New XAI tools for selecting suitable 3D printing facilities in ubiquitous manufacturing

Abstract Several artificial intelligence (AI) technologies have been applied to assist in the selection of suitable three-dimensional (3D) printing facilities ubiquitous manufacturing (UM). However, AI applications this field may not be easily understood or communicated with, especially for decision-makers without relevant background knowledge, hindering widespread acceptance such applications. Explainable (XAI) has proposed address problem. This study first reviews existing XAI techniques explain selecting 3D UM. addresses deficiencies by proposing four new techniques: (1) a gradient bar chart with baseline, (2) group chart, (3) manually adjustable and (4) bidirectional scatterplot. The methodology was case literature demonstrate its effectiveness. scatterplot results from experiment demonstrated suitability terms their proximity. Furthermore, bars increased effectiveness application subjectively adjusting derived weights. only fulfilled most requirements an effective tool application.