The Smart Self Aware Manufacturing Machine (SSAMM)

.This STTR Phase II project will build digital engineering solutions to create the next generation smart, self-aware manufacturing machine (SSAMM). Developed digital solutions will push the boundary of sustainment beyond condition-based maintenance that has minimal predictive capacity, and predictive maintenance that cannot deliver specified accuracy without protracted tuning that diminishes its scalability.  This project aims to achieve four clear technical objectives for SSAMM: Create a comprehensive digital twin map for the next-gen smart manufacturing machine composed of a mixture of physics-based and data-driven models; Employ machine learning tools to build and continuously improve data-driven evolutionary models and integrate them with the digital twin; Integrate the SSAMM digital twin with PointPro’s Adaptive Monte Carlo forecasting engine to create trustworthy prognostics for performance optimization and failure prediction; and Certify digital twin models through robust verification and validation methods. Research and development efforts in this Phase II project will employ cutting edge machine learning tools based on Koopman operator theory and reduced order modeling to transform multimodal IoT data, i.e., “observables”, into system evolutionary models. These models will feed our proprietary closed-loop adaptive simulation platform to generate sub-system and system level forecasts with guaranteed accuracy in the prediction of user-defined quantities of interest. No other existing forecasting platform possesses this salient feature, which anchors the notion of trustworthiness in prognosis. This feature also successfully isolates epistemic uncertainty in the evolutionary models, allowing the PointPro platform to be used for model robustness analysis. To close the loop on the trustworthy digital surrogate, trustworthiness indicators of forecasting outcomes will create error signals that will drive continuous improvement of data-driven and physics-based evolutionary models, leading to their certification.  Downstream analytical tools translate forecasts into system level actionable intelligence for each of prognosis, reconfiguration, and optimized scheduling. In essence, this project combines a model-based systems engineering approach with state-of-the-art uncertainty quantification tools for trustworthy actionable intelligence for repair management and production plan optimization. These are central features of a self-aware, smart manufacturing machine and eliminate the cost of unnecessary repairs while optimizing the production line. The Phase II Project tasks will align with efforts at the 402 Commodities Maintenance Group (CMXG) at Warner Robins Air Logistics Complex build out the CMXG Digital Enterprise.