Skip to content

pentanol2/RULEstimator

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

1 Commit
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

RUL Estimator Using Apache Spark

In this project the main gold is to provide a general prototype for a small CPS. We are showcasing the example of a system that predicts the remaining useful life (RUL) of a set of running engines. The job is performed through three modules:

  • ML Module:

            In machine learning module we perform not only the modeling job done in ml, but we perform data collection, eda, and preprocessing job. After validation and testing, the final output of this module is a machine learning model to deploy to work for us in real time.


  • RT Module:

            RT or Real time Analysis Module. In this module the real time analysis module, uses the last updated/deployed model to make prediction on sensor signals incoming from the MQTT broker. The prediction result is logged to text files, each corresponding to an analysis session.


  • MQTT Client Broker Module:

            The MQTT module is a simulation of sensor behavior in real life. The MQTT client reads sensor data for a dataset file line by line in pre-specified time intervals and sends the sensors reading to the MQTT broker. The MQTT broker itself forwards the sensor data to Spark's Streaming connector specified for MQTT.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages