A Novel Approach for Gas Turbine Condition Monitoring Combining CUSUM Technique and Artificial Neural Network

Investigation of a novel condition monitoring approach, combining artificial neural network (ANN) with a sequential analysis technique, has been reported in this paper. For this purpose operational data from a Siemens SGT600 gas turbine has been employed for the training of an ANN model. This ANN model is subsequently used for the prediction of performance parameters of the gas turbine. Simulated anomalies are introduced on two different sets of operational data, acquired one year apart, whereupon this data is compared with corresponding ANN predictions. The cumulative sum (CUSUM) technique is used to improve and facilitate the detection of such anomalies in the gas turbine’s performance. The results are promising, displaying fast detection of small changes and detection of changes even for a degraded gas turbine.

A Survey of New Technologies Used by Siemens Energy for the Monitoring and Diagnosis of a Global Fleet of Power Generation Systems

Siemens has been on the cutting edge of the power generation business for over a century and has been providing diagnostics systems design and implementation since the early 1980s. Siemens Power Diagnostics® Services is designed to maximize plant performance, availability and profitability. Engineering knowledge, combined with the use of sophisticated tools, provides trending and analysis capabilities to address a broad range of operating needs specific to each customer. The goal of Power Diagnostics® is to enhance Siemens assistance to our customers through the detection of impending operational problems thereby helping to minimize unplanned outages and maximize power generation availability. A variety of new technologies are being harnessed to further this goal. A survey and discussion of these technologies will be the goal of this paper. Some of the projects discussed will be; Advances in the Power Plant Automated Diagnostics Systems, Blade Vibration Monitor (BVM), Fiber Optic Vibration Monitor (FOVM), and the Radio Frequency Monitor (RFM). The development and verification phases of research projects have often been conducted at customer sites. Many aspects of these technologies are new and will be of interest to gas turbine engineers as they are not widely applied yet. It is hoped that the reader will gain a new appreciation for the scope of modern diagnostic methods for power generation systems.

New Model Based Gas Turbine Fault Diagnostics Using 1D Engine Model and Nonlinear Identification Algorithms

Gas turbine fault identification has been used worldwide in many aero and land engines. Model based techniques have improved isolation of faults in components and stages’ fault trend monitoring. In this paper a powerful nonlinear fault identification system is developed in order to predict the location and trend of faults in two major components: compressor and turbine. For this purpose Siemens V94.2 gas turbine engine is modeled one dimensionally. The compressor is simulated using stage stacking technique, while a stage by stage blade cooling model has been used in simulation of the turbine. New fault model has been used for turbine, in which a degradation distribution has been considered for turbine stages’ performance. In order to validate the identification system with a real case, a combined fault model (a combination of existing faults models) for compressor is used. Also the first stage of the turbine is degraded alone while keeping the other stages healthy. The target was to identify the faulty stages not faulty components. The imposed faults are one of the most common faults in a gas turbine engine and the problem is one of the most difficult cases. Results show that the fault diagnostic system could isolate faults between compressor and turbine. It also predicts the location of faulty stages of each component. The most interesting result is that the fault is predicted only in the first stage (faulty stage) of the turbine while other stages are identified as healthy. Also combined fault of compressor is well identified. However, the magnitude of degradation could not be well predicted but, using more detailed models as well as better data from gas turbine exhaust temperature, will enhance diagnostic results.

Improved Compressor Maps Using Approximate Solutions to the Moore-Greitzer Model

Producing compressor maps is time consuming, costly and error prone and many data samples must be collected to give sufficient accuracy. Even then, expert input is typically required to fine tune the map to the appropriate shape. In this paper, we take some of that expertise and incorporate it in the smoothing process. The main piece of knowledge used is the cubic approximation for speed lines derived from the Moore Greitzer model. This well accepted approximation captures much of the general performance properties of compressors. But it is also widely recognized as only being very roughly true of real compressors. Nevertheless, we show that embedding this approximation, however limited, in the smoothing process results in accurate interpolation and extrapolation. The aim of this work is to substantially reduce the need for human input in the fitting process. We also anticipate a number of other benefits: less data is needed, with the commensurate time and money saved; the data collection process can be monitored for possible problems; changes in the map can be quantified and, when sufficiently small, data collection can be terminated.

