Additive Manufacturing Variability Analytics for Build Quality Adjustment

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current additive manufacturing systems face challenges in diagnosing aborted or failed builds and identifying performance issues, requiring significant manual effort and time, which affects the reliability and repeatability of additive manufacturing machines.

Innovation Solution

The implementation of a system that monitors and analyzes data from additive manufacturing machines, including build-to-build variability analysis, to automatically diagnose issues, identify root causes, and adjust machine settings and processes in real-time.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual diagnosis and analysis of additive manufacturing builds is performed, then diagnostic accuracy can be achieved, but time consumption and labor requirements increase significantly

Engineering Contradiction:

Improvediagnostic accuracyVSAvoidtime consumption

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent replaces manual mechanical diagnosis with an automated computer-based system that uses machine learning models and algorithms to analyze build data, sensor data, and process parameters. This substitution eliminates the need for expert manual intervention while maintaining or improving diagnostic accuracy through consistent, data-driven analysis.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables self-diagnosis of additive manufacturing builds by automatically collecting data from sensors and build logs, processing this data through trained machine learning models, and generating diagnostic reports without requiring external expert intervention. The system serves itself by autonomously identifying issues and recommending corrections.

Inventive Principle:

Principle #25Self-service

2Difficulty of detecting and measuring

If root cause analysis of additive manufacturing failures is performed manually, then diagnostic depth can be achieved, but the process becomes impossible during active builds and extremely time-consuming between builds

Engineering Contradiction:

Improveroot cause detection depthVSAvoiddiagnosis speed

Core Design Contradiction:

Difficulty of detecting and measuringVSProductivity

Solution Approach 1:

The patent implements continuous monitoring and analysis capabilities that operate throughout the entire build process without interruption. Sensors continuously collect data from the additive manufacturing process, and the system performs real-time analysis to identify root causes of failures as they occur, rather than requiring post-build manual investigation.

Inventive Principle:

Principle #20Continuity of useful action

Solution Approach 2:

The system replaces time-consuming manual root cause analysis with automated computational algorithms that can process and analyze multiple data sources simultaneously, identifying root causes in minutes or seconds rather than hours or days of manual investigation.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Reliability

If individual additive manufacturing machines are monitored and adjusted manually, then build reliability can be maintained, but fleet-level repeatability and overall effectiveness deteriorate

Engineering Contradiction:

Improvebuild reliabilityVSAvoidfleet-level repeatability

Core Design Contradiction:

ReliabilityVSAdaptability or versatility

Solution Approach 1:

The patent implements a universal monitoring and adjustment system that can manage multiple additive manufacturing machines across a fleet through a centralized platform. The system performs the same diagnostic and optimization functions for each machine in the fleet, ensuring consistent build reliability and repeatability across all devices using standardized algorithms and data analysis approaches.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The system establishes continuous feedback loops between individual machines and the centralized fleet management platform. Data from each machine is fed back to the central system for analysis, and adjustments are automatically communicated back to the machines to maintain optimal performance. This feedback mechanism ensures both individual build reliability and fleet-wide consistency.

Inventive Principle:

Principle #23Feedback

Data Source

PatentEP4549058A1Multi-modality build-to-build and fleet-level variability analytics and adjustment of additive machine, process health, and build quality

Publication Date: 2025.05.07 GENERAL ELECTRIC CO

Figure 1
Figure 2
Figure 3

AI summary

Systems, apparatus, computer-readable medium, and associated methods to monitor, analyze, and adjust at least one of a build and/or an additive manufacturing machine configuration are disclosed. An example apparatus includes memory circuitry (304, 404), instructions, and processor circuitry (1800) to execute the instructions to implement at least a feature extractor (710), a variability analyzer (620, 720), and an output generator (730). The feature extractor (710) is to: i) group data for a plurality of builds associated with one or more additive manufacturing machines (100); and ii) extract features from the grouped data. The variability analyzer (620, 720) is to: i) process the grouped data with respect to the features to determine a measure of variability for each feature; and ii) compare the measure of variability for each feature to a respective allowable limit associated with the respective feature. The output generator (730) is to provide actionable output to adjust at least a first additive manufacturing machine (100).