IoT Equipment Relationship Discovery Through Event Synchrony
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Automated industrial and commercial environments often have inaccessible Programmable Logic Controller (PLC) logic, making it difficult to understand the relationships between IoT devices and components, requiring manual reverse engineering which is time-consuming and inefficient.
Innovation Solution
A platform and method that automatically identifies, monitors data sources, detects events, and determines relationships between IoT devices by using data source discovery, event detection, synchrony detection, and machine learning mechanisms to identify relationships quickly and accurately.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If manual reverse engineering is used to understand relationships between IoT devices, then comprehensive relationship understanding can be achieved, but the process becomes extremely time-consuming and labor-intensive
Solution Approach 1:
The patent replaces manual reverse engineering processes with automated computational methods. Machine learning algorithms analyze event logs and sensor data to automatically discover relationships between IoT devices, substituting human analysts with computational systems that can process data much faster and at lower cost while maintaining comprehensive relationship understanding.
Solution Approach 2:
The system enables self-service relationship discovery by automatically analyzing its own operational data. The IoT infrastructure uses its own event logs and sensor readings to autonomously map device relationships without requiring external manual intervention, making the discovery process self-sustaining and continuously improving over time.
2Ease of operation
If PLC logic is made accessible for analysis, then relationship discovery is simplified, but security and job protection concerns are compromised
Solution Approach 1:
The patent introduces an intermediary layer that sits between the PLC logic and the analysis tools. Instead of directly accessing protected PLC code, the system uses intermediate event logs and sensor data that indirectly reveal device relationships. This intermediary approach allows relationship discovery while maintaining security boundaries and protecting proprietary control logic.
Solution Approach 2:
Rather than accessing the original PLC logic directly, the system creates and analyzes copies of operational data such as event logs and sensor readings. These copies contain sufficient information to infer device relationships without requiring access to the actual PLC code, thus preserving security while enabling analysis.
3Productivity
If automated discovery methods are implemented, then relationship identification speed increases, but system complexity and computational requirements increase
Solution Approach 1:
The patent segments the relationship discovery process into distinct modular components: data collection from sensors, event log analysis, relationship inference algorithms, and result visualization. This segmentation allows each component to be independently optimized and managed, reducing overall system complexity while maintaining high discovery speed through specialized processing at each stage.
Data Source
AI summary
Described are platforms, systems, and methods to discover relationships among equipment in automated industrial or commercial environments by looking for synchrony in state changes among the equipment. The platforms, systems, and methods identify a plurality of data sources associated with an automation environment; detect one or more events or one or more state changes in the data sources; store the detected events or state changes; detect synchrony in the detected events or state changes by performing operations comprising: identifying combinatorial pairs of data sources having an event or state change within a predetermined time window; and conducting pairwise testing for each identified combinatorial pair of data sources by applying an algorithm to the stored detected events or state changes; and determine one or more relationships for at least one identified combinatorial pair of data sources.