<p>Thermo-acoustic systems can convert thermal energy into acoustic waves or mechanical energy. These acoustic waves can be used to induce cooling (Thermo-acoustic refrigeration) or generate electricity (thermo-acoustic generator). This conversion is due to the interaction between the heat and the gas medium within a porous material referred to as a regenerator. Although there has been significant progress about the development of efficient thermo-acoustic systems, the efficiency of the systems and the non-linearity associated with the working of the systems remain the major potential area of research. Many existing studies are using DELTAEC (Design Environment for Low-amplitude ThermoAcoustic Energy Conversion) to build theoretical models and analyse the effect of the geometrical configuration of thermo-acoustic systems. Reasonable agreements are reported between simulation results obtained with DELTAEC and experimental results. In this study, a one-stage travelling-wave thermo-acoustic engine has been modelled using DELTAEC. Six (6) parameters affecting the performance of the system have been considered to analyse the system. These parameters include the resonant frequency, the pressure amplitude, the volumetric flow rate, the phase angle, the mean temperature and the input heat. The acoustic power is considered as the main indicator of the performance of the system. The simulation was performed by considering several mean pressure within the range of 1 to 10 Bars. Several configurations have been generated to relate the output of the system to the input parameters. Forty (40) data were considered for the modelling proposed in this study. These data were used to build an Artificial Neural Network (ANN) model. Many studies have provided evidence that ANN models are reliable when it comes to relating non-linear parameters that is the case with thermo-acoustic systems. The ANN model consists of six (6) inputs parameters, one (1) output parameter, and several hidden layers. The proposed model was analysed in order to identify the best ANN architecture with respect to the number of hidden layers. A parametric analysis was performed to identify the ANN architecture that yields the highest regression value. This study contributes meaningfully to the modelling of the travelling-wave thermo-acoustic system through the development of a model suitable for the prediction of configurations that were not simulated. The approach proposed in this study could potentially improve the analysis of thermo-acoustic systems and provides a better insight into the issue related to their efficiency. This would result in a potential minimisation of time-consuming experiment and provide an alternative modelling approach to the thermo-acoustic community of researchers.</p>

Performance Analysis of a Travelling-Wave Thermo-Acoustic Engine Using Artificial Neural Network

Paper Proceedings: https://asmedigitalcollection.asme.org/IMECE/IMECE2021/volume/85543

ASME 2021 International Mechanical Engineering Congress and Exposition (IMECE2021)

Supporting the need among researchers worldwide for additional online and multimedia content, ASME now offers the ASME Conference Video Collection. This platform will collect and provide long-term access to conference presentation videos, encompassing all technology areas within ASME's technical conference and events program. About 30,000-40,000 engineers across all mechanical engineering and related disciplines participate in ASME conferences each year. This includes authors of approximately 6,000 to 8,000 technical papers published by ASME, the majority of whom also submit video presentations for our virtual conferences. The video collection will be available as an add-on to existing product packages or as a separate subscription.