Hierarchical cognize framework for the multi-fault diagnosis of the interconnected system based on domain knowledge and data fusion

作者：

Highlights：

• A novel 3-level multi-fault cognitive framework is proposed.

• Three mechanisms of knowledge-data fusion in diagnosis are summarized.

• The complex mappings among data, sensors, and fault modes are clearly depicted.

• The verification cases show that the proposed HCF can achieve better results.

摘要

•A novel 3-level multi-fault cognitive framework is proposed.•Three mechanisms of knowledge-data fusion in diagnosis are summarized.•The complex mappings among data, sensors, and fault modes are clearly depicted.•The verification cases show that the proposed HCF can achieve better results.

论文关键词：Hierarchical cognize framework (HCF),Multi-fault diagnosis (MFD),Experience fused self-adaption Gaussian mixture model (EFSA-GMM),Fault coding,Domain knowledge and data fusion,Sensor data

论文评审过程：Received 2 August 2021, Revised 31 October 2021, Accepted 1 January 2022, Available online 6 January 2022, Version of Record 10 January 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.116503