Deposition Process Parameter Prediction for Defect-Aware Fabrication

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing additive manufacturing processes lack the ability to rapidly optimize and adjust process control parameters in response to changes in process or environmental conditions, leading to suboptimal quality and yield.

Innovation Solution

Implementing real-time adaptive control methods using machine learning algorithms to predict and adjust process control parameters based on training data sets, incorporating process simulation, characterization, and inspection data, enabling iterative improvements.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If traditional additive manufacturing processes are used, then manufacturing capability is achieved, but the ability to rapidly optimize and adjust process control parameters in response to changes in process or environmental conditions is lacking

Engineering Contradiction:

Improveability to adjust process control parametersVSAvoidquality of parts produced

Core Design Contradiction:

Adaptability or versatilityVSManufacturing precision

Solution Approach 1:

The system implements real-time feedback by monitoring process parameters and environmental conditions during additive manufacturing, then using machine learning algorithms to automatically adjust process control parameters. Sensors collect data on temperature, humidity, and deposition rates, which are fed back to the control system to optimize part quality dynamically.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The invention dynamically changes process control parameters such as deposition rate, temperature, and material flow based on real-time conditions and machine learning predictions. This allows the system to adapt to environmental variations and optimize manufacturing precision without manual intervention.

Inventive Principle:

Principle #35Parameter changes

2Manufacturing precision

If real-time adaptive control using machine learning is implemented, then process yield and quality are improved, but system complexity increases

Engineering Contradiction:

Improvequality of parts producedVSAvoidcomplexity of control system

Core Design Contradiction:

Manufacturing precisionVSDevice complexity

Solution Approach 1:

The machine learning system performs self-service by automatically training on collected data and making autonomous decisions about parameter adjustments. The system improves its own performance over time without requiring complex external control infrastructure, reducing the burden on operators while maintaining high manufacturing precision.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The invention replaces traditional mechanical and manual control systems with intelligent software-based machine learning algorithms. This substitution reduces physical complexity by using computational models to predict optimal parameters and automate adjustments, rather than requiring complex mechanical adjustment mechanisms.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Adaptability or versatility

If iterative training with process characterization data is performed, then process optimization capability is enhanced, but processing time and computational resources increase

Engineering Contradiction:

Improveprocess optimization capabilityVSAvoidtime for data processing

Core Design Contradiction:

Adaptability or versatilityVSLoss of time

Solution Approach 1:

The system performs preliminary action by collecting and preprocessing process characterization data during normal manufacturing operations. Machine learning models are trained in advance on this accumulated data, so that when real-time optimization is needed, the models are already prepared and can make rapid predictions without requiring extensive processing time during critical manufacturing phases.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS12547152B2Predicting process control parameters for fabricating an object using deposition

Publication Date: 2026.02.10 RELATIVITY SPACE INC

AI summary

Process control parameters are predicted to fabricate an object using deposition. An input design geometry is provided for the object. A training data set includes past post-build physical inspection data for a plurality of objects that comprise at least one object that is different from the object to be physically fabricated; and training data generated through a repetitive process of randomly choosing values for each of multiple process control parameters and scoring adjustments to the multiple process control parameters as leading to either undesirable or desirable outcomes, the outcomes based respectively on the presence or absence of defects detected in a fabricated object arising from the process control parameter adjustments. A machine learning algorithm is trained using the provided training data set and a predicted optimal set of the multiple process control parameters is generated for initiating and performing the deposition process to fabricate the object.