结合邻域聚类分割的高光谱图像异常检测支持向量数据描述方法

支持向量数据描述方法在高光谱图像小异常目标检测中具有较好的检测性能,但是待检异常的几何形状受到约束和背景的选择具有盲目性影响检测效果,且检测需要对整幅图像进行遍历导致计算量大。提出邻域聚类分割和支持向量数据描述相结合的异常检测方法,首先利用邻域聚类方法分割图像,将几何尺寸小的分割块作为潜在异常目标;其次选择与潜在异常的形状和大小相适应的背景窗进行背景像元收集;最后采用SVDD方法从潜在异常中快速且准确地检测出异常目标。对HYMAP图像的实验结果表明,该算法提高了复杂地物背景下异常的检测性能,降低了SVDD用于高光谱图像异常检测的计算量。     

空间光学遥感器主镜背部形状的选择

本文阐述了空间光学遥感器中主镜轻量化的必要性．对双凹、平背、单拱和双拱4种形状主镜在重力载荷下的变形进行了分析计算，得出了背部3点支撑方式下双凹主镜最优的结论，并进一步研究了3点支撑的双凹主镜面形变化RMS值随规一化支撑半径r／R的变化规律．     

基于SVR的导航传感器自适应野值检测方法

针对Lagrange插值法无法处理连续野值的问题，提出了一种基于改进支持向量回归(Support Vector Regression, SVR)的导航传感器自适应野值检测方法。该方法结合了支持向量回归利用小样本数据就能够准确建模和3σ准则计算简易的优点，利用支持向量回归在线建立舰船的运动模型对测量值进行实时预测，并利用3σ准则自适应地计算阈值，然后通过比较阈值与预测残差来判别测量值是否为野值点。该方法可以自动地学习舰船的运动趋势，建立舰船的真实运动模型，而且不受连续野值点的影响，能够在没有其他传感器辅助的条件下完成野值检测。海试实测数据表明，提出的方法对离散和连续的野值点均具有较好的检测效果，同时可以更好地估计传感器的真实测量值。     

基于支持向量机方法的发动机性能趋势预测

为了提高对航空发动机性能趋势预测的精度，提出利用支持向量机方法来预测表征发动机整体性能的参数一性能综合指数。建立了基于支持向量回归的一步及多步预测模型，利用该模型对性能正常衰退及性能异常发动机的综合指数分别进行预测，并与自回归(AR)模型的预测值进行比较。结果表明，基于支持向量机的预测模型比AR模型的预测精度更高，其四步预测精度由80．56％提高到88．51％。因此该模型尤其适合中、长期预测。     

基于支持向量机的组合分类方法及应用

为了解决采用神经网络、决策树作为弱分类器的AdaBoost组合分类存在的不足,进一步改善组合分类效果,提出采用支持向量机(SVM)作为弱分类器的一种新的组合分类诊断方法——AdaBoost-SVM。该方法没有采用一个固定的SVM的核参数,而是自适应调整SVM中的核参数,从而得到一组有效的SVM弱分类器。通过对基准数据库的测试及航空发动机故障样本的诊断,结果表明,所提AdaBoost-SVM方法较好地解决了现有的Ada-Boost组合分类方法中存在的弱分类器本身参数选取困难问题及训练轮数的合理选取问题,并具有更好的泛化性能,更适合对分散程度较大、聚类性较差的航空发动机故障样本进行分类。     

Multi-state autonomous drilling for lunar exploration

Due to the lack of information of subsurface lunar regolith stratification which varies along depth, the drilling device may encounter lunar soil and lunar rock randomly in the drilling process. To meet the load safety requirements of unmanned sampling mission under limited orbital resources, the control strategy of autonomous drilling should adapt to the indeterminable lunar environments. Based on the analysis of two types of typical drilling media (i.e., lunar soil and lunar rock), this paper proposes a multi-state control strategy for autonomous lunar drilling. To represent the working circumstances in the lunar subsurface and reduce the complexity of the control algo-rithm, lunar drilling process was categorized into three drilling states:the interface detection, initi-ation of drilling parameters for recognition and drilling medium recognition. Support vector machine (SVM) and continuous wavelet transform were employed for the online recognition of dril-ling media and interface, respectively. Finite state machine was utilized to control the transition among different drilling states. To verify the effectiveness of the multi-state control strategy, drilling experiments were implemented with multi-layered drilling media constructed by lunar soil simulant and lunar rock simulant. The results reveal that the multi-state control method is capable of detect-ing drilling state variation and adjusting drilling parameters timely under vibration interferences. The multi-state control method provides a feasible reference for the control of extraterrestrial autonomous drilling.     

