Interpretable logic tree analysis: A data-driven fault tree methodology for causality analysis

作者：

Highlights：

• Interpretable logic tree extracts relevant root causes for an efficient diagnosis.

• Knowledge discovery in dataset reveals hidden root causes within the system.

• Deductive analysis from root causes to top event enriches the expert's knowledge.

• Probabilistic rules control the system state by tuning the effect of its root causes.

摘要

•Interpretable logic tree extracts relevant root causes for an efficient diagnosis.•Knowledge discovery in dataset reveals hidden root causes within the system.•Deductive analysis from root causes to top event enriches the expert's knowledge.•Probabilistic rules control the system state by tuning the effect of its root causes.

论文关键词：Causality analysis,Fault tree analysis (FTA),Knowledge discovery in database (KDD),Decision support system (DSS)

论文评审过程：Received 19 February 2019, Revised 12 June 2019, Accepted 20 June 2019, Available online 22 June 2019, Version of Record 2 July 2019.

论文官网地址：https://doi.org/10.1016/j.eswa.2019.06.042