Narendiranath Babu Thamba
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Narendiranath Babu Thamba has a total of 85 co-authors. Here are the top co-authors by number of shared publications:
D. Rama Prabha
School of Electrical Engineering, Vellore Institute of Technology (VIT), Vellore, India
5 shared publicationsM. Pandiyan
School of Mechanical Engineering, Vellore Institute of Technology, Vellore, India
3 shared publicationsRama Prabha Duraiswamy
School of Electrical Engineering, Vellore Institute of Technology, Vellore, India
3 shared publicationsA. Anwarsha
School of Mechanical Engineering, Vellore Institute of Technology, Vellore, 632 014, Tamil Nadu, India
2 shared publications- A. Anwarsha
Vellore Institute of Technology
2 shared publications Aditya Shinde
School of Mechanical Engineering Vellore Institute of Technology
2 shared publications
Latest Publications
- Open Access
- 25 October 2026
- Published by Springer Nature in Scientific Reports
Attention specialized multi-view vision transformer for physics interpretable rolling element bearing fault diagnosis
- 25 October 2026
- Published by Springer Nature in Scientific Reports
Open AccessAttention specialized multi-view vision transformer for physics interpretable rolling element bearing fault diagnosis
- 18 October 2026
- Published by Taylor & Francis in Composite Interfaces
- p. 1-27
Influence of chemical and interfacial surface engineering of spider silk – a review
1. Spider silk basically consists of a sequence of amino acids, mainly glycine and alanine, which are the main components of the proteins called spidroin [1], which, after self-folding, produce com...
- 18 October 2026
- Published by Taylor & Francis in Composite Interfaces
- p. 1-27
Influence of chemical and interfacial surface engineering of spider silk – a review
1. Spider silk basically consists of a sequence of amino acids, mainly glycine and alanine, which are the main components of the proteins called spidroin [1], which, after self-folding, produce com...
- Open Access
- 4 August 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16  (1)
Hybrid reinforcement learning and attention mechanism framework for intelligent fault diagnosis of rolling element bearings
- 4 August 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16  (1)
Open AccessHybrid reinforcement learning and attention mechanism framework for intelligent fault diagnosis of rolling element bearings
- Open Access
- 3 August 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16  (1)
Dual-stream 1D mobile-net with channel attention fusion for rolling element fault diagnosis
- 3 August 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16  (1)
Open AccessDual-stream 1D mobile-net with channel attention fusion for rolling element fault diagnosis
- Open Access
- 21 June 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16  (1)
Data-driven fault diagnosis framework of taper roller bearings using statistically ranked feature sets and machine learning algorithms
Fault diagnosis of taper roller bearings needs to be accurate and efficient to ensure industrial machinery reliability. This research has developed a vibration-based fault diagnosis method which combines statistical feature ranking and machine learning classification. Vibration signals for the five different health conditions (healthy, inner race fault, outer race fault, roller fault, and cage fault) were collected from an SKF 32,206 taper roller bearing with changing speeds and loads. Two types of features, time-domain and frequency-domain, were derived and the features with the highest discriminating power were determined by one-way ANOVA and Kruskal Wallis statistical tests. Different combinations of features were tested with six classifiers: support vector machines (SVM), neural networks, discriminant analysis, naive bayes, decision trees, and nearest neighbor. It was found that Kruskal-Wallis feature-ranking benefits not only the result accuracy but also the computational efficiency, and the best feature set had 18 features. Thus, the linear SVM classifier yielded a classification accuracy of 99% and an AUC of 1, while requiring the least training time, demonstrating that it is suitable for real-time purposes. This work proposes a novel, dependable, and computationally efficient method of identifying faults in taper roller bearings, thus leading to greater automation of condition monitoring in industrial plants.
