Search

We propose a novel technique to accurately predict carbon dioxide (CO2) concentrations even in flow fields with temperature gradients based on a single laser path absorption spectrum measurement and machine learning. Concentration measurements in typical tunable diode laser absorption spectroscopy are based on a ratio of two integrated absorbances, each from a spectral line with different temperature dependence. However, the inferred concentrations can deviate significantly from the actual concentrations in the presence of temperature gradients. Furthermore, it is also difficult to find an analytical expression to compensate for the effect of nonuniform temperature profiles on concentration measurements. In this study, the entire absorption feature was considered since its shape and peak intensities vary with temperature and concentration. Specifically, a predictive model is obtained in a data-driven manner that can identify and compensate for the effect of a nonuniform temperature field on the spectrum. Despite a very detailed understanding of the CO2 absorption spectrum, it is nearly impossible to collect sufficient spectra for model acquisition by varying all temperature gradient conditions. Therefore, the model was obtained using only simulated data, much like the concept of a "digital twin". Finally, the predictive performance of the acquired model was verified using experimental data. In all test cases, the predictive performance of the model was superior to that of the two-line method. Additionally, a gradient-weighted regression activation mapping analysis confirmed that the model utilizes both the peak intensities as well as the change in the shape of absorption lines for prediction. Graphical Abstract This is a visual representation of the abstract. [ABSTRACT FROM AUTHOR]

This review article provides a critical assessment of the progress made in computational modelling of metal-based additive manufacturing (AM) with emphasis on its ability to predict physical phenomena, concepts of microstructural evolution, residual stresses, role of multiple thermal cycles, and formation of multi-dimensional defects along with the achieved degree of experimental validation. The uniqueness of this article stems from the inclusion of comprehensive information on computational progress in the field of fusion-based, sintering-based, and mechanical deformation-based AM. A computational model's role in determining the process framework for the desired outcome of the set properties of the AM components is recognised while presenting the process-microstructure maps, thereby appraising computational ability towards the qualification of products. The inclusion of a detailed discussion on the bi-directional coupling of machine learning and physics-based computational models provides a futuristic roadmap for the digital twin of metal-based AM. [ABSTRACT FROM AUTHOR]