3D Print Orientation and Speed Tuning for Resin Layer Adhesion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In additive manufacturing using photo-curable resins, the quality of the printed object is sensitive to printing speed and orientation, with existing methods failing to optimize these parameters effectively, leading to issues like layer adhesion and mechanical stress.
Innovation Solution
Determining the optimal printing speed and orientation by employing a convolutional neural network to analyze pixel maps of object cross-sections, adjusting base lift velocity and height based on critical convolution kernel sizes, and incorporating a term for local density changes to minimize printing time and mechanical stress.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If printing speed is increased to improve productivity, then manufacturing time is reduced, but object quality deteriorates due to poor layer adhesion and increased mechanical stress
Solution Approach 1:
The patent applies dynamics by making the printing speed variable rather than constant. The system dynamically adjusts the printing speed based on the local complexity of each cross-section, using a convolutional neural network to analyze pixel maps and determine optimal speeds for different regions. This allows faster printing in simple areas while maintaining quality in complex areas with intricate geometries.
Solution Approach 2:
The patent implements local quality by applying different printing speeds to different cross-sections of the object based on their individual complexity characteristics. The convolutional neural network analyzes each pixel map locally and assigns specific printing parameters tailored to that region's geometric features, ensuring optimal quality for each local area rather than using a uniform speed throughout.
2Manufacturing precision
If printing speed is decreased to improve object quality, then layer adhesion improves, but manufacturing time increases
Solution Approach 1:
The patent applies parameter changes by systematically varying the printing speed parameter based on the analyzed complexity of each cross-section. The convolutional neural network processes pixel maps to extract complexity metrics, then transforms these into optimized printing speed parameters. This allows the system to use slower speeds only where necessary for quality while maintaining faster speeds elsewhere, minimizing overall manufacturing time.
Solution Approach 2:
The patent implements preliminary action by pre-analyzing all cross-sections using the convolutional neural network before actual printing begins. The system processes pixel maps, determines critical convolution kernel sizes, and pre-calculates optimal printing speeds for each cross-section. This preparation allows the printer to execute at optimized speeds without real-time decision-making delays.
3Device complexity
If conventional printing optimization methods are used, then process simplicity is maintained, but ability to optimize complex geometries is insufficient
Solution Approach 1:
The patent replaces conventional mechanical trial-and-error optimization methods with an intelligent system based on convolutional neural networks. Instead of manually adjusting printing parameters or using simple heuristic rules, the system uses deep learning algorithms to automatically analyze cross-section images and determine optimal printing parameters, achieving superior geometry optimization without proportionally increasing operational complexity.
Solution Approach 2:
The patent introduces a convolutional neural network as an intermediary between the raw cross-section geometry and the printing parameter selection. This intelligent mediator analyzes pixel maps, extracts complexity features through convolutional operations, and translates geometric characteristics into optimized printing speeds and orientations, bridging the gap between simple process control and complex geometry requirements.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach optimizes printing speed and orientation, reducing mechanical stress and improving object quality by ensuring efficient layer formation and minimizing the risk of layer tearing, while also allowing for intricate shape formation.
Implementation Method 1
additive manufacturing process in which a photo-curable resin is cured through exposure to radiation
Data Source
AI summary
An optimal printing speed and orientation for an object to be manufactured using an additive manufacturing process in which a photo-curable resin is cured through exposure to radiation are estimated by determining, for pixel maps defining cross-sections of the object, a critical size of a convolution kernel which provides an activation map having a maximum activation pixel value less than or equal to a predetermined threshold value. For each respective pixel map, a printing time is estimated as a function of an adjusted base lift velocity and base lift height of the printing apparatus. The optimal printing speed and orientation are then estimated as a minimum value of a function of the printing times for all respective pixel maps of the cross-sections of the object at each of a plurality of possible orientations of the object.