| 171. |
- Soibam, Jerol, et al.
(författare)
-
A Data-Driven Approach for the Prediction of Subcooled Boiling Heat Transfer
- 2020
-
Ingår i: Proceedings of The 61st SIMS Conference on Simulation and Modelling SIMS 2020. - : Linköping University Electronic Press. ; , s. 435-442
-
Konferensbidrag (övrigt vetenskapligt/konstnärligt)abstract
- In subcooled flow boiling, heat transfer mechanism involves phase change between liquid phase to the vapour phase. During this phase change, a large amount of energy is transferred, and it is one of the most effective heat transfer methods. Subcooled boiling heat transfer is an attractive trend for industrial applications such as cooling electronic components, supercomputers, nuclear industry, etc. Due to its wide variety of applications for thermal management, there is an increasing demand for a faster and more accurate way of modelling. In this work, a supervised deep neural network has been implemented to study the boiling heat transfer in subcooled flow boiling heat transfer. The proposed method considers the near local flow behaviour to predict wall temperature and void fraction of a sub-cooled mini-channel. The input of the network consists of pressure gradients, momentum convection, energy con- vection, turbulent viscosity, liquid and gas velocities, and surface information. The output of the model is based on the quantities of interest in a boiling system i.e. wall temperature and void fraction. The network is trained from the results obtained from numerical simulations, and the model is used to reproduce the quantities of interest for interpolation and extrapolation datasets. To create an agile and robust deep neural network model, state-of-the-art methods have been implemented in the network to avoid the overfitting issue of the model. The results obtained from the deep neural network model shows a good agreement with the numerical data, the model has a maximum relative error of 0.5 % while predicting the temperature field, and for void fraction, it has approximately 5 % relative error in interpolation data and a maximum 10 % relative error for the extrapolation datasets.
|
|
| 172. |
- Soibam, Jerol, et al.
(författare)
-
Application of deep learning for segmentation of bubble dynamics in subcooled boiling
- 2023
-
Ingår i: International Journal of Multiphase Flow. - 0301-9322 .- 1879-3533. ; 169
-
Tidskriftsartikel (refereegranskat)abstract
- The present work focuses on designing a robust deep-learning model to track bubble dynamics in a vertical rectangular mini-channel. The rectangular mini-channel is heated from one side with a constant heat flux, resulting in the creation of bubbles. Images of the bubbles are recorded using a high-speed camera, which serve as the input data for the deep learning model. The raw image data acquired from the high-speed camera is inherently noisy due to the presence of shadows, reflections, background noise, and chaotic bubbles. The objective is to extract the mask of the bubble given all these challenging factors. Transfer learning is adopted to eliminate the need for a large dataset to train the deep learning model and also to reduce computational costs. The trained model is then validated against the validation datasets, demonstrating an accuracy of 98% while detecting the bubbles. The model is then evaluated on different experimental conditions, such as lighting, background, and blurry images with noise. The model demonstrates high robustness to different conditions and is able to detect the edges of the bubbles and classify them accurately. Moreover, the model achieves an average intersection over union of 85%, indicating a high level of accuracy in predicting the masks of the bubbles. The method enables accurate recognition and tracking of individual bubble dynamics, capturing their coalescence, oscillation, and collisions to estimate local parameters by proving the bubble masks. This allows for a comprehensive understanding of their spatial-temporal behaviour, including the estimation of local Reynolds numbers.