- 21 June 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16  (1)
Open AccessData-driven fault diagnosis framework of taper roller bearings using statistically ranked feature sets and machine learning algorithms
Fault diagnosis of taper roller bearings needs to be accurate and efficient to ensure industrial machinery reliability. This research has developed a vibration-based fault diagnosis method which combines statistical feature ranking and machine learning classification. Vibration signals for the five different health conditions (healthy, inner race fault, outer race fault, roller fault, and cage fault) were collected from an SKF 32,206 taper roller bearing with changing speeds and loads. Two types of features, time-domain and frequency-domain, were derived and the features with the highest discriminating power were determined by one-way ANOVA and Kruskal Wallis statistical tests. Different combinations of features were tested with six classifiers: support vector machines (SVM), neural networks, discriminant analysis, naive bayes, decision trees, and nearest neighbor. It was found that Kruskal-Wallis feature-ranking benefits not only the result accuracy but also the computational efficiency, and the best feature set had 18 features. Thus, the linear SVM classifier yielded a classification accuracy of 99% and an AUC of 1, while requiring the least training time, demonstrating that it is suitable for real-time purposes. This work proposes a novel, dependable, and computationally efficient method of identifying faults in taper roller bearings, thus leading to greater automation of condition monitoring in industrial plants.
- Open Access
- 1 June 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16  (1)
ConvECA-Net: A lightweight convolutional neural network for fault diagnosis of tapered roller bearings
The paper focuses on detecting faults in tapered roller bearings to prevent unplanned shutdowns, accidents, and financial losses. Tapered roller bearings are an indispensable component used in mechanical applications, where handling of combined loads is required in rotating machinery. This study proposes a novel framework ConvECA-Net for advanced fault diagnosis of tapered roller bearings. This innovative architecture combines Efficient Channel Attention (ECA), adaptive kernel size strategy, and Leaky ReLU activation. This fault classification network is designed to classify five fault conditions in the tapered roller bearings. This proposed architecture is compared with deep learning algorithms such as ANN and ResNet50 and traditional machine learning algorithms such as SVM and RF. The proposed ConvECA-Net achieves a better classification accuracy of 95.07% and requires only 563 K trainable parameters and a model size of 2.2 MB. A systematic component-wise ablation study is conducted to validate that each component of this architectural design, namely ECA attention, adaptive kernel sizing, and Leaky-ReLU activation, individually and collectively contribute to the overall performance of this diagnostic model, as it achieves superior performance compared to its baseline variant by 5.45%. Cross-condition robustness is further established by evaluating this diagnostic model on three different rotational speeds and various load levels. Evaluation of noise robustness on this diagnostic model for various levels of Gaussian white noise and pink noise, further establishes its robustness of the proposed model. Further, Statistical validation of this diagnostic model is conducted by running this experiment ten times, using paired t-tests, Shapiro-Wilk normality tests, and stratified 5-fold cross-validation (94.82% ± 0.38%). Finally, analysis of computational efficiency of this diagnostic model reveals that it achieves 192 MFLOPs and an inference latency of 0.82 ms/sample, making it suitable for industrial condition monitoring systems of rotating machinery to prevent the plant shutdown.
- 1 June 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16  (1)
Open AccessConvECA-Net: A lightweight convolutional neural network for fault diagnosis of tapered roller bearings
The paper focuses on detecting faults in tapered roller bearings to prevent unplanned shutdowns, accidents, and financial losses. Tapered roller bearings are an indispensable component used in mechanical applications, where handling of combined loads is required in rotating machinery. This study proposes a novel framework ConvECA-Net for advanced fault diagnosis of tapered roller bearings. This innovative architecture combines Efficient Channel Attention (ECA), adaptive kernel size strategy, and Leaky ReLU activation. This fault classification network is designed to classify five fault conditions in the tapered roller bearings. This proposed architecture is compared with deep learning algorithms such as ANN and ResNet50 and traditional machine learning algorithms such as SVM and RF. The proposed ConvECA-Net achieves a better classification accuracy of 95.07% and requires only 563 K trainable parameters and a model size of 2.2 MB. A systematic component-wise ablation study is conducted to validate that each component of this architectural design, namely ECA attention, adaptive kernel sizing, and Leaky-ReLU activation, individually and collectively contribute to the overall performance of this diagnostic model, as it achieves superior performance compared to its baseline variant by 5.45%. Cross-condition robustness is further established by evaluating this diagnostic model on three different rotational speeds and various load levels. Evaluation of noise robustness on this diagnostic model for various levels of Gaussian white noise and pink noise, further establishes its robustness of the proposed model. Further, Statistical validation of this diagnostic model is conducted by running this experiment ten times, using paired t-tests, Shapiro-Wilk normality tests, and stratified 5-fold cross-validation (94.82% ± 0.38%). Finally, analysis of computational efficiency of this diagnostic model reveals that it achieves 192 MFLOPs and an inference latency of 0.82 ms/sample, making it suitable for industrial condition monitoring systems of rotating machinery to prevent the plant shutdown.
