Abstract
The aim of this work is to investigate a simple on-line control methodology applicable to press hardening. Short production runs were performed in a laboratory plant, using a pyrometer to measure sheet and die temperatures with varying processing conditions. Sheets thus treated were studied in terms of microstructure and mechanical properties. Different closing die time and refrigeration conditions were employed to force OK and Not OK conditions. The experimental data including the process variables as a well as the resultant temperatures have been analysed and modelled by means of statistical analysis and Machine Learning algorithms, to discover hidden correlations that can lead to actionable predicting models. The results show a direct link of the final temperature with the microstructure and its hardness. The outcome of this paper can be used for efficient process design and detection of anomalous temperature meanwhile an industrial hot stamping process take part. In addition, the analysis performed can help productivity and quality assurance while leading towards a smarter and more efficient manufacturing scenario.
Export citation and abstract BibTeX RIS
Content from this work may be used under the terms of the Creative Commons Attribution 3.0 licence. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.