Research on Initial Installed Power Loss of a Certain Type of Turbo-Shaft Engine Using Data Mining and Statistical Approach

Abstract

The installed positions of three domestic turbo-shaft engines mounted on a certain type of ship-borne helicopter interfere with the intake air flow of the engines, resulting in a decline of engine performance after initial installation. Due to the difference of load and adjustment method under the bench and installed conditions, it is necessary to study the change in gas turbine power rather than output shaft power of the engine before and after installation to evaluate the engine initial installed power loss. In this paper, quantum-behaved particle swarm optimization (QPSO) is applied to optimize the calculation of gas turbine power at different steady states based on the component-level aerodynamic thermal model of gas generator. Then, extreme learning machine (ELM) is adopted for regressive identification of the established gas generator state assessment model based on data mining and the identification model is applied to engine installed condition. Finally, statistical analysis of engine initial installed gas turbine power loss at three installed positions is carried out, respectively. Results show that the values of engine initial installed gas turbine power loss at three installed positions all conform to the normal distribution, the mean values are 1.658%, 9.828%, and 5.089%, respectively, and a confidence interval with 95% confidence level of the mean values are (1.388%, 1.928%), (9.178%, 10.478%) and (4.308%, 5.870%), which can provide references for determining the power monitoring thresholds after engine installation.

Self-Oscillations of The Free Turbine Speed in Testing Turboshaft Engine with Hydraulic Dynamometer

“…No change in the dynamic parameters of the engine was detected. In [22], research of turboshaft engine power loss was carried out using statistical analysis. The use of averaged data in the analysis does not allow identifying the problems of control system dynamics.…”

Improved LS-SVM Method for Flight Data Fitting of Civil Aircraft Flying at High Plateau

“…Flight data have many applications in aviation operation safety research [2][3][4][5][6]. Some scholars have applied flight data to turbine fault diagnosis, general aviation anomaly detection, aviation safety key landing index prediction [7][8][9][10][11], tower flight data manager man-machine system integration design processes, and new methods for nonlinear aerodynamic modeling of flight data [12][13][14]. Some scholars also analyze the flight characteristics of QAR data for landing at high-altitude airports, and use it for airline flight data monitoring machine learning methods, generating new operational safety knowledge from existing data, safety science insights gained from black-box-to-flight data monitoring, composite fault diagnosis using optimized MCKD and sparse representation of rolling bearings, rolling elements based on VMD, and sensitivity MCKD fault diagnosis, etc.…”