Abstract

The implementation of Artificial Intelligence (AI) systems in the manufacturing domain enable higher production efficiency, outstanding performance, and safer operations, leveraging powerful tools such as deep learning and reinforcement learningtechniques.Despitethe highaccuracy ofthesemodels,theyaremostly considered black boxes: they are unintelligible to the human. Opaqueness affects trust in the system, a factor that is critical in the context of decision-making. We presentan overview ofExplainableArtificialIntelligence(XAI)techniques asameans of boosting the transparency of models. We analyze different metrics to evaluate these techniques and describe several application scenarios in themanufacturing domain.