Automation Anomaly Root Cause Detection Using Event Correlation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing anomaly detection methods in automation systems fail to automatically identify the underlying causes of anomaly events, hindering effective root cause analysis.
Innovation Solution
A method and system that utilizes Fourier transforms, autocorrelation, and cross-correlation to analyze time-series data from multiple sensors, identifying periodicity and causal relationships between anomaly events, enabling automatic root cause analysis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If multiple separate systems (telephony, data, imaging, etc.) are used to monitor different aspects of a communication network, then comprehensive monitoring coverage is achieved, but system complexity and cost increase
Solution Approach 1:
The patent combines multiple previously separate monitoring systems (telephony, data, imaging, messaging, etc.) into a single unified communication network monitoring system. This consolidation maintains comprehensive monitoring coverage across all communication aspects while reducing system complexity by eliminating redundant infrastructure and simplifying system architecture.
Solution Approach 2:
The unified monitoring system is designed to perform multiple functions across different communication domains simultaneously. A single system can monitor voice calls, data transmissions, video conferences, instant messages, and other communication types using common core components, thereby achieving multi-functionality without proportionally increasing complexity.
2Measurement precision
If detailed analysis of all communication events is performed, then accurate cause determination is achieved, but processing time and computational resources increase
Solution Approach 1:
The system performs preliminary classification and filtering of communication events before detailed analysis. By pre-identifying anomaly types and prioritizing events based on severity indicators, the system prepares data in advance for targeted analysis, reducing the time required for thorough investigation while maintaining accuracy in cause determination.
Solution Approach 2:
The analysis process is segmented into multiple stages: initial event detection, classification by anomaly type, prioritization based on severity, and detailed cause analysis only for high-priority events. This segmentation allows the system to efficiently process large volumes of communication events by applying detailed analysis only where necessary, thereby reducing overall processing time while maintaining high accuracy for critical issues.
Data Source
Figure 1
Figure 2~3
Figure 4
AI summary
The invention relates to a method for evaluating at least one data set of at least one component of an automation system, characterized by the incorporation and/or execution of the following steps: determining an interval between two anomalous events in a first data set, said first data set comprising data based on at least one first component of the automation system, and determining repeating events which are spaced according to the interval in a second data set, said second data set comprising at least one second component of the automation system.