Papers by Author: Tian Yong Deng

Abstract: The prediction of the hardenability of gear steel has been carried using stepwise polynomial regression and artificial neural networks (ANN). The software was programmed to quantitatively predict the hardenability of gear steel by its chemical composition using two calculating models respectively. The prediction results using artificial neural networks have more precise than the stepwise polynomial regression model. The predicted values of the ANN coincide well with the actual data. So an important foundation has been laid for prediction and controlling the production of gear steel.

Abstract: The metallurgical equations have been implemented into the finite difference model to predict the microstructure evolution at different locations in the plate cross-section. Recrystallization kinetics and grain size distributions instead of average grain size values were computed for different rolling schedules. For 20mm plate, the austenite grain sizes at the surface are smaller than at the center, with the exception of the conner where there are the largest grain sizes in throughout cross-section, and the smallest grain sizes can be found near the end of the horizontal central line. The fine austenite grain size and relatively high retained strain could be obtained by modifying rolling practice, such as changing the temperature and thickness at the entrance of finishing rolling and adopting intermediate water cooling. The ferrite grain size and its distribution have a good agreement with the measurements.