Textination Newsline

Archive
Reset
2 results
NC State Research: Machine Learning to Create a Fabric-Based Touch Sensor (c) NC State University
article as PDF
13.05.2024

Machine Learning to Create a Fabric-Based Touch Sensor

A new study from NC State University combines three-dimensional embroidery techniques with machine learning to create a fabric-based sensor that can control electronic devices through touch.

As the field of wearable electronics gains more interest and new functions are added to clothing, an embroidery-based sensor or “button” capable of controlling those functions becomes increasingly important. Integrated into the fabric of a piece of clothing, the sensor can activate and control electronic devices like mobile apps entirely by touch.  

A new study from NC State University combines three-dimensional embroidery techniques with machine learning to create a fabric-based sensor that can control electronic devices through touch.

As the field of wearable electronics gains more interest and new functions are added to clothing, an embroidery-based sensor or “button” capable of controlling those functions becomes increasingly important. Integrated into the fabric of a piece of clothing, the sensor can activate and control electronic devices like mobile apps entirely by touch.  

The device is made up of two parts; the embroidered pressure sensor itself and a microchip which processes and distributes the data collected by that sensor. The sensor is triboelectric, which means that it powers itself using the electric charge generated from the friction between its multiple layers. It is made from yarns consisting of two triboelectric materials, one with a positive electric charge and the other with a negative charge, which were integrated into conventional textile fabrics using embroidery machines.

Rong Yin, corresponding author of the study, said that the three-dimensional structure of the sensor was important to get right.

“Because the pressure sensor is triboelectric, it needed to have two layers with a gap in between them. That gap was one of the difficult parts in the process, because we are using embroidery which is usually two-dimensional. It’s a technique for decorating fabric,” he said. “It’s challenging to make a three-dimensional structure that way. By using a spacer, we were able to control the gap between the two layers which lets us control the sensor’s output.”

Data from the pressure sensor is then sent to the microchip, which is responsible for turning that raw input into specific instructions for any connected devices. Machine learning algorithms are key to making sure this runs smoothly, Yin said. The device needs to be able to tell the difference between gestures assigned to different functions, as well to disregard any unintentional inputs that might come from the cloth’s normal movement.

“Sometimes the data that the sensor acquires is not very accurate, and this can happen for all kinds of reasons,” Yin said. “Sometimes the data will be affected by environmental factors like temperature or humidity, or the sensor touches something by mistake. By using machine learning, we can train the device to recognize those kinds of things.

“Machine learning also allows this very small device to achieve many different tasks, because it can recognize different kinds of inputs.”

The researchers demonstrated this input recognition by developing a simple music playing mobile app which connected to the sensor via Bluetooth. They designed six functions for the app: play/pause, next song, last song, volume up, volume down and mute, each controlled by a different gesture on the sensor. Researchers were able to use the device for several other functions, including setting and inputting passwords and controlling video games.

The idea is still in its early stages, Yin said, as existing embroidery technology is not capable of easily handling the types of materials used in the creation of the sensor. Still, the new sensor represents another piece of the developing wearable electronics puzzle, which is sure to continue picking up interest in the near future.

The paper, “A clickable embroidered triboelectric sensor for smart fabric,” is published in Device.

More information:
North Carolina State University NC State University Smart textiles textile-based sensors
Source:

North Carolina State University, Joey Pitchford

print close
more
North Carolina State University
article as PDF
17.01.2023

Embroidery as Low-Cost Solution for Making Wearable Electronics

Embroidering power-generating yarns onto fabric allowed researchers to embed a self-powered, numerical touch-pad and movement sensors into clothing. The technique offers a low-cost, scalable potential method for making wearable devices.

“Our technique uses embroidery, which is pretty simple – you can stitch our yarns directly on the fabric,” said the study’s lead author Rong Yin, assistant professor of textile engineering, chemistry and science at North Carolina State University. “During fabric production, you don’t need to consider anything about the wearable devices. You can integrate the power-generating yarns after the clothing item has been made.”

Embroidering power-generating yarns onto fabric allowed researchers to embed a self-powered, numerical touch-pad and movement sensors into clothing. The technique offers a low-cost, scalable potential method for making wearable devices.

“Our technique uses embroidery, which is pretty simple – you can stitch our yarns directly on the fabric,” said the study’s lead author Rong Yin, assistant professor of textile engineering, chemistry and science at North Carolina State University. “During fabric production, you don’t need to consider anything about the wearable devices. You can integrate the power-generating yarns after the clothing item has been made.”

In the study published in Nano Energy, researchers tested multiple designs for power-generating yarns. To make them durable enough to withstand the tension and bending of the embroidery stitching process, they ultimately used five commercially available copper wires, which had a thin polyurethane coating, together. Then, they stitched them onto cotton fabric with another material called PTFE.

“This is a low-cost method for making wearable electronics using commercially available products,” Yin said. “The electrical properties of our prototypes were comparable to other designs that relied on the same power generation mechanism.”

The researchers relied on a method of generating electricity called the “triboelectric effect,” which involves harnessing electrons exchanged by two different materials, like static electricity. They found the PTFE fabric had the best performance in terms of voltage and current when in contact with the polyurethane-coated copper wires, as compared to other types of fabric that they tested, including cotton and silk. They also tested coating the embroidery samples in plasma to increase the effect.

“In our design, you have two layers – one is your conductive, polyurethane-coated copper wires, and the other is PTFE, and they have a gap between them,” Yin said. “When the two non-conductive materials come into contact with each other, one material will lose some electrons, and some will get some electrons. When you link them together, there will be a current.”
Researchers tested their yarns as motion sensors by embroidering them with the PTFE fabric on denim. They placed the embroidery patches on the palm, under the arm, at the elbow and at the knee to track electrical signals generated as a person moves. They also attached fabric with their embroidery on the insole of a shoe to test its use as a pedometer, finding their electrical signals varied depending on whether the person was walking, running or jumping.

Lastly, they tested their yarns in a textile-based numeric keypad on the arm, which they made by embroidering numbers on a piece of cotton fabric, and attaching them to a piece of PTFE fabric. Depending on the number that the person pushed on the keypad, they saw different electrical signals generated for each number.

“You can embroider our yarns onto clothes, and when you move, it generates an electrical signal, and those signals can be used as a sensor,” Yin said. “When we put the embroidery in a shoe, if you are running, it generates a higher voltage than if you were just walking. When we stitched numbers onto fabric, and press them, it generates a different voltage for each number. It could be used as an interface.”

Since textile products will inevitably be washed, they tested the durability of their embroidery design in a series of washing and rubbing tests. After hand washing and rinsing the embroidery with detergent, and drying it in an oven, they found no difference or a slight increase in voltage. For the prototype coated in plasma, they found weakened but still superior performance compared with the original sample. After an abrasion test, they found that there was no significant change in electrical output performance of their designs after 10,000 rubbing cycles.

In future work, they plan to integrate their sensors with other devices to add more functions.
“The next step is to integrate these sensors into a wearable system,” Yin said.

The study, “Flexible, durable and washable triboelectric yarn and embroidery for self-powered sensing and human-machine interaction,” was published online in Nano Energy. Co-authors included Yu Chen, Erdong Chen, Zihao Wang, Yali Ling, Rosie Fisher, Mengjiao Li, Jacob Hart, Weilei Mu, Wei Gao, Xiaoming Tao and Bao Yang. Funding was provided by North Carolina State University through the NC State Faculty Research & Professional Development Fund and the NC State Summer REU program.

 

More information:
NC State University Wilson College embroidery thread wearable sensors wearables
Source:

North Carolina State University, Rong Yin, Laura Oleniacz

print close
more