Additive Manufacturing Design Optimization for Mechanical Assembly Clustering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Manufacturers face challenges in adopting additive manufacturing due to a lack of information and in-house expertise, and existing technologies struggle to optimize mechanical design for combining mechanical parts into single pieces for 3D printing, which can reduce lead-time and costs but requires technical analysis and decision-making support.
Innovation Solution
A method and system for optimizing mechanical design in additive manufacturing that involves scanning digital files to identify mechanical connections, clustering connected parts, and iteratively estimating eligibility for combination into a single part, using deep learning algorithms and cost estimation to suggest optimal clusters for printing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If mechanical parts are combined into a single part for additive manufacturing, then productivity and cost are improved, but device complexity increases and manufacturing eligibility becomes more difficult to determine
Solution Approach 1:
The patent combines multiple mechanical parts into a single integrated part suitable for additive manufacturing. The system identifies clusters of connected mechanical parts that can be merged into one component, eliminating the need for separate manufacturing and assembly processes. This merging approach directly improves productivity by reducing the number of manufacturing steps and assembly operations while maintaining the functional requirements of the original multi-part design.
2Ease of operation
If mechanical parts are combined into a single part, then assembly and maintenance are simplified, but the difficulty of detecting and measuring manufacturing eligibility increases
Solution Approach 1:
The system performs self-service by automatically analyzing the digital file, identifying mechanical connections between parts, determining material compatibility, and evaluating eligibility criteria without requiring manual technical expertise. The algorithm autonomously assesses whether parts can be combined for additive manufacturing by checking geometric compatibility, material similarity, and connection types, thereby simplifying the process for users who lack specialized knowledge in additive manufacturing eligibility assessment.
3Measurement precision
If deep learning algorithms are used to scan digital files, then measurement precision of mechanical connections is improved, but use of energy and computational resources increases
Solution Approach 1:
The system applies partial action by using deep learning algorithms selectively only for scanning and identifying mechanical connections in digital files, rather than applying complex analysis to all aspects of the design process. The deep learning model focuses specifically on detecting connection geometries, hole patterns, and adjacency relationships, while other aspects like material selection and eligibility determination use simpler rule-based evaluation. This selective application of computationally intensive methods reduces overall energy consumption while maintaining high precision in connection identification.
Data Source
AI summary
A method of optimizing mechanical design for additive manufacturing, comprising: acquiring a digital file containing a description of a mechanical assembly, the assembly includes a plurality of mechanical parts; scanning the digital file to identify mechanical connections between adjacent of the plurality of mechanical parts; identifying a full cluster of connected mechanical parts based on the scanning, the connected mechanical parts are designed to be manufactured from similar materials; and identifying a usable cluster of connected mechanical parts to be combined into one mechanical part, the usable cluster is a sub-cluster of the full cluster, by iteratively: estimating eligibility of the mechanical parts in a current cluster to be manufactured as one mechanical part by additive manufacturing, the current cluster is a sub-cluster of the full cluster; and removing at least one mechanical part from the current cluster.