电源学报

基于多尺度TCN与多头自注意力机制的石化行业电能质量扰动识别方法

PDF下载

王鸿章

电源学报 | 人工智能与电力电子 2026,24(9): 245-253

收起

电源学报 |人工智能与电力电子 2026 , 24 (9) : 245 -253

基于多尺度TCN与多头自注意力机制的石化行业电能质量扰动识别方法

全屏

[Author(id=1322560542535958617, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1322560539201486930, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=wanghz.aqsh@sinopec.com, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1322560542678564955, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1322560539201486930, authorId=1322560542535958617, language=EN, stringName=Hongzhang WANG, firstName=Hongzhang, middleName=null, lastName=WANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Electric Instrument Center of Sinopec Anqing Branch, Anqing 246000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322560542766645340, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1322560539201486930, authorId=1322560542535958617, language=CN, stringName=王鸿章, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=中石化安庆分公司电仪中心，安庆　246000, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322560540484943957, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1322560539201486930, xref=null, ext=[AuthorCompanyExt(id=1322560540510109782, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1322560539201486930, companyId=1322560540484943957, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Electric Instrument Center of Sinopec Anqing Branch, Anqing 246000, China), AuthorCompanyExt(id=1322560540803711063, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1322560539201486930, companyId=1322560540484943957, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=中石化安庆分公司电仪中心，安庆　246000)])])]

王鸿章

作者信息

中石化安庆分公司电仪中心，安庆　246000

通讯作者:

王鸿章（1974—　），男，通信作者，本科，高级工程师。研究方向：电气自动化。E-mail：wanghz.aqsh@sinopec.com。

A Method for Identifying Power Quality Disturbances in the Petrochemical Industry Based on Multi-scale TCN and Multi-head Self-attention Mechanism

Hongzhang WANG

Affiliations

Electric Instrument Center of Sinopec Anqing Branch, Anqing 246000, China

出版时间: 2026-09-30 doi: 10.13234/j.issn.2095-2805.2026.9.245

文章导航

摘要

收起

随着石化行业的数智化转型发展，电能质量问题也日趋严重。由于生产需要，大量非线性、非对称、冲击性的用电负荷接入电网，从而产生一系列电能质量扰动问题，影响石化行业生产安全运行。基于此，提出一种基于深度学习的石化行业电能质量扰动识别方法，使用多尺度时间卷积网络TCN（temporal convolutional network）提取电能质量时序信号的全局特征和局部特征，引入多头自注意力机制突出重要特征，提升模型的识别性能。仿真数据和某地区石化行业电网数据验证结果表明，所提方法能够实现对单一和复合电能质量扰动信号的高精度识别，且具有较强的抗噪和泛化能力。

关键词

石化行业 / 电能质量扰动 / 深度学习 / 多尺度TCN / 多头自注意力机制

Abstract

收起

With the digital transformation and development of the petrochemical industry, power quality issues are becoming increasingly serious. Due to production needs, a large number of nonlinear, asymmetric, and impactful power loads are connected to the power grid, resulting in a series of power quality disturbances that affect the safe operation of the petrochemical industry. On this basis, a deep-learning-based method for identifying power quality disturbances in the petrochemical industry is proposed. A multi-scale temporal convolutional network (TCN) is used to extract global and local features of power quality time-series signals, and a multi-head self-attention mechanism is introduced to highlight important features and improve the recognition performance of the model. Based on simulation data and power grid data from a petrochemical industry in a certain region, the experimental results show that the proposed method can achieve high-precision identification of single and composite power quality disturbance signals, and has strong anti-noise and generalization capabilities.

Key words

Petrochemical industry / power quality disturbances / deep learning / multi-scale TCN / multi-head self-attention

引用本文

王鸿章. 基于多尺度TCN与多头自注意力机制的石化行业电能质量扰动识别方法. 电源学报, 2026 , 24 (9) : 245 -253 . DOI: 10.13234/j.issn.2095-2805.2026.9.245

Hongzhang WANG. A Method for Identifying Power Quality Disturbances in the Petrochemical Industry Based on Multi-scale TCN and Multi-head Self-attention Mechanism[J]. Journal of Power Supply, 2026 , 24 (9) : 245 -253 . DOI: 10.13234/j.issn.2095-2805.2026.9.245

参考文献

收起

文献

收起

参考文献引证文献

排序方式：

[1]

钱锋, 杜文莉, 钟伟民, 等. 石油和化工行业智能优化制造若干问题及挑战[J]. 自动化学报, 2017, 43(6): 893-901. Qian Feng, Du Wenli, Zhong Weimin, et al. Problems and challenges of smart optimization manufacturing in petrochemical industries[J]. Acta Automatica Sinica, 2017, 43(6): 893-901. (in Chinese)

[2]

张士全, 黄玲琳. 石化行业电能质量分析及治理[J]. 电气技术, 2014, 15(1): 137-139, 142. Zhang Shiquan, Huang Linglin. Analysis and treatment of power quality in petrochemical industry[J]. Electrical Engineering, 2014, 15(1): 137-139, 142. (in Chinese)

