Font Size: a A A

Reliability Analysis Of Bus Braking System Based On Bayesian Network

Posted on:2017-04-20Degree:MasterType:Thesis
Country:ChinaCandidate:L ChenFull Text:PDF
GTID:2272330503474709Subject:Vehicle Engineering
Abstract/Summary:PDF Full Text Request
Braking system is one of the important parts of the bus and it directly affects the driving safety and parking reliability. So it is necessary to carry out reliability analysis. But it has the characteristics of so many failure modes and states, and the accurate fault probabilities of the parts in the system are difficult to obtain. Therefore, an improved reliability analysis method based on fuzzy multi-state Bayesian network was proposed to solve the fuzziness and polymorphism of the system.Firstly, on the basis of analyzing failure mode of bus braking system, in view of the problems of fuzziness and polymorphism in the reliability analysis, the traditional method was improved and fuzzy multi-state Bayesian network was proposed. The characteristics and the reasoning process of this method were introduced in detail.Secondly, according to standard tree-like Bayesian network structure, based on the characteristics of the hard evidence discretization, the soft and hard evidence were separated and the index algorithm based on hard evidence was proposed. This algorithm exchanged the exponential dependence of hard evidence to linear dependence. Experimental results showed that when the hard evidence of more than 40%, the efficiency of the algorithm was higher than traditional elimination algorithm and tree algorithm.And then, based on the analysis of bus braking system structure and the failure mode, Reliability assessment model of bus braking system based on fuzzy multi-state Bayesian network was established. And the probabilities of the system in different states were calculated by using the improved inference algorithm. On the basis of the advantages of Bayesian network diagnostic reasoning, the orders of fault detection were got and the bus braking system vulnerabilities were confirmed. The important element is the key indicator which was used to identify the biggest factors impact on the system. In addition, based on the results of Bayesian network diagnostic, the reliabilities of the system were allocated in this paper, and the results of allocation met the design requirements, therefore, the validity of this method was testified.Finally, a special program which can analyze the braking system reliability easily was written out by Visual Basic and MATLAB based on technology of ActiveX. It reflected the advantage of MATLAB in math problems processing and Visual Basic in form design and interface display superiority.
Keywords/Search Tags:Bus braking system, Bayesian network, Polymorphism, Fuzzy theory, Reliability analysis
PDF Full Text Request
Related items