Engine Conceptual Design Studies for a Hybrid Wing Body Aircraft

Worldwide concerns of air quality and climate change have made environmental protection one of the most critical issues in aviation today. NASA’s current Fundamental Aeronautics research program is directed at three generations of aircraft in the near, mid and far term, with initial operating capability around 2015, 2020, and 2030, respectively. Each generation has associated goals for fuel burn, NOx, noise, and field-length reductions relative to today’s aircrafts. The research for the 2020 generation is directed at enabling a hybrid wing body (HWB) aircraft to meet NASA’s aggressive technology goals. This paper presents the conceptual cycle and mechanical designs of the two engine concepts, podded and embedded systems, which were proposed for a HWB cargo freighter. They are expected to offer significant benefits in noise reductions without compromising the fuel burn.

Fundamental Differences Between Conventional and Geared Turbofans

The potential for improving the thermodynamic efficiency of aircraft engines is limited because the aerodynamic quality of the turbomachines has already achieved a very high level. While in the past increasing burner exit temperature did contribute to better cycle efficiency, this is no longer the case with today’s temperatures in the range of 1900...2000K. Increasing the cycle pressure ratio above 40 will yield only a small fuel consumption benefit. Therefore the only way to improve the fuel efficiency of aircraft engines significantly is to increase bypass ratio — which yields higher propulsive efficiency. A purely thermodynamic cycle study shows that specific fuel consumption decreases continuously with increasing bypass ratio. However, thermodynamics alone is a too simplistic view of the problem. A conventional direct drive turbofan of bypass ratio 6 looks very different to an engine with bypass ratio 10. Increasing bypass ratio above 10 makes it attractive to design an engine with a gearbox to separate the fan speed from the other low pressure components. Different rules apply for optimizing turbofans of conventional designs and those with a gearbox. This paper describes various criteria to be considered for optimizing the respective engines and their components. For illustrating the main differences between conventional and geared turbofans it is assumed that an existing core of medium pressure ratio with a two stage high pressure turbine is to be used. The design of the engines is done for takeoff rating because this is the mechanically most challenging condition. For each engine the flow annulus is examined and stress calculations for the disks are performed. The result of the integrated aero-thermodynamic and mechanical study allows a comparison of the fundamental differences between conventional and geared turbofans. At the same bypass ratio there will be no significant difference in specific fuel consumption between the alternative designs. The main difference is in the parts count which is much lower for the geared turbofan than for the conventional engine. However, these parts will be mechanically much more challenging than those of a conventional turbofan. If the bypass ratio is increased significantly above 10, then the geared turbofan becomes more and more attractive and the conventional turbofan design is no longer a real option. The maximum practical bypass ratio for ducted fans depends on the nacelle drag and how the installation problems can be solved.

Simultaneous Noise and Performance Measurements for High-Speed Jet Noise Reduction Technologies

Model scale tests are conducted to assess the Noise/Performance trade for high speed jet noise reduction technologies. It is demonstrated that measuring the near field acoustic signature with a microphone array can be used to assess the far field noise using a procedure known as acoustic holography. The near field noise measurement is mathematically propagated producing an estimate of the noise level at the new location. Outward propagation produces an estimate of the far field noise. Propagation toward the jet axis produces the source distribution. Tests are conducted on convergent/divergent nozzles with three different area ratios, and several different chevron geometries. Noise is characterized by two independent processes: Shock cell noise radiating in the forward quadrant is produced when the nozzle is operated at non-ideally expanded conditions. Mach wave radiation propagates into the aft quadrant when the exhaust temperature is elevated. These results show good agreement with actual far field measurements from tests in the GE Cell 41 Acoustic Test Facility. Simultaneous performance measurement shows the change in thrust coefficient for different test conditions and configurations. Chevrons attached to the nozzle exit can reduce the noise by several dB at the expense of a minimal thrust loss.

