Record Details

The multi sensor-based machining signal fusion to compare the relative efficacy of machine learning based tool wear models

Harvard Dataverse (Africa Rice Center, Bioversity International, CCAFS, CIAT, IFPRI, IRRI and WorldFish)

View Archive Info
 
 
Field Value
 
Title The multi sensor-based machining signal fusion to compare the relative efficacy of machine learning based tool wear models
 
Identifier https://doi.org/10.7910/DVN/7IAJWU
 
Creator Pramod A
Deepak Lawrence K
Jose Mathew
 
Publisher Harvard Dataverse
 
Description This dataset contains a force dynamometer, accelerometer sensor, acoustic emission sensor, and tool wear values for different milling conditions. For each condition, 12 experiments were conducted. Tool 1 (T1) to Tool 4 (T4) were used to develop the machine learning models and is validated with Tool 5 (T5) to Tool 8 (T8) respectively.

This dataset contains raw data taken from each sensor output for each experimental cut.

From this dataset, the relative efficacy of machine learning-based tool wear models was developed. Also, two sensor combination was used to compare the sensor effectiveness in tool wear prediction.
 
Subject Engineering
Multi sensor data fusion, Condition monitoring, Machine Learning, Tool wear prediction
 
Contributor A, PRAMOD