Neuro-Fuzzy Control for Directed Energy Deposition Precision
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The high computational expense and potential inaccuracies of thermal models make real-time control of directed energy deposition (DED) material addition techniques impractical for processes like forming or repairing gas turbine components, such as blisks, which require precise energy and material delivery.
Innovation Solution
A system that uses a neuro-fuzzy algorithm to adjust operating parameters in real-time based on detected parameters deviating from thermal model predictions, allowing for adaptive control of DED processes, including energy delivery, material flow, and cooling gas management.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If a thermal model is used to control DED MA technique, then manufacturing precision is improved, but computational expense increases and real-time control becomes impractical
Solution Approach 1:
The patent creates a simplified copy or surrogate model of the complex thermal model using neuro-fuzzy logic. This neuro-fuzzy model replicates the thermal model's predictive capabilities for melt pool geometry and material addition rates but with significantly reduced computational requirements, enabling real-time control while maintaining manufacturing precision.
Solution Approach 2:
The patent replaces the computationally intensive thermal model (mechanical/computational system) with a neuro-fuzzy algorithm (intelligent system). This substitution maintains the functional capability to predict process outcomes while dramatically reducing computational expense and enabling real-time operation.
2Manufacturing precision
If a thermal model is used to control DED MA technique, then manufacturing precision is improved, but device complexity increases
Solution Approach 1:
The patent creates a simplified copy or surrogate model of the complex thermal model using neuro-fuzzy logic. This neuro-fuzzy model replicates the thermal model's predictive capabilities for melt pool geometry and material addition rates but with significantly reduced computational requirements, enabling real-time control while maintaining manufacturing precision.
3Device complexity
If default operating parameters are used without adaptation, then device complexity is reduced, but manufacturing precision deteriorates due to parameter deviations from expected values
Solution Approach 1:
The patent implements a feedback mechanism where sensors continuously monitor actual process parameters (such as melt pool geometry and material addition rates) and compare them with expected values from the thermal model. When deviations are detected, the neuro-fuzzy algorithm adjusts operating parameters in real-time to maintain manufacturing precision.
Solution Approach 2:
The patent transitions from static default operating parameters to dynamic adaptive parameters. The neuro-fuzzy algorithm continuously adjusts operating parameters based on real-time sensor feedback and thermal model predictions, allowing the system to adapt to changing conditions while maintaining precision.
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
Enables real-time control and improved precision in DED processes, enhancing the formation and repair of complex components like gas turbine blisks by dynamically adjusting parameters to maintain optimal melt pool geometry and material addition rates.
Implementation Method 1
an energy source, an energy delivery head
Implementation Method 2
a thermal model of the DED MA technique for a component
Data Source
AI summary
A method may include controlling, by a computing device, a directed energy deposition material addition (DED MA) technique based at least in part on a thermal model. The thermal model may define a plurality of default operating parameters for the DED MA technique. The method also may include detecting, by at least one sensor, at least one parameter related to the DED MA technique. Further, the method may include, responsive to determining, by the computing device, that a value of the at least one detected parameter is different from an expected value of a corresponding parameter predicted by the thermal model, determining, by the computing device and using a neuro-fuzzy algorithm, an updated value for at least one operating parameter for the DED MA technique, and controlling, by the computing device, the DED MA technique based at least in part on the updated value.