The high temperature flow behavior of as-cast 904L austenitic stainless steel was studied using artificial neural network (ANN). Isothermal compression tests were carried out at the temperature range of 1000°C to 1200°C and strain rate range of 0.01 to 10s1. Based on the experimental flow stress data, an ANN model for the constitutive relationship between flow stress and strain, strain rate and deformation temperature was constructed by back-propagation (BP) method. Three layer structured network with one hidden layer and nine hidden neurons was trained and the normalization method was employed in training process to avoid over fitting. Modeling results show that the developed ANN model exhibits good performance for predicting the flow stresses of the 904L steel. Therefore, it can be used to reflect the hot deformation behavior in a wide working window.

Steel slag is hydraulic cementing material, which is mainly applicable approach to the production of cement, admixture of high performance concrete, road engineering. But as a result of hydration expansion of the free calcium oxide and free magnesium oxide and dicalcium silicate morphological changes which is contained in slag cause poor stability of steel slag used in engineering, the steel slag utilization is very low. Therefore, the key technology of steel slag treatment process is to improve the stability of steel slag. Steel slag is alkaline slag, with lower temperature, the viscosity increases sharply, the liquidity variation, it is one of the important factors affect the steel slag processing, According to the need for different liquidity of steel slag to choose the corresponding steel slag treatment technology. Tank-type hot disintegrating, Rotary cylinder technology processing available to small particle size, good steel slag separation, active promotion of slags, conducive to the comprehensive utilization of steel slag.

In order to utilize the converter slag that treated by the method of hot braised comprehensively. Using Jiugang hot braised slag as raw material, to determine the chemical composition of the slag with the semi-quantitative analysis and a number of chemical analytical methods. Using X-ray diffraction, optical microscopy, scanning electron microscopy and energy dispersive spectrometer to analysis the hot braised slag phase and iron phase. Also doing the measurement and analysis to the particle size of the slag, compressive strength and the grinding fineness. It was obtained the conclusion by the comprehensive analysis of hot braised slag that the hot braised slag can be returned to sintering process as solvent and it can also used in the construction、buliding materials and road engineering industry. It is a good suggestion that grounding the slag into a fine powder due to the poor effect of abrasion.

As the dynamic recrystallization (DRX) behavior of hot-deformed austenite is the basis of determining controlled rolling schedule for steel, in the present work, the dynamic recrystallization behavior of austenite of a 0.22%C-1.30%Mn-0.04%Nb micro-alloyed steel was investigated by means of high temperature compression tests on the Thermecmastor-Z simulator. By the analysis of true stress-strain curves at different deformation stages, the hot deformation equation of austenite was established for the steel. As a result, the energy to induce recrystallization of austenite for the steel is 419.1 kJmol-1, as it was influenced by the drag effect of micro-alloyed element Nb in solid solution. The ratio (σc/σp) of critical stress σc (where DRX occurs) to peak stress σp is 0.93 while the ratio (εc/εp) of critical strain εc to peak stress εp is 0.52 for the steel. The austenite grain size of dynamic recrystallization of the micro-alloyed steel is refined by decreasing the deformation temperature and improving the stain rate.

In order to control the plasticity of CaO-SiO2-Al2O3system inclusions so as to reduce the harm to the quality of 42CrMoA crankshaft steel, the target controlling ranges of CaO-SiO2-Al2O3inclusions is put forward. On the basis, influence of CaO-SiO2-Al2O3and CaO-SiO2-Al2O3-MgO system top slag on the content of calcium and aluminum in molten steel is contrasted. Theoretical research results show that, calcium activity should be controlled in the range of (90~3300)×10-10, oxygen activity should be below 7×10-6, the mass percent of calcium should be controlled more than 75ppm. And CaO-SiO2-Al2O3-MgO should be a good choice to obtain the plastic inclusions of CaO-SiO2-Al2O3.