Arvind Keprate
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Arvind Keprate has a total of 61 co-authors. Here are the top co-authors by number of shared publications:
R.M. Chandima Ratnayake
4 shared publications- Rohit Kumar
Indian Institute of Technology Mandi
4 shared publications - Subhamoy Sen
Indian Institute of Technology Mandi
4 shared publications - Haris Hameed Mian
Center of Excellence in Sciences and Applied Technologies (CESAT), Islamabad, Pakistan
3 shared publications Muhammad Salman Siddiqui
3 shared publications- Fadi Al Machot
Norwegian University of Life Sciences
2 shared publications
Latest Publications
- 21 October 2026
- Published by Elsevier in Ocean Engineering
- Vol. 369
Learning wake perturbations of floating wind turbines using motion-conditioned neural network
- 21 October 2026
- Published by Elsevier in Ocean Engineering
- Vol. 369
Learning wake perturbations of floating wind turbines using motion-conditioned neural network
- 9 October 2026
- Published by Wiley in Environmental Progress & Sustainable Energy
Technological advancements in biohydrogen production and downstream processing for green energy transition: A review
A rapid transition toward sustainable and clean energy is necessary for a secure energy future in today's dynamic world. Biohydrogen produced from waste biomass is gaining momentum; however, raw biohydrogen comprises tracer impurities, and its commercial use further requires extensive downstream technologies. Conventional purification strategies offer great selectivity with the promise of modular and low‐energy operation and can provide purities up to 99.99% with recoveries of 80%–90%, whereas storage of ~71 kg/m 3 at −253°C biohydrogen consumes ~30% of its heating value. However, advanced solid‐state carriers can achieve greater than 7–9 wt % at −196.15°C, though room temperature performance remains limited and its techno‐economic and life cycle analyses are crucial for its scalability and sustainability. Despite challenges of energy intensity, material degradation, and artificial intelligence‐driven process optimization have shown optimistic future promises. This review comprehensively analyzes advancements in biohydrogen downstream technologies, evaluating their potential to facilitate a clean energy transition.
- 9 October 2026
- Published by Wiley in Environmental Progress & Sustainable Energy
Technological advancements in biohydrogen production and downstream processing for green energy transition: A review
A rapid transition toward sustainable and clean energy is necessary for a secure energy future in today's dynamic world. Biohydrogen produced from waste biomass is gaining momentum; however, raw biohydrogen comprises tracer impurities, and its commercial use further requires extensive downstream technologies. Conventional purification strategies offer great selectivity with the promise of modular and low‐energy operation and can provide purities up to 99.99% with recoveries of 80%–90%, whereas storage of ~71 kg/m 3 at −253°C biohydrogen consumes ~30% of its heating value. However, advanced solid‐state carriers can achieve greater than 7–9 wt % at −196.15°C, though room temperature performance remains limited and its techno‐economic and life cycle analyses are crucial for its scalability and sustainability. Despite challenges of energy intensity, material degradation, and artificial intelligence‐driven process optimization have shown optimistic future promises. This review comprehensively analyzes advancements in biohydrogen downstream technologies, evaluating their potential to facilitate a clean energy transition.
- 2 July 2026
- Published by Springer Nature
- p. 111-119
Education 4.0 For Cyber-Physical Systems: A Case of Wind Turbines
- 2 July 2026
- Published by Springer Nature
- p. 111-119
Education 4.0 For Cyber-Physical Systems: A Case of Wind Turbines
- Open Access
- 15 June 2026
- Published by Elsevier in SSRN Electronic Journal
A motion-conditioned physics-integrated recurrent framework for moving-boundary flow prediction
Accurate and stable prediction of unsteady flows around moving boundaries remains challenging for data-driven models because of strong temporal dependencies, parametric forcing, and error accumulation during long-horizon integration. Existing approaches often treat moving-boundary flow prediction as snapshot-to-snapshot mapping or time-dependent regression, without explicitly introducing a dynamical state driven by prescribed body motion. This work proposes a motion-driven latent dynamical system formulation in which prescribed motion acts as a time-dependent external forcing of the latent flow evolution. The proposed Motion-Conditioned Physics-integrated Recurrent Neural Network (MoC-PiRNN) uses an encoder–decoder architecture to construct a spatial latent state, while a recurrent transition mapping advances this state under motion conditioning. A latent mixing block is included to support global information exchange beyond local convolutional recurrence, and physics-integrated regularization is used to improve physical consistency without deriving an explicit reduced-order model. From an artificial intelligence perspective, the contribution is a motion-conditioned recurrent learning framework that embeds exogenous forcing directly into latent-state evolution. From an engineering perspective, the method provides a surrogate model for stable long-horizon prediction of unsteady moving-boundary flows. The framework is evaluated on a two-dimensional heaving square cylinder simulated using overset-grid computational fluid dynamics. Numerical results show improved long-horizon stability across sampled motion amplitudes and frequencies. For the present case, the physics-integrated formulation reduces flow-field prediction error by more than 20% and lift-coefficient root-mean-square error by more than 40% relative to the motion-only model, demonstrating reduced error accumulation during autoregressive rollouts.
