Hybrid functional networks for oil reservoir PVT characterisation

作者：

Highlights：

• An intelligent system for grouping of crude oils is proposed.

• Hybrid K-means clustering and functional networks is used to predict PVT properties.

• PVT properties are predicted with hybrid K-means clustering and functional networks.

• The hybrid system outperforms all the compared existing methods.

摘要

•An intelligent system for grouping of crude oils is proposed.•Hybrid K-means clustering and functional networks is used to predict PVT properties.•PVT properties are predicted with hybrid K-means clustering and functional networks.•The hybrid system outperforms all the compared existing methods.

论文关键词：PVT,API gravity,Clustering,Functional networks,Neural network,Black oil

论文评审过程：Received 10 December 2016, Revised 9 May 2017, Accepted 9 June 2017, Available online 12 June 2017, Version of Record 30 June 2017.

论文官网地址：https://doi.org/10.1016/j.eswa.2017.06.014