基于支持向量机回归和RBF神经网络的PID整定

针对工业控制领域中非线性系统控制,在基于梯度下降法的RBF网络PID整定的基础上,对整定算法作出改进,控制目标不再是使当前跟踪误差最小,而是使当前跟踪误差和下一时刻跟踪误差的平方和最小。实现过程为:先由RBF神经网络在线辨识被控对象离散模型,得到被控对象的Jacobian信息,采用梯度下降法对PID控制器参数进行初步整定;然后,将系统跟踪误差和PID参数输入支持向量机模型,通过回归预测系统下一时刻的误差,改进的整定算法利用预测误差信息对参数进行再整定。仿真结果表明,引入支持向量机回归优化的RBF神经网络PID整定收敛速度更快,精度更高,跟踪性能优于RBF神经网络PID整定。     

Comparison of three soil-like substrate production techniques for a bioregenerative life support system

It is very important to recycle the inedible biomass of higher plants to improve the closure of bioregenerative life support system (BLSS). Processing candidate higher plant residues into the soil-like substrate (SLS) as the plant growth medium is a promising way to achieve. In this study, three different processing techniques of SLSs, using residues of wheat and rice as feedstock, were compared. As for the first traditional technique, SLS1 was obtained by successive conversion of wheat straw by oyster mushrooms and worms. In the other two methods, SLSs were produced with aerobic fermentation (SLS2) or anaerobic fermentation (SLS3) followed by worm conversion. The changes in SLS cellulose, lignin, available elements and pH were measured during the production processes. The maturity was evaluated by the value of C/N. The fertilities were compared in terms of available elements contents and lettuce productivities. The results indicated that the second technique was optimal, whose process cycle was 30 days less than that of SLS1. The total cellulose and lignin degradation of SLS2, achieved 98.6% and 93.1% during the 93-days-processing, and the lettuce productivity reached 12.0 g m⁻² day⁻¹.     

基于CSDB的装甲装备IETM技术研究

引入S1000D国际规范制作IETM,体现了装备全寿命信息管理(CALS)的思想。CSDB是S1000D规范的核心概念,所存储的技术信息能实现"一次生成、多次使用"的目标,存储有DM、PM等信息对象,负责信息对象的存储和管理工作。研究了基于CSDB的装备IETM技术,对加快装甲装备保障信息化建设的作用和意义重大。     

Effects of lighting and air movement on temperatures in reproductive organs of plants in a closed plant growth facility

Temperature increases in plant reproductive organs such as anthers and stigmas could cause fertility impediments and thus produce sterile seeds under artificial lighting conditions without adequately controlled environments in closed plant growth facilities. There is a possibility such a situation could occur in Bioregenerative Life Support Systems under microgravity conditions in space because there will be little natural convective or thermal mixing. This study was conducted to determine the temperature of the plant reproductive organs as affected by illumination and air movement under normal gravitational forces on the earth and to make an estimation of the temperature increase in reproductive organs in closed plant growth facilities under microgravity in space. Thermal images of reproductive organs of rice and strawberry were captured using infrared thermography at air temperatures of 10–11 °C. Compared to the air temperature, temperatures of petals, stigmas and anthers of strawberry increased by 24, 22 and 14 °C, respectively, after 5 min of lighting at an irradiance of 160 W m⁻² from incandescent lamps. Temperatures of reproductive organs and leaves of strawberry were significantly higher than those of rice. The temperatures of petals, stigmas, anthers and leaves of strawberry decreased by 13, 12, 13 and 14 °C, respectively, when the air velocity was increased from 0.1 to 1.0 ms⁻¹. These results show that air movement is necessary to reduce the temperatures of plant reproductive organs in plant growth facilities.     

Comparison of ANN and MLR models for estimating solar radiation in Turkey using NOAA/AVHRR data

In this paper, the estimation capacities of MLR and ANN are investigated to estimate monthly-average daily SR over Turkey. The satellite data are used for 73 different locations over Turkey. Land surface temperature, altitude, latitude, longitude and month are offered as the input variables for modeling ANN and MLR to get SR. Estimations of SR are evaluated with the meteorological values by using the statistical bases. The obtained results indicated that the ANN model could achieve a satisfactory performance when compared to the MLR model. Moreover, it is understood that more accurate results in estimation of SR are obtained in the use of satellite data, rather than the use of meteorological station data. Finally, the built ANN model is used to estimate the yearly average of daily SR over Turkey. As a result, satellite-based SR map for Turkey is generated.     

敏捷性导弹的双网络逆动态模糊神经网络控制

新疆敏捷性导弹为了获得更高的机动性、敏捷性和好的导引精度，许多采用推力矢量控制方案，本文讨论了一类带推力矢量控制导弹的数学建模，在此基础上提出了一种适用于此类新型导弹的模糊神经网络控制方案，采用双网络逆动态学控制结构，数字仿真表明所提出的控制方案对于系统内参数不确定性和非线性变化具有强的适应性。     

用于发动机涡轮盘叶片加工的夹具设计

介绍了用于加工发动机涡轮盘叶片夹具的设计准则,并给出了采用矢量三角函数和VC软件计算夹具极限偏差的公式及其判别依据,采用该准则设计的夹具用于涡轮盘叶片加工,产品满足设计要求,并通过了发动机热试车考核。     

基于GPR模型的自适应平方根容积卡尔曼滤波算法

与传统算法一样,动态系统的参数化模型(含噪声统计特性)未知或不够准确易导致容积卡尔曼滤波(CKF)效果严重下降,甚至滤波结果发散.为此,利用高斯过程回归(GPR)方法对训练数据进行学习,得到动态系统的状态转移GPR模型和量测GPR模型以及噪声统计特性,用以替代或增强原有动态系统模型,并将其融入到平方根容积卡尔曼滤波(SRCKF)中,分别提出了无模型高斯过程SRCKF (MFGP-SRCKF)和模型增强高斯过程SRCKF (MEGP-SRCKF)两种算法.仿真结果表明:这两种新的自适应滤波算法提高了动态系统模型精度,且实时自适应调整噪声的协方差,克服了传统算法滤波性能易受系统模型限制的问题;与MFGP-SRCKF相比,在给定一个不够准确的参数化模型,且有限的训练数据未能遍布估计状态空间的情况下,MEGP-SRCKF具备更高的滤波精度.     

基于数理统计的航材备件预测方法研究

备件预测是航空公司备件订货和供货方零部件生产计划的基础,本文提出以数理统计方法来判断附件寿命分布形式,对附件寿命和故障率进行估算,并据此给出航材备件需求量及其保障率预测模型,并运用实例进行了验证。     

基于鉴相器的矢量跟踪环设计

基于鉴相器的矢量跟踪环是锁定导航卫星码和载波的一种跟踪算法,这种算法适合于在弱信号环境下进行跟踪。矢量环不仅充分利用信号跟踪和导航状态解算之间的内在耦合关系,而且每一通道中采用鉴相器和锁频环结合的方式,系统一步内完成信号跟踪和导航解算任务。反馈控制量NCO是由导航滤波器和环路内部滤波器共同产生。实验表明,矢量跟踪环具有快速重捕获特性,能够在弱信号的环境下运行,比起传统环路有更小的跟踪误差。