Search for: All records

The future of intelligent manufacturing machines involves autonomous selection of process parameters to maximize productivity while maintaining quality within specified constraints. To effectively optimize process parameters, these machines need to adapt to existing uncertainties in the physical system. This paper proposes a novel framework and methodology for feedrate optimization that is based on a physics-informed data-driven digital twin with quantified uncertainty. The servo dynamics are modeled using a digital twin, which incorporates the known uncertainty in the physics-based models and predicts the distribution of contour error using a data-driven model that learns the unknown uncertainty on-the-fly by sensor measurements. Using the quantified uncertainty, the proposed feedrate optimization maximizes productivity while maintaining quality under desired servo error constraints and stringency (i.e., the tolerance for constraint violation under uncertainty) using a model predictive control framework. Experimental results obtained using a 3-axis desktop CNC machine tool and a desktop 3D printer demonstrate significant cycle time reductions of up to 38% and 17% respectively, while staying close to the error tolerances compared to the existing methods. 

Over the years, Internet of Things (IoT) devices have become more powerful. This sets forth a unique opportunity to exploit local computing resources to distribute model learning and circumvent the need to share raw data. The underlying distributed and privacy-preserving data analytics approach is often termed federated learning (FL). A key challenge in FL is the heterogeneity across local datasets. In this article, we propose a new personalized FL model, PFL-DA, by adopting the philosophy of domain adaptation. PFL-DA tackles two sources of data heterogeneity at the same time: a covariate and concept shift across local devices. We show, both theoretically and empirically, that PFL-DA overcomes intrinsic shortcomings in state of the art FL approaches and is able to borrow strength across devices while allowing them to retain their own personalized model. As a case study, we apply PFL-DA to distributed desktop 3D printing where we obtain more accurate predictions of printing speed, which can help improve the efficiency of the printers.