Aero-Engine Surge Fault Diagnosis Using Deep Neural Network

Deep learning techniques have outstanding performance in feature extraction and modelfitting.In thefield of aero-engine fault diagnosis,the intro-duction of deep learning technology is of great significance.The aero-engine is the heart of the aircraft,and its stable operation is the primary guarantee of the aircraft.In order to ensure the normal operation of the aircraft,it is necessary to study and diagnose the faults of the aero-engine.Among the many engine fail-ures,the one that occurs more frequently and is more hazardous is the wheeze,which often poses a great threat toflight safety.On the basis of analyzing the mechanism of aero-engine surge,an aero-engine surge fault diagnosis method based on deep learning technology is proposed.In this paper,key sensor data are obtained by analyzing different engine sensor data.An aero-engine surge data-set acquisition algorithm(ASDA)is proposed to sample the fault and normal points to generate the training set,validation set and test set.Based on neural net-work models such as one-dimensional convolutional neural network(1D-CNN),convolutional neural network(RNN),and long-short memory neural network(LSTM),different neural network optimization algorithms are selected to achieve fault diagnosis and classification.The experimental results show that the deep learning technique has good effect in aero-engine surge fault diagnosis.The aero-engine surge fault diagnosis network(ASFDN)proposed in this paper achieves better results.Through training,the network achieves more than 99%classification accuracy for the test set.

Fault Diagnosis for Aero-engine Applying a New Multi-class Support Vector Algorithm

Hierarchical Support Vector Machine （H-SVM） is faster in training and classification than other usual multi-class SVMs such as ＂1-V-R＂and ＂1-V-1＂. In this paper, a new multi-class fault diagnosis algorithm based on H-SVM is proposed and applied to aero-engine. Before SVM training, the training data are first clustered according to their class-center Euclid distances in some feature spaces. The samples which have close distances are divided into the same sub-classes for training, and this makes the H-SVM have reasonable hierarchical construction and good generalization performance. Instead of the common C-SVM, the v-SVM is selected as the binary classifier, in which the parameter v varies only from 0 to 1 and can be determined more easily. The simulation results show that the designed H-SVMs can fast diagnose the multi-class single faults and combination faults for the gas path components of an aero-engine. The fault classifiers have good diagnosis accuracy and can keep robust even when the measurement inputs are disturbed by noises.

Aero-engine fault diagnosis applying new fast support vector algorithm

A new fast learning algorithm was presented to solve the large-scale support vector machine ( SVM ) training problem of aero-engine fault diagnosis.The relative boundary vectors ( RBVs ) instead of all the original training samples were used for the training of the binary SVM fault classifiers.This pruning strategy decreased the number of final training sample significantly and can keep classification accuracy almost invariable.Accordingly , the training time was shortened to 1 / 20compared with basic SVM classifier.Meanwhile , owing to the reduction of support vector number , the classification time was also reduced.When sample aliasing existed , the aliasing sample points which were not of the same class were eliminated before the relative boundary vectors were computed.Besides , the samples near the relative boundary vectors were selected for SVM training in order to prevent the loss of some key sample points resulted from aliasing.This can improve classification accuracy effectively.A simulation example to classify 5classes of combination fault of aero-engine gas path components was finished and the total fault classification accuracy reached 96.1%.Simulation results show that this fast learning algorithm is effective , reliable and easy to be implemented for engineering application.

An Inter-Shaft Bearing Fault Diagnosis Dataset from an Aero-Engine System

In this paper,the aero-engine test with inter-shaft bearing fault is carried out,and a dataset is proposed for the first time based on the vibration signal of rotors and casings.First,a test rig based on a real aero-engine is established,driven by motors and equipped with a lubricating system.Then,the aero-engine is disassembled and assembled following the specification process,and the inter-shaft bearing with artificial fault is replaced.Next,the aero-engine test is conducted at 28 groups of high-and low-pressure speeds.Six measuring points are arranged,including two displacement sensors to test the displacement vibration signals of the low-pressure rotor and four acceleration sensors to test the acceleration vibration signals of the casing.The test results are integrated into an inter-shaft bearing fault dataset.Finally,based on the dataset in this paper,frequency spectrum,envelope spectrum,CNN,LSTM,and TST are used for fault diagnosis,and the results are compared with those of CWRU and XJTU datasets.The results show that the characteristic fault frequency cannot be found directly in the spectrum and envelope spectrum corresponding to this paper’s dataset but in CWRU and XJTU datasets.Using CNN,LSTM,and TST for fault diagnosis of the dataset in this paper,the accuracy is 83.13%,85.41%,and 71.07%,respectively,much lower than the diagnosis results of CWRU and XJTU datasets.It can be seen that the dataset in this paper is closer to the actual fault diagnosis situation and is a more challenging dataset.This dataset provides a new benchmark for the validation of fault diagnosis methods.Mendeley data:https://github.com/HouLeiHIT/HIT-dataset.

