Search results

Higher energy conversion efficiency of internal combustion engine can be achieved with optimal control of unsteady in-cylinder flow fields inside a direct-injection (DI) engine. However, it remains a daunting task to predict the nonlinear and transient in-cylinder flow motion because they are highly complex which change both in space and time. Recently, machine learning methods have demonstrated great promises to infer relatively simple temporal flow field development. This paper aims to feature a physics-guided machine learning approach to realize high accuracy and generalization prediction for complex swirl-induced flow field motions.

To achieve high-fidelity time-series prediction of unsteady engine flow fields, this work features an automated machine learning framework with the following objectives: (1) The spatiotemporal physical constraint of the flow field structure is transferred to machine learning structure. (2) The ML inputs and targets are efficiently designed that ensure high model convergence with limited sets of experiments. (3) The prediction results are optimized by ensemble learning mechanism within the automated machine learning framework.

The proposed data-driven framework is proven effective in different time periods and different extent of unsteadiness of the flow dynamics, and the predicted flow fields are highly similar to the target field under various complex flow patterns. Among the described framework designs, the utilization of spatial flow field structure is the featured improvement to the time-series flow field prediction process.

The proposed flow field prediction framework could be generalized to different crank angle periods, cycles and swirl ratio conditions, which could greatly promote real-time flow control and reduce experiments on in-cylinder flow field measurement and diagnostics.

The purpose of this study is to investigate the Dynamics of micropolar – water B Fluids flow simultaneously under the influence of thermal radiation and Soret–Dufour Mechanisms.

The thermal radiation contribution, the chemical change and heat generation take fluidity into account. The flow equations are used to produce a series of dimensionless equations with appropriate nondimensional quantities. By using the spectral homotopy analysis method (SHAM), simplified dimensionless equations have been quantitatively solved. With Chebyshev pseudospectral technique, SHAM integrates the approach of the well-known method of homotopical analysis to the set of altered equations. In terms of velocity, concentration and temperature profiles, the impacts of Prandtl number, chemical reaction and thermal radiation are studied. All findings are visually shown and all physical values are calculated and tabulated.

The results indicate that an increase in the variable viscosity leads to speed and temperature increases. Based on the transport nature of micropolar Walters B fluids, the thermal conductivity has great impact on the Prandtl number and decrease the velocity and temperature. The current research was very well supported by prior literature works. The results in this paper are anticipated to be helpful for biotechnology, food processing and boiling. It is used primarily in refrigerating systems, tensile heating to large-scale heating and oil pipeline reduction.

All results are presented graphically and all physical quantities are computed and tabulated.

Flow induced by rotating disks is of great practical importance in several engineering applications such as rotating heat exchangers, turbine disks, pumps and many more. The present research has been freshly displayed regarding the implementation of an engine oil-based Casson tri-hybrid nanofluid across a rotating disk in mass and heat transferal developments. The purpose of this study is to contemplate the attributes of the flowing tri-hybrid nanofluid by incorporating porosity effects and magnetization and velocity slip effects, viscous dissipation, radiating flux, temperature slip, chemical reaction and activation energy.

The articulated fluid flow is described by a set of partial differential equations which are converted into one set of higher-order ordinary differential equations (ODEs) by using convenient conversions. The numerical solution of this transformed set of ODEs has been spearheaded by using the effectual bvp4c scheme.

The acquired results show that the heat transmission rate for the Casson tri-hybrid nanofluid is intensified by, respectively, 9.54% and 11.93% when compared to the Casson hybrid nanofluid and Casson nanofluid. Also, the mass transmission rate for the Casson tri-hybrid nanofluid is augmented by 1.09% and 2.14%, respectively, when compared to the Casson hybrid nanofluid and Casson nanofluid.

The current investigation presents an educative response on how the flow profiles vary with changes in the inevitable flow parameters. As per authors’ knowledge, no such scrutinization has been carried out previously; therefore, our results are novel and unique.

Identifying the flow regime is a prerequisite for accurately modeling two-phase flow. This paper aims to introduce a comprehensive data-driven workflow for flow regime identification.

A numerical two-phase flow model was validated against experimental data and was used to generate dynamic pressure signals for three different flow regimes. First, four distinct methods were used for feature extraction: discrete wavelet transform (DWT), empirical mode decomposition, power spectral density and the time series analysis method. Kernel Fisher discriminant analysis (KFDA) was used to simultaneously perform dimensionality reduction and machine learning (ML) classification for each set of features. Finally, the Shapley additive explanations (SHAP) method was applied to make the workflow explainable.

