Aero-engine Gas Path Research Articles

Numerical analysis and experimental verification of the induced waveform characteristics for aeroengine gas path debris electrostatic sensor

This article introduces the principle of aeroengine gas path electrostatic monitoring and establishes a mathematical model of aeroengine gas path debris electrostatic sensor. In this study, we simulate particle’s movement based on the established model and perform numerical analysis of the induced charge pulse waveform. The simulation results show the quantitative relationship among particle’s charge amount, velocity, and pulse waveform’s features, and obtain the qualitative relationship between particle’s spatial position and pulse waveform’s features. A test rig is designed to verify the correctness of the mathematical model. A measurement mode based on dual-channel sensors has been proposed, and corresponding signal processing methods are used to calculate the velocity of the particle and reconstruct the charge pulse waveform from the measured voltage signal. The conclusions of this study not only avoid the shortcomings of traditional signal processing methods that directly use the measured voltage signal but also have important significance for improving the electrostatic monitoring capability.

Regression model for civil aero-engine gas path parameter deviation based on deep domain-adaptation with Res-BP neural network

The variations in gas path parameter deviations can fully reflect the healthy state of aero-engine gas path components and units; therefore, airlines usually take them as key parameters for monitoring the aero-engine gas path performance state and conducting fault diagnosis. In the past, the airlines could not obtain deviations autonomously. At present, a data-driven method based on an aero-engine dataset with a large sample size can be utilized to obtain the deviations. However, it is still difficult to utilize aero-engine datasets with small sample sizes to establish regression models for deviations based on deep neural networks. To obtain monitoring autonomy of each aero-engine model, it is crucial to transfer and reuse the relevant knowledge of deviation modelling learned from different aero-engine models. This paper adopts the Residual-Back Propagation Neural Network (Res-BPNN) to deeply extract high-level features and stacks multi-layer Multi-Kernel Maximum Mean Discrepancy (MK-MMD) adaptation layers to map the extracted high-level features to the Reproduce Kernel Hilbert Space (RKHS) for discrepancy measurement. To further reduce the distribution discrepancy of each aero-engine model, the method of maximizing domain-confusion loss based on an adversarial mechanism is introduced to make the features learned from different domains as close as possible, and then the learned features can be confused. Through the above methods, domain-invariant features can be extracted, and the optimal adaptation effect can be achieved. Finally, the effectiveness of the proposed method is verified by using cruise data from different civil aero-engine models and compared with other transfer learning algorithms.

Experimental study on simulation test system and electrostatic monitoring of rub fault of air circuit of engine based on the IoT perception

Aeroengine gas-path fault is a critical engine fault, which can seriously affect the normal operation of the engine and threaten flight safety. Due to aeroengine working characteristics, friction faults probably occur between the rotor and stator during aeroengine operation. Therefore, it is crucial to accurately and quickly judge the friction fault for the entire engine fault. According to aeroengine friction fault mechanism, a friction fault monitoring technology was proposed based on the electrostatic induction principle to solve the problem that the friction fault of aeroengine blades is difficult to monitor online. The Internet of things (IoT) technology was employed to acquire data from equipment and state information, and a friction fault test system was developed to simulate electrostatic monitoring of gas-path high-speed airflow and multi-impact loads. Then, a test bench was designed to conduct electrostatic monitoring experiments of multi-group friction under different rubbing modes, different materials and different rubbing degrees. Application of the IoT technology can fulfill real-time monitoring of the operation state of equipment and reveal the defects of large equipment, promoting the merge of IoT with the manufacturing industry and pushing IoT development towards a more transparent and intelligent future.

Gas Path Fault Diagnosis of Aeroengine Based on Soft Square Pinball Loss ELM

The ELM constructed based on the least squares loss function and ±1 label has poor generalization in the classification of data containing noise. The introduction of square pinball loss function can improve the robustness of ELM. However, the algorithm based on the squared loss function and the ±1 label imposes a margin of 1 for all training samples. At the same time, due to the unbounded nature of the loss function, the generalization of the algorithm in the classification problem is reduced. This paper proposes a soft threshold square pinball loss (SSP-Loss) function. This function can set more flexible thresholds for training samples while maintaining the robustness of the square pinball loss function. The soft-threshold square pinball loss function can approximate the bounded loss function in stages to further improve the classification performance of the algorithm. The performance of ELM based on the soft pinball loss function on several benchmark data sets proves the effectiveness of our proposed algorithm. More importantly, the excellent robustness and classification performance of the algorithm is very suitable for aeroengine gas path fault diagnosis, and is expected to become its candidate technology.