[3]

贾伯岩, 贾静然, 卢锦玲, 等. 供电电源系统电能质量稳定性监测方法[J]. 电源学报, 2024, 22(2): 345-351. Jia Boyan, Jia Jingran, Lu Jinling, et al. Monitoring method for power quality stability of power supply system[J]. Journal of Power Supply, 2024, 22(2): 345-351. (in Chinese)

[4]

杨新法, 苏剑, 吕志鹏, 等. 微电网技术综述[J]. 中国电机工程学报, 2014, 34(1): 57-70. Yang Xinfa, Su Jian, Lü Zhipeng, et al. Overview on micro-grid technology[J]. Proceedings of the CSEE, 2014, 34(1): 57-70. (in Chinese)

[5]

付勉, 刘志涵, 宋振浩, 等. 配电网络电能质量综合治理设备优化配置策略[J]. 电源学报, 2024, 22(2): 336-344. Fu Mian, Liu Zhihan, Song Zhenhao, et al. Optimal allocation strategy for comprehensive control equipment of power quality in distribution area[J]. Journal of Power Supply, 2024, 22(2): 336-344. (in Chinese)

[6]

黄建明, 瞿合祚, 李晓明. 基于短时傅里叶变换及其谱峭度的电能质量混合扰动分类[J]. 电网技术, 2016, 40(10): 3184-3191. Huang Jianming, Qu Hezuo, Li Xiaoming. Classification for hybrid power quality disturbance based on STFT and its spectral kurtosis[J]. Power System Technology, 2016, 40(10): 3184-3191. (in Chinese)

[7]

Yu Yiqing, Zhao Wei, Li Shisong, et al. A two-stage wavelet decomposition method for instantaneous power quality indices estimation considering interharmonics and transient disturbances[J]. IEEE Transactions on Instrumentation and Measurement, 2021, 70: 9001813.

[8]

李建闽, 林海军, 梁成斌, 等. 基于双分辨率S变换和学习向量量化神经网络的电能质量扰动检测方法[J]. 电工技术学报, 2019, 34(16): 3453-3463. Li Jianmin, Lin Haijun, Liang Chengbin, et al. Detection method of power quality disturbances based on double resolution S transform and learning vector quantization neural network[J]. Transactions of China Electrotechnical Society, 2019, 34(16): 3453-3463. (in Chinese)

[9]

徐永海, 赵燕. 基于短时傅里叶变换的电能质量扰动识别与采用奇异值分解的扰动时间定位[J]. 电网技术, 2011, 35(8): 174-180. Xu Yonghai, Zhao Yan. Identification of power quality disturbance based on short-term Fourier transform and disturbance time orientation by singular value decomposition[J]. Power System Technology, 2011, 35(8): 174-180. (in Chinese)

[10]

Borrás M D, Bravo J C, Montaño J C. Disturbance ratio for optimal multi-event classification in power distribution networks[J]. IEEE Transactions on Industrial Electronics, 2016, 63(5): 3117-3124.

[11]

Puliyadi Kubendran A K, Loganathan A K. Detection and classification of complex power quality disturbances using S-transform amplitude matrix-based decision tree for different noise levels: Detection and classification of complex power quality disturbances[J]. International Transactions on Electrical Energy Systems, 2017, 27(4): e2286.

[12]

陈晓静, 李开成, 肖剑, 等. 一种实时电能质量扰动分类方法[J]. 电工技术学报, 2017, 32(3): 45-55. Chen Xiaojing, Li Kaicheng, Xiao Jian, et al. A method of real-time power quality disturbance classification[J]. Transactions of China Electrotechnical Society, 2017, 32(3): 45-55. (in Chinese)

[13]

景飞, 周雒维, 卢伟国. 基于ADALINE神经网络的电能质量监测终端设计[J]. 电源学报, 2017, 15(3): 118-125. Jing Fei, Zhou Luowei, Lu Weiguo. Design of power quality monitoring terminal based on ADALINE neural[J]. Journal of Power Supply, 2017, 15(3): 118-125. (in Chinese)

[14]

武昭旭, 杨岸, 祝龙记. 基于循环神经网络的电能质量扰动识别[J]. 电力系统保护与控制, 2020, 48(18): 88-94. Wu Zhaoxu, Yang An, Zhu Longji. Power quality disturbance recognition based on a recurrent neural network[J]. Power System Protection and Control, 2020, 48(18): 88-94. (in Chinese)

[15]

王志祥. 基于循环神经网络的电能质量扰动识别算法研究[D]. 长沙: 湖南大学, 2020. Wang Zhixiang. The research on recognition algorithm of power quality disturbances based on recurrent neural network[D]. Changsha: Hunan University, 2020. (in Chinese)

[16]

Wang Shouxiang, Chen Haiwen. A novel deep learning method for the classification of power quality disturbances using deep convolutional neural network[J]. Applied Energy, 2019, 235: 1126-1140.