Research on Early Fault Self-Recovery Monitoring of Aero-Engine Rotor System

In order to increase robustness of the AERS (Aero-engine Rotor System) and to solve the problem of lacking fault samples in fault diagnosis and the difficulty in identifying early weak fault, we proposed a new method that it not only can identify the early fault of AERS but also it can do self-recovery monitoring of fault. Our method is based on the analysis of the early fault features on AERS, and it combined the SVM (Support Vector Machine) with the stochastic resonance theory and the wavelet packet decomposition and fault self-recovery. First, we zoom the early fault feature signals by using the stochastic resonance theory. Second, we extract the feature vectors of early fault using the multi-resolution analysis of the wavelet packet. Third, we input the feature vectors to a fault classifier, which can be used to identify the early fault of AERS and carry out self-recovery monitoring of fault. In this paper, features of early fault on AERS, the zoom of early fault characteristics, the extraction method of early fault characteristics, the construction of multi-fault classifier and way of fault self-recovery monitoring are studied. Results show that our method can effectively identify the early fault of AERS, especially for identifying of fault with small samples, and it can carry on self-recovery monitoring of fault.

Gas Path Fault Tolerant Control of Aero-Engine Based on On-Board Model

A fault tolerant control method is proposed in this paper for a turbofan engine gas path degradation through the full flight envelope. A Quantum-behaved Particle Swarm Optimization(QPSO) algorithm is applied to obtain engine inputs adjustments, which contribute to construct off-line performance accommodation interpolation schedules. With a double closed-loop control system structure, command control is corrected based on real-time fault diagnostic results. Simulations indicate that fault tolerant control could reduce thrust and stall margin loss effectively in gas path faults.

VIBRATION CHARACTERISTIC INVESTIGATION OF COUNTER-ROTATING DUAL-ROTOR IN AERO-ENGINE

Two methods for vibration characteristic investigation of the counter-rotating dual-rotors in an aero-en- gine are put forward. The two methods use DAMP tool on the MSC. NASTRAN platform and develope the re- solving sequence. Vibration characteristics of a turbofan engine are analyzed by using the two methods. Com- pared with results calculated using transfer matrix method and test results, the two methods are valuable and have great potential in practical applications for vibration characteristic investigation of aero-engines with high thrust-weight ratio.

MAINTENANCE LEVEL DECISION OF AERO-ENGINE BASED ON VPRS THEORY

An aero-engine is a typically repairable and complex system and its maintenance level has a close relationship with the maintenance cost. The inaccurate measurement for the maintenance level of an aero-engine can induce higher overhaul maintenance costs. Variable precision rough set （VPRS） theory is used to determine the maintenance level of an aero-engine. According to the relationship between condition information and performance parameters of aero-engine modules, decision rules are established for reflecting the real condition of an aeroengine when its maintenance level needs to be determined. Finally, the CF6 engine is used as an example to illustrate the method to be effective.

APPLICATION OF HYBRID AERO-ENGINE MODEL FOR INTEGRATED FLIGHT/PROPULSION OPTIMAL CONTROL

The real-time capability of integrated flight/propulsion optimal control （IFPOC） is studied. An appli- cation is proposed for IFPOC by combining the onboard hybrid aero-engine model with sequential quadratic pro- gramming （SQP）. Firstly, a steady-state hybrid aero-engine model is designed in the whole flight envelope with a dramatic enhancement of real-time capability. Secondly, the aero-engine performance seeking control including the maximum thrust mode and the minimum fuel-consumption mode is performed by SQP. Finally, digital simu- lations for cruise and accelerating flight are carried out. Results show that the proposed method improves real- time capability considerably with satisfactory effectiveness of optimization.

RESEARCH AND DEVELOPMENT OF HIGH TEMPERATURESTRUCTURAL MATERIALS FOR AERO-ENGINE APPLICATIONS

The status of research, development of superalloys and materials processing ＆ fabrication technologies for aero-engine applications in China Aviation Industry, with an emphasis on recent achievements at BIAM including directionally solidified and single crystal superalloys for blade and vane applications, wrought superqlloys for aero-engine disks and rings, and powder metalurgy （PM） superalloys for high performance disk applications were described. It was also reviewed the development of new class of high temperature structural materials, such as structural intermetallics, and advanced material processing technologies including rapid solidification, spray forming and so on. The trends of research and development of the above mentioned superalloys and processing technologies are outlined. Cast, wrought and PM superalloys are the workhorse materials for the hot section of current aero-engines. New high temperature materials and advanced processing technologies have been and will be the subject of study. It is speculated that high performance, high purity and low cost superalloys and technologies will play key roles in aero-engines.

