Predictive maintenance solution for industrial systems -- an unsupervised approach based on log periodic power law
This addresses maintenance prediction for industrial equipment, but appears incremental as it adapts an existing renormalization group approach to a new application.
The paper tackles predictive maintenance for industrial systems by proposing an unsupervised method based on the Log Periodic Power Law to detect critical points in time series data, applied to reciprocating compressor systems to predict valve and piston rod seal failures in advance.
A new unsupervised predictive maintenance analysis method based on the renormalization group approach used to discover critical behavior in complex systems has been proposed. The algorithm analyzes univariate time series and detects critical points based on a newly proposed theorem that identifies critical points using a Log Periodic Power Law function fits. Application of a new algorithm for predictive maintenance analysis of industrial data collected from reciprocating compressor systems is presented. Based on the knowledge of the dynamics of the analyzed compressor system, the proposed algorithm predicts valve and piston rod seal failures well in advance.