Predicting flow stress of Ni steel based on machine learning algorithm

This article builds a stress–strain prediction model based on production data from the steel industry by using machine learning algorithms. Based on the stress–strain data of 9Ni steel hot deformation behavior, the prediction model of flow stress constitutive equation of 9Ni steel is established. Four models, including Arrhenius-type model considering strain compensation, Arrhenius-type model of Stochastic Configuration Networks (SCNs) neural network, Arrhenius-type model of Multi-objective Particle Swarm Optimization (AMPSO) and Support Vector Machine (SVM) model, are adopted in this research. The results show that the Arrhenius-type model considering strain compensation can predict the stress trend under different deformation conditions, but its prediction accuracy has some deviation. The prediction model based on SVM algorithm has the best prediction accuracy. The square of Correlation Coefficient (R2), the Average Absolute Relative Error (AARE), and Mean Square Error (MSE) are 0.99996, 0.002455, and 0.1998, respectively. Based on the data of 9Ni steel hot deformation behavior, the prediction models of machine learning algorithm have good application prospects in steel industry.

The effect of non-metallic inclusion size and orientation on tensile properties of stainless steel (simulation and experiment)

In this study, the effect of non-metallic inclusions (NMIs) on tensile behavior of titanium stabilized Fe-20Cr-9Ni steel was investigated. The size of NMIs was decreased via the electro-slag remelting (ESR) process. JK-inclusion rating method revealed that the studied steel consisted of D-type (square-shaped) inclusions. According to energy dispersive spectroscopy, it was determined that the appeared inclusions in the matrix of the titanium stabilized Fe-20Cr-9Ni steel is predominantly titanium nitride (TiN). As a result of the ESR process, excellent improvement in the tensile properties of the studied steel was observed. Subsequently, the effect of inclusion size (d = 5, 10, 25, 50 µm) and orientation (α = 0, 45°) on stress concentration factor around the non-metallic inclusion and metallic matrix was simulated. The result of finite element analysis indicated that, for both square (α = 0 °) and rhombus (α = 45°) shape inclusions, increasing inclusion size has resulted in high-stress concentration factor during plastic deformation. On the other hands, generated Mises stress field around the non-metallic inclusion presented that, for the same inclusion size, rhombus (α = 45°) shape inclusion is more susceptible to homogenous deformation in comparison with square (α = 0°) one.

The Study on Welding Technology of 9Ni Steel

9Ni steel is a low temperature serving ferrite steel, providing high strength and excellent low temperature toughness, which could serve well at-196°C. Therefore 9Ni steel is widely used in storage tanks and transport ships for liquefied natural gas (LNG). Nevertheless there are some challenges in the industrial application, such as hot cracking, cold cracking, magnetic arc blow, etc.. In this paper, the study on the welding technology of 9Ni steel developed by Baosteel is carried out. Firstly the weldability is analyzed through welding thermal simulation using Gleeble 3500 system, Y-groove cracking test, maximum hardness in weld heat-affected zone test. The results prove that 9Ni steel could be welded without preheating. The welding consumables have also significant influence on the performance of the welded joints. In this paper the characteristics of different types of welding consumables, including ferrite base type, austenitic stainless steel type, Ni-base alloy type and Fe-Ni base alloy type are analyzed, then the selecting principle for welding consumables is proposed. Furthermore welding process experiments are undertaken using various welding procedures such as SMAW, GTAW, FCAW and SAW. The results indicate that heat input and interpass temperature should be controlled to ensure a sound weld joint. Finally fracture toughness at-196°C of 9Ni steel and its joint is studied using CTOD test. In conclusion, 9Ni steel developed by Baosteel has good weldability and can meet the requirements of industrial application.