Prediction of Wear Properties of CaO and MgO Doped Stabilized Zirconia Ceramics with Artificial Neural Networks

İngilizce (OpenAlex)

In this research, the production and wear behavior of CaO and MgO doped stabilized zirconia ceramics prepared by powder metallurgy method were investigated and artificial neural network (ANN) models were established and predicted with the data produced as a result of real experiments. CaO/MgO doped stabilized zirconia ceramics were produced using a combination of ball milling, cold pressing - cold isostatic pressing and sintering methods. CaO and MgO were mixed with zirconia in different amounts (0-8 mol%). These mixtures were prepared by mechanical alloying. Green compacts were sintered at 1600°C. The wear experimental results produced from the trials were converted into data suitable for modelling with ANN. Wear load, wear time of the load, MgO and CaO were given as input to the ANN model. The amount of wear according to the pressing method was set as the output variable value of the ANN. An ANN approach model was established to predict the wear behavior characteristics of zirconia ceramic composites. In order to emphasize the success of the model, the test data set was presented to the ANN model and the results produced were compared with the results produced experimentally, and as a result of these tests, high R2 values of 0.99409 for 65N and 0.97512 for 80N were produced.