Výsledky vyhledávání

Report

Interpreting What Typical Fault Signals Look Like via Prototype-matching

Autor: Chen, Qian, Dong, Xingjian, Peng, Zhike

Neural networks, with powerful nonlinear mapping and classification capabilities, are widely applied in mechanical fault diagnosis to ensure safety. However, being typical black-box models, their application is limited in high-reliability-required sc

Externí odkaz: http://arxiv.org/abs/2403.07033

Zobrazit plný text záznamu

Akademický článek

Relaxation Characteristics of Hold-Down Spring of Core Support Barrel in Nuclear Reactor

Autor: YANG Taibo, LIU Jiaxin, PENG Zhike, LUO Neng, LIU Caixue

Publikováno v: Shanghai Jiaotong Daxue xuebao, Vol 58, Iss 8, Pp 1290-1296 (2024)

The stability of the core support barrel (CSB) in a nuclear reactor is the guarantee and premise for the normal operation of the reactor core. As the constraint and support of the CSB, the hold-down spring (HDS) directly affects the vibration charact

Externí odkaz: https://doaj.org/article/f0741cb408a24d969b03d8b0aac74592

Zobrazit plný text záznamu

Report

TFN: An Interpretable Neural Network with Time-Frequency Transform Embedded for Intelligent Fault Diagnosis

Autor: Chen, Qian, Dong, Xingjian, Tu, Guowei, Wang, Dong, Zhao, Baoxuan, Peng, Zhike

Publikováno v: Mechanical Systems and Signal Processing, vol. 207, p. 110952, Jan. 2024

Convolutional Neural Networks (CNNs) are widely used in fault diagnosis of mechanical systems due to their powerful feature extraction and classification capabilities. However, the CNN is a typical black-box model, and the mechanism of CNN's decision

Externí odkaz: http://arxiv.org/abs/2209.01992

Zobrazit plný text záznamu