A prescriptive analysis tool for improving manufacturing processes

Recently more digital twins have been developed and used in the manufacturing industry. Some are based on detailed models of a particular machine/process oriented to monitoring, but others can represent a full manufacturing plant for production planning. These models involve a lot of parameters, and it is not easy to evaluate the effect of their change in the manufactured product or how they are correlated among them. This paper presents a prescriptive analysis tool that allows testing and ranking multiple scenarios using a previously generated digital twin. This is thus, a simulation, evaluation, and prescription tool. It uses a set of available models, allowing the selection of the parameters and defining the scenarios to be simulated, as well as the evaluation configuration. The tool performs exhaustive simulations making initially all possible combinations of the parameters selected and obtaining the simulation results for each of them. After this the evaluation is performed over some of the outputs of the model, leading to a ranking of all the simulations. The prescription obtained can be later used to configure a machine or to change some production parameters to optimize the system