Machine learning assisted modeling of thermohydraulic correlations for heat exchangers with twisted tape inserts

Panda, J. P.; Kumar, Bipin; Patil, Anil Kumar; Kumar, Manoj; Kumar, Rajiv

doi:10.1007/s10409-022-22036-x

Cited by 4 publications

(3 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, non-uniform intake may cause cylinder deformation and an uneven belt gap, indirectly increasing air leakage loss [23], and the Thomas/Alford force produced by non-uniform intake may also result in rotor instability [24]. Obviously, the numerical calculation method is an effective method for the thermal and aerodynamic optimization design of thermal equipment [25,26].…”

Section: Figurementioning

confidence: 99%

Research on the Aerodynamic Performance and Collaborative Optimization Design of the Full-Scale Compact Inlet Chamber of a Nuclear-Powered Steam Turbine

Zhang,

Jiang,

Xie

et al. 2024

Machines

View full text Add to dashboard Cite

In nuclear-powered steam turbines, the aerodynamic performance of the inlet chamber tends to be contradictory to the compact design, which makes it difficult to achieve optimal efficiency and power in a nuclear-powered steam turbine. In this study, the quantitative correlation between compact design and aerodynamic performance was investigated to reveal the interaction mechanism between the aerodynamic performance of the inlet chamber of the steam turbine with its compactness. First, the effects of peripheral quantity and arrangement of inlets in the chamber inlet on its aerodynamic performance were studied. The results indicated that the proposed cross configuration exhibited optimized aerodynamic performance in multiple aspects. Then, the effects of two compactness indices (inlet/outlet area ratio and axial spacing at outlet) on the aerodynamic performance of the inlet chamber were investigated. The results indicated that the volume of the inlet chamber was proportional to the inlet/outlet area ratio, and an appropriate design of the inlet chamber can achieve compactness without significantly affecting its aerodynamic performance. In addition, the influencing mechanism of the compact optimization design on the aerodynamic performances of the inlet chamber was revealed. This study provides references for optimization designing an effective and compacted inlet chamber of steam turbines.

show abstract

Section: Figurementioning

confidence: 99%

Research on the Aerodynamic Performance and Collaborative Optimization Design of the Full-Scale Compact Inlet Chamber of a Nuclear-Powered Steam Turbine

Zhang,

Jiang,

Xie

et al. 2024

Machines

View full text Add to dashboard Cite

show abstract

“…The model achieved the lowest mean absolute error (MAE) with an intermediate layer structure of 5-10-10-10-1. Jyoti Prakash Panda [18] employed three machine learning methods, namely, polynomial regression (PR), random forest (RF), and an artificial neural network (ANN), for regression analysis of the Reynolds numbers (Re), twist ratio (t), percentage of perforation (p), and the number of twisted tapes (n) against the Nusselt numbers and friction factors inside tubes fitted with twisted tape inserts. The results indicated that the ANN model outperformed the other two.…”

Section: Introductionmentioning

confidence: 99%

Multi-Output Regression Algorithm-Based Non-Dominated Sorting Genetic Algorithm II Optimization for L-Shaped Twisted Tape Insertions in Circular Heat Exchange Tubes

Li,

Qian,

Liu

2024

Energies

View full text Add to dashboard Cite

In this study, an optimization method using various multi-output regression models as model proxies within the NSGA-II framework was applied to determine the geometric parameters (P, W, D) of L-shaped twisted tape inserts for achieving the optimal overall heat transfer performance in a circular heat exchange tube. Herein, 4 multi-output regression models, namely, MOLR, MOSVR, MOGPR, and BPNN, were selected as proxy models and trained on a dataset containing 74 groups of data. The training results indicated that the MOGPR model, balancing high accuracy and low error conditions, exhibited moderate training times among the four algorithms. BPNN showed a comparatively lower comprehensive training effect, obtaining training accuracy close to that of the MOGPR algorithm but with approximately twice the training time. The worst fitting performance was gained with the MOSVR algorithm. Due to its fitting performance, the MOSVR algorithm was excluded from the subsequent NSGA-II model proxy. Through multi-objective optimization with NSGA-II, the optimal structural dimensions for three sets of L-shaped twisted tape inserts were obtained to achieve the best overall heat transfer efficiency within the tube.

show abstract

“…and R.F. across different test datasets [26]. ML tools considerably diminish the attempt to build multivariable heat transfer relationships.…”

Section: Introductionmentioning

confidence: 99%

Experimental Thermohydraulic Assessment of Novel Curved Ribs for Heat Exchanger Tubes: A Machine Learning Approach

Deshmukh,

Lahane,

Sumant

et al. 2023

Aerospace

View full text Add to dashboard Cite

Heat transfer enhancement using curved ribs of different cross sections, viz., square, rectangular, triangular, and circular, is a crucial study for designing heat-exchanging devices for various applications, and their thermohydraulic performance prediction using machine learning technique is a vital part of the modern world. An experimental study on using curved ribs suitable for heat transfer enhancement for the circular tube is presented for turbulent airflow with Reynolds numbers varying from 10,000 to 50,000. The machine learning methodology is used to predict the thermohydraulic performance assessment of curved ribs. The square cross-sectioned curved ribs produce the highest performance factor R3 of 1.5 to 2.65 to the equivalent Reynolds number Rec value of 20,000. It is observed that most of the curved rib configurations show a performance ratio R3 maximum and are suitable at a low Reynolds number value. At moderate and high Reynolds number values, the performance factor values decrease due to a rise in the pressure drop values for a few curved rib configurations. An artificial neural network (ANN) model predicts with an accuracy of 95% with the present study experimental values for the heat transfer performance indicators like average heat transfer enhancement Nua/Nus, average heat transfer enhancement fa/fs, and performance ratio R3, i.e., Nua/Nuc.

show abstract

Machine learning assisted modeling of thermohydraulic correlations for heat exchangers with twisted tape inserts

Cited by 4 publications

References 34 publications

Research on the Aerodynamic Performance and Collaborative Optimization Design of the Full-Scale Compact Inlet Chamber of a Nuclear-Powered Steam Turbine

Research on the Aerodynamic Performance and Collaborative Optimization Design of the Full-Scale Compact Inlet Chamber of a Nuclear-Powered Steam Turbine

Multi-Output Regression Algorithm-Based Non-Dominated Sorting Genetic Algorithm II Optimization for L-Shaped Twisted Tape Insertions in Circular Heat Exchange Tubes

Experimental Thermohydraulic Assessment of Novel Curved Ribs for Heat Exchanger Tubes: A Machine Learning Approach

Contact Info

Product

Resources

About