Correlating Internal and External Data Streams in Industrial Systems
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional industrial network systems struggle to synchronize and analyze internal and external data streams effectively, leading to inefficiencies in diagnostic and prognostic processes due to the lack of synchronization and manual deduction of relationships between these streams, which complicates management and delays corrective actions.
Innovation Solution
The system correlates synchronized internal and external data streams using a process trend component that employs heuristic models to predict outcomes and facilitate diagnostics, synchronizing timing and sequence relationships between events, and employs a coordination component to collect and analyze both data streams simultaneously, enabling timely and stringent control adjustments.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If internal and external data streams are collected independently using separate devices, then data collection coverage is comprehensive, but synchronization and correlation between streams become complex and manual
Solution Approach 1:
The patent combines internal data stream collection and external network traffic analysis into a single integrated device. The network interface card includes both a historian component for internal data and a traffic analyzer component for external network monitoring, eliminating the need for separate synchronization processes and manual correlation efforts between disparate systems.
Solution Approach 2:
The network interface card is designed with multi-functionality, serving both as an internal data acquisition device (historian) and an external network traffic analyzer. This universal device simultaneously captures process control data and network traffic data, providing comprehensive monitoring capabilities in a single platform.
2Measurement precision
If data streams are not synchronized, then collection independence is maintained, but timing relationships and sequence counting between events cannot be determined
Solution Approach 1:
The system implements a common timestamp mechanism that provides feedback timing information for both internal and external data streams. Each data packet from either source is tagged with a precise timestamp, enabling automatic correlation and sequence determination without manual intervention, while maintaining the independence of data collection processes.
3Productivity
If manual deduction of relationships between data streams is performed, then flexibility in analysis is maintained, but diagnostic and prognostic processes become inefficient and delayed
Solution Approach 1:
The system performs preliminary correlation of internal and external data streams by assigning common timestamps at the moment of data capture. This preliminary action establishes timing relationships and sequence information in advance, enabling immediate diagnostic and prognostic analysis without requiring time-consuming manual deduction when problems occur.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Systems and methods that correlate among disparate pieces of synchronized data, collected from an "internal" data stream (e.g., history data collected from an industrial unit) and an "external" data stream (e.g., traffic data on network services). A process trend component that determines/predicts an outcome of an industrial process and facilitates diagnostics/prognostics of an industrial system. Accordingly, relations among various parameters can be discovered (e.g., dynamically) and proper corrective adjustments supplied to the industrial process. Such enables a tight control and short reaction time to process parameters, and for a modification thereof