|
|
| 173. |
- Soibam, Jerol
(författare)
-
Data-Driven Techniques for Fluid Mechanics and Heat Transfer
- 2022
-
Licentiatavhandling (övrigt vetenskapligt/konstnärligt)abstract
- One of the main challenges in fluid mechanics and heat transfer is the need for detailed studies andfast computational speed to monitor and optimise a system. These fluid/heat flows comprise time-dependent velocity, multi-scale, pressure, and energy fluctuations. Although there has been major advancements in computational power and technology, modelling detailed physical problems is currently falling short. The fluid mechanics and heat transfer domains are rapidly advancing, driven by unprecedented volumes of data from experiments, field measurements, and large-scale simulations at multiple spatio temporal scales. Such an increase in the volume of data unlocks the possibility of using techniques like machine learning. These machine learning algorithms offer a wealth of techniques to extract information from data that can be translated into knowledge about the underlying physics. Moreover, machine learning algorithms can augment domain knowledge and automate tasks related to flow control and optimisation. A significant milestone in the area of machine learning is the rise of deep learning, which is a powerful tool which can handle large data sets describing complex nonlinear dynamics that are commonly encountered in heat transfer and fluidflows.Therefore, this thesis aims to investigate data obtained from numerical simulations with deep learning techniques to reproduce the underlying physics present in data and considerably speed up the process. In this study, subcooled boiling transfer data has been used to train the deep neural network model then the trained model is validated using a validation dataset. The performance of the model is further evaluated using a set of interpolation and extrapolation datasets for different operating conditions outside the training and validation data. Furthermore, to highlight the robustness and reliability of the deep learning model, uncertainty quantification techniques such as Monte Carlo dropout and Deep Ensemble are implemented.This study demonstrates how a data-driven model can be used for subcooled boiling heat transfer and highlights why uncertainty quantification is important for such a model. The analysis and discussion in this thesis serve as the basis for further extending the potential use of data-driven methods for system optimisation, control and monitoring, diagnostic, and industrial applications.
|
|
| 174. |
- Soibam, Jerol, et al.
(författare)
-
Derivation and Uncertainty Quantification of a Data-Driven Subcooled Boiling Model
- 2020
-
Ingår i: Energies. - : MDPI. - 1996-1073. ; 13:22
-
Tidskriftsartikel (refereegranskat)abstract
- Subcooled flow boiling occurs in many industrial applications where enormous heat transfer is needed. Boiling is a complex physical process that involves phase change, two-phase flow, and interactions between heated surfaces and fluids. In general, boiling heat transfer is usually predicted by empirical or semiempirical models, which are horizontal to uncertainty. In this work, a data-driven method based on artificial neural networks has been implemented to study the heat transfer behavior of a subcooled boiling model. The proposed method considers the near local flow behavior to predict wall temperature and void fraction of a subcooled minichannel. The input of the network consists of pressure gradients, momentum convection, energy convection, turbulent viscosity, liquid and gas velocities, and surface information. The outputs of the models are based on the quantities of interest in a boiling system wall temperature and void fraction. To train the network, high-fidelity simulations based on the Eulerian two-fluid approach are carried out for varying heat flux and inlet velocity in the minichannel. Two classes of the deep learning model have been investigated for this work. The first one focuses on predicting the deterministic value of the quantities of interest. The second one focuses on predicting the uncertainty present in the deep learning model while estimating the quantities of interest. Deep ensemble and Monte Carlo Dropout methods are close representatives of maximum likelihood and Bayesian inference approach respectively, and they are used to derive the uncertainty present in the model. The results of this study prove that the models used here are capable of predicting the quantities of interest accurately and are capable of estimating the uncertainty present. The models are capable of accurately reproducing the physics on unseen data and show the degree of uncertainty when there is a shift of physics in the boiling regime.
|
|
| 175. |
- Soibam, Jerol, et al.
(författare)
-
Inverse flow prediction using ensemble PINNs and uncertainty quantification
- 2024
-
Ingår i: International Journal of Heat and Mass Transfer. - 0017-9310 .- 1879-2189. ; 226
-
Tidskriftsartikel (refereegranskat)abstract
- The thermal boundary conditions in a numerical simulation for heat transfer are often imprecise. This leads to poorly defined boundary conditions for the energy equation. The lack of accurate thermal boundary conditions in real-world applications makes it impossible to effectively solve the problem, regardless of the advancement of conventional numerical methods. This study utilises a physics-informed neural network to tackle ill-posed problems for unknown thermal boundaries with limited sensor data. The network approximates velocity and temperature fields while complying with the Navier-Stokes and energy equations, thereby revealing unknown thermal boundaries and reconstructing the flow field around a square cylinder. The method relies on optimal sensor placement determined by the QR pivoting technique, which ensures the effective capture of the dynamics, leading to enhanced model accuracy. In an effort to increase the robustness and generalisability, an ensemble physics-informed neural network is implemented. This approach mitigates the risks of overfitting and underfitting while providing a measure of model confidence. As a result, the ensemble model can identify regions of reliable prediction and potential inaccuracies. Therefore, broadening its applicability in tackling complex heat transfer problems with unknown boundary conditions.
|
|
| 176. |
- Soibam, Jerol, et al.