Convergence Analysis of the Numerical Solution for Cathode Design of Aero-engine Blades in Electrochemical Machining

As a main difficult problem encountered in electrochemical machining （ECM）, the cathode design is tackled, at present, with various numerical analysis methods such as finite difference, finite element and boundary element methods. Among them, the finite element method presents more flexibility to deal with the irregularly shaped workpieces. However, it is very difficult to ensure the convergence of finite element numerical approach. This paper proposes an accurate model and a finite element numerical approach of cathode design based on the potential distribution in inter-electrode gap. In order to ensure the convergence of finite element numerical approach and increase the accuracy in cathode design, the cathode shape should be iterated to eliminate the design errors in computational process. Several experiments are conducted to verify the machining accuracy of the designed cathode. The experimental results have proven perfect convergence and good computing accuracy of the proposed finite element numerical approach by the high surface quality and dimensional accuracy of the machined blades.

Machining the Integral Impeller and Blisk of Aero-Engines:A Review of Surface Finishing and Strengthening Technologies

The integral impeller and blisk of an aero-engine are high performance parts with complex structure and made of difficult-to-cut materials. The blade surfaces of the integral impeller and blisk are functional surfaces for power transmission, and their surface integrity has signif- icant effects on the aerodynamic efficiency and service life of an aero-engine. Thus, it is indispensable to finish and strengthen the blades before use. This paper presents a comprehensive literature review of studies on finishing and strengthening technologies for the impeller and blisk of aero-engines. The review includes independent and inte- grated finishing and strengthening technologies and dis- cusses advanced rotational abrasive flow machining with back-pressure used for finishing the integral impeller and blisk. A brief assessment of future research problems and directions is also presented.

Aero-engine Blade Fatigue Analysis Based on Nonlinear Continuum Damage Model Using Neural Networks

Fatigue life and reliability of aero-engine blade are always of important significance to flight safety.The establishment of damage model is one of the key factors in blade fatigue research.Conventional linear Miner＇s sum method is not suitable for aero-engine because of its low accuracy.A back propagation neutral network（BPNN） based on the combination of Levenberg-Marquardt（LM） and finite element method（FEM） is used to describe process of nonlinear damage accumulation behavior in material and predict fatigue life of the blade.Fatigue tests of standard specimen made from TC4 are carried out to obtain material fatigue parameters and S-N curve.A nonlinear continuum damage model（CDM）,based on the BPNN with one hidden layer and ten neurons,is built to investigate the nonlinear damage accumulation behavior,in which the results from the tests are used as training set.Comparing with linear models and previous nonlinear models,BPNN has the lowest calculation error in full load range.It has significant accuracy when the load is below 500 MPa.Especially,when the load is 350 MPa,the calculation error of the BPNN is only 0.4%.The accurate model of the blade is built by using 3D coordinate measurement technology.The loading cycle in fatigue analysis is defined from takeoff to cruise in 10 min,and the load history is obtained from finite element analysis（FEA）.Then the fatigue life of the compressor blade is predicted by using the BPNN model.The final fatigue life of the aero-engine blade is 6.55 104 cycles（10 916 h） based on the BPNN model,which is effective for the virtual design of aero-engine blade.

Application of multi-outputs LSSVR by PSO to the aero-engine model

Considering the modeling errors of on-board self-tuning model in the fault diagnosis of aero-engine, a new mechanism for compensating the model outputs is proposed. A discrete series predictor based on multi-outputs least square support vector regression （LSSVR） is applied to the compensation of on-board self-tuning model of aero-engine, and particle swarm optimization （PSO） is used to the kernels selection of multi-outputs LSSVR. The method need not reconstruct the model of aero-engine because of the differences in the individuals of the same type engines and engine degradation after use. The concrete steps for the application of the method are given, and the simulation results show the effectiveness of the algorithm.

APPLICATION OF ROUGH SET THEORY TO MAINTENANCE LEVEL DECISION-MAKING FOR AERO-ENGINE MODULES BASED ON INCREMENTAL KNOWLEDGE LEARNING

The maintenance of an aero-engine usually includes three levels,and the maintenance cost and period greatly differ depending on the different maintenance levels.To plan a reasonable maintenance budget program, airlines would like to predict the maintenance level of aero-engine before repairing in terms of performance parameters,which can provide more economic benefits.The maintenance level decision rules are mined using the historical maintenance data of a civil aero-engine based on the rough set theory,and a variety of possible models of updating rules produced by newly increased maintenance cases added to the historical maintenance case database are investigated by the means of incremental machine learning.The continuously updated rules can provide reasonable guidance suggestions for engineers and decision support for planning a maintenance budget program before repairing. The results of an example show that the decision rules become more typical and robust,and they are more accurate to predict the maintenance level of an aero-engine module as the maintenance data increase,which illustrates the feasibility of the represented method.

