您的位置:山东大学 -> 科技期刊社 -> 《山东大学学报(工学版)》

山东大学学报 (工学版) ›› 2021, Vol. 51 ›› Issue (4): 124-130.doi: 10.6040/j.issn.1672-3961.0.2020.538

• • 上一篇    

基于LSTM的阀冷系统入水温度及冷却裕度预测

廖毅1,罗炜2,蒋峰伟1,李亚锦3,于大洋3*   

  1. 1.中国南方电网超高压输电公司广州局, 广东 广州 510405;2.中国南方电网公司, 广东 广州510623;3.山东大学电气工程学院, 山东 济南250061
  • 发布日期:2021-08-18
  • 作者简介:廖毅(1987— ),男,湖南长沙人,硕士,主要研究方向为高压直流输电运行与维护. E-mail:liaoyi.hn@foxmail.com. *通信作者简介:于大洋(1979— ),男,山东胶州人,副教授,主要研究方向为电力系统优化技术. E-mail:yudayang@sdu.edu.cn

Prediction of converter valve cooling capacity and water inlet temperature based on LSTM

LIAO Yi1, LUO Wei2, JIANG Fengwei1, LI Yajin3, YU Dayang3*   

  1. 1. Guangzhou Bureau, China Southern Power Grid EHV Power Transmission Co., Ltd., Guangzhou 510405, Guangdong, China;
    2. China Southern Power Grid Co., Ltd., Guangzhou 510623, Guangdong, China;
    3. School of Electrical Engineering, Shandong University, Jinan 250061, Shandong, China
  • Published:2021-08-18

摘要: 为解决换流站阀冷系统状态缺乏智能预测手段和极端工况下冷却能力是否充裕难以评估的问题,提出基于长短期记忆网络(long short-term memory, LSTM)的换流阀冷却裕度预测方法。在阀冷系统冷却裕度指标量化评估的基础上,考虑多源影响因素,通过相关性强弱选择特征量并构建数据样本集,利用长短时记忆网络建立预测模型,并基于大量实际样本数据进行训练,对入水温度和冷却裕度发展趋势做出预测、提前预警,同时提供极端工况下冷却裕度的分析模型,为现场处理决策提供依据。通过穗东换流站的实例分析,验证了算法的有效性和可行性。

关键词: 阀冷系统, 长短时记忆网络算法, 入水温度预测, 冷却裕度, 极端工况

Abstract: In order to solve the problems of lacking of intelligent prediction means for the condition of converter valve cooling system and the difficulty of evaluating the cooling capacity under extreme conditions, a prediction method of cooling margin of converter valve based on LSTM(long short-term memory,LSTM)was proposed. On the basis of quantitative evaluation of cooling margin index of valve cooling system, the long-term and long-term memory network was used to establish the prediction model. Considering the multi-source influencing factors, the feature quantity was selected through the correlation strength and the data sample set was constructed, which was used to train the model. Training was carried out to predict the development trend of water inlet temperature and cooling margin.The analysis model of cooling margin under extreme conditions was provided,which provided the basis for on-site treatment decision. The effectiveness and feasibility of the algorithm were analyzed and verified by an example of converter station.

Key words: valve cooling system, LSTM algorithm, water inlet temperature, cooling capacity, extreme conditions

中图分类号: 

