The Bayesian Networks Applied to a Steering Gear System Fault Diagnostics

2010 ◽  
Author(s):  
Marcelo R. Martins ◽  
Daniel F. da Silva ◽  
Fabio M. Maruyama ◽  
Fabio F. Loriggio ◽  
Marcelo F. Pedro ◽  
...  
Keyword(s):  
Bayesian Networks ◽  
Bayesian Belief Network ◽  
Gear System ◽  
Fault Diagnostics ◽  
Fault Trees ◽  
Belief Network ◽  
Ship Security

In this paper it is presented a brief description of a method that consists in using Bayesian Belief Network (BBN) created by converting Fault Trees (FT) to determine the most probable causes of a failure in a system given some evidence through observation. In addition, it is presented an example based on the steering gear system of a containership focusing on the cases in which the vessel is operating in restricted waters or performing the procedure for mooring/unmooring. The steering gear system was chosen due to its importance to restricted water navigation and to the mooring operation. The system must be completely available for these situations; otherwise, the ship security and the crew safety are implicated.

scholarly journals Sensor selection for fault diagnostics using performance metric

2018 ◽  
Vol 233 (4) ◽  
pp. 537-552
Author(s):  
J Reeves ◽  
R Remenyte-Prescott ◽  
J Andrews
Keyword(s):  
System Performance ◽  
Selection Process ◽  
Bayesian Belief Network ◽  
Sensor Selection ◽  
Fault Diagnostics ◽  
Belief Network ◽  
Performance Metric ◽  
Large Numbers ◽  
Potential Component ◽  
Component Failures

As technology advances, modern systems are becoming increasingly complex, consisting of large numbers of components, and therefore large numbers of potential component failures. These component failures can result in reduced system performance, or even system failure. The system performance can be monitored using sensors, which can help to detect faults and diagnose failures present in the system. However, sensors increase the weight and cost of the system, and therefore, the number of sensors may be limited, and only the sensors that provide the most useful system information should be selected. In this article, a novel sensor performance metric is introduced. This performance metric is used in a sensor selection process, where the sensors are chosen based on their ability to detect faults and diagnose failures of components, as well as the effect the component failures have on system performance. The proposed performance metric is a suitable solution for the selection of sensors for fault diagnostics. In order to model the outputs that would be measured by the sensors, a Bayesian Belief Network is developed. Sensors are selected using the performance metric, and sensor readings can be introduced in the Bayesian Belief Network. The results of the Bayesian Belief Network can then be used to rank the component failures in order of likelihood of causing the sensor readings. To illustrate the proposed approach, a simple flow system is used in this article.

scholarly journals Increasing Local Fish Consumption: A Bayesian Belief Network Analysis

2021 ◽  
Vol 33 (1) ◽  
pp. 104-121
Author(s):  
Samantha Paredes ◽  
Sean Pascoe ◽  
Louisa Coglan ◽  
Carol Richards
Keyword(s):  
Network Analysis ◽  
Fish Consumption ◽  
Bayesian Belief Network ◽  
Belief Network

scholarly journals Estimating Survival in Patients with Operable Skeletal Metastases: An Application of a Bayesian Belief Network

PLoS ONE ◽  
2011 ◽  
Vol 6 (5) ◽  
pp. e19956 ◽  
Author(s):  
Jonathan Agner Forsberg ◽  
John Eberhardt ◽  
Patrick J. Boland ◽  
Rikard Wedin ◽  
John H. Healey
Keyword(s):  
Bayesian Belief Network ◽  
Skeletal Metastases ◽  
Belief Network

Detecting ECG abnormalities using an ensemble framework enhanced by Bayesian belief network

2022 ◽  
Vol 72 ◽  
pp. 103320
Author(s):  
Jingyu Han ◽  
Guangpeng Sun ◽  
Xinhai Song ◽  
Jing Zhao ◽  
Jin Zhang ◽  
...  
Keyword(s):  
Bayesian Belief Network ◽  
Belief Network ◽  
Ecg Abnormalities
Sign in / Sign up

Export Citation Format

Share Document