A Method for Forecasting the Condition of Several HPT Parts by Using Bayesian Belief Networks

2015 ◽  
Author(s):  
Daniel Giesecke ◽  
Moritz Wehking ◽  
Jens Friedrichs ◽  
Matthias Binner
Keyword(s):  
Expert Knowledge ◽  
Guide Vane ◽  
Forecast Accuracy ◽  
Pilot Project ◽  
Bayesian Belief Networks ◽  
Rotor Blades ◽  
Second Stage ◽  
Customer Segment ◽  
Engine Maintenance ◽  
Maintenance Process

The competitive ability of jet engine maintenance companies depends mainly on turn around time and overhaul costs. Both airline and maintenance companies need the best possible accuracy regarding the prediction of emerging costs and time of engine maintenance process to secure their operation. Estimating the deterioration status of engine modules prior to disassembling is one of the greatest challenges for the maintenance process. In a pilot project a Bayesian belief network (BBN) has been developed to determine the deterioration condition of the General Electric CF6-80C2 first stage high pressure turbine (HPT) nozzle guide vane (NGV). The aim of this paper is to extend the used BBN techniques to the HPT first and second stage rotor blades and the second stage vanes. Thereby, its objective is to prove the successful application of the developed method for constructing a BBN for component hardware forecast. The BBN is composed of following parameters: component repair history, region, on-wing cycles, airfoil material, thrust rating, engine wing position and customer segment. Performing statistical data analysis and combining these parameters with expert knowledge result in component specific BBNs. These nets provide a moderate forecast accuracy of 59 percent for the first stage rotor blades, 65 percent for the second stage rotor blades and promising 89 percent for the second stage NGVs. The paper concludes that a BBN has very good qualities to forecast the hardware condition of HPT components impressively shown by virtue of the nozzles. Therefore, it is worth to transfer the developed method to other modules in order to accurately predict the degradation of the components in an unconventional way.

A Method for Forecasting the Condition of HPT NGVs by Using Bayesian Belief Networks and a Statistical Approach

2014 ◽  
Author(s):  
Daniel Giesecke ◽  
Jens Friedrichs ◽  
Thomas Kenull ◽  
Matthias Binner ◽  
Martin Siegert
Keyword(s):  
Statistical Method ◽  
Expert Knowledge ◽  
Guide Vane ◽  
Hypothesis Test ◽  
Bayesian Belief Networks ◽  
Statistical Hypothesis ◽  
Linear Regression Method ◽  
Arithmetic Means ◽  
Jet Engine ◽  
Maintenance Process

Jet engine maintenance is a very competitive field in terms of time and costs. To increase planning security and reduce turnaround time (TAT) of the maintenance process it is important to get as much engine data as possible before disassembly. Aero engines are especially subjected to environmental and operational influences. For the high pressure turbine (HPT), the following parameters have been identified to describe the deterioration of its nozzle guide vane (NGV): On-wing cycles, NGV material, airport region, engine wing position, thrust rating, vane repair history and customer business segment. The combined influences of the parameters are non-trivial and it is not possible to acquire them analytically. There are no known mathematical laws connecting the above-mentioned parameters. The linear regression method set limits for processing data in an adequate manner. This is confirmed by the analysis of the arithmetic means and standard deviations. Especially the standard deviation values fit in a broad spectrum due to various reasons. Thus, it is not feasible to make an appropriate forecast with a simple statistical method due to the multidimensional character of the parameters influencing the accuracy. For this reason, advanced methods need to be developed to derive a feasible forecast method. By applying a statistical hypothesis test, a bayesian belief network (BBN) has been designed. It allows the use of imprecise data without suffering a significant loss in forecast accuracy and additionally, the implementation of expert knowledge. The objective of this study is to develop an effective BBN in order to adequately predict the next repair of the first stage HPT NGV of the General Electric CF6-80C2 engine. The reason for selecting the NGV is due to its high susceptibility to different influences, combined with the significant costs and TAT during the maintenance process. Having poor forecasting quality by using a simple statistical method, the evaluation of the BBN provides very satisfactory accuracy of above 80 percent which is equivalent to 19 out of 23 vane segments. Furthermore, the developed BBN emphasises robustness when detecting the expected tendencies while having only a limited amount of input parameters. Further work includes application of this method on other engine components as well as establishing the business value of the developed method. In conclusion, BBN have tremendous potential for forecasting the repair of the entire jet engine.

