Industrial IoT Gateway Data Selection for Faster AI Analytics
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Industrial automation systems face challenges in deriving value from large amounts of unstructured and uncorrelated industrial data, leading to inefficiencies in data processing and storage, and often produce spurious correlations that require significant human verification.
Innovation Solution
A smart gateway platform that leverages domain expertise to select and model relevant industrial data subsets, applying pre-defined correlations and causalities to reduce data space and enhance AI analytics efficiency, by storing executable components and model templates associated with business objectives, and normalizing data values with modeling metadata.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If all industrial data is collected and stored for analytics, then comprehensive analysis coverage is improved, but data storage requirements and processing time increase significantly
Solution Approach 1:
The system extracts only the relevant subset of industrial data needed for specific analytics objectives rather than collecting all available data. Model templates define precise data requirements, allowing the platform to extract and process only necessary data points from industrial devices, thereby reducing storage needs while maintaining analysis effectiveness.
Solution Approach 2:
The data collection and processing is segmented into targeted subsets based on analytics objectives. Each model template represents a segmented view of data relevant to specific business questions, allowing the system to process multiple focused data subsets rather than one monolithic comprehensive dataset, improving efficiency while maintaining coverage.
2Measurement precision
If domain expertise is incorporated through model templates, then analytics accuracy is improved, but system complexity increases
Solution Approach 1:
Domain expertise is incorporated in advance through pre-defined model templates that encode analytical logic, data relationships, and business rules. These templates are prepared beforehand and can be selected and applied without requiring complex real-time decision-making, thereby improving analytics accuracy while keeping the runtime system relatively simple.
Solution Approach 2:
The system manages complexity by parameterizing analytics through configurable model templates. Instead of hardcoding complex analytical logic, the system uses parameter-based templates that can be adjusted and configured through user interfaces, allowing domain expertise to be encoded in a manageable, flexible format that balances accuracy with system simplicity.
3Productivity
If data is normalized with modeling metadata, then data quality and AI analytics efficiency are improved, but data processing time increases
Solution Approach 1:
Data normalization and metadata assignment are performed in advance as part of the data preparation process defined by model templates. By pre-normalizing data structures and attaching relevant metadata before AI analytics execution, the system reduces the processing burden during actual analytics runs, improving overall efficiency while managing the time investment through structured preparation.
Data Source
AI summary
A smart gateway platform leverages pre-defined industrial expertise to identify limited subsets of available industrial data deemed relevant to a desired business objective, and to collect and model this relevant data to apply useful constraints on subsequent artificial intelligence or machine learning analytics applied to the data. This approach can reduce the data space to which AI analytics are applied, and assist data analytic systems to more quickly derive valuable insights and business outcomes. In some embodiments, the smart gateway platform can operate within the context of a multi-level industrial analytic system, feeding pre-modeled data to one or more AI or machine learning systems executing on one or more different levels of an industrial enterprise.