Industrial Gas Turbine Engine Research Articles

Hybrid intelligence for enhanced fault detection and diagnosis for industrial gas turbine engine

In context of industry 4.0, intelligent manufacturing and maintenance play a significant role. The fault detection and diagnosis (FDD) of industrial gas turbine (IGT) engine is very crucial in smart manufacturing. With the advancement of machine learning and sensor technology, artificial neural network (ANN) and multi-sensor data fusion have made it possible to solve the above issues. In this work, a hybrid model is proposed for the FDD of an IGT engine. Principal component analysis (PCA) is firstly employed to combine the multi-sensor monitoring data as a pre-processing step. The PCA approach has the capacity to glean insights from raw data and optimize the amalgamation of various condition monitoring datasets, with the aim of enhancing accuracy and maximizing the utility of gas turbine information. Later, ANN based FDD method is applied on the fused multiple sensors monitoring data. The present work also implements a comparative account of supervised and unsupervised ANN learning techniques, like multilayer perceptron and self-organizing map, and their pattern classification evaluations. The proposed model facilitates the attainment of early FDD with minimum error and has been validated and tested using real time data from actual operation environments. The data is collected from twin-shaft (18.7 MW) IGT engine as a case study. Results demonstrate that the proposed hybrid model is able to detect the conditions of industrial gas turbine engine with best diagnosis accuracy and calculated errors of 0.00173 and 1.9498. Comparison of two learning techniques demonstrates the superior performance of supervised learning technique.

Three Shaft Industrial Gas Turbine Transient Performance Analysis.

The power demand from gas turbines in electrical grids is becoming more dynamic due to the rising demand for power generation from renewable energy sources. Therefore, including the transient data in the fault diagnostic process is important when the steady-state data are limited and if some component faults are more observable in the transient condition than in the steady-state condition. This study analyses the transient behaviour of a three-shaft industrial gas turbine engine in clean and degraded conditions with consideration of the secondary air system and variable inlet guide vane effects. Different gas path faults are simulated to demonstrate how magnified the transient measurement deviations are compared with the steady-state measurement deviations. The results show that some of the key measurement deviations are considerably higher in the transient mode than in the steady state. This confirms the importance of considering transient measurements for early fault detection and more accurate diagnostic solutions.

Research Progress of Laser Additive Manufacturing Nickel-Based Alloy Metal Matrix Composites

Nickel-based alloy metal matrix composite (NAMMC) is a new type of composite material which is expected to replace traditional Nickel-base superalloy used in the manufacture of important hot-end components in aerospace, naval ships and industrial gas turbine engines due to its excellent high temperature strength, superior thermal fatigue resistance, high oxidation resistance and thermal corrosion resistance. However, these outstanding properties make it hard to process these materials with conventional manufacturing methods such as forging and machining owing to posing problems of high cost and energy consumptions. Laser additive manufacturing (AM) with a high degree of machining freedom and a high-energy-density laser beam as heat source has been used for processing NAMMC hot-end components with superior performance and complicated structure. Nevertheless, some manufacturing defects of poor bonding, high residual stress, cracking, pore etc. still exist in laser AM NAMMC parts. Therefore, this paper reviews research progress of laser AM NAMMC at present. The control method of manufacturing defect and the effect of reinforcements on the microstructure and mechanical properties of NAMMC are summarized. In addition, the challenges and prospects of laser AM NAMMC in the future are also discussed.

Unveiling the dynamics of ultra high velocity droplet impact on solid surfaces.

