Reduced order model for unsteady aerodynamic performance of compressor cascade based on recursive RBF

Based on Recursive Radial Basis Function (RRBF) neural network, the Reduced Order Model (ROM) of compressor cascade was established to meet the urgent demand of highly efficient prediction of unsteady aerodynamics performance of turbomachinery. One novel ROM called ASA-RRBF model based on Adaptive Simulated Annealing (ASA) algorithm was developed to enhance the generalization ability of the unsteady ROM. The ROM was verified by predicting the unsteady aerodynamics performance of a highly-loaded compressor cascade. The results show that the RRBF model has higher accuracy in identification of the dimensionless total pressure and dimensionless static pressure of compressor cascade under nonlinear and unsteady conditions, and the model behaves higher stability and computational efficiency. However, for the strong nonlinear characteristics of aerodynamic parameters, the RRBF model presents lower accuracy. Additionally, the RRBF model predicts with a large error in the identification of aerodynamic parameters under linear and unsteady conditions. For ASA-RRBF, by introducing a small-amplitude and high-frequency sinusoidal signal as validation sample, the width of the basis function of the RRBF model is optimized to improve the generalization ability of the ROM under linear unsteady conditions. Besides, this model improves the predicting accuracy of dimensionless static pressure which has strong nonlinear characteristics. The ASA-RRBF model has higher prediction accuracy than RRBF model without significantly increasing the total time consumption. This novel model can predict the linear hysteresis of dimensionless static pressure happened in the harmonic condition, but it cannot accurately predict the beat frequency of dimensionless total pressure.     

基于神经网络的预膜雾化模型

为了实现对预膜雾化质量的快速预估，基于神经网络建立了以结构参数和工况参数为输入,SMD值为输出的预膜雾化模型。使用试验数据训练和测试网络模型,结果显示,模型在较宽的工作范围内具有较高的精度和较好的泛化能力。SMD预测值随输入参数的变化规律符合试验结论,可作为给定工况参数下预膜式雾化装置的结构参数优化依据。神经网络能够较好地学习预膜雾化过程中的隐含规律。随着供油压差的增大,预膜器逐渐出现阻雾化效应,导致其雾化效果比单喷嘴和直混式雾化均差。     

An intelligent approach for flight risk prediction under icing conditions

Flight risk prediction is significant in improving the flight crew’s situational awareness because it allows them to adopt appropriate operation strategies to prevent risk expansion caused by abnormal conditions, especially aircraft icing conditions. The flight risk space representing the nonlinear mapping relations between risk degree and the three-dimensional commanded vector(commanded airspeed, commanded bank angle, and commanded vertical velocity) is developed to provide the crew with practi...     

基于自适应神经模糊推理系统的导弹直/气复合控制系统设计

针对导弹直/气复合控制问题,提出了一种基于自适应神经模糊推理系统的导弹直/气复合控制系统设计方法.首先,建立了直/气复合导弹数学模型.然后,针对常规模糊控制设计严重依赖经验的问题,在模糊控制的基础上引入神经网络,通过样本数据学习建立自适应神经模糊推理系统(ANFIS),并设计了脉冲调宽调频调制器.最后,通过仿真试验验证了所提的控制系统设计方法.仿真结果表明,基于ANFIS的导弹直/气复合控制系统能够快速精确地跟踪加速度指令.     

基于深度强化学习的四足机器人后空翻动作生成方法

四足机器人灵巧运动技能的生成一直受到机器人研究者们的广泛关注,其中空中翻滚运动既能展现四足机器人运动的灵活性又具有一定的实用价值.近年来,深度强化学习方法为四足机器人的灵巧运动提供了新的实现思路,利用该方法得到的闭环神经网络控制器具有适应性强、稳定性高等特点.本文在绝影Lite机器人上使用基于模仿专家经验的深度强化学习方法,实现了仿真环境中四足机器人的后空翻动作学习,并进一步证明了设计的后空翻闭环神经网络控制器相比于开环传统位置控制器具有适应性更高的特点.     

