AI Scan Strategy Optimization for Additive Construction Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing additive manufacturing processes face challenges in optimizing process variables to balance component quality, mechanical properties, and productivity, as well as efficiency and cost, due to the complex interplay of factors such as scanning direction, energy beam parameters, and material application methods.
Innovation Solution
A method utilizing AI-based optimization units, particularly neural networks, to determine optimized scanning direction distributions and parameter sets for additive manufacturing processes, which are then used to generate control data for production devices, ensuring adherence to predefined evaluation criteria and maintaining quality and efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If traditional optimization methods are used to determine process variable values, then manufacturing precision and component quality can be improved, but productivity and construction speed deteriorate due to extensive computational requirements
Solution Approach 1:
The patent creates a trained neural network model in advance that has learned the complex relationships between process variables and component properties. During actual production, this pre-trained model provides instant predictions and optimizations without requiring extensive computational resources, thus maintaining high manufacturing precision while significantly improving construction speed and productivity
Solution Approach 2:
The patent replaces traditional computational optimization methods (which require extensive calculations and simulations) with an AI-based neural network system. This substitution transforms the optimization process from a computationally intensive mechanical calculation system into an intelligent prediction system that delivers results much faster, resolving the contradiction between precision and productivity
2Strength
If extensive optimization calculations are performed to achieve optimal process parameters, then component mechanical properties improve, but energy consumption and construction costs increase
Solution Approach 1:
The neural network model is trained in advance using comprehensive datasets that capture the relationships between process parameters and mechanical properties. Once trained, the model can instantly predict optimal parameters without requiring extensive computational resources during production, thus achieving optimal mechanical properties while minimizing energy consumption and construction costs
Solution Approach 2:
The patent creates a virtual model (neural network) that copies and represents the complex physical relationships between process variables and material properties. This digital twin allows for rapid predictions and optimizations without requiring physical experiments or extensive computational simulations, reducing both energy consumption and costs while maintaining high component quality
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
This approach enables a comprehensive optimization of additively manufactured components, balancing quality, mechanical properties, and productivity while reducing computational effort, and allows for the generation of control data that ensures precise and efficient production processes.
Implementation Method 1
the construction material is selectively solidified by spatially limited irradiation of the points that are to be part of the manufacturing product to be manufactured after production in a kind of 'welding process', in which the powder grains of the construction material are partially or completely melted with the help of the energy introduced locally by the radiation at this point
Implementation Method 2
Some of the process variables have a significant influence on the resulting local microstructure in the component... the key process variables can include not only the aforementioned process parameter values of the energy beam
Data Source
AI summary
Disclosed is a method and a device for generating optimized process variable values for an additive manufacturing process of a manufacturing product. For this purpose, requirement data of the manufacturing product is provided. An optimization process is then carried out in order to determine the optimized process variable values while taking into consideration the requirement data, wherein at least one optimized scanning direction distribution for at least one region of the manufacturing product is determined as an optimized process variable value using an AI-based optimization unit. The optimized process variable values are then provided. Further disclosed is a method and a control data generating device for generating control data, to a method for creating an AI-based optimization unit, to a control method, and to a controller for a production device for the additive manufacturing process, and to a corresponding production device.