The impact of a liquid droplet onto a solid surface is a phenomenon present in a wide range of natural processes and technological applications. In this study, we focus on impact conditions characterised by ultra high velocities (up to 500 m/s), to investigate—for the first time—how the impact dynamics change when the compressibility of the liquid in the droplet is no longer negligible. A water droplet impacting a dry substrate at four different velocities, from 50 to 500 m/s, is simulated. Such conditions are particularly relevant to aviation as well as industrial gas turbine engine risk management. Thus, numerical investigations as the one we present here provide a powerful tool to analyse the process. We find that increasing the impact velocity changes the flow field within and outside the droplet the moment that the compressibility can no longer be neglected, with the rise of pressure fronts in both regions. Increasing the impact velocity, the compressibility affects also the lamella formed and changes its ejection velocity observed over time (and thus the wetting behaviour) when the region shift from incompressible to compressible. Moreover, it is found that the maximum pressure observed at the wall during the impact is located at the corner of the impact, where the lamella is ejected, not in the centre, and it is influenced by the initial velocity. To predict the maximum pressure experienced by the surface during the high velocity impact, we propose a correlation based on the initial Weber and Reynolds number of the droplet. The complexity and the scales of the dynamics involved in the ultra-high velocity impact is limiting the experimental and analytical studies. To the best of our knowledge there are no experimental data currently available at such conditions. In this study, through numerical simulations, new insights about the impact dynamics at such conditions are provided.

Selection of inoculant additives for modifying nickel alloys

Heat-resistant nickel alloys are widely used in the production of castings for aircraft and industrial gas turbine engines. Structural factors are the main determinants of the performance properties of cast nickel alloys. The main disadvantage of castings obtained from these alloys is the coarse-crystalline structure, uneven grain size and columnar crystals in the cross-section. Therefore, the creation of an optimal alloy structure is an important condition for obtaining high properties and ensuring the increased operability of cast parts. Obtaining a fine-grained structure has a beneficial effect on the level of mechanical and operational properties of cast metal. The most promising way to create such a structure is to introduce a small number of additives into the melt that cause heterogeneous formation of crystal nuclei, i.e. modification of the melt with dispersed particles of refractory elements and inocular compounds. To select the type of inocular particles required to initiate crystallization of a particular phase, it is necessary to have a set of data that allows one to form a theoretical understanding of the principles of such a choice. The paper provides a rationale for the selection of the type of particles of inoculators capable of causing the process of artificial changes in the structure of cast metal. For a heat-resistant nickel alloy, the use of refractory particles of ultra-dispersed titanium carbo nitride powder as inoculators are the most effective. When introduced into the melt 0.025 wt. % of such particles, a fine-grained structure of the alloy is obtained, and its ductility in comparison with the unmodified one is more than doubled.

Performance and Techno-Economic Analysis of Inlet Fogging System Implementation in Heavy Duty Industrial Gas Turbines

This study investigates the performance and economic benefits of applying inlet fogging in a heavy duty industrial gas turbine. To achieve the aim of the study, a heavy duty industrial gas turbine engine was modelled using a gas turbine performance software, GasTurb. The modelled engine was derived from the Frame 9E class of gas turbines. Consequent upon completing the engine modelling, ambient temperature profile data obtained from a location in Niger Delta region of Nigeria were used as input into the engine model to simulate its effect on the engine performance. Inlet fogging was simulated on the industrial gas turbine by inputting a water-to-air ratio of 0.4%, to cool and reduce the air inlet temperature by 10 degree Celsius. The simulation plots show that the gas turbine performance which dropped as a result of increased ambient temperature was enhanced by the application of inlet fogging. Economic analysis shows that approximately $2.4 million profit was recorded in one year when inlet fogging system was employed.

Nonlinear generalized predictive controller based on ensemble of NARX models for industrial gas turbine engine

