Aircraft Engine Fault Diagnosis Model Based on 1DCNN-BiLSTM with CBAM.

As the operational status of aircraft engines evolves, their fault modes also undergo changes. In response to the operational degradation trend of aircraft engines, this paper proposes an aircraft engine fault diagnosis model based on 1DCNN-BiLSTM with CBAM. The model can be directly applied to raw monitoring data without the need for additional algorithms to extract fault degradation features. It fully leverages the advantages of 1DCNN in extracting local features along the spatial dimension and incorporates CBAM, a channel and spatial attention mechanism. CBAM could assign higher weights to features relevant to fault categories and make the model pay more attention to them. Subsequently, it utilizes BiLSTM to handle nonlinear time feature sequences and bidirectional contextual feature information. Finally, experimental validation is conducted on the publicly available CMAPSS dataset from NASA, categorizing fault modes into three types: faultless, HPC fault (the single fault), and HPC&Fan fault (the mixed fault). Comparative analysis with other models reveals that the proposed model has a higher classification accuracy, which is of practical significance in improving the reliability of aircraft engine operations and for Remaining Useful Life (RUL) prediction.

Health State Estimation of On-Board Lithium-Ion Batteries Based on GMM-BID Model.

As a single feature parameter cannot comprehensively evaluate the health status of a battery, a multi-source information fusion method based on the Gaussian mixture model and Bayesian inference distance is proposed for the health assessment of vehicle batteries. The missing and abnormal data from real-life vehicle operations are preprocessed to extract the sensitive characteristic parameters which determine the battery performance. The normal state Gaussian mixture model is established using the fault-free state data, whereas the Bayesian inference distance is constructed as an index to quantitatively evaluate the battery performance state. In order to solve the problem that abnormal data may exist in the measured data and introduce errors into evaluation results, the determination rules of abnormal data are formulated. The verification of real-life vehicle operation data reveals that the proposed method can accurately evaluate the onboard battery state and reduce safety hazards of electric vehicles during the normal operation process.

A DLSTM-Network-Based Approach for Mechanical Remaining Useful Life Prediction.

Remaining useful life prediction is one of the essential processes for machine system prognostics and health management. Although there are many new approaches based on deep learning for remaining useful life prediction emerging in recent years, these methods still have the following weaknesses: (1) The correlation between the information collected by each sensor and the remaining useful life of the machinery is not sufficiently considered. (2) The accuracy of deep learning algorithms for remaining useful life prediction is low due to the high noise, over-dimensionality, and non-linear signals generated during the operation of complex systems. To overcome the above weaknesses, a general deep long short memory network-based approach for mechanical remaining useful life prediction is proposed in this paper. Firstly, a two-step maximum information coefficient method was built to calculate the correlation between the sensor data and the remaining useful life. Secondly, the kernel principal component analysis with a simple moving average method was designed to eliminate noise, reduce dimensionality, and extract nonlinear features. Finally, a deep long short memory network-based deep learning method is presented to predict remaining useful life. The efficiency of the proposed method for remaining useful life prediction of a nonlinear degradation process is demonstrated by a test case of NASA's commercial modular aero-propulsion system simulation data. The experimental results also show that the proposed method has better prediction accuracy than other state-of-the-art methods.

Prediction and Screening Model for Products Based on Fusion Regression and XGBoost Classification.

Performance prediction based on candidates and screening based on predicted performance value are the core of product development. For example, the performance prediction and screening of equipment components and parts are an important guarantee for the reliability of equipment products. The prediction and screening of drug bioactivity value and performance are the keys to pharmaceutical product development. The main reasons for the failure of pharmaceutical discovery are the low bioactivity of the candidate compounds and the deficiencies in their efficacy and safety, which are related to the absorption, distribution, metabolism, excretion, and toxicity (ADMET) of the compounds. Therefore, it is very necessary to quickly and effectively perform systematic bioactivity value prediction and ADMET property evaluation for candidate compounds in the early stage of drug discovery. In this paper, a data-driven pharmaceutical products screening prediction model is proposed to screen drug candidates with higher bioactivity value and better ADMET properties. First, a quantitative prediction method for bioactivity value is proposed using the fusion regression of LGBM and neural network based on backpropagation (BP-NN). Then, the ADMET properties prediction method is proposed using XGBoost. According to the predicted bioactivity value and ADMET properties, the BVAP method is defined to screen the drug candidates. And the screening model is validated on the dataset of antagonized Erα active compounds, in which the mean square error (MSE) of fusion regression is 1.1496, the XGBoost prediction accuracy of ADMET properties are 94.0% for Caco-2, 95.7% for CYP3A4, 89.4% for HERG, 88.6% for hob, and 96.2% for Mn. Compared with the commonly used methods for ADMET properties such as SVM, RF, KNN, LDA, and NB, the XGBoost in this paper has the highest prediction accuracy and AUC value, which has better guiding significance and can help screen pharmaceutical product candidates with good bioactivity, pharmacokinetic properties, and safety.

