Development of Predictive Maintenance Model for Induction Motor
Nguyen, Thanh (2021)
Nguyen, Thanh
2021
All rights reserved. This publication is copyrighted. You may download, display and print it for Your own personal use. Commercial use is prohibited.
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi:amk-202104296414
https://urn.fi/URN:NBN:fi:amk-202104296414
Tiivistelmä
The aim of this project was to create a model to predict the remaining useful life of induction motor with minor investment available in the plant. The project helps to broaden electronics student’s horizons of automation and machine learning field. It answers whether Siemens Programmable Logical Controller (PLC) can work with other Internet of Things (IoT) tools in the Fourth Industrial revolution. This project’s result can be used as one method alternative for a maintenance engineer to perform predictive maintenance without attaching additional sensor devices on a machine or buying expensive predictive software from a third party.
In this project, the development of a predictive maintenance model is started by collecting induction motor data. The induction motor data is collected by the PLC and stored on the Microsoft SQL local server. The raw data is fetched and loaded into the data frame for predicting the induction motor’s remaining useful life. The remaining useful life of the induction motor is estimated by using the linear regression model. Lastly, the efficiency of a predictive model is evaluated by calculating its root mean square error.
In this project, the development of a predictive maintenance model is started by collecting induction motor data. The induction motor data is collected by the PLC and stored on the Microsoft SQL local server. The raw data is fetched and loaded into the data frame for predicting the induction motor’s remaining useful life. The remaining useful life of the induction motor is estimated by using the linear regression model. Lastly, the efficiency of a predictive model is evaluated by calculating its root mean square error.