Neural Network Exposure Strategy for 3D UV Dose Distribution
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current 3D printing technologies, such as DLP processes, face challenges in efficiently calculating and achieving a desired dose distribution of UV light for optimal exposure strategies, which affects the accuracy and mechanical properties of printed components, relying on time-consuming trial-and-error methods rather than systematic calculations.
Innovation Solution
A neural network-based method is employed to calculate exposure strategies by inputting desired dose distributions, using CAD/CAM software, to optimize exposure data for 3D printing, allowing for the determination of optimal layer decomposition and exposure times, thereby improving printing speed, accuracy, and mechanical properties.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional trial-and-error methods are used to determine exposure data, then the exposure strategy can be obtained through printing jobs/tests, but the process is time-consuming and inefficient
Solution Approach 1:
The patent performs simulations and calculations of dose distribution before actual printing to determine optimal exposure data. By pre-calculating the dose distribution for different exposure parameters using light propagation models, the system identifies the best exposure strategy in advance, avoiding time-consuming trial-and-error printing jobs while ensuring accurate dose distribution.
2Ease of manufacture
If simulations are used to calculate dose distribution from exposure data, then the calculation is easy and straightforward, but the reverse calculation to achieve desired dose distribution is complex
Solution Approach 1:
The patent implements an iterative optimization process where the simulated dose distribution is continuously compared with the desired dose distribution. Based on the deviation between actual and desired dose distributions, the exposure parameters are adjusted and re-simulated until convergence is achieved. This feedback loop systematically solves the complex reverse calculation problem by breaking it down into manageable iterative steps.
3Manufacturing precision
If exposure parameters are optimized for accurate dose distribution, then printing accuracy and mechanical properties improve, but the calculation and optimization process becomes more complex
Solution Approach 1:
The patent replaces complex iterative trial-and-error mechanical testing with computational light propagation simulations and neural network-based optimization. By using physics-based models to simulate light behavior and neural networks to predict optimal exposure parameters, the system achieves high printing accuracy through virtual optimization rather than physical experimentation, reducing overall system complexity despite the sophisticated calculations involved.
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 enables faster and more accurate determination of exposure strategies, leading to enhanced printing results in terms of speed, accuracy, and mechanical properties, replacing conventional trial-and-error methods with data-driven optimization.
Implementation Method 1
the photoreactive resin is solidified layer by layer through spatially selective UV irradiation
Implementation Method 2
the exposure is carried out from below through a transparent bottom into a vat
Implementation Method 3
the photoreactive resin is solidified layer by layer through spatially selective UV irradiation
Implementation Method 4
a transport apparatus for at least moving the build platform downward and upward in the vat
Data Source
AI summary
A method of printing a component by using 3D printer, including: inputting a desired dose distribution in terms of the amount of UV light absorbed as a function of location within the component to be printed into a neural network by CAD/CAM software; calculation of the exposure strategy including the exposure data by means of the neural network, which optimally maps the specified desired dose distribution for the component; and printing the component with the calculated exposure data.