Fleet Parameter Distribution for Additive Manufacturing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional additive manufacturing sensor configurations produce 'context-less' data, leading to incomplete and inaccurate process models, resulting in defects such as subsurface porosity and thermal issues in direct metal laser melting (DMLM) processes, due to inadequate data collection and analysis.
Innovation Solution
The implementation of contextualized sensor data linking manufacturing and sensor data during the build process, enabling the development of high-fidelity digital twin models for real-time analytics and feedback loops, which allows for consistent build quality, anomaly detection, and optimization of machine performance across a fleet of additive manufacturing machines.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional sensor configurations are used to monitor the DMLM process, then data collection is simplified, but the data produced is context-less and incomplete, leading to inaccurate process models and defects
Solution Approach 1:
The patent implements feedback by continuously monitoring sensor data during the DMLM process and using this information to adjust process parameters in real-time. The system compares actual sensor readings against expected values and automatically modifies laser parameters, build plate temperature, or recoater settings to maintain optimal process conditions, thereby improving data quality and part outcomes without requiring overly complex sensor configurations
Solution Approach 2:
The patent introduces an intermediary layer of contextualization that links sensor data to specific process events and parameters. This intermediary system correlates temperature readings with laser passes, aligns acoustic emissions with layer formation events, and integrates camera imagery with build progress, transforming context-less sensor data into meaningful process information without complicating the sensor hardware itself
2Reliability
If sensors monitor the build process at high data acquisition rates (e.g., 50 kHz pyrometer), then real-time analytics capability is improved, but unmanageable quantities of data are produced (e.g., 2 GB per hour or more)
Solution Approach 1:
The patent extracts and isolates only the most critical sensor data points and events for storage and analysis. It identifies key process events such as laser power transitions, layer completion markers, and anomaly detections, then extracts only these significant data points at high resolution while summarizing or down-sampling less critical continuous data, thereby maintaining real-time detection capability while reducing overall data volume to manageable levels
Solution Approach 2:
The patent segments the build process into discrete layers and process stages, collecting high-resolution sensor data at these segmentation boundaries while using lower-resolution sampling between segments. This segmentation approach allows real-time monitoring at critical transition points without generating unmanageable quantities of continuous data throughout the entire build process
3Manufacturing precision
If process parameters are optimized for one machine, then build quality on that machine is improved, but other machines in the fleet continue to produce defects due to parameter variations
Solution Approach 1:
The patent systematically varies process parameters across different machines in the fleet, collecting sensor data and part outcomes for each parameter set. It then uses this data to identify which parameters have the greatest impact on build quality and which parameters show the most variation between machines, enabling targeted parameter optimization that maintains fleet-wide compatibility while improving individual machine performance
Solution Approach 2:
The patent creates a universal parameter framework that identifies core process parameters that should remain consistent across the fleet versus machine-specific parameters that can be adjusted. This universal framework allows the system to maintain fleet-wide parameter compatibility while enabling machine-specific optimizations, ensuring that fundamental process quality drivers are standardized while accommodating individual machine characteristics
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 consistent build quality, real-time anomaly detection, and optimization of machine performance by providing meaningful insights for design changes and process improvements, reducing defects and improving production efficiency.
Implementation Method 1
The metal powder is fused into a solid part by melting it locally using the focused laser beam
Implementation Method 2
direct metal laser sintering (DMLS), which uses a laser fired into a bed of powdered metal, with the laser being aimed automatically at points in space defined by a 3D model, thereby melting the material together to create a solid structure
Data Source
AI summary
Method, and corresponding system, for iteratively distributing improved process parameters to a fleet of additive manufacturing machines. The method includes receiving sensor data from a sensor for a first machine of the fleet of machines. The method further includes comparing the sensor data values at the working tool positions of the plurality of layers to reference data values at the working tool positions for the plurality of layers to determine a set of comparison measures for the first machine. The method further includes selecting a machine from among the first machine and at least a second machine of the fleet of machines based at least in part on the comparison measures of each of the machines. The method further includes receiving, from the selected machine, process parameters of the selected machine; and transmitting at least part of the process parameters of the selected machine to other machines of the fleet.