Modeling a Practical Dual-Fuel Gas Turbine Power Generation System Using Dynamic Neural Network and Deep Learning

Accurate simulations of gas turbines’ dynamic performance are essential for improvements in their practical performance and advancements in sustainable energy production. This paper presents models with extremely accurate simulations for a real dual-fuel gas turbine using two state-of-the-art techniques of neural networks: the dynamic neural network and deep neural network. The dynamic neural network has been realized via a nonlinear autoregressive network with exogenous inputs (NARX) artificial neural network (ANN), and the deep neural network has been based on a convolutional neural network (CNN). The outputs selected for simulations are: the output power, the exhausted temperature and the turbine speed or system frequency, whereas the inputs are the natural gas (NG) control valve, the pilot gas control valve and the compressor variables. The data-sets have been prepared in three essential formats for the training and validation of the networks: normalized data, standardized data and SI units’ data. Rigorous effort has been carried out for wide-range trials regarding tweaking the network structures and hyper-parameters, which leads to highly satisfactory results for both models (overall, the minimum recorded MSE in the training of the MISO NARX was 6.2626 × 10−9 and the maximum MSE that was recorded for the MISO CNN was 2.9210 × 10−4, for more than 15 h of GT operation). The results have shown a comparable satisfactory performance for both dynamic NARX ANN and the CNN with a slight superiority of NARX. It can be newly argued that the dynamic ANN is better than the deep learning ANN for the time-based performance simulation of gas turbines (GTs).

State of the Art in Separation Processes for Alternative Working Fluids in Clean and Efficient Power Generation

Gas turbines must now comply with much stricter emission control regulations. In fact, to combat the greenhouse effect, regulatory authorities have drastically reduced allowable emission levels. For example, in less than 12 years, the United States’ Clean Air Act issued the New Source Performance Standards (NSPS), which tightened the NOx emission margin of natural gas combustion (from 75 ppm to 10 ppm). On the other hand, despite those efforts, the high demand for energy produced by fossil-fueled gas turbines in power plants has resulted in dramatic increases in anthropogenic CO2 and NOx emitted by gas combustors. Most systems responsible for these undesirable emissions are directly linked to power generation, with gas turbines playing a pivotal role. Yet, gas turbines are still widely used in power plants and will continue to meet the growing demand. Therefore, sequestration and separation techniques such as Carbon Capture and Storage (CCS) and Air Separation Units (ASU) are essential to reduce CO2 and NOx emissions while allowing large amounts of power to be generated from these systems. This paper provides an in-depth examination of the current state of the art in alternative working fluids utilized in the power generation industry (i.e., gas turbines, combustion). In addition, this paper highlights the recent contribution of integrating separation techniques, such as air separation, steam methane reforming, and water-gas shifting, to the power generation industry to facilitate a continuous and adequate supply of alternative working fluids.

Determination of average relative capital investment of 30–125 MW combined-cycle plants commissioned at Russian thermal power plants in 2015–2020. Comparative analysis with data obtained in 2010–2014

The present work examines average relative capital investment and fuel consumption for electric and thermal energy supply of the combined-cycle plants having 30–125 MW gas turbines commissioned at Russian thermal power plants in 2015–2020. In this work, we used general calculation methods of average relative capital investments and fuel consumption for the electrical and thermal energy supply using power equipment of thermal power plants. To assess the scope of commissioning gas turbines incorporated into the combined-cycle plants, they were classified into three groups by electrical power: 30–59 MW, 60–99 MW and 100–125 MW. The scope of commissioning gas turbines incorporated into the Russian combined-cycle plants in 2015–2020 was analysed. The average relative capital invest-ment in combined-cycle plants having 30–125 MW gas turbines, as well as the average specific fuel consumption for the electrical and thermal energy supply, were calculated. The calculations were carried out for each part of combined-cycle plants integrated into thermal power plants with a breakdown by seven Unified Energy Systems of Russia. The quantita-tive commissioning of gas turbines is compared for the periods from 2010 to the economic crisis of 2014 and after 2014 to the present: a ~2.5-fold decrease is demonstrated. A preliminary evaluation of the increase in average relative capital investment in combined-cycle plants having gas turbines of the same electric power was performed.

Octave Band Technique for Noise Measurement at the Source, Path, and Receiver of Gas Turbines in Oil and Gas Facilities

Noise measurement is essential for industrial usage. However, further attention to preventing noise pollution is needed, especially when working with equipment generating a high noise level, such as gas turbines. This study aims to determine the best way to perform noise measurement and analyze the octave band frequency generated by noise pollution caused by gas turbine equipment. Data from site measurements show that the gas turbines produce more than 85 dB of noise with a Z-weighted measurement. A noise measuring investigation was conducted to obtain the data for the 1/3 octave band. A frequency-domain was used to comprehend the properties of the noise measurement frequency band. The frequency band was classified into three different zones called low, medium, and high frequency, which is useful in noise measurement analysis to identify a viable solution to reduce the noise. On-site sampling was performed at the source, path, and receiver of three separate gas turbine locations within oil and gas operations. The 1/3 octave band data collection results at the sound source, path, and receiver demonstrate the noise level distribution at the perimeter of gas turbine installations in the low and medium frequency ranges. Most of the high noise frequency range is between 250 Hz and 2 kHz for source, path, and receiver. All acquired values are compared to the Department of Safety and Health (Occupational Safety and Health (Noise Exposure) Regulations 2019 in Malaysia. As a result, oil and gas service operators can monitor and take countermeasures to limit noise exposure at oil and gas facilities.

