The numerical prediction of draghead motion of trailing suction Hopper dredger in time domain

Chen, Zhanglan; Ye, Jiawei; Wang, Dongjiao; Hong-li, Yuan

doi:10.1016/j.oceaneng.2014.09.009

Cited by 5 publications

(2 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…FFN accepts the signal from the multi-head attention layer, and maps the input vector to a higher dimensional space through two linear transformation layers, followed by a nonlinear transformation through the activation function to finally obtain a new output, which ensures that the model can learn more complex features. The calculation process of FFN can be expressed as Equation (12):…”

Section: Feed Forward Network and Normalization Layermentioning

confidence: 99%

“…However, the operational environment for dredgers is inherently intricate and influenced by many factors [10]. During each construction period, factors such as soil quality variations, vibrations from wind and waves, and high salinity and corrosion in the sea can cause the sensor of the underwater pump to lose or even fail, resulting in the inability to accurately measure the pressure value of the shaft seal water pressure [11,12]. Therefore, establishing how to predict the shaft seal water pressure of the underwater pump in real time is crucial to the safe operation of the mud pump.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Replacement of Fault Sensor of Cutter Suction Dredger Mud Pump Based on MCNN Transformer

Long,

Fan,

Gao

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

The mud pump water sealing system (MPWSS) is important in the efficient operation and prolonged service life of the cutter suction dredger’s (CSD) mud pump. Considering that the underwater pump operates underwater and the shaft seal water pressure sensor is prone to failure, a hybrid deep learning model MCNN transformer is proposed to predict the underwater pump shaft seal water pressure in the event of sensor failure. This paper uses big data from the dredging project to deeply excavate the relationship between the shaft end sealing water pressure and other construction data by combining experience and artificial intelligence, and then uses multi-scale convolutional neural network (MCNN) to reconstruct the data, highlighting the time series characteristics of the multi-scale data were then input into the transformer model for prediction, and compared with a single MCNN, transformer model and four other neural networks. Finally, the cutter suction dredger “Hua An Long” was selected as an application research case; experimental comparisons were conducted on seven different models to verify the accuracy and applicability of the MCNN-transformer model.

show abstract

Section: Feed Forward Network and Normalization Layermentioning

confidence: 99%