural channel to the size of iodide were then predicted to be able to incorporate iodide in the structural channel. The calculations suggest that combinations of A site cations of Ag + , K + , Sr 2+ , Pb 2+ , Ba 2+ , and Cs + , and X site cations, mostly formed tetrahedron, of Mn 5+ , As 5+ , Cr 5+ , V 5+ , Mo 5+ , Si 4+ , Ge 4+ , and Re 7+ are possible apatite compositions that are able to incorporate iodide. The charge balance of different apatite compositions can be achieved by multiple substitutions at a single site or coupled substitutions at both A and X sites. The results give important clues for designing experiments to synthesize new apatite compositions and also provide a fundamental understanding how iodide is incorporated in the apatite structure. This understanding can provide important insights for apatite waste forms design by optimizing the chemical composition and synthesis procedure.

show abstract

Section: Method-artificial Neural Network Simulationmentioning

confidence: 99%

Incorporation of iodine into apatite structure: a crystal chemistry approach using Artificial Neural Network

Wang

2015

Front. Earth Sci.

View full text Add to dashboard Cite

show abstract

“…It is fairly important to determine the learning method for the ANN model. One of the most popular learning method is the back-propagation (BP) learning algorithm, which is a typical means of adjusting the weights and biases by utilizing gradient descent to minimize the target error in a particular training pattern [17,18]. Therefore, a three-layer feed forward back-propagation artificial neural network (as shown in Fig.…”

Section: Development Of Artificial Neural Network Modelmentioning

confidence: 99%

Artificial neural network and constitutive equations to predict the hot deformation behavior of modified 2.25Cr–1Mo steel

Wei

et al. 2012

Materials & Design

View full text Add to dashboard Cite

“…When the actual output and the expected output are not the same, the BP-ANN enters into the stage of error back propagation. The errors in output layer modify the weights and biases of each layer, and pass inversely through the input layer and hidden layer 27,28 . N. Haghdadi et al 29 successfully designed an ANN to predict the flow stress of A356 aluminum alloy.…”

Section: Modelling the Hot Flow Behaviors Of Az80 Alloy By Bp-ann Andmentioning

confidence: 99%

“…If there are deviations between the actual output and the expected output, the BP-ANN enters into the stage of error back propagation. The output layer timely modifies the weights and biases of each layer based on the error level to reduce the output error of the network till an acceptable level 27,28 . The forward propagation of information and the back-propagation of error constitute the training process of BP-ANN model, accompanying continuous adjustment of the weights and biases.…”

Section: Construction Process Of Bp-ann Model For As-cast Az80 Magnesmentioning

confidence: 99%

Modelling the Hot Flow Behaviors of AZ80 Alloy by BP-ANN and the Applications in Accuracy Improvement of Computations

et al. 2015

View full text Add to dashboard Cite

Hot compressions of as-cast AZ80 magnesium alloy in a wide temperature range of 523-673 K and strain rate range of 0.01-10 s -1 with a height reduction of 60% were conducted by a Gleeble-1500 thermo-mechanical test simulator. The hot flow behaviors show highly non-linear intrinsic relationships with temperature, strain and strain rate. In order to model the complicated flow behaviors, error back-propagation algorithm, a representative method to minimize the target error, was selected to train the artificial neural network. A comparative study was made on the predictabilities of the improved Arrhenius-type and BP-ANN model by using two standard statistical parameters including correlation coefficient (R) and average absolute relative error (AARE). Comparison results show that the well-trained BP-ANN has higher prediction accuracy. Three highlight applications were presented. Firstly, the strain-stress data volume was expanded by BP-ANN predictions above experimental conditions. Secondly, the expanded data were applied in the simulations of isothermal compressions, and high simulation accuracy for the load-stroke curve was achieved. Thirdly, a three-dimensional (3D) interaction space of stress, strain, temperature and strain rate was constructed based on the intensive data, which supplies the stress data to arbitrary temperature, strain rate, and strain.

show abstract

An artificial neural network approach to multiphase continua constitutive modeling

Cited by 41 publications

References 15 publications

Incorporation of iodine into apatite structure: a crystal chemistry approach using Artificial Neural Network

Incorporation of iodine into apatite structure: a crystal chemistry approach using Artificial Neural Network

Artificial neural network and constitutive equations to predict the hot deformation behavior of modified 2.25Cr–1Mo steel

Modelling the Hot Flow Behaviors of AZ80 Alloy by BP-ANN and the Applications in Accuracy Improvement of Computations

Contact Info

Product

Resources

About