HMI Graphics Migration With ML-Based Missing Object Correction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing HMI migration tools are not 100% accurate, requiring manual intervention to correct HMI graphics, which is time-consuming and prone to errors, especially when dealing with complex HMI objects, reducing migration efficiency and increasing costs.
Innovation Solution
A computer-implemented method using machine learning and image processing techniques to identify and correct missing industrial objects in HMI graphics by comparing legacy and migrated graphics, leveraging a historical labelled dataset for accurate object recognition and auto-verification.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual intervention is used to correct HMI graphics during migration, then accuracy can be maintained, but time consumption and cost increase significantly
Solution Approach 1:
The patent replaces manual mechanical verification with an automated machine learning-based object detection system. The system uses trained models to automatically identify and correct missing industrial objects in migrated HMI graphics, substituting human operators with an automated computational system that maintains high accuracy while dramatically reducing time consumption.
Solution Approach 2:
The migration system performs self-verification through automated object detection and comparison mechanisms. The system automatically identifies discrepancies between source and target HMI graphics, detects missing objects, and corrects them without requiring external manual intervention, enabling the system to service itself during the migration process.
2Reliability
If manual verification is performed for each HMI object, then migration accuracy improves, but productivity decreases due to enormous time consumption
Solution Approach 1:
The patent replaces manual verification mechanics with automated machine learning-based object detection. The system uses trained models to rapidly analyze migrated HMI graphics, identify missing industrial objects, and perform corrections automatically, achieving both high reliability and improved productivity by eliminating the bottleneck of manual verification.
Solution Approach 2:
The system changes the operational parameters of the verification process by transitioning from sequential manual inspection to parallel automated processing. The machine learning model can simultaneously analyze multiple objects and attributes in the HMI graphics, fundamentally changing the speed and scale at which verification can be performed while maintaining accuracy standards.
3Productivity
If automated HMI migration tools are used, then productivity increases, but measurement precision decreases due to incomplete accuracy
Solution Approach 1:
The patent applies preliminary action by training machine learning models in advance using historical labeled datasets of HMI graphics. This pre-training enables the automated tools to achieve high measurement precision during actual migration operations, resolving the accuracy-deficiency problem while maintaining the productivity benefits of automation.
Solution Approach 2:
The system implements feedback mechanisms where the object detection model continuously learns from detected discrepancies and corrections. By feeding back the results of automated detection and comparison between source and target graphics, the system refines its accuracy over time, progressively improving measurement precision while maintaining high productivity through automated operation.
Data Source
AI summary
A computer-implemented method and arrangements for generating human machine interface, HMI, graphics associated with an industrial automation system implementing machine learning include receiving migrated HMI graphics. The migrated HMI graphics are obtained from a legacy HMI graphics and comprise a plurality of industrial objects. Further, the method comprises 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 to include the identified missing industrial object and a corrected HMI graphics is generated. Furthermore, the method comprises transmitting a notification indicating the corrected HMI graphics to a computing device.