- Open Access
- 30 April 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16  (1)
Rolling element bearing fault diagnosis based on modified Pufferfish optimization assisted efficient customized convolutional neural network with IMI-EMD
Deep learning (DL) models have become a powerful alternative that learns the relevant features automatically from raw vibration signals without extensive manual intervention. This research addresses the existing gap in fault diagnosis by introducing a novel methodology through an efficient customized convolutional neural network (CCNN) with the modified Pufferfish optimization algorithm (MPOA) model. The proposed method includes two main phases. The initial phase involves preprocessing the input vibration signal using an improved mutual information based empirical mode decomposition technique, which effectively decomposes the signal. In the second phase, fault diagnosis is carried out using the proposed CCNN model. To improve the performance of the model, the weights of the CCNN are optimized through the MPOA. The efficient CCNN model for fault diagnosis is compared with the conventional models through a thorough evaluation using metrics like precision, accuracy, sensitivity, specificity, false positive rate, and false negative rate. The CCNN-MPOA model, exhibited effective performance in fault diagnosis applications. By using a 70/30 training–testing data split, the model achieved an accuracy rate of 96.1% with a moderate computational cost of 12.22 GFLOPS along with a relatively short training time of 64.179 s. The proposed model was less prone to errors since it had a low FNR of 0.039 and an FDR of 0.037, the latter being a feature that reflected its performance in not confusing the present faults with the normal states. The computational efficiency and diagnostic accuracy of the proposed model suggest its potential suitability for future industrial deployment.
- 30 April 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16  (1)
Open AccessRolling element bearing fault diagnosis based on modified Pufferfish optimization assisted efficient customized convolutional neural network with IMI-EMD
Deep learning (DL) models have become a powerful alternative that learns the relevant features automatically from raw vibration signals without extensive manual intervention. This research addresses the existing gap in fault diagnosis by introducing a novel methodology through an efficient customized convolutional neural network (CCNN) with the modified Pufferfish optimization algorithm (MPOA) model. The proposed method includes two main phases. The initial phase involves preprocessing the input vibration signal using an improved mutual information based empirical mode decomposition technique, which effectively decomposes the signal. In the second phase, fault diagnosis is carried out using the proposed CCNN model. To improve the performance of the model, the weights of the CCNN are optimized through the MPOA. The efficient CCNN model for fault diagnosis is compared with the conventional models through a thorough evaluation using metrics like precision, accuracy, sensitivity, specificity, false positive rate, and false negative rate. The CCNN-MPOA model, exhibited effective performance in fault diagnosis applications. By using a 70/30 training–testing data split, the model achieved an accuracy rate of 96.1% with a moderate computational cost of 12.22 GFLOPS along with a relatively short training time of 64.179 s. The proposed model was less prone to errors since it had a low FNR of 0.039 and an FDR of 0.037, the latter being a feature that reflected its performance in not confusing the present faults with the normal states. The computational efficiency and diagnostic accuracy of the proposed model suggest its potential suitability for future industrial deployment.
