Vipul Dave
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Vipul Dave has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Himanshu Borade
Mechanical Engineering Department, Medi-Caps University, Indore 453331, India
2 shared publications - Hitesh Agrawal
Mechanical Engineering Department, Medi-Caps University, Indore 453331, India
2 shared publications - Vinay Vakharia
Pandit Deendayal Energy University
2 shared publications - Anshuman Purohit
Mechanical Engineering Department, Medi-Caps University, Indore 453331, MP, India
1 shared publication - Bharat Tank
Parul Institute of Engineering and Technology
1 shared publication - Khyati Zalawadia
Parul University
1 shared publication
Latest Publications
- Open Access
- 22 July 2026
- Published by Atlantis Press SARL
- p. 227-234
IoT-Enabled Monitoring and Control Framework for Rotary Friction Welding Processes: Smart Manufacturing Integration
- 22 July 2026
- Published by Atlantis Press SARL
- p. 227-234
Open AccessIoT-Enabled Monitoring and Control Framework for Rotary Friction Welding Processes: Smart Manufacturing Integration
- Open Access
- 31 March 2026
- Published by University Library in Kragujevac in Advanced Engineering Letters
- Vol. 5 (1)
A Machine Learning Approach for Bearing Fault Identification Using IFWHT, GLCM, and Feature Ranking
Time–frequency analysis is necessary for condition monitoring of rotating machinery; comparatively limited attention has been given to image- based texture feature analysis derived from time–frequency representations. A bearing fault diagnosis model is proposed that combines the Inverse Fast Walsh-Hadamard Transform (IFWHT), texture feature extraction, feature ranking, and machine learning classification. First, IFWHT transforms vibration signals into time-frequency images, thereby improving the effective representation of transient and fault- related data. Based on these images, two-dimensional texture attributes are derived from the Gray Level Co-occurrence Matrix (GLCM), which records the spatial relationships and structural patterns of various bearing health conditions. The ReliefF algorithm ranks and selects the most discriminative features, reducing feature redundancy and improving classification performance. Machine learning classifiers are then trained and evaluated using the ranked feature set. The findings show that the suggested ranked feature-based framework provides consistent and good-quality fault classification performance. Fine KNN and Cubic SVM are among the compared models, where the former will reach a maximum classification accuracy of 93.8%, and the latter will reach an accuracy of 91.7% at various combinations of faults. The methodology suggested offers a strong and adaptable approach in the context of fault diagnosis, which effectively promotes predictive maintenance by lessening unforeseen downtimes and increasing the dependability of operations in industries.
- 31 March 2026
- Published by University Library in Kragujevac in Advanced Engineering Letters
- Vol. 5 (1)
Open AccessA Machine Learning Approach for Bearing Fault Identification Using IFWHT, GLCM, and Feature Ranking
Time–frequency analysis is necessary for condition monitoring of rotating machinery; comparatively limited attention has been given to image- based texture feature analysis derived from time–frequency representations. A bearing fault diagnosis model is proposed that combines the Inverse Fast Walsh-Hadamard Transform (IFWHT), texture feature extraction, feature ranking, and machine learning classification. First, IFWHT transforms vibration signals into time-frequency images, thereby improving the effective representation of transient and fault- related data. Based on these images, two-dimensional texture attributes are derived from the Gray Level Co-occurrence Matrix (GLCM), which records the spatial relationships and structural patterns of various bearing health conditions. The ReliefF algorithm ranks and selects the most discriminative features, reducing feature redundancy and improving classification performance. Machine learning classifiers are then trained and evaluated using the ranked feature set. The findings show that the suggested ranked feature-based framework provides consistent and good-quality fault classification performance. Fine KNN and Cubic SVM are among the compared models, where the former will reach a maximum classification accuracy of 93.8%, and the latter will reach an accuracy of 91.7% at various combinations of faults. The methodology suggested offers a strong and adaptable approach in the context of fault diagnosis, which effectively promotes predictive maintenance by lessening unforeseen downtimes and increasing the dependability of operations in industries.
- Open Access
- 2 September 2024
- Published by MDPI AG in Electronics
- Vol. 13 (17) , 3484
Utilizing TGAN and ConSinGAN for Improved Tool Wear Prediction: A Comparative Study with ED-LSTM, GRU, and CNN Models
Developing precise deep learning (DL) models for predicting tool wear is challenging, particularly due to the scarcity of experimental data. To address this issue, this paper introduces an innovative approach that leverages the capabilities of tabular generative adversarial networks (TGAN) and conditional single image GAN (ConSinGAN). These models are employed to generate synthetic data, thereby enriching the dataset and enhancing the robustness of the predictive models. The efficacy of this methodology was rigorously evaluated using publicly available milling datasets. The pre-processing of acoustic emission data involved the application of the Walsh-Hadamard transform, followed by the generation of spectrograms. These spectrograms were then used to extract statistical attributes, forming a comprehensive feature vector for model input. Three DL models—encoder-decoder long short-term memory (ED-LSTM), gated recurrent unit (GRU), and convolutional neural network (CNN)—were applied to assess their tool wear prediction capabilities. The application of 10-fold cross-validation across these models yielded exceptionally low RMSE and MAE values of 0.02 and 0.16, respectively, underscoring the effectiveness of this approach. The results not only highlight the potential of TGAN and ConSinGAN in mitigating data scarcity but also demonstrate significant improvements in the accuracy of tool wear predictions, paving the way for more reliable and precise predictive maintenance in manufacturing processes.
