检索结果-内蒙古大学图书馆

Reinforcement learning based closed-loop reference model adaptive flight control system design

INTERNATIONAL JOURNAL OF adaptive control AND SIGNAL PROCESSING 2021年第3期35卷 420-440页

作者： Yuksek, Burak Inalhan, Gokhan Istanbul Tech Univ Aerosp Res Ctr Ayazaga Campus TR-34469 Istanbul Turkey Cranfield Univ Sch Aerosp Transport & Mfg Ctr Autonomous & Cyber Phys Syst Bedford England

In this study, we present a reinforcement learning (RL)-based flight control system design method to improve the transient response performance of a closed-loop reference model (CRM) adaptive control system. The methodology, known as RL-CRM, relies on the generation of a dynamic adaption strategy by implementing RL on the variable factor in the feedback path gain matrix of the reference model. An actor-critic RL agent is designed using the performance-driven reward functions and tracking error observations from the environment. In the training phase, a deep deterministic policy gradient algorithm is utilized to learn the time-varying adaptation strategy of the design parameter in the reference model feedback gain matrix. The proposed control structure provides the possibility to learn numerous adaptation strategies across a wide range of flight and vehicle conditions instead of being driven by high-fidelity simulators or flight testing and real flight operations. The performance of the proposed system was evaluated on an identified and verified mathematical model of an agile quadrotor platform. Monte-Carlo simulations and worst case analysis were also performed over a benchmark helicopter example model. In comparison to the classical model reference adaptive control and CRM-adaptive control system designs, the proposed RL-CRM adaptive flight control system design improves the transient response performance on all associated metrics and provides the capability to operate over a wide range of parametric uncertainties.

关键词： adaptive flight control system reinforcement learning resilient control variable closed-loop reference model adaptive control

来源：评论

学校读者我要写书评

暂无评论

Correction to: selection and evaluation of FOPID criteria for the X-15 adaptive flight control system (AFCS) via Lyapunov candidates: Optimizing trade-offs and critical values using optimization algorithms

引用

e-Prime - Advances in Electrical Engineering, Electronics and Energy 2024年 8卷

作者： Basil, Noorulden Marhoon, Hamzah M. Department of Electrical Engineering College of Engineering Mustansiriyah University Baghdad Iraq Department of Systems Engineering College of Information Engineering Al-Nahrain University Baghdad Jadriya Iraq

Recently, there has been a growing interest among academics worldwide in studying flight control systems. The advancement of tracking technologies, such as the X-15 adaptive flight control system developed at NASA (National Aeronautics and Space Administration), has sparked significant exploration efforts by scientists. The vast availability of aerial resources further contributes to the importance of studying adaptive flight control systems (AFCS). The successful operation of AFCS relies on effectively managing the three fundamental motions: pitch, roll, and yaw. Therefore, scientists have been diligently working on developing optimization algorithms and models to assist AFCS in achieving optimal gains during motion. However, in real-world scenarios, each motion requires its own set of criteria, which presents several challenges. Firstly, there are multiple criteria available for selecting appropriate optimization values for each motion. Secondly, the relative importance of these criteria influences the selection process. Thirdly, there is a trade-off between the performance of the criteria within a single optimization case and across different cases. Lastly, determining the critical value of the criteria poses another obstacle. Consequently, evaluating and selecting optimum methods for AFCS trajectory controls becomes a complex operation. To address the need for optimizing AFCS for various maneuvers, this study proposes a new selection process. The suggested approach involves utilizing black hole optimization (BHO), Jaya optimization algorithm (JOA), and sunflower optimization (SFO) as methods for detecting and correcting trajectories in adaptive flight control systems. These methods aim to determine the best launch of missiles from the AFCS based on the coordinate location for both long and short distances. Additionally, the methods determine the optimal gains for the FOPID (fractional order proportional integral derivative) controller and enhance protection agai

关键词： adaptive flight control system black hole optimization fopid controller criteria Jaya optimization algorithm Sunflower optimization