- Open Access
- 11 April 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16  (1)
Comparative analysis of deep learning algorithms for rolling element bearing fault classification under variable loads and speeds
This paper presents a comparative study of deep learning methods used to classify roller bearing faults. We obtained experimental vibration data by conducting controlled tests on roller bearings with various faults under different load conditions to simulate real-world industrial conditions. The methodology first evaluates four different time-frequency techniques-STFT, CWT, WPT and CQ-NSGT, establishing CQ-NSGT as the superior method for feature visualization. A novel hybrid transfer learning architecture that integrates pre-trained backbones (EfficientNetB0, MobileNetV2, InceptionV3) with custom residual blocks is proposed. These CNNs are compared to a baseline CNN and a Vision Transformer (ViT). Their performance was rigorously evaluated using fivefold cross-validation and tested against additive white Gaussian noise at Signal-to-Noise Ratios (SNR) of 1 dB, 3 dB, and 5 dB. The EfficientNetB0 hybrid model was able to reach the highest baseline accuracy of 99.83% while also exhibiting excellent robustness-maintaining 98.8% accuracy even at 1 dB SNR. MobileNetV2 is the most computationally efficient model with a training time of only 121.4 s and 0.50 GFLOPS making it perfect for edge deployment. ViT has potential but is less noise stable and lacks the inductive bias of CNNs which is important for this particular application. These results can be used as a guide for trading off accuracy of diagnosis and computational cost in industrial predictive maintenance.
- 11 April 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16  (1)
Open AccessComparative analysis of deep learning algorithms for rolling element bearing fault classification under variable loads and speeds
This paper presents a comparative study of deep learning methods used to classify roller bearing faults. We obtained experimental vibration data by conducting controlled tests on roller bearings with various faults under different load conditions to simulate real-world industrial conditions. The methodology first evaluates four different time-frequency techniques-STFT, CWT, WPT and CQ-NSGT, establishing CQ-NSGT as the superior method for feature visualization. A novel hybrid transfer learning architecture that integrates pre-trained backbones (EfficientNetB0, MobileNetV2, InceptionV3) with custom residual blocks is proposed. These CNNs are compared to a baseline CNN and a Vision Transformer (ViT). Their performance was rigorously evaluated using fivefold cross-validation and tested against additive white Gaussian noise at Signal-to-Noise Ratios (SNR) of 1 dB, 3 dB, and 5 dB. The EfficientNetB0 hybrid model was able to reach the highest baseline accuracy of 99.83% while also exhibiting excellent robustness-maintaining 98.8% accuracy even at 1 dB SNR. MobileNetV2 is the most computationally efficient model with a training time of only 121.4 s and 0.50 GFLOPS making it perfect for edge deployment. ViT has potential but is less noise stable and lacks the inductive bias of CNNs which is important for this particular application. These results can be used as a guide for trading off accuracy of diagnosis and computational cost in industrial predictive maintenance.
- 1 March 2026
- Published by IOP Publishing in Engineering Research Express
- Vol. 8  (5) , 055507
Precision fault diagnosis on taper roller bearing using residual attention enhanced convolutional networks
The paper focuses on detecting faults in tapered roller bearings to prevent unplanned shutdowns, accidents, and financial losses. Utilisation of deep learning and machine learning models for monitoring can reduce these shutdowns. Tapered roller bearings are an indispensable component used in mechanical applications, where handling of combined loads is required in rotating machinery. Majority of deep learning and machine learning models rely on extraction of time domain features for fault detection. Different deep learning (ANN and CNN ResNet-101) and machine learning (XGBoost, Catboost and LightGBM) models are trained and compared against our model compared with our custom model Res-CBAM-CNN to detect faults in the tapered roller bearing. Models are evaluated on parameters like confusion matrix, AUC score and metric evaluation in order to identify and select optimal algorithm for fault detection. It was found out that deep learning models provided a high accuracy at the cost of high computational resources, but machine learning algorithms provided satisfactory accuracy with limited computational resources. A general trade-off was set between accuracy and computational complexity in order to identify the most relevant algorithm, catering to real world scenarios. The most suitable model for real-world tapered roller bearing fault detection proved to be Res-CBAM-CNN because it delivered peak accuracy together with efficient computation along with superior classification results.
