Additive Manufacturing Candidate Screening Using ML and Data Filtering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing additive manufacturing processes lack a systematic and holistic approach to identify suitable objects for manufacturing, relying on manual and ad-hoc methods that are complex and inefficient, limiting the adoption and benefits of additive manufacturing.
Innovation Solution
A method utilizing data aggregation, filtering, and machine learning, specifically neural networks, to systematically identify candidate objects suitable for additive manufacturing by analyzing various data types, including economical, geometrical, and material features, and generating objects using additive manufacturing techniques.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If manual and ad-hoc methods are used to identify suitable objects for additive manufacturing, then the process can be performed without complex systems, but the complexity of the identification process increases and efficiency decreases
Solution Approach 1:
The patent replaces manual mechanical evaluation methods with an automated machine learning system that uses neural networks to evaluate objects for additive manufacturing suitability. The system automatically processes geometric, material, and economic data to identify suitable objects, eliminating the need for complex manual assessment procedures while improving ease of manufacture.
Solution Approach 2:
The machine learning system performs self-evaluation of objects by automatically analyzing their characteristics and determining suitability for additive manufacturing. The system serves itself by continuously learning from data and improving its identification accuracy without requiring external manual intervention for each object assessment.
2Productivity
If manual methods are used to identify suitable objects, then system complexity is reduced, but productivity and lead time are worsened
Solution Approach 1:
The patent replaces slow manual identification processes with an automated machine learning system that rapidly evaluates multiple objects simultaneously. The neural network architecture enables parallel processing of geometric, material, and economic data, dramatically increasing identification speed and productivity while accepting the necessary system complexity.
Solution Approach 2:
The system performs preliminary filtering of objects based on geometric, material, and economic criteria before detailed additive manufacturing evaluation. This preliminary action reduces the number of objects requiring full assessment, thereby increasing overall productivity while managing system complexity through staged processing.
3Measurement precision
If comprehensive data analysis is performed to identify suitable objects, then identification accuracy is improved, but processing time and computational resources increase
Solution Approach 1:
The patent segments the identification process into multiple independent evaluation modules: geometric suitability assessment, material compatibility analysis, and economic feasibility evaluation. Each module processes specific data types independently, allowing parallel computation that maintains high identification accuracy while reducing overall processing time through divided computational tasks.
Solution Approach 2:
The system performs preliminary filtering of objects and data before comprehensive analysis. By pre-processing data and eliminating obviously unsuitable objects early in the process, the system reduces the computational burden of detailed analysis while maintaining identification accuracy for the remaining candidate objects.
Data Source
AI summary
Examples described herein provide a computer-implemented method that includes aggregating data. The method further includes filtering the data to eliminate objects known not to be suitable for additive manufacturing. The method further includes performing machine learning on the data to identify objects suitable for additive manufacturing. The method further includes generating, using additive manufacturing, at least one of the objects identified as being suitable for additive manufacturing.