Automated Condition Evaluation of Hot-Gas Path Components of Jet Engines Through Exhaust Jet Analysis

2018 ◽  
Author(s):  
Ulrich Hartmann ◽  
Joerg R. Seume
Keyword(s):  
Density Distribution ◽  
Outlier Detection ◽  
Detection Algorithm ◽  
Automated Detection ◽  
Reference State ◽  
Jet Engines ◽  
Density Distributions ◽  
Hot Gas ◽  
Svm Algorithm ◽  
Exhaust Jet

This paper determines the influence of different defective components in the hot-gas path (HGP) of a civil aircraft engine on the density distribution in the exhaust. The intention is to automate the identification of defective components inside the HGP through an analysis of the density distribution in the exhaust jet. The defects include an increased radial gap of the blades in the high-pressure turbine (HPT), and a reduction of the film cooling air mass flow in the first stage of the HPT. In addition, several combinations of both defects are simulated. In the present paper the exhaust density distributions are generated numerically using CFD simulations of the HGP. The density distribution in the exhaust jet is reconstructed with synthetic Background-Oriented Schlieren (BOS) measurements and automatically analyzed. The methodology for the automated defect detection consists of two algorithms, a Support Vector Machine (SVM) algorithm to automatically classify each measurement into a corresponding defect or reference class and an outlier detection algorithm to detect variations from the reference state — without assignment. It is shown that BOS provides a sufficient reconstruction quality to automatically detect defective HGP components with a SVM algorithm. It is possible to automatically detect both defects, even when they occur at the same time. For this purpose, different features were calculated to isolate the influence of each defect on the density distribution. The outlier detection algorithm allows for an automated detection of variations in the density distribution compared to the reference state without any previous knowledge of the influence of the defects on the density distributions during the training procedure. With this algorithm it is possible to detect unknown or new defects which have not been observed or regarded yet. These results strengthen the hypothesis, that an automated detection of defects in jet engines prior to the disassembly is possible.

Automatic Detection of Defects in a Swirl Burner Array Through an Exhaust Jet Pattern Analysis

2016 ◽  
Vol 139 (3) ◽  
Author(s):  
Ulrich Hartmann ◽  
Christoph Hennecke ◽  
Friedrich Dinkelacker ◽  
Joerg R. Seume
Keyword(s):  
Pattern Recognition ◽  
Density Distribution ◽  
Defect Detection ◽  
Detection System ◽  
Regeneration Process ◽  
Support Vector ◽  
Jet Engines ◽  
Swirl Burner ◽  
Recognition Algorithms ◽  
Exhaust Jet

A significant challenge in improving the regeneration process of jet engines is the reduction of engine down-time during inspection. As such, early defect detection without engine disassembly will speed up the regeneration process. Defects in the engines hot-gas path (HGP) influence the density distribution of the flow and lead to irregularities in the density distribution of the exhaust jet which can be detected with the optical background-oriented Schlieren (BOS) method in a tomographic setup. The present paper proposes a combination of tomographic BOS measurements and supervised learning algorithms to develop a methodology for an automatic defect detection system. In the first step, the methodology is tested by analyzing the exhaust jet of a swirl burner array with a nonuniform fuel-supply of single burners with tomographic BOS measurements. The measurements are used to implement a support vector machine (SVM) pattern recognition algorithm. It is shown that the reconstruction quality of tomographic BOS measurements is high enough to be combined with pattern recognition algorithms. The results strengthen the hypothesis that it is possible to automatically detect defects in jet engines with tomographic BOS measurements and pattern recognition algorithms.

Numerical Evaluation of the Condition of a Jet Engine Through Exhaust Jet Analysis

2016 ◽  
Author(s):  
Rafael R. Adamczuk ◽  
Joerg R. Seume
Keyword(s):  
Density Distribution ◽  
Mass Flow ◽  
Aircraft Engine ◽  
Local Area ◽  
Core Mass ◽  
Second Stage ◽  
Hot Gas ◽  
Radial Gap ◽  
Exhaust Jet ◽  
Cooling Air

The present work numerically investigates the influences that four defects in the hot gas path of a civil aircraft engine have on the density distribution of the exhaust jet. The defects detectability with tomographic measurements using the Background-oriented schlieren method (BOS) is evaluated in order to draw conclusions on the condition of the engine before disassembly. The modeled defects are: the variation of the radial gap between the rotor blade tip and the casing in the second stage of a high-pressure turbine (HPT), the burning of the trailing edge of the stator vanes and rotor blades of the second stage of the HPT, the variation of the cooling air mass flow in the first stage of the HPT, and the variation of the temperature at the outlet of the combustion chamber. Synthetic measurements show that a characteristic signature at the outer border of the core mass flow in the exhaust jet can be measured with BOS when the radial gap is varied. However, the burning of the trailing edges cannot be detected. The variation of the cooling air massflow affects the entire density distribution and can be measured with BOS. Defects of the burner nozzles affect a larger local area of the exhaust jet and thus can also clearly be identified with BOS. The results show that different defects in the hot gas path result in characteristic signatures in the density distribution of the exhaust jet and that they can be measured with BOS. It is thus possible to detect defects in the hot gas path with BOS before the disassembly of the engine.