- 2 September 2024
- Published by MDPI AG in Electronics
- Vol. 13 (17) , 3484
Open AccessUtilizing TGAN and ConSinGAN for Improved Tool Wear Prediction: A Comparative Study with ED-LSTM, GRU, and CNN Models
Developing precise deep learning (DL) models for predicting tool wear is challenging, particularly due to the scarcity of experimental data. To address this issue, this paper introduces an innovative approach that leverages the capabilities of tabular generative adversarial networks (TGAN) and conditional single image GAN (ConSinGAN). These models are employed to generate synthetic data, thereby enriching the dataset and enhancing the robustness of the predictive models. The efficacy of this methodology was rigorously evaluated using publicly available milling datasets. The pre-processing of acoustic emission data involved the application of the Walsh-Hadamard transform, followed by the generation of spectrograms. These spectrograms were then used to extract statistical attributes, forming a comprehensive feature vector for model input. Three DL models—encoder-decoder long short-term memory (ED-LSTM), gated recurrent unit (GRU), and convolutional neural network (CNN)—were applied to assess their tool wear prediction capabilities. The application of 10-fold cross-validation across these models yielded exceptionally low RMSE and MAE values of 0.02 and 0.16, respectively, underscoring the effectiveness of this approach. The results not only highlight the potential of TGAN and ConSinGAN in mitigating data scarcity but also demonstrate significant improvements in the accuracy of tool wear predictions, paving the way for more reliable and precise predictive maintenance in manufacturing processes.
- Open Access
Deep Learning-Enhanced Small-Sample Bearing Fault Analysis Using Q-Transform and HOG Image Features in a GRU-XAI Framework
Timely prediction of bearing faults is essential for minimizing unexpected machine downtime and improving industrial equipment’s operational dependability. The Q transform was utilized for preprocessing the sixty-four vibration signals that correspond to the four bearing conditions. Additionally, statistical features, also known as attributes, are extracted from the Histogram of Oriented Gradients (HOG). To assess these features, the Explainable AI (XAI) technique employed the SHAP (Shapely Additive Explanations) method. The effectiveness of the GRU, LSTM, and SVM models in the first stage was evaluated using training and tenfold cross-validation. The SSA optimization algorithm (SSA) was employed in a subsequent phase to optimize the hyperparameters of the algorithms. The findings of the research are rigorously analyzed and assessed in four specific areas: the default configuration of the model, the inclusion of selected features using XAI, the optimization of hyperparameters, and a hybrid technique that combines SSA and XAI-based feature selection. The GRU model has superior performance compared to the other models, achieving an impressive accuracy of 98.2%. This is particularly evident when using SSA and XAI-informed features. The subsequent model is the LSTM, which has an impressive accuracy rate of 96.4%. During tenfold cross-validation, the Support Vector Machine (SVM) achieves a noticeably reduced maximum accuracy of 84.82%, even though the hybrid optimization technique shows improvement. The results of this study usually show that the most effective model for fault prediction is the GRU model, configured with the attributes chosen by XAI, followed by LSTM and SVM.
Open AccessDeep Learning-Enhanced Small-Sample Bearing Fault Analysis Using Q-Transform and HOG Image Features in a GRU-XAI Framework
Timely prediction of bearing faults is essential for minimizing unexpected machine downtime and improving industrial equipment’s operational dependability. The Q transform was utilized for preprocessing the sixty-four vibration signals that correspond to the four bearing conditions. Additionally, statistical features, also known as attributes, are extracted from the Histogram of Oriented Gradients (HOG). To assess these features, the Explainable AI (XAI) technique employed the SHAP (Shapely Additive Explanations) method. The effectiveness of the GRU, LSTM, and SVM models in the first stage was evaluated using training and tenfold cross-validation. The SSA optimization algorithm (SSA) was employed in a subsequent phase to optimize the hyperparameters of the algorithms. The findings of the research are rigorously analyzed and assessed in four specific areas: the default configuration of the model, the inclusion of selected features using XAI, the optimization of hyperparameters, and a hybrid technique that combines SSA and XAI-based feature selection. The GRU model has superior performance compared to the other models, achieving an impressive accuracy of 98.2%. This is particularly evident when using SSA and XAI-informed features. The subsequent model is the LSTM, which has an impressive accuracy rate of 96.4%. During tenfold cross-validation, the Support Vector Machine (SVM) achieves a noticeably reduced maximum accuracy of 84.82%, even though the hybrid optimization technique shows improvement. The results of this study usually show that the most effective model for fault prediction is the GRU model, configured with the attributes chosen by XAI, followed by LSTM and SVM.