Study on Gas Mixture Identification Method Based on Modulation Cycle and Channel Attention Network

LIU Weifeng; LIU Yufang; QIAN Zhixiang; REN Tianyi; ZHONG Lipeng; WANG Feng; LIU Jie; WU Yuran; ZHAO Donghui

doi:10.13296/j.1001-1609.hva.2026.09.012

您当前的位置：

首页 >

文章列表页 >

Study on Gas Mixture Identification Method Based on Modulation Cycle and Channel Attention Network

Research on Insulation Medium and Discharge Mechanisms | 更新时间：2026-09-10

- Study on Gas Mixture Identification Method Based on Modulation Cycle and Channel Attention Network
- High Voltage Apparatus Vol. 62, Issue 9, Pages: 108-116(2026)
- 作者机构：
  
  湖南大学电气与信息工程学院，长沙 410082
  郑州电力高等专科学校电力工程学院，郑州 450000
- 作者简介：
- 基金信息：
- DOI：10.13296/j.1001-1609.hva.2026.09.012
  CLC：
- Received：22 March 2026，
  
  Revised：2026-05-21，
  
  Published：16 September 2026
- 稿件说明：
移动端阅览
LIU Weifeng, LIU Yufang, QIAN Zhixiang, et al. Study on Gas Mixture Identification Method Based on Modulation Cycle and Channel Attention Network[J]. High Voltage Apparatus, 2026, 62(9): 108-116.
DOI：

LIU Weifeng, LIU Yufang, QIAN Zhixiang, et al. Study on Gas Mixture Identification Method Based on Modulation Cycle and Channel Attention Network[J]. High Voltage Apparatus, 2026, 62(9): 108-116. DOI： 10.13296/j.1001-1609.hva.2026.09.012.

摘要

温度调制技术能够显著提升金属氧化物半导体气体传感器的选择性，增强其识别能力。然而，现有方法对温度调制过程与气体吸附—反应动力学共同作用下形成的结构化动态响应信息利用不足，且预测过程可解释性有限。为此，提出一种基于传感器—周期注意力机制的混合气体体积分数预测方法。通过在调制周期维度建模响应演化规律，在传感器通道维度刻画多通道交互关系，并通过可学习重要性加权机制融合关键传感器—周期特征，实现混合气体体积分数联合预测。以电缆缓冲层烧蚀释放气体为对象的实验结果表明，所提方法较所选对比模型具有更优预测性能，体积分数预测决定系数达到0.99。同时，能够反映不同时序响应对预测结果的贡献，为混合气体动态响应分析提供可解释依据。

Abstract

Temperature modulation technology can significantly improve the selectivity of metal oxide semiconductor gas sensors and enhance their identification capability. However

existing methods inadequately utilize the structured dynamic response information formed by the synergistic interplay between the temperature modulation process and gas adsorption-reaction kinetics. Moreover

the interpretability of their prediction processes remains limited. To address these limitations

in this paper a gas mixture concentration prediction method based on a sensor-period attention mechanism is proposed. By modeling the response evolution patterns along the modulation-period dimension and characterizing multi-channel interaction relationships across the sensor channel dimension

a lernable importance weighting mechanism is employed to fuse critical sensor-period features

thereby enabling joint prediction of gas mixture concentrations. Experimental results targeting the gases released from the abalation of the cable buffer layer demonstrate that the proposed method achieves superior prediction performance compared to the selected benchamark models

with a coefficient of determination of 0.99 for concentration prediction. Furthermore

the method is capable of revealing the contributions of different temporal responses to the prediction results

thereby providing an interpretable basis for dynamic responses analysis of gas mixture.

关键词

Keywords

references

汪可,郑东阳,王健一,等.变压器油过热故障产气特性及机理研究综述[J].中国电机工程学报,2025,45(21):8605-8621.

Wang Ke,Zheng Dongyang,Wang Jianyi,et al. Overview of gas generation mechanism of transformer oil under local overheating faults[J]. Proceedings of the SCEE,2025,45(21):8605-8621.

段肖力,刘雨丰,刘三伟,等.高压XLPE电缆缓冲层烧蚀机理及检测方法综述[J].电工技术学报,2025,40(5):1540-1558.

