Search

High-angle-of-attack uncommanded roll oscillations are dangerous and can cause significant challenges in flight control. This paper constructs a stability augmented system to suppress roll oscillations with nonzero mean roll angles in a canard-configuration model. To overcome the problem of weak traditional ailerons caused by large-scale flow separations at high angles of attack, spanwise blowing was used as fluid effectors to generate lateral control moments. The control effect and mechanism of spanwise blowing were analyzed through the results of force measurements and experiments using particle image velocimetry (PIV), respectively. Spanwise blowing generates the control moment by changing the trajectory of the leading-edge vortex and delaying vortex breakdown. Subsequently, virtual flight experiment technology was used to train a policy for the stability augmented system based on real-world data using deep reinforcement learning in the wind tunnel. When testing the agent, the transient flow fields around the model were obtained synchronously using time-resolved particle image velocimetry (TR-PIV). The test results showed that the agent learned to keep the model roll at approximately zero by effectively controlling the flow field using fluid effectors. The rapid development of artificial intelligence (AI) brings new ideas for various industries. Among various AI technologies, deep reinforcement learning is a self-evolving technique that is suitable for solving complex control and decision-making problems. on the other hand, the complex dynamic characteristics of aircraft at high angles of attack leads to the emergence of uncommanded motions, making flight dangerous. Therefore, this paper focuses on the suppression of uncommanded motion of canard configuration at high angles of attack, using deep reinforcement learning. The technology of jet flow control was used to play the role of aileron. After enough training in wind tunnel, the AI finally learned how to suppress the uncommanded motion of the aircraft and showed interesting behavioral logic. The results of this paper show that deep reinforcement learning can be used for complex control problems in aerospace science; however, the practicality of deep reinforcement learning in real flight needs further verification. [ABSTRACT FROM AUTHOR]

Load rating is gaining popularity as a method for inspecting the structural performance of aging bridges and determining maintenance actions. Cost-effective condition-based strategies have been developed in previous studies to balance the additional costs and structural safety. However, due to the lack of constant replacement thresholds usually stipulated in governmental guidelines, they may not be suitable in practice. Furthermore, those studies neglected the preferences of decision makers, which influences the choice of optimal plans. This paper proposes a decision-making framework incorporating risk attitudes and time preference for a cost-effective load rating strategy. This strategy utilizes replacement thresholds from current guidelines and determines the time of the next load rating adaptively based on the observation results. It is formulated as a Markov decision process (MDP) compatible with discounted utility theory. Deep reinforcement learning (DRL) is employed to solve the MDP efficiently for a bridge system with large state space. Special focus is given to hyperbolic discounting, one popular type of time preference. Its inconsistency with the MDP formulation is addressed by DRL implemented with auxiliary tasks that simultaneously learns multiple Q functions. An existing multigirder bridge was used as an illustrative example. Results showed that DRL can obtain cost-efficient load rating plans tailored to preferences of decision makers. [ABSTRACT FROM AUTHOR]

The increasing number of defunct and fragmented spacecraft poses a growing hazard to existing onorbit assets. The redundant continuum manipulator with high flexibility provides dual-arm robotic systems with apparent advantages in active debris removal missions in space. Existing autonomously-coordinated control approaches for dual-arm continuum manipulators require a real-time inverse kinematic solution and a security assurance mechanism for possible collisions, which are difficult to upscale for space debris capture systems with high-speed maneuverability. In this paper, we consider collision avoidance and input saturation control in proposing a multiagent reinforcement learning approach, named the multiagent twin delayed deep deterministic policy gradient (MATD3), to generate a real-time inverse kinematic solution for coordinated manipulators. During the training process, the MATD3 algorithm performs lower overestimation than the multiagent deep deterministic policy gradient (MADDPG) algorithm. Then, a feedback dynamics controller is designed for the continuum manipulators. Under the guidance of the policy networks, each agent can schedule the joint trajectory design online according to the collaborator and target debris information. During the capture operation, a competitive mechanism for the anticollision function is developed through reasonable reward functions to maintain dual arms at a safe distance. Simulation results show that the average accuracy of the proposed approach is 42% higher than that of MADDPG in inverse kinematic trajectory planning. The designed integrated tracking controller can effectively perform capture missions in the simulation environment. Multiagent reinforcement learning shows promise for future onorbit servicing missions. [ABSTRACT FROM AUTHOR]

The transient wind field during a nonsynoptic wind event (e.g., thunderstorm downburst) presents time-varying mean and nonstationary fluctuating components, and hence is not easy to be reproduced in a conventional boundary-layer wind tunnel with various passive devices (e.g., spires, roughness elements, and barriers). As a promising alternative, the actively controlled multiple-fan wind tunnel has emerged to effectively generate the laboratory-scale, spatiotemporally varying wind flows. The tracking accuracy of target wind speed histories at selected locations in the multiple-fan wind tunnel depends on the control signals input to individual fans. Conventional hand-design linear control schemes cannot ensure good performance due to the complicated fluid dynamics and nonlinear interactions inside the wind tunnel. In addition, the determination of the control parameters involves a time-consuming manual tuning process. In this paper, an accurate and efficient control scheme based on deep reinforcement learning (RL) is developed to realize the prescribed spatiotemporally varying wind field in a multiple-fan wind tunnel. Specifically, the fully connected deep neural network (DNN) is trained using RL methodology to perform active flow control in the multiple-fan wind tunnel. Accordingly, the optimal parameters (network weights) of the DNN-based nonlinear controller are obtained based on an automated trial-and-error process. The controller complexity needed for active simulation of transient winds can be well captured by a DNN due to its powerful function approximation ability, and the "model-free" and "automation" features of RL paradigm eliminate the need of expensive modeling of fluid dynamics and costly hand tuning of control parameters. Numerical results of the transient winds during a moving downburst event (including nose-shape vertical profiles, time-varying mean wind speeds, and nonstationary fluctuations) present good performance of the proposed deep RL-based control strategy in a simulation environment of the multiple-fan wind tunnel at the University at Buffalo. [ABSTRACT FROM AUTHOR]