University of Texas System

Chinese Academy of Sciences

South China University of Technology

Iplook Networks Co., Ltd

Zhen Wang

Rolf A Brekken

Ke Ding

Zhengchao Tu

Xiaomei Ren

Weihua Li

Kristina Y Aguilera

Ruyi Huang

Zhanhui Bu

Yunpu Wu

Youlin Zhu

Wanyi Xie

Hai Qin

A multi-task feature sharing neural network-based intelligent fault diagnosis method has the following steps: (1) separately collecting original vibration acceleration signals of rotating machinery under different experimental conditions, forming samples by means of intercepting signal data having a certain length, and performing labeling; (2) constructing a multi-task feature sharing neural network, having: an input layer, a feature extractor, a classification model and a prediction model; (3) using multi-task joint training to simultaneously train the classification model and the prediction model; and (4) inputting a vibration acceleration signal collected in an actual industrial environment into the trained models to obtain a multi-task diagnosis result.

Intelligent fault diagnosis method based on multi-task feature sharing neural network

Compounds of formula (I), their pharmaceutically acceptable salts and stereoisomers thereof, as well as application in effectively inhibiting the enzymatic activity of discoidin domain receptor 1 and can be used as new therapeutic agents for preventing and treating e.g. inflammation, liver fibrosis, kidney fibrosis, lung fibrosis, skin scar, atherosclerosis, and cancer. The compound of formula I is: wherein the variables are as defined herein. 

Small-molecule inhibitors targeting discoidin domain receptor 1 and uses thereof

Growing community of inventors

Guangzhou, China

Zhen Wang