An integrated deep learning-based approach for automobile maintenance prediction with GIS data

• An automobile RUL prediction model with GIS data through a data-driven approach is established. A integration scheme was researched to handle the discrepancy of type and sampling rates. Cox proportional hazard introduced construct health index for integrated maintenance data. deep learning structure called M-LSTM network designed modelling. The mapped by predicted model. Using sizable real-world fleet revealed effectiveness impact factors on RUL. Predictive (PdM) can be beneficial industry in terms lowering cost improve productivity. Remaining useful life (RUL) an important task PdM. impacted various surrounding such as weather, traffic terrain, which captured geographical information system (GIS). Recently, most researchers have conducted studies modelling based sensor Owing fact that collection expensive, while relatively easy obtain. This study aims establish approach. In this approach, firstly, due rate are different, researched. Secondly, (Cox PHM) (HI) Then, (Merged-long-short term memory) HI contains both sequential ordinary numeric Finally, PHM. experimental using dataset provided UK company proposed automobiles under investigation.