Search research articles

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Integration of RNN and CatBoost models in a tea-waste biochar filtration system for toxic organic pollutant removal efficiency prediction.

RSC advances·2025

See all related articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Aug 1, 2025

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

Enhancing Tool Wear Prediction Accuracy Using Walsh-Hadamard Transform, DCGAN and Dragonfly Algorithm-Based Feature

Milind Shah¹, Himanshu Borade², Vedant Sanghavi³

¹Department of Mechanical Engineering, School of Technology, PDEU, Gandhinagar 382426, Gujarat, India.

Sensors (Basel, Switzerland)

|April 28, 2023

Summary

This study introduces a tool condition monitoring (TCM) system using advanced signal processing and machine learning. The proposed method accurately predicts tool wear, minimizing manufacturing downtime and costs.

Keywords:

Dragonfly Harris hawk Walsh–Hadamard transform feature selection generative adversarial network tool wear

More Related Videos

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers

Published on: March 1, 2024

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

Related Experiment Videos

Last Updated: Aug 1, 2025

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers

Published on: March 1, 2024

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

Area of Science:

Manufacturing Engineering
Machine Learning Applications
Signal Processing

Background:

Tool wear significantly impacts manufacturing quality, productivity, and operational costs.
Tool Condition Monitoring (TCM) systems are increasingly vital for optimizing manufacturing processes.
Limited experimental data often hinders the development of effective TCM systems.

Purpose of the Study:

To develop an advanced TCM system for accurate tool wear prediction.
To address the challenge of limited datasets using Generative Adversarial Networks (GANs).
To evaluate the efficacy of different machine learning models and feature selection algorithms for tool wear prediction.

Main Methods:

Implementation of the Walsh-Hadamard transform for signal processing.
Utilizing a Deep Convolutional Generative Adversarial Network (DCGAN) to augment limited datasets.
Employing Support Vector Regression (SVR), Gradient Boosting Regression (GBR), and Recurrent Neural Networks (RNN) for wear prediction.
Applying metaheuristic algorithms (Dragonfly, Harris Hawk, Genetic Algorithms) for feature selection.

Main Results:

The Recurrent Neural Network (RNN) model, combined with features selected by the Dragonfly algorithm, achieved the lowest prediction errors: Mean Squared Error (MSE) of 0.03, Root Mean Squared Error (RMSE) of 0.17, and Mean Absolute Error (MAE) of 0.14.
Comparison of prediction errors across different machine learning models and feature selection techniques was performed.
The proposed system demonstrated effective tool wear pattern identification.

Conclusions:

The developed TCM system, integrating Walsh-Hadamard transform, DCGAN, Dragonfly feature selection, and RNN, offers a robust solution for tool wear prediction.
Accurate tool wear prediction enables predictive maintenance, reducing repair costs and production downtime.
This methodology can significantly contribute to lowering overall manufacturing costs and enhancing operational efficiency.