Influence of Leading Edge Fillet and Nonaxisymmetric Contoured Endwall on Turbine NGV Exit Flow Structure and Interactions With the Rim Seal Flow

2013 ◽  
Author(s):  
Özhan H. Turgut ◽  
Cengiz Camcı
Keyword(s):  
Flow Structure ◽  
Total Pressure ◽  
Guide Vane ◽  
Axial Flow ◽  
Leading Edge ◽  
Turbine Rotor ◽  
Rotor Blades ◽  
Constant Thickness ◽  
Computational Evaluation ◽  
Nozzle Guide

Three different ways are employed in the present paper to reduce the secondary flow related total pressure loss. These are nonaxisymmetric endwall contouring, leading edge (LE) fillet, and the combination of these two approaches. Experimental investigation and computational simulations are applied for the performance assessments. The experiments are carried out in the Axial Flow Turbine Research Facility (AFTRF) having a diameter of 91.66cm. The NGV exit flow structure was examined under the influence of a 29 bladed high pressure turbine rotor assembly operating at 1300 rpm. For the experimental measurement comparison, a reference Flat Insert endwall is installed in the nozzle guide vane (NGV) passage. It has a constant thickness with a cylindrical surface and is manufactured by a stereolithography (SLA) method. Four different LE fillets are designed, and they are attached to both cylindrical Flat Insert and the contoured endwall. Total pressure measurements are taken at rotor inlet plane with Kiel probe. The probe traversing is completed with one vane pitch and from 8% to 38% span. For one of the designs, area averaged loss is reduced by 15.06%. The simulation estimated this reduction as 7.11%. Computational evaluation is performed with the rotating domain and the rim seal flow between the NGV and the rotor blades. The most effective design reduced the mass averaged loss by 1.28% over the whole passage at the NGV exit.

Bayesian belief networks: applications in ecology and natural resource management

2006 ◽  
Vol 36 (12) ◽  
pp. 3053-3062 ◽  
Author(s):  
Robert K McCann ◽  
Bruce G Marcot ◽  
Rick Ellis
Keyword(s):  
Resource Management ◽  
Natural Resource Management ◽  
Natural Resource ◽  
Expert Knowledge ◽  
Bayesian Belief Networks ◽  
Belief Networks ◽  
Costs And Benefits ◽  
Management Decisions ◽  
Management Guidelines ◽  
Management Framework

In this introduction to the following series of papers on Bayesian belief networks (BBNs) we briefly summarize BBNs, review their application in ecology and natural resource management, and provide an overview of the papers in this section. We suggest that BBNs are useful tools for representing expert knowledge of an ecosystem, evaluating potential effects of alternative management decisions, and communicating with nonexperts about making natural resource management decisions. BBNs can be used effectively to represent uncertainty in understanding and variability in ecosystem response, and the influence of uncertainty and variability on costs and benefits assigned to model outcomes or decisions associated with natural resource management. BBN tools also lend themselves well to an adaptive-management framework by posing testable management hypotheses and incorporating new knowledge to evaluate existing management guidelines.

Quick Start of an Industrial Gas Turbine Engine Through the Development of “Silent Start” VGV Schedule

2020 ◽  
Author(s):  
Senthil Krishnababu ◽  
Vili Panov ◽  
Simon Jackson ◽  
Andrew Dawson
Keyword(s):  
Guide Vane ◽  
Pressure Ratio ◽  
Axial Compressor ◽  
Rotating Stall ◽  
Rotor Blades ◽  
Start Time ◽  
Turbine Engine ◽  
High Pressure Ratio ◽  
Compressor Map ◽  
Industrial Gas Turbine

Abstract In this paper, research that was carried out to optimise an initial variable guide vane schedule of a high-pressure ratio, multistage axial compressor is reported. The research was carried out on an extensively instrumented scaled compressor rig. The compressor rig tests carried out employing the initial schedule identified regions in the low speed area of the compressor map that developed rotating stall. Rotating stall regions that caused undesirable non-synchronous vibration of rotor blades were identified. The variable guide vane schedule optimisation carried out balancing the aerodynamic, aero-mechanical and blade dynamic characteristics gave the ‘Silent Start’ variable guide vane schedule, that prevented the development of rotating stall in the start regime and removed the non-synchronous vibration. Aerodynamic performance and aero-mechanical characteristics of the compressor when operated with the initial schedule and the optimised ‘Silent Start’ schedule are compared. The compressor with the ‘Silent Start’ variable guide vane schedule when used on a twin shaft engine reduced the start time to minimum load by a factor of four and significantly improved the operability of the engine compared to when the initial schedule was used.

