Development of Real-time Condition Monitoring System Based on Machine Learning for Winch Equipment of Floating Crane

2020 ◽  
Vol 25 (4) ◽  
pp. 445-454
Author(s):  
Se-Yun Hwang ◽  
Jang-Hyun Lee ◽  
Kwang-Sik Kim ◽  
Jae-Won Oh ◽  
Cheon-Hong Min
Author(s):  
Ting-Chi Yeh ◽  
Min-Chun Pan

When rotary machines are running, acousto-mechanical signals acquired from the machines are able to reveal their operation status and machine conditions. Mechanical systems under periodic loading due to rotary operation usually respond in measurements with a superposition of sinusoids whose frequencies are integer (or fractional integer) multiples of the reference shaft speed. In this study we built an online real-time machine condition monitoring system based on the adaptive angular-velocity Vold-Kalman filtering order tracking (AV2KF_OT) algorithm, which was implemented through a DSP chip module and a user interface coded by the LabVIEW®. This paper briefly introduces the theoretical derivation and numerical implementation of computation scheme. Experimental works justify the effectiveness of applying the developed online real-time condition monitoring system. They are the detection of startup on the fluid-induced instability, whirl, performed by using a journal-bearing rotor test rig.


2001 ◽  
Author(s):  
John Donelson ◽  
Wayne M. Zavis ◽  
S. K. (John) Punwani ◽  
Monique Ferguson Stewart ◽  
Mark C. Edwards

Abstract Science Applications International Corporation (SAIC) and Wilcoxon Research have developed a real-time on-board condition monitoring system for freight trains. The Office of Research and Development of the Federal Railroad Administration funded the development of the system. The system monitors bearings, wheels, trucks and brakes on freight trains in order to detect equipment defects and derailments. The objectives of the system are to improve railroad safety and operation efficiency through continuous monitoring of mechanical components on freight trains.


Sign in / Sign up

Export Citation Format

Share Document