Industrial Analytics Architecture for Edge-Cloud Data Correlation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Industrial automation systems face challenges in effectively monitoring and analyzing data from diverse sources, leading to lost opportunities for collective analysis and insight into industrial operations, as data from different sources is often non-compatible and lacks correlations.
Innovation Solution
A cloud-based data ingestion and analysis architecture that integrates and normalizes data from multiple sources, using a system that includes a device interface, data queuing, discovery, and metadata generation components to identify relationships and generate actionable insights, enabling predictive maintenance and process supervision.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If data from multiple industrial automation systems is collected and analyzed collectively, then insights and predictive capabilities are improved, but data compatibility and integration complexity worsen
Solution Approach 1:
The patent employs data normalization components and metadata generation systems as intermediaries between diverse industrial data sources and the analysis platform. These intermediaries translate and standardize data from different protocols and formats into a unified structure, enabling collective analysis without direct complex integrations between all data sources.
Solution Approach 2:
The system segments the data integration challenge by processing data from each industrial automation system independently through individual normalization components, then aggregating the normalized results. This modular approach reduces overall integration complexity while enabling comprehensive collective analysis.
2Speed
If analytics are performed at device level only, then response time is improved, but scope of analysis and collective insights worsen
Solution Approach 1:
The patent introduces a multi-level analytics architecture that adds a cloud-based collective analysis dimension alongside device-level analysis. Device-level analytics operate in real-time for immediate responses, while cloud-level analytics process aggregated data for broader insights, creating a hierarchical structure that satisfies both speed and scope requirements.
3Productivity
If all industrial data is sent to cloud for analysis, then centralized control and comprehensive analysis are improved, but data transmission volume and network requirements worsen
Solution Approach 1:
The system extracts and processes critical data elements at the device level before transmission to the cloud. By performing preliminary normalization and filtering locally, only essential processed data and metadata are transmitted, significantly reducing data transmission volume while maintaining comprehensive analysis capability at the cloud level.
Data Source
AI summary
A scalable industrial data ingestion and analysis architecture integrates and collects data from multiple diverse sources at one or more industrial facilities. Data sources can include plant-level industrial devices and higher-level business systems. The data can be integrated and collected from multiple sources at an on-premise edge or gateway device, which sends the data to event queues on the cloud platform. The data queues orchestrate and store the data on cloud storage, and an analytics layer performs business analytics or other types of analysis on the stored data to produce various outcomes. Similar analytic platforms can also be implemented at the device level, and analytic functions can be scaled between the device level and higher levels in accordance with the scope of a given analytic function.