INTELLIGENT FUSION FOR AEROENGINE WEAR FAULT DIAGNOSIS

Four common oil analysis techniques, including the ferrography analysis （FA）, the spectrometric oil analysis （SOA）, the particle count analysis （PCA）, and the oil quality testing （OQT）, are used to implement the military aeroengine wear fault diagnosis during the test drive process. To improve the precision and the reliability of the diagnosis, the aeroengine wear fault fusion diagnosis method based on the neural networks （NN） and the Dempster-Shafter （D-S） evidence theory is proposed. Firstly, according to the standard value of the wear limit, original data are pre-processed into Boolean values. Secondly, sub-NNs are established to perform the single diagnosis, and their training samples are dependent on experiences from experts. After each sub-NN is trained, diagnosis results are obtained. Thirdly, the diagnosis results of each sub-NN are considered as the basic probability allocation value to faults. The improved D-S evidence theory is applied to the fusion diagnosis, and the final fusion results are obtained. Finally, the method is verified by a diagnosis example.

SIMULATION INVESTIGATION OF AEROENGINE FAULT DIAGNOSIS USING NEURAL NETWORKS

Traditional scheduled maintenance systems are costly, labor intensive, and typically provide noncomprehensive detection and diagnosis of engine faults. The engine monitoring system (EMS) on modern aircrafts has the potential to provide maintenance personnel with valuable information for detecting and diagnosing engine faults. In this paper, an RBF neural network approach is applied to aeroengine gas path fault diagnosis. It can detect multiple faults and quantify the amount of deterioration of the various engine components as a function of measured parameters. The results obtained demonstrate that the accuracy of diagnosis is consistent with practical requirements. The approach takes advantage of the nonlinear mapping feature of neural networks to capture the appropriate characteristics of an aeroengine. The methodology is generic and applicable to other similar plants having high complexity.

Application of Genetic Algorithm to Solving Nonlinear Model of Aeroengines

Solving the nonlinear model of an aeroengine is converted to an optimization problem, and thus some optimization search methods can be used. An approach to solving the nonlinear model of an aeroengine by use of the genetic algorithm (GA) is developed. By comparison with N R algorithm, the accuracy of the values of initial guesses is not required for GA. Especially, the approach developed can be used when no priori knowledges of the values of initial guesses are availabe, and the convergence is improved significantly. GA properly combined with N R algorithm can increase the convergence speed.

3D Measurement and Stereo Reconstruction for Aeroengine Interior Damage

The borescopy inspection problem of aeroengine interior important partdamages such as firebox's burn and corruption, vane' s crack, bump, abrade and concave pit, is aimedat. A new system is developed to carry out 3D measurement and stereo reconstruction of engineinterior damage, in which the borescope of Japanese OLYMPUS Corporation is used as hardware. In thesystem, functions are implemented, such as image collection, camera calibration, imagepreprocessing, stereo matching, 3D measurement and stereo reconstruction. It can provide moredetailed inspection and more accurate estimation of engine interior damages. Finally, an example isused to verify the effectivity of the new method.

Remaining Useful Life Prediction of Aeroengine Based on Principal Component Analysis and One-Dimensional Convolutional Neural Network

In order to directly construct the mapping between multiple state parameters and remaining useful life(RUL),and reduce the interference of random error on prediction accuracy,a RUL prediction model of aeroengine based on principal component analysis(PCA)and one-dimensional convolution neural network(1D-CNN)is proposed in this paper.Firstly,multiple state parameters corresponding to massive cycles of aeroengine are collected and brought into PCA for dimensionality reduction,and principal components are extracted for further time series prediction.Secondly,the 1D-CNN model is constructed to directly study the mapping between principal components and RUL.Multiple convolution and pooling operations are applied for deep feature extraction,and the end-to-end RUL prediction of aeroengine can be realized.Experimental results show that the most effective principal component from the multiple state parameters can be obtained by PCA,and the long time series of multiple state parameters can be directly mapped to RUL by 1D-CNN,so as to improve the efficiency and accuracy of RUL prediction.Compared with other traditional models,the proposed method also has lower prediction error and better robustness.

Application of Small Sample Analysis in Life Estimation of Aeroengine Components

The samples of fatigue life tests for aeroengine components are usually less than 5,so the evaluation of these samples belongs to small sample analysis. The Weibull distribution is known to describe the life data accurately,and the Weibayes method （developed from Bayesian method） expands on the experiential data in the small sample analysis of fatigue life in aeroengine. Based on the Weibull analysis,a program was developed to improve the efficiency of the reliability analysis for aeroengine compgnents. This program has complete functions and offers highly accurate results. A particular turbine disk＇s low cycle fatigue life was evaluated by this program. From the results,the following conclusions were drawn：（a） that this program could be used for the engineering applications,and （b） while a lack of former test data lowered the validity of evaluation results,the Weibayes method ensured the results of small sample analysis did not deviate from the truth.

