CAD-Based Control Program Generation With Smart Tag Contextualization
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 machine learning and AI analytics, as they require significant processing time and storage capacity, and often produce spurious correlations that need human verification.
Innovation Solution
A smart gateway platform leverages domain expertise to selectively model and contextualize relevant industrial data, reducing the data space for AI analytics by pre-defining correlations and causalities, and using smart tags to label data items based on business objectives, thereby streamlining the derivation of actionable insights.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If AI analytics are applied to large amounts of unstructured industrial data, then comprehensive analysis coverage is improved, but processing time and storage requirements increase significantly
Solution Approach 1:
The system performs preliminary action by pre-defining correlations and causalities between data items before AI analytics are applied. Domain expertise is used to establish these relationships in advance, creating a structured framework that guides the analytics process. This preliminary structuring reduces the computational burden during actual analysis, thereby decreasing processing time while maintaining comprehensive analysis coverage.
Solution Approach 2:
The system extracts only the relevant data items and relationships needed for specific business objectives, rather than processing all available unstructured data. By using smart tags and pre-defined correlations to identify and extract pertinent data, the system reduces the data volume requiring intensive AI processing, thus reducing processing time while preserving analysis quality.
2Reliability
If AI analytics process large amounts of unstructured industrial data, then analysis completeness is improved, but storage capacity requirements increase
Solution Approach 1:
The system extracts and retains only the essential data items and their relationships that are relevant to business objectives. By using domain expertise to identify and extract pertinent data elements, the system maintains analysis completeness while significantly reducing the total data volume that requires storage capacity.
Solution Approach 2:
The system performs preliminary action by pre-structuring data relationships and defining correlations before analytics are applied. This advance organization allows the system to maintain complete analytical coverage using a more compact, efficiently structured data representation, thereby reducing storage requirements.
3Reliability
If AI analytics are applied to unstructured industrial data, then comprehensive insights are improved, but spurious correlations increase requiring human verification
Solution Approach 1:
The system performs preliminary action by incorporating domain expertise to pre-define correlations and causalities before AI analytics are applied. This preliminary structuring with domain-knowledge-guided relationships ensures that the analytics process focuses on meaningful connections, reducing the generation of spurious correlations and minimizing the need for human verification.
4Manufacturing precision
If manual programming is used for industrial control systems, then program accuracy is improved, but development time increases
Solution Approach 1:
The system performs preliminary action by automatically generating portions of the control program based on pre-defined correlations and domain expertise. This automated program generation handles routine and predictable programming tasks, reducing development time while maintaining accuracy through the guidance of pre-established domain-knowledge-based rules and relationships.
Solution Approach 2:
The system acts as an intermediary between domain expertise and program generation. It uses pre-defined correlations and causalities as intermediate representations that bridge the gap between manual programming requirements and automated generation, producing accurate control programs more efficiently by leveraging structured domain knowledge.
Data Source
AI summary
An industrial control programming development platform simplifies generation of an industrial control program and associated tag definitions by generating at least a portion of the control program and tag definitions based on analysis of digital engineering drawings of an automation system to be monitored and controlled. This drawing-based program generation includes creation and configuration of smart data tags that model and contextualize controller data at the device level for processing by higher level analytic systems. This device-level contextualization can be based in part on inferences drawn from the digital engineering drawings.