Generative Additive Design for Rapid Industrial Asset Geometry Exploration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional design tools for industrial asset items, especially those intended for additive manufacturing, are reductive and require expert knowledge, limiting designer interaction and being slow for rapid exploration of design spaces, whereas additively manufactured parts require continuous designer interaction and feedback.
Innovation Solution
A system incorporating a deep learning model platform that uses prior industrial asset item designs to automatically create boundaries and geometries for industrial asset items based on constraint and load information, allowing for generative design and optimization with continuous designer feedback, leveraging a design experience data store and additive manufacturing processes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If traditional optimization techniques (e.g., topology optimization) are used to begin with a large block of material and systematically remove portions, then the design process works well for reductive manufacturing processes, but it significantly limits the interaction that the designer has with the design process and is not suited for rapid exploration of multiple design spaces
Solution Approach 1:
The patent inverts the traditional reductive design approach by using generative design techniques that start with design requirements and constraints to directly generate optimal geometries for additive manufacturing, rather than starting with a bulk material and removing portions. This inversion enables better designer interaction and rapid exploration of multiple design spaces while being specifically suited for additive manufacturing processes.
Solution Approach 2:
The patent implements continuous feedback loops between the designer and the generative design system, allowing real-time interaction and adjustment of design parameters. This feedback mechanism enables rapid exploration of multiple design spaces and maintains high designer engagement throughout the design process, unlike traditional automated optimization approaches.
2Manufacturing precision
If traditional design tools are used, then expert knowledge from multiple disciplines is required, but this makes the design process relatively slow
Solution Approach 1:
The generative design system performs automated multi-disciplinary optimization, automatically integrating structural, thermal, and manufacturing constraints without requiring continuous expert intervention. The system serves itself by autonomously exploring design spaces and generating optimized geometries, thereby maintaining high design accuracy while dramatically reducing design cycle time.
Solution Approach 2:
The patent utilizes parameter-driven generative design where design geometries are automatically adjusted based on changing constraints and requirements. This parameter-based approach allows rapid exploration of multiple design configurations while maintaining manufacturing precision, eliminating the need for slow manual re-evaluation by experts.
3Shape
If additively manufactured parts are designed to look like sculpted components, then continuous interaction by the designer is required, but this increases the complexity of the design process
Solution Approach 1:
The generative design system acts as an intermediary between the designer's intent and the complex sculpted geometries required for additive manufacturing. The system translates simple design requirements into complex optimized shapes automatically, maintaining the desired sculpted component geometry while reducing design process complexity by eliminating manual iteration.
Data Source
AI summary
According to some embodiments, a system may include a design experience data store containing electronic records associated with prior industrial asset item designs. A deep learning model platform, coupled to the design experience data store, may include a communication port to receive constraint and load information from a designer device. The deep learning platform may further include a computer processor adapted to automatically and generatively create boundaries and geometries, using a deep learning model associated with an additive manufacturing process, for an industrial asset item based on the prior industrial asset item designs and the received constraint and load information. According to some embodiments, the deep learning model computer processor is further to receive design adjustments from the designer device. The received design adjustments might be for example, used to execute an optimization process and/or be fed back to continually re-train the deep learning model.