Prediction Approach to Life on Wing for Civil Aeroengine

To reduce engine maintenance cost and support safe operation, a prediction method of engine life on wing was proposed. This method is a kind of regression model which is a function of the condition monitoring and failure data. Key causes of engine removals were analyzed, and the life limit due to performance deterioration was predicted by proportional hazards model. Then the scheduled removal causes were considered as constraints of engine life to predicte the finai life on wing. Application of the proposed prediction method to the case of CF6-80C2A5 engine fleet in an airline proved its effectiveness.

Aeroengine Nonlinear Sliding Mode Control Based on Artificial Bee Colony Algorithm

For a class of aeroengine nonlinear systems,a novel nonlinear sliding mode controller(SMC)design method based on artificial bee colony(ABC)algorithm is proposed.In view of the strong nonlinearity and uncertainty of aeroengines,sliding mode control strategy is adopted to design controller for the aeroengine.On basis of exact linearization approach,the nonlinear sliding mode controller is obtained conveniently.By using ABC algorithm,the parameters in the designed controller can be tuned to achieve optimal performance,resulting in a closedloop system with satisfactory dynamic performance and high steady accuracy.Simulation on an aeroengine verifies the effectiveness of the presented method.

Fault diagnosis method for an Aeroengine Based on Independent Component Analysis and the Discrete Hidden Markov Model

The vibration signals of an aeroengine are a very important information source for fault diagnosis and condition monitoring. Considering the nonstationarity and low repeatability of the vibration signals, it is necessary to find a corresponding method for feature extraction and fault recognition. In this paper, based on Independent Component Analysis （ICA） and the Discrete Hidden Markov Model （DHMM）, a new fault diagnosis approach named ICA-DHMM is proposed. In this method, ICA separates the source signals from the mixed vibration signals and then extracts features from them, DHMM works as a classifier to recognize the conditions of the aeroengine. Compared with the DHMM, which use the amplitude spectrum of mixed signals as feature parameters, experimental results show this method has higher diagnosis accuracy.

Application study on plasma ignition in aeroengine strut–cavity–injector integrated afterburner

To increase the thrust-weight ratio in next-generation military aeroengines,a new integrated afterburner was designed in this study.The integrated structure of a combined strut–cavity–injector was applied to the afterburner.To improve ignition characteristics in the afterburner,a new method using a plasma jet igniter was developed and optimized for application in the integrated afterburner.The effects of traditional spark igniters and plasma jet igniters on ignition processes and ignition characteristics of afterburners were studied and compared with the proposed design.The experimental results show that the strut–cavity–injector combination can achieve stable combustion,and plasma ignition can improve ignition characteristics.Compared with conventional spark ignition,plasma ignition reduced the ignition delay time by 67 ms.Additionally,the ignition delay time was reduced by increasing the inlet velocity and reducing the excess air coefficient.This investigation provides an effective and feasible method to apply plasma ignition in aeroengine afterburners and has potential engineering applications.

High Cycle Fatigue Life Prediction and Reliability Analysis of Aeroengine Blades

Based on the nonlinear continuum damage model （CDM） developed by Chaboehe, a modified model for high cycle fatigue of TC4 alloy was proposed. Unsymmetrical cycle fatigue tests were conducted on rod specimens at room temperature. Then the material parameters needed in the CDM were obtained by the fatigue tests, and the stress distribution of the specimen was calculated by FE method. Compared with the linear damage model （LDM）, the dam- age results and the life prediction of the CDM show a better agreement with the test and they are more precise than the LDM. By applying the CDM developed in this study to the life prediction of aeroengine blades, it is concluded that the root is the most dangerous region of the whole blade and the shortest life is 58 211 cycles. Finally, the Cox propor- tional hazard model of survival analysis was applied to the analysis of the fatigue reliability. The Cox model takes the covariates into consideration, which include diameter, weight, mean stress and tensile strength. The result shows that the mean stress is the only factor that accelerates the fracture process.

Aeroengine Performance Parameter Prediction Based on Improved Regularization Extreme Learning Machine

Performance parameter prediction technology is the core research content of aeroengine health management,and more and more machine learning algorithms have been applied in the field.Regularized extreme learning machine(RELM)is one of them.However,the regularization parameter determination of RELM consumes computational resources,which makes it unsuitable in the field of aeroengine performance parameter prediction with a large amount of data.This paper uses the forward and backward segmentation(FBS)algorithms to improve the RELM performance,and introduces an adaptive step size determination method and an improved solution mechanism to obtain a new machine learning algorithm.While maintaining good generalization,the new algorithm is not sensitive to regularization parameters,which greatly saves computing resources.The experimental results on the public data sets prove the above conclusions.Finally,the new algorithm is applied to the prediction of aero-engine performance parameters,and the excellent prediction performance is achieved.

