Condition monitoring of milling tools is crucial to achieve autonomous and resource-efficient production. It is, however, a challenging task due to the dynamic nature of the cutting process and the complex wear mechanisms. The majority of existing approaches is relying on data that is only accessible through additional instrumentation, such as cutting forces. Furthermore, high frequency data is often required. The current paper presents a novel approach for condition monitoring of milling tools using low-frequency machine-tool data. For the industrial-scale milling of titanium alloy, a decrease in signal roughness in servo-motor torque data is identified through exploratory data analysis. As a consequence, we propose a condition monitoring strategy that uses fractal analysis to quantify this effect. A threshold was set for the moving range of the fractal dimension to detect a significant drop and recommend tool exchange. For several milling experiments under identical conditions, tool exchange was recommended by our approach when the cutting tool is subject to significant damage, as documented in microscopy images, demonstrating consistency and robustness of the proposed approach. Additionally, only data stemming from sensors installed in standard machine tools in a relatively low frequency is required, leading to high industrial applicability.
Machine-learning potentials (MLIPs) have been a breakthrough for computational physics in bringing the accuracy of quantum mechanics to atomistic modeling. To achieve near-quantum accuracy, it is necessary that neighborhoods contained in the training set are rather close to the ones encountered during a simulation. Yet, constructing a single training set that works well for all applications is, and likely will remain, infeasible, so, one strategy is to supplement training protocols for MLIPs with additional learning methods, such as active learning, or fine-tuning. This strategy, however, yields very complex training protocols that are difficult to implement efficiently, and cumbersome to interpret, analyze, and reproduce. To address the above difficulties, we propose AutoPot, a software for automating the construction and archiving of MLIPs. AutoPot is based on BlackDynamite, a software that operates parametric tasks, e.g., running simulations, or single-point ab initio calculations, in a highly-parallelized fashion, and Motoko, an event-based workflow manager for orchestrating interactions between the tasks. The initial version of AutoPot supports selection of training configurations from large training candidate sets, and on-the-fly selection from molecular dynamics simulations, using Moment Tensor Potentials as implemented in MLIP-2, and single-point calculations of the selected training configurations using VASP. Another strength of AutoPot is its flexibility: BlackDynamite tasks and orchestrators are Python functions to which own existing code can be easily added and manipulated without writing complex parsers. Therefore, it will be straightforward to add other MLIP and ab initio codes, and manipulate the Motoko orchestrators to implement other training protocols.
The nickel-based superalloys are used in the field of hydrogen storage and transport where cryogenic temperatures are often required. The combined influence of hydrogen and cryogenic temperatures on their mechanical performance remains largely unexplored. In this work, the fracture behavior of alloy 718 was investigated using a slow strain rate testing (SSRT). The results at room temperature (RT) with and without previous gaseous hydrogen charging have been compared to the SSRT results obtained at 4.2 K using the same testing procedure. The findings show a pronounced embrittling effect due to hydrogen at room temperature, whereas no embrittlement was observed at cryogenic temperatures, which is attributed to limited hydrogen diffusivity at 4.2 K.
In this work we develop a bainite model which can describe bainite formation for arbitrary cooling conditions. To investigate the influence of carbon on bainite formation, the model is applied to a set of steels with different carbon concentrations and heat treatments. For the investigated steels the T0 ' temperature and the prior austenite grain size are measured and used in the calculation. The redistribution of carbon is considered and the respective parameters are given a carbon dependency. The efforts to get a consistent set of parameters are laid out. The calculations for isothermal bainite formation and bainite formation upon continuous cooling are compared to data from dilatometer and XRD measurements.
