.png){kind=icon}
.png){kind=icon}
Return
A causal inference-based root cause analysis framework using multi-modal data in large-complex system
.png){kind=icon}
PRE
AI
DOI：10.1016/j.ress.2025.111520.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Root cause analysis is crucial for ensuring the safe and reliable operation of the system. At present, root cause analysis for complex systems mostly relies on single-modal data. However, root cause analysis using single-modal data cannot provide comprehensive root cause information. To address this issue, we propose a causal inference-based root cause analysis framework using multi-modal data. This framework is based on causal inference and deeply integrates both table data and log data generated in complex system. It can not only identify the cause events of recorded events in the logs but also pinpoint the system variables that trigger the events and their specific values, providing accurate guidance to prevent the recurrence of these events. The proposed framework is validated on an unmanned swarm complex system and a simulated industrial transportation system, and is compared with the latest multi-modal root cause analysis methods. The experimental results demonstrate the superiority of the proposed approach.
Keywords:
causal inference
root cause analysis
multi-modal data
complex systems
system reliability
Journal
R
IF:
11
Papers:
9.0K
Citations:
4.2W