An Effective Fault Diagnosis Method for Aero Engines Based on GSA-SAE

The health status of aero engines is very important to the flight safety.However,it is difficult for aero engines to make an effective fault diagnosis due to its complex structure and poor working environment.Therefore,an effective fault diagnosis method for aero engines based on the gravitational search algorithm and the stack autoencoder(GSA-SAE)is proposed,and the fault diagnosis technology of a turbofan engine is studied.Firstly,the data of 17 parameters,including total inlet air temperature,high-pressure rotor speed,low-pressure rotor speed,turbine pressure ratio,total inlet air temperature of high-pressure compressor and outlet air pressure of high-pressure compressor and so on,are preprocessed,and the fault diagnosis model architecture of SAE is constructed.In order to solve the problem that the best diagnosis effect cannot be obtained due to manually setting the number of neurons in each hidden layer of SAE network,a GSA optimization algorithm for the SAE network is proposed to find and obtain the optimal number of neurons in each hidden layer of SAE network.Furthermore,an optimal fault diagnosis model based on GSA-SAE is established for aero engines.Finally,the effectiveness of the optimal GSA-SAE fault diagnosis model is demonstrated using the practical data of aero engines.The results illustrate that the proposed fault diagnosis method effectively solves the problem of the poor fault diagnosis result because of manually setting the number of neurons in each hidden layer of SAE network,and has good fault diagnosis efficiency.The fault diagnosis accuracy of the GSA-SAE model reaches 98.222%,which is significantly higher than that of SAE,the general regression neural network(GRNN)and the back propagation(BP)network fault diagnosis models.

Solution of idle LBO problem for high FAR aero combustor

The paper sheds light on the idle lean blow off(LBO)problem for high fuel air ratio(FAR)com⁃bustor,which is impossible to be addressed with traditional aero combustor design.A significant improvement in aero combustor design is required to resolve the idle LBO issue.The authors detailed a practical and efficient solu⁃tion,which not only solved the idle LBO issue but also defined the aero-thermal design for high-FAR combustor.The design will usher in a new era of aero combustor.

RELIABILITY ANALYSIS FOR AN AERO ENGINE TURBINE DISK UNDER LOW CYCLE FATIGUE CONDITION

Reliability analysis methods based on the linear damage accumulation law (LDAL) and load-life interference model are studied in this paper. According to the equal probability rule, the equivalent loads are derived, and the reliability analysis method based on load-life interference model and recurrence formula is constructed. In conjunction with finite element analysis (FEA) program, the reliability of an aero engine turbine disk under low cycle fatigue (LCF) condition has been analyzed. The results show the turbine disk is safety and the above reliability analysis methods are feasible.

Xi'an Aero Engine Corporation

The value of the exports of the Xi’anAero Engine Corporation wasUS＄15.45 million in 1995,40% upfrom 1994 and the highest figure among allthe production enterprises in the Chineseaviation industry. The corporation is a large enterprisefor the research and manufacture of multi-type aero engines.Since the early 1980s.ithas established cooperation and trade relationswith the the US GE Corporation,the AmericanUnited Technologies Corporation,the USPW Corporation,the British LL Company,the Canadian PW Corporation and a leadingFrench aero engine company.It has undertakenproduction of airplane engines and otherparts in 300 projects with them.By the endof 1995.it had earned US＄65 million for

Effects of Tightening Torque on Dynamic Characteristics of Low Pressure Rotors Connected by a Spline Coupling

A rotor dynamic model is built up for investigating the effects of tightening torque on dynamic characteristics of low pressure rotors connected by a spline coupling.The experimental rotor system is established using a fluted disk and a speed sensor which is applied in an actual aero engine for speed measurement.Through simulating calculation and experiments,the effects of tightening torque on the dynamic characteristics of the rotor system connected by a spline coupling including critical speeds,vibration modes and unbalance responses are analyzed.The results show that when increasing the tightening torque,the first two critical speeds and the amplitudes of unbalance response gradually increase in varying degrees while the vibration modes are essentially unchanged.In addition,changing axial and circumferential positions of the mass unbalance can lead to various amplitudes of unbalance response and even the rates of change.

A Hydrodynamic Model for Dimpled Mechanical Gas Seal Considering Interaction Effect

The mechanical gas seal of aero engine has to face the problems of high wear rate and short lifetime.Surface texture has shown beneficial effects over the tribological characteristics.Here,a hydrodynamic model for dimpled annular area of mechanical gas seal considering the″interaction effect″between adjacent dimples is developed based on the Reynolds equation.Different multi-row columns are chosen and the dimensionless pressure in radial and circumferential directions is calculated.The results indicate that the″interaction effect″is more obvious in the circumferential direction than in the radial direction,even when the area and depth of the dimples are same.Moreover,for the 5×5column,the dimensionless average pressure considering the″interaction effect″increases by45.41% compared with the 1×5column.Further analysis demonstrates that the model with the 5×5column can be more reasonable with the consideration of reducing the calculation error caused by boundary conditions to investigate the hydrodynamic effect for dimpled mechanical gas seal.