The results highlighted that the DWT + KFDA method exhibited the highest testing and training accuracy at 95.2% and 88.8%, respectively. Results also include a virtual flow regime map to facilitate the visualization of features in two dimension. Finally, SHAP analysis showed that minimum and maximum values extracted at the fourth and second signal decomposition levels of DWT are the best flow-distinguishing features.

This workflow can be applied to opaque pipes fitted with pressure sensors to achieve flow assurance and automatic monitoring of two-phase flow occurring in many process industries.

This paper presents a novel flow regime identification method by fusing dynamic pressure measurements with ML techniques. The authors’ novel DWT + KFDA method demonstrates superior performance for flow regime identification with explainability.

The purpose of this paper is to develop a load detection method for domestic induction cooktops. The solution aims to minimize its impact in the converter power transmission while enabling the estimation of the equivalent electrical parameters of the load. This method is suitable for a multi-output resonant inverter topology with shared power devices.

The considered multi-output converter presents power devices that are shared between several loads. Thus, applying load detection methods in the literature requires a halt in the power transfer to ensuring safe operation. The proposed method uses a complementary short-voltage pulse to excite the induction heating (IH) coil without stopping the power transfer to the remaining IH loads. With the current through the coil and the analytical equations, the equivalent inductance and resistance of the load is estimated. The precision of the method has been evaluated by simulation, and experimental results are provided.

The measurement of the current through the induction coil as a response to a short-time single-pulse voltage variation provides enough information to estimate the load equivalent parameters, allowing to differentiate between no-load, non-suitable IH load and suitable IH load situations.

The proposed method provides a solution for load detection without requiring additional circuitry. It aims for low power transmission to the load and ensures zero-voltage switching and reduced peak current even in no-load cases. Moreover, the proposed solution is extensible to less complex converters, as the half bridge.

This study aims to investigate whether consumers and small businesses can transition from disposable to reusable coffee cups, using a community social marketing intervention, led by a Social Purpose Organisation.

An emergent case study approach using multiple sources of data developed an in-depth, multifaceted, real-world context evaluation of the intervention. The methodology draws on citizen science “messy” data collection involving multiple, fragmented sources.

Moving from single-use cups to reusables requires collective commitment by retailers, consumers and policymakers, despite the many incentives and penalties applied to incentivise behaviour change. Difficult post-COVID economics, austerity and infrastructure gaps are undermining both reusable acceptance and interim solutions to our dependence upon disposables.

Although the non-traditional methodology rendered gaps and omissions in the data, the citizen science was democratising and inclusive for the community.

Our practical contribution evaluates a whole community intervention setting to encourage reusable cups, integrating multiple stakeholders, in a non-controllable, non-experimental environment in contrast to previous research. This paper demonstrates how small community grants can foster impactful collaborative partnerships between an SPO and researchers, facilitate knowledge-exchange beyond the initial remit and provide a catalyst for possible future impact and outcomes.

To assess the impact at both the outcome and the process level of the intervention, we use Pawson and Tilley’s realist evaluation theory – the Context Mechanism Outcome framework. The methodological contribution demonstrates the process of citizen science “messy” data collection, likely to feature more frequently in future social science research addressing climate change and sustainability challenges.

This study aims to investigate the individual electrochemical transients arising from local anodic events on stainless steel, to uncover the potential mechanisms producing different types of transients and to derive appropriate parameters indicative of the corrosion severity of such transient events.

An equivalent circuit model was used for the transient analysis, which was performed using a local current allocation rule based on the relative instant cathodic resistance of the coupled electrodes, as well as the kinetic parameters derived from the electrochemical polarization measurement.

The shape and size of the electrochemical current transients arising from SS 316 L were influenced by the film stability, local anodic dissolution kinetics and the symmetry of the cathodic kinetics between the coupled electrodes, where the ultralong transient might correspond to the propagation of film damage with a slow anodic dissolution rate. The dynamic cathodic resistance during the final stage of transient current growth can serve as a characteristic parameter that reflects the loss of passive film protection.

Estimation of the local anodic current trace opens a new way for individual electrochemical transient analysis associated with the charges involved, local current densities and changes in film resistance throughout localized corrosion processes.