Bifurcation analysis of aero-engine's rotor system under constant maneuver load

When an aircraft is hovering or doing a dive-hike flight at a fixed speed, a constant additional inertial force will be induced to the rotor system of the aero-engine, which can be called a constant maneuver load. Take hovering as an example. A Jeffcott rotor system with a biased rotor and several nonlinear elastic supports is modeled, and the vibration characteristics of the rotor system under a constant maneuver load are analytically studied. By using the multiple-scale method, the differential equations of the system are solved, and the bifurcation equations are obtained. Then, the bifurcations of the system are analyzed by using the singularity theory for the two variables. In the EG-plane, where E refers to the eccentricity of the rotor and G represents the constant maneuver load, two hysteresis point sets and one double limit point set are obtained. The bifurcation diagrams are also plotted. It is indicated that the resonance regions of the two variables will shift to the right when the aircraft is maneuvering. Furthermore, the movement along the horizontal direction is faster than that along the vertical direction. Thus, the different overlapping modes of the two resonance regions will bring about different bifurcation modes due to the nonlinear coupling effects. This result lays a theoretical foundation for controlling the stability of the aero-engine＇s rotor system under a maneuver load.

Aero-engine Thrust Estimation Based on Ensemble of Improved Wavelet Extreme Learning Machine

Aero-engine direct thrust control can not only improve the thrust control precision but also save the operating cost by reducing the reserved margin in design and making full use of aircraft engine potential performance.However,it is a big challenge to estimate engine thrust accurately.To tackle this problem,this paper proposes an ensemble of improved wavelet extreme learning machine(EW-ELM)for aircraft engine thrust estimation.Extreme learning machine(ELM)has been proved as an emerging learning technique with high efficiency.Since the combination of ELM and wavelet theory has the both excellent properties,wavelet activation functions are used in the hidden nodes to enhance non-linearity dealing ability.Besides,as original ELM may result in ill-condition and robustness problems due to the random determination of the parameters for hidden nodes,particle swarm optimization(PSO)algorithm is adopted to select the input weights and hidden biases.Furthermore,the ensemble of the improved wavelet ELM is utilized to construct the relationship between the sensor measurements and thrust.The simulation results verify the effectiveness and efficiency of the developed method and show that aero-engine thrust estimation using EW-ELM can satisfy the requirements of direct thrust control in terms of estimation accuracy and computation time.

Linear-in-Parameter Models Based on Parsimonious Genetic Programming Algorithm and Its Application to Aero-Engine Start Modeling

A novel Parsimonious Genetic Programming （PGP） algorithm together with a novel aero-engine optimum data-driven dynamic start process model based on PGP is proposed. In application of this method, first, the traditional Genetic Programming（GP） is used to generate the nonlinear input-output models that are represented in a binary tree structure; then, the Orthogonal Least Squares algorithm （OLS） is used to estimate the contribution of the branches of the tree （refer to basic function term that cannot be decomposed anymore according to special rule） to the accuracy of the model, which contributes to eliminate complex redundant subtrees and enhance GP＇s convergence speed; and finally, a simple, reliable and exact linear-in-parameter nonlinear model via GP evolution is obtained. The real aero-engine start process test data simulation and the comparisons with Support Vector Machines （SVM） validate that the proposed method can generate more applicable, interpretable models and achieve comparable, even superior results to SVM.

H∞ Tracking Control for Switched LPV Systems With an Application to Aero-Engines

This paper focuses on the H_∞ model reference tracking control for a switched linear parameter-varying(LPV)model representing an aero-engine. The switched LPV aeroengine model is built based on a family of linearized models.Multiple parameter-dependent Lyapunov functions technique is used to design a tracking control law for the desirable H_∞ tracking performance. A control synthesis condition is formulated in terms of the solvability of a matrix optimization problem.Simulation result on the aero-engine model shows the feasibility and validity of the switching tracking control scheme.

Sparsity-Assisted Intelligent Condition Monitoring Method for Aero-engine Main Shaft Bearing

Weak feature extraction is of great importance for condition monitoring and intelligent diagnosis of aeroengine.Aimed at achieving intelligent diagnosis of aero-engine main shaft bearing,an enhanced sparsity-assisted intelligent condition monitoring method is proposed in this paper.Through analyzing the weakness of convex sparse model,i.e.the tradeoff between noise reduction and feature reconstruction,this paper proposes an enhanced-sparsity nonconvex regularized convex model based on Moreau envelope to achieve weak feature extraction.Accordingly,a sparsity-assisted deep convolutional variational autoencoders network is proposed,which achieves the intelligent identification of fault state through training denoised normal data.Finally,the effectiveness of the proposed method is verified through aero-engine bearing run-to-failure experiment.The comparison results show that the proposed method is good at abnormal pattern recognition,showing a good potential for weak fault intelligent diagnosis of aero-engine main shaft bearings.