Numerical and experimental investigation of plasma plume deflection with MHD flow control

This paper presents a composite magneto hydrodynamics（MHD） method to control the lowtemperature micro-ionized plasma flow generated by injecting alkali salt into the combustion gas to realize the thrust vector of an aeroengine.The principle of plasma flow with MHD control is analyzed.The feasibility of plasma jet deflection is investigated using numerical simulation with MHD control by loading the User-Defined Function model.A test rig with plasma flow controlled by MHD is established.An alkali salt compound with a low ionization energy is injected into combustion gas to obtain the low-temperature plasma flow.Finally,plasma plume deflection is obtained in different working conditions.The results demonstrate that plasma plume deflection with MHD control can be realized via numerical simulation.A low-temperature plasma flow can be obtained by injecting an alkali metal salt compound with low ionization energy into a combustion gas at 1800–2500 K.The vector angle of plasma plume deflection increases with the increase of gas temperature and the magnetic field intensity.It is feasible to realize the aim of the thrust vector of aeroengine by using MHD to control plasma flow deflection.

Parameterization Modeling of a Gas Turbine Coverplate

In order to reduce product development cycle time, aerospace companies tend to develop various correlations integrating geometric and performance parameters. This paper covers the development of a parameterization modeling, to be used in the preliminary design phase, for the turbine cover plate of an aero-engine. The parameterization modeling of the turbine cover plate is achieved by using commercial CAD （computer aided design） software processing in batch mode. Two main approaches are presented the outer face and the skeleton models. These models can then be integrated into an iterative process for designing optimal shapes. Both models are capable of reproducing existing cover plate with reasonable accuracy in relatively shorter time periods. However, the skeleton approach provides probably the best results in terms of flexibility and accuracy, but increases programming complexity and requires greater run times.

Numerical simulation research on multiphase flow of aviation centrifugal pump based on OpenFOAM

This paper aims to tackle the calculation efficiency problem raised in the cavitation-flow simulation of the aviation centrifugal pump due to the fading-away interface resulting from the dissipation of numerics used in the phase-change control equation for unstructured-grid multiphase flow,and due to the limitation of flow time-step in whole flow regimes,the control equation of vapor–liquid two-phase flow considering cavitation mass transport is established firstly,modifying the momentum equation by introducing the surface tension,and adding the artificial convective flow to the phase equation to solve the numerical dissipation problem.Secondly,in consideration of the local time step principle and based on the multi-dimensional general limiter algorithm with explicit solutions under the OpenFOAM platform,a solution method of steady-state VOF (Volume of Fluid) model considering cavitation two-phase change is constructed,and the feasibility of this method is verified by NACA hydrofoil and NASA flat plate inducer.Finally,based on the platform developed,the cavitation performance of an aviation centrifugal pump inducer is analyzed.The research results show that the error of the calculated cavitation pressure distribution for NACA hydrofoil between the simulation test and the experimental-test is less than 5%,and the maximum error of calculated cavitation number at pump head dropping for NASA high-speed flat plate inducer between the simulation test and the experimental-test is 2.1%.The cavitation area observed in the simulation test is the same as that obtained in the high-speed photography test.Based on the OpenFOAM simulation method,the position of pump head dropping of the fuel centrifugal pump can be accurately captured.The error of the calculated cavitation number at pump head dropping between the simulation test and the experimental test is about 3.7%,showing high calculation accuracy.

A review of high‐velocity impact on fiber‐reinforced textile composites: Potential for aero engine applications

Considerable research has indicated that fiber‐reinforced textile composites are significantly beneficial to the aerospace industry,especially aero engines,due to their high specific strength,specific stiffness,corrosion resistance,and fatigue re-sistance.However,damage caused by high‐velocity impacts is a critical limitation factor in a wide range of applications.This paper presents an overview of the development,material characterizations,and applications of fiber‐reinforced textile composites for aero engines.These textile composites are classified into four ca-tegories including two‐dimensional(2D)woven composites,2D braided composites,3D woven composites,and 3D braided composites.The complex damage me-chanisms of these composite materials due to high‐velocity impacts are discussed in detail as well.

Development of acoustic liner in aero engine: A review

Noise reduction for aircraft engine has attracted great concern due to the strict noise control regulation nowadays. Conventional perforated sheet-over-honeycomb acoustic liners have been widely used to attenuate turbofan engine noise. To dampen the broadband noise and resist the harsh service conditions with high temperature and pressure in modern turbofan engine,new acoustic liner concepts are proposed and evaluated in the latest decade. In this review,available studies regarding the recent development of liners are gathered. The paper starts with the introduction of acoustic absorption mechanism of local-reacting and extended-reacting liners. The progress of novel passive liners(e.g.,mesh-cap liner,variable-depth liner,metal foam liner,hybrid liner,etc.) is summarized. Furthermore,adaptive liners with tunable geometry dimension or bias flow are illustrated in details.Metamaterial is also mentioned as a hot candidate in the next generation of acoustic liners. Finally,this review identifies benefits and some technical challenges with the goal of unveiling the potential of novel acoustic liner technologies in aero engine.