CFD Computation of Fan Interaction Noise

2007 ◽  
Author(s):  
Sheryl M. Grace ◽  
Douglas L. Sondak ◽  
Daniel J. Dorney ◽  
Michaela Logue
Keyword(s):  
Surface Pressure ◽  
Second Harmonic ◽  
Guide Vane ◽  
Power Level ◽  
Broadband Noise ◽  
Rotor Blades ◽  
Navier Stokes ◽  
Fan Noise ◽  
Guide Vanes ◽  
Blade Passage

In this study, a 3-D, unsteady, Reynolds-averaged Navier-Stokes (RANS) CFD code coupled to an acoustic calculation is used to predict the contribution of the exit guide vanes to tonal fan noise downstream. The configuration investigated is that corresponding to the NASA Source Diagnostic Test (SDT) 22-in fan rig. One configuration from the SDT matrix is considered here: the approach condition, and outlet guide vane count designed for cut-off of the blade passage frequency. In this chosen configuration, there are 22 rotor blades and 54 stator blades. The stators are located 2.5 tip chords downstream of the rotor trailing edge. The RANS computations are used to obtain the spectra of the unsteady surface pressure on the exit guide vanes. The surface pressure at the blade passage frequency and its second harmonic are then integrated together with the Green’s function for an annular duct to obtain the pressure at locations in the duct. Comparison of the computed sound power level at the exhaust plane with experiment show good agreement at the cut-on circumferential mode. The results from this investigation validate the use of the CFD code along with the acoustic model for downstream fan noise predictions. This validation enables future investigations such as the effect of duct variation on the exhaust tonal power level and the validity of using this method for predicting broadband noise levels.

scholarly journals Impact assessment of water and nutrient reuse in hydroponic systems using Bayesian Belief Networks

2020 ◽  
Vol 10 (4) ◽  
pp. 431-442 ◽  
Author(s):  
Martin Zimmermann ◽  
Michaela Fischer
Keyword(s):  
Water Reuse ◽  
Crop Production ◽  
Municipal Wastewater ◽  
Expert Knowledge ◽  
Research Question ◽  
Agricultural Practices ◽  
Bayesian Belief Networks ◽  
Ecological Impacts ◽  
Small Scale ◽  
Hydroponic Systems

Abstract Water-saving agricultural practices can reduce negative environmental impacts in water-scarce regions all over the world. This study deals with an innovation that combines hydroponic crop production and municipal wastewater reuse for irrigation purposes. The research question was what impacts such hydroponic water reuse systems have on product confidence, economic viability, groundwater recharge, biodiversity and landscape quality. It should also be clarified under which conditions and with which measures these systems can be sustainable. To answer these questions, a number of generic hydroponic water reuse systems were modeled and assessed using a Bayesian Belief Network that included both numerical values and expert knowledge. The hydroponic water reuse systems with the most positive overall impacts are small-scale food production systems (tomatoes) equipped with lighting and heating whose products are marked with a quality label or with a label for regional products. The systems are located in a former industrial area. In addition, a wetland system and landscape integration are implemented as landscaping measures. Hydroponic systems can be operated economically viable, their products have a high level of product confidence and their ecological impacts can be positive. No tradeoffs have to be accepted between economic, social and ecological goals.

Influence of Hot Streak Circumferential Length-Scale in Transonic Turbine Stage

2004 ◽  
Author(s):  
L. He ◽  
V. Menshikova ◽  
B. R. Haller
Keyword(s):  
Heat Transfer ◽  
Computational Study ◽  
Guide Vane ◽  
Strong Dependence ◽  
Rotor Blades ◽  
Inlet Temperature ◽  
Turbine Stage ◽  
Blade Vibration ◽  
Nozzle Guide ◽  
Hot Streak

A computational study is carried out on the influence of turbine inlet temperature distortion (hot streak). The hot streak effects are examined from both aeromechanical (forced blade vibration) and aero-thermal (heat transfer) points of view. Computations are firstly carried out for a transonic HP turbine stage, and the steady and unsteady surface pressure results are compared with the corresponding experimental data. Subsequent analysis is carried out for hot-streaks with variable circumferential wavelength, corresponding to different numbers of combustion burners. The results show that the circumferential wavelength of the temperature distortion can significantly change unsteady forcing as well as the heat-transfer to rotor blades. In particular, when the hot-streak wavelength is the same as the nozzle guide vane (NGV) blade pitch, there is a strong dependence of the preferential heating characteristics on the relative clocking position between hot-streak and NGV blade. However, this clocking dependence is shown to be qualitatively weakened for the cases with fewer hot streaks with longer circumferential wavelengths.

