Deep understanding in industrial processes by complementing human expertise with interpretable patterns of machine learning

作者：

Highlights：

• The paper combines domain knowledge (DK) with machine learning (ML).

• Patterns of logical analysis of data (LAD) are used by experts to enrich the DK.

• The LAD patterns identify fault causes that are not represented in the DK.

• The identified causes are used to enrich the fault trees in industrial plants.

摘要

•The paper combines domain knowledge (DK) with machine learning (ML).•Patterns of logical analysis of data (LAD) are used by experts to enrich the DK.•The LAD patterns identify fault causes that are not represented in the DK.•The identified causes are used to enrich the fault trees in industrial plants.

论文关键词：Fault detection and diagnosis (FDD),Logical analysis of data (LAD),Fault tree analysis (FTA),Machine learning and pattern recognition,Causality analysis

论文评审过程：Received 28 September 2018, Revised 7 December 2018, Accepted 4 January 2019, Available online 6 January 2019, Version of Record 15 January 2019.

论文官网地址：https://doi.org/10.1016/j.eswa.2019.01.011