MATEC Web Conf.
Volume 128, 20172017 International Conference on Electronic Information Technology and Computer Engineering (EITCE 2017)
|Number of page(s)||4|
|Section||Simulation Model and Algorithm|
|Published online||25 October 2017|
Fault detection Based Bayesian network and MOEA/D applied to Sensorless Drive Diagnosis
Wuhan University of Technology, School of Automation, 122 Luoshi Road, Wuhan, China
2 Wuhan University of Technology, School of Management, 205 Xiongchu Road, Wuhan, China
a Qing Zhou: firstname.lastname@example.org
Sensorless Drive Diagnosis can be used to assess the process data without the need for additional cost-intensive sensor technology, and you can understand the synchronous motor and connecting parts of the damaged state. Considering the number of features involved in the process data, it is necessary to perform feature selection and reduce the data dimension in the process of fault detection. In this paper, the MOEA / D algorithm based on multi-objective optimization is used to obtain the weight vector of all the features in the original data set. It is more suitable to classify or make decisions based on these features. In order to ensure the fastness and convenience sensorless drive diagnosis, in this paper, the classic Bayesian network learning algorithm-K2 algorithm is used to study the network structure of each feature in sensorless drive, which makes the fault detection and elimination process more targeted.
© The authors, published by EDP Sciences, 2017
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. (http://creativecommons.org/licenses/by/4.0/).
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.