ML-Guided Object Design for Manufacturability Feedback

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional design processes for manufacturing objects often fail to consider production and cost implications, leading to non-ideal outcomes in terms of quality and cost due to limited feedback and outdated specifications, resulting in designs that are not producible or cost-effective.

Innovation Solution

A system utilizing a processor and machine-learning model that analyzes design data to suggest modifications or adjustments for production conditions, incorporating object features, process parameters, and environmental factors to improve manufacturing efficiency and reduce defects.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If designers focus on performance metrics without considering production constraints, then design performance is improved, but manufacturability and cost effectiveness deteriorate

Engineering Contradiction:

Improvedesign performanceVSAvoidmanufacturability

Core Design Contradiction:

ReliabilityVSEase of manufacture

Solution Approach 1:

The system implements a feedback mechanism where production data from the manufacturing system is fed back to designers through a user interface. This feedback includes information about design choices and their consequences on production, allowing designers to adjust their designs to balance performance with manufacturability and cost effectiveness.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

A machine learning model acts as an intermediary between the design system and production system. The model processes design data and production data to generate predictions about manufacturability and cost, translating complex production constraints into actionable insights for designers without requiring them to become experts in manufacturing processes.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Stability of the object's composition

If static production specifications are used, then production stability is maintained, but adaptability to new manufacturing technologies deteriorates

Engineering Contradiction:

Improveproduction stabilityVSAvoidadaptability to new technologies

Core Design Contradiction:

Stability of the object's compositionVSAdaptability or versatility

Solution Approach 1:

The system transitions from static production specifications to dynamic, adaptive specifications. The machine learning model continuously learns from new production data and updates its predictions, allowing the production system to adapt to new manufacturing technologies and processes while maintaining stability through data-driven decision making.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system performs preliminary analysis of design choices using the machine learning model before actual production begins. This allows potential issues with new manufacturing technologies to be identified and addressed in advance, maintaining production stability while enabling adaptability to new methods.

Inventive Principle:

Principle #10Preliminary action

3Productivity

If designers work without real-time production feedback, then design speed is improved, but design quality and cost effectiveness deteriorate

Engineering Contradiction:

Improvedesign speedVSAvoiddesign quality

Core Design Contradiction:

ProductivityVSManufacturing precision

Solution Approach 1:

The system provides real-time feedback to designers during the design process through a user interface. The machine learning model analyzes design data as it is created and immediately provides predictions about production consequences, allowing designers to make informed decisions without slowing down the design process.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The system replaces traditional manual consultation with manufacturing engineers or post-design reviews with an automated machine learning-based feedback system. This substitution provides immediate, consistent, and scalable feedback to multiple designers simultaneously, improving both design speed and quality without requiring additional human resources.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS11256231B2Object design using machine-learning model

Publication Date: 2022.02.22 THE BOEING CO

AI summary

A system to aid in design for manufacturing an object includes a processor and a memory configured to store instructions. The processor is configured to receive first data representing a design of the object to be manufactured and second data representing a machine-learning model. The processor is configured to execute the instructions to generate third data using the first data and the second data. The third data indicates at least one of a modification to the design of the object or process conditions for production of the object. The processor is configured to send the design of the object, the process conditions, or both, to a manufacturing tool to enable production of the object. The machine-learning model is representative of production data and based at least partially on one or more of: object features, process parameters, environmental factors, and quality data.