Causal Graph Extraction From PLC Code for Root Cause Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Identifying causal relationships in industrial automation systems is challenging due to confounding variables, complex causal relationships, lack of experimental control, complexity, non-linearity, and hidden variables, which complicates determining the root cause of anomalies such as security breaches and unauthorized control modifications.
Innovation Solution
A system and method that extract and derive causal graph relationships directly from design sources like PLC code and digital twin models, generating dynamic and real-time causal graphs to provide a custom system view for root cause analysis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If historical data is used to determine probable causes of anomalies, then analysis can be performed without experimental control, but certainty of root cause identification is reduced and multiple remedial actions must be tried
Solution Approach 1:
The system performs preliminary parsing of design artifacts during the design phase to extract causal relationships before anomalies occur. This creates a pre-established causal model that can be immediately applied during anomaly analysis, eliminating the need for multiple remedial action attempts and providing certain root cause identification from the start.
Solution Approach 2:
The system creates a digital copy of the design artifact's causal structure by parsing PLC code, function block diagrams, and other design artifacts to generate a causal model that mirrors the actual system relationships. This copied causal structure enables precise root cause analysis without needing physical experimental control.
2Measurement precision
If design artifacts are parsed to extract causal relationships, then certain root cause identification is achieved, but processing complexity and computational requirements increase
Solution Approach 1:
The system extracts only the essential causal relationships from design artifacts by parsing PLC code, function block diagrams, and other artifacts to identify input-output relationships. This extraction process isolates the critical causal structure from the complex design documentation, achieving precise cause identification without requiring the full complexity of the original design system.
Solution Approach 2:
The system replaces manual analysis of design artifacts with automated computational parsing that uses string matching, pattern recognition, and data structure analysis. This substitution of mechanical/manual processes with computational methods reduces the perceived complexity while maintaining high precision in cause identification.
3Reliability
If real-time causal graphs are generated from design sources, then up-to-date causal insights are provided for security breach detection, but data processing time and computational resources increase
Solution Approach 1:
The system performs preliminary parsing of design artifacts and pre-generates the causal model structure during system initialization or design phase. This preliminary action creates a ready-to-use causal framework that can be rapidly updated with real-time data, reducing the time required for real-time security detection while maintaining high reliability.
Solution Approach 2:
The system implements dynamic causal graphs that can be efficiently updated in real-time as new data becomes available. The causal model is structured to allow incremental updates rather than complete regeneration, enabling the system to maintain current causal insights with minimal processing time while ensuring reliable security breach detection.
Data Source
AI summary
A system for providing causal graph relationships for industrial automation systems. The system receives a first input indicative of a selection of a design artifact associated with an industrial automation system having one or more industrial automation devices, where the design artifact defines an industrial automation project configured to control operations of the one or more industrial automation devices. In response to the first input, the system parses the design artifact to identify causal relationships between the one or more industrial automation devices, stores data indicative of the identified causal relationships in a database, and generates causal graphs based on the stored data. The system receives a second input indicative of a request to generate a custom view of the industrial automation system, and generates a custom view of the industrial automation system in response to the second input, where the custom view includes the causal graphs.