Artificial Intelligence Assisted Social Failure Mode and Effect Analysis (FMEA) for Sustainable Product Design

Nowadays, the social dimension of product sustainability is increasingly in demand, however, industrial designers struggle to pursue it much more than the environmental or economic one due to their unfamiliarity in correlating design choices with social impacts. In addition, this gap is not filled even by the supporting methods that have been conceived to only support specific areas of application. To fill this gap, this study proposed a method to support social failure mode and effect analysis (SFMEA), though the automatic failure determination, based on the use of a chatbot (i.e., an artificial intelligence (AI)-based chat). The method consists of 84 specific questions to ask the chatbot, resulting from the combination of known failures and social failures, elements from design theories, and syntactic structures. The starting hypothesis to be verified is that a GPT Chat (i.e., a common AI-based chat), properly queried, can provide all the main elements for the automatic compilation of a SFMEA (i.e., to determine the social failures). To do this, the proposed questions were tested in three case studies to extract all the failures and elements that express predefined SFMEA scenarios: a coffee cup provoking gender discrimination, a COVID mask denying a human right, and a thermometer undermining the cultural heritage of a community. The obtained results confirmed the starting hypothesis by showing the strengths and weaknesses of the obtained answers in relation to the following factors: the number and type of inputs (i.e., the failures) provided in the questions; the lexicon used in the question, favoring the use of technical terms derived from design theories and social sustainability taxonomies; the type of the problem. Through this test, the proposed method proved its ability to support the social sustainable design of different products and in different ways. However, a dutiful recommendation instead concerns the tool (i.e., the chatbot) due to its filters that limit some answers in which the designer tries to voluntarily hypothesize failures to explore their social consequences.