Fault diagnosis based on measurement reconstruction of HPT exit pressure for turbofan engine

Aero-engine gas path health monitoring plays a critical role in Engine Health Management (EHM). To achieve unbiased estimation, traditional filtering methods have strict requirements on measurement parameters which sometimes cannot be measured in engineering. The most typical one is the High-Pressure Turbine (HPT) exit pressure, which is vital to distinguishing failure modes between different turbines. For the case of an abrupt failure occurring in a single turbine component, a model-based sensor measurement reconstruction method is proposed in this paper. First, to estimate the missing measurements, the forward algorithm and the backward algorithm are developed based on corresponding component models according to the failure hypotheses. Then, a new fault diagnosis logic is designed and the traditional nonlinear filter is improved by adding the measurement estimation module and the health parameter correction module, which uses the reconstructed measurement to complete the health parameters estimation. Simulation results show that the proposed method can well restore the desired measurement and the estimated measurement can be used in the turbofan engine gas path diagnosis. Compared with the diagnosis under the condition of missing sensors, this method can distinguish between different failure modes, quantify the variations of health parameters, and achieve good performance at multiple operating points in the flight envelope.

Detect and evaluate dependencies between aero-engine gas path system variables based on multiscale horizontal visibility graph analysis

Identifying the interaction in aero-engine gas path system is a crucial problem that facilitates the understanding of emerging structures in the complex system. By employing the multiscale horizontal visibility graph method to aero-engine gas path system, the interaction characteristics between gas path system parameters are established. Comparing with normalized mutual information method, the advantage of the multiscale horizontal visibility graph method in detecting interaction is showed. And then, the effect of time scaleson the multiscale horizontal visibility graph analysis is investigated. The results show that the multiscale horizontal visibility graph method is effective to detect the interaction of gas path system parameters.

The Lempel–Ziv measure based pedigree map to detect and evaluate correlation between aero-engine gas path system variables

There is a great interest in studying complexity of the aero-engine gas path time series. This paper presents a Lempel–Ziv complexity measure for analysis of aero-engine gas path system signals. By applying a binary Lempel–Ziv measure to define the absolute distance between two non-null numerical sequences, the pedigree map of systemic clustering is constructed to provide a metric for the number of distinct deterministic patterns. And then, we propose a ternary Lempel–Ziv measure, improving on the binary Lempel–Ziv measure, and making it more suited for the analysis of aero-engine gas path time series. The results indicate that the maps, demonstrating the relationship between parameters, based on ternary Lempel–Ziv measure are more vivid than the map based on binary Lempel–Ziv measure.

Fault diagnosis based on grey relational analysis and synergetic pattern recognition for aero-engine gas-path systems

The gas-path system is an important sub-system in aero-engines. There are various indistinguishable faults in aero-engine gas-path systems. These faults are easily misjudged because the characteristic parameters are similar. Due to the many kinds of faults, current studies have poor accuracy in distinguishing similar faults. To improve fault diagnosis accuracy for gas-path systems, a fault diagnosis method based on grey relational analysis and synergetic pattern recognition is proposed. In the proposed method, grey relational analysis is used to initially distinguish the faults into different types and obtain similar fault types. Synergetic pattern recognition contributes to accurately diagnose faults which are difficult to recognize. A case study is used to verify the effectiveness and accuracy of the proposed model. The results show that faults in common types of gas-path systems can be diagnosed accurately by the proposed method.

Particle Swarm Optimisation of Hole Quality Characteristics in Laser Trepan Drilling of Inconel 718


 
 
 Inconel-718 is a nickel based super alloy and is extensively in use for working at very high temperature (upto 2000 °C) such as aero engine gas path equipment, nuclear equipment etc. Drilling micro size hole in such material with laser beam has been a proven choice and laser drilling process produces geometrically and dimensionally improved hole. Hole geometrical features can be improved further if laser drilling system operated at optimal input parameter setting. This paper experimentally investigates the behavior of hole geometrical features hole circularity and hole taper in laser trepan drilling of Inconel -718 sheet. Optimal value of laser input parameters for improved hole circularity and reduced hole taper have been suggested with the help of computational intelligence technique particle swarm optimisation. The effect of each laser input parameter on hole quality characteristics are also discussed and demonstrated graphically. Finally the experimental validation of the predicted results has been carried out.
 
