Neural Network Feed Forward Control for 3D Printer Peel-Off
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current 3D printing processes, such as SLA and DLP, face challenges in optimizing the peel-off process to balance speed and component protection without damaging the printed component, as existing feed forward control methods are often too slow and require sensor systems for active control.
Innovation Solution
A 3D printing system utilizing a neural network for feed forward control of the pull-off motion, which calculates optimized peel-off movements based on the properties of the photoreactive resin and energy distribution, eliminating the need for sensor systems and control units, and allowing for training on laboratory machines for use on field machines without force measurement devices.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conservative pull-off movement based on empirical values is used, then component damage is avoided, but printing speed is unnecessarily slow
Solution Approach 1:
The neural network predicts detachment forces and optimal pull-off parameters in advance, before the actual pull-off movement occurs. This allows the system to prepare and execute the pull-off movement with optimized parameters, avoiding both excessive slowness and potential damage by pre-calculating the safe and efficient detachment profile based on learned patterns from training data.
2Productivity
If active control with sensor system is implemented, then maximum speed with given force maximum is achieved, but device complexity increases
Solution Approach 1:
The patent replaces the mechanical sensor-based active control system with a neural network-based predictive system. Instead of using sensors to detect detachment in real-time and adjust pull-off parameters dynamically, the system uses a neural network that has learned optimal detachment patterns from training data to predict and determine the pull-off movement parameters in advance, eliminating the need for complex sensor hardware and real-time control mechanisms.
3Reliability
If unnecessary travel is performed to ensure detachment, then component safety is maintained, but process time increases
Solution Approach 1:
The neural network is trained using feedback from detachment detection systems during the training phase, allowing it to learn the optimal pull-off parameters that ensure safe detachment without unnecessary travel. During actual operation, the network uses this learned feedback to predict the precise pull-off profile needed, eliminating redundant movements while maintaining component safety.
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 optimized peel-off processes that enhance printing speed and safety by predicting detachment forces and times, allowing for efficient operation of 3D printers without the need for additional sensors, ensuring optimal performance for specific printers and printing jobs.
Implementation Method 1
a projector for projecting the layer geometries onto the transparent bottom
Implementation Method 2
curing photoreactive resin layer by layer
Data Source
AI summary
Aspects relates to a 3D printer including a vat having an at least partially transparent bottom for receiving liquid photoreactive resin to produce a solid component; a building platform for holding and pulling out the component layer by layer from the vat; a projector for projecting the layer geometry onto the transparent bottom; a transport apparatus for at least downward and upward movement of the building platform in the tray; and a control device for controlling the projector and the transport apparatus. The control device optimally feed forward controls the pull-off movement of the build platform in the 3D printer using a neural network.