Wyniki wyszukiwania - BazTech

Ograniczanie wyników

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Sortuj według:

Ogranicz wyniki do:

Phase unwrapping method based on improved U-net network

Li Jiansu, Zhang Jingjing, Dang Changying, Chen Haowen, Yang Zhao, Zhao Junsheng

Optica Applicata

2024

Vol. 54, nr 4

523--539

In order to solve the problem of unwrapping the phase in digital holographic reconstruction, a new convolutional architecture is proposed. The proposed method takes the U-net network as a framework, and incorporates the lightweight deep learning network of Mobilenetv1 in the encoding part to reduce the model complexity, the number of parameters, and the cost of computation; and proposes a complex dual-channel convolutional block in the decoding part instead of the 3×3 convolution in the original U-net network, which fully incorporates the features in the decoding process. (abbreviated as DC-UMnet network) Meanwhile, the loss value is calculated using the SmoothL1Loss function, and the activation function uses ReLU6. Finally, the simulated dataset containing noise is used for training; and the experimentally obtained wrapped phase maps is used for verifying. The simulation results show that under different degrees of noise conditions, compared with the DCT method and the deep learning phase unwrapping network, the structural similarity index values of the DC-UMnet network are improved by 0.416 and 0.064; and the normalized root-mean-square errors are reduced respectively by 13.2% and 5.8%. Through the actual measurement data, the proposed network model of the feasibility and good noise reduction ability are verified, which can realize digital holographic phase unwrapping in a simple, fast and efficient way.

Sound Field Modelling and Noise Reduction for a Forklift Power Compartment Based on Perfectly Matched Layer and Acoustic Packaging Design

Zhang Enlai, Liu Zhiqi, Zhang Jingjing, Lin Jiahe

Archives of Acoustics

2021

Vol. 46, No. 3

491--498

The core goal of this paper is to put forward a feasible scheme of noise reduction for a target forklift on the basis of solving the problem of vibration and acoustic radiation from complex structures in infinite domain. Based on the previous report and vibration acceleration tests, the acoustic virtual wind tunnel model of forklift power compartment was established using finite element method and boundary element method, in which the perfectly matched layer was first applied to simulate the attenuation propagation of sound waves in air. In addition, according to the distribution characteristics of sound pressure field with different frequencies, the acoustic energy mainly radiated through the bottom and right side, and concentrated in the low frequency. Consequently, the acoustic packaging design for the whole forklift power compartment was presented, and a satisfying noise reduction effect was achieved.