来源：评论

学校读者我要写书评

暂无评论

Selection and evaluation of FOPID criteria for the X-15 adaptive flight control system (AFCS) via Lyapunov candidates: Optimizing trade-offs and critical values using optimization algorithms

引用

e-Prime - Advances in Electrical Engineering, Electronics and Energy 2023年 6卷

关键词： adaptive flight control system Black hole optimization FOPID controller criteria Jaya optimization algorithm Sunflower optimization

来源：评论

学校读者我要写书评

暂无评论

An adaptive flight control system for a Morphing Flapping Wing Aircraft

An Adaptive Flight Control system for a Morphing Flapping Wi...

引用

AIAA Science and Technology Forum and Exposition (AIAA SciTech)

作者： Chandrasekaran, Balaji Kartikeyan Steck, James E. Wichita State Univ Aerosp Engn Wichita KS 67220 USA

ISBN: (数字)9781624105951

ISBN: (纸本)9781624105951

Our prior work(1, 2) developed a model for a bird-like flapping wing aircraft using Modified strip theory(3) for aerodynamics, a flight dynamics model(4) and an adaptive flight controller. This model was simulated in MATLAB/Simulink(5) using existing data for the Slow Hawk Ornithopter(6). One of the control architectures developed was an Optimal control Modification (OCM) of an adaptive Neural Network Inverse controller, and a gain study was carried out to determine optimal gains. This work expands on the previous work by introducing a new basis function(7) and performing a Gain Study on this OCM architecture with a PI controller. The proportional Gain (K-p), Integral Gain (K-i), Learning rate and the damping constant were optimized using the error metric introduced by Stepanyan(8). In this error metric study, K-p was varied from 10 to 100 and a value of 40 was selected. Similarly, Ki was varied from 10 to 105 and a value of 30 was selected, and a good learning rate of 20000 was found. Subsequently, a basic concept of a morphing wing was introduced where wing Properties dependent on camber were assumed to vary linearly with a morphing factor Previously developed control architectures were tested for various morphed states of the wing. OCM with new basis function kept states within limits. The adaptation was able to keep the tracking error low for the pitch rate commanded doublet.

关键词： Flapping Frequency Ornithopter Aerodynamic Properties flight Path Angle Camber Optimal control adaptive flight control system Neural Networks PI controller MATLAB

来源：评论

学校读者我要写书评

暂无评论

Composite adaptive flight control Based on Matrix Decomposition and Enhanced Excitation

Composite Adaptive Flight Control Based on Matrix Decomposit...

引用

AIAA SciTech Forum

作者： Lee, Keum W. Singh, Sahjendra N. Catholic Kwandong Univ Dept Elect Engn Gangwon 25601 South Korea Univ Nevada Las Vegas Dept Elect & Comp Engn Las Vegas NV 89154 USA

ISBN: (数字)9781624107115

ISBN: (纸本)9781624107115

The paper presents a composite adaptive flight control system for aircraft roll-coupled maneuvers. All the aerodynamic parameters and the input matrix are assumed to be unknown. The objective is to control the roll angle, angle of attack, and sideslip angle using aileron, elevator, and rudder. First, an adaptive state feedback control law is derived based on the decomposition of the input matrix and backstepping design method. Then, a composite parameter estimator is designed by combining a gradient scheme-based update law and an estimation law using regressor integral feedback for enhanced parameter excitation. The designed adaptation law enables exact parameter estimation if a mild initial excitation (IE) condition is satisfied. The closed-loop system including the composite adaptive control law is simulated. These results show precise roll angle, angle of attack, and sideslip angle trajectory control. Furthermore, the composite identifier, including regressor integral feedback, achieves significant reduction in the norm of parameter error compared with the simple gradient algorithm-based adaptation law.

