The aeroengine control system is a piece of complex thermal machinery which works under high-speed, high-load, and high-temperature environmental conditions over lengthy periods time; it must be designed for the utmost reliability safety to function effectively. consequences sensor faults are often extremely serious. inherent complexity engine structure creates difficulty in establishing accurate mathematical models model-based fault diagnosis. This paper proposes an intelligent diagnosis...

Abstract In the field of Structural Health Monitoring (SHM), complete datasets are fundamental for modal identification analysis and risk prediction. However, data loss due to sensor failures, transmission interruptions, or hardware issues is a common problem. To address this challenge, study develops method combining Variational Mode Decomposition (VMD) Sparrow Search Algorithm (SSA)-optimized Gate Recurrent Unit (GRU) recovering structural response data. The methodology initially employs...

Abstract The purpose of this paper is to suppress the tip leakage vortex and cavitation fuel pump by using casing slot. flow fields blades with different slots were studied numerical simulation under conditions no respectively. results show that loss increases 37 % compared condition without cavitation. Under conditions, optimal scheme c6 scheme, reduced 9.3 %. can be effectively cavitation, slot in a wide range axial positions. After applied, shape blade significantly changed, size reduced,...

Sensor health assessments are of great importance for accurately understanding the an aeroengine, supporting maintenance decisions, and ensuring flight safety. This study proposes intelligent framework based on a physically guided neural network (PGNN) convolutional (CNN) to diagnose sensor faults under dynamic conditions. The strength approach is that it integrates information from physics-based performance models deep learning models. In addition, has structure...

Timely and effective fault diagnosis of sensors is crucial to enhance the working efficiency reliability aeroengine. A new intelligent scheme combining improved pattern gradient spectrum entropy (IPGSE) convolutional neural network (CNN) proposed in this paper, aiming at problem poor effect real-time performance when CNN directly processes one-dimensional time series signals Firstly, raw are converted into spectral images by introducing (PGSE), which used as input CNN, because great...

Improving the efficacy and dependability of aeroengines requires timely effective sensor fault diagnosis. Deep learning-based diagnosis method is a current research hotspot. To overcome some method's existing shortcomings improve reliability diagnosis, this paper proposes novel intelligent framework with higher quality features more classifiers. The proposed plan includes three stages. Firstly, multidomain (time frequency domain features) are extracted to describe sensor's health from...

A high-speed centrifugal pump is the key facility to deliver oil in an aero-engine. The stable operation quite important safety of engine. High-speed stability essentially caused by transient pressure pulsations excited complex flow within pump, which needs be clarified, especially for under a rotating stall condition. In current research, unsteady pulsation and corresponding distribution are analyzed using delayed detached-eddy simulation (DDES) method. Pressure signals extracted monitoring...

This paper aims to tackle the calculation efficiency problem raised in cavitation-flow simulation of aviation centrifugal pump due fading-away interface resulting from dissipation numerics used phase-change control equation for unstructured-grid multiphase flow, and limitation flow time-step whole regimes, vapor-liquid two-phase considering cavitation mass transport is established firstly, modifying momentum by introducing surface tension, adding artificial convective phase solve numerical...

For hybrid reliability analysis under random and multi-super-ellipsoidal variables (HRA-RM) with small failure probability, a combination of kriging subset simulation importance sampling (SSIS) was proposed in this paper. Firstly, to quantify epistemic uncertainties more accurately, the super-ellipsoidal model used replace interval/ellipsoid ones. Besides, real performance function replaced by metamodel, which can be updated sequentially selecting candidate samples from first last levels...

Purpose The purpose of this paper is to improve the hydraulic efficiency without changing overall dimension. blade profile optimization design aero-centrifugal pump based on biharmonic equation surrogate model has been studied. Design/methodology/approach First all, Bezier curves and linear function are used control annular angle distribution stacking under MATLAB platform. Grid independence analysis studied find finest mesh scheme. After precision comparison test data computation fluid...

Aiming at the problems of implicit and highly nonlinear limit state function in process reliability analysis mechanical products, a method structures based on Kriging model improved EGO active learning strategy is proposed. For problem that traditional cannot effectively select points surface region, an By dealing with predicted values sample point absolute assume distribution response remains same, work focus selection moved to vicinity, where are larger prediction variance or close...

In order to study the complex transient flow characteristics of a high-pressure aero-fuel centrifugal pump within its full working envelope, certain type is numerically simulated, in which simulation results are compared with experiment verify effectiveness present method. Then, verified method selected analyze characteristics, time-frequency characteristic pressure pulsation at monitored positions analyzed by using fast fourier transform. addition, unsteady structures studied focusing on...