Additive Manufacturing Sensor Data Contextualization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional additive manufacturing sensor configurations produce 'context-less' data, leading to incomplete and inaccurate predictive models for DMLS processes, resulting in defects such as subsurface porosity and thermal distortion, and overwhelming data quantities that are difficult to manage.
Innovation Solution
The system contextualizes sensor data by linking it to manufacturing process data, enabling the development of high-fidelity digital twin models that provide insights for design and engineering teams, allowing for real-time anomaly detection and optimization of machine performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If conventional sensor configurations are used to monitor the DMLM process, then sensor data is collected, but the data is context-less and cannot be accurately mapped to specific build parameters and tool positions
Solution Approach 1:
The patent introduces process data as an intermediary that bridges sensor data and build parameters. The system receives process data from the additive manufacturing machine that includes tool positions and build parameters, and uses this intermediary data to map sensor readings to specific contextual information about the manufacturing process state
Solution Approach 2:
The system establishes a feedback loop where sensor data is continuously collected and mapped to process data, enabling real-time monitoring and analysis of the DMLM process. This feedback mechanism allows the system to correlate sensor readings with specific build parameters and tool positions, providing contextual information for process optimization
2Measurement precision
If sensors monitor the DMLM process at high data acquisition rates (e.g., 50 kHz pyrometer), then detailed process data is captured, but unmanageable quantities of data are produced
Solution Approach 1:
The system extracts only the relevant contextual information from the high-volume sensor data by mapping it to process data. Instead of storing and processing all raw sensor data, the system extracts meaningful correlations between sensor readings and specific build parameters, tool positions, and process states, reducing the effective data volume that needs to be managed
Solution Approach 2:
The patent segments the data management approach by separating sensor data collection from sensor data interpretation. The system divides the monitoring function into collecting raw sensor data at high rates and then mapping that data to contextual process information, allowing high measurement precision while managing data volume through selective processing
3Reliability
If conventional predictive models are used for DMLM processes, then some predictions can be made, but the models are incomplete and inaccurate due to lack of contextual sensor data
Solution Approach 1:
The system uses mapped sensor data to continuously refine and improve predictive models for the DMLM process. By correlating sensor readings with build parameters and tool positions, the system generates feedback that enhances model accuracy for predicting melt pool characteristics, thermal cycles, and potential defects
Solution Approach 2:
The patent applies preliminary actions by using the mapped contextual sensor data to identify trends and potential issues before they result in defects. The system proactively monitors process parameters and predicts potential problems such as subsurface porosity or thermal distortion before they occur, allowing preventive adjustments
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 ensures consistent build quality, reduces defects, and optimizes production effectiveness by enabling informed design changes and individualized CAM processes, capturing key machine performance characteristics.
Implementation Method 1
The metal powder is fused into a solid part by melting it locally using the focused laser beam
Implementation Method 2
melting it locally using the focused laser beam
Implementation Method 3
A pyrometer may be used to detect a temperature of a melt pool
Data Source
AI summary
Method, and corresponding system, for receiving and processing sensor data for an additive manufacturing machine. The method includes determining values of the sensor data relative to time; and determining tool positions relative to time based on process data which controls operation of the additive manufacturing machine. The method further includes determining the sensor data values at the working tool positions based on a correlation of the values of the sensor data relative to time and the working tool positions relative to time. A representation of the sensor data values at the working tool positions is displayed by a user interface device.