关键词： flight control system Closed Loop system Elevator Deflection control Surfaces Sideslip Angle adaptive flight control system Feedback Linearization Aircraft control flight Envelope adaptive control systems

来源：评论

学校读者我要写书评

暂无评论

Aircraft Mass Properties Estimation During Airdrop Maneuver: A Nonlinear Filtering Approach

引用

JOURNAL OF AIRCRAFT 2021年第5期58卷 982-996页

作者： Manshadi, Ali Dehghan Saghafi, Fariborz Sharif Univ Technol Aerosp Engn Tehran *** Iran Sharif Univ Technol Dept Aerosp Engn Tehran *** Iran

Unlike a single-body approach, modeling based on a two-body approach has been employed to prepare the required system dynamic model as a time update equation in the applied filtering technology and measurement data for the estimation process. This more precise mathematical model enabled better understanding about the dynamics of the change in the aircraft mass properties during the airdropping operation. The problem is defined as estimation of the optimal mass properties parameters for the best possible fit of the model output to the real data. The parameter estimation problem is investigated by a nonlinear filtering methodology in two sequential steps. In the first step, the single extended Kalman filter is used to estimate the aircraft total mass and moment of inertia before entering an airdrop maneuver. In the second step, both the aircraft dynamic states and mass parameters are estimated during an airdrop maneuver using a joint extended Kalman filter. Monte Carlo simulations have then been performed to assess the performance of the algorithm in the presence of measurement errors and model uncertainties. The results indicate that time-varying aircraft mass properties estimation, as a technological requirement for the aircraft adaptive flight control system to reduce the risks involved with the airdrop operation, is satisfactorily possible.

关键词： Longitudinal control Light Transport Aircraft Unscented Kalman Filter Monte Carlo Simulation Mathematical Models adaptive flight control system Earth Reference Frame Histograms Elevator Deflection Aerodynamic Coefficients

来源：评论

学校读者我要写书评

暂无评论

adaptive Dynamic Surface control for Unmanned Aerial Vehicles Based on Attractive Manifolds

引用

JOURNAL OF GUIDANCE control AND DYNAMICS 2013年第6期36卷 1779-1785页

作者： Zhang, Jiaming Li, Qing Cheng, Nong Liang, Bin Tsinghua Univ Dept Automat Beijing 100084 Peoples R China

Advanced nonlinear control methods are proposed to overcome the shortcoming of linear design approaches, such as feedback linearization, back-stepping, and dynamic surface control. The feedback linearization approach requires an accurate aircraft mathematical model. The adaptive back-stepping method makes use of the step-by step coordinate transformation and uses some states as intermediate virtual controls to regulate other states. This method relies on finding an adaptive control law and a parameter update law to yield that the Lyapunov function of the closed-loop system is negative. Once the estimation error reaches the manifold, the closed loop system does not suffer from the undesired transient performance resulting from the parameter estimation and behaves like a deterministic system. Additionally, the convergence performance can be improved by increasing the learning-rate parameters. Moreover, the estimate converges to the true value if the reference signal is persistently exciting.

关键词： UAV adaptive Backstepping Method Aerodynamic Characteristics flight control Law Mathematical Models Feedback Linearization control Surfaces adaptive flight control system Six Degree of Freedom flight control system

来源：评论

学校读者我要写书评

暂无评论

Online Aerodynamic Model Identification Using a Recursive Sequential Method for Multivariate Splines

引用

JOURNAL OF GUIDANCE control AND DYNAMICS 2013年第5期36卷 1278-1288页

作者： Sun, L. G. de Visser, C. C. Chu, Q. P. Mulder, J. A. Delft Univ Technol NL-2600 GB Delft Netherlands

Avoiding high computational loads is essential to online aerodynamic model identification algorithms, which are at the heart of any model-based adaptive flight-control system. Multivariate simplex B-spline methods are excellent function approximation tools for modeling the nonlinear aerodynamics of high-performance aircraft. However, the computational efficiency of the multivariate simplex B-spline method must be improved in order to enable real-time onboard applications, for example, in adaptive nonlinear flight-control systems. In this paper, a new recursive sequential identification strategy is proposed for the multivariate simplex B-spline method aimed at increasing its computational efficiency, thereby allowing its use in onboard system identification applications. The main contribution of this new method is a significant reduction of the computational load for large-scale online identification problems as compared to the existing multivariate simplex B-spline methods. The proposed method consists of two sequential steps for each time interval and makes use of a decomposition of the global problem domain into a number of subdomains, called modules. In the first step, the B-coefficients for each module are estimated using a least-squares estimator. In the second step, the local B-coefficients for each module are then smoothened into a single global B-coefficient vector using a linear minimum mean-square errors estimation. The new method is compared to existing batch and recursive multivariate simplex B-spline methods in a numerical experiment in which an aerodynamic model is recursively identified based on data from a NASA F-16 wind-tunnel model.

关键词： Spline Method Wind Tunnel Models Aerodynamic Coefficients flight control system system Identification adaptive flight control system High Performance Aircraft Lagrange Multipliers Mean Aerodynamic Chord Singular Value Decomposition

来源：评论

学校读者我要写书评

暂无评论

Time-Delay Margin Analysis for an adaptive controller

引用

JOURNAL OF GUIDANCE control AND DYNAMICS 2012年第5期35卷 1418-1425页

作者： Dorobantu, Andrei Seiler, Peter Balas, Gary J. Univ Minnesota Dept Aerosp Engn & Mech Minneapolis MN 55455 USA

adaptive control has the potential to improve the performance and reliability of aircraft systems. Implementation of adaptive control on commercial and military aircraft requires the flight control system to be verified and validated with respect to modeling error, uncertainty, and time delay. Currently, there is a lack of tools available to rigorously analyze the robustness of adaptive controllers due to their inherently nonlinear dynamics. Newly proposed nonlinear robustness analysis tools are applied to adaptive flight control in this paper. A standard model reference adaptive controller with sigma modification is designed for a linear short-period aircraft model. The resulting nonlinear closed-loop system is governed by polynomial dynamics. The nonlinear analysis algorithms rely on sum-of-squares polynomial optimization to assess the robustness of the adaptive closed-loop system with respect to a time delay. Time-delay margins are computed for various combinations of design parameters in the adaptive control law, as well as in the presence of parametric model uncertainty. Advantages and limitations of the proposed sum-of-squares-based robustness analysis are presented. Analysis results show a significant promise in the context of recent development in nonlinear robustness analysis.

关键词： Model Reference adaptive control flight control system Military Aircraft Aircraft systems Nonlinear Dynamics Monte Carlo Simulation Nonlinear systems Elevator Deflection adaptive flight control system adaptive control systems

来源：评论

学校读者我要写书评

暂无评论

Stabilator Failure Adaptation from flight Tests of NF-15B Intelligent flight control system

引用

JOURNAL OF AEROSPACE COMPUTING INFORMATION AND COMMUNICATION 2009年第3期6卷 187-206页

作者： Bosworth, John T. Williams-Hayes, Peggy S. NASA Dryden Flight Res Ctr Edwards AFB CA 93523 USA

adaptive flight control systems have the potential to be more resilient to extreme changes in airplane behavior. Extreme changes could be a result of a system failure or of damage to the airplane. A direct adaptive neural-network-based flight control system was developed for the National Aeronautics and Space Administration NF-15B Intelligent flight control system airplane and subjected to an inflight simulation of a failed (frozen) (unmovable) stabilator. Formation flight handling qualities evaluations were performed with and without neural network adaptation. The results of these flight tests are presented. Comparison with simulation predictions and analysis of the performance of the adaptation system are discussed. The performance of the adaptation system is assessed in terms of its ability to decouple the roll and pitch response and reestablish good onboard model tracking. flight evaluation with the simulated stabilator failure and adaptation engaged showed that there was generally improvement in the pitch response;however, a tendency for roll pilot-induced oscillation was experienced. A detailed discussion of the cause of the mixed results is presented.

关键词： flight Testing Stabilator NF 15B Intelligent flight control system Aeroplane Neural Network Software Handling Qualities National Aeronautics and Space Administration Pilot Induced Oscillation adaptive flight control system Test Pilots

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：