Turbo-fan engine acceleration control schedule optimization based on DNN-LPV model

Gu, Z.; Pang, Shuwei; Li, Yuchen; Li, Qiuhong; Zhang, Yongliang

doi:10.1016/j.ast.2022.107797

Cited by 17 publications

(7 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One typical way is to use online identification techniques, which achieves online modelling through the identification of sensor measurement data with the least-square principle. In particular, with the rise of intelligent algorithms, model identification can be performed using methods such as support vector machines and neural networks [18][19][20][21][22]. For example, in the literature [17,22], an LPV model identification method based on the OS-ELM algorithm has been proposed, which utilizes a specially designed ELM network structure to identify the parameters required for the LPV model.…”

Section: Introductionmentioning

confidence: 99%

“…In particular, with the rise of intelligent algorithms, model identification can be performed using methods such as support vector machines and neural networks [18][19][20][21][22]. For example, in the literature [17,22], an LPV model identification method based on the OS-ELM algorithm has been proposed, which utilizes a specially designed ELM network structure to identify the parameters required for the LPV model. However, this network is used only to identify the model based on the data of the single time instant, ignoring the nonlinear dynamics of the engine shown in the response of past time instants.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

An Improved Onboard Adaptive Aero-Engine Model Based on an Enhanced Neural Network and Linear Parameter Variance for Parameter Prediction

Pang,

Lu,

et al. 2024

Energies

Self Cite

View full text Add to dashboard Cite

Achieving measurable and unmeasurable parameter prediction is the key process in model-based control, for which an accurate onboard model is the most important part. However, neither nonlinear models like component level models or LPV models, nor linear models like state–space models can fully meet the requirements. Hence, an original ENN-LPV linearization strategy is proposed to achieve the online modelling of the state–space model. A special network structure that has the same format as the state–space model’s calculation was applied to establish the state–space model. Importantly, the network’s modelling ability was improved through applying multiple activation functions in the single hidden layer and an experience pool that records data of past sampling instants, which strengthens the ability to capture the engine’s strongly nonlinear dynamics. Furthermore, an adaptive model, consisting of a component-level model with adaptive factors, a linear Kalman filter, a predictive model, an experience pool, and two ENN-LPV networks, was developed using the proposed linearization strategy as the core process to continuously update the Kalman filter and the predictive model. Simulations showed that the state space model built using the ENN-LPV linearization strategy had a better model identification ability in comparison with the model built using the OSELM-LPV linearization strategy, and the maximum output error between the ENN-LPV model and the simulated engine was 0.1774%. In addition, based on the ENN-LPV linearization strategy, the adaptive model was able to make accurate predictions of unmeasurable performance parameters such as thrust and high-pressure turbine inlet temperature, with a maximum prediction error within 0.5%. Thus, the effectiveness and the advantages of the proposed method are demonstrated.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

An Improved Onboard Adaptive Aero-Engine Model Based on an Enhanced Neural Network and Linear Parameter Variance for Parameter Prediction

Pang,

Lu,

et al. 2024

Energies

Self Cite

View full text Add to dashboard Cite

show abstract

“…Also, the selection of an appropriate objective function is vital to the performance of the MPC, where such a suitable function may not always be readily available. 26 On the contrary, the proposed control algorithm works based on self-supervised learning. The ONN adapts itself to the system dynamics during the training phase.…”

Section: Introductionmentioning

confidence: 99%

Neural network steering control algorithm for autonomous ground vehicles having signal time delay

Dinçmen

2023

Proceedings of the Institution of Mechanical Engineers, Part I:

View full text Add to dashboard Cite

An adaptive neural network–based steering control algorithm is proposed for yaw rate tracking of autonomous ground vehicles with in-vehicle signal time delay. The control system consists of two neural networks: the observer neural network and the controller neural network. The observer neural network adapts itself to the system dynamics during the training phase. Once trained, the observer neural network cooperates with the controller neural network, which constantly adapts itself during the control task. In this way, an adaptive and intelligent control structure is proposed. Through simulation studies, it has been shown that while a proportional-integral-derivative type steering controller fails to perform its control task in case of steering signal delay, the proposed control algorithm manages to adapt itself according to the control problem and achieves reference yaw rate tracking. The robustness of the control algorithm according to the signal delay magnitude has been demonstrated by simulation studies. A rigorous Lyapunov stability analysis of the control algorithm is also presented.

show abstract

“…The jet engine has different operating points, each of which can cause severe changes in parameters and loss of optimal performance in different operating conditions. 33 Therefore, the PMRAC method is one of the appropriate methods to achieve the desired control objectives in this system. The simulations are performed on the dynamical model of the JetCat SPT5 turboshaft engine using MATLAB software.…”

Section: Introductionmentioning

confidence: 99%

“…Then, an optimization process is used to optimize the system performance in the future by choosing the appropriate values for the appropriate control inputs. 33 On the contrary, the predictive model reference adaptive control (PMRAC) strategy uses an integrated tracking error based on the Lyapunov stability theory to minimize the parameter and tracking errors, not by solving an optimization algorithm. So, achieving the proper control input can be faster and more reliable than MPC.…”

Section: Introductionmentioning

confidence: 99%

Control of a jet engine using predictor-based adaptive strategy in different flight modes

Ranjbar

Khosravi

Ahmadian

2023

Proceedings of the Institution of Mechanical Engineers, Part I:

View full text Add to dashboard Cite

In this article, a predictor-based model reference adaptive control method is proposed for a JetCat SPT5 turboshaft engine in full thrust, cruise, and idle modes. In the predictor-based model reference adaptive control method, in addition to the tracking error, the predictor error is also utilized in adaptive laws to achieve the desired control objectives, such as improving the tracking performance and control signals, and reducing the tracking error. The proposed method is implemented on a turboshaft engine system with actual dynamic values. First, three properly separated equilibrium points are selected on the nominal plant equilibrium manifold to linearize the plant model at the equilibrium points. Then, the predictor-based model reference adaptive control controller is designed and investigated for the three equilibrium points generating three operating modes of the engine, that is, full thrust, cruise, and idle. The stability of the control system is proved by the Lyapunov method. To evaluate the efficiency of the state predictor method in the simulation scenarios, the proposed method is compared with the classic model reference adaptive control method. The simulation results illustrate the superiority of the predictor-based model reference method due to the reduction of unwanted fluctuations in tracking performance, faster convergence of the tracking error to zero, and smoother control signals for all the equilibrium points.

show abstract

Turbo-fan engine acceleration control schedule optimization based on DNN-LPV model

Cited by 17 publications

References 36 publications

An Improved Onboard Adaptive Aero-Engine Model Based on an Enhanced Neural Network and Linear Parameter Variance for Parameter Prediction

An Improved Onboard Adaptive Aero-Engine Model Based on an Enhanced Neural Network and Linear Parameter Variance for Parameter Prediction

Neural network steering control algorithm for autonomous ground vehicles having signal time delay

Control of a jet engine using predictor-based adaptive strategy in different flight modes

Contact Info

Product

Resources

About