Anomaly Detection for Complex Systems

In performance maintenance in large, complex systems, sensor information from sub-components tends to be readily available, and can be used to make predictions about the system's health and diagnose possible anomalies.

However, existing methods can only use predictions of individual component anomalies to guess at systemic problems, not accurately estimate the magnitude of the problem, nor prescribe good solutions.

Since physical complex systems usually have well-defined semantics of operation, we here propose using anomaly detection techniques drawn from data mining in conjunction with an automated theorem prover working on a domain-specific knowledge base to perform systemic anomalydetection on complex systems.

For clarity of presentation, the remaining content of this submission is presented compactly in Fig 1.