Assembly Sequence Generation Using AI Contact Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current assembly planning methods are inefficient and costly due to the complexity of finding an optimal assembly sequence for products with many components, often requiring manual trial and error or specific algorithms that focus on validating rather than generating assembly sequences.
Innovation Solution
A system that uses data analytics and artificial intelligence to generate a feasible assembly plan by representing the assembly of a product as an assembly graph, which is then processed through data analytics modules, including an assembly descriptor module, a graph encoder module, and a contact generation model, to predict sequential contact connections between components.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual trial and error or brute force methods are used to generate assembly sequences, then complete exploration of assembly possibilities is achieved, but time consumption and computational cost increase exponentially
Solution Approach 1:
The system performs preliminary actions by representing the assembly problem as a graph structure before search begins, pre-computing component relationships, constraints, and compatibility information. This preliminary graph representation organizes all possible assembly states and transitions, enabling the subsequent search algorithm to efficiently navigate only feasible paths rather than exploring the entire exponential search space through brute force.
2Measurement precision
If algorithms are used to validate assembly sequences, then verification of assembly feasibility is improved, but the ability to generate assembly sequences from product information is limited
Solution Approach 1:
The graph-based representation serves multiple functions: it encodes component information, represents assembly constraints, models possible assembly states, and guides the search for valid sequences. This universal representation structure enables the system to both generate new assembly sequences from product information and validate existing sequences, combining the capabilities previously separated in different approaches.
3Manufacturing precision
If complete details of individual parts including geometry, alignment, and movement constraints are analyzed, then accurate assembly sequencing is achieved, but computational complexity and data processing requirements increase
Solution Approach 1:
The system segments the complex assembly planning problem into discrete graph elements: nodes represent assembly states or components, edges represent valid transitions or connections, and attributes encode specific constraints. This segmentation transforms the continuous, complex problem of analyzing geometry, alignment, and movement constraints into a discrete graph structure that can be processed efficiently by search algorithms while preserving all necessary detail for accurate sequencing.
Data Source
AI summary
Aspects of the present disclosure provide systems, methods, and computer-readable storage media that support mechanisms for generating a feasible assembly plan for a product based on data analytics. In aspects, information on components of a product is obtained from one or more product models (e.g., a three-dimensional (3D) computer aided design (CAD) model) that define the individual components of the product. The individual component information may be used to represent the assembly of the product as an assembly graph, in which each node of the assembly graph represents one of the components of the product to be assembled. The assembly graph is passed through a set of data analytics modules to generate the feasible assembly plan, or assembly sequence, as a series of sequential contact predictions, wherein each contact prediction identifies a component to be connected to one or more other components of the product.