Gas Turbine Engine Identification Based on a Bank of Self-Tuning Wiener Models Using Fast Kernel Extreme Learning Machine

Lü, Feng; Ye, Yu; Huang, Jinquan

doi:10.3390/en10091363

Cited by 7 publications

(10 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The engine characteristics are listed in Table 2. A reduced order Wiener model based on experimental results is generated to predict the dynamic behavior of the engine [35]. The engine is modelled and analyzed with details by the authors in [12], and [22].…”

Section: Simulation Resultsmentioning

confidence: 99%

Turbojet Engine Industrial Min–Max Controller Performance Improvement Using Fuzzy Norms

Jafari

Nikolaidis

2018

Electronics

View full text Add to dashboard Cite

The Min–Max control strategy is the most widely used control algorithm for gas turbine engines. This strategy uses minimum and maximum mathematical functions to select the winner of different transient engine control loops at any instantaneous time. This paper examines the potential of using fuzzy T and S norms in Min–Max selection strategy to improve the performance of the controller and the gas turbine engine dynamic behavior. For this purpose, different union and intersection fuzzy norms are used in control strategy instead of using minimum and maximum functions to investigate the impact of this idea in gas turbine engines controller design and optimization. A turbojet engine with an industrial Min–Max control strategy including steady-state and transient control loops is selected as the case study. Different T and S norms including standard, bounded, Einstein, algebraic, and Hamacher norms are considered to be used in control strategy to select the best transient control loop for the engine. Performance indices are defined as pilot command tracking as well as the engine response time. The simulation results confirm that using Einstein and Hamacher norms in the Min–Max selection strategy could enhance the tracking capability and the response time to the pilot command respectively. The limitations of the proposed method are also discussed and potential solutions for dealing with these challenges are proposed. The methodological approach presented in this research could be considered for enhancement of control systems in different types of gas turbine engines from practical point of view.

show abstract

Section: Simulation Resultsmentioning

confidence: 99%

Turbojet Engine Industrial Min–Max Controller Performance Improvement Using Fuzzy Norms

Jafari

Nikolaidis

2018

Electronics

View full text Add to dashboard Cite

show abstract

“…The i-th LSRM node receives both the position feedback information from its linear encoder and the j-th node and only the leader node accesses the position reference information. Each node is composed of a local position controller, the multiphase excitation scheme with look-up table linearization, current controllers to form the force and current control loop, and an LSRM [22]. For the i-th LSRM node, error is decided from the difference between reference r (the leader only) and actual position x i of the i-th LSRM, along with the position information from the j-th LSRM x j .…”

Section: Of 18mentioning

confidence: 99%

“…Meanwhile, by applying Equation (21) and the Kronecker produ Equation (22) can be derived as follows,…”

Section: Controllability Of Lsrm Networkmentioning

confidence: 99%

“…Meanwhile, by applying Equation (21) and the Kronecker product properties Equation (22) can be derived as follows, (22)- (24), we can derive the equation as,…”

Section: Controllability Of Lsrm Networkmentioning

confidence: 99%

“…Meanwhile, by applying Equation (21) and the Kronecker product properties, the left side of Equation (22) can be derived as follows, According to Definition 1 and [23], the prerequisite for using some external signal to manipulate freely the LSRM network Equation (18) is that its controllability can be guaranteed.…”

Section: Controllability Of Lsrm Networkmentioning

confidence: 99%

See 2 more Smart Citations

Controllability and Leader-Based Feedback for Tracking the Synchronization of a Linear-Switched Reluctance Machine Network

et al. 2017

View full text Add to dashboard Cite

This paper investigates the controllability of a closed-loop tracking synchronization network based on multiple linear-switched reluctance machines (LSRMs). The LSRM network is constructed from a global closed-loop manner, and the closed loop only replies to the input and output information from the leader node. Then, each local LSRM node is modeled as a general second-order system, and the model parameters are derived by the online system identification method based on the least square method. Next, to guarantee the LSRM network's controllability condition, a theorem is deduced that clarifies the relationship among the LSRM network's controllability, the graph controllability of the network and the controllability of the node dynamics. A state feedback control strategy with the state observer located on the leader is then proposed to improve the tracking performance of the LSRM network. Last, both the simulation and experiment results prove the effectiveness of the network controller design scheme and the results also verify that the leader-based global feedback strategy not only improves the tracking performance but also enhances the synchronization accuracy of the LSRM network experimentally.

show abstract

Gas turbine system identification using a bilayer equilibrium manifold expansion model

Zhu

Liu

et al. 2022

AEAT

View full text Add to dashboard Cite

Purpose This paper aims to establish a multi-input equilibrium manifold expansion (EME) model for gas turbine (GT). It proposes that the extension of model input dimension is realized based on similarity theory and affine structure in the framework of single-input EME model. The study aims to expand the scope of application of the EME model so that it can be used for the control or fault diagnosis of GTs. Design/methodology/approach In this paper, the concepts of corrected equilibrium manifold expansion (CEME) model and multi-cell equilibrium manifold expansion (MEME) model are first proposed. This paper uses theoretical analysis and simulation experiments to demonstrate the effectiveness of the bilayer equilibrium manifold expansion (BEME) model, which is a combination of the CEME and the MEME models. Simulation experiments include confirmatory experiments and comparative experiments. Findings The paper provides a new sight into building a multiple-input EME (MI-EME) model for GTs. The proposed method can build an accurate and robust MI-EME model that has superior performance compared with widely used nonlinear models including Wiener model (WM), Hammerstein model (HM), Hammerstein–Wiener model (HWM) and nonlinear autoregressive with exogenous inputs (NARX) network model. In terms of accuracy, the maximum error percentage of the proposed model is just 1.309%, far less than WM, HM and HWM. In terms of the stability of model calculation, the range of the mean error percentage of the proposed model is just a quarter of that of NARX network model. Originality/value The paper fulfills the construction of a novel multi-input nonlinear model, which has laid a foundation for the follow-up research of model-based GT fault detection and isolation or GT control.

show abstract

Gas Turbine Engine Identification Based on a Bank of Self-Tuning Wiener Models Using Fast Kernel Extreme Learning Machine

Cited by 7 publications

References 34 publications

Turbojet Engine Industrial Min–Max Controller Performance Improvement Using Fuzzy Norms

Turbojet Engine Industrial Min–Max Controller Performance Improvement Using Fuzzy Norms

Controllability and Leader-Based Feedback for Tracking the Synchronization of a Linear-Switched Reluctance Machine Network

Gas turbine system identification using a bilayer equilibrium manifold expansion model

Contact Info

Product

Resources

About