Virtual Food Packaging Simulation for Shape-Conforming Packs
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Predicting the final shapes and geometries of food products during processing is challenging, affecting their handling, packaging, and consumer experience, and existing systems lack real-time control over production and packaging processes.
Innovation Solution
Utilizing simulation engines and machine learning models to predict and simulate food product shapes and packaging parameters in real-time, integrating imaging systems to capture 2D and 3D data, and applying AI models like Soft Point Flow NN and UNIST to generate synthetic product pieces for accurate simulations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional manual testing and physical prototyping are used to determine product shape and packaging parameters, then accuracy of packaging fit can be achieved, but time consumption and production delays increase significantly
Solution Approach 1:
The patent creates virtual copies of food products through 3D scanning and digital modeling, then uses these digital twins in simulation environments to test packaging parameters. This eliminates the need for physical prototypes while maintaining measurement accuracy, as the virtual models accurately represent the physical product's geometry and behavior.
Solution Approach 2:
The system performs virtual testing and simulation of packaging parameters before actual production begins. By predicting product shape changes during processing and pre-determining optimal packaging parameters in the virtual environment, the system eliminates iterative physical testing, significantly reducing development time while maintaining accuracy.
2Productivity
If real-time prediction and control systems are implemented, then productivity and waste reduction improve, but device complexity and implementation cost increase
Solution Approach 1:
The patent replaces complex mechanical measurement and testing systems with computational methods. Instead of using physical sensors and manual measurement devices throughout the production line, the system uses image processing, computer vision, and machine learning algorithms to predict product shape and determine packaging parameters, simplifying the physical infrastructure while maintaining real-time capabilities.
Solution Approach 2:
The system enables the production process to self-adjust by automatically predicting product shape changes and determining optimal packaging parameters in real-time. The automated control system adjusts packaging machine settings without manual intervention, improving productivity while the standardized algorithms keep system complexity manageable.
3Manufacturing precision
If extensive physical testing and iteration are performed to optimize packaging parameters, then packaging conformity improves, but material waste and resource consumption increase
Solution Approach 1:
The patent uses virtual copies and digital twins to test packaging parameters extensively without consuming physical materials. The simulation environment allows for repeated testing and optimization of packaging fit, seal parameters, and machine settings using only digital data, eliminating material waste associated with physical prototyping and iterative testing.
Solution Approach 2:
The system determines optimal packaging parameters through virtual testing before actual production begins. By pre-optimizing all packaging parameters in the simulation environment, the system ensures packaging conformity is achieved on the first physical production run, eliminating the need for iterative adjustments that would consume additional materials.
Data Source
AI summary
Disclosed are techniques for virtual food product development. A method may include: receiving, from an imaging system, two-dimensional (2D) data of food products in a production line at a plant, converting the 2D data of the food products into three-dimensional (3D) mesh data of the food products based on applying a neural network (NN) to the 2D data, generating a dataset of synthetic food product pieces based on applying an artificial intelligence (AI) model to the 3D mesh data of the food products, running a simulation of a process for packaging the synthetic food product pieces in the dataset, and returning simulation results in response to running the simulation.