Three-dimensional machine knitting of electronic textile for activity recognition and biomechanical monitoring

Patent metadata

Field	Value
Publication number	US-12247332-B2
Application number	US-202318311527-A
Country	US
Kind code	B2
Filing date	May 3, 2023
Priority date	May 3, 2022
Publication date	Mar 11, 2025
Grant date	Mar 11, 2025

Abstract

Disclosed herein are systems and techniques for seamless and scalable piezoresistive matrix-based intelligent textile development using digital flat-bed and circular knitting machines. Disclosed embodiments allow for combining and customizing functional conductive and polyester and spandex yarns, thus allowing for designing the aesthetics and architecting and engineering both the electrical and mechanical properties of the pressure sensing textile. In addition, by incorporating a melting fiber, disclosed embodiments allow for shaping and personalizing a three-dimensional piezoresistive fabric structure that can conform to the human body through thermoforming principles.

First claim

The invention claimed is:

1. A system for use with a knitted textile having a plurality of pressure sensing points, the system comprising:
a plurality of column lines connected to the textile and a first multiplexer;
a plurality of row lines connected to the textile and a second multiplexer; and
one or more digital circuits configured to:
control the first multiplexer to periodically switch a voltage supply to each of the plurality of column lines while putting the rest of the column lines on high-impedance,
control the second multiplexer to sequentially connect to ones of the plurality of row lines to a potential divider while grounding the other row lines for reading out values of the plurality of pressure sensing points, and
provide the values of the plurality of pressure sensing points to a processing system configured to generate one or more pressure distributions based on the values of the plurality of pressure sensing points and to recognize activities of a wearer of the knitted textile based on the pressure distributions and using machine learning (ML).

2. The system of claim 1 wherein the one or more digital circuits comprise a shift register arranged to control the second multiplexer.

3. The system of claim 1 wherein the one or more digital circuits comprise a processor configured to control the first multiplexer.

4. The system of claim 3 wherein the processor is further configured to wirelessly transmit the values of the plurality of pressure sensing points to a remote the processing system.

5. The system of claim 1 wherein the pressure distributions are images having 2D arrays of pixels, wherein the processing system is configured to recognize the activities of the wearer by providing the images as input to a Convolutional Neural Network (CNN) trained to classify human activities.

6. The system of claim 1 comprising the processing system.

Assignees

• Massachusetts Inst Technology

Inventors

• Paradiso Joseph A
• Wicaksono Irmandy

Classifications

• G06F2203/04105

  Pressure sensors for measuring the pressure or force exerted on the touch surface without providing the touch position · CPC title

• G06F3/045

  using resistive elements, e.g. a single continuous surface or two parallel surfaces put in contact · CPC title

• G06F3/0416

  Control or interface arrangements specially adapted for digitisers · CPC title

• G06F3/04144

  using an array of force sensing means (position sensing using the local deformation of sensor cells G06F3/0447) · CPC title

• D10B2331/02

  polyamides (D10B2331/08 takes precedence) · CPC title