Fabric Feature Prediction via Reference Equations

Solution Overview

Problem

Current methods for determining fabric features require manual measurements, which are time-consuming and costly.

Innovation Solution

A fabric feature predicting method that generates equations based on actual feature values and information groups of known fabrics to predict the features of a second fabric without manual measurement, using a processor and memory to select corresponding fabrics and calculate predicted feature values.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual measurements are performed to determine fabric features, then accurate fabric feature data is obtained, but the process consumes more time and incurs higher costs

Engineering Contradiction:

Improvefabric feature accuracyVSAvoidmeasurement time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system performs preliminary actions by pre-measuring multiple reference fabrics and storing their actual feature values and information groups in advance. When predicting features for a target fabric, the system selects relevant reference fabrics from the pre-established database and applies pre-generated equations, eliminating the need for real-time manual measurement of the target fabric while maintaining measurement accuracy through the use of empirically validated prediction models

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system creates a virtual copy of the measurement process by establishing mathematical relationships (equations) between fabric information groups and actual feature values based on reference fabrics. These equations serve as digital replicas of the physical measurement process, allowing the system to predict fabric features through calculation rather than physical measurement, thereby reducing time and cost while preserving measurement precision

Inventive Principle:

Principle #26Copying

2Measurement precision

If manual measurements are performed to determine fabric features, then accurate fabric feature data is obtained, but the process incurs higher costs

Engineering Contradiction:

Improvefabric feature accuracyVSAvoidmeasurement cost

Core Design Contradiction:

Measurement precisionVSEase of manufacture

Solution Approach 1:

The system performs preliminary actions by pre-measuring multiple reference fabrics and storing their actual feature values and information groups in advance. When predicting features for a target fabric, the system selects relevant reference fabrics from the pre-established database and applies pre-generated equations, eliminating the need for real-time manual measurement of the target fabric while maintaining measurement accuracy through the use of empirically validated prediction models

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system creates a virtual copy of the measurement process by establishing mathematical relationships (equations) between fabric information groups and actual feature values based on reference fabrics. These equations serve as digital replicas of the physical measurement process, allowing the system to predict fabric features through calculation rather than physical measurement, thereby reducing time and cost while preserving measurement precision

Inventive Principle:

Principle #26Copying

3Loss of time

If equations are generated based on selected reference fabrics to predict fabric features, then measurement time and cost are reduced, but the prediction accuracy depends on the selection of appropriate reference fabrics

Engineering Contradiction:

Improvemeasurement timeVSAvoidprediction accuracy

Core Design Contradiction:

Loss of timeVSReliability

Solution Approach 1:

The system applies local quality by selecting reference fabrics that are locally similar to the target fabric based on fabric information group characteristics. The selection process identifies reference fabrics with comparable properties (such as fiber composition, weave structure, or weight) to ensure that the mathematical relationships established from these references are applicable and accurate for the specific target fabric being predicted

Inventive Principle:

Principle #3Local quality

Solution Approach 2:

The system implements feedback by using the fabric information group as a selection criterion to identify the most relevant reference fabrics. This feedback mechanism ensures that only reference fabrics with similar characteristics to the target fabric are used for prediction, thereby maintaining high prediction accuracy while reducing measurement time through targeted selection rather than comprehensive measurement

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS20240151707A1Fabric feature predicting method

Publication Date: 2024.05.09 TAIWAN TEXTILE RESEARCH INSTITUTE

AI summary

A fabric feature predicting method includes following operations: measuring multiple first fabrics to generate multiple first fabric actual feature value groups; storing the first fabric actual feature value groups and multiple first fabric information groups of the first fabrics; selecting multiple third fabrics from the first fabrics according to a second fabric information group of a second fabric; generating at least one equation according to multiple third fabric actual feature value groups of the third fabrics and multiple third fabric information groups of the third fabrics; generating a second fabric predicted feature value group of the second fabric according to the at least one equation and the second fabric information group. The first fabric actual feature value groups include the third fabric actual feature value groups. The first fabric information groups include the third fabric information groups.