Assembly Dimension Tolerance Optimization Using Neural Yield Prediction

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current methods for determining dimension tolerance, such as Worst-Case Method Analysis and Statistical Model Analysis, are not effective in optimizing tolerances for assembled products, leading to potential assembly issues and increased manufacturing costs due to inadequate precision.

Innovation Solution

A method and system utilizing a neural network model to generate key parameters and calculate assembly yield rates based on tolerance data sets, optimizing dimension tolerances for assembled products by selecting the most suitable tolerance data set within a design range.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Manufacturing precision

If smaller dimension tolerance is used to achieve higher dimension precision, then manufacturing cost and equipment requirements increase

Engineering Contradiction:

Improvedimension precisionVSAvoidmanufacturing cost

Core Design Contradiction:

Manufacturing precisionVSEase of manufacture

Solution Approach 1:

The patent applies parameter changes by using a neural network model to dynamically determine optimal tolerance values for different parts based on their specific characteristics, functional requirements, and assembly relationships. Instead of uniformly applying small tolerances, the system calculates customized tolerance parameters that achieve necessary precision while minimizing manufacturing costs.

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The patent implements partial action by applying strict tolerances only to critical parts where precision is essential for assembly functionality, while allowing larger tolerances for non-critical parts. The neural network identifies which parts require tight tolerances and which can tolerate larger variations, optimizing the overall balance between precision and cost.

Inventive Principle:

Principle #16Partial or excessive action

2Ease of manufacture

If larger dimension tolerance is used to reduce manufacturing cost, then assembly quality and functionality may be compromised

Engineering Contradiction:

Improvemanufacturing costVSAvoidassembly quality

Core Design Contradiction:

Ease of manufactureVSReliability

Solution Approach 1:

The patent applies preliminary action by performing tolerance analysis and optimization during the design stage using a neural network model. The system predicts assembly outcomes and identifies potential quality issues before manufacturing begins, allowing tolerance adjustments to be made proactively rather than reacting to assembly problems after production.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent implements feedback by using the neural network model to evaluate the impact of proposed tolerance values on assembly quality and functionality. The system provides feedback on whether selected tolerances will achieve the required assembly performance, allowing iterative optimization of tolerance parameters to ensure both cost-effectiveness and quality.

Inventive Principle:

Principle #23Feedback

3Productivity

If traditional tolerance analysis methods (Worst-Case or Statistical Model) are used, then assembly yield rate may be insufficient

Engineering Contradiction:

Improveassembly yield rateVSAvoidtolerance optimization effectiveness

Core Design Contradiction:

ProductivityVSManufacturing precision

Solution Approach 1:

The patent applies mechanics substitution by replacing traditional mechanical tolerance analysis methods (Worst-Case Method and Statistical Model Analysis) with an intelligent neural network-based system. The neural network learns from historical data and simulation results to predict optimal tolerances and assembly yield rates, providing a more accurate and efficient alternative to conventional analytical methods.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent implements preliminary action by using the neural network model to pre-determine optimal tolerance values and predict assembly yield rates before actual manufacturing and assembly. The system performs virtual tolerance analysis and optimization in advance, allowing manufacturers to set appropriate tolerances that maximize assembly yield rate without requiring extensive trial-and-error testing.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS11703840B2Dimension tolerance determining method and dimension tolerance determination system thereof

Publication Date: 2023.07.18 LIN JHONG YI

AI summary

A dimension tolerance determining method and a system are disclosed. The method includes: determining initial tolerances of parts in assembled product; generating a plurality of tolerance data sets according to initial tolerances of parts, each tolerance data set containing a calculated part tolerance of each part; inputting the plurality of tolerance data sets into a key parameter generation module to generate a plurality of key parameters corresponding to the assembled product, wherein each key parameter corresponds to one tolerance data set; when the key parameters are located within a design range, calculating a plurality of assembly yield rates based on the tolerance data sets corresponding to the key parameters located within the design range; and selecting the tolerance data set corresponding to one of the assembly yield rates as the tolerances of the parts in the assembled product; wherein the key parameter generation module includes a neural network model.