This webinar addresses the design, testing, and evaluation of an integrated and holistic framework for integrity management of manufacturing components/systems/processes seeking to improve productivity and product quality while reducing the logistics footprint. Traditional maintenance practices in government and industry have been mostly reactive in addressing needs for “fix it when broken” or “fix it in so many hours.” As the complexity of legacy and new equipment/facilities has increased substantially in recent years, a paradigm shift is occurring toward “fix it only when needed.” Recent advances in condition-based maintenance and prognostics and health management, as well as parallel advances in sensing, computing, and communications, motivate the development and implementation of innovative artificial intelligence (AI), machine learning (ML), and data analytics technologies on the manufacturing floor.
We introduce a novel approach to predictive maintenance of complex manufacturing processes exploiting AI and ML tools/methods and a novel reasoning paradigm called Dynamic Case-Based Reasoning, where reasoning, learning, and adaptation attributes contribute to a holistic and integrated predictive maintenance framework.