Task-driven manufacturing cloud service proactive discovery and optimal configuration method

Cloud manufacturing (CMfg) is emerging as a promising manufacturing paradigm, which can realize and provide distributed and heterogeneous manufacturing resources as services for all phases of the product lifecycle. A task-driven manufacturing cloud service (MCS) proactive discovery and optimal configuration method is presented in this paper to realize full-scale sharing, on-demand use, and collaborative configuration of manufacturing resources in CMfg. In this research, two kinds of resources, including manufacturing machine and manufacturing cell (MC), are viewed as a breakthrough point of the investigation of multi-granularity resource configuration process. During resource modeling, advanced information and sensor technologies are adopted to construct the information models of resources, which consist of static attributes, real-time manufacturing data, and evaluation information. It makes the traditional production process more transparent, traceable, and on-line controllable. By applying the service proactive discovery mechanism, service providers rapidly respond to task requirements on the basis of real-time status and submit requests to perform tasks proactively. Hence, the responsiveness and initiative of service providers are highly enhanced. Consequently, the efficient discovery of potential services can be achieved. In service configuration process, a scientific evaluation system is established to perform the comprehensive assessment of services. Then, through the evaluation method based on grey relational analysis (GRA), the service optimal configuration is implemented. Finally, the effectiveness of proposed models and methods is validated by a case study.