[1]谭邹卿,杜宸宇,万安平.基于数字孪生的压气机水洗运维决策[J].郑州大学学报(工学版),2024,45(06):129-136.[doi:10.13705/j.issn.1671-6833.2024.03.013]
　TAN Zouqing,DU Chenyu,WAN Anping.Operation and Maintenance Decision of Compressor Water Wash Based on Digital Twin[J].Journal of Zhengzhou University (Engineering Science),2024,45(06):129-136.[doi:10.13705/j.issn.1671-6833.2024.03.013]
点击复制

基于数字孪生的压气机水洗运维决策()
分享到：

《郑州大学学报(工学版)》[ISSN:1671-6833/CN:41-1339/T]

卷:
45
期数:
2024年06期
页码:
129-136
栏目:
出版日期:
2024-09-25

文章信息/Info

Title:
Operation and Maintenance Decision of Compressor Water Wash Based on Digital Twin
文章编号:
1671-6833(2024)06-0129-08
作者:
谭邹卿1;  杜宸宇1; 2;  万安平2
1. 常州大学 机械与轨道交通学院,江苏 常州 213164;2. 浙大城市学院 工程学院,浙江 杭州 310015
Author(s):
TAN Zouqing1;  DU Chenyu1; 2;  WAN Anping2
1. School of Mechanical Engineering And Rail Transit, Changzhou University, Changzhou 213164, China; 2. School of Engineering,Hangzhou City University, Hangzhou 310015, China
关键词:
压气机;  数字孪生;  极端梯度提升树;  离线水洗;  健康管理
Keywords:
compressor;  digital twin;  extreme gradient boosting;  offline water washing;  health management
分类号:
TK39
DOI:
10.13705/j.issn.1671-6833.2024.03.013
文献标志码:
A
摘要:
为了提高燃气轮机的发电效率,针对压气机水洗运维经济成本过高的问题,对压气机进行基于数字孪生的运维决策研究,提出一种基于数字孪生的电厂燃气轮机健康管理框架,基于该框架对压气机运行数据进行处理,使用极端梯度提升树算法搭建水洗周期预测模型,选取数据集内部分参数作为模型输入量,气耗量为输出量,分析其变化规律及其与输入量之间的关系,对水洗周期及水洗恢复率进行计算和比较,得出合适的水洗周期,对压气机进行运维决策。 模型预测结果表明:8 次水洗气耗量预测的平均 R2_score 达到 0. 98,预测结果准确;8 次水洗中,第2、第 3 次水洗周期合适,第 3 次水洗恢复率最优,得出压气机水洗周期的指导小时数为 1 824 h;与电厂实际执行的平均水洗周期相比,每次水洗成本可以降低 2190 万元。
Abstract:
In order to improve the power generation efficiency of the gas turbine,and to solve the problem of thehigh cost of the operation and maintenance (O&M) of the compressor water washing system, a digital twin-basedO&M decision study of the compressor was conducted. And a health management framework for gas turbine in power plants based on digital twin was proposed. Based on that the compressor operation data was processed, and theextreme gradient boosting algorithm was used to build a prediction model for the washing cycle, and some of the parameters within the dataset were selected as inputs to the model, with the gas consumption as the output quantity,analyzed the change rule and its relationship with the input quantity. the water washing cycle and water washing recovery rate were calculated and compared, and the appropriate water washing cycle for O&M decision of the compressor was derived. The model prediction results showed that: the average R2_score of the eight water washing gasconsumption prediction reached 0. 98, and the prediction results were accurate. Among the eight times of waterwashing, the second and third water washing cycles were appropriate, and the third water washing recovery rate wasoptimal, resulting in the guiding hours of gas turbine compressor water washing cycle of 1 824 hours. Comparedwith the average water washing cycle of the power plant in the actual implementation, the cost of water washingcould be reduced by 21. 9 million yuan per time.

参考文献/References:

[1] 曹思佳, 胡汀, 唐瑞, 等. 基于工业互联网的船用燃气轮机健康管理平台[ J] . 热能动力工程, 2022, 37(5) : 180-186.

