Aero-engine Condition Monitoring Research Articles

Optimization of aero-engine condition monitoring by autoregressive model analysis based on wireless communication

The high value of aero-engines makes it necessary to extend their life in terms of econ-omy of use. Health management is an important basis for this work. Background: The vibration signal is an important representation of the working state of an aero-engine. The current usual method is based on wired communication with simple waveform presentation. The many incon-veniences of this method have seriously affected the further development of this work. Methods: This research team acquires engine vibration signals in real time through a designed wireless signal sensor, and then analyzes and visualizes the signals in depth. Results: Through this method, it can visually and effectively demonstrate signal characteristics for engineers, effectively identify fault signals, and monitor engine operating conditions in real time. Conclusions: The method enables the optimization of aero-engine work-state monitoring.

A Lubricating Oil Condition Monitoring System Based on Wear Particle Kinematic Analysis in Microfluid for Intelligent Aeroengine.

Lubricating oil monitoring technology is a commonly used method in aeroengine condition monitoring, which includes particle counting technology, as well as spectral and ferrography technology in offline monitoring. However, these technologies only analyze the characteristics of wear particles and rely on physical and chemical analysis techniques to monitor the oil quality. In order to further advance offline monitoring technology, this paper explores the potential role of differences in wear particle kinematic characteristics in recognizing changes in wear particle diameter and oil viscosity. Firstly, a kinematic force analysis of the wear particles in the microfluid was carried out. Accordingly, a microfluidic channel conducive to observing the movement characteristics of particles was designed. Then, the wear particle kinematic analysis system (WKAS) was designed and fabricated. Secondly, a real-time tracking velocity measurement algorithm was developed by using the Gaussian mixture model (GMM) and the blob-tracking algorithm. Lastly, the WKAS was applied to a pin–disc tester, and the experimental results show that there is a corresponding relationship between the velocity of the particles and their diameter and the oil viscosity. Therefore, WKAS provides a new research idea for intelligent aeroengine lubricating oil monitoring technology. Future work is needed to establish a quantitative relationship between wear particle velocity and particle diameter, density, and oil viscosity.

Aero-engine exhaust gas temperature prediction based on LightGBM optimized by improved bat algorithm

In this paper, an aero-engine exhaust gas temperature prediction model based on LightGBM optimized by the chaotic rate bat algorithm is proposed to monitor aero-engine performance effectively. By introducing chaotic rate, the convergence speed and precision of bat algorithm are improved, which chaotic rate bat algorithm is obtained. The LightGBM is optimized by chaotic rate bat algorithm and it is used to predict exhaust gas temperature. Taking a type of aero-engine for example, some relevant performance parameters from the flight data measured by airborne sensors were selected as input variables and exhaust gas temperature as output variables. The data set is divided into training and test sets, and the CRBA-LightGBM model is trained and tested, and compared with ensemble algorithms such as RF, XGBoost, GBDT, LightGBM, and BA-LightGBM. The results show that the mean absolute error of this method in the prediction of exhaust gas temperature (after normalization) is 0.0065, the mean absolute percentage error is 0.77% and goodness of fit R2 has reached to 0.9469. The prediction effect of CRBA-LightGBM is better than other comparison algorithms and it is suitable for aero-engine condition monitoring.

Correlation analysis of aeroengine operation monitoring using deep learning

To analyze the reliability of aeroengine more accurately, based on the analysis of operation reliability and complex reliability, the deep learning method is adopted to deal with the nonlinear and time-varying problems between the state parameters and operation reliability of aeroengine, and the condition monitoring method and deep learning of aeroengine are discussed. The results show that, based on the deep learning integrated network, the remaining useful life of aeroengine is predicted, and the key parameters of aeroengine are fitted and predicted by the back propagation (BP) algorithm. The artificial neural network method is used to predict the aeroengine parameters. For the collected aeroengine monitoring parameters, the greedy layer by layer training algorithm is used to mine the relationship between the parameters, extract the evaluation features, and evaluate the performance degradation, which verify the statistical significance and robustness of the conclusions. The proposed algorithm is more accurate and robust than the results of back BP neural network and support vector machine. It can prevent the over-fitting of small samples in aeroengine condition monitoring and further improve its nonlinear processing and generalization ability.

Evaluation of the aeroengine performance reliability based on generative adversarial networks and Weibull distribution

Evaluating the reliability of aeroengines with few or zero failures through the use of the Weibull distribution has become a key problem in aviation, as the difficulty of obtaining sufficient sample sizes of monitoring data limits the reliability of evaluations. This paper aims to solve this problem by using generative adversarial networks to generate aeroengine condition monitoring data and increase the volume of usable data. The experimental results show that after a large number of network training epochs, the generated data can reflect the regularity of empirical monitoring data. The relationship between monitoring parameters and Weibull distribution parameters is determined, the generated data are used to estimate Weibull parameters, and the Weibull distribution reliability function for aeroengines is established. The results indicate that the combined use of generative adversarial networks and the Weibull distribution reliability function can indeed solve the problem of limited data volume, and that this method can improve the accuracy of aeroengine reliability assessment. The effectiveness of the proposed method is verified by analyzing monitoring data and time on wing data of 30 aeroengines, calculating engine reliability, and comparing the results with those yielded from the generated data.

