一种基于学习的高超声速飞行器智能控制方法

针对吸气式高超声速飞行器的飞行控制问题,提出一种基于学习的智能控制方法。为便于控制器设计,将飞行器动力学模型划分为速度子系统和高度子系统：为解决速度子系统控制输入受限的问题,提出一种基于强化学习的智能控制方案;对于考虑有限通信资源的高度子系统跟踪控制问题,提出一种基于事件触发的确定学习控制方案。该方案包含离线学习训练和在线触发控制两个阶段。首先在本地离线学习训练阶段获取并存储系统的未知动态知识,随后利用所获取的经验知识设计基于事件触发机制的在线触发控制器。本文所提方案基于学习的思想将离线学习训练获取的智能体和经验知识应用于在线控制,使得所提方案能够快速计算控制指令且通信资源占用少。仿真结果说明了所提出方法的有效性。     

基于深度卷积网络的海洋涡旋检测模型

传统的利用遥感数据检测涡旋的方法通常是基于物理参数、几何特征、手工特征或专家知识。本文重点研究了基于深度学习技术从海表面高度图中识别海洋涡旋的方法。针对海洋卫星拍摄的海洋表面高度图中的涡旋检测问题,提出了一种基于卷积神经网络的多涡旋检测模型,该模型能够准确提取涡旋的特征信息,拟合语义信息与海面高度之间的关系。同时,在用于涡旋检测的最新公开数据集SCSE-Eddy上进行模型训练,以评估基于人工智能的涡旋检测方法性能,该数据集涵盖了15年来位于中国南海及其东部部分海域的每日卫星遥感海表面高度数据。实验结果表明,与现有的方法相比,本文模型取得了更好的检测结果,能够更好地区分相距较近的涡旋。     

机器学习技术在气动优化中的应用

近年来优化设计在气动设计中发挥了越来越多的作用,但实用性和效率是制约其发挥作用的两大障碍。在大型客机超临界机翼设计中,通过"人在回路"（依靠人的经验在优化进行过程中实施必要干预）等努力,取得了较好的效果,机器学习技术逐步得到发展。提出了利用机器学习技术模拟人在优化过程中的合理行为和作用机制,以深层次利用信息和知识,改善优化的实用性和效率。梳理了机器学习技术在气动优化中应用的发展脉络,并结合工作实践介绍了机器学习在优化设计中的典型应用。进一步探讨了深度学习在气动优化中的可能应用方式。     

基于迭代滑模的机械臂控制策略

针对机械臂这类非线性的不确定性系统,基于迭代学习控制与滑模控制策略,提出了一种有效的迭代滑模控制方法。该控制方法通过将滑模控制律引入到迭代学习控制中,并运用Lyapunov理论对控制律进行证明,从而确保系统的稳定性。基于拉格朗日力学法建立动力学模型,得到相对简化的n关节机械臂模型。以一个二关节机械臂为例,通过MATLAB仿真验证所提控制策略可有效提高关节的跟踪速度与跟踪精度,并且在一定程度上可减缓传统滑模控制的抖振现象,与传统迭代学习控制相比,系统具有鲁棒性。物理试验验证了所提控制策略的有效性。     

An aero-engine life-cycle maintenance policy optimization algorithm: Reinforcement learning approach

An aero-engine maintenance policy plays a crucial role in reasonably reducing maintenance cost. An aero-engine is a type of complex equipment with long service-life. In engineering,a hybrid maintenance strategy is adopted to improve the aero-engine operational reliability. Thus,the long service-life and the hybrid maintenance strategy should be considered synchronously in aero-engine maintenance policy optimization. This paper proposes an aero-engine life-cycle maintenance policy optimization algorithm that synchronously considers the long service-life and the hybrid maintenance strategy. The reinforcement learning approach was adopted to illustrate the optimization framework, in which maintenance policy optimization was formulated as a Markov decision process. In the reinforcement learning framework, the Gauss–Seidel value iteration algorithm was adopted to optimize the maintenance policy. Compared with traditional aero-engine maintenance policy optimization methods, the long service-life and the hybrid maintenance strategy could be addressed synchronously by the proposed algorithm. Two numerical experiments and algorithm analyses were performed to illustrate the optimization algorithm in detail.     