Duan Xiaoli,Liu Yufeng,Liu Sanwei,et al. Review on ablative mechanism of the buffer layer in high voltage XLPE cable and associated detection methods[J]. Transactions of China Electrotechnical Society,2025,40(5):1540-1558.

潘兴亚,汪超,邵建伟,等.痕量乙炔气体光热干涉多谐波信号联合检测技术[J].高压电器,2025,61(1):112-120.

Pan Xingya,Wang Chao,Shao Jianwei,et al. Combined detection technology of trace acetylene gas photothermal interference and multi-harmonic signal[J]. High Voltage Apparatus,2025,61(1):112-120.

李鹏,毕建刚,于浩,等.变电设备智能传感与状态感知技术及应用[J].高电压技术,2020,46(9):3097-3113.

Li Peng,Bi Jiangang,Yu Hao,et al. Technology and application of intelligent sensing and state sensing for transformation equipment[J]. High Voltage Engineering,2020,46(9):3097-3113.

陈伟根,赵立志,彭尚怡,等.激光拉曼光谱应用于变压器油中溶解气体分析[J].中国电机工程学报,2014,34(15):2485-2492.

Chen Weigen,Zhao Lizhi,Peng Shangyi,et al. Analysis of dissolved gas in transformer oil based on laser raman spectroscopy[J]. Proceedings of the CSEE,2014,34(15):2485-2492.

陈伟根,万福,顾朝亮,等.变压器油中溶解气体拉曼剖析及定量检测优化研究[J].电工技术学报,2016,31(2):236-243.

Chen Weigen,Wan Fu,Gu Chaoliang,et al. The research for raman analysis of dissolved gases in transformer oil and optimization of quantitative detection[J]. Transactions of China Electrotechnical Society,2016,31(2):236-243.

张晓星,胡隽宇,张引,等.基于中红外激光光声光谱的乙炔气体检测研究[J].高压电器,2025,61(12):181-187.

Zhang Xiaoxing,Hu Juanyu,Zhang Yin,et al. Study on detection of acetylene based on mid-infrared laser photoacoustic spectroscopy[J]. High Voltage Apparatus,2025,61(12):181-187.

张寅浩,张镱议,李泽瑞,等.不同放电类型下电缆附件绝缘界面逸出气体特性[J].高电压技术,2026,52(1):481-491. Zhang Yinhao,Zhang Yiyi,Li Zerui,et al. Characteristics of evolved gas from the insulation interface of cable accessories under different discharge types[J]. High Voltage Engineering,2026,52 (1):481-491.

张潮海,邹可园,张晓星.高压电气设备绝缘气体分解产物光学检测技术研究综述[J].高电压技术,2023,49(7):2806-2815.

Zhang Chaohai,Zou Keyuan,Zhang Xiaoxing. Review on optical detection technology of insulating gas decomposition products for high voltage electrical equipment[J]. High Voltage Engineering,2023,49(7):2806-2815.

雷芳菲,褚继峰,刘洋,等.基于半导体气体传感阵列的电缆过热故障诊断方法[J].电工技术学报,2023,38(13):3651-3664.

Lei Fangfei,Chu Jifeng,Liu Yang,et al. Fault diagnosis of cable overheating based on semiconductor gas sensing array[J]. Transactions of China Electrotechnical Society,2023,38(13):3651-3664.

梁坤,刘慧聪,伍洁,等.基于多传感阵列的高压电缆缓冲层烧蚀缺陷检测方法[J].电气工程学报,2025,20(6):125-134.

Liang Kun,Liu Huicong,Wu Jie,et al. Detection method for ablation defects in high-voltage cable buffer layers based on multisensor arrays[J]. Journal of Electrical Engineering,2025,20(6):125-134.

李浩源,刘洋,朱颖,等.基于超声—气体融合感算的空气开关柜放电故障诊断方法[J].高电压技术,2026,52(4):1969-1982.

Li Haoyuan,Liu Yang,Zhu Ying,et al. Discharge fault diagnosis method for air-insulated switchgear based on integrated ultrasonicgas sensing and computing[J]. High Voltage Engineering,2026,52 (4):1969-1982.

杨爱军,潘健彬,王琼苑,等.电力嗅觉传感原理与关键技术研究综述[J].高电压技术,2024,50(8):3339-3353.

