scholarly journals Research on Fault Diagnosis for Pumping Station Based on T-S Fuzzy Fault Tree and Bayesian Network

2017 ◽  
Vol 2017 ◽  
pp. 1-7 ◽  
Author(s):  
Zhuqing Bi ◽  
Chenming Li ◽  
Xujie Li ◽  
Hongmin Gao
Keyword(s):  
Fault Diagnosis ◽  
Bayesian Network ◽  
Historical Data ◽  
Complex Structure ◽  
Fault Tree ◽  
Uncertain Information ◽  
New Approach ◽  
Pumping Station ◽  
The One ◽  
Tree Method

According to the characteristics of fault diagnosis for pumping station, such as the complex structure, multiple mappings, and numerous uncertainties, a new approach combining T-S fuzzy gate fault tree and Bayesian network (BN) is proposed. On the one hand, traditional fault tree method needs the logical relationship between events and probability value of events and can only represent the events with two states. T-S fuzzy gate fault tree method can solve these disadvantages but still has weaknesses in complex reasoning and only one-way reasoning. On the other hand, the BN is suitable for fault diagnosis of pumping station because of its powerful ability to deal with uncertain information. However, it is difficult to determine the structure and conditional probability tables of the BN. Therefore, the proposed method integrates the advantages of the two methods. Finally, the feasibility of the method is verified through a fault diagnosis model of the rotor in the pumping unit, the accuracy of the method is verified by comparing with the methods based on traditional Bayesian network and BP neural network, respectively, when the historical data is sufficient, and the results are more superior to the above two when the historical data is insufficient.

Fault Diagnosis of the Foundation Brake Rigging System Based on Fault Tree and Bayesian Network

2016 ◽  
Vol 693 ◽  
pp. 1734-1740 ◽  
Author(s):  
Dan Wang ◽  
Ying Tian ◽  
Tai Yong Wang ◽  
Shi Feng Ye ◽  
Qiong Liu
Keyword(s):  
Complex System ◽  
Fault Diagnosis ◽  
Bayesian Network ◽  
Fault Tree ◽  
Fault Analysis ◽  
Inference Process ◽  
Tree Algorithm ◽  
Junction Tree ◽  
Bayesian Tree

Based on the analysis of the advantages and limits of the traditional fault tree and Bayesian network in fault diagnosis, the method that building the fault Bayesian network based on fault tree is proposed in this paper. The paper introduces the correspondences between elements of the fault tree and the fault Bayesian network, also describes the inference process of the junction tree algorithm in the fault Bayesian network. Then with the foundation brake rigging system of CRH380AL EMU as an example, we build up the fault tree, complete its transmission to the fault Bayesian network, proving the superiority of the fault Bayesian tree in fault analysis of the complex system at last.

Fault Diagnosis Method of Vehicle Power System Using Bayesian Network

2014 ◽  
Vol 556-562 ◽  
pp. 3134-3138
Author(s):  
He Jia Li ◽  
Yan Wei Cheng ◽  
Cheng Yao ◽  
Hai Feng Xu ◽  
Zhao Yao ◽  
...  
Keyword(s):  
Fault Diagnosis ◽  
Power System ◽  
Bayesian Network ◽  
Graph Model ◽  
Small Sample ◽  
Uncertain Information ◽  
Multiple Faults ◽  
Diagnosis Method ◽  
Mutual Relations ◽  
Network Fault

The fault diagnosis of vehicle power system that the structure and characteristics of components are complex, each module and internal modules exist coupling, cross-linked mutual relations and the uncertainties, the system status and working conditions are difficult to describe by precisely mathematical model, and test cost expensive, less fault samples. Thus its fault diagnosis is the decision problem of uncertain information in a small sample. it is proposed that combining multi-signal flow graph model with Bayesian network fault diagnosis method. The fault diagnosis model of power system and the corresponding Bayesian network structure are built, which achieve the fault diagnosis of power system, Diagnosis example shows that the method of the vehicle power has a higher failure troubleshooting capabilities of the system single and multiple faults.

Equipment Impact Rate Assessment Using Bayesian Networks

2016 ◽  
Author(s):  
Smitha D. Koduru ◽  
Dongliang Lu
Keyword(s):  
Bayesian Networks ◽  
Bayesian Network ◽  
Common Ground ◽  
Fault Tree ◽  
Prior Probabilities ◽  
Tree Methods ◽  
Reporting Tool ◽  
Triggering Events ◽  
Intuitive Method ◽  
Tree Method

Bayesian networks offer an intuitive method of modelling causal relationships between the triggering events that lead to equipment impact on a pipeline. This method offers an advantage over the more well-known fault-tree methods due to its ability to use Bayesian inference for updating the prior probabilities of triggering events that lead to equipment impact such as, failure of permanent markers, use of one-call system, or failure of right-of-way patrol. In this paper, a modelling approach for a Bayesian network for equipment impact assessment, based on the available fault-tree method, is demonstrated. The advantages of the Bayesian network, such as updating the occurrence rates of basic triggering events and tracking information flow based on partial and incomplete information are illustrated by using the event data available from the damage incident reporting tool (DIRT) of Common Ground Alliance (CGA).

Sign in / Sign up

Export Citation Format

Share Document