Tool wear monitoring using artificial neural network based on extended Kalman filter weight updation with transformed input patterns

2009 ◽  
Vol 21 (6) ◽  
pp. 717-730 ◽  
Author(s):  
Srinivasan Purushothaman
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Kalman Filter ◽  
Tool Wear ◽  
Extended Kalman Filter ◽  
Tool Wear Monitoring ◽  
Wear Monitoring ◽  
Artificial Neural

Estimation of Critical Platform Integrity Parameters in the Absence of Direct Measurements in the Context of Integrated Marine Monitoring Systems

2013 ◽  
Author(s):  
Soma Maroju ◽  
Kevin Delaney ◽  
Christopher Leon ◽  
Igor Prislin
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Kalman Filter ◽  
Missing Data ◽  
Extended Kalman Filter ◽  
Working Condition ◽  
Operational Risk ◽  
Monitoring Systems ◽  
Marine Monitoring ◽  
Direct Measurements

Integrated Marine Monitoring Systems (IMMS) are designed to help operators to reduce operational risk by providing information about the environment and the platform responses in real time. In spite of efforts to keep monitoring systems in working condition by following planned maintenance and upgrades, some sensors may fail intermittently or may generate spurious data. Quite often, intervention to repair or to replace a faulty sensor is either difficult, or even not feasible. This paper discusses various methods to estimate critical platform integrity parameters with satisfactory confidence in the cases when direct measurements are temporarily unavailable or questionable. Methods such as Artificial Neural Network and Extended Kalman Filter have been employed and specifically tuned to particular challenges. Estimated results for the missing data, such as platform position or riser loads, are reliable as they have been validated against historically good data. The merit of the paper is to present the methods that can increase reliability of the IMMS, enhance safety, reduce operational risk and decrease cost in maintaining expensive offshore systems.

Sign in / Sign up

Export Citation Format

Share Document