ML-Based HMI Graphic Correction for Legacy Migration Errors
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing HMI migration tools are not 100% accurate, requiring manual intervention for correcting HMI graphics, which is time-consuming and prone to errors, especially when dealing with complex objects, thus reducing migration efficiency and increasing costs.
Innovation Solution
A machine learning-based graphic object detection model automatically identifies and corrects inaccuracies in migrated HMI graphics by leveraging industrial domain knowledge and machine vision intelligence, reducing the need for manual effort and enhancing migration accuracy and efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual intervention is used to correct HMI graphics, then accuracy can be improved, but time consumption and cost increase significantly
Solution Approach 1:
The patent introduces an automated verification system that acts as an intermediary between the HMI migration tool and the final HMI graphics output. This system uses machine learning models and computer vision algorithms to automatically detect and correct discrepancies in migrated graphics, eliminating the need for manual verification while maintaining high accuracy.
Solution Approach 2:
The patent replaces the mechanical manual verification process with an automated computational system. Machine learning models and image processing algorithms substitute human operators, automatically analyzing migrated HMI graphics, identifying errors, and suggesting corrections without human intervention.
2Measurement precision
If manual verification is performed for each HMI, then accuracy is maintained, but productivity decreases due to enormous time consumption
Solution Approach 1:
The patent implements a self-verification system where the HMI migration process automatically checks and corrects its own output. The system uses trained machine learning models to autonomously identify discrepancies in migrated graphics and generate correction suggestions, enabling the process to self-validate without external manual intervention.
Solution Approach 2:
The automated verification system operates continuously throughout the HMI migration process, real-time analyzing migrated graphics as they are generated. This continuous automated checking maintains accuracy while enabling parallel processing of multiple HMI files, significantly improving overall migration productivity.
3Productivity
If automated migration tools are used, then productivity increases, but measurement precision decreases due to inaccuracies
Solution Approach 1:
The patent implements a feedback loop where the automated verification system continuously analyzes the output of the migration tool, identifies errors, and feeds correction suggestions back to improve the migration process. This closed-loop system allows the automated tool to learn from its mistakes and progressively improve accuracy while maintaining high productivity.
Solution Approach 2:
The system performs preliminary verification and correction before final output generation. Machine learning models pre-analyze migrated graphics, predict potential errors, and apply corrections in advance, ensuring high accuracy is achieved automatically before the migration process completes.
Data Source
Figure 1A
Figure 1B
Figure 2
AI summary
The present disclosure relates to computer-implemented method and arrangements for generating human machine interface, HMI, graphics associated with an industrial automation system implementing machine learning. The method comprises receiving (5402) a migrated HMI graphics. The migrated HMI graphics being obtained from a legacy HMI graphics and that the migrated HMI graphics comprising a plurality of industrial objects. Further, the method comprises (5404) identifying a missing industrial object in said migrated HMI graphics using a historical labelled dataset comprising a plurality of labelled HMI graphics of the industrial object that comprises a graphical object and a data object. Once, the missing industrial object is identified the migrated HMI graphics is therefore corrected (S406) to include the identified missing industrial object and a corrected HMI graphics is generated (S408). Furthermore, the method comprises transmitting (S408) a notification indicating the corrected HMI graphics to a computing device.