2022
DOI: 10.1039/d2ta03422k
|View full text |Cite
|
Sign up to set email alerts
|

Object recognition by a heat-resistant core-sheath triboelectric nanogenerator sensor

Abstract: Compared to traditional rigid, and energy-consumptive sensors, self-powered flexible sensors have attracted extensive attention. However, few of them can survive at high temperatures, which restricts their application in many extreme...

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1

Citation Types

0
8
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
6

Relationship

1
5

Authors

Journals

citations
Cited by 31 publications
(11 citation statements)
references
References 40 publications
0
8
0
Order By: Relevance
“…Support vector machine (SVM) is an efficient method for data classification and has been widely used in human motion monitoring. [37,38] Therefore, an SVM machine-learning algorithm is designed, which is combined with IF-TENG sensors to classify and recognize the above motions (Figure 4c). Specifically, the analog voltage data of IF-TENGs is collected by the hardware circuit through an oscilloscope and converted into digital voltage.…”
Section: Resultsmentioning
confidence: 99%
“…Support vector machine (SVM) is an efficient method for data classification and has been widely used in human motion monitoring. [37,38] Therefore, an SVM machine-learning algorithm is designed, which is combined with IF-TENG sensors to classify and recognize the above motions (Figure 4c). Specifically, the analog voltage data of IF-TENGs is collected by the hardware circuit through an oscilloscope and converted into digital voltage.…”
Section: Resultsmentioning
confidence: 99%
“…The vertical burning test was conducted on a horizontal vertical burning tester (CZF-3, China) according to GB/T 5455-2014, and the samples with a size of 300 mm × 89 mm were conditioned at (20 ± 2) °C, (65 ± 4)% RH for 24 h with an ignition time of 12 s. To study the triboelectric outputs of the FRT-TENG at high temperatures, the sample with the size of 30 mm × 30 mm was placed on a hot stage and heated at specific temperatures for 5 min to ensure sufficient heating. [58] The limiting oxygen index test was carried out by an oxygen index meter (DYNISCO, USA) according to GB/T 5455-1997, and the size of the specimens was 150 mm × 58 mm. The cone calorimetry test was conducted according to ISO 5660-1 by using a cone calorimeter (FTTL, UK) under an external heat flux of 35 kW m −2 , and the size of the tested samples was 100 mm × 100 mm × 1.14 mm.…”
Section: Methodsmentioning
confidence: 99%
“…In order to achieve more precise distinction, the support vector machine (SVM) algorithm of machine learning was employed for auxiliary recognition, which is a related supervised learning method for classification and regression, which can build a model via training data to classify data in new samples. 39,40 Each of the objects was subjected to 50 cycles of grasp tests to enrich the data set, as depicted in the confusion matrix of Fig. 6(g), the average accuracy of recognition can achieve 98.6%, demonstrating the excellent recognition capability of the object shapes.…”
Section: Materials Classification and Shape Recognition Of The Sensormentioning
confidence: 99%