PredictiveIQ was selected as a finalists in the CTMA Technology Competition for its pioneering technology in “Solving the Data Problem for Conditioned Based Maintenance Using Physics Informed Machine Learning.” CTMA is a Cooperative Agreement in partnership with the Office of Deputy Assistant Secretary of Defense, Materiel Readiness and NCMS. Its efforts focus on defense maintenance, sustainment, and logistics.
- Condition Based Maintenance Plus (CBM+) aims to increase combat power by ensuring materiel availability and readiness (CBM+ Brochure. 2010 OASDS). CBM+ shifts from reactive to proactive and predictive approach driven by condition sensing and integrated, analysis-based decisions (CBM+ DoD Guidebook. 2008 OASDS).
- Predictive Maintenance algorithms are not widely used due prohibitive computing power needs, accessibility, bandwidth, and storage issues (Digital Twin Technologies to Improve Mission Readiness and Sustainment. 2020 NAVAIR).
- Data is difficult and expensive to obtain since it needs to be collected, processed, transmitted, aggregated, cleaned, warehoused, post-processes, etc. (Army CBM+ Innovations. 2020 JTEG NCMS)
Having the right data at the right time is arguably one of the biggest obstacles to achieving the goals of CBM+.
Physics Informed Machine Learning or PIML transforms big data problems into small data by intelligently combining physics-based methods with machine learning techniques. The results are algorithms that use very little data, are very fast and accurate, can extrapolate its training data set, can provide diagnostics and finally can integrate different sources of data.
- Data Reduction: A 90%+ reduction in number of sensors, instrumentation, data storage, transmissions, required for predictive maintenance prognostics and diagnostic systems.
- Optimal planned maintenance scheduling.
- Reduction of unplanned maintenance events.
- Real-time monitoring and inflight servicing of equipment.
- Improved supply chain and inventory management.
- Reduction of spare parts requirements.