Abstract:Purpose -The purpose of this paper is to develop and compare conventional and neural network based controllers for gas turbines.Design/methodology/approach -Design of two different controllers is considered. These controllers consist of a NARMA-L2 which is an ANN-based nonlinear autoregressive moving average (NARMA) controller with feedback linearization, and a conventional proportional-integrator-derivative (PID) controller for a low-power aero gas turbine.They are briefly described and their parameters are a… Show more
“…Proceedings of SIMS 2020 Virtual, Finland, 22-24 September 2020 (Lazzaretto and Toffolo, 2001;Kim et al, 2001Kim et al, , 2002Ogaji et al, 2002;Basso et al, 2004;Jurado, 2005;Simani and Patton, 2008;Fast et al, 2008Fast et al, , 2009Yoru et al, 2009;Tavakoli et al, 2009;Fast and Palmé, 2010;Palmé et al, 2011;Bartolini et al, 2011;Asgari et al, 2013bAsgari et al, , 2015Asgari et al, , 2016. ANN has also been used for control-oriented modelling of GTs (Asgari et al, 2017). ANN may be used for fault identification and warning generation with high reliability.…”
In this study, a model of a single shaft gas turbine (GT) is developed by using artificial intelligence (AI). A recurrent neural network (RNN) is employed to train the datasets of the GT variables in Python programming environment by using Pyrenn Toolbox. The resulting model is validated against the Test datasets. Thirteen significant variables of the gas turbine are considered for the modelling process. The results show that the RNN model developed in this study is capable of performance prediction of the system with a high reliability and accuracy. This methodology provides a simple and effective approach in dynamic simulation of gas turbines, especially when real datasets are only available over a limited operational range and using simulated datasets for modelling and simulation purposes is unavoidable.
“…Proceedings of SIMS 2020 Virtual, Finland, 22-24 September 2020 (Lazzaretto and Toffolo, 2001;Kim et al, 2001Kim et al, , 2002Ogaji et al, 2002;Basso et al, 2004;Jurado, 2005;Simani and Patton, 2008;Fast et al, 2008Fast et al, , 2009Yoru et al, 2009;Tavakoli et al, 2009;Fast and Palmé, 2010;Palmé et al, 2011;Bartolini et al, 2011;Asgari et al, 2013bAsgari et al, , 2015Asgari et al, , 2016. ANN has also been used for control-oriented modelling of GTs (Asgari et al, 2017). ANN may be used for fault identification and warning generation with high reliability.…”
In this study, a model of a single shaft gas turbine (GT) is developed by using artificial intelligence (AI). A recurrent neural network (RNN) is employed to train the datasets of the GT variables in Python programming environment by using Pyrenn Toolbox. The resulting model is validated against the Test datasets. Thirteen significant variables of the gas turbine are considered for the modelling process. The results show that the RNN model developed in this study is capable of performance prediction of the system with a high reliability and accuracy. This methodology provides a simple and effective approach in dynamic simulation of gas turbines, especially when real datasets are only available over a limited operational range and using simulated datasets for modelling and simulation purposes is unavoidable.
