Laser-based continuous monitoring and resolution of steel grades in sequence casting machines

• We performed a LIBS and ANN analysis on steels.
• We demonstrated that this combined approach can be successfully used for the determination of the slab/billet composition.
• We found that ANN significantly reduces the time of analysis, preserving at the same time the accuracy of the results.

Laser induced breakdown spectroscopy (LIBS) is a well-established technique for on-line industrial applications where robustness, stability, reliability, speed of analysis and operational availability are important topics to be taken into account. In this work, we propose an advanced methodology for in situ analysis of transition as-cast products during continuous casting with the purpose of improving the productivity and cost-efficiency in the fabrication of stainless steel and special steels. We have applied LIBS combined with Artificial Neural Network (ANN) for elemental analysis of casting steels. We have found that the quantitative determination of the material's composition across the slab/billet length is possible and that the intermediate chemical composition between sequential heats can be readily identified.