Adaptive Edge Compute Management for IIoT Digital Twins
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Industrial environments face challenges in efficiently collecting, processing, and utilizing vast amounts of data from vibration sensors and other IoT devices to predict maintenance needs and optimize operations, due to complexity and limited data availability, leading to delayed problem diagnosis and expertise loss when experienced workers leave.
Innovation Solution
A platform for the Industrial Internet of Things (IIoT) that includes multiple data-handling layers for monitoring, storage, and adaptive intelligent systems, enabling the creation and management of digital twins for industrial entities, which collect and update data in real-time using IoT sensors, robotic process automation, and machine learning models to simulate operations and optimize processes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If data is collected from vibration sensors and IoT devices in industrial environments, then operational efficiency and predictive maintenance capability are improved, but system complexity and data processing burden increase
Solution Approach 1:
The patent segments the data processing system into multiple layers: edge devices for local data collection and preprocessing, intermediate processing nodes for pattern recognition, and centralized platforms for comprehensive analysis. This hierarchical segmentation reduces the complexity burden on any single component while maintaining overall system effectiveness for predictive maintenance and operational optimization.
Solution Approach 2:
The patent introduces digital twins as intermediary virtual representations of physical industrial assets. These digital twins serve as mediators between raw sensor data and decision-making systems, enabling complex data processing to occur in the virtual domain while simplifying the interface for operational efficiency improvements in the physical domain.
2Reliability
If real-time data processing is implemented using IoT sensors and machine learning models, then predictive maintenance capability is improved, but data processing time and computational resources increase
Solution Approach 1:
The patent implements preliminary action by pre-training machine learning models offline using historical data, and by performing initial data filtering and feature extraction at the edge devices before data reaches central processing systems. This preliminary processing reduces the computational burden during real-time operation, enabling faster predictive maintenance decisions without sacrificing reliability.
Solution Approach 2:
The patent employs periodic action through scheduled batch processing for comprehensive analysis alongside continuous streaming processing for critical real-time monitoring. This hybrid approach allows the system to maintain high reliability for urgent predictive maintenance needs while managing overall data processing time through periodic deep analysis cycles.
3Adaptability or versatility
If digital twins are created and updated in real-time for industrial entities, then operational agility and decision-making quality are improved, but data storage requirements and system complexity increase
Solution Approach 1:
The patent applies local quality by creating digital twins at different levels of detail and granularity appropriate to each industrial entity and its specific operational needs. Critical assets receive high-fidelity digital twins with comprehensive data, while less critical entities use simplified representations. This selective approach enhances operational agility for key processes while managing overall data storage requirements through differentiated data quality levels.
4Productivity
If multiple data-handling layers are implemented for monitoring and analysis, then data processing capability and intelligence development are improved, but system complexity and implementation difficulty increase
Solution Approach 1:
The patent implements universality by designing standardized data interfaces and communication protocols that allow the same data-handling layer architecture to serve multiple different industrial applications and asset types. This multi-functional design enables the system to process diverse data sources (vibration sensors, IoT devices, operational data) through a unified layered architecture, improving data processing capability while reducing implementation difficulty through standardization.
Data Source
AI summary
A platform for facilitating development of intelligence in an Industrial Internet of Things (IIoT) system generally includes a plurality of distinct data-handling layers having an industrial monitoring systems layer that collects data from or about a plurality of industrial entities in an industrial environment; an industrial entity-oriented data storage systems layer that stores the data collected by the industrial monitoring systems layer; and an adaptive intelligent systems layer that facilitates the coordinated development and deployment of intelligent systems in the IIoT system; wherein the adaptive intelligent systems layer includes an adaptive edge compute management system that adaptively manages edge computation, storage, and processing in the IIoT system.