 

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

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

The mutual information based minimum spanning tree to detect and evaluate dependencies between aero-engine gas path system variables

There is a great interest in studying statistical dependence characteristics of aero-engine gas path system time series. The mutual information is effective, mainly in quantifying the dependency of time series. By applying the mutual information and average mutual information method to aero-engine gas path system, the statistical dependence between two data steams from a finite number of samples are established. To better understand dependency of gas path system time series, we define the mutual information distance and propose the mutual information based minimum spanning tree to investigate the performance parameters and their interaction of gas path system. By examining the minimum spanning tree, we find that the exhaust gas temperature (EGT) and the low-spool rotor speed (N1) are confirmed as the predominant variables in fourteen gas path parameters. The results show that the proposed method is effective to detect the statistical dependence of gas path system parameters and has more valuable information.

Aero Engine Gas Path Performance Tracking Based on Multi-Sensor Asynchronous Integration Filtering Approach

Kalman filter (KF) is a widely used technique to obtain health condition in aero engine health management, and each kind of measurement is commonly assumed to be collected and tackled simultaneously from one sensor in the KF for state tracking in previous studies. However, there are redundant sensor measurements of the same kind employed with different sampling and transmission rate, and it is hard to achieve state estimation using multiple sensors at one time, especially, in the advanced distributed architecture. For these purposes, a multi-sensor asynchronous fusion approach is proposed to track engine health state using distributed cubature information filter (CIF) in this paper. The sequential and distributed integration structures are designed for asynchronous computation, and the square-root cubature rule are combined with the CIF to complete state estimation. The global state estimate of distributed square-root CIF (DSCIF) is obtained from the fusion of local estimates using multi-scale sampling strategy. The performance comparisons of the examined methodologies are conducted to state estimation with asynchronous measurements in aero engine gas path health tracking applications. The results illustrate the superiority of the DSCIF with regards to estimation accuracy and computational efforts, and confirm our viewpoints in the asynchronous filtering estimation for the multi-sensor system.

Symbolic Time-Series Analysis of Gas Turbine Gas Path Electrostatic Monitoring Data

The aero-engine gas-path electrostatic monitoring system is capable of providing early warning of impending gas-path component faults. In the presented work, a method is proposed to acquire signal sample under a specific operating condition for on-line fault detection. The symbolic time-series analysis (STSA) method is adopted for the analysis of signal sample. Advantages of the proposed method include its efficiency in numerical computations and being less sensitive to measurement noise, which is suitable for in situ engine health monitoring application. A case study is carried out on a data set acquired during a turbojet engine reliability test program. It is found that the proposed symbolic analysis techniques can be used to characterize the statistical patterns presented in the gas path electrostatic monitoring data (GPEMD) for different health conditions. The proposed anomaly measure, i.e., the relative entropy derived from the statistical patterns, is confirmed to be able to indicate the gas path components faults. Finally, the further research task and direction are discussed.

Optimized Research for Aero Engine Off-gas Monitor

Since the majority of aero engine faults are aero engine gas path faults, it is important to monitor its working condition. But the monitoring is under the condition where electrostatic signal of charged particles in aero engine gas path is weak and the sensor works in an environment of high temperature and high noise, so that it is difficult to monitor continuously. Using the gas-solid two phase flow device to simulate the aero engine gas path, and designing a signal processing circuit and simulate the signal processing circuit in the software MULTISIM, and using the software LabVIEW to establish the virtual instrument data acquisition system, a monitoring model which include a data acquisition system and a aero engine gas path fault analyze system is designed. As a result, the model which can be adapted to high temperature and high noise, and is sensitive to charge signal, has the advantages of high resolution, high signal-to-noise ratio, and high stability, could be operated steadily and continuously in various working condition of aero engine, and could provide a reliable basis for fault diagnosis of aero engine gas path.

Dynamical mechanism in aero-engine gas path system using minimum spanning tree and detrended cross-correlation analysis

Abstract Identifying the mutual interaction in aero-engine gas path system is a crucial problem that facilitates the understanding of emerging structures in complex system. By employing the multiscale multifractal detrended cross-correlation analysis method to aero-engine gas path system, the cross-correlation characteristics between gas path system parameters are established. Further, we apply multiscale multifractal detrended cross-correlation distance matrix and minimum spanning tree to investigate the mutual interactions of gas path variables. The results can infer that the low-spool rotor speed (N1) and engine pressure ratio (EPR) are main gas path parameters. The application of proposed method contributes to promote our understanding of the internal mechanisms and structures of aero-engine dynamics.

