Search

Capability assessment plays a crucial role in the demonstration and construction of equipment. To improve the accuracy and stability of capability assessment, we study the neural network learning algorithms in the field of capability assessment and index sensitivity. Aiming at the problem of overfitting and parameter optimization in neural network learning, the paper proposes an improved machine learning algorithm—the Ensemble Learning Based on Policy Optimization Neural Networks (ELPONN) with the policy optimization and ensemble learning. This algorithm presents an optimized neural network learning algorithm through different strategies evolution, and builds an ensemble learning model of multi-intelligent algorithms to assess the capability and analyze the sensitivity of the indexes. Through the assessment of capabilities, the algorithm effectively avoids parameter optimization from entering the minimum point in performance to improve the accuracy of equipment capability assessment, which is significantly better than previous neural network assessment methods. The experimental results show that the mean relative error is 4.10%, which is better than BP, GABP, and early stopping. The ELPONN algorithm has better accuracy and stability performance, and meets the requirements of capability assessment. [ABSTRACT FROM AUTHOR]

Multiple unmanned aerial vehicle (UAV) collaboration has great potential. To increase the intelligence and environmental adaptability of multi-UAV control, we study the application of deep reinforcement learning algorithms in the field of multi-UAV cooperative control. Aiming at the problem of a non-stationary environment caused by the change of learning agent strategy in reinforcement learning in a multi-agent environment, the paper presents an improved multiagent reinforcement learning algorithm—the multiagent joint proximal policy optimization (MAJPPO) algorithm with the centralized learning and decentralized execution. This algorithm uses the moving window averaging method to make each agent obtain a centralized state value function, so that the agents can achieve better collaboration. The improved algorithm enhances the collaboration and increases the sum of reward values obtained by the multiagent system. To evaluate the performance of the algorithm, we use the MAJPPO algorithm to complete the task of multi-UAV formation and the crossing of multiple-obstacle environments. To simplify the control complexity of the UAV, we use the six-degree of freedom and 12-state equations of the dynamics model of the UAV with an attitude control loop. The experimental results show that the MAJPPO algorithm has better performance and better environmental adaptability. [ABSTRACT FROM AUTHOR]

Electromechanical actuator (EMA) systems are widely employed in missiles. Due to the influence of the nonlinearities, there is a flat-top of about 64 ms when tracking the small-angle sinusoidal signals, which significantly reduces the performance of the EMA system and even causes the missile trajectory to oscillate. Aiming to solve these problems, this paper presents a hybrid control for flat-top situations. In contrast to the traditional PID or sliding mode controllers that missiles usually use, this paper utilizes improved sliding mode control based on a novel reaching law to eliminate the flat-top during the steering of the input signal, and utilizes the PID control to replace discontinuous control and improve the performance of EMA system. In addition, boundary layer and switching function are employed to solve the high-frequency chattering problem caused by traditional sliding mode control. Experiments indicate that the hybrid control can evidently reduce the flat-top time from 64 ms to 12 ms and eliminate the trajectory limit cycle oscillation. Compared with PID controllers, the proposed controller provides better performance—less chattering, less flat-top, higher precision, and no oscillation. [ABSTRACT FROM AUTHOR]