STUDY ON TURBOMACHINERY PERFORMANCE PREDICTION WITH NEURAL NETWORKS

Traditional methods for performance prediction of a turbomachinery are usually based on certain computations from a set of data obtained in limited experiment measurements of the machine, or the machinemodels. Since the computational (mathematical) models used in such performance prediction are often crude, most of the predicted results are only correct in very small ranges around the known data points. Beyond the limited ranges, the accuracy of the resultant predictions decrease abruptly. Therefore, an alternative approach, neural network technique, is studied for performance prediction of turbomachinery. The new approach has been applied to two typical performance prediction cases to verify its feasibility and reliability.

Shape Optimization of the Turbomachine Channel by a Gradient Method - Accuracy Improvement

An algorithm of the gradient method of the channel shape optimization has been built on the basis of 3D equations of mass, momentum and energy conservation in the fluid flow. The gradient of the functional that is posed for minimization has been calculated by two methods, via sensitivities and - for comparison - by the finite difference approximation. The equations for sensitivities have been generated through a differentiate-then-discretize approach. The exemplary optimization of the blade shape of the centrifugal compressor wheel has been carried out for the inviscid gas flow governed by Euler equations with a non-uniform mass flow distribution as the inlet boundary condition. Mixing losses have been minimized downstream the outlet of the centrifugal wheel in this exemplary optimization. The results of the optimization problem accomplished by the two above-mentioned methods have been presented. In the case sparse grids have been used, the method with the gradient approximated by finite differences has been found to be more consistent. The discretization accuracy has turned out to be crucial for the consistency of the gradient method via sensitivities.

A Self-Learning Diagnosis Algorithm Based on Data Clustering

The article describes an approach to building a self-learning diagnostic algorithm. The self-learning algorithm creates models of the object under consideration. The models are formed periodically through a certain time period. The model includes a set of functions that can describe whole object, or a part of the object, or a specified functionality of the object. Thus, information about fault location can be obtained. During operation of the object the algorithm collects data received from sensors. Then the algorithm creates samples related to steady state operation. Clustering of those samples is used for the functions definition. Values of the functions in the centers of clusters are stored in the computer’s memory. To illustrate the considered approach, its application to the diagnosis of turbomachines is described.

Aeroelastic simulation of the first 1.5-stage aeroengine fan at rotating stall

A massive parallel aeroelastic simulation platform has been built to investigate the first1.5-stage fan of an aeroengine at rotating stall.The Computational Fluid Dynamics(CFD)solver and Computational Structural Dynamics(CSD)solver are coupled directly by non-matching mesh interfaces.The unsteady rotor/stator interaction is solved by the Sliding Mesh Interface method.The original rotor blades are shrouded by the midspan shrouds.An unshrouded fan is also created to investigate the effects of the midspan shrouds.Both the shrouded fan and unshrouded fan have stable aeroelasticity at the designed state.At rotating stall,the stalled region rotates at 30%of the rotor speed on the absolute reference frame.The energy spectrum of the rotating stalled flow is measured quantitatively.It shows that the first two order excitations are much stronger than the higher order excitations.In the flow of rotating stall,the fifth backward travelling wave mode of shrouded fan is resonated by the fifth excitation of the rotational stalled flow because the rotational speed of the stalled region coincides with the modal rotational speed,while for the unshrouded fan,the first bending mode is resonated by the second excitation of the rotational stalled flow,forming two waves in the circumference of the annulus blades.At rotating stall,the vibration of the shrouded blades is still under control but the vibration of the unshrouded blades is diverged and out of control.A novel tool,i.e.,resonance map,is proposed to predict the resonance.It provides a perspective to explain the effects of midspan shrouds at a theoretical level,and it would also be helpful in the structural design of blades.

FINITE ELEMENT ANALYSIS OF THE FLOW INDUCED BY ROTATING BLADES IN AN INCOMPRESSIBLE VISCOUS FLUID

Aerodynamic loads on a multi-bladed helicopter rotor in hovering flight were calculated by solving the three-dimensional incompressible Navier-Stokes equations. The rotor wake effects were accounted by the correction of local geometric angle of attack according to a free-wake modeling in addition to an empirical modification for the tip flow effect. The validity and efficiency of the present method were verified by the comparisons between numerical results and experimental data.

HYDRODYNAMIC CHARACTERISTICS AND OPTIMIZATION DESIGN OF EFFICIENT AXIAL-FLOW BLAST WITH LOW NOISE AND ENERGY SAVING

Based on the demand on efficient axial-flow blast with low noise and energy saving, a blade was designed through the application of the unequal work distribution principle and the exponential twisted camber was used to shape blades. Then, the hydrodynamic characteristics of blades were studied and the strengths and vibrations of blades and hydro-dynamic noise of blast were analyzed. Furthermore, the software of optimization design of axial-flow blast was developed. Finally, the HMF-T40No.20 axial-flow blast used in large textile conditioner system of cotton spinning industry was designed, which could meet the required total safety and environmental requirements as the corresponding test demonstrates. The study is beneficial to designing axial-flow blast.

OPTIMAL HYDRAULIC DESIGN AND CAD APPLICATIONS OF AXIAL FLOW HYDRAULIC TURBINE′S RUNNER

Method of optimal hydraulic design and CAD application of runner blades of axial-flow hydraulic turbines are discussed on the basis of optimization principle and CAD technique in this paper. Based on the theory of fluid dynamics, the blade's main geometrical parameter, working parameters and performances index of the blades and the relationship between them are analysed, and the mathematical model of optimal hydraulic design of axial-flow runners has been established. Through nonlinear programming, the problems can be solved. By making use of the calculation geometry and computer graphics, the distribution method of the singular points, and an CAD applied software, an optimal hydraulic design are presented.

Optimization Method for Turbine Airfoil Designing Using Genetic Algorithms,CFD and Parallel Computing

An optimization method to design turbine airfoils using a Genetic Algorithm (GA) design shell coupled directly with a viscous CFD (Computational Fluid Dynamics) analysis code is proposed in this paper. The blade geometry is parameterized and the optimization method is used to search for a blade geometry that will minimize the loss in the turbine cascade passage. The viscous flow prediction code is verified by the experimental data of cascade, which is typical for a gas turbine rotor blade section. A comparative study of the blades designed by the optimization technique and the original one is presented[