【摘 要】
：
The prediction of Exhaust Gas Temperature Margin (EGTM) after washing aero-engines can provide a theoretical basis for airlines not only to evaluate the energy-saving effect and emission reduction,but also to formulate reasonable maintenance plans.However
【机 构】
：
School of Mechatronics Engineering,Harbin Institute of Technology,Harbin 150001,China;Department of
论文部分内容阅读
The prediction of Exhaust Gas Temperature Margin (EGTM) after washing aero-engines can provide a theoretical basis for airlines not only to evaluate the energy-saving effect and emission reduction,but also to formulate reasonable maintenance plans.However,the EGTM encounters step changes after washing aeroengines,while,in the traditional models,a persistence tendency exists between the prediction results and the previous data,resulting in low accuracy in prediction.In order to solve the problem,this paper develops a step parameters prediction model based on Transfer Process Neural Networks (TPNN).Especially,“step parameters” represent the parameters that can reflect EGTM step changes.They are analyzed in this study,and thus the model concentrates on the prediction of step changes rather than the extension of data trends.Transfer learning is used to handle the problem that few cleaning records result in few step changes for model learning.In comparison with Long Short-Term Memory (LSTM) and Kernel Extreme Learning Machine (KELM) models,the effectiveness of the proposed method is verified on CFM56-5B engine data.
其他文献
With the improvement of the accuracy of the inertial system,the influence of the dis-turbing gravity field on the accuracy of long-range rocket has become increasingly prominent.How-ever,in actual engineering,there are problems of low accuracy and being t
The ultrahigh strength 300M steel has been commonly used in the manufacture of air-craft landing gear and rotor shaft parts due to its excellent mechanical properties.Creep feed grind-ing is one of the essential operations during the whole component manuf
Space swarms,enabled by the miniaturization of spacecraft,have the potential capability to lower costs,increase efficiencies,and broaden the horizons of space missions.The formation con-trol problem of large-scale spacecraft swarms flying around an ellipt
The considerable uncertainty in mechanical properties of composite bolted joints not only prevents advanced composite materials from efficient applications,but also threatens the safety and reliability of the aircraft structures.In this paper,the uncertai
Uncontrolled residual stresses have significant effects on the service time and defects of the spun parts.Nowadays,X-Ray Diffraction (XRD) method has been widely used in the residual stress measurement of industry products with different forming processes
To address deeper understandings about the aero-thermal performance of an integrating infrared suppressor under more realistic situations,a numerical investigation is motivated in the cur-rent study,concerning the effects of forward-flight speed on exhaus
This research develops an accurate and efficient method for the Perspective-n-Line (PnL)problem.The developed method addresses and solves PnL via exploiting the problem\'s geometry in a non-linear least squares fashion.Specifically,by representing the r
The nickel-based superalloy Inconel 718 is treated with Coupled Ultrasonic and Electric Pulse Treatment (CUEPT),and the surface grain is refined from the average size of 9550.0 nm to 287.9,216.3,150.5,126.3,25.8 nm by different effective treatment current
The development of hypersonic precooled combined cycle engine provides a reliable power system for the future intercontinental navigation and reusable space orbital transportation.The compact heat exchanger precooler is the key component of the cooling cy
As the complexity of flight missions continues to increase,sending a timely warning or providing assistance to pilots helps to reduce the probability of operational errors and flight acci-dents.Monitoring pilots\' physiological data,real-time evaluation