Comparison of Cutter Suction Dredger slurry concentration soft measurement method based on the mechanism and data dual-driven model

被引:0
作者
Wang, Bin [1 ,2 ]
Fan, Shidong [1 ,2 ,3 ]
Zhu, Hanhua [1 ,2 ]
Xiong, Ting [3 ]
机构
[1] Wuhan Univ Technol, Sch Naval Architecture Ocean & Energy Power Engn, Wuhan 430063, Peoples R China
[2] Minist Transport, PRC, Key Lab Marine Power Engn & Technol, Wuhan 430063, Peoples R China
[3] Wuhan Univ Technol, Sch Transportat & Logist Engn, Wuhan 430063, Peoples R China
来源
PROCEEDINGS OF ASME 2022 41ST INTERNATIONAL CONFERENCE ON OCEAN, OFFSHORE & ARCTIC ENGINEERING, OMAE2022, VOL 5B | 2022年
基金
中国国家自然科学基金;
关键词
cutter suction dredger; slurry concentration; machine learning; reliability;
D O I
暂无
中图分类号
P75 [海洋工程];
学科分类号
0814 ; 081505 ; 0824 ; 082401 ;
摘要
Aiming at the problem that the cutter suction dredger (CSD) slurry concentration measurement method (gamma-ray concentration meter) is single, and the frequent failures affect the construction continuity. A soft measurement method of slurry concentration based on the mechanism and data dual-mode drive was proposed. First, analyze the process of cutter cutting and the force of the mud and sand particles inside of the cutter. Then, the concentration prediction model of the slurry transportation process was presented by digital simulation modeling technology. Second, a data-driven slurry concentration prediction model was established, using big data, machine learning, data mining, and other technologies, which learn the historical data of the dredger. To verify the accuracy of the two models, this paper designed three different parameters and five operating conditions on the experimental platform. Experiments show that the prediction performance of the two models is good. In most working conditions, the mechanism-driven slurry concentration model and the data-driven slurry concentration model maintain an error rate of less than 5%, but the prediction error of the mechanism-driven slurry concentration model is relatively large under the flow velocity at the suction port is 3.5 m/s. Overall, the slurry concentration prediction model based on the mechanism & data has high prediction accuracy and can improve construction efficiency and reliability.
引用
收藏
页数:11
相关论文
共 20 条
[1]  
Bin W., 2020, Ship Engineering, V42, P7
[2]   Optimization of mechanical dredging operations for sediment remediation [J].
Blazquez, CA ;
Adams, TM ;
Keillor, P .
JOURNAL OF WATERWAY PORT COASTAL AND OCEAN ENGINEERING-ASCE, 2001, 127 (06) :299-307
[3]  
Burger M. d., 2005, Terra et Aqua, V98, P12
[4]   XGBoost: A Scalable Tree Boosting System [J].
Chen, Tianqi ;
Guestrin, Carlos .
KDD'16: PROCEEDINGS OF THE 22ND ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING, 2016, :785-794
[5]   Influence functions of the Spearman and Kendall correlation measures [J].
Croux, Christophe ;
Dehon, Catherine .
STATISTICAL METHODS AND APPLICATIONS, 2010, 19 (04) :497-515
[6]   Experimental and numerical investigation of cutter head dredging flows [J].
Dekker, MA ;
Kruyt, NP ;
den Burger, M ;
Vlasblom, WJ .
JOURNAL OF WATERWAY PORT COASTAL AND OCEAN ENGINEERING, 2003, 129 (05) :203-209
[7]   Greedy function approximation: A gradient boosting machine [J].
Friedman, JH .
ANNALS OF STATISTICS, 2001, 29 (05) :1189-1232
[8]  
Ledezma A., 2010, Intelligent Data, V14
[9]   Novel Method of Construction-Efficiency Evaluation of Cutter Suction Dredger Based on Real-Time Monitoring Data [J].
Li, Mingchao ;
Kong, Rui ;
Han, Shuai ;
Tian, Guiping ;
Qin, Liang .
JOURNAL OF WATERWAY PORT COASTAL AND OCEAN ENGINEERING, 2018, 144 (06)
[10]   A novel stacked generalization ensemble-based hybrid LGBM-XGB-MLP model for Short-Term Load Forecasting [J].
Massaoudi, Mohamed ;
Refaat, Shady S. ;
Chihi, Ines ;
Trabelsi, Mohamed ;
Oueslati, Fakhreddine S. ;
Abu-Rub, Haitham .
ENERGY, 2021, 214