Wang Mingxiang, Zeng Qingbin, Chen Dachang, Zhang Yiyi, Liu Jiefeng, Ma Changyou, Jia Pengfei
School of Electrical Engineering, Guangxi University, Nanning 530004, China; Guangxi Key Laboratory of intelligent Control and Maintenance of Power Equipment, Guangxi University, Nanning 530004, China.
School of Electrical Engineering, Guangxi University, Nanning 530004, China.
J Hazard Mater. 2025 Jan 5;481:136567. doi: 10.1016/j.jhazmat.2024.136567. Epub 2024 Nov 19.
The man-made gas sulfur hexafluoride (SF) is an excellent and stable insulating medium. However, some insulation defects can cause SF to decompose, threatening the safe operation of power grids. Based on this, it is of great significance to find and effectively control the decomposition products of SF in time. Gas sensors have proven to be an effective way to detect these decomposition gases (SO, SOF, SOF, HS, and HF). Nanomaterials with gas-sensitive properties are at the heart of gas sensors. In recent years, data-driven machine learning (ML) has been widely used to predict material properties and discover new materials. However, it has become a major challenge to establish a common model between material properties derived from various types of calculations and intelligent algorithms. In order to make some progress in addressing this challenge. In this work, 250 data sets were extracted from 52 publications exploring the detection of SF decomposition products by nanocomposites based on relevant work over the past 10 years, and the adsorption behavior of SF decomposition products can be predictively analyzed. By comparing six different algorithmic models, the best model for predicting the adsorption distance (XGBoost: R = 91.94 %) and adsorption energy (GBR: R = 78.63 %) of SF decomposed gas was identified. Subsequently, the importance of each of the selected feature descriptors in predicting the gas adsorption effect was explained. This work combines first-principles computational results and machine-learning algorithms with each other to provide a new research idea for evaluating the gas sensing capability of nanocomposites.
人造气体六氟化硫（SF₆）是一种优良且稳定的绝缘介质。然而，一些绝缘缺陷会导致SF₆分解，威胁电网的安全运行。基于此，及时发现并有效控制SF₆的分解产物具有重要意义。气体传感器已被证明是检测这些分解气体（SO₂、SOF₂、SOF₄、H₂S和HF）的有效方法。具有气敏特性的纳米材料是气体传感器的核心。近年来，数据驱动的机器学习（ML）已被广泛用于预测材料性能和发现新材料。然而，在源自各种类型计算的材料性能与智能算法之间建立通用模型已成为一项重大挑战。为了在应对这一挑战方面取得一些进展。在这项工作中，基于过去10年的相关工作，从52篇探索基于纳米复合材料检测SF₆分解产物的出版物中提取了250个数据集，并对SF₆分解产物的吸附行为进行了预测分析。通过比较六种不同的算法模型，确定了预测SF₆分解气体吸附距离（XGBoost：R = 91.94%）和吸附能（GBR：R = 78.63%）的最佳模型。随后，解释了每个选定特征描述符在预测气体吸附效果中的重要性。这项工作将第一性原理计算结果与机器学习算法相互结合，为评估纳米复合材料的气敏能力提供了一种新的研究思路。