Diagnostic Analysis of Maintenance Data of a Gas Turbine for Driving an Electric Generator

Monitoring algorithms analyzing measured gas path variables provide invaluable insight into gas turbine operating health. Some useful information about a gas turbine and its measurement system can be obtained from a direct analysis of raw measurements. To draw more comprehensive diagnostic information, deviations are usually calculated as discrepancies between the measured and baseline values of monitored variables. The deviations can serve as good indicators of different engine degradation mechanisms. However, there are many negative factors that tend to mask degradation effects. For a long period of time we have analyzed quality of gas path measurement data and a deviation accuracy problem of a gas turbine power plant driving a natural gas pipeline compressor. Possible error sources were examined and some methods were proposed to improve the accuracy of deviation calculations. This paper looks at maintenance data of another object, the General Electric LM2500 gas turbine used as a drive of an electric generator. The data cover prolonged periods of axial compressor fouling with washings between them, and provide valuable information for a deviation examination. In order to reduce deviation errors, the paper considers different cases of the abnormal functioning of the sensors and baseline model inadequacy and proposes measures to avoid them. As a result of these and previous efforts, the deviations have become good fouling indicators. They are capable to quantify the increase of exhaust gas temperature (EGT) and, consequently, to improve planning axial compressor washings.

Requirements for Gas Turbine Inlet Systems in Russia

Russian power generation, oil and gas businesses are rapidly growing. Installation of new industrial gas turbines is booming to fulfill the demand from economic growth. Russia is a unique country from the annual temperature variation point of view. Some regions may reach up to 100C. One of the biggest challenges for world producers of gas turbines in Russia is the ability to operate products at power plants during cold winters, when ambient temperature might be −60C for a couple of weeks in a row. The reliability and availability of the equipment during the cold season is very critical. Design of inlet systems and filter houses for the Russian market, specifically for northern regions, has a lot of specifics and engineering challenges. Joint Stock Company CKTI is the biggest Russian supplier of air intake systems for industrial gas turbines and axial-flow compressors. In 1969 this enterprise designed and installed the first inlet for the power plant Dagskaya GRES (State Regional Electric Power Plant) with the first 100MW gas-turbine which was designed and manufactured by LMZ. Since the late 1960s CKTI has designed and manufactured inlet systems for the world market and been the main supplier for the Russian market. During the last two years CKTI has designed inlet systems for a broad variety of gas turbine engines ranging from 24MW up to 110MW turbines which are used for power generation and as a mechanical drive for the oil and gas industry. CKTI inlet systems with filtering devices or houses are successfully used in different climate zones including the world’s coldest city Yakutsk and hot Nigeria. CKTI has established CTQs (Critical to quality) and requirements for industrial gas turbine inlet systems which will be installed in Russia in different climate zones for all types of energy installations. The last NPI project of the inlet system, including a nonstandard layout, was done for a small gas-turbine engine which is installed on a railway cart. This arrangement is designed to clean railway lines with the exhaust jet in a quarry during the winter. The design of the inlet system with efficient multistage compressor extraction for deicing, dust and snow resistance has an interesting solution. The detailed description of challenges, weather requirements, calculations, losses, and design methodologies to qualify the system for tough requirements, are described in the paper.

Blended Education in Turbomachinery and Fluid Dynamics

The paper deals with blended education in turbomachinery and fluid dynamics courses in Finland. The teaching methodology of these courses has been developed to comply with the new challenges of the education in technology. Presently six of the courses in the curriculum are following the schemes explained in this presentation. The courses are studied in the last year of the Bachelor level and in the Masters level quantifying from 2 to 4 ECTS credits. Students get all the material from the teaching platform in the web, which can be accessed freely anytime and practically from anywhere. Before attending the teaching events, the students go through the study material, perform several exercises and take a quiz, which can give them extra points for the exam tally. The contact teaching of the course is divided into four Learning Sessions of four hours. The first half is reserved to deepen the acquired knowledge, and performed in a way to attract a more interactive atmosphere. In the second half the students are divided to groups, where they solve more difficult study exercises compared to those they already have trained on. As the students are expected to study with the material of blended learning in advance, the percentage of the contact hours has to be lowered in comparison to the traditional teaching in order to maintain a balance with the credits in the course. However, with the acquired knowledge, the students are more interactive with the teachers and the teaching becomes more efficient. The students have given positive feedback on the courses. The instructors have found that the blended learning is not necessary an easier task, although there are less contact hours with the student. The efficiency of teaching has increased and the teaching is more rewarding. Both the students and the teachers found that blended education suited best for student groups around 10 students.