Digital Twin Optical Inspection for Adaptive Product Quality Checks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing optical quality control methods for production plants, especially in autonomous and automated systems, require significant engineering effort to adapt to changing conditions and products, necessitating a more efficient and adaptive setup.
Innovation Solution
A computer-implemented method utilizing a digital twin and generative adversarial network (GAN) for domain adaptation, transforming real product images into a synthetic image space for comparison, allowing for automated quality evaluation with reduced setup effort.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If traditional rule-based optical quality control methods are used, then quality control can be performed, but significant engineering effort is required to adapt to changing conditions and products
Solution Approach 1:
The patent creates a digital twin (virtual copy) of the production plant that mirrors the real system. This digital replica includes 3D models, process parameters, and product specifications. By copying the entire production environment virtually, the system eliminates the need for manual rule configuration when products change - the digital twin automatically updates to reflect new product requirements, thereby reducing engineering effort while maintaining adaptability.
Solution Approach 2:
The system performs preliminary actions by pre-configuring the digital twin with all possible product variations and quality requirements before actual production changes occur. When a product change is anticipated, the digital twin is updated in advance, and quality control parameters are automatically adjusted. This preliminary preparation eliminates the need for time-consuming reconfiguration during production transitions.
2Reliability
If traditional optical quality control setup methods are used, then quality rules can be defined, but the process requires manual verification and parameter adjustment
Solution Approach 1:
The system implements continuous feedback loops where the digital twin receives real-time data from the actual production plant and automatically adjusts quality control parameters accordingly. The virtual environment simulates quality checks and provides feedback on expected outcomes, which are then compared with actual sensor data. This automated feedback mechanism maintains high reliability while eliminating manual verification steps that consume time.
Solution Approach 2:
The digital twin system performs self-service by automatically configuring quality control rules, adjusting parameters, and verifying settings without human intervention. When product specifications change, the system autonomously updates the digital model, derives appropriate quality criteria, and validates the configuration against historical data. This self-configuration capability dramatically reduces setup time while maintaining reliable quality control through automated validation.
3Productivity
If autonomous automated production plants are used, then productivity increases, but the systems must adapt to new products with minimal effort
Solution Approach 1:
The digital twin serves multiple functions simultaneously: it acts as a virtual production environment for simulation, a quality control configuration system, a training platform for operators, and a real-time monitoring tool. This multi-functional universal system supports various product types and production scenarios without requiring separate specialized systems, thereby maintaining high productivity while enabling easy adaptation to new products through a single unified platform.
Data Source
AI summary
In order to reduce the effort required to set up quality control for optical quality control of intermediate or finished products of a production plant (PW) under constantly changing conditions and circumstances at the production plant, and to adapt the plant's use accordingly, it is proposed that for optical quality control, where a product image (PB) of the production plant is captured by an image acquisition device (AID) for given intrinsic and extrinsic parameters and digital twin data (DTD) from a digital twin (DT) of the production plant is used, the digital twin being synchronized with the production plant at runtime, (i) a synthetic simulation image (SBsyn) based on the digital twin data (DTD) be rendered (rdn).wherein the rendered synthetic simulation image (SBsyn) is based on the same intrinsic and extrinsic parameters as in the product image acquisition, (ii) to transfer the product image from a real domain to an artificial domain using a trained (trn) domain adaptation (DA) (trf) and thereby to generate a synthetic product image (PBsyn) from the product image using domain transfer parameters (DTP) obtained through training, (iii) to compare the synthetic product image with the synthetic simulation image using a comparison operator (VO) (cf) and (iv) to output a comparison result (VGE) that qualitatively evaluates the product (asg).