Container Treatment DoE Planning Using Parameter Inertia
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing digital static design of experiments (DoE) methods for container treatment machines are time-consuming due to the varying dynamics of the machines' responses to changes in operating parameters, necessitating a more efficient method to generate a digital static experimental design (DSO) with high quality and reduced operating time.
Innovation Solution
A computer-implemented method that predicts operating parameter values based on target characteristic sizes by varying operating parameters with consideration for their parameter inertia, allowing for a structured approach to generate a digital SVP that reduces the time required while maintaining quality, using neural networks or adaptive algorithms.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If operating parameters are varied to generate a digital static experimental design (DoE) for a container treatment machine, then the quality and accuracy of the digital DoE is improved, but the time required to generate the digital DoE increases significantly
Solution Approach 1:
The patent segments the operating parameters into different groups based on their dynamics characteristics (fast-changing vs. slow-changing parameters). This segmentation allows the experimental design process to treat different parameters differently, varying fast parameters more extensively while limiting variations of slow parameters, thereby reducing the total number of experiments needed while maintaining DoE quality.
Solution Approach 2:
The patent applies dynamic classification to operating parameters, categorizing them based on their response time and inertia characteristics. Fast-changing parameters (with low inertia) are varied more frequently and extensively in the experimental design, while slow-changing parameters (with high inertia) are varied less frequently. This dynamic approach optimizes the experimental design generation time while preserving the quality of the digital DoE.
2Reliability
If all operating parameters are varied extensively to ensure high quality digital DoE, then the accuracy and reliability of predictions are improved, but the energy consumption and operating time increase
Solution Approach 1:
The patent segments operating parameters into groups based on their dynamics characteristics and varies them differently in the experimental design. Fast parameters are varied more extensively while slow parameters are varied less, reducing the total number of experimental runs required. This segmentation maintains prediction accuracy for critical parameters while reducing overall energy consumption during the DoE generation process.
Solution Approach 2:
The patent changes the approach to parameter variation by classifying parameters according to their dynamics and inertia characteristics. Instead of uniformly varying all parameters extensively, the method adjusts the extent of variation based on each parameter's characteristics, thereby maintaining reliability of predictions while reducing the energy and time resources required for generating the digital DoE.
Data Source
Figure 1
Figure 2
Figure 3~4
AI summary
A computer-implemented method for generating a digital static design of experiments (DSO) for a container treatment machine, wherein the digital DSO can predict a value of an operating parameter of the container treatment machine based on a setpoint of a characteristic quantity of a container to be treated, the method comprising: - obtaining a parameter inertia for operating parameters of the container treatment machine; - operating the container treatment machine with a fixed operating parameter value of a first operating parameter with a first parameter inertia and varying at least one second operating parameter with a smaller second parameter inertia than the first parameter inertia; - determining at least one characteristic quantity of a treated container depending on the operating parameter value of the first operating parameter and the operating parameter values of the second operating parameter;- Generating the digital SVP based on the operating parameter values and the characteristic size.;