Please login first
Tool Wear Estimation in the Milling Process Using a Simple Machine Learning Backpropagation Algorithm
* 1, 2 , * 1 , 1 , 1 , 1
1  Department of Electrical and Computer Engineering, São Carlos School of Engineering, University of São Paulo USP, Av. Trab. São Carlense, 400-Pq. Arnold Schimidt, São Carlos 13566-590, SP, Brazil
2  Aranouá Project, Federal Institute of Amazonas IFAM, R. dos Açaizeiros-São José Operário, Manaus, AM, Brazil
Academic Editor: Stefano Mariani (registering DOI)

Tool condition monitoring (TCM) systems are essential in milling operations to guarantee the product’s quality, and when those are paired with indirect measure techniques, such as vibration or acoustic emission sensors, the monitoring can happen without sacrificing productivity. Some more advanced techniques in tool wear estimation are based on supervised machine learning algorithms, like several other applications in the Industry 4.0’s context, however, a satisfactory performance can be obtained with simple techniques and low computational power. This work focuses on an application of tool wear estimation using a simple backpropagation neural network in a milling dataset. Statistics techniques, i.e., the mean, variance, skewness and kurtosis were used as features extracted of indirect measurements from vibration and acoustic emission sensors’ data in a real milling testbench dataset containing multiple experiments with sensor data and a direct measure of the flank wear (VB) in most instances. The data was preprocessed, specifically to acquire clean and normalized values for the neural network training, assuming the VB measure as the target variable to predict tool wear, and all incomplete samples without a VB measure, as well as outliers, were removed beforehand. The train and test subsets were chosen randomly after making sure that the maximum values of every variable were represented in the training subset. A multiple topology approach was implemented to test multiple backpropagation neural networks’ configurations to determine the most suitable one based on two performance criteria, i.e., Mean Absolute Percent Error (MAPE) and variance. Although only a simple backpropagation algorithm was used, the results were adequate to demonstrate a balance between accuracy and computational resource usage.

Keywords: Tool Condition Monitoring; Milling; Backpropagation; Machine Learning