- 15 June 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessA motion-conditioned physics-integrated recurrent framework for moving-boundary flow prediction
Accurate and stable prediction of unsteady flows around moving boundaries remains challenging for data-driven models because of strong temporal dependencies, parametric forcing, and error accumulation during long-horizon integration. Existing approaches often treat moving-boundary flow prediction as snapshot-to-snapshot mapping or time-dependent regression, without explicitly introducing a dynamical state driven by prescribed body motion. This work proposes a motion-driven latent dynamical system formulation in which prescribed motion acts as a time-dependent external forcing of the latent flow evolution. The proposed Motion-Conditioned Physics-integrated Recurrent Neural Network (MoC-PiRNN) uses an encoder–decoder architecture to construct a spatial latent state, while a recurrent transition mapping advances this state under motion conditioning. A latent mixing block is included to support global information exchange beyond local convolutional recurrence, and physics-integrated regularization is used to improve physical consistency without deriving an explicit reduced-order model. From an artificial intelligence perspective, the contribution is a motion-conditioned recurrent learning framework that embeds exogenous forcing directly into latent-state evolution. From an engineering perspective, the method provides a surrogate model for stable long-horizon prediction of unsteady moving-boundary flows. The framework is evaluated on a two-dimensional heaving square cylinder simulated using overset-grid computational fluid dynamics. Numerical results show improved long-horizon stability across sampled motion amplitudes and frequencies. For the present case, the physics-integrated formulation reduces flow-field prediction error by more than 20% and lift-coefficient root-mean-square error by more than 40% relative to the motion-only model, demonstrating reduced error accumulation during autoregressive rollouts.
- 1 April 2026
- Published by Springer Nature
- p. 679-692
Integrating Machine Learning and Simulink for Predictive Maintenance in Sewage Treatment Plant Pump
- 1 April 2026
- Published by Springer Nature
- p. 679-692
Integrating Machine Learning and Simulink for Predictive Maintenance in Sewage Treatment Plant Pump
- Open Access
- 18 March 2026
- Published by Elsevier in SSRN Electronic Journal
MoC-PiRNN: A motion-conditioned physics-integrated recurrent framework for moving-boundary flow prediction
Accurate and stable prediction of unsteady flows around moving boundaries remains challenging for data-driven models due to strong temporal dependencies, parametric forcing, and error accumulation during long-horizon integration. Existing approaches typically treat moving-boundary flow prediction as either a sequence of snapshot-to-snapshot mappings or as a time-dependent regression problem. While these methods have shown success for short-term prediction, they typically do not introduce an explicit dynamical state whose evolution is directly driven by prescribed body motion. In this work, we propose a motion-driven latent dynamical system formulation for moving-boundary flows, in which prescribed body motion serves as a time-dependent external forcing that drives the evolution of the latent flow state. The proposed Motion-Conditioned Physics-integrated Recurrent Neural Network (MoC-PiRNN) introduces a spatial latent state via an encoder-decoder architecture, with temporal evolution represented by a learned recurrent-state transition mapping. Prescribed body motion is incorporated as a time-dependent exogenous forcing signal that explicitly drives the latent-state evolution at each recurrent step. In addition, a latent mixing block is introduced to enable global information exchange beyond purely convolutional recurrent dynamics. Physics-integrated regularization is incorporated to produce physically consistent predictions without requiring an explicit derivation of the reduced-order model. The method is evaluated on a canonical moving-boundary problem involving a two-dimensional heaving square cylinder simulated using overset-grid CFD. Numerical experiments demonstrate improved long-horizon stability of the predicted flow evolution, while maintaining competitive performance across a sampled range of motion amplitudes and frequencies.In particular, for the present case, the physics-integrated formulation reduces the flow-field prediction error by more than 20% and improves the accuracy of lift coefficient predictions by more than 40%. The results indicate that the proposed formulation is effective in mitigating error accumulation during temporal rollouts and highlight the remaining challenges in generalizing to unseen motion conditions.
