Arnav Bhardwaj
Research Subjects
Arnav Bhardwaj has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
Raj Kumar Singh
3 shared publications- Abhishek Kumar Mishra2 shared publications
Abhishek Kumar Mishra
1 shared publication- Gaurav Kumar
Delhi Technological University
1 shared publication Shubhanshu Rao
1 shared publication
Latest Publications
- Open Access
- 12 October 2026
- Published by Elsevier in SSRN Electronic Journal
Multi-Objective Optimization of Shell-and-Tube Heat Exchanger Performance Using CFD-Driven Surrogate and Learning-Based Methods
Shell-and-tube heat exchanger performance is governed by competing thermal and hydraulic objectives that single-variable optimisation cannot resolve simultaneously. This study introduces a unified surrogate-assisted framework in which baffle inclination angle θ ∈ [-25◦,25◦] and perforation diameter d ∈[2,5] mm are treated as continuous co-design variables. A twelve-member ANN ensemble trained on 35 CFD-generated samples serves as the frozen evaluation oracle for four independent optimisation paradigms: NSGA-II, Bayesian optimisation, particle swarm optimisation, and deep reinforcement learning. Saturation diagnostics confirmed surrogate fidelity prior to every run. Perforation diameter emerged as the dominant hydraulic lever, with large perforations triggering a shift from recirculation-dominated cross-flow to jet-assisted wake suppression that reduces friction substantially without proportional thermal penalty. DRL-PPO located the globally superior con figuration (θ = 20.88◦, d = 4.46 mm), achieving a CFD-verified thermo hydraulic ratio of j/f = 0.01264: an 18.6% gain over the conventional perpendicular unperforated baseline, a 20.0% improvement over the PEC optimal solid inclined reference, and a 35.1% friction factor reduction relative to the same inclined solid reference. All surrogate prediction errors remained below 2.8% at verified optima, establishing physical credibility of the reported improvements.
- 12 October 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessMulti-Objective Optimization of Shell-and-Tube Heat Exchanger Performance Using CFD-Driven Surrogate and Learning-Based Methods
Shell-and-tube heat exchanger performance is governed by competing thermal and hydraulic objectives that single-variable optimisation cannot resolve simultaneously. This study introduces a unified surrogate-assisted framework in which baffle inclination angle θ ∈ [-25◦,25◦] and perforation diameter d ∈[2,5] mm are treated as continuous co-design variables. A twelve-member ANN ensemble trained on 35 CFD-generated samples serves as the frozen evaluation oracle for four independent optimisation paradigms: NSGA-II, Bayesian optimisation, particle swarm optimisation, and deep reinforcement learning. Saturation diagnostics confirmed surrogate fidelity prior to every run. Perforation diameter emerged as the dominant hydraulic lever, with large perforations triggering a shift from recirculation-dominated cross-flow to jet-assisted wake suppression that reduces friction substantially without proportional thermal penalty. DRL-PPO located the globally superior con figuration (θ = 20.88◦, d = 4.46 mm), achieving a CFD-verified thermo hydraulic ratio of j/f = 0.01264: an 18.6% gain over the conventional perpendicular unperforated baseline, a 20.0% improvement over the PEC optimal solid inclined reference, and a 35.1% friction factor reduction relative to the same inclined solid reference. All surrogate prediction errors remained below 2.8% at verified optima, establishing physical credibility of the reported improvements.
- Open Access
- 23 September 2026
- Published by Elsevier in SSRN Electronic Journal
Multi-Objective Optimization of Shell-and-Tube Heat Exchanger Performance Using CFD-Driven Surrogate and Learning-Based Methods
Shell-and-tube heat exchanger performance is governed by competing thermal and hydraulic objectives that single-variable optimisation cannot resolvesimultaneously. This study introduces a unified surrogate-assisted frameworkin which baffle inclination angle θ ∈ [-25◦,25◦] and perforation diameterd ∈[2,5] mmare treated as continuous co-design variables. A twelve-memberANN ensemble trained on 35 CFD-generated samples serves as the frozenevaluation oracle for four independent optimisation paradigms: NSGA-II,Bayesian optimisation, particle swarm optimisation, and deep reinforcementlearning. Saturation diagnostics confirmed surrogate fidelity prior to everyrun. Perforation diameter emerged as the dominant hydraulic lever, withlarge perforations triggering a shift from recirculation-dominated cross-flowto jet-assisted wake suppression that reduces friction substantially withoutproportional thermal penalty. DRL-PPO located the globally superior configuration (θ = 20.88◦, d = 4.46 mm), achieving a CFD-verified thermohydraulic ratio of j/f = 0.01264: an 18.6% gain over the conventionalperpendicular unperforated baseline, a 20.0% improvement over the PECoptimal solid inclined reference, and a 35.1% friction factor reduction relative to the same inclined solid reference. All surrogate prediction errorsremained below 2.8% at verified optima, establishing physical credibility ofthe reported improvements.
- 23 September 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessMulti-Objective Optimization of Shell-and-Tube Heat Exchanger Performance Using CFD-Driven Surrogate and Learning-Based Methods
Shell-and-tube heat exchanger performance is governed by competing thermal and hydraulic objectives that single-variable optimisation cannot resolvesimultaneously. This study introduces a unified surrogate-assisted frameworkin which baffle inclination angle θ ∈ [-25◦,25◦] and perforation diameterd ∈[2,5] mmare treated as continuous co-design variables. A twelve-memberANN ensemble trained on 35 CFD-generated samples serves as the frozenevaluation oracle for four independent optimisation paradigms: NSGA-II,Bayesian optimisation, particle swarm optimisation, and deep reinforcementlearning. Saturation diagnostics confirmed surrogate fidelity prior to everyrun. Perforation diameter emerged as the dominant hydraulic lever, withlarge perforations triggering a shift from recirculation-dominated cross-flowto jet-assisted wake suppression that reduces friction substantially withoutproportional thermal penalty. DRL-PPO located the globally superior configuration (θ = 20.88◦, d = 4.46 mm), achieving a CFD-verified thermohydraulic ratio of j/f = 0.01264: an 18.6% gain over the conventionalperpendicular unperforated baseline, a 20.0% improvement over the PECoptimal solid inclined reference, and a 35.1% friction factor reduction relative to the same inclined solid reference. All surrogate prediction errorsremained below 2.8% at verified optima, establishing physical credibility ofthe reported improvements.