Asset Extraction From Engineering Diagrams for Intuitive Plant HMI
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 approach, which is costly and time-consuming to design, and do not align with the asset-centric view of plant operators.
Innovation Solution
The system uses machine learning models and algorithms to extract plant assets from engineering diagrams, create a plant asset hierarchy, build an ontological knowledge base, and provide an HMI that is asset-centric, allowing for intuitive control and operation of industrial process automation systems.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If a process-centric approach is used to design HMI, then the HMI captures process definitions accurately, but the HMI becomes non-intuitive and difficult to use for plant operators
Solution Approach 1:
The patent inverts the traditional process-centric HMI design approach by implementing an asset-centric architecture. Instead of organizing the HMI around process definitions, it organizes the HMI around plant assets (equipment, instruments, connectors) and their relationships, allowing operators to interact with the system in a more intuitive, asset-based manner while still maintaining accurate process definitions in the background
2Reliability
If a process-centric approach is used to design HMI, then the HMI provides accurate process control, but the design becomes costly and time-consuming
Solution Approach 1:
The patent performs preliminary action by automatically extracting asset information, relationships, and process definitions from engineering data sources (P&ID diagrams, equipment datasheets, instrument specifications) before HMI design begins. This pre-extraction and pre-organization of data eliminates the need for manual, time-consuming HMI design while ensuring accurate process control definitions are captured from the source engineering documents
3Manufacturing precision
If manual HMI design is performed with specialized knowledge, then the HMI is accurately designed, but the process becomes costly and complex
Solution Approach 1:
The patent implements self-service by enabling the system to automatically extract, validate, and organize HMI design data from engineering sources without requiring specialized manual intervention. The system uses machine learning and pattern recognition to interpret engineering diagrams and specifications, automatically generating asset models and relationships that would traditionally require expert designers, thereby reducing both cost and complexity
Data Source
AI summary
Systems and methods for controlling industrial an industrial plant comprise: inputting an engineering diagram for a unit of the industrial plant, the engineering diagram including symbols representing assets of the industrial plant; extracting one or more assets from the engineering diagram using machine learning to recognize the one or more assets, the one or more assets including equipment, instruments, connectors, and lines, the lines relating the equipment, instruments, and connectors to one another; determining one or more relationships between the equipment, instruments, connectors, and lines to one another using machine learning to recognize the one or more relationships; and creating a flow graph from the equipment, instruments, connectors, and lines and the relationships between the equipment, instruments, connectors, and lines.