Layer Configuration Prediction for 3D Printed Texture Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current building technologies, such as 3D printers, require a trial-and-error process to achieve desired textures in objects built by layering materials, which is time-consuming and inefficient, especially when multiple materials and colors are involved.
Innovation Solution
A method involving the production of specimens with varying layer configurations, measurement of texture parameters, and machine learning to predict the appropriate layer configuration for a desired texture, allowing a computer to output the corresponding layering pattern for a building apparatus.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If a trial-and-error process is used to determine layer configuration, then desired texture can be achieved, but time consumption and work amount increase significantly
Solution Approach 1:
The patent creates a database of layer configurations and their corresponding texture parameters before actual object building. By pre-analyzing and storing the relationships between layer configurations and textures, the system eliminates the need for trial-and-error during production, directly querying the database for optimal configurations based on desired textures.
Solution Approach 2:
The patent uses computer graphics images as virtual copies to represent actual objects and their textures. By working with digital representations rather than physical prototypes, the system can simulate and evaluate different layer configurations without physical trial-and-error, significantly reducing time and material consumption.
2Adaptability or versatility
If multiple kinds of ink are used to create various colors, then texture expression capability improves, but complexity of determining layer configuration increases
Solution Approach 1:
The patent divides the complex task of determining layer configuration into manageable components by creating a database that separately stores layer configuration data and texture parameter data. This segmentation allows the system to independently analyze and optimize each aspect, reducing overall complexity while maintaining versatility.
Solution Approach 2:
The patent transforms the complex qualitative problem of texture determination into quantitative parameter analysis. By measuring and storing specific texture parameters (such as transparency, color intensity, and surface properties) for different layer configurations, the system converts complex material interactions into measurable and comparable numerical data, simplifying the determination process.
Data Source
AI summary
A layer configuration prediction method is provided and includes: a specimen production step of producing multiple specimens by depositing layers of a material in configurations different from each other; a specimen measurement step of performing, on each specimen, measurement to acquire a texture parameter corresponding to a texture; a learning step of causing a computer to perform machine learning of a relation between each of the specimens and the texture parameter; a setting parameter calculation step of calculating a setting parameter corresponding to the texture set to a computer graphics image; and a layer configuration acquisition step of providing the setting parameter as an input to the computer having been caused to perform the machine learning, and acquiring an output representing the layering pattern of layers of the material corresponding to the setting parameter.