(författare)
-
Inverse Flow Prediction Using Pinns In An Enclosure Containing Heat Sources
- 2023
-
Ingår i: Proc. Thermal Fluids Eng. Summer Conf.. - : Begell House Inc.. ; , s. 429-438
-
Konferensbidrag (refereegranskat)abstract
- While simulating heat transfer problems using a numerical method, the thermal boundary conditions are never known precisely, which leads to ill-posed boundary conditions for the energy equation. The lack of knowledge of accurate thermal boundary conditions in a practical application makes it impossible to solve this problem no matter how sophisticated the conventional numerical method is. Hence, the current work addresses this ill-posed problem using physics informed neural network by assuming that the thermal boundary near the source is unknown and only a few measurements of temperature are known in the domain. Physics-informed neural network is employed to represent the velocity and temperature fields, while simultaneously enforcing the Navier-Stokes and energy equations at random points in the domain. This work serves as an inverse problem since the goal here is to reproduce the global flow field and temperature profile in the domain with few measurement data points. Furthermore, the work focuses on using transfer learning for different parameters such as the position and size of the source term inside the enclosure domain. These parameters are of particular interest while designing a thermal system and being able to predict the flow and thermal behaviour instantly will allow for better design of the system. For this study, the sensors' data are extracted from numerical simulation results. The placement of the sensors in the domain plays a vital role in accuracy hence, sensors were optimized using the residual of the energy equation. The results obtained from this work demonstrate that the proposed method is in good agreement with the underlying physics represented by the numerical results.
|
|
| 177. |
- Soibam, Jerol
(författare)
-
Machine Learning Techniques for Enhanced Heat Transfer Modelling
- 2024
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- With the continuous growth of global energy demand, processes from power generation to electronics cooling become vitally important. The role of heat transfer in these processes is crucial, facilitating effective monitoring, control, and optimisation. Therefore, advancements and understanding of heat transfer directly correlate to system performance, lifespan, safety, and cost-effectiveness, and they serve as key components in addressing the world's increasing energy needs.The field of heat transfer faces the challenge of needing intensive studies while retaining fast computational speeds to allow for system optimisation. While advancements in computational power are significant, current numerical models lack in handling complex physical problems such as ill-posed. The domain of heat transfer is rapidly evolving, driven by a wealth of data from experimental measurements and numerical simulations. This data influx presents an opportunity for machine learning techniques, which can be used to harness meaningful insights about the underlying physics.Therefore, the current thesis aims to the explore machine learning methods concerning heat transfer problems. More precisely, the study looks into advanced algorithms such as deep, convolutional, and physics-informed neural networks to tackle two types of heat transfer: subcooled boiling and convective heat transfer. The thesis further addresses the effective use of data through transfer learning and optimal sensor placement when available data is sparse, to learn the system behaviour. This technique reduces the need for extensive datasets and allows models to be trained more efficiently. An additional aspect of this thesis revolves around developing robust machine learning models. Therefore, significant efforts have been directed towards accounting for the uncertainty present in the model, which can further illuminate the model’s behaviour. This thesis shows the machine learning model's ability for accurate prediction. It offers insights into various parameters and handles uncertainties and ill-posed problems. The study emphasises machine learning's role in optimising heat transfer processes. The findings highlight the potential of synergistic application between traditional methodologies and machine learning models. These synergies can significantly enhance the design of systems, leading to greater efficiency.
|
|
| 178. |
- Soibam, Jerol, 1992-, et al.
