Cascade ADRC with neural network-based ESO for hypersonic vehicle

Liu, Lei; Liu, Yongxiong; Zhou, Lilin; Wang, Bo; Cheng, Zhongtao; Fan, Huijin

doi:10.1016/j.jfranklin.2022.09.019

Cited by 12 publications

(5 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In equations ( 3) to (10), i is the neuron number of the input layer (i=1, 2, 3, 4), j is the neuron number of the hidden layer (j=1, 2, 3, 4, 5, 6), and h is the neuron number of the output layer (h=1,2); is the connection weight value from the input layer to the hidden layer, while ℎ is the connection weight value from the hidden layer to the output layer; Variables marked with single quotes represent hidden layer variables, while variables marked with double quotes represent output layer variables.…”

Section: Output Layer Algorithmmentioning

confidence: 99%

A Starter Performance Testing System Based of PIDNN Controller

Zhou,

Zhang

2024

AETR

View full text Add to dashboard Cite

Starter performance tester requires high precision and fast speed with a complex nonlinear structure and strong interference. The traditional PID controller always brings the bad effect with larger current and torque shocks. The complex intelligent algorithm is difficult to be realized in practical engineering for its trouble of parameter tuning. A new PID neural network(PIDNN) controller is designed which integrated the advantages of PID and intelligent controller. PIDNN has simple structure as PID and self-learning ability as NN to optimize parameters. The experiments verified the precision and efficiency of the test system.

show abstract

Section: Output Layer Algorithmmentioning

confidence: 99%

A Starter Performance Testing System Based of PIDNN Controller

Zhou,

Zhang

2024

AETR

View full text Add to dashboard Cite

show abstract

“…To address the uncertain dynamic parameters and external disturbances in the system, Lu et al used neural networks to identify uncertain parameters in the system, which performed well in the control of such nonlinear systems [21]. However, the instability of the control system due to external or self-disturbances, as well as actuator and sensor failures, is a common phenomenon for UAVs [22,23]. Therefore, many researchers have considered combining intelligent control algorithms with robust and adaptive control to propose fault-tolerant control algorithms that can solve a class of faults [24][25][26].…”

Section: Introductionmentioning

confidence: 99%

“…Zhong et al introduced the model reference adaptive control into the RBFNN for online identification of the system model's changing parameters [16]. Similarly, Liu et al designed a new cascade double loop ADRC method of neural network-based extended state observer (NNESO) to solve the attitude control problem of hypersonic vehicles in order to solve the disturbance problem of hypersonic vehicles [22]. The controller design ideas in this article have given us some inspiration.…”

Section: Introductionmentioning

confidence: 99%

Fractional Gradient Descent RBFNN for Active Fault-Tolerant Control of Plant Protection UAVs

Hua,

Zhang,

et al. 2024

CMES

View full text Add to dashboard Cite

With the increasing prevalence of high-order systems in engineering applications, these systems often exhibit significant disturbances and can be challenging to model accurately. As a result, the active disturbance rejection controller (ADRC) has been widely applied in various fields. However, in controlling plant protection unmanned aerial vehicles (UAVs), which are typically large and subject to significant disturbances, load disturbances and the possibility of multiple actuator faults during pesticide spraying pose significant challenges. To address these issues, this paper proposes a novel fault-tolerant control method that combines a radial basis function neural network (RBFNN) with a second-order ADRC and leverages a fractional gradient descent (FGD) algorithm. We integrate the plant protection UAV model's uncertain parameters, load disturbance parameters, and actuator fault parameters and utilize the RBFNN for system parameter identification. The resulting ADRC exhibits load disturbance suppression and fault tolerance capabilities, and our proposed active fault-tolerant control law has Lyapunov stability implications. Experimental results obtained using a multi-rotor fault-tolerant test platform demonstrate that the proposed method outperforms other control strategies regarding load disturbance suppression and fault-tolerant performance.

show abstract

“…The ADRC not only has faster response and smaller overshoot than PID control, but also effectively attenuates unknown disturbances, exhibits excellent adaptability to external disturbances, and ensures system stability [5]. Several studies have demonstrated the successful application of ADRC in different control systems with impressive control performance [6][7][8]. Additionally, combining ADRC with the inertia control method has resulted in significant improvements in system frequency fluctuation amplitude and settling time [9][10].…”

Section: Introductionmentioning

confidence: 99%

Wind Power Virtual Inertia Frequency Modulation Control Based on Intelligent Swarm Auto-Disturbance Rejection

Li,

Yao

et al. 2024

Advances in Transdisciplinary Engineering

View full text Add to dashboard Cite

This paper proposes a wind power virtual inertia control strategy based on the intelligent bee colony active disturbance rejection controller (ABC-ADRC). The proposed control method aims to improve the anti-interference capability of the virtual inertia control system and solve the challenge of tuning the parameters of the active disturbance rejection control (ADRC).The control strategy is developed based on the system frequency dynamic response equation. An active disturbance rejection controller is designed using a nonlinear feedback control law and an extended state observer. This controller aims to enhance the system’s ability to reject disturbances. However, tuning the parameters of the ADRC can be difficult. To address this issue, an ABC algorithm based on nectar collection behavior is proposed to iteratively optimize the ADRC parameters. The proposed control method is verified through simulations using Matlab/Simulink. The results demonstrate that the ABC-ADRC control strategy is more effective compared to traditional algorithms. It successfully controls the rotor speed to adjust the frequency of the power grid system, achieves power sharing, and eliminates adaptive noise. Furthermore, this method reduces the complexity of parameter settings, improves anti-interference ability, and enhances the robustness of the system.

show abstract

Cascade ADRC with neural network-based ESO for hypersonic vehicle

Cited by 12 publications

References 27 publications

A Starter Performance Testing System Based of PIDNN Controller

A Starter Performance Testing System Based of PIDNN Controller

Fractional Gradient Descent RBFNN for Active Fault-Tolerant Control of Plant Protection UAVs

Wind Power Virtual Inertia Frequency Modulation Control Based on Intelligent Swarm Auto-Disturbance Rejection

Contact Info

Product

Resources

About