Optimal location and shape definition of elliptical ventilation openings on aero engine turbine rotors with stress concentration effect

The aero engine turbine rotors are under strong centrifugal load and the highest thermal load.The ventilation openings on the rotors are inevitable,because air flow need to pass through them to cool the temperatures down and keep the air pressure balanced in internal aero engine.The ventilation openings will lead to stress concentration effect.In this paper,the stress concentration factor of elliptical opening on rotating disc is deduced by superposition method.How to define the optimal location and shape of the elliptical opening on rotating disc to decrease the stress concentration effect has been investigated specifically.The reliability and accuracy of the theoretical deviation process is verified by Finite Element Method(FEM).The process of how to obtain the optimal location of the elliptical ventilation opening with particular shape on turbine sealing disc is described as an engineering application case.The investigation provides sufficient theoretical support for optimal location and shape definition of elliptical ventilation opening on aero engine rotors with stress concentration effect by pure mechanics consideration.

Research on an Arc Air-Lubricating Oil Radiator Equipped in Internal Surface of Air Intake for the Aero Engine

Due to huge-power aircraft development and more electronic devices applied onboard,high heat flow density and uneven thermal distribution are becoming new problems.One new try is adding an air-lubricating oil radiator as the secondary cooling component but there are still few reports on its research.Therefore,this paper proposes a newly-design plate-fin air-lubricating oil radiator different from tube-fin or shell-tube conventionally used in previous engine system.This radiator is arc,and equipped in internal surface of air intake.Numerical and experimental analyses were carried out on fin performance.Their results agreed well with average error of 13%on thermal resistance.Then heat and flow behaviors of oil side were presented with different structures and sizes of flowing passage.According to all research,optimized radiator is gained with fin spacing of 3.76 mm,fin thickness of 2 mm,single flowing path with width of 13 mm and gradient inlet and outlet.Its heat dissipation of 28.35 k W and pressure loss of 2.2 MPa can meet actual working requirements.The research proves an air-lubricating oil radiator with arc structure and layout mode of internal surface to be feasible,which is a new but efficient cooling scheme and can lead to an innovative but wide use in modern aircrafts.

A Fast Method to Calculate the Oil Droplet Velocity in Aero Engine Bearing Chambers

The oil droplet velocity in an aero engine bearing chamber can determine the initial film state which is the fundament for lubrication design and heat analysis. This paper studied the droplet motion in a respective aero engine bearing chamber and obtained a fast method to calculate the droplet velocity by an analytical method. Comparing the velocity results calculated by the fast method with those from the literatures by the numerical method under different operating conditions, the method proposed in this paper is confirmed to be fast and reliable. The effects of operating conditions on droplet velocity are obtained at the same time. This study contribute to follow-up research work on droplet deposition properties in aero engine bearing chambers

Research on disruptive design pre-identification in the preliminary design phase of aero engine flow pass multidisciplinary optimization

In aero engine design, determining whether the preliminary design will have disruptive effects on the detailed design is the key to multidisciplinary design optimization in the preliminary design stage. In order to adapt to the non-orthogonal parameter value range caused by the selfconstrained parametric modeling method, a non-orthogonal space mapping method that maps the optimal Latin hypercube sampling points of the traditional orthogonal design space to the non-orthogonal design space is proposed. Based on the logical regression method in machine learning field, a kind of feasible domain boundary identification method is employed to identify whether the sample spatial response meets the relevant criteria. The method proposed in this paper is used to identify and analyze the key technologies of the high-pressure turbine mortise joint structure. It is found that the preliminary design of the aero engine may lead to the failure to obtain a mortise joint structure meeting the design requirements in the detailed design stage. The mortise joint structure needs to be pre-optimized in the preliminary design stage.

Conditional Generative Adversarial Networks for modelling fuel sprays

In this study, the probabilistic, data driven nature of the generative adversarial neural networks (GANs)was utilized to conduct virtual spray simulations for conditions relevant to aero engine combustors. Themodel consists of two sub-modules: (i) an autoencoder converting the variable length droplet trajectories intofixed length, lower dimensional representations and (ii) a Wasserstein GAN that learns to mimic the latentrepresentations of the evaporating droplets along their lifetime. The GAN module was also conditioned withthe injection location and the diameters of the droplets to increase the generalizability of the whole framework.The training data was provided from highly resolved 3D, transient Eulerian–Lagrangian, large eddy simulationsconducted with OpenFOAM. Neural network models were created and trained within the open source machinelearning framework of PyTorch. Predictive capabilities of the proposed method was discussed with respect tospray statistics and evaporation dynamics. Results show that conditioned GAN models offer a great potentialas low order model approximations with high computational efficiency. Nonetheless, the capabilities of theautoencoder module to preserve local dependencies should be improved to realize this potential. For the currentcase study, the custom model architecture was capable of conducting the simulation in the order of secondsafter a day of training, which had taken one week on HPC with the conventional CFD approach for the samenumber of droplets (200,000 trajectories).