[17]

王维博, 张斌, 曾文入, 等. 基于特征融合一维卷积神经网络的电能质量扰动分类[J]. 电力系统保护与控制, 2020(6): 53-60. Wang Weibo, Zhang Bin, Zeng Wenru, et al. Power quality disturbance classification of one-dimensional convolutional neural networks based on feature fusion[J]. Power System Protection and Control, 2020(6): 53-60. (in Chinese)

[18]

赵晨, 李开成, 张浩毅, 等. 少量已知历史数据下的电能质量复合扰动识别方法[J]. 科学技术与工程, 2022, 22(8): 3087-3092. Zhao Chen, Li Kaicheng, Zhang Haoyi, et al. A method of multiple power quality disturbances classification without adequate history data[J]. Science Technology and Engineering, 2022, 22(8): 3087-3092. (in Chinese)

[19]

Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need[C]//Advances in Neural Information Processing Systems. Long Beach, CA, USA, 2017: 5998-6008.

[20]

IEEE Power & Energy Society. IEEE Std 1159-2019: IEEE recommended practice for monitoring electric power quality[S]. New York: IEEE, 2019.

[21]

Kim P. Convolutional Neural Network[M]. MATLAB deep learning. Berkeley, CA: Apress, 2017: 121-147.

[22]

Lawrence S, Giles C L, Tsoi A C, et al. Face recognition: A convolutional neural-network approach[J]. IEEE Transactions on Neural Networks, 1997, 8(1): 98-113.

[23]

Ioffe S, Szegedy C. Batch normalization: Accelerating deep network training by reducing internal covariate shift[C]//International Conference on Machine Learning. Lille, France, 2015: 448-456.

[24]

Nair V, Hinton G E. Rectified linear units improve restricted Boltzmann machines[C]//International Conference on Machine Learning. Haifa, Israel, 2010: 807-814.

[25]

毕贵红, 鲍童语, 陈臣鹏, 等. 基于混合分解多尺度时频图和Res-GRU-AT的电能质量复合扰动识别[J]. 电力系统保护与控制, 2024, 52(4): 12-25. Bi Guihong, Bao Tongyu, Chen Chenpeng, et al. Composite PQDs identification based on a hybrid decomposition multi-scale time-frequency map and Res-GRU-AT[J]. Power System Protection and Control, 2024, 52(4): 12-25. (in Chinese)

[26]

钱倍奇, 陈谦, 李宗源, 等. 基于马尔可夫转换场与多头注意力机制的电能质量扰动分类方法[J]. 电网技术, 2024, 48(2): 721-729. Qian Beiqi, Chen Qian, Li Zongyuan, et al. Power quality disturbances classification based on Markov transition field and multi-head attention[J]. Power System Technology, 2024, 48(2): 721-729. (in Chinese)

[27]

贺才郡, 李开成, 董宇飞, 等. 基于知识蒸馏与RP-MobileNetV3的电能质量复合扰动识别[J]. 电力系统保护与控制, 2023, 51(14): 75-84. He Caijun, Li Kaicheng, Dong Yufei, et al. Power quality compound disturbance identification based on knowledge distillation and RP-MobilenetV3[J]. Power System Protection and Control, 2023, 51(14): 75-84. (in Chinese)

2026年第24卷第9期

PDF下载

引用本文

BibTeX

文章信息

doi: 10.13234/j.issn.2095-2805.2026.9.245

接收时间：2024-12-27
首发时间：2026-10-29
出版时间：2026-09-30

补充材料

相关文章

文章信息

作者

出版历史

收稿日期：2024-12-27
修回日期：2025-02-24
录用日期：2025-03-01

基金

作者信息

中石化安庆分公司电仪中心，安庆　246000

通讯作者:

王鸿章（1974—　），男，通信作者，本科，高级工程师。研究方向：电气自动化。E-mail：wanghz.aqsh@sinopec.com。

参考文献

分享链接

https://castjournals.cast.org.cn/joweb/dyxb/CN/10.13234/j.issn.2095-2805.2026.9.245

分享至

全文二维码

扫描看全文

引用本文

BibTeX

本文的引用情况

2种不同金属材料的力学参数

科 Family	属数 Number of genus	种数 Number of species	占总种数比例 Percentage of total species (%)	属 Genus	种数 Number of species	占总种数比例 Percentage of total species (%)
鹅膏菌科Amanitaceae	2	11	5.26	鹅膏菌属 Amanita	10	4.78
小菇科 Mycenaceae	2	12	5.74	丝盖伞属 Inocybe	5	2.39
多孔菌科 Polyporaceae	8	14	6.70	蜡蘑属 Laccaria	5	2.39
红菇科 Russulaceae	3	23	11.00	小皮伞属 Marasmius	6	2.87
				小菇属 Mycena	11	5.26
				光柄菇属 Pluteus	5	2.39
				红菇属 Russula	17	8.13
				栓菌属 Trametes	5	2.39

关闭全屏

BibTeX
EndNote
RefWorks
TxT