Cross-heating-rate prediction of thermogravimetry of PVC and XLPE cable insulation material : a novel artificial neural network framework

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review

2 Scopus Citations
View graph of relations

Author(s)

Detail(s)

Original languageEnglish
Pages (from-to)14467–14478
Number of pages12
Journal / PublicationJournal of Thermal Analysis and Calorimetry
Volume147
Issue number24
Online published5 Oct 2022
Publication statusPublished - Dec 2022

Link(s)

Abstract

The analysis of thermogravimetric data of material at multiple heating rates is very labor-intensive and time-consuming. To provide an accurate and effective prediction of the thermogravimetric (TG) curves at various heating rates, this work presents a novel artificial neural network (ANN) framework for cross-heating-rate prediction on the TG curves of commonly used cable insulation materials. The proposed ANN framework consists of data transformation and division techniques that differ from previous studies. By comparing the actual test results and predicted TG results of polyvinyl chloride (PVC), the effectiveness of the proposed ANN framework in the cross-heating-rate prediction of TG curves is validated. By which, the relationship between heating rates and conversion rates can be reliably captured, demonstrating the capability of the proposed ANN framework in interpreting cross-heating-rate TG data. In addition to PVC, the proposed ANN framework has been extended to analyze the TG curves of XLPE.

Research Area(s)

  • PVC, XLPE, Thermogravimetry, Artificial neural network, Cross-heating-rate, THERMAL-DEGRADATION, KINETIC-PARAMETERS, ELECTRICAL CABLES, ACTIVATION-ENERGY, SEWAGE-SLUDGE, TG-FTIR, PYROLYSIS, SHEATH, DECOMPOSITION

Citation Format(s)

Cross-heating-rate prediction of thermogravimetry of PVC and XLPE cable insulation material: a novel artificial neural network framework. / Wang, Yalong; Kang, Ning; Lin, Jin et al.
In: Journal of Thermal Analysis and Calorimetry, Vol. 147, No. 24, 12.2022, p. 14467–14478.

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review

Download Statistics

No data available