The Demand Supply Steady-State Process-Based Multi-Level Spare Parts Optimization.

Spare parts are one of the important components of the equipment comprehensive support system. Spare parts management plays a decisive role in achieving the desired availability with the minimum cost. With the equipment complexity increasing, the price of spare parts has risen sharply. The traditional spare parts management makes the contradiction between fund shortage and spare parts shortage increasingly prominent. Based on the analysis of the multi-echelon and multi-indenture spare parts support model VARI-METRIC (vary multi-echelon technology for recoverable item control, VARI-METRIC), which is widely used by troops and enterprises in various countries, the model is mainly used in high system availability scenarios. However, in the case of low equipment system availability, the accuracy and cost of model inventory prediction are not ideal. This paper proposed the multi-level spare parts optimization model, which is based on the demand-supply steady-state process. It is an analytical model, which is used to solve the low accuracy problem of the VARI-METRIC model in the low equipment system availability. The analytical model is based on the multi-level spare parts support process. The article deduces methods for solving demand rate, demand-supply rate, equipment system availability, and support system availability. The marginal analysis method is used in the model to analyze the spare parts inventory allocation strategy's current based cost and availability optimal value. Finally, a simulation model is established to evaluate and verify the model. Then, the simulation results show that, when the low availability of equipment systems are 0.4, 0.6, the relative errors of the analytical model are 3.54%, 3.86%, and its costs are 0.52, 1.795 million ¥ RMB. The experiment proves that the inventory prediction accuracy of the analytical model is significantly higher than that of the VARI-METRIC model in low equipment system availability. Finally, the conclusion and future research directions are discussed.

New instrument based on electrostatic sensor array for measuring tribo-electrification charging due to single particle impacts.

In the processing of particulate solids, particle-particle and particle-wall collisions can generate electrostatics. This is called contact/impact/frictional electrification and can lead to many problems such as affecting powder flow and explosion hazards. It is necessary to research the tribo-electrification charging due to single particle impacts on a target as the fundamental understanding of tribo-electrification. A new impact charging test rig based on an electrostatic sensor array that can measure charge transfer caused by a single impact between a particle and a target plane has been designed and established. Combined with the electrostatic sensor array, the compressed sensing algorithm is used to estimate not only the spatial position but also the charge amount of particle. The cross-correlation algorithm is used to determine particle's velocity instead of using other devices such as a photodetector. The new instrument allows single particles impacting target planes at different angles with a velocity exceeding 100 m/s. An oil calibration test rig has been constructed to verify the proposed methods. The estimation errors of the spatial position and charge amount are both within 5% when the particle is located at the central area of the pipeline and the estimation errors of velocities are within 2%. The impact charging experiments show a special initial charge prior to impact for which no net charge transfer would occur for polymer particles, but the charge would completely transfer for metal particles.

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.

Identification methods of charged particles based on aero-engine exhaust gas electrostatic sensor array.

This paper presents a study of aero-engine exhaust gas electrostatic sensor array to estimate the spatial position, charge amount and velocity of charged particle. Firstly, this study establishes a mathematical model to analyze the inducing characteristics and obtain the spatial sensitivity distribution of sensor array. Then, Tikhonov regularization and compressed sensing are used to estimate the spatial position and charge amount of particle based on the obtained sensitivity distribution; cross-correlation algorithm is used to determine particle's velocity. An oil calibration test rig is established to verify the proposed methods. Thirteen spatial positions are selected as the test points. The estimation errors of spatial positions and charge amounts are both within 5% when the particles are locating at central area. The errors are higher when the particles are closer to the wall and may exceed 10%. The estimation errors of velocities by using cross-correlation are all within 2%. An air-gun test rig is further established to simulate the high velocity condition and distinguish different kinds of particles such as metal particles and non-metal particles.

Roller Bearing Performance Degradation Assessment Based on Fusion of Multiple Features of Electrostatic Sensors.