  • TM721.1
[1] 洪乐洲,江一,翁洪志,等.换流站阀冷系统设计缺陷与改进措施[J].南方电网技术,2013,7(1):44-46. HONG Lezhou, JIANG Yi, WENG Hongzhi, et al. Design flaws andcorrective measures of valve cooling system at converter station[J]. Southern Power System Technology, 2013, 7(1):44-46.
[2] 毕文瑾,李亚龙.柔性直流换流阀控制系统运行安全性研究[J].电测与仪表,2019,56(17):26-30. BI Wenjin, LI Yalong. Research on operation safety of flexible DC converter valve control system[J].Electrical Measurement & Instrumentation, 2019, 56(17):26-30.
[3] 赵明,洪乐洲,严伟.换流站阀冷外冷水系统散热能力评估方法优化与应用[J].电工技术,2020(13):134-137. ZHAO Ming, HONG Lezhou, YAN Wei. Optimization and application of evaluation method for cooling capacity of external value cooling system in converter station[J].Electric Engineering, 2020(13):134-137.
[4] 廖毅,罗炜,蒋峰伟,等.换流阀冷却能力多维度分析与预警模型[J].南方电网技术,2020,14(7):1-9. LIAO Yi, LUO Wei, JIANG Fengwei, et al. Multi-dimensional analysis and early warning model for the cooling capacity of converter valve[J] Southern Power System Technology, 2020, 14(7):1-9.
[5] 陈强华. 基于多维时序数据的运维优化技术研究[D].济南:山东大学,2020. CHEN Qianghua. Research on operation and maintenance optimization technology based on multidimensional time series data[D]. Jinan: Shandong University, 2020.
[6] 彭红霞,文艳,王磊,等.基于两层知识架构的电力设备差异化运维技术[J].高压电器,2019,55(7):221-226. PENG Hongxia, WEN Yan, WANG Lei, et al.Differentialoperating maintenance technology of power equipment based on two-layer knowledgearchitecture[J].High Voltage Apparatus, 2019, 55(7):221-226.
[7] 蒋峰伟,廖毅,张思光.高压直流换流阀冷却系统冷却能力评估方法和提升措施研究[J].机电信息,2019(33):16-18. JIANG Fengwei, LIAO Yi, ZHANG Siguang. Research on evaluation method and lifting measures of cooling capacity of HVDC converter valve cooling system[J]. Mechanical and Electrical Information, 2019(33):16-18.
[8] 蒲天骄,乔骥,韩笑,等.人工智能技术在电力设备运维检修中的研究及应用[J]. 高电压技术,2020,46(2): 369-383. PU Tianjiao, QIAO Ji, HAN Xiao, et al. Research andapplication of artificial intelligence in operation and maintenance for power equipment[J]. High Voltage Engineering, 2020, 46(2):369-383.
[9] 王宏伟,张利民,姜建平,等.特高压站避雷器泄漏电流在线监测和分析系统[J].电瓷避雷器,2019(6):67-72. WANG Hongwei, ZHANG Limin, JIANGJianping, et al. On-line monitoring and analysis system of lightning arrester leakage current in UHV substation[J]. Insulators and Surge Arresters, 2019(6):67-72.
[10] 尹金良,朱永利.支持向量机参数优化及其在变压器故障诊断中的应用[J].电测与仪表,2012,49(5):11-16. YIN Jinliang, ZHU Yongli. Parameteroptimization for support vector machine and its application to fault diagnosis of power transformers[J].Electrical Measurement & Instrumentation, 2012, 49(5):11-16.
[11] SONG H, DAI J J, LUO L G, et al. Power transformer operating state prediction method based on an LSTM network[J]. Energies, 2018, 11(4): 914-928.
[12] 黄梦辉,蒋涛,董建军,等.基于LSTM的箱式变压器高压套管温度预测[J/OL].电测与仪表. [2020-12-17].http://58.194.172.13:80/rwt/CNKI/http/NNYHGLUDN3W-XTLUPMW4A/kcms/detail/23.1202.th.20201116.1707.002.html.
[13] 3HOCHREITER S, SCHMIDHUBER J. Long short- term memory[J]. Neural Computation, 1997, 9(8):1735-1780.
[14] 周虎兵,王玉磊,张曼,等.熵值法赋权的智能变电站二次设备效能模糊综合评价[J].电测与仪表,2018,55(3):73-79. ZHOU Hubing, WANG Yulei, ZHANG Man, et al. Comprehensive fuzzy evaluation of effectiveness of secondary equipment in smart substation based on entropy method[J]. Electrical Measurement & Instrumentation, 2018, 55(3):73-79.
[15] SZEKELY G J, RIZZO M L, BAKIROV N K. Measuring and testing dependence by correlation of distances[J]. Annals of Statistics, 2007, 35(6):2769-2794.
[1] 麻常辉,王亮,谭邵卿,卢奕,马欢,赵康. 考虑同步调相机无功特性的多馈入直流同时换相失败风险评估方法[J]. 山东大学学报 (工学版), 2020, 50(3): 98-103.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!