A Numerical Investigation of Aerodynamic Characteristics of a Deteriorated Gas Turbine

2017 ◽  
Author(s):  
Koichi Yonezawa ◽  
Genki Nakai ◽  
Kazuyasu Sugiyama ◽  
Katsuhiko Sugita ◽  
Shuichi Umezawa
Keyword(s):  
Numerical Investigation ◽  
Gas Turbine ◽  
Rotor Blade ◽  
High Efficiency ◽  
Aerodynamic Characteristics ◽  
Rotor Blades ◽  
Second Stage ◽  
The Third ◽  
Time Operation ◽  
Third Stage

In order to keep a high efficiency of a gas turbine, it is important to make a suitable maintenance. Gas turbine nozzle guide vanes (NGVs) and turbine rotor blades deteriorate through a long-time operation due to various causes such as a particle attachment, erosion, and a thermal stress. In the present study, a numerical investigation has been carried out to clarify the influence of the NGV and the rotor blade deterioration on aerodynamics in a 3-stage gas turbine. Geometries of the NGV and the rotor blade were measured from a real gas turbine using a 3-D scanner. The first stage NGVs and rotor blades usually deteriorate seriously and are usually replaced at certain intervals. Two kinds of the geometries of the NGV and the rotor blade of the first stage were obtained, which are the new ones before use and the used ones to be replaced. For the second stage and the third stage, the geometries before use were used in the computations. The numerical results show that the isentropic efficiency of the first stage increases and that of the second stage decrease due to the deterioration of the first stage. The efficiency of the third stage is not affected significantly. The mechanisms are discussed from the observation of the flow fields.

Nozzle Guide Vane Cooling System Optimization

2012 ◽  
Author(s):  
Julian Girardeau ◽  
Frederic Pardo ◽  
Jérôme Pailhès ◽  
Jean-Pierre Nadeau
Keyword(s):  
High Performance ◽  
Cooling System ◽  
Guide Vane ◽  
Optimization Methods ◽  
System Optimization ◽  
Aggregation Functions ◽  
Nozzle Guide Vane ◽  
Low Efficiency ◽  
Engine Maintenance ◽  
Nozzle Guide

The authors would like to address improvements on cooling system optimization within a turboshaft Nozzle Guide Vane (NGV). Designing high performance cooling systems able to preserve the life duration of the NGV can lead to significant aerodynamic losses. Theses losses jeopardize the performance of the whole engine. In the same time, a low efficiency cooling system may affect engine Maintenance Repair and Overhaul (MRO) costs as component life decreases. To help turbine designers, the authors studied a vane and searched for an optimal cooling design by means of an evolutionary algorithm. The associated objective function is based on satisfaction indexes, using Harrington’s desirability curves and Antonsson’s aggregation functions. Evaluation and optimization methods will be presented as well as optimized designs.

scholarly journals Design and Analysis of a Split Deswirl Vane in a Two-Stage Refrigeration Centrifugal Compressor

2014 ◽  
Vol 6 ◽  
pp. 130925 ◽  
Author(s):  
Jeng-Min Huang ◽  
Yue-Hann Tsai
Keyword(s):  
Centrifugal Compressor ◽  
Rotation Angle ◽  
Guide Vane ◽  
Low Flow ◽  
Working Fluid ◽  
Inlet Guide Vane ◽  
Two Stage ◽  
Double Row ◽  
Second Stage ◽  
Better Than

This study numerically investigated the influence of using the second row of a double-row deswirl vane as the inlet guide vane of the second stage on the performance of the first stage in a two-stage refrigeration centrifugal compressor. The working fluid was R134a, and the turbulence model was the Spalart-Allmaras model. The parameters discussed included the cutting position of the deswirl vane, the staggered angle of two rows of vane, and the rotation angle of the second row. The results showed that the performance of staggered angle 7.5° was better than that of 15° or 22.5°. When the staggered angle was 7.5°, the performance of cutting at 1/3 and 1/2 of the original deswirl vane length was slightly different from that of the original vane but obviously better than that of cutting at 2/3. When the staggered angle was 15°, the cutting position influenced the performance slightly. At a low flow rate prone to surge, when the second row at a staggered angle 7.5° cutting at the half of vane rotated 10°, the efficiency was reduced by only about 0.6%, and 10% of the swirl remained as the preswirl of the second stage, which is generally better than other designs.

Sign in / Sign up

Export Citation Format

Share Document