The modern gas turbine engine has been used in current power generation industry for almost half a century. They are designed to operate with the best efficiency during normal operating conditions and at specific operating points. However, due to power grid demands, different ambient temperatures, fuel types, relative humidity and driven equipment speed the gas turbine units have to work today on partial load too, which can affect the hot gas path condition and life expectancy. At these off-design conditions, gas turbine's efficiency and life deterioration rate might significantly deviate from the design specifications. In this paper, a digital twin concept for gas turbine unit off-design performance prediction (AxSTREAM® platform) is used. The description of created digital twin is presented. The validation of proposed gas turbine unit digital twin is carried out by comparison with literature source test data. The GTU performance estimation controlling cooling air at part load modes using digital twin was performed.
Central-station power plants (CSPP) are the main provider of energy today. In the process of power generation at central-power stations, about 67% of primary energy is wasted. Distributed cogeneration or combined heat and power (CHP) systems are an alternative to central-station power plants. In these systems, an electrical generation system located in a residence or at a commercial site consumes natural gas to generate electricity locally and then the exhaust heat is utilized for local heating needs (in contrast to being wasted at central-stations). Microturbines offer a number of potential advantages compared to other technologies for small-scale power generation. For example, compact size and low-weight leading to reduced civil engineering costs, a small number of moving parts, lower noise and vibration, multi-fuel capabilities, low maintenance cost as well as opportunities for lower emissions. Inverter generators allow using micro-turbines of different shaft rotation speed that opens opportunities to unit optimization at off-design modes. The common approach to predict the off-design performance of gas turbine unit is the mapping of the compressor and the turbine separately and the consequent matching of common operation points. However, the above-mentioned approach might be rather inaccurate if the unit has some secondary flows. In this article an alternative approach for predicting off-design performance without using component maps is presented. Here the off-design performance is done by direct calculation of the components performances. On each off-design mode, the recalculation of the characteristic of all scheme components, including a compressor, gas turbine, combustor, recuperator and secondary flow system is performed. The different approaches for obtaining the performance at off-design modes considering the peculiarities of the gas turbine engine are presented in this paper.
This paper demonstrates the application of artificial intelligence-driven turbomachinery design, its numerical performance predictions and their numerical validation. A common problem in the industrial application of turbomachinery is that readily available turbomachines are not necessarily matching the desired performance targets (performance characteristics) required for a specific application. Many machines operate under off-design conditions and hence are not operating at maximum efficiency. Traditional numerical analysis and response-driven optimization methods are ineffective and still too time-consuming and are particularly sensitive to changing performance targets. Most commercially available optimization algorithms are based on maximizing or minimizing a response function, for instance the standard error from a desired target performance characteristic of a turbomachine, by changing design variables. This work uses a newly developed artificial intelligence-based approach that is not dependent on the specific design target using the turbomachinery design software AxSTREAM from SoftInWay. Here a neural network was trained within a constraint design space by many samples of design variables and their respective numerical performance predictions. For the numerical verification of the designs the solver Simcenter STAR-CCM+ from Siemens was used. Subsequently the trained neural network was applied to generate a set of design parameters that satisfied the physically feasible desired target performance characteristics very fast. This trained neural network enabled an effective reversal of the traditional iterative design process where now the desired target performance characteristics became the input and the geometry became the output, turning it into a generative inverse design process. This method was applied to generate a centrifugal compressor design within a given geometrically and physically constraint design space. A specific desired target performance characteristic was chosen. The generated designs and results are presented in detail.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.