Automobile Maintenance Prediction Using Deep Learning with GIS Data

Predictive maintenance is of importance to various industries. Fleet management can be beneficial if the time-between-failures (TBF) of an automobile can be predicted. Conventionally, the prediction models in predictive maintenance are established using historical maintenance data or sensor data. In...

Full description

Saved in:
Bibliographic Details
Published in:Procedia CIRP 2019, Vol.81, p.447-452
Main Authors: Chen, Chong, Liu, Ying, Sun, Xianfang, Cairano-Gilfedder, Carla Di, Titmus, Scott
Format: Article
Language:English
Subjects:
data mining
deep learning
GIS
predictive maintenance
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Predictive maintenance is of importance to various industries. Fleet management can be beneficial if the time-between-failures (TBF) of an automobile can be predicted. Conventionally, the prediction models in predictive maintenance are established using historical maintenance data or sensor data. In the era of big data, the availability of data has been significantly increased. This study aims to introduce geographic information systems data into TBF modelling and research their impact on automobile TBF using deep learning. An experimental study based on real-world maintenance data reveals that the performance of deep neural network improved with the help of GIS data.
ISSN:2212-8271
2212-8271
DOI:10.1016/j.procir.2019.03.077