A comprehensive framework from real‐time prognostics to maintenance decisions

Studying the influence of imperfect prognostics information on maintenance decisions is an underexplored area. To bridge this gap, a new comprehensive support system proposed. First, survival theory-based module employing Weibull time-to-event recurrent neural network was deployed in which competence enhanced by predicting parameters failure distribution. In conjunction with this, predictive (PdM) planning model framed via trade-off between corrective and time lost due to PdM. This optimises based operational cost from historical data. The performance proposed framework demonstrated using experimental case study for cutting tools within manufacturing facility. Systematic sensitivity analysis provided, impact discussed. Results show that uncertainty about prediction declines as goes on, declines, timing becomes closer remaining useful life. expected, risk making wrong decision decreases over time.