Search

This study explores the application of machine learning algorithms—gene expression programming (GEP), adaptive neuro-fuzzy inference system (ANFIS), and artificial neural networks (ANN)—to predict machining responses during the milling of Inconel 690, a superalloy known for its exceptional mechanical properties and oxidation resistance. Machining Inconel 690 presents significant challenges due to its toughness and work-hardening tendencies, which can lead to rapid tool wear and poor surface finish. Traditional optimization methods often rely on empirical models and trial-and-error approaches, which are time-consuming and costly. In contrast, machine learning techniques can effectively model complex, nonlinear relationships between machining parameters and performance outcomes, such as surface roughness, cutting force, and cutting temperature. This study employs statistical metrics, including Root mean square error (RMSE), coefficient of determination (R2), and mean absolute percentage error (MAPE), to determine the predictive performance of the models. The results show that the GEP model achieved an R2 ranging from 0.944 572 to 0.992 999, with an RMSE between 0.015 527% and 0.694 523% and a MAPE ranging from 1.452 397% to 4.947 892%. ANFIS and ANN also demonstrated strong predictive capabilities, although GEP outperformed them. The importance of this study lies in its demonstration of advanced AI techniques as effective tools for optimizing machining processes, ultimately contributing to improved efficiency and quality in manufacturing superalloys. [ABSTRACT FROM AUTHOR]

The most widely used equation to calculate water saturation or suitable shaly water saturation in clean or shaly formation, respectively, is the modified Archie formula. The quality of Archie parameters including saturation exponent affects the preciseness of water saturation, and thus estimated oil and gas in place. Therefore, estimating the saturation exponent by the soft computation methods deems to be necessary. In this study, intelligent models such as multilayer perceptron neural network, least squares support vector machine, radial basis function neural network, and adaptive neuro-fuzzy inference system are developed to predict saturation exponent in terms of petrophysical data including porosity, absolute permeability, water saturation, true resistivity, and resistivity index by utilizing a databank for middle east oil and gas reservoirs. The introduced models are optimized using particle swarm optimization, genetic algorithm, and levenberg marquardt techniques. Graphical and statistical methods are used to demonstrate the capability of the constructed models. Based on the statistical indexes obtained for each model, it is found that radial basis function neural network, multilayer perceptron neural network, and least squares support vector machine are the most robust models as they possess the smallest mean squared error, root mean squared error and average absolute relative error as well as highest coefficient of determination. Moreover, the sensitivity analysis indicates that water saturation has the most effect and porosity has the least effect on the saturation exponent. The developed models are simple-to-use and time-consuming tools to predict saturation exponent without needing laboratory methods which are tedious and arduous. [ABSTRACT FROM AUTHOR]

Investigations on the properties of polycrystalline bulk and melt-spun ribbons of composition Ni50Mn29Ga21 are contrasted. Both samples are subjected to quenching after melting and then were homogenized at the same temperature. Though the electron per atom ratio is unchanged, the quenched-in disorder has caused the structural and magnetic transformations to occur in close proximity in the ribbon giving rise to magnetic entropy change of –9.2 J/kg-K at the martensitic transformation. The bulk alloy showed significantly high magnetic field-induced strain of 0.7% at 5 kOe magnetic field and an apparent compressive strain of 5.3% at 40 MPa compression stress, without training the sample. Large grain size and micro-twinning are observed in the bulk, while nano-scale twinning is seen in the ribbon. The variations in the process altered the degree of ordering, which modified the transformation temperatures, the crystal structure, the microstructures of the ribbon and the mechanical properties of the bulk specimen significantly. [ABSTRACT FROM AUTHOR]

Investigations on the properties of polycrystalline bulk and melt-spun ribbons of composition Ni50Mn29Ga21 are contrasted. Both samples are subjected to quenching after melting and then were homogenized at the same temperature. Though the electron per atom ratio is unchanged, the quenched-in disorder has caused the structural and magnetic transformations to occur in close proximity in the ribbon giving rise to magnetic entropy change of –9.2 J/kg-K at the martensitic transformation. The bulk alloy showed significantly high magnetic field-induced strain of 0.7% at 5 kOe magnetic field and an apparent compressive strain of 5.3% at 40 MPa compression stress, without training the sample. Large grain size and micro-twinning are observed in the bulk, while nano-scale twinning is seen in the ribbon. The variations in the process altered the degree of ordering, which modified the transformation temperatures, the crystal structure, the microstructures of the ribbon and the mechanical properties of the bulk specimen significantly. [ABSTRACT FROM AUTHOR]

Abstract: Investigations on Ni53.5Mn26.0Ga20.5B x system with x = 0, 0.5 and 1.0 show that boron addition does not alter the monoclinic crystal structure, but modifies the superstructural ordering of the boron-free parent compound. Observed reduction in the martensitic transformation temperature by nearly 30 K differs from the usual trend expected with a rise in electron concentration. Contrary to the reports on Ni–Mn–Ga alloys with boron substitution, saturation magnetization at low temperatures increases substantially (∼19% per formula unit) on boron addition. The observed large rise in magnetization is correlated to the compositional shift in the majority matrix phase caused by the secondary phase segregation at the grain boundaries, promoted by addition of B. Formation of Ni-rich secondary phase and the associated reduction in Ni content in the matrix phase results in redistribution of Mn atoms at Mn and Ga sites. This causes an effective change in the balance between Mn moments with ferro- and anti-ferromagnetic order in the unit cell, thus explaining the magnetic properties. [Copyright &y& Elsevier]

Abstract: Results from a systematic study of the effect of cobalt, selectively substituted for Ni and Mn, in the modulated orthorhombic (7M) Ni50Mn29Ga21 alloy are contrasted. Substitution of Co for Mn resulted in the stabilization of a non-modulated tetragonal (NM) phase at higher Co content. At lower Co contents, a mixture of 7M and NM phases were found to co-exist. Increasing in Co content caused suppression of long-range twin deformation leading to sporadic islands within which twin variants were confined. These effects are attributed to the considerable stresses generated by an atomic volume change of 9.5% caused locally when Co is substituted for Mn. On the other hand, substitution of Co for Ni, which causes only 1.7% atomic volume change locally, was observed not to alter either the superstructural ordering or the long-range twin deformation. Our results show that the microstructures resultant on Co doping have a strong correlation to the structural ordering, which in turn depends on whether Co is substituted for Mn or for Ni, and also on the concentration of Co. [Copyright &y& Elsevier]

We report a seven-layered modulated monoclinic crystal structure in the Ni-rich, Ga-poor Ni53.5Mn26.0Ga20.5 alloy. The present composition exhibits coupled magneto-structural transformation around 350K. Multi-mode twinning with a predominance of crossing twins, indicative of low residual stresses, is observed. A significant shape memory effect of 1.6% and a high strain recovery ratio of 89% are achieved in the polycrystalline specimen at low stresses, owing to lower twinning energies arising from lattice modulation. [ABSTRACT FROM AUTHOR]