@inproceedings{SwaddiwudhipongThoLiu2004,
  author    = {Swaddiwudhipong, Somsak and Tho, Kee Kiat and Liu, Zishun},
  title     = {Material characterization using artificial neural network},
  doi       = {10.25643/bauhaus-universitaet.155},
  url       = {http://nbn-resolving.de/urn:nbn:de:gbv:wim2-20111215-1550},
  year      = {2004},
  abstract  = {Indentation experiments have been carried out over the past century to determine hardness of materials. Modern indentation machines have the capability to continuously monitor load and displacement to high precision and accuracy. In recent years, research interests have focussed on methods to extract material properties from indentation load-displacement curves. Analytical methods to interpret the indentation load-displacement curves are difficult to formulate due to material and geometric nonlinearities as well as complex contact interactions. In the present study, an artificial neural network model was constructed for interpretation of indentation load-displacement curves. Large strain-large deformation finite element analyses were first carried out to simulate indentation experiments. The data from finite element analyses were then used to train the artificial neural network model. The artificial neural network model was able to accurately determine the material properties when presented with load-displacement curves which were not used in the training process. The proposed artificial neural network model is robust and directly relates the characteristics of the indentation loaddisplacement curve to the elasto-plastic material properties.},
  subject      = {Neuronales Netz},
  language  = {en}
}
@inproceedings{TahaSherifHegger2004,
  author    = {Taha, M. M. Reda and Sherif, Alaa and Hegger, Josef},
  title     = {A nouvelle approach for predicting the shear cracking angle in RC and PC beams using artificial neural networks},
  doi       = {10.25643/bauhaus-universitaet.107},
  url       = {http://nbn-resolving.de/urn:nbn:de:gbv:wim2-20111215-1071},
  year      = {2004},
  abstract  = {The truss model for predicting shear resistance of reinforced concrete beams has usually been criticized because of its underestimation of the concrete shear strength especially for beams with low shear reinforcement. Two challengers are commonly encountered in any truss model and are responsible for its inaccurate shear strength prediction. First: the cracking angle is usually assumed empirically and second the shear contribution of the arching action is usually neglected. This research introduces a nouvelle approach, by using Artificial Neural Network (ANN) for accurately evaluating the shear cracking angle of reinforced and prestressed concrete beams. The model inputs include the beam geometry, concrete strength, the shear reinforcement ratio and the prestressing stress if any. ...},
  subject      = {Neuronales Netz},
  language  = {en}
}