Failure time prediction using adaptive logical analysis of survival curves and multiple machining signals

This paper develops a prognostic technique called the logical analysis of survival curves (LASC). This technique is used to learn the degradation process of any physical asset, and consequently to predict its failure time ( T ). It combines the reliability information that is obtained from a classical Kaplan–Meier non-parametric curve to that obtained from online measurements of multiple sensed signals of degradation. An analysis of these signals by the machine learning technique, logical analysis of data (LAD), is performed to exploit the instantaneous knowledge about the state of degradation of the asset studied. The experimental results of the predictions of failure times for cutting tools are reported. The results show that LASC prognostic results are better than the results obtained by well-known machine learning techniques. Other advantages of the proposed techniques are also discussed.