PointPro, Inc

PointPro, Inc. offers a computational platform that performs adaptive, closed-loop predictive simulations in order to support the Air Force in its sustainment operations. The future of sustainment is in prescriptive analytics: predicting what will fail, when & how it will fail, and, what can be done about it?

Prescriptive analytics demands timely, accurate forecasts of a system’s path to failure. PointPro builds on the user’s digital twin physics-based models to deliver forecasts within user defined accuracy. Our software leverages the time-tested robustness and versatility of Monte Carlo simulations in a closed-loop architecture, making it possible to deliver guaranteed accuracy in the forecast of system specific quantities of interest. When prediction errors are detected to exceed user-defined bounds, a sequence of optimization problems are solved, that in effect answer a long-standing question in predictive simulation: to meet a required level of accuracy, how big should the simulation size be? Consequently, a decision-quality, certifiably actionable forecast is generated in a single-shot, in minimal time. The platform integrates equally with physics-based evolutionary models and with data-driven (ML) models; and offers means to improve such models. In benchmark studies conducted so far, up to 3x productivity gain has been demonstrated. Moreover, gains improve with increasing system complexity.

In this Phase I STTR, a feasibility study is proposed to elicit feedback from SMEs regarding PointPro use for forecasting complex systems. In particular, the project will focus on optimized asset sustainment needs for USAF jet engines and space assets. We intend to support existing predictive maintenance needs and accelerate prescriptive maintenance capabilities. Feedback related to specific users, applications, and necessary additions to the software will serve as a workplan for further work.

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: 1). Create a comprehensive digital twin map for the next-gen smart manufacturing machine composed of a mixture of physics-based and data-driven models; 2). Employ machine learning tools to build and continuously improve data-driven evolutionary models and integrate them with the digital twin; 3). Integrate the SSAMM digital twin with PointPro’s Adaptive Monte Carlo forecasting engine to create trustworthy prognostics for performance optimization and failure prediction; and 4). 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.