No abstract

Ventilation systems are used in gas turbine packages to control the air temperature, to protect electrical instrumentation and auxiliary items installed inside the enclosure and to ensure a proper dilution of potentially dangerous gas leakages. These objectives are reached only if the ventilation flow is uniformly distributed in the whole volume of the package, providing a good air flow quality as prescribed by international codes such as ISO 21789. To evaluate the effectiveness of the ventilation design, numerical computations are performed for several purposes, one of which is the identification of poorly ventilated portions of the enclosure. In fact, it is essential to accurately detect the regions which are less ventilated, since they could be prone to the accumulation of an accidental fuel gas leak. There are different approaches to identify these portions, such as decay regression or inlet source analysis, that require unsteady simulations of the flow field inside the package. The present work discusses the implementation of a new methodology using machine learning and artificial neural networks (ANN) to detect the poorly ventilated regions where a gas cloud can accumulate. The concentration of fuel gas is estimated starting from a steady-state computation without running a more expensive unsteady computation. The entire process is built around an accurate training of the ANN using a proper set of simpler test-cases that have been identified to match the characteristics of the gas turbine enclosure. During the training phase accuracy and overfitting of the ANN were monitored to ensure robustness of the method. The procedure is then applied to a real case scenario and the results are presented in this paper highlighting the main advantages of this approach respect to a conventional use of CFD analysis. Computations of the flow fields are carried out using OpenFOAM with RANS and U-RANS approaches, while the ANN is developed and trained in Python.

In this paper, a systematic CFD work is carried out with the aim to inspect the influence of different cascade parameters on the aerodynamic performance of a reversible fan blade profile. From the obtained results, we derive a meta-model for the aerodynamic properties of this profile. Through RANS simulations of different arrangements in cascades, the aerodynamic performance of airfoils are analyzed as Reynolds number, solidity, pitch angle and angle of attack are varied. The definition of a trial matrix allows the reduction of the minimum number of simulations required. The computed CFD values of lift and drag coefficients, stall margin and the zero-lift angle strongly depend on cascade configuration and differ significantly from standard panel method software predictions. In this work, X-Foil has been used as a benchmark. Particularly, the high influence of pitch angle and solidity is here highlighted, while a less marked dependence from the Reynolds number has been found. Meta-models for lift and drag coefficients have been later derived, and an analysis of variance has improved the models by reducing the number of significant factors. The application of the meta-models to a quasi-3D in-house software for fan performance prediction is also shown. The effectiveness of the derived meta-models is proven through a spanwise comparison of a reversible fan with the X-Foil based and meta-model based versions of the software and 3D fields from a standard CFD simulation. The meta-model improves the software prediction capability, leading to a very low global overestimation of the specific work of the fan.

The integration of rotating machineries in human-populated environments requires to limit noise emissions, with multiple aspects impacting on control of amplitude and frequency of the acoustic signature. This is a key issue to address and when combined with compliance of minimum efficiency grades, further complicates the design of axial fans. The aim of this research is to assess the capability of unsupervised learning techniques in unveiling the mechanisms that concur to the sound generation process in axial fans starting from high-fidelity simulations. To this aim, a numerical dataset was generated by means of LES simulation of a low-speed axial fan. The data set is enriched with sound source computed solving a-posteriori the perturbed convective wave equation (PCWE). First, the instantaneous flow features are associated to the sound sources through correlation matrices and then projected on latent basis to highlight the features with the highest importance. This analysis in also carried out on a reduced dataset, derived by considering two surfaces at 50% and 95% of the blade span. The sampled features on the surfaces are then exploited to train three cluster algorithms based on partitional, density and Gaussian criteria. The cluster algorithms are optimized and their results are compared, with the Gaussian Mixture one demonstrating the highest similarity (>80%). The derived clusters are analyzed, and the role of statistical distribution of velocity and pressure gradients is underlined. This suggests that design choices that affect these aspects may be beneficial to control the generation of noise sources.

Air-cooled condensers (ACCs) are commonly found in power plants working with concentrated solar power or in steam power plants operated in regions with limited water availability. In ACCs, the flow of air is driven toward the heat exchangers by axial fans that are characterized by large diameters and operate at very high mass flow rates with a near-zero static pressure rise. Given the overall requirements in steam plants, these fans are subjected to inflow distortions, unstable operations, and are characterized by high noise emissions. Previous studies show that leading edge bumps in the tip region of axial fans can effectively reduce the sound pressure levels without affecting the static efficiency. Nevertheless, the effects of this treatment in terms of flow patterns and heat exchange in the whole ACC system were not investigated. In this work, the effect of leading edge bumps on the flow patterns is analyzed. Two RANS simulations were carried out using OpenFOAM on a simplified model of the air-cooled condenser. The fans are simulated using a frozen rotor approach. Turbulence modeling relies on the RNG k-epsilon model. The fan is characterized by a diameter of 7.3 m and a 333 m3/s volumetric flow rate at the design point. The presence of the heat exchanger is modeled using a porous medium. The comparison between the flow fields clearly exerts that the modified blade is responsible for the redistribution of radial velocities in the rotor region. This drastically reduces the losses related to the installation of the fan in a real configuration.