Artificial Neural Network and Fuzzy Logic Based Techniques for Numerical Modeling and Prediction of Aluminum-5%Magnesium Alloy Doped with REM Neodymium

In this study, the mechanical properties of aluminum-5%magnesium doped with rare earth metal neodymium were evaluated. Fuzzy logic (FL) and artificial neural network (ANN) were used to model the mechanical properties of aluminum-5%magnesium (0-0.9 wt%) neodymium. The single input (SI) to the fuzzy logic and artificial neural network models was the percentage weight of neodymium, while the multiple outputs (MO) were average grain size, ultimate tensile strength, yield strength elongation and hardness. The fuzzy logic-based model showed more accurate prediction than the artificial neutral network-based model in terms of the correlation coefficient values (R).

Characterization of grain growth behaviors by BP-ANN and Sellars models for nickle-base superalloy and their comparisons

In order to deeply understand the grain growth behaviors of Ni80A superalloy,a series of grain growth experiments were conducted at holding temperatures ranging from 1223 to 1423 K and holding time ranging from 0 to 3600 s.A back-propagation artificial neural network(BP-ANN)model and a Sellars model were solved based on the experimental data.The prediction and generalization capabilities of these two models were evaluated and compared on the basis of four statistical indicators.The results show that the solved BP-ANN model has better performance as it has higher correlation coefficient(r),lower average absolute relative error(AARE),lower absolute values of mean value(μ)and standard deviation(ω).Eventually,a response surface of average grain size to holding temperature and holding time is constructed based on the data expanded by the solved BP-ANN model,and the grain growth behaviors are described.

Microstructural evolvement of wrought magnesium alloy sheet during heat treatment

Magnesium alloy is the lightest structural metal material. As its ductility is usually limited because of its hexagonal closest packing (hcp) structure, it is significant to improve its forming performance. The primary way to achieve this goal is by grain refinement. This study explores new ways of grain refinement for cold-rolled sheet of magnesium alloy AZ31B by probing into its structural evolvement in heat treatment. It is found that recrystallization mostly takes place in the cold-rolled sheet in heat-treatment, and refined and equiaxial recrystallization grains with an average diameter of (14 to 15) mm can be obtained by heat-treatment at 260 C for (60 to 90) min, which is an effective method to obtain refined symmetrical grains of magnesium alloy by heat treatment at a lower recrystallization temperature after cold-rolling.

Deformation behavior and dynamic recrystallization of Mg-Y-Nd-Gd-Zr alloy

The characteristics of dynamic recrystallization （DRX） in Mg-Y-Nd-Gd-Zr-RE magnesium alloy were investigated by compression tests at temperatures between 523 and 723 K and at strain rates ranging from 0.002 to 1 s^-1 with maximum strain of 0.693. The strainhardening rate can be obtained from true stress-true strain curves, plots of θ-σ, -（δθ/δσ-）-a and lnθ-σ in different compression conditions were obtained by further study. The critical condition of the onset of DRX process was determined as （（δ/δσ（ δθ/δσ））=0. In the range of the above deformation temperature and strain rate, the ratio of critical stress （σc） to peak stress （σm） and critical strain （εc） to the peak strain （εm） stood at σc/σm=0.62-0.89 and εc/εm=0.11-0.37, respectively. DRX could be observed during hot detormation process, microstructure evolution of the magnesium alloy at different temperatures and strain rates were studied with the aid of optical microscope（OM）, and the average recrystallized grain size was measured by means of intercepts on photomicrographs. It was shown that the average dynamically recrystallized grain size （drew） changed with different deformation parameters, the natural logarithm of the average recrystallized grain size varied linearly with the natural logarithm of Zener-Hollomon parameter; the peak stress changed with the average recrystallized grain size, and the natural logarithm of the average recrystallized grain size varied linearly with the natural logarithm of the peak stress.

Towards understanding the microstructure and temperature rule in large strain extrusion machining

Large strain extrusion machining(LSEM)is a typical process for preparing ultrafine or nanocrystalline strips.It.is based on large plastic deformation.The processing parameters of LSEM in this study were optimized by experiments and simulations.Using the orthogonal array,signal-to-noise ratio,and analysis of variance,the influence and contribution of processing parameters on response variables were analyzed.Because of the difference in processing parameters between optimizing the average grain size and the maximum temperature,the response variables analyzed must be correctly selected.Furthermore,the optimal processing parameters for obtaining the minimum average grain size and the lowest maximum temperature are analyzed.The results show that the tool rake angle is the most important factor.However,the level of this factor required to achieve the minimum average grain size is different from that required to obtain the lowest maximum temperature.The validity of the method is verified through experiments and simulations.