Behavior and functional modeling methods of doubly salient electromagnetic generators for aircraft electrical power system applications

The Doubly Salient Electromagnetic Generator(DSEG) is a promising candidate in aircraft generator application due to the simplicity, robustness and reliability. However, the field windings and the armature windings are strongly coupled, which makes the inductance characteristics non-linear and too complex to model. The complex model with low precision also leads to difficulties in modeling and analysis of the entire aircraft Electrical Power System(EPS). A behavior level modeling method based on modified inductance Support Vector Machine(SVM) is proposed. The Finite Element Analysis(FEA) inductance data are modified based on the experiment results to improve the precision. A functional level modeling method based on input–output characteristics SVM is also proposed. The two modeling methods are applied to a 9 kW DSEG prototype. The steady state and transient process precision of the proposed methods are proved by comparing with the experiment results. Meanwhile, the modeling time consumption, the application time consumption and the calculation resource demand are compared. The DSEG behavior and functional modeling methods provide precious results with high efficiency, which accelerates theoretical analysis and expands the application foreground of the DSEG in the aircraft EPS.     

基于滑动时窗策略自适应优化支持向量机的航空发动机性能参数在线预测

针对传统航空发动机性能参数时间序列预测方法存在的不足,提出了基于滑动时窗策略自适应优化支持向量机(Support Vector Machine,SVM)在线预测模型。该方法解决了训练样本动态适应性差的特点和老旧数据信息影响预测模型精度的问题。在该方法中,滑动时窗策略实时更新时窗数据训练样本,最终误差预报准则(Final Prediction Error,FPE)自适应地确定嵌入维数,遗传算法(Genetic Algorithm,GA)则实时自适应优化SVM建模参数。应用航空发动机排气温度偏差值(Delta Exhaust Gas Temperature,DEGT)数据进行实例验证,结果表明基于滑动时窗策略的自适应GA优化的SVM (GASVM)在线预测模型比传统的GASVM预测模型预测精度有显著提高。进一步分析了预测模型不同时窗宽度对短期预测精度的影响,展示了1步～10步预测的效果,结果表明在线预测模型在不同时窗宽度下短中期(5步以内)预测效果良好且稳定。文中提出的在线预测模型可用于航空发动机性能参数的预测,实现对航空发动机未来性能变化的预警。     

A straw-soil co-composting and evaluation for plant substrate in BLSS

Material closure is important for the establishment of Bioregenerative Life Support System, and many studies have focused on transforming candidate plant residues into plant culture medium. For the limitations of using wheat straw compost as substrate for plant cultivation, a straw-soil co-composting technique was studied. The changes of pH, C/N value, germination index, cellulose, lignin and so on were monitored during the co-composting process. The maturity was evaluated by the C/N value and the germination index. The result showed that after 45 days’ fermentation, the straw-soil final co-compost with inoculation (T1) became mature, while the co-compost without inoculation (T0) was not mature. In the plant culture test, the T1 substrate could satisfy the needs for lettuce’s growth, and the edible biomass yield of lettuce averaged 74.42 g pot⁻¹ at harvest. But the lettuces in T0 substrate showed stress symptoms and have not completed the growth cycle. Moreover, the results of nitrogen (N) transformation experiment showed that about 10.0% and 3.1% N were lost during the T1 co-composting and plant cultivation, respectively, 23.5% N was absorbed by lettuce, and 63.4% N remained in the T1 substrate after cultivation.     

Application of SVM on satellite images to detect hotspots in Jharia coal field region of India

The present paper deals with the application of Support Vector Machine (SVM) and image analysis techniques on NOAA/AVHRR satellite image to detect hotspots on the Jharia coal field region of India. One of the major advantages of using these satellite data is that the data are free with very good temporal resolution; while, one drawback is that these have low spatial resolution (i.e., approximately 1.1 km at nadir). Therefore, it is important to do research by applying some efficient optimization techniques along with the image analysis techniques to rectify these drawbacks and use satellite images for efficient hotspot detection and monitoring. For this purpose, SVM and multi-threshold techniques are explored for hotspot detection. The multi-threshold algorithm is developed to remove the cloud coverage from the land coverage. This algorithm also highlights the hotspots or fire spots in the suspected regions. SVM has the advantage over multi-thresholding technique that it can learn patterns from the examples and therefore is used to optimize the performance by removing the false points which are highlighted in the threshold technique. Both approaches can be used separately or in combination depending on the size of the image. The RBF (Radial Basis Function) kernel is used in training of three sets of inputs: brightness temperature of channel 3, Normalized Difference Vegetation Index (NDVI) and Global Environment Monitoring Index (GEMI), respectively. This makes a classified image in the output that highlights the hotspot and non-hotspot pixels. The performance of the SVM is also compared with the performance obtained from the neural networks and SVM appears to detect hotspots more accurately (greater than 91% classification accuracy) with lesser false alarm rate. The results obtained are found to be in good agreement with the ground based observations of the hotspots. This type of work will be quite helpful in the near future to develop a hotspots monitoring system using these operational satellites data.