The invention discloses a manufacturing
system sustainability evaluation and improvement method based on data driving, and belongs to the technical field of manufacturing
system sustainability evaluation and improvement, and the method specifically comprises the steps: S1, obtaining a process yield and
material consumption data, and constructing an environment load rate based on the
material consumption data and a preset energy value conversion rate
database; s2, obtaining
photoresist sensitivity and production takt conformity, and establishing a
nonlinear coupling relationship model for representing a
coupling relationship between a process yield and an environmental load rate; establishing a
sustainability index obtained by calculating the energy value output rate and the environment load rate; s3, constructing a digital twinborn model which takes the controllable process parameters as input and outputs the predicted process yield and the predicted environmental load rate; the optimal process parameters used for maximizing the sustainability index are solved through a
reinforcement learning decision engine, a process formula is generated to achieve closed-
loop control, and the problem that the multi-dimensional performance cannot be comprehensively evaluated through a traditional method is solved.