Extrapolation for Aeroengine Gas Path Faults with SVM Bases on Genetic Algorithm

Mining aeroengine operational data and developing fault diagnosis models for aeroengines are to avoid running aeroengines under undesired conditions.Because of the complexity of working environment and faults of aeroengines,it is unavoidable that the monitored parameters vary widely and possess larger noise levels.This paper reports the extrapolation of a diagnosis model for 20 gas path faults of a double-spool turbofan civil aeroengine.By applying support vector machine(SVM)algorithm together with genetic algorithm(GA),the fault diagnosis model is obtained from the training set that was based on the deviations of the monitored parameters superimposed with the noise level of 10%.The SVM model(C=24.7034;γ=179.835)was extrapolated for the samples whose noise levels were larger than 10%.The accuracies of extrapolation for samples with the noise levels of 20%and 30%are 97%and 94%,respectively.Compared with the models reported on the same faults,the extrapolation results of the GASVM model are accurate.

Application of Interval Multi-attribute Decision-Making Method to Aeroengine Performance Ranking

In view of the uncertainty of the monitored performance parameters of aeroengines, the fluctuating scope of the monitored infurmation during a period is taken as interval numbers, and the interval multi-attribute decision-making method is employed to predict the performance of aeroengine, The synthetic weights of interval numbers are obtained by calculating deviation degree and possibility degree. As an example of application, 5 performance parameters monitored on 10 CF6 aeroengines of China Eastern Airlines Co., Ltd are adopted as decision attributes to verify the algorithm. The obtained synthetic ranking result shows the effectiveness and rationality of the proposed method in reflecting the performance stares of aeroengins.

Research on Time-Synchronization-Based Test and Control System of Aeroengine

This paper presents a method of NTP-based time synchronization and a strategy of master-slave server structured time synchronization to ensure the test and control system of aeroengine to be time-synchronized. Based on time synchronization, the hierarchy and the integration of the measurement and control system of aeroengine are investigated. In result, our method is successfully applied for multiple front-end tests in a simulative altitude test facility of aeroengine.

Novel high-safety aeroengine performance predictive control method based on adaptive tracking weight

Increasing attention has been attracted to the dynamic performance and safety of advanced performance predictive control systems of the next-generation aeroengine.The latest research demonstrates that Subspace-based Improved Model Predictive Control(SIMPC)can overcome the difficulty in solving the predictive model in MPC/NMPC applications.However,applying constant design parameters cannot maintain consistent control effects in all states.Meanwhile,the designed system relies too much on sensor-measured data,and thus it is difficult to thoroughly validate the safety of the system because of its high complexity.This means that any potential hardware/software faults will endanger the engine.Therefore,this paper first presents a novel nonlinear mapping relationship to adaptively tune the tracking weight online with the change of Power Lever Angle(PLA)and real-time relative tracking error.Thus,without introducing additional design parameters,an Adaptive Tracking Weight-based SIMPC(ATW-SIMPC)controller is designed to improve the control performance in all operating states effectively.Then,a Primary/Backup Hybrid Control(PBHC)strategy with the ATW-SIMPC controller as the primary system and the traditional speed(Nf)controller as the backup system is proposed to ensure safety.The designed affiliated switching controller and the real-time monitor therein can be used to realize reasonable and smooth switching between primary/backup systems,so as to avoid bump transition.The PBHC system switches to the Nf controller when the ATW-SIMPC controller is wrong because of potential hardware/software faults;otherwise,the ATW-SIMPC controller keeps acting on the engine.The main results prove that the ATW-SIMPC controller with the optimal nonlinear mapping relationship,compared with the existing SIMPC controller,uplifts the dynamic control performance by 32%and reduces overshoots to an allowable limit,resulting in a better control effect in full state.The comparison results consistently indicate that the PBHC can guarantee engine safety in occurrence of hardware/software faults,such as sensor/onboard adaptive model faults.The approach proposed is applicable to the design of a model-based engine intelligent control system.