- 18 March 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessMoC-PiRNN: A motion-conditioned physics-integrated recurrent framework for moving-boundary flow prediction
Accurate and stable prediction of unsteady flows around moving boundaries remains challenging for data-driven models due to strong temporal dependencies, parametric forcing, and error accumulation during long-horizon integration. Existing approaches typically treat moving-boundary flow prediction as either a sequence of snapshot-to-snapshot mappings or as a time-dependent regression problem. While these methods have shown success for short-term prediction, they typically do not introduce an explicit dynamical state whose evolution is directly driven by prescribed body motion. In this work, we propose a motion-driven latent dynamical system formulation for moving-boundary flows, in which prescribed body motion serves as a time-dependent external forcing that drives the evolution of the latent flow state. The proposed Motion-Conditioned Physics-integrated Recurrent Neural Network (MoC-PiRNN) introduces a spatial latent state via an encoder-decoder architecture, with temporal evolution represented by a learned recurrent-state transition mapping. Prescribed body motion is incorporated as a time-dependent exogenous forcing signal that explicitly drives the latent-state evolution at each recurrent step. In addition, a latent mixing block is introduced to enable global information exchange beyond purely convolutional recurrent dynamics. Physics-integrated regularization is incorporated to produce physically consistent predictions without requiring an explicit derivation of the reduced-order model. The method is evaluated on a canonical moving-boundary problem involving a two-dimensional heaving square cylinder simulated using overset-grid CFD. Numerical experiments demonstrate improved long-horizon stability of the predicted flow evolution, while maintaining competitive performance across a sampled range of motion amplitudes and frequencies.In particular, for the present case, the physics-integrated formulation reduces the flow-field prediction error by more than 20% and improves the accuracy of lift coefficient predictions by more than 40%. The results indicate that the proposed formulation is effective in mitigating error accumulation during temporal rollouts and highlight the remaining challenges in generalizing to unseen motion conditions.
- 14 October 2025
- Published by Springer Nature
- p. 603-618
Development of Human Cognition Inspired Digital Twins for Optimized Performance of Process Equipment
- 14 October 2025
- Published by Springer Nature
- p. 603-618
Development of Human Cognition Inspired Digital Twins for Optimized Performance of Process Equipment
- 14 October 2025
- Published by Springer Nature
- p. 59-68
Temporal Feature Extraction Based Real Time Damage Detection of Floating Offshore Wind Turbine Mooring Lines
- 14 October 2025
- Published by Springer Nature
- p. 59-68
Temporal Feature Extraction Based Real Time Damage Detection of Floating Offshore Wind Turbine Mooring Lines
- 14 October 2025
- Published by Springer Nature
- p. 47-57
Fatigue Damage Assessment of FOWT Mooring Lines Using Sequence-to-Sequence Based Indirect Sensing
- 14 October 2025
- Published by Springer Nature
- p. 47-57
Fatigue Damage Assessment of FOWT Mooring Lines Using Sequence-to-Sequence Based Indirect Sensing
- Open Access
- 9 September 2025
- Published by Intelligence Science and Technology Press Inc. in Journal of Dynamics, Monitoring and Diagnostics
Fault Detection in Wind Turbine Bearings by Coupling Knowledge Graph and Machine Learning Approach
Fault sensing in wind turbine generators bearing is essential for ensuring reliability and holding down maintenance costs. Feeding raw sensor data to machine learning (ML) model often overlook the enveloping interdependencies between system elements. This study proposes a new hybrid method that combines the domain knowledge via Knowledge Graphs (KGs) and the traditional feature-based data. Incorporation of contextual relationships through construction of graph embedding methods as Node2Vec can capture meaningful information, such as the relationships among key parameters (e.g. wind speed, rotor RPM, and temperature) in the enriched feature representations. These Node embeddings when Augmented with the original data, these embeddings can be used to allow the model to learn and generalize better. As shown in results achieved on experimental data, the augmented ML model (with KG) is much better at predicting with the help of accuracy and error measure compared to traditional ML methods. Paired t-test analysis proves the statistical validity of this improvement. Moreover, graph-based feature importance increases the interpretability of the model and helps to uncover the structurally significant variables that are otherwise ignored by the common methods. The approach provides an excellent, knowledge-guided manner through which intelligent fault detection can be executed on wind turbine systems.
- 9 September 2025
- Published by Intelligence Science and Technology Press Inc. in Journal of Dynamics, Monitoring and Diagnostics
Open AccessFault Detection in Wind Turbine Bearings by Coupling Knowledge Graph and Machine Learning Approach
Fault sensing in wind turbine generators bearing is essential for ensuring reliability and holding down maintenance costs. Feeding raw sensor data to machine learning (ML) model often overlook the enveloping interdependencies between system elements. This study proposes a new hybrid method that combines the domain knowledge via Knowledge Graphs (KGs) and the traditional feature-based data. Incorporation of contextual relationships through construction of graph embedding methods as Node2Vec can capture meaningful information, such as the relationships among key parameters (e.g. wind speed, rotor RPM, and temperature) in the enriched feature representations. These Node embeddings when Augmented with the original data, these embeddings can be used to allow the model to learn and generalize better. As shown in results achieved on experimental data, the augmented ML model (with KG) is much better at predicting with the help of accuracy and error measure compared to traditional ML methods. Paired t-test analysis proves the statistical validity of this improvement. Moreover, graph-based feature importance increases the interpretability of the model and helps to uncover the structurally significant variables that are otherwise ignored by the common methods. The approach provides an excellent, knowledge-guided manner through which intelligent fault detection can be executed on wind turbine systems.