Additive Manufacturing Fault Detection Using Multiple Process Models

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional additive manufacturing (AM) process monitoring struggles to detect process deviations and defects in real-time, leading to potential production of low-quality parts and increased costs due to delayed diagnostics.

Innovation Solution

The implementation of time-dependent and spatially-dependent models for laser-on transient behavior, combined with multiple model hypothesis testing (MMHT) algorithms, allows for enhanced in-process monitoring. This system compares sensor data to outputs from multiple process models to detect anomalies and improve part quality control.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Manufacturing precision

If conventional between-build diagnostics are used, then device complexity is reduced, but manufacturing precision deteriorates due to delayed detection of process deviations

Engineering Contradiction:

Improvepart qualityVSAvoidmonitoring system complexity

Core Design Contradiction:

Manufacturing precisionVSDevice complexity

Solution Approach 1:

The system performs preliminary diagnostics during the manufacturing process itself rather than waiting for between-build checks. Sensors continuously monitor melt pool characteristics and compare them against expected values, enabling early detection of process deviations before they result in defective parts.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent introduces an intermediary monitoring system that acts as a bridge between the manufacturing process and quality control. This system uses sensors and algorithms to indirectly detect process deviations through melt pool characteristic analysis, avoiding the need for complex direct measurement of every process parameter.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Measurement precision

If steady state measurement of melt pool characteristics is used, then measurement precision is improved, but reliability deteriorates due to inability to detect parameter shifts

Engineering Contradiction:

Improvemelt pool measurement accuracyVSAvoidprocess deviation detection

Core Design Contradiction:

Measurement precisionVSReliability

Solution Approach 1:

The system transitions from static steady-state measurements to dynamic monitoring that captures transient behavior. By analyzing how melt pool characteristics evolve over time during laser-on transients, the system can detect parameter shifts and process deviations while maintaining measurement precision through time-resolved analysis.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The monitoring system performs periodic measurements during each laser-on transient cycle, capturing melt pool characteristics at multiple time points. This periodic sampling enables detection of parameter shifts by comparing temporal patterns against expected behavior, improving reliability without sacrificing measurement precision.

Inventive Principle:

Principle #19Periodic action

3Reliability

If additional diagnostics are added to discriminate parameter shifts, then reliability is improved, but device complexity increases

Engineering Contradiction:

Improveparameter shift detectionVSAvoiddiagnostic system complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

Instead of implementing multiple independent diagnostic systems for different parameters, the patent uses a single diagnostic approach that analyzes melt pool characteristics with sufficient detail to detect various types of parameter shifts. This partial action approach achieves reliable detection without the complexity of comprehensive multi-parameter monitoring.

Inventive Principle:

Principle #16Partial or excessive action

4Manufacturing precision

If in-situ process monitoring is implemented, then manufacturing precision is improved, but device complexity increases due to measurement variability from multiple sources

Engineering Contradiction:

Improvepart quality controlVSAvoidmonitoring system complexity

Core Design Contradiction:

Manufacturing precisionVSDevice complexity

Solution Approach 1:

The system focuses monitoring efforts on local melt pool characteristics rather than attempting to measure all process parameters globally. By concentrating on specific local features of the melt pool that are most sensitive to process deviations, the system achieves improved manufacturing precision control without the complexity of comprehensive system-wide monitoring.

Inventive Principle:

Principle #3Local quality

Data Source

PatentUS12222838B2System and methods for generating fault indications for an additive manufacturing process based on a probabilistic comparison of the outputs of multiple process models to measured sensor data

Publication Date: 2025.02.11 GENERAL ELECTRIC CO

AI summary

Generating fault indications for an additive manufacturing machine based on a comparison of the outputs of multiple process models to measured sensor data. The method receiving sensor data from the additive manufacturing machine during manufacture of at least one part. Models are selected from a model database, each model generating expected sensor values for a defined condition. Difference values are computed between the received sensor data and an output of each of the models. A probability density function is computed, which defines, for each of the models, a likelihood that a given difference value corresponds to each respective model. A probabilistic rule is applied to determine, for each of the models, a probability that the corresponding model output matches the received sensor data. An indicator is output of a defined condition corresponding to a model having the highest match probability.