Predictive Maintenance with Machine Learning on Oracle Database 20c

According to McKinsey's study "Visualizing the uses and potential impact of AI and other analytics", 2018, the estimated impact of artificial intelligence and other analytics on all industries regarding anomaly detection is between $1.0T and $1.4T. Anomaly detection is the critical success factor in predictive maintenance, which tries to anticipate when maintenance is required. This differs from the classical preventive approach, in which activities are planned on a regularly scheduled basis, or condition-based maintenance activities, in which assets are monitored through IoT sensors. Applying anomaly detection algorithms based on machine learning, it's possible to perform prognostics to estimate the condition of a system or a component and its remaining useful life (RUL), in order to predict an incoming failure. One of the most famous algorithms is the MSET-SPRT, well-described with a use case in this blog post: "Machine Learning Use Case: Real-Time Support for Engineered Systems."