Automatic Detection of Defects in a Swirl Burner Array Through an Exhaust Jet Pattern Analysis

2016 ◽  
Author(s):  
Ulrich Hartmann ◽  
Christoph Hennecke ◽  
Friedrich Dinkelacker ◽  
Joerg R. Seume
Keyword(s):  
Pattern Recognition ◽  
Density Distribution ◽  
Defect Detection ◽  
Detection System ◽  
Regeneration Process ◽  
Support Vector ◽  
Jet Engines ◽  
Swirl Burner ◽  
Recognition Algorithms ◽  
Exhaust Jet

A significant challenge in improving the regeneration process of jet engines is the reduction of engine down-time during inspection. As such, early defect detection without engine disassembly will speed up the regeneration process. Defects in the engines hot-gas path (HGP) influence the density distribution of the flow and lead to irregularities in the density distribution of the exhaust jet which can be detected with the optical Background-Oriented Schlieren (BOS) method in a tomographic set-up. The present paper proposes a combination of tomographic BOS measurements and supervised learning algorithms to develop a methodology for an automatic defect detection system. In a first step, the methodology is verified by analyzing the exhaust jet of a swirl burner array with a non-uniform fuel-supply of single burners with tomographic BOS measurements. The measurements are used to implement a Support Vector Machine (SVM) pattern recognition algorithm. It is shown that the reconstruction quality of tomographic BOS measurements is high enough to be combined with pattern recognition algorithms. The results strengthen the hypothesis, that it is possible to automatically detect defects in jet engines with tomographic BOS measurements and pattern recognition algorithms.

scholarly journals Automated detection of hot-gas path defects by Support Vector Machine based analysis of exhaust density fields

2021 ◽  
pp. 1-16
Author(s):  
Marcel Oettinger ◽  
Lars Wein ◽  
Dajan Mimic ◽  
Philipp Gilge ◽  
Ulrich Hartmann ◽  
...  
Keyword(s):  
Support Vector Machine ◽  
Gas Turbines ◽  
Automated Detection ◽  
Support Vector ◽  
Acceptance Test ◽  
Hot Gas ◽  
Monitoring Applications ◽  
Aero Engines ◽  
The Individual ◽  
Exhaust Jet

Defects in the hot-gas path of aero engines have been shown to leave typical signatures in the density distribution of the exhaust jet. These signatures are superposed when several defects are present. For improved maintenance and monitoring applications, it is important to not only detect that there are defects present but to also identify the individual classes of defects. This diagnostic approach benefits both, the analysis of prototype or acceptance test and the preparation of Maintenance, Repair, and Overhaul. Recent advances in the analysis of tomographic Background-Oriented Schlieren (BOS) data have enabled the technique to be automated such that typical defects in the hot-gas path of gas turbines can be detected and distinguished automatically. This automation is achieved by using Support Vector Machine (SVM) algorithms. Choosing suitable identification parameters is critical and can enable SVM algorithms to distinguish between different defect types. The results show that the SVM can be trained such that almost no defects are missed and that false attributions of defect classes can be minimized.

scholarly journals RODA: A Fast Outlier Detection Algorithm Supporting Multi-Queries

IEEE Access ◽  
2021 ◽  
Vol 9 ◽  
pp. 43271-43284
Author(s):  
Xite Wang ◽  
Jiafan Li ◽  
Mei Bai ◽  
Qian Ma
Keyword(s):  
Outlier Detection ◽  
Detection Algorithm

Research on the framework of university ideological and political education management system based on artificial intelligence

2021 ◽  
pp. 1-10
Author(s):  
Xuying Sun ◽  
Yu Zhang
Keyword(s):  
Artificial Intelligence ◽  
Political Theory ◽  
Outlier Detection ◽  
Management System ◽  
Detection Algorithm ◽  
Colleges And Universities ◽  
Ideological And Political Education ◽  
Political Education ◽  
Data Simulation ◽  
Artificial Intelligence Technology

The importance of the management of ideological and political theory courses in colleges and universities is objective to the importance of ideological and political theory courses. At present, the management of ideological and political theory courses in colleges and universities has big problems in both macro and micro aspects. This paper combines artificial intelligence technology to build an intelligent management system for ideological and political education in colleges and universities based on artificial intelligence, and conducts classroom supervision through intelligent recognition of student status. The KNN outlier detection algorithm based on KD-Tree is proposed to extract the state information of class students. Through data simulation, it can be known that the KD-KNN outlier detection algorithm proposed in this paper significantly improves the efficiency of the algorithm while ensuring the accuracy of the KNN algorithm classification. Through experimental research, it can be seen that the construction of this system not only clarifies the direction of management from a macro perspective, but also reveals specific methods of management from a micro perspective, and to a certain extent effectively solves the problems in the management of ideological and political theory courses in colleges and universities.

scholarly journals Die zeitliche Änderung der radialen Elektronendichteverteilung beim Theta-Pinch

1963 ◽  
Vol 18 (8-9) ◽  
pp. 895-900
Author(s):  
Franz Peter Küpper
Keyword(s):  
Density Distribution ◽  
Electron Density ◽  
Electron Density Distribution ◽  
Electron Distribution ◽  
Radial Symmetry ◽  
Zero Order ◽  
Time Interval ◽  
Interferometric Method ◽  
Density Distributions ◽  
Theta Pinch

In a θ-pinch the radial symmetry of the electron density distribution as a function of time has been measured by a MACH—ZEHNDER interferometer. In a time interval of 400 nsec during a discharge an image converter made three pictures (exposure times of 10 nsec each) . Up to 100 nsec after the first compression, the experimental results show different density distributions for the cases of trapped parallel and antiparallel magnetic fields. Complete radial symmetry of the electron density distribution was not found.Another interferometric method for measuring the radial symmetry of the electron distribution by observing “zero order” fringes is described.

Sign in / Sign up

Export Citation Format

Share Document