Additive Manufacturing Layer Imaging for Location-Normalized Control

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing additive manufacturing systems face challenges in accurately monitoring and controlling the build process due to variations in sensor data across the build plate, leading to potential errors and defects in the final product.

Innovation Solution

The system obtains images of build layers using an imaging device, removes variations between features, and normalizes the data to eliminate location dependence, allowing for precise adjustments to the energy beam parameters to mitigate errors.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If multiple sensors are used to monitor the build process, then measurement coverage is improved, but data processing complexity increases

Engineering Contradiction:
Improvemeasurement coverageVSAvoiddata processing complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent combines data from multiple sensors into a unified dataset and processes them together through normalization and variation removal algorithms, reducing the complexity of handling multiple separate sensor streams while maintaining comprehensive measurement coverage

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The patent transforms sensor data by removing variations and normalizing features, changing the parameter representation of sensor readings to eliminate location dependence and reduce data complexity while preserving essential build process information

Inventive Principle:
Principle #35Parameter changes

2Measurement precision

If multiple sensors generate more data, then monitoring accuracy is improved, but build process speed decreases

Engineering Contradiction:
Improvemonitoring accuracyVSAvoidbuild process speed
Core Design Contradiction:
Measurement precisionVSProductivity

Solution Approach 1:

The patent applies parameter transformations by removing variations and normalizing sensor data features, which reduces data complexity and enables faster processing while maintaining the high monitoring accuracy provided by multiple sensors

Inventive Principle:
Principle #35Parameter changes

Solution Approach 2:

The patent implements continuous real-time processing of sensor data through automated normalization and variation removal, ensuring that the useful action of monitoring continues without interruption or speed reduction despite the volume of data from multiple sensors

Inventive Principle:
Principle #20Continuity of useful action

3Productivity

If sensor data is processed without normalization, then processing speed is maintained, but location dependence causes errors

Engineering Contradiction:
Improveprocessing speedVSAvoidbuild accuracy
Core Design Contradiction:
ProductivityVSManufacturing precision

Solution Approach 1:

The patent applies normalization as a parameter transformation that removes location dependence from sensor data, enabling accurate build process monitoring without sacrificing processing speed, as the normalization is implemented through efficient computational algorithms

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentUS20250187076A1System and method for additive manufacturing control
Publication Date: 2025.06.12 GENERAL ELECTRIC CO
  • US20250187076A1 patent drawing
  • US20250187076A1 patent drawing
  • US20250187076A1 patent drawing

AI summary

An additive manufacturing apparatus, a computing system, and a method for operating an additive manufacturing apparatus are provided. The method includes obtaining two or more images corresponding to respective build layers at a build plate, wherein each image comprises a plurality of data points comprising a feature and corresponding location at the build plate; removing variation between the features of the plurality of data points; and normalizing each feature to remove location dependence in the plurality of data points.