Machine Learning-Based Predictions on the Self-Heating Characteristics of Nanocomposites with Hybrid Fillers

Abstract

A machine learning-based prediction of the self-heating characteristics and the negative temperature coefficient (NTC) effect detection of nanocomposites incorporating carbon nanotube (CNT) and carbon fiber (CF) is proposed. The CNT content was fixed at 4.0 wt.%, and CFs having three different lengths (0.1, 3 and 6 mm) at dosage of 1.0 wt.% were added to fabricate the specimens. The self-heating properties of the specimens were evaluated via self-heating tests. Based on the experiment results, two types of artificial neural network (ANN) models were constructed to predict the surface temperature and electrical resistance, and to detect a severe NTC effect. The present predictions were compared with experimental values to verify the applicability of the proposed ANN models. The ANN model for data prediction was able to predict the surface temperature and electrical resistance closely, with corresponding R-squared value of 0.91 and 0.97, respectively. The ANN model for data detection could detect the severe NTC effect occurred in the nanocomposites under the self-heating condition, as evidenced by the accuracy and sensitivity values exceeding 0.7 in all criteria.

A multiscale modeling framework for predicting strain‐dependent electrical conductivity of carbon nanotube‐incorporated nanocomposites considering the electron tunneling effect

“…The CNTs had an average length of approximately 10.0 μm and a diameter of 26.0 nm. 14,39 To improve the dispersion of the CNTs into the nanocomposites, polysodium4-styrene sulfonate (PSS) was used as a dispersant. Five different mix proportions were used to fabricate the CNT/PDMS samples, as summarized in Table 3.…”

“…Multi‐walled CNT (Kumho Petrochemical, Co., K‐Nanos 100P) with a purity rate of >90% and a bulk density of 0.02 g/cm 3 was used as the nanoscale conductive filler. The CNTs had an average length of approximately 10.0 μm and a diameter of 26.0 nm 14,39 . To improve the dispersion of the CNTs into the nanocomposites, polysodium4‐styrene sulfonate (PSS) was used as a dispersant.…”

“…Five different mix proportions were used to fabricate the CNT/PDMS samples, as summarized in Table 3. The CNT content and CNT‐to‐PSS ratio were determined by references from a previous study 14 . The sample ID in each case was designated based on the corresponding CNT content used: i.e., 3.0‐CNT/PDMS samples indicate the PDMS samples incorporating 3.0 wt.% CNTs.…”

“…12 Meanwhile, predicting the strain-dependent electrical conductivity of CNT-incorporated nanocomposites is challenging due to the effects of the waviness of the CNTs in the polymer matrix and the electron tunneling phenomenon at the imperfect interface. [14][15][16][17] First, CNTs incorporated in the polymer matrix are often observed to be curved and looped instead of straight due to the viscosity of a polymer matrix used and the high aspect ratio of CNTs. 18,19 As a result, curved CNT may lead to an inhomogeneous distribution within the matrix, decreasing the electrical conductivity of the nanocomposites.…”

Electrical Stability and Piezoresistive Sensing Performance of High Strain-Range Ultra-Stretchable CNT-Embedded Sensors

“…For these reasons, conductive polymeric composites are regarded as potential candidates to be utilized as such sensors [ 5 ]. Many types of conductive fillers have been introduced to fabricate the conductive polymeric composites; however, the carbon nanotubes (CNTs) are found to be favorable conductive fillers due to their outstanding mechanical and piezoresistive sensing properties [ 6 , 7 , 8 ].…”