Condition-based reliability prediction based on logical analysis of survival data
This paper presents a novel approach for incorporating condition information based on historical data into the development of reliability curves.
The approach uses a variation of Kaplan-Meier (KM) estimator and degradation-based estimators of survival patterns.
From a statistical perspective, the use of KM estimator to create a reliability curve of a specific type of equipment, results in a general curve that does not take into consideration the instantaneous condition of each individual equipment.
The proposed degradation-based estimator updates the KM estimator in order to capture the actual condition of equipment based on the detected patterns.
These patterns identify interactions between condition indicators.
The degradation-based reliability curves are obtained by a new methodology called `Logical Analysis of Survival Data (LASD).
LASD identifies interactions between condition indicators without any prior hypotheses.
It generates patterns based on machine learning and pattern recognition technique.
Using these set of patterns, survival curves, which can predict the reliability of any device at any time based on its actual condition, are developed.
To evaluate the LASD approach, it was applied to experimental results that represent cutting tool degradation during turning TiMMCs with condition monitoring.
The performance of the LASD when compared to the traditional Kaplan-Meier based reliability curve improves the reliability prediction.