Anshuman Purohit
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Anshuman Purohit has a total of 8 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 - Vinay Vakharia
Pandit Deendayal Energy University
2 shared publications - Hitesh Agrawal
Mechanical Engineering Department, Medi-Caps University, Indore 453331, India
1 shared publication - Milind Shah
Department of Product Development, Production and Design, School of Engineering, Jönköping University, 55318 Jönköping, Sweden
1 shared publication - Nandan Padia
Department of Computer Science Engineering, School of Technology, Pandit Deendayal Energy University, Raisan, Gandhinagar 382007, GJ, India
1 shared publication - Vedant Sanghavi
Department of Mechanical and Aerospace Engineering, New York University, Brooklyn, New York, NY 11201, USA
1 shared publication
Latest Publications
- 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.
- Open Access
Enhancing Tool Wear Prediction Accuracy Using Walsh–Hadamard Transform, DCGAN and Dragonfly Algorithm-Based Feature Selection
Tool wear is an important concern in the manufacturing sector that leads to quality loss, lower productivity, and increased downtime. In recent years, there has been a rise in the popularity of implementing TCM systems using various signal processing methods and machine learning algorithms. In the present paper, the authors propose a TCM system that incorporates the Walsh–Hadamard transform for signal processing, DCGAN aims to circumvent the issue of the availability of limited experimental dataset, and the exploration of three machine learning models: support vector regression, gradient boosting regression, and recurrent neural network for tool wear prediction. The mean absolute error, mean square error and root mean square error are used to assess the prediction errors from three machine learning models. To identify these relevant features, three metaheuristic optimization feature selection algorithms, Dragonfly, Harris hawk, and Genetic algorithms, were explored, and prediction results were compared. The results show that the feature selected through Dragonfly algorithms exhibited the least MSE (0.03), RMSE (0.17), and MAE (0.14) with a recurrent neural network model. By identifying the tool wear patterns and predicting when maintenance is required, the proposed methodology could help manufacturing companies save money on repairs and replacements, as well as reduce overall production costs by minimizing downtime.
Open AccessEnhancing Tool Wear Prediction Accuracy Using Walsh–Hadamard Transform, DCGAN and Dragonfly Algorithm-Based Feature Selection
Tool wear is an important concern in the manufacturing sector that leads to quality loss, lower productivity, and increased downtime. In recent years, there has been a rise in the popularity of implementing TCM systems using various signal processing methods and machine learning algorithms. In the present paper, the authors propose a TCM system that incorporates the Walsh–Hadamard transform for signal processing, DCGAN aims to circumvent the issue of the availability of limited experimental dataset, and the exploration of three machine learning models: support vector regression, gradient boosting regression, and recurrent neural network for tool wear prediction. The mean absolute error, mean square error and root mean square error are used to assess the prediction errors from three machine learning models. To identify these relevant features, three metaheuristic optimization feature selection algorithms, Dragonfly, Harris hawk, and Genetic algorithms, were explored, and prediction results were compared. The results show that the feature selected through Dragonfly algorithms exhibited the least MSE (0.03), RMSE (0.17), and MAE (0.14) with a recurrent neural network model. By identifying the tool wear patterns and predicting when maintenance is required, the proposed methodology could help manufacturing companies save money on repairs and replacements, as well as reduce overall production costs by minimizing downtime.