New design and operation of modern gas turbine engines (GTEs) are becoming more and more complex where several limitations and control modes should be fulfilled at the same time to accomplish a safe and ideal performance for the engine. For this purpose, a constrained multi-input multi-output (MIMO) non-linear model predictive controller (NMPC) based on neural network model is designed to fulfill the control requirements of a Siemens SGT-A65 three-spool aero-derivative gas turbine engine (ADGTE) used for power generation. However, the implementation of NMPC in real time has two challenges: Firstly, the design of an accurate non-linear model, which can run many times faster than real time. Secondly, the usage of a rapid and reliable optimization algorithm to solve the optimization problem in real time. To solve these issues, the constrained MIMO NMPC is created based on the generalized predictive control (GPC) algorithm as a result of its clarity, ease of use, and capacity to deal with problems in one algorithm. In addition, seven ensembles of eight multi-input single-output (MISO) non-linear autoregressive network with exogenous inputs (NARX) models are used as a base model for the GPC controller to predict the future process outputs. Estimation of free and forced responses of the GPC based on the neural network (NN) model of the plant each sampling time without performing instantaneous linearization is proposed in this study, which reduces the NMPC optimization problem to a linear optimization problem at each sampling step. In addition, the Hildreth's quadratic programming algorithm is used to solve the quadratic optimization problem within the NMPC controller, which offers ease of use and reliability in real time applications. To demonstrate the performance of the NNGPC controller developed in this study, we have compared the performance of the neural network generalized predictive control (NNGPC) controller to the existing controller of the SGT-A65 engine. The simulation results show that the NNGPC has demonstrated output responses with less oscillatory behavior and smoother control actions to the sudden variation in the electric load disturbance than those observed in the existing min-max controller. However, the min-max controller has faster response than that of the NNGPC controller.

Overview of Joining and Repairing Techniques of Ni-Based Superalloy for Industrial Gas Turbine Applications

In industrial gas turbine (IGT) engine manufacturing, nickel-based superalloys are used mainly to meet the needs of components of the hot gas pathway. Although these alloys have high-temperature capabilities, the parts are prone to damage during service. The high working temperatures of these engines lead to component degradation due to creep, fatigue, and oxidation reactions; therefore, due to the high cost of newly produced superalloy components, it is usually more cost-effective to repair the damaged parts rather than completely replacing them. Joining and repairing techniques are necessary when manufacturing and repairing these alloys. This article will present an overview of the Ni-based superalloy for industrial gas turbine application by studying the microstructure of Ni-based superalloy, weldability issues, and cracking phenomena. Joining/repairing techniques of Ni-base superalloy with advantages and limitations to each technique are discussed to know a suitable technique for use in the high-temperature application.

Flame investigations of a laboratory-scale CECOST swirl burner at atmospheric pressure conditions

Experimental and numerical studies were performed to understand the stabilization of lean premixed natural gas/air flames in a gas turbine model combustor which was equipped with a swirl burner, known as the CECOST burner, designed to replicate the flow and flame structures in an industrial gas turbine engine. The operability range, flame stabilization, and flashback were investigated employing simultaneous OH– and CH2O-PLIF, and high-speed chemiluminescence imaging. Large eddy simulation (LES) was carried out for analysis of the vortex breakdown structures under non-reacting conditions. It was found that the vortex breakdown structures under isothermal conditions were insensitive to the Reynolds number (Re) for Re ≥ 10000; however, the stability of the flames and operability range of the burner were highly sensitive to Re as well as to equivalence ratio (ϕ). The equivalence ratio was varied at various Reynolds numbers to observe different regimes of the flame ranging from the lean blowout (LBO) limit to the flashback limit. The LBO limit was found to be mainly a function of equivalence ratio while being nearly independent of the Reynolds number, whereas the occurrence of flashback showed distinct characteristics for different ranges of the Reynolds number. At low and moderate Reynolds numbers, (Re ≤ 17000), flashback occurred when increasing ϕ from lean towards stoichiometric conditions. The coupling between the flow field and heat release induces vortex breakdown in the mixing tube and initiates flashback. In contrast, at higher Reynolds numbers (Re > 17000) no flashback was observed even when ϕ was increased to stoichiometric conditions. At these conditions with high Re, the increase in the bulk flow velocity affects the vortex breakdown structure, pushing the vortex breakdown downstream, which in turn prevents the flame from flashing back into the mixing tube.