Yang Aijun,Pan Jianbin,Wang Qiongyuan,et al. Review on sensing principles and key technologies of electric olfaction[J]. High Voltage Engineering,2024,50(8):3339-3353.

Lee A P,Reedy B J. Temperature modulation in semiconductor gas sensing[J]. Sensors and Actuators B-Chemical,1999,60(1):35-42.

Yin Xin,Zhang Lei,Tian Fengchun,et al. Temperature modulated gas sensing e-nose system for low-cost and fast detection[J]. IEEE Sensors Journal,2016,16(2):464-474.

Zhao Wenjie,Ding Kailun,Chen Yinsheng,et al. Optimized low frequency temperature modulation for improving the selectivity and linearity of SnO 2 gas sensor[J ] . IEEE Sensors Journal,2020,20 (18):10433-10443.

Gosangi R,Gutierrez-Osuna R. Active temperature modulation of metal-oxide sensors for quantitative analysis of gas mixtures[J]. Sensors and Actuators B-Chemical,2013(185):201-210.

Lee B,Kang Mingu,Lee K,et al. Multigas identification by temperature-modulated operation of a single anodic aluminum oxide gas sensor platform and deep learning algorithm[J]. ACS Sensors,2025,10(2):954-964.

Hu Z A,Zhao Wenjie,Cheng Haonan,et al. Application of PSO-CNN algorithm in semiconductor gas sensors based on temperature modulation[J]. IEEE Sensors Journal,2024,24(20):32717-32728.

Ji Hanyang,Mi Chunjin,Yuan Zhenyu,et al. Multicomponent gas detection method via dynamic temperature modulation measurements based on semiconductor gas sensor[J]. IEEE Transactions on Industrial Electronics,2023,70(6):6395-6404.

Wang Hao,Zhao Yong,Yuan Zhenyu,et al. Multiscale bidirectional temporal convolutional framework for industrial ketone organic solvent detection based on semiconductor gas sensor[J]. IEEE Transactions on Industrial Electronics,2024,71(12):16772-16782.

Mei Haixia,Peng Jingyi,Wang Tao,et al. Overcoming the limits of cross-sensitivity:pattern recognition methods for chemiresistive gas sensor array[J]. Nano-Micro Letters,2024,16(1):269.

Zhang Y,Yan J. Crossformer:transformer utilizing cross-dimension dependency for multivariate time series forecasting[C]//International Conference on Learning Representations,2023:9.

Hsieh T Y,Wang S,Sun Y,et al. Explainable multivariate time series classification:a deep neural network which learns to attend to important variables as well as time intervals[C]//Proceedings of the 14th ACM International Conference on Web Search and Data Mining,2021:607-615.

Lim B,Arık S Ö,Loeff N,et al. Temporal fusion transformers for interpretable multi-horizon time series forecasting[J]. International Journal of Forecasting,2021,37(4):1748-1764.

杜鑫,黄萍,唐崇年,等.基于图时间卷积的变压器油中溶解气体预测方法[J].广东电力,2025,38(4):101-108.

Du Xin,Huang Ping,Tang Chongnian,et al. Prediction of dissolved gases in transformer oil based on graph time convolution[J]. Guangdong Electric Power,2025,38(4):101-108.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Day-ahead Photovoltaic Power Forecasting Model Based on Spatio-temporal Local Attention Network and LSTM

Transformer Oil Temperature Prediction Based on Attention-gated Recurrent-temporal Covolutional Network

Detection Method for Insulator Defect Based on Improved YOLOv5s

Research on Application of Improved YOLOv11n in Detection of Main Defects of Insulators on Transmission Lines

Insulator Defect Detection Algorithm for Multi-scale Feature Extraction Based on Improved YOLOv7

Related Author

WU Kai

ZHI Detian

FAN Jingyu

SU Lianchao

LIU Bao

ZHANG Jing'e

CHENG Zhongjie

PENG Yanfei

Related Institution

State Key Laboratory of Alternate Electrical Power System With Renewable Energy Sources, North China Electric Power University

Tianjin Guotou Jinneng Power Generation Co., Ltd.

State Grid Shandong Electric Power Company

State Grid Weifang Power Supply Company

College of Electrical and Control Engineering, Xi'an University of Science and Technology

⁰