Failure Knowledge Graphs

Abstract

Failure analysis is the cornerstone of asset management via life-cycle costs optimizations. Knowledge graphs are semantic nets that are the next level of database technology. Machine learning (ML) is a field of inquiry devoted to understanding and building methods that “learn”, that is, methods that leverage data to improve performance on some set of tasks. We propose to structure the machine learning data into knowledge graphs to foster advanced failure analysis leveraging optimum life-cycle costs where costs are considered in the largest possible sense including the cost of human life preservation (safety) and the cost (impact) on the environment.