A combined technique of Kalman filter, artificial neural network and fuzzy logic for gas turbines and signal fault isolation

The target of this paper is the performance-based diagnostics of a gas turbine for the automated early detection of components malfunctions. The paper proposes a new combination of multiple methodologies for the performance-based diagnostics of single and multiple failures on a two-spool engine. The aim of this technique is to combine the strength of each methodology and provide a high success rate for single and multiple failures with the presence of measurement malfunctions. A combination of KF (Kalman Filter), ANN (Artificial Neural Network) and FL (Fuzzy Logic) is used in this research in order to improve the success rate, to increase the flexibility and the number of failures detected and to combine the strength of multiple methods to have a more robust solution. The Kalman filter has in his strength the measurement noise treatment, the artificial neural network the simulation and prediction of reference and deteriorated performance profile and the fuzzy logic the categorization flexibility, which is used to quantify and classify the failures. In the area of GT (Gas Turbine) diagnostics, the multiple failures in combination with measurement issues and the utilization of multiple methods for a 2-spool industrial gas turbine engine has not been investigated extensively.This paper reports the key contribution of each component of the methodology and brief the results in the quantification and classification success rate. The methodology is tested for constant deterioration and increasing noise and for random deterioration. For the random deterioration and nominal noise of 0.4%, in particular, the quantification success rate is above 92.0%, while the classification success rate is above 95.1%. Moreover, the speed of the data processing (1.7 s/sample) proves the suitability of this methodology for online diagnostics.

저선회 모델 연소기의 스월러 코어 막힘률에 따른 난류연소유동장에 관한 수치적 연구

A low swirl combustor is an alternative technology to sustain a stable flame and to meet the required emission restriction of industrial gas turbine engines. The flame is lifted above the combustor front wall due to a balance between the flame speed and the local flow velocity. The present study is on the numerical simulations of reacting flows of a low swirl model combustor. The flamelet-generated manifold (FGM) method, which is one of the combustion chemistry reduction techniques, is coupled with a large eddy simulation solver. For a premixed CH₄ and air inflow at an equivalence ratio of 0.65, the combustion flow field in the combustor is investigated for two kinds of core blockage configurations, using three-dimensional large eddy simulations based on FGM. Compared to conventional swirl combustors, the low swirl model combustor presents turbulent core flow through the center body of the swirler, which turns out to play an important role in producing stable lifted flames.

Electrodeposited Mcraly Coatings for Gas Turbine Engine Applications

Electrolytic codeposition is a promising alternative process for fabricating MCrAlY coatings (where M = Ni, Co, or Ni + Co) for protecting high-temperature components used in various industrial gas turbine engines. The coating process involves codeposition of CrAlY-based particles and a metal matrix of Ni, Co, or (Ni,Co), followed by a diffusion treatment to convert the composite coating to the desired MCrAlY microstructure. Despite the advantages of low cost and non-line-of-sight, this coating process is less known compared to electron beam-physical vapor deposition and thermal spray processes for manufacturing high-temperature coatings. This presentation provides an overview of the electrodeposited MCrAlY coatings for gas turbine applications, highlighting the unique features of this coating process and some important findings in the past 30 years. Recent coating development progress from a collaborative research project between Tennessee Tech University and Oak Ridge National Laboratory will be presented. The effects of additional elements (e.g., Ta, Si and Hf) on the coating oxidation/corrosion performance will be discussed.

Metallurgical Failure Analysis of Cracked First Stage Vane of Heavy-Duty Industrial Gas Turbine Engine for Power Generation

Abstract A first stage turbine vane of a heavy-duty gas turbine engine, exhibiting an outward bulge of approximately 0.6 mm and a visible crack in the top coating, was delivered by the client for a detailed destructive failure investigation. The subject component was an experimental part used in a test field engine. The suction side wall of the casting was cut off to reveal a gaping crack on the inside of the aft cavity that was also visible by borescopic inspection. The cooling insert of the aft cavity was clean and did not have any blocked cooling holes. The cooling pattern on the inside wall of the aft cavity was unremarkable. No evidence whatever of impact damage was found on the suction side surface of the subject vane in the cracked region. The hypothesis as to the most probable root cause of the cracking that is still standing is a combination of low wall thickness, non-optimal process parameters for bond coat pre-heat, and potentially high thermal/mechanical loading during engine operation. It appears this is not a wide-spread phenomenon but rather an isolated occurrence.

