Neural networks assisted computational aero-acoustic analysis of an isolated tire

Abstract

The computational aero-acoustic study of an isolated passenger car tire is carried out to understand the effect of dimensions of longitudinal tire grooves and operational parameters (velocity and temperature) on tire noise. The computational fluid dynamics and acoustic models are used to obtain aero-acoustic tire noise at near-field and far-field receivers around the tire and artificial neural networks-based regression are used to study the highly non-linear and interactive causal relationships in the system. Unsteady Reynolds-Averaged Navier-Stokes based realizable k-epsilon model is used to solve the flow field in the computational domain. The Ffowcs Williams and Hawkings model is used to obtain aero-acoustic tire noise at far-field positions. Spectral analysis is used to convert the output time domain to frequency domain and to obtain A-weighted sound pressure level. Artificial neural network–based response surface regression is conducted to understand casual relationships between A-weighted sound pressure level and control variables (Groove depth, Groove width, Temperature and velocity). Maximum A-weighted sound pressure level is observed in the wake region of the tire model. The interaction study indicates that ∼10% reduction in the aero-acoustic emissions is possible by selecting appropriate combinations of groove width and groove depth. The interaction of velocity with width is found to be most significant with respect to A-weighted sound pressure level at all receivers surrounding the tire. The interaction of operational parameters, that is, velocity and temperature are found to be significant with respect to A-weighted sound pressure level at wake and front receivers. Therefore, the regional speed limits and seasonal temperatures need to be considered while designing the tire to achieve minimum aero-acoustic emissions.

Optimization of a 660 MWe Supercritical Power Plant Performance—A Case of Industry 4.0 in the Data-Driven Operational Management. Part 2. Power Generation

“…The minimum, average, and maximum values of the thermo-electric operating parameters at 50% and 100% unit load are listed in Table 6. Comprehensive Monte-Carlo experiments are constructed, and gaussian noise is equal to one percent of the operating range of the thermo-electric operating parameters [54,55]. It is essential to mention here that the generator power trends are constructed with a 99% confidence interval to ensure the relationship and interaction among the thermo-electric operating parameters and generator power, as discussed in the next sections.…”

Modeling Viscosity and Density of Ethanol-Diesel-Biodiesel Ternary Blends for Sustainable Environment

“…To develop more precise viscosity models, the natural log of all viscosity values was determined. After that, Equation (12) was developed for the calculation of viscosity of HSD, all biodiesels, and bioethanol from 15 • C to 105 • C. The higher coefficients of determination specifies that these models are appropriate and best fit in the calculation of viscosity of all components of ternary blends.…”

“…log η = −f × T + Y (12) where, T indicates the temperature ( • C) and η indicates the kinematic viscosity (mm 2 /s), f is regression parameter and y is a constant value. Table 6 represents the corresponding values of regression parameters, constants, and R 2 for biodiesels, HSD, and bioethanol.…”

“…On the other hand, energy demand is increasingly growing due to the rapidly expanding population coupled with the increasing urbanization rate [6][7][8]. The global economy has been affected badly by the predominant energy crisis [9][10][11][12]. The developing countries' economies have been uncompetitive because of unavailability of useable energy [13][14][15][16].…”

Artificial Intelligence Modeling-Based Optimization of an Industrial-Scale Steam Turbine for Moving toward Net-Zero in the Energy Sector

“…ANN and SVM models as bottom-up approaches for modeling the isentropic efficiency of HP steam turbine are selected. The two modeling techniques have presented useful results in scientific and industrial research studies. − ANN possesses nonlinear learning characteristics desirable for approximating an ill-defined and complex objective function, which is modeled on the hyperdimensional and interacting input parameters . On the other hand, SVM has demonstrated an excellent generalization ability in numerous applications ranging from atomic domain to enterprise-level optimization. , The performance comparison of the two models is investigated so that a better-performing model could be selected.…”