Effects of Intrinsic Flame Instabilities On Thermoacoustic Oscillations in Lean Premixed Gas Turbines

Thermoacoustic instabilities are commonly encountered in the development of aeroengines and rocket motors. Research on the fundamental mechanism of thermoacoustic instabilities is beneficial for the optimal design of these engine systems. In the present study, a thermoacoustic instability model based on the lean premixed gas turbines (LPGT) combustion system was established. The longitudinal distribution of heat release caused by the intrinsic instability of flame front is considered in this model. Effects of different heat release distributions and characteristics parameters of the premixed gas (Lewis number Le, Zeldovich Number and Prandtl number Pr) on thermoacoustic instability behaviors of the LPGT system are investigated based on this model. Results show that the LPGT system features with two kinds of unstable thermoacoustic modes. The first one corresponds to the natural acoustic mode of the plenum and the second one corresponds to that of the combustion chamber. The characteristic parameters of premixed gases have a large impact on the stability of the system and even can change the system from stable to unstable state.

Estimation and Mitigation of Unknown Airplane Installation Effects on GPA Diagnostics

In gas turbines used for airplane propulsion, the number of sensors are kept at a minimum for accurate control and safe operation. Additionally, when data are communicated between the airplane main computer and the various subsystems, different systems may have different constraints and requirements regarding what data transmit. Early in the design process, these parameters are relatively easy to change, compared to a mature product. If the gas turbine diagnostic system is not considered early in the design process, it may lead to diagnostic functions having to operate with reduced amount of data. In this paper, a scenario where the diagnostic function cannot obtain airplane installation effects is considered. The installation effects in question is air intake pressure loss (pressure recovery), bleed flow and shaft power extraction. A framework is presented where the unknown installation effects are estimated based on available data through surrogate models, which is incorporated into the diagnostic framework. The method has been evaluated for a low-bypass turbofan with two different sensor suites. It has also been evaluated for two different diagnostic schemes, both determined and underdetermined. Results show that, compared to assuming a best-guess constant-bleed and shaft power, the proposed method reduce the RMS in health parameter estimation from 26% up to 80% for the selected health parameters. At the same time, the proposed method show the same degradation pattern as if the installation effects were known.

Assessing NO2-Hydrocarbon Interactions during Combustion of NO2/Alkane/Ar Mixtures in a Shock Tube Using CO Time Histories

Modern gas turbines use combustion chemistry during the design phase to optimize their efficiency and reduce emissions of regulated pollutants such as NOx. The detailed understanding of the interactions during NOx and natural gas during combustion is therefore necessary for this optimization step. To better assess such interactions, NO2 was used as a sole oxidant during the oxidation of CH4 and C2H6 (the main components of natural gas) in a shock tube. The evolution of the CO mole fraction was followed by laser-absorption spectroscopy from dilute mixtures at around 1.2 atm. The experimental CO profiles were compared to several modern detailed kinetics mechanisms from the literature: models tuned to characterize NOx-hydrocarbons interactions, base-chemistry models (C0–C4) that contain a NOx sub-mechanism, and a nitromethane model. The comparison between the models and the experimental profiles showed that most modern NOx-hydrocarbon detailed kinetics mechanisms are not very accurate, while the base chemistry models were lacking accuracy overall as well. The nitromethane model and one hydrocarbon/NOx model were in relatively good agreement with the data over the entire range of conditions investigated, although there is still room for improvement. The numerical analysis of the results showed that while the models considered predict the same reaction pathways from the fuels to CO, they can be very inconsistent in the selection of the reaction rate coefficients. This variation is especially true for ethane, for which a larger disagreement with the data was generally observed.

Measurement of Heat Transfer and Flow Structures in a Closed Rotating Cavity

Buoyancy-induced flow occurs inside the rotating compressor cavities of gas turbines. These cavities are usually open at the inner radius, but in some industrial gas turbines, they are effectively closed. This paper presents measurements of the disc heat transfer and rotating flow structures in a closed cavity over a wide range of engine relevant conditions. These experimentally derived distributions of disc temperature and heat flux are the first of their kind to be published. The radial distribution of the non-dimensional disc temperature virtually collapsed onto a single curve over the full experimental range. There was a small, monotonic departure from this common curve with increasing Reynolds number; this was attributed to compressibility effects where the core temperature increases as the rotational speed increases. These results imply that, if compressibility effects are negligible, all rotating closed cavities should have a disc temperature distribution uniquely related to the geometry and disc material; this is of important practical use to the engine designer. Unsteady pressure sensors detected either three or four vortex pairs across the experimental range. The number of pairs changed with Grashof number, and the structures slipped relative to the rotating discs by less than 1% of the disc speed.

Study on nitrogen barrier protection of an airend oil-free compressor bearings in H2 compression

The oil free compressors were specially designed for air compression. The National Research and Development Institute for Gas Turbines COMOTI gained a great deal of experience in producing/designing certified oil injection screw compressors for the natural gas field and for several years it has been focusing its research on the use of “dry” (oil-free) compressors in natural gas compression and more recently in hydrogen compression. Working with an explosive gas, one of an idea was to use a nitrogen barrier in oil bearing sealing, which are open source of gases in the atmosphere for such compressors. Worldwide, on-site nitrogen generators have been developed for a purity range of 95…99.5%, and that nitrogen can be supplied in any environment conditions. The present paper will address nitrogen flow with low percentage of oxygen for bearing sealing at the working pressure, the nitrogen consumption, ideas for H2 re-injection and the influence over the global efficiency of the process. Due to the Energy Strategy worldwide, and the studies regarding production, transport and storage of hydrogen in natural gas network, COMOTI has involved researches in developing such possibilities and to express a point of view in existing research in the newly created industry.