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

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 so complex that the operational data show strong characteristics dynamic, nonlinearity, time delay, which make it difficult to predict productivity accurately via principles models. In this paper, we propose novel integrating PCA-LSTM model improve prediction dredger. Firstly, multiple variables are reduced in dimension selected by PCA method based on working mechanism Then predicted mud concentration long short-term memory network with relevant time-series data. Finally, proposed successfully applied an actual case study China. Also, performs well cross-validation comparative several important characteristics: (i) involves parameters analysis; (ii) deep-learning-based approach can deal operation series special mechanism. This provides heuristic idea data-driven supervision human knowledge application practical engineering.