New benchmark dataset driven reconfiguration path optimization for smart RMT using NSGA-Ⅲ

In industry 4.0/5.0 era, the demand becomes more uncertain, which requires smarter and more flexible manufacturing systems. Reconfigurable manufacturing systems (RMS) is a typical paradigm for dealing with demand changes supporting by reconfigurable machine tools (RMT). Recently, smart RMS (SRMS) as the evolution version of RMS driven by new technologies (Digital twin, AI, etc.) was proposed. Reconfiguration remains one of the core research topics in RMS/SRMS, yet the lack of empirical reconfiguration data has significantly limited progress. Therefore, this study constructs a new benchmark dataset of RMT reconfiguration times based on desktop-level RMT suites. While this dataset is not a direct representation of industrial-scale RMTs, it provides a valuable initial reference and foundation for subsequent optimization research. And then, a reconfiguration path optimization problem of SRMS with RMTs is investigated based on the proposed benchmark dataset, which the number of RMTs, the reconfiguration time and the cost of reconfiguration and RMT investment are selected as optimization objectives. The NSGA-Ⅲ algorithm is employed to solve the problem, leveraging its advantage in maintaining solution diversity in high-dimensional objective spaces. Moreover, a case study is provided to implement the proposed benchmark dataset and reconfiguration path optimization method. The results highlight not only the effectiveness of the optimization approach but also the potential and limitations of applying the constructed dataset, paving the way for future validation in industrial-scale SRMS.