Heuristic sample reduction method for support vector data description

Support vector data description (SVDD) has become one of the most promising methods for one-class classication fornding the boundary of the training set. However, SVDD has a time complexity of O ( N 3 ) and a space complexity of O ( N 2 ) . When dealing with very large sizes of training sets, e.g., a training set of the aeroengine gas path parameters with the size of N > 10 6 sampled from several months of ight data, SVDD fails. To solve this problem, a method called heuristic sample reduction (HSR) is proposed for obtaining a reduced training set that is manageable for SVDD. HSR maintains the classication accuracy of SVDD by building the reduced training set heuristically with the samples selected from the original. For demonstration, several articial datasets and real-world datasets are used in the experiments. In addition, a practical example of the training set of the aeroengine gas path parameters is also used to compare the performance of SVDD based on the proposed HSR with conventional SVDD and other improved methods. The experimental results are very encouraging.

Formation Mechanism Analysis and Detection of Charged Particles in an Aero-engine Gas Path

The components of an aero-engine gas path cannot be monitored in a timely way due to a lack of real-time monitoring technologies. As an attempt to address this problem, we have conducted research on a condition monitoring technology based on the charging characteristics of particles in an aero-engine gas path, and emphatically analyze the formation of particles in an aero-engine gas path, the charging mechanism of carbon particles and the factors that influence the charge quantity and polarity. The verification experiments are performed on the simulated experiment platform and a turbo-shaft engine test bench. The results show the carbon particles' carry charge, and an obvious change in the total electrostatic charge level in the aero-engine gas path due to the increased carbon particles produced by burning or abnormal metal particles; the charge number is related to the size of particles, and the bigger carbon particles carry a negative charge and metal particles carry a positive charge; the change in engine power can lead to an obvious change in the level of electrostatic charge in the gas path, and the change in electrostatic charge results from the extra carbon particles formed in the rich-oil burning process. The research provides a reference for establishing the baseline of electrostatic charge while the engine runs on different power. The study also demonstrates the validity of the electrostatic monitoring technology and establishes a base for developing the application of electrostatic monitoring technology in aero-engines.

Cross-Correlations and Structures of Aero-Engine Gas Path System Based on DCCA Coefficient and Rooted Tree

Identifying the mutual interaction is a crucial problem that facilitates the understanding of emerging structures in complex system. We here focus on aero-engine dynamic as an example of complex system. By applying the detrended cross-correlation analysis (DCCA) coefficient method to aero-engine gas path system, we find that the low-spool rotor speed (N1) and high-spool rotor speed (N2) fluctuation series exhibit cross-correlation characteristic. Further, we employ detrended cross-correlation coefficient matrix and rooted tree to investigate the mutual interactions of other gas path variables. The results can infer that the exhaust gas temperature (EGT), N1, N2, fuel flow (WF) and engine pressure ratio (EPR) are main gas path parameters.

Analysis of an Aero-Engine Gas Path Fault Monitoring Sensor Model

A new aero-engine gas path fault monitoring technology is presented in this paper, which is based on the capacitive sensor. The working conditions of the aero-engine gas path components can be monitored through the sensor, which is the main source of the aero-engine faults such as the gas path debris. The capacitive sensor has advantages of non-contact measurement, high sensitivity and simple structure, which can effectively solve the problems of the traditional aero-engine gas path fault diagnosis technology, such as the poor operability, the weak real-time performance and the high cost. Through the analysis of the capacitive sensor model, the feasibility of the capacitive sensor in the aero-engine gas path fault monitoring is verified.

Aero-engine Gas Path Fault Diagnosis Based on Improved Support Vector Machine and Synergetic Neural Network

In order to distinguish similar failures of the aero-engine gas path fault diagnosis and improve the diagnostic accuracy, a fault diagnosing method based on improved SVM and Synergetic Neural Network was put forward. Firstly, the SVM after being optimized by Genetic Algorithms was used to diagnose and classify faults preliminarily for measured data, and the diagnosis results were analyzed to acquire indistinguishable similar failures, then the Synergetic Neural Network was introduced to distinguish similar failures and further determine the corresponding fault type, finally analyzed this fault model based on actual data. The experimental results show that the aero-engine gas path fault diagnosis method based on improved SVM and Synergetic Neural Network has high diagnostic accuracy and noise immunity.