Compressor geometric uncertainty quantification under conditions from near choke to near stall

Geometric and working condition uncertainties are inevitable in a compressor, deviating the compressor performance from the design value. It’s necessary to explore the influence of geometric uncertainty on performance deviation under different working conditions. In this paper, the geometric uncertainty influences at near stall, peak efficiency, and near choke conditions under design speed and low speed are investigated. Firstly, manufacturing geometric uncertainties are analyzed. Next, correlation models between geometry and performance under different working conditions are constructed based on a neural network. Then the Shapley additive explanations (SHAP) method is introduced to explain the output of the neural network. Results show that under real manufacturing uncertainty, the efficiency deviation range is small under the near stall and peak efficiency conditions. However, under the near choke conditions, efficiency is highly sensitive to flow capacity changes caused by geometric uncertainty, leading to a significant increase in the efficiency deviation amplitude, up to a magnitude of ?3.6%. Moreover, the tip leading-edge radius and tip thickness are two main factors affecting efficiency deviation. Therefore, to reduce efficiency uncertainty, a compressor should be avoided working near the choke condition, and the tolerances of the tip leading-edge radius and tip thickness should be strictly controlled.     

Recent progress of machine learning in flow modeling and active flow control

In terms of multiple temporal and spatial scales, massive data from experiments, flow field measurements, and high-fidelity numerical simulations have greatly promoted the rapid development of fluid mechanics. Machine Learning(ML) provides a wealth of analysis methods to extract potential information from a large amount of data for in-depth understanding of the underlying flow mechanism or for further applications. Furthermore, machine learning algorithms can enhance flow information and automat...     

Transition control of a tail-sitter unmanned aerial vehicle with L1 neural network adaptive control

The main task of this work is to design a control system for a small tail-sitter Unmanned Aerial Vehicle(UAV) during the transition process. Although reasonable control performance can be obtained through a well-tuned single PID or cascade PID control architecture under nominal conditions, large or fast time-varying disturbances and a wide range of changes in the equilibrium point bring nonlinear characteristics to the transition control during the transition process, which leads to control prec...     

机动发射弹道导弹集群诸元快速规划

针对机动发射条件下弹道导弹集群的飞行诸元快速规划问题，将神经网络预测与最小二乘优化相结合，提出了一种弹道导弹发射诸元快速规划方法。首先分析了弹道导弹助推段飞行策略并选取适当的发射诸元，以发落点信息为输入，设计双隐藏层诸元预测网络，通过弹道仿真获取弹道数据建立数据集完成网络训练，利用该网络可以得到发射诸元迭代初值。在此基础上，为了消除数据集中样本数据不平衡对发射诸元规划精度的影响，以落点射程、横程、高程偏差最小为指标函数，结合最小二乘优化方法进行迭代获得发射诸元精确解。最后在典型发射场景下，进行了弹道导弹集群机动快速发射仿真验证。结果表明，该方法相较于传统方法可显著提高计算速度与精度，且在给定的大范围机动条件下，能够满足弹道导弹集群对远距离、多目标的快速精确打击。     

运载火箭遥测数据智能判读算法应用

在运载火箭高发射密度、高判读需求、高数据量的背景下，现有自动化判读的判据覆盖率不全、判据编写门槛高、耗时多的问题日益凸显，缺少较通用的算法对传统判读算法未覆盖的判读任务进行判读补充，进而影响运载火箭效果评估与系统性能评定。为充分挖掘海量遥测数据中隐含的参数变化规律，设计智能判读算法作为传统算法的有益补充，提升传统判读的判读覆盖率和判读效率。以液体运载火箭长期加电试验产生的遥测数据为研究对象，设计集成神经网络智能判读算法，在给出的判读指标下研究得出，集成神经网络在频率异常、丢帧等五种现有判据难以描述的判读场景下，判读性能提升30%，提高了现有判据的覆盖率，后续可为判读体系完善和智能判读落地提供研究参考。