This study aims to offer a hybrid stand-alone system for electric vehicle (EV) charging stations (CS), an emerging power scheme due to the availability of renewable and environment-friendly energy sources. This paper presents the analysis of a photovoltaic (PV) with an adaptive neuro-fuzzy inference system (ANFIS) algorithm, solid oxide fuel cell (SOFC) and a battery storage scheme incorporated for EV CS in a stand-alone mode. In previous studies, either the hydrogen fuel of SOFC or the irradiance is controlled using artificial neural network. These parameters are not controlled simultaneously using an ANFIS-based approach. The ANFIS-based stand-alone hybrid system controlling both the fuel flow of SOFC and the irradiance of PV is discussed in this paper.

The ANFIS algorithm provides an efficient estimation of maximum power (MP) to the nonlinear voltage–current characteristics of a PV, integrated with a direct current–direct current (DC–DC) converter to boost output voltage up to 400 V. The issue of fuel starvation in SOFC due to load transients is also mitigated using an ANFIS-based fuel flow regulator, which robustly provides fuel, i.e. hydrogen per necessity. Furthermore, to ensure uninterrupted power to the CS, PV is integrated with a SOFC array, and a battery storage bank is used as a backup in the current scenario. A power management system efficiently shares power among the aforesaid sources.

A comprehensive simulation test bed for a stand-alone power system (PV cells and SOFC) is developed in MATLAB/Simulink. The adaptability and robustness of the proposed control paradigm are investigated through simulation results in a stand-alone hybrid power system test bed.

The simulation results confirm the effectiveness of the ANFIS algorithm in a stand-alone hybrid power system scheme.

As data centres grow in size and complexity, traditional air-cooling methods are becoming less effective and more expensive. Immersion cooling, where servers are submerged in a dielectric fluid, has emerged as a promising alternative. Ensuring reliable operations in data centre applications requires the development of an effective control framework for immersion cooling systems, which necessitates the prediction of server temperature. While deep learning-based temperature prediction models have shown effectiveness, further enhancement is needed to improve their prediction accuracy. This study aims to develop a temperature prediction model using Long Short-Term Memory (LSTM) Networks based on recursive encoder-decoder architecture.

This paper explores the use of deep learning algorithms to predict the temperature of a heater in a two-phase immersion-cooled system using NOVEC 7100. The performance of recursive-long short-term memory-encoder-decoder (R-LSTM-ED), recursive-convolutional neural network-LSTM (R-CNN-LSTM) and R-LSTM approaches are compared using mean absolute error, root mean square error, mean absolute percentage error and coefficient of determination (R²) as performance metrics. The impact of window size, sampling period and noise within training data on the performance of the model is investigated.

The R-LSTM-ED consistently outperforms the R-LSTM model by 6%, 15.8% and 12.5%, and R-CNN-LSTM model by 4%, 11% and 12.3% in all forecast ranges of 10, 30 and 60 s, respectively, averaged across all the workloads considered in the study. The optimum sampling period based on the study is found to be 2 s and the window size to be 60 s. The performance of the model deteriorates significantly as the noise level reaches 10%.

The proposed models are currently trained on data collected from an experimental setup simulating data centre loads. Future research should seek to extend the applicability of the models by incorporating time series data from immersion-cooled servers.

The proposed multivariate-recursive-prediction models are trained and tested by using real Data Centre workload traces applied to the immersion-cooled system developed in the laboratory.

In this study, the authors propose a novel digital twinning approach specifically designed for controlling transient thermal systems. The purpose of this study is to harness the combined power of deep learning (DL) and physics-based methods (PBM) to create an active virtual replica of the physical system.

To achieve this goal, we introduce a deep neural network (DNN) as the digital twin and a Finite Element (FE) model as the physical system. This integrated approach is used to address the challenges of controlling an unsteady heat transfer problem with an integrated feedback loop.

The results of our study demonstrate the effectiveness of the proposed digital twinning approach in regulating the maximum temperature within the system under varying and unsteady heat flux conditions. The DNN, trained on stationary data, plays a crucial role in determining the heat transfer coefficients necessary to maintain temperatures below a defined threshold value, such as the material’s melting point. The system is successfully controlled in 1D, 2D and 3D case studies. However, careful evaluations should be conducted if such a training approach, based on steady-state data, is applied to completely different transient heat transfer problems.

The present work represents one of the first examples of a comprehensive digital twinning approach to transient thermal systems, driven by data. One of the noteworthy features of this approach is its robustness. Adopting a training based on dimensionless data, the approach can seamlessly accommodate changes in thermal capacity and thermal conductivity without the need for retraining.