Failure Prediction Methodology for Improved Proactive Maintenance using Bayesian Approach

Abstract Failure prediction is essential for predictive maintenance due to its ability to prevent failure occurrences and maintenance costs. At present, mathematical and statistical modeling are the prominent approaches used for failure predictions. These are based on equipment degradation physical models and machine learning methods, respectively. None of these approaches ensures failure predictions well before their occurrence to provide sufficient time to treat potential causes pro actively. Therefore, in this paper, we present a Bayesian based methodology to learn and associate failure signatures with potential failure occurrences. In this approach, event driven maintenance data is used as symptoms which is aggregated on discretized intervals. The failures probabilities as predicted by the Bayesian network are plotted as temporal evolution. This is further exploited to extract either rules or patterns as failure signatures and critical regions. These are then used to monitor and predict the potential failure occurrences. The proposed methodology is tested on the data collected from a well reputed semiconductor manufacturer with promising results.