Deep reinforcement learning based active surge control for aeroengine compressors

This study proposes an active surge control method based on deep reinforcement learning to ensure the stability of compressors when adhering to the pressure rise command across the wide operating range of an aeroengine.Initially,the study establishes the compressor dynamic model with uncertainties,disturbances,and Close-Coupled Valve(CCV)actuator delay.Building upon this foundation,a Partially Observable Markov Decision Process(POMDP)is defined to facilitate active surge control.To address the issue of unobservability,a nonlinear state observer is designed using a finite-time high-order sliding mode.Furthermore,an Improved Soft Actor-Critic(ISAC)algorithm is developed,incorporating prioritized experience replay and adaptive temperature parameter techniques,to strike a balance between exploration and convergence during training.In addition,reasonable observation variables,error-segmented reward functions,and random initialization of model parameters are employed to enhance the robustness and generalization capability.Finally,to assess the effectiveness of the proposed method,numerical simulations are conducted,and it is compared with the fuzzy adaptive backstepping method and Second-Order Sliding Mode Control(SOSMC)method.The simulation results demonstrate that the deep reinforcement learning based controller outperforms other methods in both tracking accuracy and robustness.Consequently,the proposed active surge controller can effectively ensure stable operation of compressors in the high-pressure-ratio and high-efficiency region.

Knowledge and data jointly driven aeroengine gas path performance assessment method

Aeroengines,as the sole power source for aircraft,play a vital role in ensuring flight safety.The gas path,which represents the fundamental pathway for airflow within an aeroengine,directly impacts the aeroengine's performance,fuel efficiency,and safety.Therefore,timely and accurate evaluation of gas path performance is of paramount importance.This paper proposes a knowledge and data jointly driven aeroengine gas path performance assessment method,combining Fingerprint and gas path parameter deviation values.Firstly,Fingerprint is used to correct gas path parameter deviation values,eliminating parameter shifts caused by non-component performance degradation.Secondly,coarse errors are removed using the Romanovsky criterion for short-term data divided by an equal-length overlapping sliding window.Thirdly,an Ensemble Empirical Mode Decomposition and Non-Local Means(EEMD-NLM)filtering method is designed to“clean”data noise,completing the preprocessing for gas path parameter deviation values.Afterward,based on the characteristics of gas path parameter deviation values,a Dynamic Temporary Blended Network(DTBN)model is built to extract its temporal features,cascaded with Multi-Layer Perceptron(MLP),and combined with Fingerprint to construct a Dynamic Temporary Blended AutoEncoder(DTB-AutoEncoder).Eventually,by training this improved autoencoder,the aeroengine gas path multi-component performance assessment model is formed,which can sufficiently decouple the nonlinear mapping relationship between aeroengine gas path multi-component performance degradation and gas path parameter deviation values,thereby achieving the performance assessment of engine gas path components.Through practical application cases,the effectiveness of this model in assessing the aeroengine gas path multi-component performance is verified.

Structural design of aeroengine radiators:State of the art and perspectives

Structural modularization,lightweight and functional integration are the urgent devel-opment directions for next generation high-performance aeroengines.Heat concentration during aeroengine operation would lead to local high temperature,which tremendously negative impacts on aeroengine structural life and performance.Therefore,the design and optimization of radiator structures are significant for the efficiency and reliability of aeroengine.The structural geometry design and layout optimization of radiators is promising to improve the heat dissipation efficiency and reduce aerodynamic loss.The purpose of this study is to investigate the state of the art and perspectives of aeroengine radiator structural design by a comprehensive literature review.The main contents involve the review on the structural design and layout optimization technologies of radiator structures,the analyses of the structural features,design theory and methods of existed radiator structures,the induction of the theory and method of different radiators structural opti-mization design,and the discussion on the application perspectives of advanced structures in aeroengine radiators,the report on the current challenges and development directions of the design of radiator structures,including smart materials,lattice structures,variable structures,advanced optimization theories and methods,heat dissipation methods and so forth.The efforts of this study are promising to support the high-performance and lightweight design of aeroengine structures besides radiators,and thermal management system.

Pneumatic pressure control based on improved NMPC and its application to aeroengine surge simulation

In the semi-physical simulation of aeroengines,using the pneumatic pressure servo control technology to provide realistic pneumatic excitation to the sensors and electronic controller can improve the confidence of the simulation and reduce the test cost and risk.However,the existing methods could not satisfy the precise simulation of large-amplitude and high-frequency pulsating pressure during aeroengine surge.In this paper,a pneumatic pressure control system with asymmetric groups of the High-Speed on–off Valve(HSV)is designed,and an Improved Nonlinear Model Predictive Control(INMPC)method is proposed.First,the volumetric flow characteristics of HSV are tested and analyzed with Pulse Width Modulation(PWM)signal input.Then,a simplified HSV model with the volume flow characteristic correction is developed.Based on these,an integrated model for the whole system is further established and used as the prediction model in INMPC.To improve the computational speed of the rolling optimization process,the mapping scheme from control signal to PWM duty cycle of HSVs and the objective function with exterior penalty function are designed.Finally,the random step,sinusoidal and real engine surge data are set as the reference pressure in multiple comparative experiments to verify the effectiveness of the pressure tracking system.