RESEARCH PAPER
Deep learning-based CNC milling tool wear stage estimation with multi-signal analysis
More details
Hide details
1
Department of Mechanical Engineering, Karadeniz Technical University, Turkey
Submission date: 2023-03-02
Final revision date: 2023-05-12
Acceptance date: 2023-06-11
Online publication date: 2023-06-13
Publication date: 2023-06-13
Corresponding author
Yunus Emre Karabacak
Department of Mechanical Engineering, Karadeniz Technical University, Trabzon, Turkey
Eksploatacja i Niezawodność – Maintenance and Reliability 2023;25(3):168082
HIGHLIGHTS
- The convolutional neural network (CNN) was performed to detect the wear stages of the milling tool.
- Short Time Fourier Transform (STFT) was applied to signals, and signal spectrograms were used to train CNN models.
- Pre-trained CNNs (GoogleNet, AlexNet, ResNet-50, and EfficientNet-B0) detected the tool wear stage with varying accuracies.
- CNN shows promise for condition monitoring of milling operations and detecting tool wear stage.
KEYWORDS
TOPICS
ABSTRACT
In this work, the convolutional neural network (CNN), which is a deep learning method in which the features are extracted by an inner process, was performed to detect the wear stages of the milling tool. These stages that define the total lifespan of the tool are known as initial wear (IW), steady-state wear (SSW), and accelerated wear (AW). Short Time Fourier Transform (STFT) was applied to signals, and signal spectrograms were used to train CNN models with different complex architectures. Vibration signals, acoustic emission signals, and motor current signals from The Nasa Ames Milling Dataset were used to obtain the spectrograms. Pre-trained CNNs (GoogleNet, AlexNet, ResNet-50, and EfficientNet-B0) detected the tool wear stage with varying accuracies. It has been seen that the time duration of model training increases as the size of the dataset grows and the network architecture becomes more complex. The recommended method has also been tested on the 2010 PHM Data Challenge Dataset. CNN shows promise for condition monitoring of milling operations and detecting tool wear stage.
CITATIONS (4):
1.
Ultrasound Brain Tomography: Comparison of Deep Learning and Deterministic Methods
Manuchehr Soleimani, Tomasz Rymarczyk, Grzegorz Kłosowski
IEEE Transactions on Instrumentation and Measurement
2.
Intelligent milling tool wear estimation based on machine learning algorithms
Yunus Emre Karabacak
Journal of Mechanical Science and Technology
3.
Predicting Mechanical Behavior of Different Thin-Walled Tubes Using Data-Driven Models
Hamdi KULEYİN, Yunus Emre KARABACAK, Recep GÜMRÜK
Materials Today Communications
4.
Condition monitoring of a CNC hobbing cutter using machine learning approach
Nagesh Tambake, Bhagyesh Deshmukh, Sujit Pardeshi, Sachin Salunkhe, Robert Čep, Emad Abouel Nasr
Advances in Mechanical Engineering