Sequential pattern mining applied to aeroengine condition monitoring with uncertain health data

Numerical algorithms that can assess Engine Health Monitoring (EHM) data in aeroengines are influenced by the high level of uncertainty inherent to gas path measurements and engine-to-engine variability. Among them, fuzzy rule-based techniques have been successfully used due to their robustness towards noisy signals and their capability to learn human-readable rules from data. These techniques are useful in detecting the presence of certain types of abnormal events or general engine deterioration, through the identification of specific combinations of EHM signals associated with these specific cases. However, there are also other types of engine events that manifest themselves as an ordered sequence of otherwise normal combinations of the EHM signals. These combinations are dismissed when considered in isolation as the current existing techniques cannot assess them. In this paper it is proposed to use sequence mining techniques in order to obtain fuzzy rules from uncertain EHM data which can in turn be used to identify the cases where an engine event is determined as a sequence of otherwise normal combinations of EHM signals. The results are subsequently tested on a representative sample of aeroengine data.

Unified Multi-speed analysis (UMA) for the condition monitoring of aero-engines

For rotating machinery in which speeds and dynamics constantly change, performing vibration-based condition monitoring can be challenging. Thus, an effort is made here to develop a Unified Multi-speed fault diagnosis technique that can exploit useful vibration information available at various speeds from a rotating machine in a single analysis. Commonly applied indicators are computed from data collected from a rig at different speeds for a baseline case and different faults. Four separate analyses are performed: single speed at a single bearing, integrated features from multiple speeds at a single bearing, single speed for integrated features from multiple bearings and the proposed Unified Multi-speed analysis. The Unified Multi-speed approach produces the most conspicuous separation and isolation among the conditions tested. Observations made here suggest integration of more dynamic features available at different speeds improves the learning process of the tool which could prove useful for aero-engine condition monitoring.

Experimental Research on Energy Spectrum Analysis on Chips from Aeroengine Oil System

Inspection on chips from oil system is an important method for modern aeroengine condition monitoring. Energy spectrum analysis technique is the most widely used and effective method in inspection on metal chips. In this method, size and quantity of chips are observed by scanning electronic microscope and qualitative and quantitative analysis of element contents are finished by energy dispersive spectrometer. Through above experiments, material type of metal chips can be analyzed and material mark can be determined by comparison with the materials list used in the aeroengine. In this article, characteristics and advantages of energy spectrum analysis technology are systematically introduced and typical appearance feature and energy spectrum curve of common l chips are summarized in engineering practice. In addition, problems and prospects of energy spectrum analysis technique are proposed.

Aeroengine Exhaust Gas Temperature Prediction Using Process Neural Network with Time-Varying Threshold Functions

To predict the aeroengine exhaust gas temperature (EGT) more precisely, a process neuron with time-varying threshold function is proposed in this paper, and then the time-varying threshold process neural network model comprised of the presented process neurons is used for EGT prediction. By introducing a group of appropriate orthogonal basis functions, the input functions, the weight functions and the threshold functions of the time-varying threshold process neural network can be expanded as linear combinations of the given orthogonal basis functions, thus to eliminate the integration operation, then to simplify the time aggregation operation. The corresponding learning algorithm is also presented, and the effectiveness of the time-varying threshold process neural network model is evaluated through the prediction of EGT series from practical aeroengine condition monitoring.

Research of Aero-Engine Life Prediction Based on Take-Off EGTM

Life prediction is one important of area Engine research. Take-off EGTM is an important parameter to monitor Engine performance. Take-off EGTM have great influence on Engine life, Reducing EGT will help to extend Engine life on wing (LOW), thereby reducing operating costs. Aiming at aero-Engine condition monitoring, the definition of take-off EGT Margin is given, estimation methods and their application on Engine life prediction are discussed.

Forecasting Research Of Aero-engine Rotate Speed Signal Based on ARMA Model

This paper presents a method to analyze and forecast the rotate speed signal of one type of aero-engine that is based on time series theory by establishing ARMA model, and establishes ARMA (3, 1) model to predict the value and transformation trend of rotate speed signal. The application results show that the established ARMA (3, 1) model can simulate rotate speed signal series quite well with good prediction accuracy, so it suggests that the method which is based on time series and ARMA model can be affectively and applicably used in aero-engine condition monitoring and fault diagnosis.

Time-frequency analysis for non-stationary signal from mechanical measurement of bearing vibration

The aeroengine has been an important power source in aircraft and usually its operating condition is under mal-condition, so keeping it operating in safety status is essential. To improve performance of fault diagnosis method applied in aeroengine condition monitoring, a novel approach combining wavelet transform and neural network is proposed. By locating the converging local modulus maxima of the wavelet transform at fine scales, the wavelet transform has a good effect on detecting signal singularity or sharp transients. When the signal changes abruptly, it results in the wavelet maxima. The effective feature vectors are acquired by discrete orthonormal wavelet transform based on multi-resolution analysis and inputted as variables of neural network. The wavelet neural network can be extended by adding appropriate units to the network which are trained to represent signal time-frequency characteristics. The proposed neural network has three advantages over a typical neural network: data driven learning, local interconnections and entropy based self-organisation. The synthesised method of recursive orthogonal least squares algorithm is used to calculate the network parameters. The simulation results and actual applications show that the method can effectively diagnose and analyse aeroengine vibration fault.