Industrial gas turbine engine response and combustion performance to fuel changeovers in compositions and heating values

Extension of gaseous fuel flexibility for an industrial gas turbine engine is reported in this paper. A Siemens SGT-400 engine with 13.4 MW rating with hybrid combustion system configuration was string tested to operate on and switch between three different gaseous fuels with temperature corrected Wobbe Index varying between 45 MJ/m3, 38 MJ/m3 and 30 MJ/m3. The alteration of fuel heating value was achieved by injection or withdrawal of N2 into or from the fuel system. The results show that NOx decreases for fuels with lower heating value at the same engine output power and most importantly the engine can maintain stable operation on, and switching between these three different fuels with heating values changeover rate faster than 10% per minute without shutdown or change in load condition. The effect of gaseous fuels with different compositions and heating values on turbine entry temperature, NOx emission and combustion was further investigated in a high pressure combustion testing rig and it is found that the peak temperature and temperature gradient of turbine entry temperature are reduced by application of lower heating value of fuels. It is also noted that for the fuels having the same heating value different diluent, either CO2 or N2, has insignificant effect on hot gas temperature profile, however, different diluent does have impact on NOx emission and NOx emissions is lower by up to 5 ppm if CO2 is selected as diluent compared to N2 as diluent. The physical and chemical mechanisms for NOx reduction for gas turbine engines operating on lower heating value fuels have been identified: improving fuel and air mixing by stronger fuel to air momentum ratio and enhanced turbulence level, slowing chemical reaction by decreasing laminar flame speed and reduction of thermal NOx due to decrease in adiabatic flame temperature and flame shifted to downstream.

On increasing the attractiveness of domestic industrial gas-turbine engines when participating in tenders for equipment procurement

On increasing the attractiveness of domestic industrial gas-turbine engines when participating in tenders for equipment procurement

Gas path fault diagnostics using a hybrid intelligent method for industrial gas turbine engines

There are many challenges against an accurate gas turbine fault diagnostics, such as the nonlinearity of the engine health, the measurement uncertainty, and the occurrence of simultaneous faults. The conventional methods have limitations in effectively handling these challenges. In this paper, a hybrid intelligent technique is devised by integrating an autoassociative neural network (AANN), nested machine learning (ML) classifiers, and a multilayer perceptron (MLP). The AANN module is used as a data preprocessor to reduce measurement noise and extract the important features for visualisation and fault diagnostics. The features are extracted from the bottleneck layer output values based on the concept of the nonlinear principal component analysis (NLPCA). The nested classifier modules are then used in such a manner that fault and no-fault conditions, component and sensor faults, and different component faults are distinguished hierarchically. As part of the classification, evaluation of the fault classification performance of five widely used ML techniques aiming to identify alternative approaches is undertaken. In the end, the MLP approximator is utilised to estimate the magnitude of the isolated component faults in terms of flow capacity and isentropic efficiency indices. The developed system was implemented to diagnose up to three simultaneous faults in a two-shaft industrial gas turbine engine. Its robustness towards the measurement uncertainty was also evaluated based on Gaussian noise corrupted data. The test results show the derivable benefits of integrating two or more methods in engine diagnostics on the basis of offsetting the weakness of the one with the strength of another.

Performance-based fault diagnosis of a gas turbine engine using an integrated support vector machine and artificial neural network method

An effective and reliable gas path diagnostic method that could be used to detect, isolate, and identify gas turbine degradations is crucial in a gas turbine condition-based maintenance. In this paper, we proposed a new combined technique of artificial neural network and support vector machine for a two-shaft industrial gas turbine engine gas path diagnostics. To this end, an autoassociative neural network is used as a preprocessor to minimize noise and generate necessary features, a nested support vector machine to classify gas path faults, and a multilayer perceptron to assess the magnitude of the faults. The necessary data to train and test the method are obtained from a performance model of the case engine under steady-state operating conditions. The test results indicate that the proposed method can diagnose both single- and multiple-component faults successfully and shows a clear advantage over some other methods in terms of multiple fault diagnosis. Moreover, 5-8 sets of measurements have been used to assess the prediction accuracy, and only a 2.3% difference was observed. This result indicates that the proposed method can be used for multiple fault diagnosis of gas turbines with limited measurements.

