Transfer learning to detect neonatal seizure from electroencephalography signals

A Caliskan, S Rencuzogullari - Neural Computing and Applications, 2021 - Springer
This paper offers a solution to the problem of detecting neonatal seizures via a transfer
learning technique that judiciously reconstructs pre-trained deep convolution neural …

An indirect flow measurement method for bi-tandem axial piston pump based on leakage flow estimation

Z Sun, Q Zeng, L Wan - Measurement, 2024 - Elsevier
In pump-controlled hydraulic systems, configuring a flowmeter at a variable piston pump to
monitor output flow causes additional losses. A method for indirect flow measurement of the …

A fault detection method for a practical electro-hydraulic variable-displacement pump with unknown swashplate moment

B Xu, X Huang, J Zhang, W Huang… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Electro-hydraulic controlled variable-displacement pump (EHVDP) is a power source of the
hydraulic system, which is extensively used in the electro-hydraulic system due to its high …

Experimental investigation and theoretical evaluation on the leakage mechanisms of seawater hydraulic axial piston pump under sea depth circumstance

K Ma, D Wu, R Xu, H Pang, Y Liu - Engineering Failure Analysis, 2022 - Elsevier
Seawater hydraulic axial piston pump (SHAPP) is an important component of underwater
hydraulic system. However, due to the particularity of the deep-sea high-pressure …

Impact of printing parameters on the dynamic outputs of a slider-crank mechanism with FFF-based 3D-printed crank-arms

Ç Sevim, Ö Özmen, M Parlak… - Proceedings of the …, 2024 - journals.sagepub.com
In this study, the crank-arm of the slider-crank mechanism was produced with different raster
angles (45°, 90°, 135°) and infill densities (25%, 50%, 75%, 100%). The effect of these …

A transfer learning based artificial neural network in geometrical design of textured surfaces for tribological applications

SJ Mousavirad, R Rahmani… - … Metrology and Properties, 2023 - iopscience.iop.org
This study aims at introducing the potential to utilise transfer learning methods in the training
of artificial neural networks for tribological applications. Artificially enhanced surfaces …

Multi-objective optimization of surface texture for the slipper/swash plate interface in EHA pumps

J Zhang, Y Shen, M Gan, Q Su, F Lyu, B Xu… - Frontiers of Mechanical …, 2022 - Springer
Well-designed surface textures can improve the tribological properties and the efficiency of
the electrohydrostatic actuator (EHA) pump under high-speed and high-pressure conditions …

An initial residual stress inference method by incorporating monitoring data and mechanism model

S Wang, Y Li, C Liu, Z Zhao - Chinese Journal of Mechanical Engineering, 2022 - Springer
Initial residual stress is the main reason causing machining deformation of the workpiece,
which has been deemed as one of the most important aspects of machining quality issues …

Analysis of Slipper overturning and collision behavior of the axial piston pump based on rigid-flexible coupling

L Wan, J Jiang, Z Sun, H Niu - IEEE Access, 2023 - ieeexplore.ieee.org
In the working process of the axial piston pump, the composite multi-degree motion of the
slipper and its coupling, as well as the complex working conditions, cause the slipper to …

Analysis of leakage characteristics for bent-axis piston pump based on elastohydrodynamic deformation

L Qing, L Gu, Y Wang, Z Lei - Industrial Lubrication and Tribology, 2022 - emerald.com
Purpose This paper aims to revel the leakage characteristics of the bent-axis piston pump
considering elastohydrodynamic deformation via a dynamic leakage model …