Additive manufacturing is rapidly evolving and revolutionizing the fabrication of complex metal components with tunable properties. Machine learning and neural networks have emerged as powerful tools for process–property optimization in additive manufacturing. These techniques work well for the prediction of a single property but their applicability in optimizing multiple properties is limited. In the present work, an exclusive neural network is developed to demonstrate the potential of a single neural network in optimizing multiple part properties. The model is used to identify the optimal process parameter values for laser power, scan speed, and hatch spacing for the required surface roughness, relative density, microhardness, and dimensional accuracy in stainless steel parts. In-house-generated experimental data are used to train the model. The model has seven neurons in the hidden layer, which are selected using hyperparameter optimization. K-fold cross-validation is performed to ensure the robustness of the model, which results in a mean squared error of 0.0578 and R2 score of 0.59. The developed model is then used to predict the optimal process parameters corresponding to the user-required part properties. The model serves as a significant pre-processing step to identify the best parameters before printing, thus saving time and costs for repeated part fabrication. The study provides more insights into the usage of a single artificial neural network for the optimization of multiple properties of printed metal parts.
1 February 2020 in Materials Science and Engineering: A
Inconel 718 (IN718) is a nickel-based superalloy which is widely used in aerospace, oil, and gas industries due to its outstanding mechanical properties at high temperatures, corrosion, fatigue resistance, and excellent weldability. Selective laser melting (SLM), one of the most used powder-bed based methods, is being extensively used to fabricate functional IN718 components with high accuracy. The accuracy and the properties of the SLM fabricated IN718 parts highly depend on the process parameters employed during fabrication. Thus, depending on the desired properties, the process parameters for a given material need to be optimized for improving the overall reliability of the SLM devices. In this study, design of experiment (DOE) was used to evaluate the dimensional accuracy, composition, and hardness corresponding to the interaction between the SLM process parameters such as laser power (P), scan speed (v), and hatch spacing (h). Contour plots were generated by co-relating the determined values for each characteristic and the process parameters to improve the as-built characteristics of the fabricated IN718 parts and reduce the post-processing time. The outcome of this study shows a range of energy density values for the IN718 superalloy needed to attain optimal values for each of the analyzed characteristics. Finally, an optimal processing region for SLM IN718 fabrication was identified which is in accordance with the values for each characteristic mentioned in literature.
Inconel 718 is a nickel-based superalloy and an excellent candidate for the aerospace, oil, and gas industries due to its high strength and corrosion resistance properties. The machining of IN718 is very challenging; therefore, the application of additive manufacturing (AM) technology is an effective approach to overcoming these difficulties and for the fabrication of complex geometries that cannot be manufactured by the traditional techniques. Selective laser melting (SLM), which is a laser powder bed fusion method, can be applied for the fabrication of IN718 samples with high accuracy. However, the process parameters have a high impact on the properties of the manufactured samples. In this study, a prediction model is developed for obtaining the optimal process parameters, including laser power, hatch spacing, and scanning speed, in the SLM process of the IN718 alloy. For this purpose, artificial neural network (ANN) modeling with various algorithms is employed to estimate the process outputs, namely, sample height and surface hardness. The modeling results fit perfectly with the experimental output, and this consequently proves the benefit of ANN modeling for predicting the optimal process parameters.
Laser powder bed fusion (LPBF) is an emerging technique for the fabrication of triply periodic minimal surface (TPMS) structures in metals. In this work, different TPMS structures such as Diamond, Gyroid, Primitive, Neovius, and Fisher–Koch S with graded relative densities are fabricated from 316L steel using LPBF. The graded TPMS samples are subjected to sandblasting to improve the surface finish before mechanical testing. Quasi-static compression tests are performed to study the deformation behavior and energy absorption capacity of TPMS structures. The results reveal superior stiffness and energy absorption capabilities for the graded TPMS samples compared to the uniform TPMS structures. The Fisher–Koch S and Primitive samples show higher strength whereas the Fisher–Koch S and Neovius samples exhibit higher elastic modulus. The Neovius type structure shows the highest energy absorption up to 50% strain among all the TPMS structures. The Gibson–Ashby coefficients are calculated for the TPMS structures, and it is found that the C2 values are in the range suggested by Gibson and Ashby while C1 values differ from the proposed range.
13 October 2023 in Progress in Additive Manufacturing