МОДЕРНІЗАЦІЯ УКРАЇНСЬКОЇ ГАЗОТРАНСПОРТНОЇ СИСТЕМИ: НАЦІОНАЛЬНІ ТА МІЖНАРОДНІ ВИКЛИКИ

Показано, що газотранспортна система України відіграє ключову роль у національній енергетиці та поставках російського газу до ЄС. Проте вона є дуже застарілою, має низьку конкурентоспроможність і потребує невідкладної модернізації. Особливо це стосується техніко-технологічних та організаційно-управлінських складових української ГТС.У цьому зв’язку необхідно комплексно дослідити умови, напрями і механізми модернізації української ГТС у контексті конвергенції українського та європейського газових ринків для посилення енергетичної безпеки і досягнення сталого розвитку України та ЄС на основі дотримання вимог Третього енергопакета.Виявлено особливості модернізації ГТС України, які пов’язані з її великими масштабами (понад 38,5 тис. км), зношеністю основних фондів, дуже неефективною системою управління, низькою (менш як на 50%) завантаженістю виробничих потужностей, що призводить до малої ефективності функціонування ГТС, яка потребує значних коштів для модернізації.Важливим напрямом техніко-технологічної модернізації ГТС є якнайшвидше створення спеціально для України промислових газотурбінних двигунів нового покоління, здатних підвищити ККД до рівня кращих зарубіжних аналогів. Окремою складовою техніко-технологічної модернізації української ГТС є адаптація її ланок до функціонування в умовах неповного використання транспортно-перекачувальних потужностей.Зроблено висновок про те, що без партнерства з провідними іноземними газотранспортними компаніями як у процесі поточної модернізації, так і надалі підвищити конкурентоспроможність української ГТС до європейського рівня принципово неможливо. Партнери потрібні українському оператору не стільки для обміну досвідом, скільки для кардинальної модернізації вітчизняної ГТС. Обраний нами партнер повинен взяти на себе частину відповідальності за майбутню долю української ГТС.

Data Analytics for Performance Monitoring of Gas Turbine Engine

Performance analysis of a low power rating and partially loaded industrial gas turbine engine (GTE) was carried out by using a model-free data analytic approach. By adopting an efficient input selection method, several performance indices (PI) are proposed to quantify the performance of the GTE. These indices are extracted using engine operating data related to power output and parameters related to fuel consumption, and validated with engine performance monitoring measurements for a three year period corresponding to one time between overhaul intervals. The dependency of the PIs on ambient temperature has been studied by using linear and polynomial fitting curves. Then novel methods are introduced for analysis of short-term and long-term performance deterioration arising from compressor fouling and structural degradation respectively. The results have clearly shown the ability of the proposed PIs to detect short-term compressor fouling as well as long-term performance deterioration, which is directly relevant to the Prognostics and Health Management of gas turbine engine.

Effects of Compressor Fouling and Compressor Turbine Degradation on Engine Creep Life Consumption

The effect of engine degradation in the form of compressor fouling and compressor turbine degradation on the creep life consumption of the high-pressure (HP) turbine blades of an LM2500+ industrial gas turbine engine is investigated in this work. The degradations are flow capacity degradation and isentropic efficiency degradation. An engine model was created in Cranfield gas turbine performance and diagnostics software, pythia. Blade thermal and stress models were developed together with the Larson–Miller parameter (LMP) method for creep life analysis. The percentage decreases in creep life due to each effect were examined. For the engine considered, compressor degradation has more impact on engine creep life toward peak power operation, while HP turbine degradation has more impact on creep life at lower power levels. The results of this work will give engine operators an idea of how engine components creep life is consumed and make reasonable decisions concerning operating at part loads.