Tool Health Monitoring of a Milling Process Using Acoustic Emissions and a ResNet Deep Learning Model

Ahmed, Mustajab; Kamal, Khurram; Ratlamwala, Tahir Abdul Hussain; Hussain, Ghulam; Alqahtani, Mejdal; Alkahtani, Mohammed; Alatefi, Moath; Alzabidi, Ayoub

doi:10.3390/s23063084

Open AccessArticle

Tool Health Monitoring of a Milling Process Using Acoustic Emissions and a ResNet Deep Learning Model

by

Mustajab Ahmed

¹,

Khurram Kamal

¹,

Tahir Abdul Hussain Ratlamwala

¹

,

Ghulam Hussain

²,

Mejdal Alqahtani

^3,*

,

Mohammed Alkahtani

³

,

Moath Alatefi

³ and

Ayoub Alzabidi

³

¹

Department of Engineering Sciences, National University of Sciences and Technology, Islamabad 44000, Pakistan

²

Mechanical Engineering Department, Faculty of Engineering, University of Bahrain, Isa Town 32038, Bahrain

³

Industrial Engineering Department, College of Engineering, King Saud University, Riyadh 11421, Saudi Arabia

^*

Author to whom correspondence should be addressed.

Sensors 2023, 23(6), 3084; https://doi.org/10.3390/s23063084

Submission received: 6 January 2023 / Revised: 20 February 2023 / Accepted: 1 March 2023 / Published: 13 March 2023

(This article belongs to the Section Intelligent Sensors)

Download

Browse Figures

Versions Notes

Abstract

In the industrial sector, tool health monitoring has taken on significant importance due to its ability to save labor costs, time, and waste. The approach used in this research uses spectrograms of airborne acoustic emission data and a convolutional neural network variation called the Residual Network to monitor the tool health of an end-milling machine. The dataset was created using three different types of cutting tools: new, moderately used, and worn out. For various cut depths, the acoustic emission signals generated by these tools were recorded. The cuts ranged from 1 mm to 3 mm in depth. In the experiment, two distinct kinds of wood—hardwood (Pine) and softwood (Himalayan Spruce)—were employed. For each example, 28 samples totaling 10 s were captured. The trained model’s prediction accuracy was evaluated using 710 samples, and the results showed an overall classification accuracy of 99.7%. The model’s total testing accuracy was 100% for classifying hardwood and 99.5% for classifying softwood.

Keywords: acoustic emission; spectrograms; convolutional neural network; signal processing; feature extraction; tool health monitoring

Share and Cite

MDPI and ACS Style

Ahmed, M.; Kamal, K.; Ratlamwala, T.A.H.; Hussain, G.; Alqahtani, M.; Alkahtani, M.; Alatefi, M.; Alzabidi, A. Tool Health Monitoring of a Milling Process Using Acoustic Emissions and a ResNet Deep Learning Model. Sensors 2023, 23, 3084. https://doi.org/10.3390/s23063084

AMA Style

Ahmed M, Kamal K, Ratlamwala TAH, Hussain G, Alqahtani M, Alkahtani M, Alatefi M, Alzabidi A. Tool Health Monitoring of a Milling Process Using Acoustic Emissions and a ResNet Deep Learning Model. Sensors. 2023; 23(6):3084. https://doi.org/10.3390/s23063084

Chicago/Turabian Style

Ahmed, Mustajab, Khurram Kamal, Tahir Abdul Hussain Ratlamwala, Ghulam Hussain, Mejdal Alqahtani, Mohammed Alkahtani, Moath Alatefi, and Ayoub Alzabidi. 2023. "Tool Health Monitoring of a Milling Process Using Acoustic Emissions and a ResNet Deep Learning Model" Sensors 23, no. 6: 3084. https://doi.org/10.3390/s23063084

APA Style

Ahmed, M., Kamal, K., Ratlamwala, T. A. H., Hussain, G., Alqahtani, M., Alkahtani, M., Alatefi, M., & Alzabidi, A. (2023). Tool Health Monitoring of a Milling Process Using Acoustic Emissions and a ResNet Deep Learning Model. Sensors, 23(6), 3084. https://doi.org/10.3390/s23063084

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Menu

Tool Health Monitoring of a Milling Process Using Acoustic Emissions and a ResNet Deep Learning Model

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI