A Varying-Parameter Adaptive Multi-Layer Neural Dynamic Method for Designing Controllers and Application to Unmanned Aerial Vehicles

Zhang, Zhijun; Zhou, Bowen; Zheng, Lunan; Zhang, Zihao; Song, Chen; Pei, Hailong

doi:10.1109/tits.2020.2983522

Cited by 13 publications

(5 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The direction of the needle is perpendicular to the direction of the fracture line. For minor treatments of posterior cartilage cartilage, it is difficult to develop detailed information and be treated without data by three-dimensional reconstruction of spiral CT and line data alone [ 21 ].…”

Section: Methodsmentioning

confidence: 99%

Application of Multislice Spiral CT and Three-Dimensional Image Reconstruction Technology in the Observation of Ankle Sports Injury under the Microscope

Zhao

2022

Scanning

View full text Add to dashboard Cite

In order to solve the problem of multislice spiral CT and three-dimensional image reconstruction technology in the observation of ankle sports injuries under the microscope, to meet the needs of the accuracy of the diagnosis of traumatic fractures, to make up for the shortcomings of the traditional treatment cycle, and to improve the recovery speed of patients. The subjects were inpatients in the Orthopedics and Traumatology Department of a hospital from January 2020 to January 2021.The ankle joint belongs to the flexion joint, which is formed by a dense joint at the lower end of the fibula, tibia, and talus. Osteoarthritis is the most common type of bone fracture, accounting for approximately 3.9% of the total skeletal system, and is most likely to occur in adolescents.

show abstract

Section: Methodsmentioning

confidence: 99%

Application of Multislice Spiral CT and Three-Dimensional Image Reconstruction Technology in the Observation of Ankle Sports Injury under the Microscope

Zhao

2022

Scanning

View full text Add to dashboard Cite

show abstract

“…e(t) ∈ R denotes deviation between prediction output and expectation over t.ė(t) denotes the derivative of the deviation e(t) with respect to t. λ > 0, λ ∈ R denotes NDLA parameter. Φ(•) denotes mapping function, which is a monotonically increasing and odd function 35,37,40,42 . Because NDLA is conducted in digital computer, such serial time expression is transformed into a discrete ones combined with Euler discrete formula 43 , which is shown as…”

Section: Learning Algorithm Of Dynamic Learning Networkmentioning

confidence: 99%

“…Related theoretical analysis has proved that using VP-CDNN can make the residual error over the continuous time converge to zero super-exponentially. Based on the proposed VP-CDNN, various practical problems about time varying over-determined system 30 , time varying complex Sylvester equation 31 , disturbed time varying inversion systems 32 , robot tracking 33,34 and unmanned aerial vehicle controller 35 have been effectively solved. Furthermore, Zhang et al designed an adaptive multi-layer neural dynamics-based controllers of multi-rotor unmanned aerial vehicles for the sake of adapting to various complex transportation 36 .…”

Section: Introductionmentioning

confidence: 99%

A Bagging Dynamic Deep Learning Network for Diagnosing COVID-19

Zhang

Chen

Sun

2021

Preprint

Self Cite

View full text Add to dashboard Cite

COVID-19 is a serious epidemic all over the world. As an efficient way in intelligent medical services, using X-ray chest radiography image for automatically diagnosing COVID-19 provides huge assistances and conveniences for clinicians in practice. In this paper, a bagging dynamic deep learning network (B-DDLN) is proposed for diagnosing COVID-19 by intelligently recognizing X-ray chest radiography images. After a series of preprocessing steps for images, we pre-train convolution blocks as a feature extractor. For the extracted features, bagging dynamic learning network classifier is trained based on neural dynamic learning algorithm and bagging algorithm. B-DDLN connects feature extractor and bagging classifier in series. Experimental results verify that using the proposed B-DDLN can achieve 98.8889% testing accuracy, which illustrates the best diagnosis performances among existing methods on the open image set and provides evidences for further detection and treatment.

show abstract

“…The cascade control structure technique is proposed in this paper to realize the control system solutions for the quadrotor UAV, wherein PID controllers have been used in the cascaded control loop. Several control strategies have been designed for the multirotor UAVs over the years, such as [17][18][19][20][21]. PID controllers are supposed to be the most vastly utilized controllers in the quadrotor control system because of their simplified structure and ease of practical implementation [22,23].…”

Section: Introductionmentioning

confidence: 99%

Cascaded Control System Design for Quadrotor UAV through Relay with Embedded Integrator-Based Automatic Tuning Approach

Hoshu,

Mustafa Abro,

Alhussein

et al. 2023

International Journal of Aerospace Engineering

View full text Add to dashboard Cite

Due to their enormous characteristics and applicability, quadrotor unmanned aerial vehicles (UAVs) have enjoyed much popularity lately. However, designing a stable control strategy for quadrotors still remains one of the major concerns mainly due to the requirement of an accurate system model. They are naturally underactuated systems, with complex and nonlinear dynamics as well as interaxes couplings. Considering the dynamical complexities of these vehicles, one of the efficient methods is to utilize the relay feedback experiments and automatic tuning approach to tackle these issues. This paper investigates the employment of the relay with embedded integrator approach, wherein the quadrotor dynamics are estimated effectively with minimal parameters as compared to previously utilized relay with hysteresis technique. Frequency sampling filter (FSF) is further utilized for the extraction of the needful data through the signals obtained using the relay experiments, followed by the estimation of the plant dynamics. PID controllers have then been developed using the approximated quadrotor models. Which are used in the proposed cascade control structure for the quadrotor. The demonstrated results and analysis present the efficacy of designed control system technique for the quadrotor UAV.

show abstract

A Varying-Parameter Adaptive Multi-Layer Neural Dynamic Method for Designing Controllers and Application to Unmanned Aerial Vehicles

Cited by 13 publications

References 17 publications

Application of Multislice Spiral CT and Three-Dimensional Image Reconstruction Technology in the Observation of Ankle Sports Injury under the Microscope

Application of Multislice Spiral CT and Three-Dimensional Image Reconstruction Technology in the Observation of Ankle Sports Injury under the Microscope

A Bagging Dynamic Deep Learning Network for Diagnosing COVID-19

Cascaded Control System Design for Quadrotor UAV through Relay with Embedded Integrator-Based Automatic Tuning Approach

Contact Info

Product

Resources

About