This paper presents a new method to assess the performance degradation of roller bearings based on the fusion of multiple features, with the aim of improving the early degradation detection ability of the electrostatic monitoring system. At first, a set of feature parameters of the electrostatic monitoring system indicating the normal state of the bearings are extracted from the perspective of the time domain, frequency domain and complexity. Then, the parameter set is processed to reduce the dimensions and eliminate the redundancy using spectral regression. With the processed features, a Gaussian mixed model is established to gauge the health of the bearing, providing the distance value obtained using Bayesian inference as a quantitative indicator for assessing the performance degradation. The method is applied to access the life of a bearing in which the mechanic fatigue is artificially accelerated. The test results show that the proposed method can better reflect the degradation process of the bearing compared to other evaluation methods. This enables the electrostatic monitoring technique to detect the degradation of the bearing earlier than the vibration monitoring, providing a powerful tool for the condition monitoring of roller bearings.

Electrostatic Sensor Application for On-Line Monitoring of Wind Turbine Gearboxes.

The oil-line electrostatic sensor (OLES) is a new online monitoring technology for wear debris based on the principle of electrostatic induction that has achieved good measurement results under laboratory conditions. However, for practical applications, the utility of the sensor is still unclear. The aim of this work was to investigate in detail the application potential of the electrostatic sensor for wind turbine gearboxes. Firstly, a wear debris recognition method based on the electrostatic sensor with two-probes is proposed. Further, with the wind turbine gearbox bench test, the performance of the electrostatic sensor and the effectiveness of the debris recognition method are comprehensively evaluated. The test demonstrates that the electrostatic sensor is capable of monitoring the debris and indicating the abnormality of the gearbox effectively using the proposed method. Moreover, the test also reveals that the background signal of the electrostatic sensor is related to the oil temperature and oil flow rate, but has no relationship to the working conditions of the gearbox. This research brings the electrostatic sensor closer to practical applications.

[Remote passive sensing of aeroengine exhausts using FTIR system].

The traditional method of measuring the aeroengine exhausts is intrusive gas sampling analysis techniques. The disadvantages of the techniques include complex system, difficult operation, high costs and potential danger because of back-pressure effects. The non-intrusive methods have the potential to overcome these problems. So the remote FTIR passive sensing is applied to monitor aeroengine exhausts and determine the concentration of the exhausts gases of aeroengines. The principle of FTIR remote passive sensing is discussed. The model algorithm for the calibration of FTIR system, the radiance power distribution and gas concentration are introduced. TENSOR27 FTIR-system was used to measure the spectra of infrared radiation emitted by the hot gases of exhausts in a test rig. The emission spectra of exhausts were obtained under different thrusts. By analyzing the spectra, the concentrations of CO2, CO and NO concentration were calculated under 4 thrusts. Researches on the determination of concentration of the exhausts gases of aeroengines by using the remote FTIR sensing are still in early stage in the domestic aeronautics field. The results of the spectra and concentration in the aeroengine test are published for the first time. It is shown that the remote FTIR passive sensing techniques have a great future in monitoring the hot gas of the aeroengines exhausts.

[Passive detection of aeroengine exhaust based on Fourier transform infrared system].

Since the composition and concentration of aeroengine exhaust can reflect the combustion efficiency, they can provide the basis for condition based maintenance, and also the basis for the analysis of environment pollution caused by aeroengine exhaust. So the importance of aeroengine exhaust detection is evident. Up to now, the measurement of aeroengine exhaust is based on sampling analysis which is not convenient and can't meet the detection requirements when an aeroplane is flying-off or flying in the sky. Hence, new methods of exhaust detection must be studied. The passive measurement technology based on Fourier transform infrared spectroscopy (FTIR) was applied to the measurement of aeroengine exhaust in the present paper. At first, the principle of passive measurement based on FTIR was introduced in detail. On this basis, a model algorithm for gas concentration calculation was deduced based on the principle of infrared transmission. Then the feasibility of aeroengine exhaust measurement based on passive FTIR was analyzed, and the passive measurement method of aeroengine exhaust based on FTIR was given. In the end, an experiment of aeroengine exhaust passive measurement was carried out by a FTIR with the type of Tensor 27 produced by BRUKER. Good quality spectra of the exhaust and the background were measured. Based on the model algo rithm of passive measurement, the absorbance spectra of CO and NO were obtained respectively, and the concentrations of CO and NO were figured out. To check up the veracity of this method, a comparison was made with another apparatus. There were only little differences between the results of the two experiments, showing that the passive measurement technology based on FTIR could meet the requirements of aeroengine exhaust detection.