Development of a Neural Network-Based Real-Time Fatigue Monitoring System for the Heavy Load Carrying Facility

Abstract:

Article Preview

The heavy load carrying facility, such as ladle crane, is operating under severe working environment. It usually carries melted iron to the furnace, and thus, the accident due to crane failure may cause detrimental damage to the entire steel making factory. While the ladle crane is designed for 20 years of safe operation in a steel making company, several critical cracks due to fatigue loading have been reported during the maintenance process. In order to prevent fatal failure due to crack growth, ladle crane has been periodically inspected and maintained. However, the inspection and maintenance including repair and replacement cause the whole manufacturing line to stop, it is critical to set the appropriate inspection interval and replacement criteria. For this reason, the importance of plant maintenance (PM) has been highly raised to provide efficient plant operation. Recently, a number of engineering methodologies, such as fitness for service guidelines (FFS) and plant lifecycle management (PLM) system, have been applied to improve the plant operation efficiency. Also, a network-based business operation system, which is called ERP (Enterprise Resource Planning), has been introduced in the field of plant maintenance. However, there hasn’t been any attempt to connect engineering methodologies to the ERP PM(Plant Maintenance) system. In this paper, an engineering methodology which provides life time evaluation under fatigue loading has been implemented to the web-based ERP PM system along with real-time fatigue monitoring system. In order to monitor the real time loading, a web-based fatigue monitoring system for ladle crane has been developed and installed inside the ladle crane. For the estimation of fatigue life, 3-dimensional finite element (FE) analyses were conducted for actual transients. Finally, the fatigue life time estimation program is developed by integrating FE analysis results and real-time monitoring data. For the direct calculation of remained fatigue life, an artificial neural network (ANN) algorithm has been applied. The proposed system is expected to play a great role in determining appropriate inspection and maintenance schedule which has become critical issue for the efficient plant maintenance.

Info:

Periodical:

Solid State Phenomena (Volume 110)

Edited by:

Young-Jin Kim

Pages:

201-212

DOI:

10.4028/www.scientific.net/SSP.110.201

Citation:

J. C. Kim et al., "Development of a Neural Network-Based Real-Time Fatigue Monitoring System for the Heavy Load Carrying Facility", Solid State Phenomena, Vol. 110, pp. 201-212, 2006

Online since:

March 2006

Export:

Price:

$35.00

In order to see related information, you need to Login.

In order to see related information, you need to Login.