journal article·2021-09-02Open access

A Novel Principal Component Analysis Integrating Long Short-Term Memory Network and Its Application in Productivity Prediction of Cutter Suction Dredgers

Ke Yang, Jun-Lang Yuan, Ting Xiong, Bin Wang, Shi-Dong Fan

Applied Sciences· Volume 11· Issue 17

Abstract

Dredging is a basic construction for waterway improvement, harbor basin maintenance, land reclamation, environmental protection dredging, and deep-sea mining. The dredging process of cutter suction dredgers is so complex that the operational data show strong characteristics of dynamic, nonlinearity, and time delay, which make it difficult to predict the productivity accurately via basic principles models. In this paper, we propose a novel integrating PCA-LSTM model to improve the productivity prediction of cutter suction dredger. Firstly, multiple variables are reduced in dimension and selected by PCA method based on the working mechanism of cutter suction dredger. Then the productivity is predicted via mud concentration in long short-term memory network with relevant operational time-series data. Finally, the proposed method is successfully applied to an actual case study in China. Also, it performs well in the cross-validation and comparative study for several important characteristics: (i) it involves the operational parameters based on the mechanism analysis; and (ii) it is a deep-learning-based approach that can deal with operation series data with a special memory mechanism. This study provides a heuristic idea for integrating the data-driven method and supervision of human knowledge for application in practical engineering.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Environmental and Sediment Control · Modeling, Simulation, and Optimization

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

School of Energy and Power Engineering, Wuhan University of Technology, Wuhan 430063, China

Funding

National Natural Science Foundation of China

References (27)

Show source-provided references
1. Seismic evidence for deep-water transportation in the mantle10.1126/science.1140855 ↗
2. Nature of sediment accumulation on the Amazon continental shelf10.1016/0278-4343(86)90061-0 ↗
3. Contrasting styles of off-shelf sediment accumulation in New Guinea10.1016/S0025-3227(03)00069-0 ↗
4. Expert system for operation optimization and control of cutter suction dredger10.1016/j.eswa.2007.02.025 ↗
5. Research on predicting the productivity of cutter suction dredgers based on data mining with model stacked generalization10.1016/j.oceaneng.2020.108001 ↗
6. Modeling and simulation for mission operations work system design10.1080/07421222.2003.11045745 ↗
7. Optimization of mechanical dredging operations for sediment remediation10.1061/(ASCE)0733-950X(2001)127:6(299) ↗
8. A Novel Method for Evaluating Dredging Productivity Using a Data Envelopment Analysis-Based Technique10.1155/2019/5130835 ↗
9. Review of machine learning based remaining useful life prediction methods for equipment10.3901/JME.2019.08.001 ↗
10. Research and analysis on construction output prediction of cutter suction dredger based on RBF neural network
11. Application of extreme learning machines in productivity prediction of trailing suction hopper dredger
12. Prediction of cutter suction dredger production based on double hidden layer BP neural network
13. Bearing remaining useful life prediction based on deep autoencoder and deep neural networks10.1016/j.jmsy.2018.04.008 ↗
14. Applicability of deep neural networks on production forecasting in bakken shale reservoirs10.1016/j.petrol.2019.04.016 ↗
15. DBN based SD-ARX model for nonlinear time series prediction and analysis10.1007/s10489-020-01804-2 ↗
16. A prognostic model based on DBN and diffusion process for degrading bearing10.1109/TIE.2019.2947839 ↗
17. Using deep learning-based approach to predict remaining useful life of rotating components10.1109/TSMC.2017.2697842 ↗
18. Multiobjective deep belief networks ensemble for remaining useful life estimation in prognostics10.1109/TNNLS.2016.2582798 ↗
19. Operational Trend Prediction and Classification for Chemical Processes: A Novel Convolutional Neural Network Method Based on Symbolic Hierarchical Clustering10.1016/j.ces.2020.115796 ↗
20. A recurrent neural-network-based real-time learning control strategy applying to nonlinear systems with unknown dynamics10.1109/41.661316 ↗
21. Prognosis of defect propagation based on recurrent neural networks10.1109/TIM.2010.2078296 ↗
22. Learning Adaptive Semi-Supervised Multi-Output Soft-Sensors with Co-Training of Heterogeneous Models10.1109/ACCESS.2020.2979611 ↗
23. Yang, K., Liu, Y., Yao, Y., Fan, S., and Ali, M. (2021). Operational time-series data modeling via LSTM network integrating principal component analysis based on human experience. J. Manuf. Syst., in press.10.1016/j.jmsy.2020.11.020 ↗
24. Preedy, V.R., and Watson, R.R. (2020). Principal Components Analysis. Handbook of Disease Burdens and Quality of Life Measures, Springer.
25. Long short-term memory10.1162/neco.1997.9.8.1735 ↗
26. A New Method for Calculating General Lagrange Multiplier in the Variational Iteration Method10.1002/num.20567 ↗
27. Data mining approach to construction productivity prediction for cutter suction dredgers10.1016/j.autcon.2019.102833 ↗