- 1 March 2026
- Published by IOP Publishing in Engineering Research Express
- Vol. 8  (5) , 055507
Precision fault diagnosis on taper roller bearing using residual attention enhanced convolutional networks
The paper focuses on detecting faults in tapered roller bearings to prevent unplanned shutdowns, accidents, and financial losses. Utilisation of deep learning and machine learning models for monitoring can reduce these shutdowns. Tapered roller bearings are an indispensable component used in mechanical applications, where handling of combined loads is required in rotating machinery. Majority of deep learning and machine learning models rely on extraction of time domain features for fault detection. Different deep learning (ANN and CNN ResNet-101) and machine learning (XGBoost, Catboost and LightGBM) models are trained and compared against our model compared with our custom model Res-CBAM-CNN to detect faults in the tapered roller bearing. Models are evaluated on parameters like confusion matrix, AUC score and metric evaluation in order to identify and select optimal algorithm for fault detection. It was found out that deep learning models provided a high accuracy at the cost of high computational resources, but machine learning algorithms provided satisfactory accuracy with limited computational resources. A general trade-off was set between accuracy and computational complexity in order to identify the most relevant algorithm, catering to real world scenarios. The most suitable model for real-world tapered roller bearing fault detection proved to be Res-CBAM-CNN because it delivered peak accuracy together with efficient computation along with superior classification results.
- Open Access
- 6 February 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16  (1)
Self-aligning ball bearing fault classification using selective kernel modules in resnext architecture
Self-aligning ball bearings are widely used in many applications including industrial manufacturing systems. Therefore, it is important to assess the faults that may occur in a self- aligning bearing. Deep learning techniques can be applied to various types of machinery for predictive maintenance. We can train various deep learning models to analyze the patterns of vibrations obtained from the machinery during their operations and use the trained model to predict the fault when any kind of fault occurs in the machinery. This study aims at finding a novel method for bearing fault analysis and classification using several convolutional neural network algorithms to find out the algorithm that gives the highest classification accuracy. The vibration data has been denoised using Daubechies wavelet denoising and then converted to vibration plot in time domain for all the faults. The denoised vibration has been rescaled to a common range using Min-Max normalization. The normalized vibration plots have been segmented in time intervals and split into training and testing image datasets. These datasets have been put in different advanced CNN models to analyze the performance of the model in the classification of the bearing faults. A comparative study has been done amongst five different convolutional neural networks. These networks are ResNet50, ResNeSt50, ResNext50_32x4d, DenseNet121, and SKResNext50_32x4d, the last one being the proposed model. The accuracy of the bearing fault classification using ResNext is 97.51% which has been improved further when selective kernel modules have been integrated into it. The highest accuracy attained by the ResNext architecture integrated with Selective Kernel attention modules, called SkResNext, has come out to be 98.51%.
- 6 February 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16  (1)
Open AccessSelf-aligning ball bearing fault classification using selective kernel modules in resnext architecture
Self-aligning ball bearings are widely used in many applications including industrial manufacturing systems. Therefore, it is important to assess the faults that may occur in a self- aligning bearing. Deep learning techniques can be applied to various types of machinery for predictive maintenance. We can train various deep learning models to analyze the patterns of vibrations obtained from the machinery during their operations and use the trained model to predict the fault when any kind of fault occurs in the machinery. This study aims at finding a novel method for bearing fault analysis and classification using several convolutional neural network algorithms to find out the algorithm that gives the highest classification accuracy. The vibration data has been denoised using Daubechies wavelet denoising and then converted to vibration plot in time domain for all the faults. The denoised vibration has been rescaled to a common range using Min-Max normalization. The normalized vibration plots have been segmented in time intervals and split into training and testing image datasets. These datasets have been put in different advanced CNN models to analyze the performance of the model in the classification of the bearing faults. A comparative study has been done amongst five different convolutional neural networks. These networks are ResNet50, ResNeSt50, ResNext50_32x4d, DenseNet121, and SKResNext50_32x4d, the last one being the proposed model. The accuracy of the bearing fault classification using ResNext is 97.51% which has been improved further when selective kernel modules have been integrated into it. The highest accuracy attained by the ResNext architecture integrated with Selective Kernel attention modules, called SkResNext, has come out to be 98.51%.