期刊名称：Lecture Notes in Engineering and Computer Science
印刷版ISSN：2078-0958
电子版ISSN：2078-0966
出版年度：2019
卷号：2240
页码：252-257
出版社：Newswood and International Association of Engineers
摘要：Successfully deploying AI models for a
reconfigurable AI-driven enterprise is a challenge. This work
focuses on the design and implementation of a reconfigurable
machine learning data analytics tool supporting flexible and
automatic configurability in manufacturing. This tool provides a
user interface and RESTful API to be used by other components
of the architecture for deployment and use of machine learning
and statistical models as a service for the purpose of predictive
maintenance. This tool supports text classification to label
unstructured data and uses machine-learning models based on
decision-trees to predict failure of the production machines.
关键词：machine learning; condition monitoring;
predictive maintenance; text mining; service orientated architecture