(författare)
-
PREDICTION OF THE CRITICAL HEAT FLUX USING PARAMETRIC GAUSSIAN PROCESS REGRESSION
- 2021
-
Ingår i: Proceedings of the 15th International Conference on Heat Transfer, Fluid Mechanics andThermodynamics (HEFAT2021). - : HEFAT. - 9781775922162 ; , s. 1865-1870
-
Konferensbidrag (refereegranskat)abstract
- A sound understanding of the critical heat flux is of prime importance for any industrial boiling system design and safety. From the literature, the majority of the critical heat flux studies are based on empirical knowledge, often supported by ex- perimental investigations which are performed under specific conditions difficult to be generalized. Consequently, most of the available correlations have ±30% predictive error when com- pared to measurement data. Hence, accurate prediction of this quantity remains an open challenge for the thermal engineering community. The present study aims to investigate the hidden features that exist in experimental data using a machine learning technique. Firstly, a literature survey is carried out to collect experimental data for boiling flows in tubes under low pressure and low flow conditions. These experimental data consist of the following parameters: system pressure, mass flux, characteristic dimensions, thermodynamic quality, inlet subcooling, and critical heat flux. A parametric Gaussian process regression model is used to predict the critical heat flux. The prediction obtained from the model is then compared with experimental measurements and the values obtained from the critical heat flux look-up table. The model used in this study is capable of predicting the critical heat flux with better accuracy along with the information of prediction uncertainty. Moreover, it provides insights on the relevance of the different input parameters to the prediction of the critical heat flux and aligns well with the underlying physics. The model used in this study shows a good level of robustness which can be further extended for other geometries, datasets, and operating conditions.
|
|
| 179. |
- Stenfelt, Mikael, 1983-, et al.
(författare)
-
AUTOMATIC GAS TURBINE MATCHING SCHEME ADAPTATION FOR ROBUST GPA DIAGNOSTICS
- 2019
-
Ingår i: Proceedings of the ASME Turbo ExpoVolume 6, 2019.
-
Konferensbidrag (refereegranskat)abstract
- When performing gas turbine diagnostics using Gas Path Analysis (GPA), a convenient way of extracting the degradations is by feeding the measured data from a gas turbine to a well-tuned gas turbine performance code, which in turn calculates the deltas on the chosen health parameters matching the measured inputs. For this, a set of measured parameters must be matched with suitable health parameters, such as deltas on compressor and turbine efficiency and flow capacity.In aero engines, the number of sensors are in general limited due to cost and weight constraints and only the necessary sensors for safe engine operation are available. Some important sensors may have redundancy in case of a sensor loss but it is far from certain that this applies to all sensors available.If a sensor malfunctions by giving false or no values, the functions using the sensor will be negatively affected in some way causing them to either synthesize a fictive measurement, changing operating scheme, going into a degraded operating mode or shutting down parts or the whole process. If an onboard diagnostic algorithm fails due to sensor faults it will lead to a decrease in flight safety, thus there is a need for a robust system.This paper presents a strategy for automatic modifications of the gas turbine diagnostic matching scheme when sensors malfunction to ensure a robust function. When a sensor fault is detected and classified as malfunctioning, the gas turbine matching scheme is modified according to predefined rules. If possible, a redundant measurement replaces the faulty measurement. If not, the matching scheme will be modified by determining if any health parameters cannot be derived by the functional set of measurements and remove the least valuable health parameter while maintaining a working matching scheme for the remaining health parameters.
|
|
| 180. |
- Stenfelt, Mikael, et al.
(författare)
-
Estimation and Mitigation of Unknown Airplane Installation Effects on GPA Diagnostics
- 2022
-
Ingår i: Machines. - : MDPI. - 2075-1702. ; 10:1
-
Tidskriftsartikel (refereegranskat)abstract
- In gas turbines used for airplane propulsion, the number of sensors are kept at a minimum for accurate control and safe operation. Additionally, when data are communicated between the airplane main computer and the various subsystems, different systems may have different constraints and requirements regarding what data transmit. Early in the design process, these parameters are relatively easy to change, compared to a mature product. If the gas turbine diagnostic system is not considered early in the design process, it may lead to diagnostic functions having to operate with reduced amount of data. In this paper, a scenario where the diagnostic function cannot obtain airplane installation effects is considered. The installation effects in question is air intake pressure loss (pressure recovery), bleed flow and shaft power extraction. A framework is presented where the unknown installation effects are estimated based on available data through surrogate models, which is incorporated into the diagnostic framework. The method has been evaluated for a low-bypass turbofan with two different sensor suites. It has also been evaluated for two different diagnostic schemes, both determined and underdetermined. Results show that, compared to assuming a best-guess constant-bleed and shaft power, the proposed method reduce the RMS in health parameter estimation from 26% up to 80% for the selected health parameters. At the same time, the proposed method show the same degradation pattern as if the installation effects were known.
|
|
