Sewing Machine Optical Sensor Calibration via Neural Networks

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing sewing machines lack advanced control systems that can adapt to various sewing tasks and materials, providing inadequate feedback and precision in stitch formation and material handling.

Innovation Solution

A sewing machine equipped with data gathering devices, storage, and neural networks that process data to control user interfaces and motors, enabling adaptive operation and precision through machine learning and sensor calibration.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If traditional control systems are used in sewing machines, then the device complexity is low, but the adaptability to various sewing tasks and materials is insufficient

Engineering Contradiction:
Improveadaptability to sewing tasksVSAvoidcontrol system complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent implements feedback mechanisms through optical sensors that continuously monitor stitch formation and material properties, with the control system adjusting sewing parameters in real-time based on sensor data to achieve adaptive operation

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The patent replaces traditional mechanical control systems with electronic and optical systems, including microprocessors, optical sensors, and automated needle position control, to enable sophisticated adaptability without proportional increase in mechanical complexity

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

2Manufacturing precision

If advanced control systems with sensors and neural networks are implemented, then precision in stitch formation is improved, but device complexity increases

Engineering Contradiction:
Improvestitch formation precisionVSAvoidcontrol system complexity
Core Design Contradiction:
Manufacturing precisionVSDevice complexity

Solution Approach 1:

Optical sensors provide real-time feedback on stitch formation quality and needle position, enabling the control system to make precise adjustments to maintain high stitching accuracy

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The neural network enables the system to automatically learn and optimize sewing parameters for different materials and tasks, reducing the need for manual configuration and achieving self-optimization of stitch formation precision

Inventive Principle:
Principle #25Self-service

3Adaptability or versatility

If real-time data processing through neural networks is implemented, then adaptability and precision are improved, but loss of time in data processing occurs

Engineering Contradiction:
Improvereal-time adaptabilityVSAvoiddata processing time
Core Design Contradiction:
Adaptability or versatilityVSLoss of time

Solution Approach 1:

The neural network is pre-trained with extensive sewing data and material characteristics before operation, enabling it to quickly process and respond to real-time sensor data without extensive computation during actual sewing

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP4430237B1Sewing machine and methods of using the same
Publication Date: 2025.09.24 SINGER SOURCING LTD LLC
  • EP4430237B1 patent drawingFigure 1
  • EP4430237B1 patent drawingFigure 2~3
  • EP4430237B1 patent drawingFigure 4~5

AI summary

A method for calibrating one or more optical sensors on a sewing machine, including collecting data of one or more features of one or more predefined regions associated with the sewing machine, processing the data through one or more neural networks, wherein the one or more neural networks detect and recognize the one or more features of the one or more predetermined regions from the data, calculating one or more accuracy indicators of the one or more features from the data as compared to one or more trained features from the one or more neural networks, comparing the value of the one or more accuracy indicators to one or more indicator thresholds and adjusting one or more parameters of one or more optical sensors based on the comparison between the one or more accuracy indicators and the one or more indicator thresholds.