IIoT Gateway Risk Prioritization for Industrial Facility Monitoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current automated systems monitoring industrial facilities with IIoT sensors and connected devices generate numerous irrelevant event indicators, alerts, or alarms, overwhelming personnel and constraining the number of sensors due to limited computational resources.
Innovation Solution
A distributed computing platform employing a gateway device that executes tasks to monitor alarms, identify risks, and dynamically construct causal networks for risk evaluation using behavior trees and causal Bayesian networks, optimizing sensor data analysis and resource allocation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If automated systems generate comprehensive event indicators and alerts from IIoT sensors, then monitoring coverage and detection capability are improved, but personnel are overwhelmed by low-relevance alerts and system complexity increases
Solution Approach 1:
The patent extracts and removes low-relevance alerts from the comprehensive set of event indicators generated by IIoT sensors. The system prioritizes and filters alerts to present only high-relevance information to personnel, thereby maintaining monitoring coverage while reducing the overwhelming effect of irrelevant notifications.
Solution Approach 2:
The patent segments the monitoring system into multiple functional layers: sensor data collection, event indicator generation, alert prioritization, and personnel notification. This segmentation allows comprehensive monitoring to continue at lower layers while only essential prioritized alerts are presented to personnel at the notification layer, reducing perceived complexity.
2Quantity of substance
If more IIoT sensors are deployed to increase monitoring capacity, then sensor coverage is improved, but computational resources are exceeded due to limited processing capability
Solution Approach 1:
The patent extracts only the essential and high-value sensor data for processing, rather than analyzing all data from all sensors equally. By identifying and processing only critical parameters and events, the system can support a larger number of sensors while consuming manageable computational resources.
Solution Approach 2:
The patent implements partial processing of sensor data, focusing computational resources on analyzing only the most critical subsets of sensor information. This selective partial action allows the system to accommodate more sensors than would be possible with complete analysis of all sensor data.
3Loss of information
If all generated event indicators are presented to personnel for review, then information completeness is improved, but personnel efficiency decreases due to time spent analyzing low-relevance alerts
Solution Approach 1:
The patent extracts and removes low-relevance event indicators from the complete set before presentation to personnel. The system maintains information completeness in its internal processing and storage, but presents only prioritized high-relevance indicators to personnel, thereby preserving information integrity while improving personnel efficiency.
Solution Approach 2:
The patent performs preliminary prioritization and filtering of event indicators before they are presented to personnel. By pre-processing and ranking alerts based on relevance and urgency, the system ensures that personnel receive information in optimal order, reducing the time required for effective review while maintaining access to complete information when needed.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Systems and methods are provided for monitoring operations of an industrial facility. A gateway device (11) is located at the industrial facility and operably coupled to sensors disposed at the industrial facility. The gateway device executes tasks configured to i) monitor alarms or triggers or other events related to operating conditions of the industrial facility, ii) identify a particular alarm or trigger or other event that is activated or set, iii) identify at least one risk associated with the particular alarm or trigger or other event that is activated or set, and iv) dynamically construct a causal network to evaluate the at least one risk. The tasks can be implemented by a behavior tree (BT) that combines automated causal network generation and risk analysis. The BT performs real-time analysis of the sensor data to generate actions or indicators from the sensor data for input to the casual network for risk analysis.