AM Scan Parameter Dictionary for First-Time-Right Part Builds
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional additive manufacturing processes, such as direct metal laser sintering, require multiple iterations and laborious testing to optimize part quality and production rate, leading to increased time and cost due to the complex relationship between build parameters and part quality.
Innovation Solution
A system and method using an iterative learning control process to generate a dictionary of optimized scan parameter sets for additive manufacturing, which maps parameters to feature sets of geometric structures, allowing for the fabrication of parts with tailored optimal parameters without the need for extensive trial builds.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If conventional trial-and-error testing is used to optimize build parameters, then part quality can be improved, but time consumption and cost increase significantly
Solution Approach 1:
The system performs preliminary action by generating a build plan using a trained machine learning model before actual manufacturing begins. The model predicts optimal build parameters based on historical data and geometric features, allowing the system to prepare optimized parameters in advance rather than through iterative trial-and-error testing during production.
Solution Approach 2:
The system uses copying by creating virtual models and digital twins of physical parts for simulation and testing. The machine learning model is trained on historical build data and virtual simulations, allowing optimization to be performed on digital copies rather than requiring multiple physical trial builds, thereby reducing material waste and time consumption.
2Manufacturing precision
If multiple trial builds are performed to optimize parameters, then manufacturing precision improves, but material waste increases
Solution Approach 1:
The system replaces physical trial builds with virtual simulations and digital modeling. The machine learning model is trained on historical build data and virtual test results, allowing parameter optimization to be performed entirely in the digital domain. This eliminates or significantly reduces the need for physical trial parts, thereby minimizing material waste while achieving the same parameter optimization goals.
Solution Approach 2:
The system substitutes the mechanical trial-and-error build process with a computational machine learning approach. Instead of physically building and testing multiple iterations, the system uses algorithms to predict optimal parameters directly, replacing the mechanical testing cycle with an information-processing system that requires minimal physical material consumption.
3Manufacturing precision
If iterative testing is conducted to determine optimal build parameters, then part quality improves, but production rate decreases
Solution Approach 1:
The system performs parameter optimization in advance by training the machine learning model on historical data before production begins. Once trained, the model can rapidly generate build plans for new parts without requiring iterative testing during production, thereby maintaining high part quality while preserving production rate.
Solution Approach 2:
The system implements feedback by continuously learning from historical build data and outcomes. The machine learning model is trained on past successful builds and uses this feedback to improve its predictions for future parts. This feedback mechanism allows the system to achieve high part quality through learned patterns rather than time-consuming iterative testing, thereby maintaining productivity.
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 reduces the time and cost of material/part parameter development, minimizes material debits associated with sub-optimal segmentation, and produces higher-quality parts with reduced iterations, enabling 'first time right' fabrication by providing optimized parameters from the outset.
Implementation Method 1
Some AM systems use a laser (or similar energy source) and a series of lenses and mirrors to direct the laser over a powdered material in a pattern provided by a digital model
Implementation Method 2
The laser solidifies the powdered material by sintering or melting the powdered material
Implementation Method 3
direct metal laser melting (DMLM) may more accurately reflect the nature of this process since it typically achieves a fully developed, homogenous melt pool and fully dense bulk upon solidification
Implementation Method 4
The nature of the rapid, localized heating and cooling of the melted material enables near-forged material properties
Implementation Method 5
The AMM forms the object by solidifying successive layers of material one on top of the other on a build plate
Data Source
AI summary
According to some embodiments, system and methods are provided comprising receiving, via a communication interface of a part parameter dictionary module comprising a processor, geometry data for a plurality of geometric structures forming a plurality of parts, wherein the parts are manufactured with an additive manufacturing machine; determining, using the processor of the part parameter dictionary module, a feature set for each geometric structure; generating, using the processor of the part parameter dictionary module, one of a coupon and a coupon set for the feature set; generating an optimized parameter set for each coupon, using the processor of the part parameter dictionary module, via execution of an iterative learning control process for each coupon; mapping, using the processor of the part parameter dictionary module, one or more parameters of the optimized parameter set to one or more features of the feature set; and generating a dictionary of optimized scan parameter sets to fabricate geometric structures with a material used in additive manufacturing. Numerous other aspects are provided.