CAO S J, HU T, TANG R, et al. Marine gas turbinehealth management based on industrial Internet platform[ J] . Journal of Engineering for Thermal Energy and Power, 2022, 37(5) : 180-186.
[2] SINGH M, FUENMAYOR E, HINCHY E, et al. Digitaltwin: origin to future [ J ] . Applied System Innovation,2021, 4(2) : 36.
[3] HE B, BAI K J. Digital twin-based sustainable intelligentmanufacturing: a review [ J] . Advances in Manufacturing, 2021, 9(1) : 1-21.
[4] TAO F, CHENG J F, QI Q L, et al. Digital twin-drivenproduct design, manufacturing and service with big data[ J] . The International Journal of Advanced Manufacturing Technology, 2018, 94(9) : 3563-3576.
[5] GRAESSLER I, POEHLER A. Integration of a digitaltwin as human representation in a scheduling procedure ofa cyber-physical production system [ C]∥2017 IEEE International Conference on Industrial Engineering and Engineering Management ( IEEM ) . Piscataway: IEEE,2017: 289-293.
[6] 王睿瑞, 陈芃樾, 邱思琦, 等. 基于数字孪生的船用燃气轮机健康管理工业互联网平台[ J] . 热能动力工程, 2022, 37(12) : 189-196.
WANG R R, CHEN P Y, QIU S Q, et al. An industrialInternet platform for PHM of marine gas turbine based ondigital twins[ J] . Journal of Engineering for Thermal Energy and Power, 2022, 37(12) : 189-196.
[7] 张旭辉, 张雨萌, 王岩, 等. 融合数字孪生与混合现实技术的机电设备辅助维修方法[ J] . 计算机集成制造系统, 2021, 27(8) : 2187-2195.
ZHANG X H, ZHANG Y M, WANG Y, et al. Auxiliarymaintenance method for electromechanical equipment integrating digital twin and mixed reality technology [ J ] .Computer Integrated Manufacturing Systems, 2021, 27(8) : 2187-2195.
[8] 杨悦, 姚树磊, 刘长利, 等. 叶片水射流表面强化工艺的数字孪生系统设计[ J] . 华东理工大学学报( 自然科学版) , 2023, 49(2) : 295-304.
YANG Y, YAO S L, LIU C L, et al. Design of digitaltwin system for blade water jet surface strengtheningprocess[ J] . Journal of East China University of Scienceand Technology, 2023, 49(2) : 295-304.
[9] XU Q F, ZHOU G H, ZHANG C, et al. Digital twindriven intelligent maintenance decision-making systemand key-enabling technologies for nuclear power equipment[ J] . Digital Twin, 2022, 2: 14.
[10] 姜伟强, 孔令海, 唐武成, 等. 水洗对燃气透平效率影响浅析[ J] . 中国石油石化, 2017(4) : 12-14.
JIANG W Q, KONG L H, TANG W C, et al. Analysison the influence of water washing on gas turbine efficiency[ J] . China Petrochem, 2017(4) : 12-14.
[11] 韩朝兵, 朱泓逻, 黄伟栋, 等. 压气机离线水洗后燃气轮机性能衰退分析研究[ J] . 动力工程学报, 2019,39(8) : 626-633.
HAN C B, ZHU H L, HUANG W D, et al. Performancedegradation analysis of a gas turbine after offline waterwashing of the compressor[ J] . Journal of Chinese Societyof Power Engineering, 2019, 39(8) : 626-633.
[12] 陈家伦, 卞韶帅, 黄新. 基于 BP 神经网络的 9F 燃气轮机压气机离线水洗周期优化 [ J] . 燃气轮机技术,2020, 33(1) : 47-53.
CHEN J L, BIAN S S, HUANG X. Optimization of offline washing cycle of 9F gas turbine compressor based onBP neural network[ J] . Gas Turbine Technology, 2020,33(1) : 47-53.
[13] RAO P N S, ACHUTHA NAIKAN V N. An optimal maintenance policy for compressor of a gas turbine powerplant[ J] . Journal of Engineering for Gas Turbines andPower, 2008, 130(2) : 1.
