ICS Data Tap and Computational Twin for Predictive Maintenance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Industrial control systems (ICS) face challenges in providing comprehensive data to end users due to limited computing resources and design constraints, making it difficult to access and process additional information without affecting system operation, and existing solutions often result in inefficient data retrieval and high false positive maintenance alerts.
Innovation Solution
A network tap is used to extract I/O data from ICS controllers, which is processed by a computational twin to emulate the control code, allowing for faster and more comprehensive data analysis using modern hardware, combined with a digital twin for virtual representation, and a learned model to predict and prescribe maintenance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If data is extracted directly from ICS controllers, then data access is enabled, but system operation is affected due to limited computing resources
Solution Approach 1:
The system segments data extraction from ICS operation by using a network tap to capture data packets at the network level, separating the data collection function from the controller's processing functions. This allows comprehensive data access without burdening the controller's limited computing resources.
Solution Approach 2:
A network tap acts as an intermediary device that intercepts and copies data traffic between the ICS controller and the network. This intermediary enables data extraction without directly interfacing with or affecting the controller's operational integrity.
2Measurement precision
If comprehensive data analysis is performed using original control code, then accurate insights are achieved, but processing speed is limited by legacy hardware
Solution Approach 1:
The system creates a copy of the control code and runs it on a separate computational platform (cloud server or modern workstation). This copying enables comprehensive data analysis using the original logic while leveraging modern hardware capabilities for faster processing.
Solution Approach 2:
The analysis is moved from the original controller's time dimension to a separate computational dimension (cloud/server environment). This dimensional shift allows parallel processing and faster execution without constraining the original real-time control operations.
3Loss of information
If additional processing is added to ICS to provide more data, then data comprehensiveness is improved, but computing resource constraints are exceeded
Solution Approach 1:
The system extracts the data processing function from the ICS controller and relocates it to an external computational platform. The network tap extracts data packets, and the control code execution is extracted from the controller, enabling comprehensive data collection without adding processing complexity to the original system.
4Reliability
If maintenance monitoring is enhanced, then predictive capability is improved, but false positive alerts increase
Solution Approach 1:
The system performs preliminary analysis by executing the control code and simulating operational scenarios before actual maintenance events occur. This preliminary action establishes baseline behavior patterns, enabling more accurate detection of genuine anomalies and reducing false positives.
Data Source
AI summary
Some implementations of the disclosure are directed to a method including: receiving tapped data that was tapped from a controller of an industrial control system (ICS) while the controller controlled one or more ICS devices of the ICS, the tapped data comprising input data obtained from one or more input components of the controller communicatively coupled to the one or more ICS devices, or output data obtained from one or more output components of the controller communicatively coupled to the one or more ICS devices; and generating, using at least a trained model and the tapped data, a prediction output by the trained model that indicates a future failure of the ICS, a future maintenance event of the ICS, or a prescribed maintenance of the ICS.