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, require extensive physical testing to assess part quality, which is laborious, expensive, and time-consuming, leading to increased development time and costs.
Innovation Solution
A method that predicts part quality using sensor data and build parameters during the manufacturing process, eliminating the need for physical testing in every iteration, by developing a part quality model that analyzes data in real-time and adjusts parameters algorithmically to improve part quality.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If physical testing is performed to assess part quality, then measurement precision is improved, but loss of time and productivity deteriorate
Solution Approach 1:
The patent creates a digital twin or virtual model of the physical part quality assessment process. Sensor data collected during manufacturing is fed into a computational model that simulates and predicts part quality outcomes, replacing the need for physical testing while maintaining assessment accuracy. This virtual copying enables quality evaluation without the time cost of physical tests.
Solution Approach 2:
The patent replaces mechanical/physical testing systems with a data-driven computational system. Instead of physically measuring and testing parts, the system uses sensor data combined with machine learning algorithms and digital models to predict quality metrics, substituting physical measurement processes with information-based assessment.
2Measurement precision
If physical testing is performed to assess part quality, then measurement precision is improved, but productivity deteriorates
Solution Approach 1:
The patent creates a digital twin or virtual model of the physical part quality assessment process. Sensor data collected during manufacturing is fed into a computational model that simulates and predicts part quality outcomes, replacing the need for physical testing while maintaining assessment accuracy. This virtual copying enables quality evaluation without the time cost of physical tests.
Solution Approach 2:
The patent replaces mechanical/physical testing systems with a data-driven computational system. Instead of physically measuring and testing parts, the system uses sensor data combined with machine learning algorithms and digital models to predict quality metrics, substituting physical measurement processes with information-based assessment.
3Reliability
If extensive physical testing is performed, then reliability of quality assessment is improved, but device complexity and cost increase
Solution Approach 1:
The patent creates a digital twin or virtual model of the physical part quality assessment process. Sensor data collected during manufacturing is fed into a computational model that simulates and predicts part quality outcomes, replacing the need for physical testing while maintaining assessment accuracy. This virtual copying enables quality evaluation without the time cost of physical tests.
Solution Approach 2:
The patent replaces mechanical/physical testing systems with a data-driven computational system. Instead of physically measuring and testing parts, the system uses sensor data combined with machine learning algorithms and digital models to predict quality metrics, substituting physical measurement processes with information-based assessment.
4Manufacturing precision
If physical testing is performed on every iteration, then manufacturing precision is improved, but loss of time and cost increase
Solution Approach 1:
The patent implements a feedback loop where sensor data from manufacturing processes is continuously collected and fed into predictive models. The model outputs quality predictions that feed back into process parameter optimization, enabling iterative improvement without physical testing. This closed-loop feedback system maintains manufacturing precision while eliminating testing time delays.
Solution Approach 2:
The patent creates a digital twin or virtual model of the physical part quality assessment process. Sensor data collected during manufacturing is fed into a computational model that simulates and predicts part quality outcomes, replacing the need for physical testing while maintaining assessment accuracy. This virtual copying enables quality evaluation without the time cost of physical tests.
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 development time and costs by allowing for quick, in-situ quality assessment, minimizing the reliance on destructive and non-destructive testing methods, and enabling faster convergence to optimal parameter sets, thus lowering new product introduction cycle times and increasing throughput.
Implementation Method 1
The metal powder is fused into a solid part by melting it locally using the focused laser beam
Implementation Method 2
A sensor integrated into the machine detects process quality in real time
Data Source
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.