Application of knowledge transfer to ML-based quality decision support practice in the steel manufacturing process

The aim of our research is the enhancement of decision support methods grounded in statistical quality control. In our study we combine machine learning classifiers, and explanatory algorithms (XAI) with the Six Sigma practice to automate the evaluation of quality of steel products and determine origins of their defects. We use knowledge transfer to expand the available set of quality information in order to create explanations that are easier to interpret, especially without detailed knowledge of the data. We describe our original method, and provide evaluation of the results with real–life data from our industrial partner.