Font Size: a A A

Design And Implementation Of Equipment Health Management System Software

Posted on:2017-03-15Degree:MasterType:Thesis
Country:ChinaCandidate:P YangFull Text:PDF
GTID:2348330488474223Subject:Information Warfare Technology
Abstract/Summary:PDF Full Text Request
In recent years,the failures in electronic system’s essential module parts or the key components often lead to the disastrous accidents occur,which cause the vast loss of the manpower,the material resource and the financial resource et al. All governments urgently need to realize Condition-Based Maintenance on electronic systems,which is based on the fault prognostic and health management technique,and this technique can avoid the overmuch maintenance of traditional fixed-time maintenance or the huge loss of subsequent maintenance. Fault Prognostic and Health Management(PHM) arouses the domestic and foreign researchers’ enormous interest.At present the research results in this domain are very few especially the domestic research just is in start stage,therefore PHM will be the key research direction in the future.PHM mainly includes some key points such as state monitoring and health management,module-level or component-level fault diagnosis and state prediction et al. In this paper, the power system of theodolite is research object,the main works of this dissertation are shown as follows:(1) Based on the OSA-CBM model of open architecture, the framework, requirement, function module and key technology of health management system are analyzed.(2) For the specific power system of theodolite, after comparing many kinds of feature extraction algorithms, the improved LDA algorithm is selected to extract the feature of voltage, and the CHMM diagnosis algorithm is combined to realize the state monitoring and fault diagnosis of the power system.(3) By analyzing the time series forecasting method based on LS-SVM, proposing two kinds of super parameters optimization method based on multi level grid search and genetic algorithm,and compared their performance through experiments. Then combined with the good fault recognition ability of HMM, the LSSVM-HMM prediction method is proposed, and its effectiveness is verified by experiments.(4) Finally, based on the above theoretical knowledge, this paper analyzes the requirements of fault diagnosis and health management system, and develops the main function of the system software. This software is a universal software, which can provide reference for future health management software.In this paper, the coupling between the different modules of the health management software is low, and it can be used as a prototype system to further expand the health management system software.
Keywords/Search Tags:Fault diagnosis, Hidden Markov Model, Failure prediction, Least Squares Support Vector, Software Implementation
PDF Full Text Request
Related items