3D Printed Conformal Strain and Humidity Sensors for Human Motion Prediction and Health Monitoring via Machine Learning

Abstract Wearable sensors have garnered considerable attention due to their flexibility and lightweight characteristics in the realm of healthcare applications. However, developing robust wearable sensors with facile fabrication and good conformity remains a challenge. In this study, a conductive graphene nanoplate‐carbon nanotube (GC) ink is synthesized for multi jet fusion (MJF) printing. The layer‐by‐layer fabrication process of MJF not only improves the mechanical and flame‐retardant properties of the printed GC sensor but also bolsters its robustness and sensitivity. The direction of sensor bending significantly impacts the relative resistance changes, allowing for precise investigations of joint motions in the human body, such as those of the fingers, wrists, elbows, necks, and knees. Furthermore, the data of resistance changes collected by the GC sensor are utilized to train a support vector machine with a 95.83% accuracy rate for predicting human motions. Due to its stable humidity sensitivity, the sensor also demonstrates excellent performance in monitoring human breath and predicting breath modes (normal, fast, and deep breath), thereby expanding its potential applications in healthcare. This work opens up new avenues for using MJF‐printed wearable sensors for a variety of healthcare applications.


3D Printed Conformal Strain and Humidity Sensors for Human Motion Prediction and Health Monitoring via Machine Learning
Yanbei Hou, Ming Gao, Jingwen Gao, Lihua Zhao, Teo Hang Tong Edwin, Dong Wang, H. Jerry Qi, and S1.Advanced MJF printing process.A repeated unit is composed of fused TPU powder and dried GC ink.Following the deposition of TPU powder on the initial unit, the next step involved selectively spraying FA in accordance with the design.Upon heat absorption by the FA, the TPU powder particles fuse together to form a fresh TPU layer.Subsequently, the GC ink is selectively applied to the TPU layer and allowed to dry to create a conductive layer.These steps ultimately lead to the creation of the second unit.Units are stacked repeatedly to form a multilayered printing product.    of conductivity and printability of GNP, CNTs, and GC inks.The electrical resistances of ink compositions that are not suitable for printing, namely GNP and GNP (75%)/CNTs (25%), were measured by analyzing films produced through ink drying.In contrast, the conductivities of other ink formulations were determined by examining printed samples created through a MJF testbed that utilized 3-pass ink jetting.The samples used for the conductivity test are of identical size to the GC/TPU samples that were printed.

Figure S2 .
Figure S2.Characterization of GC ink.(a) SEM image of exfoliated GNPs; (b) TEM image of CNTs; (c) SEM image of the GC ink; (d) SEM fractography of the selfsupporting GC film.

Figure
Figure S3. a The thermosensitive properties of the GC film.A lamp emitting radiation equivalent to 1 solar intensity was employed to thermally stimulate the GC film, which underwent gradual torsional deformation until it reached a stabilized conformation; b The fractured section of GC film.

Figure
Figure S4. a Schematic illustration of the simulated solar irradiation setup; b The photothermal performance of GC ink deposited with different passes.

Figure
Figure S5. a The conductivity of printed parts with different passes; b The comparison

Figure S6 .
Figure S6.TGA results of GC hybrids, PVP, and dried GC ink.The final residue weights of GC, PVP, and dried GC ink were 75.70 wt%, 2.06 wt%, and 44.51 wt%, respectively.Based on the equation  GC  +  PVP (1 − ) =  dried GC , where w is the weight percentage of GC in the dried GC ink, and  GC ,  PVP , and  dried GC are the final residue weight of GC, PVP, and dried GC ink, respectively.The content of GC in the ink was calculated to be 42.998%, which matched well with the designed composition.

Figure S8 .
Figure S8.Output signals of the GC sensor collected at the bending of the neck.a lower head; b Raise head.

Figure S9 .
Figure S9.Relative resistance variation of GC sensor versus relative humidity ranging from 10% to 90%.

Table S1 .
The comparison of manufacturing approaches of strain/humidity sensors.

Table S2 .
Data summary presented in the manuscript.The sign "-" denotes that the item was not tested in this work.

Table S3 .
Sample size distribution