In this work, the area-averaged film cooling effectiveness (AAFCE) on a gas turbine blade leading edge was predicted by employing an artificial neural network (ANN) using as input variables: hole diameter, injection angle, blowing ratio, hole and columns pitch. The database used to train the network was built using computational fluid dynamics (CFD) based on a two level full factorial design of experiments. The CFD numerical model was validated with an experimental rig, where a first stage blade of a gas turbine was represented by a cylindrical specimen. The ANN architecture was composed of three layers with four neurons in hidden layer and Levenberg-Marquardt was selected as ANN optimization algorithm. The AAFCE was successfully predicted by the ANN with a regression coefficient R²<0.99 and a root mean square error RMSE=0.0038. The ANN weight coefficients were used to estimate the relative importance of the input parameters. Blowing ratio was the most influential parameter with relative importance of 40.36 % followed by hole diameter. Additionally, by using the ANN model, the relationship between input parameters was analyzed.

The performance of the porous gas bearing depends on the geometric characteristics, material, fluid properties, and the properties of the porous media, which is a restrictor that controls the gas flow. Its application in industrial environments must support higher loads, higher supply pressure, and, consequently, higher pressure in the lubricant fluid film. Because porous media has a relatively low elastic modulus, it is necessary to consider its deformation when designing porous gas bearings. The design of porous gas bearings is a multi-objective problem in engineering because the optimization objectives commonly are to maximize the load capacity or static stiffness coefficient and minimize the airflow; these objectives conflict. This work presents a multi-objective optimization algorithm based on the nature-inspired Flower Pollination Algorithm enhanced with Non-Dominated Sorting Genetic Algorithm II. The algorithm is applied to optimize the design of a porous gas bearing, maximizing the resultant force and the static stiffness coefficient and minimizing the airflow. The results indicate a better performance of the Multi-Objective Flower Pollination Algorithm than the Multi-Objective Cuckoo Search. The results show a relatively short running time of 6 min for iterations and a low number of iterations of 50.

This paper presents a test rig for evaluation of gas thrust foil bearings (GTFBs) and details measurements of load capacity conducted with a commercial GTFB comprising a single 360 deg, 0.127 mm thick top foil divided into six continuous arc segments with a formed taper of 0.102 mm. Coated with Teflon®, the top foil rests on a stack of shims above six underspring structures, each comprising three strips of bump foils, 0.102 mm thick. Measurements include the applied static load and break-away torque, rotor speed, bearing axial displacements at three locations 120 deg apart, the flow of a cooling stream, and temperatures in and out of the bearing. Static load tests produce the underspring deformation and a dry-sliding friction coefficient f ∼ 0.12. The underspring is rather flexible though quickly hardening for specific load (P*) > 25 kN/m2 to reach an ultimate deformation of ∼0.320 mm. Measurements at 30 krpm (OD surface speed = 111 m/s) and increasing static loads produce bearing displacements that parallel the displacements without shaft rotation. Most importantly, the difference between displacements approaches ∼0.060 mm for P* > 45 kN/m2. The test bearing operated safely to P* = 90 kN/m2 and failed at P* = 120 kN/m2. When heavily loaded, the GTFB is significantly stiffer than when lightly loaded. Designed for easiness of installation and operation, the test bearing demonstrated a stable and repeatable performance with likely a uniform gap or film thickness even for the largest loads applied.