Automated Plant Topology Generation from Operating Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing plant topology data structures are often not available in a computer-readable format, leading to manual and time-consuming creation processes, which are prone to errors and do not reflect the current operational state of the plant, limiting the application of automatic improvement and optimization methods.
Innovation Solution
A computer system and method that generates a plant topology data structure from operating data using predefined rules, processing signals from control objects to identify correlations and construct a computer-interpretable representation of the plant's connections, enabling the creation of a current and accurate topology model.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If plant topology data structures are created manually from paper P&ID diagrams, then the topology model can be generated, but the process is time-consuming and error-prone
Solution Approach 1:
The patent uses optical character recognition (OCR) and image processing techniques to create a digital copy of the paper P&ID diagrams. The system captures images of paper P&ID diagrams and automatically converts them into computer-readable data structures, eliminating manual transcription while preserving the original information accurately.
Solution Approach 2:
The patent replaces the manual mechanical process of transcribing P&ID data with automated optical recognition and image processing systems. The system uses computer vision algorithms to detect, recognize, and extract information from visual representations of plant diagrams, substituting human manual work with automated computational processes.
2Adaptability or versatility
If plant topology data structures are created during the engineering phase, then the topology model is available for automation engineering, but the model does not reflect current plant modifications
Solution Approach 1:
The patent implements a dynamic system that can continuously or periodically capture and process updated P&ID diagrams. The system allows for ongoing scanning and recognition of plant topology changes, enabling the digital model to adapt and reflect current plant modifications rather than remaining static from the engineering phase.
Solution Approach 2:
The system establishes a feedback mechanism where the digital topology model can be compared against newly scanned P&ID diagrams to detect changes. This allows the system to automatically identify and update modifications, ensuring the model remains synchronized with the actual plant state.
3Ease of manufacture
If paper P&ID diagrams are used to represent plant topology, then the visual representation is available, but the data is not in computer-readable format
Solution Approach 1:
The patent creates a digital copy of the paper P&ID diagrams through optical scanning and image processing. The system captures the visual information from paper diagrams and converts it into structured digital data formats that computers can process, store, and manipulate while maintaining the original visual representation's integrity.
Solution Approach 2:
The patent introduces an intermediary processing layer between the paper P&ID diagrams and the automation engineering systems. This layer includes optical recognition and data extraction components that translate visual information into computer-readable formats, enabling communication between the physical documentation and digital systems.
4Reliability
If manual creation of plant topology is undertaken to reflect current plant state, then the topology model can be updated, but the process is time-consuming and error-prone
Solution Approach 1:
The patent replaces manual updating processes with automated optical recognition and image processing systems. The system can rapidly scan, recognize, and extract data from P&ID diagrams without human intervention, dramatically increasing the speed of updates while reducing transcription errors through consistent automated processing.
Solution Approach 2:
The system enables continuous or frequent updating of the topology model by maintaining an ongoing process of scanning and processing P&ID diagrams. Rather than periodic manual updates, the automated system can continuously monitor and capture changes, ensuring the model remains current without interrupting plant operations.
Data Source
Figure 1
Figure 2
Figure 3A~3C
AI summary
A computer system (100), computer-implemented method and computer program product for generating a plant topology data structure (150) from operating data (OD) created by at least a subset of control objects (310) of an automation system during plant operation, the plant topology data structure reflecting at least a portion of the plant topology. The system has a tag list (160) with a list of signals associated with at least the subset of control objects; an interface module (110) configured to receive operating data (OD) from said control objects (310; a rule engine (120) configured to: apply a first rule set (130) to the received operating data (OD) wherein the first rule set includes rules configured to identify a plurality of object clusters including connected control objects, and iteratively apply a second rule set (140) to the identified plurality of object clusters wherein the second rule set is configured to identify consistent combinations of the object clusters as further object clusters; and a generator module (170) configured to generate, in the plant topology data structure (150), for a selected connection scenario, representations (R1 to Rn) of the respective connected control objects, and representations (C1 to Cn) of the connections between the control object representations (R1 to Rn).