“…The DNN is used to identify the dynamics of the turbofan engine, and the topological structure of the DNN is the single hidden layer feedforward neural network. 12 The inputs and outputs to train the DNN are the vector { y ( k ), y ( k − 1), y ( k − 2), …, y ( k − n ), u ( k − 1), u ( k − 2), …, u ( k − n )} and { y ( k + 1)}, where u is the fuel flow and y is the high-pressure rotor speed. In this article, the speed control of the turbofan engine based on the NARMA-L2 model is shown in Figure 2.Figure 2.The turbofan engine speed control based on NARMA-L2 model: (a) training stage; (b) operating stage.…”
Section: Turbofan Engine Speed Model and Controlmentioning
confidence: 99%
“…11 Asgari applied a NARMA-L2 controller to a single-shaft gas turbine, and the involved test also reveals the superior performance to the PID method. 12 Manonmani presents two intelligent control schemes, namely, neural predictive controller and NARMA-L2 controller, for better yield by humidity and temperature of growth conditions. 13 Compared to the applications above, the turbofan engine speed control is more complicated due to the modeling error and dynamic uncertainties in the envelope.…”
Nonlinear control of turbofan engines in the flight envelope has attracted much attention in consideration of the inherent nonlinearity of the engine dynamics. Most nonlinear control design techniques rely on the correction theory of reference model parameter to extend the typical flight operations from ground operation. However, dynamic uncertainties in flight envelope lead to the deviation of operating state, and it is negative to control performance. This article is to develop online correction neural network–based speed control approaches for the turbofan engine with dynamic uncertainty in the flight envelope. Two improved online correction nonlinear ways combined with nonlinear autoregressive moving average (NARMA) are proposed, such as gradient search nonlinear autoregressive moving average with feedback linearization (NARMA-L2) control and iterative learning NARMA-L2 control. The contribution of this article is to provide better control quality of fast regulation and less steady errors of engine speed by the proposed methodology in comparison to the conventional NARMA-L2 control. Some important results are reached on both turbofan engine controller design and dynamic uncertainty tolerance at the typical flight operations, and the numerical examples demonstrate the superiority of the proposed control in the flight envelope.
“…Because of the online learning capabilities of adaptive NNs, modeling of nonlinear systems and the compensation capabilities make them one of the most popular techniques for FDI. NNs have been used extensively in various applications varying from robust and adaptive control approaches (He et al , 2016c; He et al , 2016b, He et al , 2016a, Asgari et al , 2017; Lian et al , 2018; Abbaspour et al ., 2017) to FTC approaches (Samy et al , 2011; Talebi et al , 2009; Khorasgani et al , 2012; Oktay et al , 2018).…”
Purpose
The purpose of this paper is to propose an adaptive neural-sliding mode-based observer for the estimation and reconstruction of unknown faults and disturbances for time-varying nonlinear systems such as aircraft, to ensure preciseness in the diagnosis of fault magnitude as well as the shape without enhancement of system complexity and cost. Fault-tolerant control (FTC) strategy based on adaptive neural-sliding mode is also proposed in the existence of faults for ensuring the stability of the faulty system.
Design/methodology/approach
In this paper, three strategies are presented: adaptive radial basis functions neural network (ARBFNN), conventional radial basis functions neural network (CRBFNN) and integral-chain differentiator. For the purpose of enhancement of fault diagnosis and isolation, a new sliding mode-based concept is introduced for the weight updating parameters of radial basis functions neural network (RBFNN).The main objective of updating the weight parameters adaptively is to enhance the effectiveness of fault diagnosis and isolation without increasing the computational complexities of the system. Results depict the effectiveness of the proposed ARBFNN approach in fault detection (FD) and approximation compared to CRBFNN, integral-chain differentiator and schemes existing in literature. In the second step, the FTC strategy is presented separately for each observer in the presence of unknown faults and failures for ensuring the stability of the system, which is validated on Boeing 747 100/200 aircraft.
Findings
The proposed adaptive neural-sliding mode approach is investigated, which depicts more effectiveness in numerous situations such as faults, disturbances and uncertainties compared to algorithms used in literature. In this paper, both the fault approximation and isolation and the fault tolerance approaches are studied.
Practical implications
For the enhancement of safety level as well as for avoiding any kind of damage, timely FD and fault tolerance have always had a significant role; therefore, the algorithms proposed in this research ensure the tolerance of faults and failures, which plays a vital role in practical life for avoiding any kind of damage.
Originality/value
In this study, a new neural-sliding mode concept is adopted for the adaptive faults approximation and reconstruction, and then the FTC algorithms are studied for each observer separately, whereas in previous studies, only the fault detection and isolation (FDI) or the fault tolerance problems were studied. Results demonstrate the effectiveness of the proposed strategy compared to the approaches given in the literature.
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.
