BFBEST知识库生成系统设计技术

本文介绍了医学专家系统开发工具BFBEST的知识库生成系统设计技术。包括:(1)灵活友好的用户接口,(2)帮助用户避免输入知识时的语法和语义错误;(3)允许用户用领域规范化形式的知识与系统对话,输入知识;(4)具有事务薄记功能;(5)具有对知识库进行增、删、改的能力;(6)能对输入知识进行完整性和一致性的检查;(7)能将知识的机内表示复原成规范化的形式;(8)具有传授式的部分自动获取知识的功能。 BFBEST开发机是在IBM-PC机上用Turbo-Prolog语言实现的。它实用性强、智能化程度高,能用来快速生成各种高性能的医学专家系统知识库。     

BACKGROUND KNOWLEDGE AND SECONDARY KNOWLEDGE BASES IN LEARNINGS YSTEMS

讨论了背景知识和领域理论在学习过程中的作用，强调了学习系统中背景知识的重要性。文中介绍了一个以领域理论为主知识库、以背景知识为二级知识库的基于解释的学习系统，说明基于解释的学习系统如何利用背景知识克服不完全的领域理论带来的问题，使其能通过纯演绎的方法实现知识级的学习。最后，本文还简单讨论了学习系统中背景知识的获取方法。     

Modelling of air temperature using remote sensing and artificial neural network in Turkey

The aim of this research was to forecast monthly mean air temperature based on remote sensing and artificial neural network (ANN) data by using twenty cities over Turkey. ANN contained an input layer, hidden layer and an output layer. While city, month, altitude, latitude, longitude, monthly mean land surface temperatures were chosen as inputs, and monthly mean air temperature was chosen as output for network. Levenberg–Marquardt (LM) learning algorithms and tansig, logsig and linear transfer functions were used in the network. The data of Turkish State Meteorological Service (TSMS) and Technological Research Council of Turkey–Bilten for the period from 1995 to 2004 were chosen as training when the data of 2005 year were being used as test. Result of research was evaluated according to statistical rules. The best linear correlation coefficient (R), and root mean squared error (RMSE) between the estimated and measured values for monthly mean air temperature with ANN and remote sensing method were found to be 0.991–1.254 K, respectively.     

Precise output loads control of load-diffusion components with topology optimization

The purpose of this paper is to present a novel topology optimization approach to control precisely the output loads under static loads and harmonic excitations. We introduce the Artificial Bar Element (ABE) at the designated output positions, where the output loads are equivalently measured and constrained with the nodal displacements of ABE. Optimization model is then formulated considering the output load constraints as well as the minimization of strain energy and dynamic displacement responses respectively under the static and dynamic conditions. The influences of the ABEs stiffness, different material usages of the design domain, widths of the output loads constraint intervals and variation ratios of output loads are discussed in detail. The proposed method is verified with several numerical examples with clear and reasonable load transfer paths.     

基于深度神经网络的航天器姿态控制系统故障诊断与容错控制研究

针对传统航天姿控系统故障诊断与容错控制诊断精度及控制分配效率较低的问题，提出了一种基于深度神经网络的航天器姿态控制系统故障诊断与容错控制方法。以控制力矩陀螺为执行机构的航天器发生执行机构故障工况时，所提出的方法可保证鲁棒的姿态控制。首先，利用三个异构深度神经网络实现传统容错控制器的故障诊断、姿态控制和力矩分配等功能，建立了全神经网络的智能自适应容错控制器架构。然后，对三个神经网络的网络层数、神经元数目和激活函数等参数进行优化调整，对比分析了神经网络参数对控制器性能的影响。最后，对所提出的新型控制器在控制力矩陀螺发生故障时的控制精度和鲁棒性进行了仿真验证。仿真结果表明，对于具有冗余控制力矩陀螺的航天器，提出的方法不仅能在单一陀螺故障下实现高精度的容错控制，也能在发生多陀螺故障时保证一定的姿态稳定控制。     

The lower ionosphere response to its disturbances by powerful radio waves

The paper presents data from some campaigns at Sura heating facility in 2011–1016. The experiments on probing of the artificial disturbed region of the lower ionosphere were carried out at two observation sites. One of them was located near Vasil’sursk 1 km from Sura facility (56.1°N; 46.1°E) and the other site was located at the Observatory (55.85°N; 48.8°E) of Kazan State University, 170 km to the East. Investigation of the features of the disturbed region of the lower ionosphere based on its diagnostics by the methods of the vertical sounding and oblique backscattering is the main goal of this paper. Ionosphere disturbance was fulfilled by the effect of the powerful radio wave of the ordinary or extraordinary polarization emitted by transmitters of the Sura facility with effective radiated power ERP = 50–120 MW at the frequency of 4.3, 4.7 and 5.6 MHz. Pumping waves were emitted with period from 30 s to 15 min. The disturbed region of the ionosphere in Vasil’sursk was probed by the vertical sounding technique using the partial reflexion radar at the frequency of 2.95 and 4.7 MHz. For the oblique sounding of the disturbed region the modified ionosonde Cyclon-M, operating at ten frequencies from 2.01 to 6.51 MHz was used at the Observatory site. On many heating sessions simultaneous variations of the probing partial reflection signals in Vasil’sursk and backscattered signals in Observatory were observed at the height at 40–100 km below the reflection height of the pumping wave. These observations were correlated with the pumping periods of the Sura facility. Possible mechanisms of the appearance of the disturbance in the lower ionosphere and its effect on the probing radio waves are discussed.     