[14] 汪祖民, 王冬昊, 梁霞, 等. 基于 DBSCAN_GAN_XGBOOST 的网络入侵检测方法[ J] . 郑州大学学报( 工学版) , 2022, 43(3) : 44-51.
WANG Z M, WANG D H, LIANG X, et al. Network intrusion detection method based on DBSCAN _GAN _XGBOOST[ J] . Journal of Zhengzhou University ( Engineering Science) , 2022, 43(3) : 44-51.
[15] CHOI H S, KIM S, OH J E, et al. XGBoost-based instantaneous drowsiness detection framework using multitaper spectral information of electroencephalography[C]∥Proceedings of the 2018 ACM International Conference onBioinformatics, Computational Biology, and Health Informatics. New York: ACM, 2018: 111-121.
[16] CHEN T Q, GUESTRIN C. Xgboost: a scalable treeboosting system [ C ] ∥ Proceedings of the 22nd ACMSIGKDD International Conference on Knowledge Discoveryand Data Mining. New York: ACM, 2016: 785-794.
[17] HENDERI H. Comparison of min-max normalization andz-score normalization in the k-nearest neighbor ( kNN) algorithm to test the accuracy of types of breast cancer[ J] .IJIIS: International Journal of Informatics and InformationSystems, 2021, 4(1) : 13-20.
[18] ISLAM S N, SHOLAHUDDIN A, ABDULLAH A S. Extreme gradient boosting ( XGBoost ) method in makingforecasting application and analysis of USD exchange ratesagainst rupiah [ J] . Journal of Physics: Conference Series, 2021, 1722(1) : 012016.
[19] TOPIC A, RUSSO M. Emotion recognition based on EEGfeature maps through deep learning network [ J] . Engineering Science and Technology, an International Journal, 2021, 24(6) : 1442-1454.
[20] OGUNLEYE A, WANG Q G. XGBoost model for chronickidney disease diagnosis[ J] . IEEE / ACM Transactions on Computational Biology and Bioinformatics, 2020, 17(6) :2131-2140.
[21] CHAI T, DRAXLER R R. Root mean square error(RMSE) or mean absolute error ( MAE) ? Arguments against avoiding RMSE in the literature[ J] . GeoscientificModel Development, 2014, 7(3) : 1247-1250.
[22] SHAHID F, ZAMEER A, MUNEEB M. Predictions forCOVID-19 with deep learning models of LSTM, GRU andBi-LSTM [ J ] . Chaos, Solitons & Fractals, 2020,140: 110212.
[23] DE MYTTENAERE A, GOLDEN B, LE GRAND B, etal. Mean Absolute Percentage Error for regression models[ J] . Neurocomputing, 2016, 192: 38-48.
[24] 陈创庭. 大型电站燃气轮机的水洗经济周期研究[ J] .广东电力, 2009, 22(7) : 18-23.
CHEN C T. Research on economic wash period of heavyduty power gas turbine [ J] . Guangdong Electric Power,2009, 22(7) : 18-23.
[25] 程元, 陈坚红, 盛德仁, 等. 联合循环发电机组燃气轮机水洗策略优化模型研究[ J] . 中国电机工程学报,2013, 33(26) : 95-100.
CHENG Y, CHEN J H, SHENG D R, et al. Researchon washing strategy optimization model of combined cyclegas turbines [ J ] . Proceedings of the CSEE, 2013, 33(26) : 95-100.
[26] 李爱民, 王海隆, 许有成. 优化随机森林算法的城市湖泊 DOC 质量浓度遥感反演[ J] . 郑州大学学报( 工学版) , 2022, 43(6) : 90-96.
LI A M, WANG H L, XU Y C. Remote sensing retrievalof urban lake DOC concentration based on optimized random forest algorithm[ J] . Journal of Zhengzhou University(Engineering Science) , 2022, 43(6) : 90-96.

更新日期/Last Update: 2024-09-29