Additive Manufacturing Quality Scoring From In-Situ Sensor Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional additive manufacturing processes, such as direct metal laser melting (DMLM), require laborious and costly physical testing to assess part quality, which is time-consuming and dependent on human expertise, leading to prolonged development cycles and increased costs.
Innovation Solution
A method to predict part quality using sensor data and build parameters without physical testing, employing a quality score model that analyzes data during the build process, allowing for in-situ assessment and algorithmic optimization of manufacturing parameters.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If physical testing (destructive or non-destructive) is used to assess part quality, then measurement precision is improved, but loss of time and productivity deteriorate
Solution Approach 1:
The system performs preliminary quality assessment during the additive manufacturing build process itself, rather than after completion. Sensors monitor melt pool characteristics, laser parameters, and build conditions in real-time, enabling early detection of potential defects before the part is fully manufactured, thus eliminating the need for time-consuming post-build testing iterations
Solution Approach 2:
The patent replaces physical mechanical testing systems (sectioning, microscopy, physical property measurements) with optical and sensor-based monitoring systems. The quality score generator uses sensor data from the manufacturing process to predict part quality, substituting destructive and non-destructive physical testing with computational analysis of process parameters and sensor readings
2Measurement precision
If physical testing is used to assess part quality, then measurement precision is improved, but manufacturing cost increases
Solution Approach 1:
The manufacturing system performs self-assessment of part quality using integrated sensors and automated analysis. The quality score generator automatically evaluates build quality based on sensor data and process parameters, eliminating the need for external testing equipment, expert analysts, and manual inspection processes, thereby reducing manufacturing costs while maintaining assessment accuracy
3Manufacturing precision
If expert assessment of trial part quality is used, then manufacturing precision is improved, but loss of time and productivity deteriorate
Solution Approach 1:
The system implements automated feedback loops where sensor data from the manufacturing process is continuously analyzed by the quality score generator. This automated feedback provides immediate quality assessments without requiring expert intervention, enabling rapid iteration and optimization of build parameters while maintaining high manufacturing precision through data-driven decision-making
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
Reduces development time and costs by enabling rapid, accurate quality evaluation and optimization of additive manufacturing processes, minimizing the need for destructive and non-destructive testing, and improving part quality through iterative learning control.
Implementation Method 1
The metal powder is fused into a solid part by melting it locally using the focused laser beam
Implementation Method 2
The nature of the rapid, localized heating and cooling of the melted material enables near-forged material properties
Implementation Method 3
receiving sensor data from the additive manufacturing machine during manufacture of the part
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Determining a quality score for a part manufactured by an additive manufacturing machine based on build parameters and sensor data without the need for extensive physical testing of the part. Sensor data is received from the additive manufacturing machine during manufacture of the part using a first set of build parameters. The first set of build parameters is received. A first algorithm is applied to the first set of build parameters and the received sensor data to generate a quality score. The first algorithm is trained by receiving a reference derived from physical measurements performed on at least one reference part built using a reference set of build parameters. The quality score is output via the communication interface of the device.