A comparative analysis of SLR,MLR, ANN,XGBoost and CNN for crop height estimation of sunflower using Sentinel-1 and Sentinel-2

Sustainable monitoring and determining the biophysical characteristics of crops is of global importance due to the increase in demand for food. In this context, remote sensing data provide valuable information on crops. This study investigates the relationship between the variables determined from both Synthetic Aperture Radar (SAR) and optical images and crop height. For this purpose, backscatter (σVH, σVV, σVH / σVV) and coherence (?VH, ?VV) of multi-temporal dual-polarized Sentinel-1 and vegetation indices of multi-temporal Sentinel-2 data are analyzed. Two indices, namely, Normalized Difference Vegetation Index (NDVI) and NDVI with the red-edge band (NDVIred), are interpreted to identify the contribution of the red-edge band over the near-infrared band. The Zile District of Tokat province in Turkey where dominantly sunflower cultivation is carried out, was selected as the study area. In the analysis of the data, Simple Linear Regression (SLR), Multiple Linear Regression (MLR), Artificial Neural Network (ANN), EXtreme Gradient Boosting (XGBoost), and Convolutional Neural Network (CNN) were used. In the results of the study, ANN showed the lowest RMSE = 3.083 cm (RMSE%= 11.284) in the stem elongation period. The CNN followed the lowest RMSE for the Inflorescence development and flowering stages 19.223 cm (RMSE%=15.458) and 8.731 cm (RMSE%=5.821), respectively. In the ripening period, XGBoost achieved the lowest RMSE = 8.731 cm (RMSE%=6.091). All the best models in four methods were created using common variables of σVH, σVV, ?VH, ?VV and NDVIred, except ANN which exclude coherence variables. The results concluded that NDVIred contributed more than NDVI which is widely interpreted in previous studies.     

精确打击武器集群作战技术发展研究

对中远程精确打击武器集群作战进行综合评述，并对集群智能化技术体系发展布局进行探讨。首先基于分布式作战概念内涵提出了集群作战的共性特点，指出网络化和智能化是集群作战的本质特征。随后从目标指示、体系对抗、自主作战三个方面提出了对集群智能化作战的军事需求，并对由集群智能化技术带来的作战能力提升进行了分析研判。最后按照观察-判断-决策-行动作战循环梳理了集群智能化技术体系布局。综述表明，集群作战将是未来精确打击武器的主要作战形态，集群智能化技术是当前以及未来一段时间内的研究热点。     

Deep reinforcement learning for six degree-of-freedom planetary landing

This work develops a deep reinforcement learning based approach for Six Degree-of-Freedom (DOF) planetary powered descent and landing. Future Mars missions will require advanced guidance, navigation, and control algorithms for the powered descent phase to target specific surface locations and achieve pinpoint accuracy (landing error ellipse <5 m radius). This requires both a navigation system capable of estimating the lander’s state in real-time and a guidance and control system that can map the estimated lander state to a commanded thrust for each lander engine. In this paper, we present a novel integrated guidance and control algorithm designed by applying the principles of reinforcement learning theory. The latter is used to learn a policy mapping the lander’s estimated state directly to a commanded thrust for each engine, resulting in accurate and almost fuel-optimal trajectories over a realistic deployment ellipse. Specifically, we use proximal policy optimization, a policy gradient method, to learn the policy. Another contribution of this paper is the use of different discount rates for terminal and shaping rewards, which significantly enhances optimization performance. We present simulation results demonstrating the guidance and control system’s performance in a 6-DOF simulation environment and demonstrate robustness to noise and system parameter uncertainty.     

基于混合人工鱼群算法的传感器网络优化

针对传感器网络节点优化的问题,提出一种混合人工鱼群算法.该算法在人工鱼群算法优化的末段引入模式搜索法,以人工鱼搜索到的最优解作为模式搜索法的初始解,利用模式搜索法的单调搜索特性,将解引向全局极值.新算法保留了人工鱼群算法全局搜索能力强、寻优速度快的特点,使寻优精度得到了提高.仿真实验表明:混合人工鱼群算法能够有效地优化传感器网络节点部署,提高覆盖率.