A linear ADRC-based robust high-dynamic double-loop servo system for aircraft electro-mechanical actuators

Compared with traditional hydraulic actuators, an Electro-Mechanical Actuator(EMA)is small in size and light in weight, so it has become more widely used. Aerodynamic load on aircraft control surface varies dramatically, and a change of flight environment leads to uncertainties of motor parameters. Therefore, high-dynamic response and strong anti-disturbance capability of an EMA are of great significance for aircraft rudder control and flight attitude adjustment. In order to improve dynamic response and disturbance rejection of an EMA and simplify control parameters tuning, a robust high-dynamic servo system based on Linear Active Disturbance Rejection Control(LADRC) is proposed for an EMA employing a Permanent Magnet Synchronous Motor(PMSM).Firstly, total disturbances of the EMA are analyzed, including parameter uncertainties, load variation, and static friction. A disturbance observer based on a reduced-order Extended State Observer(ESO) is designed to improve the anti-interference ability and dynamic performance. Secondly, the servo control architecture is simplified to a double-loop system, and a composite control of position and speed with acceleration feed-forward is presented to improve the EMA frequency bandwidth.Thirdly, the ideal model of the EMA is transformed into a simple cascade integral form with a disturbance observer, which makes it convenient to analyze and design the controller. Robustness performance comparisons are realized in frequency domain. Finally, simulation and experimental results have verified the effectiveness of the proposed strategy for EMAs.     

An efficient algorithm for calculating Profust failure probability

For efficiently estimating the Profust failure probability based on probability input variables and fuzzy-state assumption, a General Performance Function(GPF) expression is established under the strict mathematical derivation for the Profust reliability model. By constructing the GPF,the calculation of the Profust failure probability can be transformed into the calculation of the traditional failure probability. Then various existing methods for the traditional failure probability can be used to estimate the Profust failure probability. Due to the high efficiency of the Adaptive Kriging(AK) model and the universality of the Monte Carlo Simulation(MCS), AK inserted MCS(abbreviated as AK-MCS) has been proven to be an efficient method for estimating the failure probability. Therefore, the AK-MCS combined with the GPF(abbreviated as AK-MCS + GPF)is proposed for estimating Profust failure probability. The proposed method greatly reduces the computational cost while ensuring the accuracy. Finally, four examples are given to validate the proposed AK-MCS + GPF. The results of the examples show the rationality and the efficiency of the proposed AK-MCS + GPF.     

基于深度学习的超临界裂解煤油流量特性研究

为了明晰超临界裂解煤油的流量特性,实现对超临界裂解煤油流量的准确预测,采用实验方法测量了较大压力和温度范围内超临界裂解煤油的流量,对超临界裂解煤油流量特性进行了分析,基于多元线性回归方法,多元多项式回归方法和深度学习方法分别建立了超临界裂解煤油流量预测模型并给出了模型评估指标。研究结果表明,超临界裂解煤油流量主要与压降和温度有关,并且流量与压降和温度之间存在着很强的非线性关系;基于深度学习方法的深度神经网络模型性能优于多元线性回归模型和多元多项式回归模型,能够更加准确地刻画超临界裂解煤油的流量特性,其平均相对预测误差在1.1%左右,最大相对预测误差在7%以下。     

压气机叶片加工误差影响不确定分析

为了正确评估加工误差的影响,提出了一种考虑加工误差大小、分布随机性的数值研究方法以实现叶片性能不确定性分析。采用NURBS(非均匀有理B样条) 方法实现叶型参数化,通过检测及统计手段获取误差真实分布,运用蒙特卡洛模拟生成随机样本,并训练Kriging代理模型进行不确定性分析,得到了叶片加工误差对气动性能的影响。结果表明:加工误差对气动性能的影响与所处工况有关,最高使得损失增加0.853%;叶型性能对于吸力面表面型线更为敏感,在加工及检测过程应给予更高要求。      

Rotorcraft flight endurance estimation based on a new battery discharge model

To avoid the numerical complexities of the battery discharge law of electric-powered rotorcrafts,this study uses the Kriging method to model the discharge characteristics of Li-Po batteries under standard conditions.A linear current compensation term and an ambient temperature compensation term based on radial basis functions are then applied to the trained Kriging model,leading to the complete discharged capacity-terminal voltage model.Using an orthogonal experimental design and a sequential method,the coefficients of the current and ambient temperature compensation terms are determined through robust optimization.An endurance calculation model for electric-powered rotorcrafts is then established,based on the battery discharge model,through numerical integration.Laboratory tests show that the maximum relative error of the proposed discharged capacity-terminal voltage model at detection points is 0.0086,and that of the rotorcraft endurance calculation model is 0.0195,thus verifying their accuracy.A flight test further demonstrates the applicability of the proposed endurance model to general electric-powered rotorcrafts.