Plant Asset Extraction for Asset-Centric Industrial HMIs
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current human-machine interfaces (HMIs) for industrial plants are non-intuitive and difficult to use due to a process-centric design, which does not align with the asset-centric view of plant operators, leading to inefficiencies in plant commissioning and operations.
Innovation Solution
A control system that uses machine learning to extract and organize plant assets into a hierarchical structure, providing an asset registry API and displaying knowledge bases as interlinked labeled-property nodes, allowing users to conduct natural language searches and visualize relationships, thereby improving the usability and effectiveness of HMIs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If a process-centric design approach is used for HMI, then the system captures process definitions accurately, but the interface becomes non-intuitive and difficult for plant operators to use
Solution Approach 1:
The system segments the HMI into multiple views: a process-centric view for engineers during commissioning and an asset-centric view for operators during operations. This segmentation allows each user group to interact with the interface in a way that matches their mental model, resolving the contradiction between process definition accuracy and operator usability.
Solution Approach 2:
The HMI dynamically adapts its presentation based on the user's role and context. The same underlying process data is presented differently depending on whether the user is an engineer needing process definitions or an operator needing asset information, thereby maintaining both process accuracy and operational ease.
2Adaptability or versatility
If custom HMI design is performed for each plant, then the interface captures specific plant components and operations, but the design process becomes costly and time-consuming
Solution Approach 1:
The system performs preliminary actions by automatically generating the asset-centric view and asset hierarchy from existing process control data during the commissioning phase. This preliminary structuring of data eliminates the need for time-consuming custom design during operations, as the framework is already in place to support plant-specific configurations.
Solution Approach 2:
The system creates a digital copy of the plant's asset hierarchy and relationships from process control data, which can then be used directly by operators without requiring custom design. This copying approach preserves plant-specific details while eliminating redundant design work.
3Reliability
If specialized knowledge of plant and process engineering is required for HMI design, then the interface can be tailored to technical requirements, but the design complexity increases
Solution Approach 1:
The system introduces an automated intermediary process that transforms process control data into an asset-centric hierarchy. This intermediary automatically handles the complex mapping between process definitions and asset structures, eliminating the need for designers to manually apply specialized knowledge while maintaining technical accuracy.
Solution Approach 2:
The system replaces the manual mechanical process of expert-driven HMI design with an automated computational process. Machine learning algorithms and data transformation routines substitute for human experts, reducing design complexity while preserving technical accuracy through systematic data processing.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Systems and methods for controlling industrial process automation and control systems can automatically, through the use of machine learning (ML) models and algorithms, extract plant assets from engineering diagrams and other plant engineering data sources. The systems and methods can establish asset relationships to create a plant asset registry and build an asset hierarchy from the plant assets. The systems and methods can generate an ontological knowledge base from the plant asset hierarchy, and provide an HMI for controlling the industrial process based on the plant asset hierarchy and the ontological knowledge base.