Data-driven casting defect prediction model for sand casting based on random forest classification algorithm

The complex sand-casting process combined with the interactions between process parameters makes it difficult to control the casting quality,resulting in a high scrap rate.A strategy based on a data-driven model was proposed to reduce casting defects and improve production efficiency,which includes the random forest(RF)classification model,the feature importance analysis,and the process parameters optimization with Monte Carlo simulation.The collected data includes four types of defects and corresponding process parameters were used to construct the RF model.Classification results show a recall rate above 90% for all categories.The Gini Index was used to assess the importance of the process parameters in the formation of various defects in the RF model.Finally,the classification model was applied to different production conditions for quality prediction.In the case of process parameters optimization for gas porosity defects,this model serves as an experimental process in the Monte Carlo method to estimate a better temperature distribution.The prediction model,when applied to the factory,greatly improved the efficiency of defect detection.Results show that the scrap rate decreased from 10.16% to 6.68%.

Elastic-viscoplastic constitutive equations of K439B superalloy and thermal stress simulation during casting process

K439B nickel-based superalloy is a new type of high-temperature material.There is insufficient research on its constitutive equations and numerical modeling of thermal stress.Isothermal tensile experiments of K439B superalloy at different temperatures(20°C-1,000°C)and strain rates(1.33×10^(-3)s^(-1)-5.33×10^(-3)s^(-1))were performed by using a Gleeble-3800 simulator.The elastic moduli at different temperatures(20°C-650°C)were measured by resonance method.Subsequently,stress-strain curves were measured for K439B superalloy under different conditions.The elastic-viscoplastic constitutive equations were established and the correspongding parameters were solved by employing the Perzyna model.The verification results indicate that the calculated values of the constitutive equations are in good agreement with the experimental values.On this basis,the influence of process parameters on thermal stress was investigated by numerical simulation and orthogonal experimental design.The results of orthogonal experimental design reveal that the cooling mode of casting has a significant influence on the thermal stress,while pouring temperature and preheating temperature of shell mold have minimal impact.The distribution of physical fields under optimal process parameters,determined based on the orthogonal experimental design results,was simulated.The simulation results determine separately the specific positions with maximum values for effective stress,plastic strain,and displacement within the casting.The maximum stress is about 1,000.0 MPa,the plastic strain is about 0.135,and the displacement is about 1.47 mm.Moreover,the distribution states of thermal stress,strain,and displacement are closely related to the distribution of the temperature gradient and cooling rate in the casting.The research would provide a theoretical reference for exploring the stress-strain behavior and numerical modeling of the effective stress of the alloy during the casting process.

A review of refractory high-entropy alloys

This work reviews recent progress in the alloy design,microstructure,and mechanical properties of refractory high-entropy alloys(RHEAs).What’s more,the underlying strengthening mechanisms and deformation behavior are discussed.Composed mainly of near-equimolar refractory elements,RHEAs have superior mechanical properties,especially at high temperatures.However,many of them have limited room-temperature ductility.Much work has been done to solve this trade-off,and some of the RHEAs have the potential to be used for high-temperature applications in the future.In addition to their mechanical properties,RHEAs have other attractive properties,such as biocompatibility and wear resistance,which are discussed.Finally,current problems and future suggestions for RHEAs are discussed.

Microstructural evolution and mechanical performance of cast Mg−3Nd−0.2Zn−0.5Zr alloy with Y additions

This work investigated the effects of different Y additions(0,1.5,3.0 and 4.5 wt.%)on the microstructural evolution and mechanical performance of cast Mg−3Nd−0.2Zn−0.5Zr alloy.The results show that as the Y content increases,the key secondary phases in as-cast alloys change from the Mg_(12)Nd type to the Mg_(24)Y_(5) type.Meanwhile,the number density of Zn−Zr particles in the grains of as-quenched alloys gradually decreases.HAADF-STEM observations of peak-aged samples reveal that element Y is greatly enriched in the globularβ¢precipitates,leading to a significantly increased volume fraction and promoted precipitation kinetics ofβ¢precipitates,resulting in enhanced strength of the alloy.Tensile tests reveal that,with the addition of 4.5 wt.%Y,the yield strength of the base alloy is substantially increased by 88 and 61 MPa after being aged at 200 and 225°C under peak-aged conditions,respectively.

Effect of trace boron on grain refinement of commercially pure aluminum by Al-5Ti-1B

The effect of boron content on grain refinement of commercially pure aluminum by Al-5Ti-1B was quantitatively assessed.When the boron content is less than 0.03 wt.%,the refining performance of Al-5Ti-1B gradually is weakened as the boron content increases,which is attributed to the reaction of boron with the Al_(3)Ti interlayer on TiB_(2)and the consumption of solute Ti.On the contrary,when the boron content exceeds 0.03 wt.%,the refining performance of Al-5Ti-1B gradually recovers with increasing boron content,which is related to the formation of primary AlB_(2)particles that provide additional nucleant substrates.

Influence Factors of Aluminum–Slag Interfacial Reaction Under Electric Field

The interfacial reaction between aluminum melt and molten slag under an electric field plays a significant role in aluminum electro-slag refining. Here we studied this interracial reaction within 680 and 820 ℃ under an electric field between 0 and 9 V. The evolution of aluminum composition was analyzed by inductively coupled plasma atomic emission spectroscopy. The dominant factor during the interfacial reaction was identified through orthogonal experiments, in which the slag-to-aluminum mass ratio, initial silicon concentration, electric voltage, reaction time, and temperature were selected as the influence factors. The greatest influence factor on the interracial reaction was found to be the reaction time. Also, single-factor experiments revealed that the reaction kinetic processes largely obeyed an irreversible kinetic model, and the silicon removal efficiency was enhanced by increasing the voltage and slag/metal ratio.