基于颜色和纹理特征的花生仁外观品质检测研究

为了提高对花生仁外观缺陷的在线分类准确率及效率。通过对采集完好、破损、霉变的花生仁RGB图像进行均值位移法、灰度处理以及阈值分割等预处理,研究提取了花生仁HSV颜色空间下的H、S、V各分量的一阶矩和二阶矩共6个颜色特征值,再基于灰度共生矩阵法提取能量、熵、对比度、逆差分矩共4个纹理特征值,构建颜色和纹理结合的特征向量,最后分别采用BP神经网络和SVM分类器对花生仁进行分类识别。结果表明：在花生仁的整体识别准确率上,BP神经网络为96.67%,SVM分类器为97.22%,后者优于前者,在识别时间上BP和SVM分别为2.5 s和1.1 s,识别效率上也是SVM更好,综合识别准确率和效率两方面考虑,优先选择SVM分类器模型来对花生仁进行分类识别。     

Analysis of UHF Method Used in Partial Discharge Detection in GIS

The possibility of UHF (ultra high frequency) method used in partial discharge detection in GIS is analyzed, and the UHF sensor, simulating passive filter, detecting the method of wide-band and narrow-band are studied, in order to avoid interferes of low-frequency. The authors develop an inner loop sensor in GIS model and investigate UHF method detecting partial discharge in GIS. The results indicate that the UHF system of detecting PD can effectively detect partial discharge and avoid outer corona interfere and Periodic pulse interfere. At the same time, narrow-frequency PD detection is an effective detection method to restrain UHF interferes.     

GIS Partial Discharge Signal and Its Internal Sensor Detection

Partial discharge electromagnetic waves in GIS propagate is not only in the transverse electric and magnetic(TEM)mode, but also in transverse electric(TE) and transverse magnetic(TM)mode. The paper deduces out the mathematic expressions transient field excited by PD in GIS anywhere by using dyadic Green function theory. The contributions of TEM mode and all high order modes in the detecting frequency scope should be taken into consideration when calculating the electric field excited by PD in GIS. In simulative GIS laboratory, the designed inner couplers are superior to other outer sensors in detection of partial discharge. Inner couplers for the GIS model are developed and their frequency responses are analyzed in antenna model. At last the PD pulses excited by man-made defect are detected by inner couplers using high parameters oscilloscope.     

Statistical characteristics analysis of partial discharge in high voltage cable joint

Four typical physical models for the internal insulation defects of 110kV cable joint are designed, while the test platform for Partial Discharges (PD) research on cable joint is constructed. A large number of PD data under different models are obtained by inner broadband ring sensor. The statistical analysis on the PD pattern indicates that there are significant differences between four PD forms on the statistical characteristics such as the phase distribution, skewness, kurtosis and degree of asymmetry, which can be used as effective features to reflect different characteristics of PD. Surface discharge and conductive particles may cause more serious damage to the insulation performance of cable joint, so high precaution should be paid on site operation.     

Study on separation algorithm of convolutive mixing model and separation of mixing signals of multiple partial discharges

To identify individual partial discharges(PD)signals produced by multiple insulation defects in gas insolated switchgear (GIS),this paper analyses the mechanism of propagation and mixing of multiple PD electromagnetic wave signals in GIS cylinder and proposes the convolutive mixing model to describe it for a separation algorithm to acquire individual PD signals. With the non-stationary property,mixing PD signals are changed at time domain into a set consisting of short-time stationary PD signals and then the Molgedey-Schuster decorrelation approach is employed to separate these stationary PD signals at frequency domain. The correlation of the envelope of separated PD signals in this set is used to reconstruct PD signals to realize the separation of non-stationary UHF PD mixtures. The effective separation of actual UHF PD mixing signals validates the assumption of convolutive mixing process in GIS and also offers a new approach to the identification of mixing PD signals by external ultra-high frequency detection scheme from multiple insulation defects in GIS.     

GIS技术在中国农业气候区划中的应用进展

地理信息系统（GIS）的空间分析功能与传统区划方法的结合,可以得到更加精细的农业气候区划结果,其作为一种技术手段已经广泛应用于农业气候区划,为当地农业生产决策提供可靠的依据。笔者着重从气候要素细网格化、区划成果数字化、信息服务、“3S”技术相结合等四个方面,总结GIS技术在中国农业气候区划中的应用进展,对应用中所存在的问题进行分析讨论,提出将来可能的研究方向,以期对该领域的研究提供参考。几点建议如下：（1）进行农业气候区划时应综合考虑多种自然环境因素和社会因子;（2）运用GIS技术进行“自下而上”的区域合并过程中,需要更好地结合自动合并与人工合并;（3）区划指标应考虑运用逻辑交集运算;（4）建立基于Web技术的开放式共享GIS农业气候区划平台;（5）GIS结合GPS、卫星遥感数据可以从宏观的角度全面监测农作物的整个生长发育过程,对指导农业生产具有重要的应用价值。     

Multi class obstacles recognition for intelligent vehicle in urban traffic scenes

For multi class obstacles recognition for intelligent vehicle in urban traffic scenes, an improved Binary Tree Support Vector Machine (BT SVM) based on ensemble learning is presented. Based on the distributing probability and pattern diversity of each obstacle in urban traffic scenes, a compatible tree structure of BT SVM is designed. An approach based on AdaBoost ensemble learning is applied to reduce the transfer error and improve the accuracy and generalization ability of per node classifier. The proposed method can efficiently recognize 6 kinds of normal obstacle patterns in urban traffic scenes.     

Multi stage Classifier for Unconstrained Handwritten Numerals Recognition

A multi stage character classifier model is presented. By combining four independent algorithms, we integrate on line recognition method, off line recognition method, neural network method, tradition method into an unique pattern recognition system. The results and experiments show that our system has the merit of high recognition rate.     

Partial discharge pattern recognition based on S transform and two-directional 2DPCA

A new feature extraction method is proposed to recognize different types of partial discharge (PD) signals. Firstly,four typical categories of PD artificial defect models are made and S transform (ST) is employed to obtain a time-frequency representation of the recorded UHF signals. Then,two-directional two-dimensional principal component analysis ((2D) 2PCA) is applied to compress the ST amplitude (STA) matrix to extract features. Finally,support vector machine (SVM) combined with particle swarm optimization (PSO) algorithm is introduced to accomplish the recognition of experimental samples. Classification results demonstrate that the average recognition rate of (10,5) combination is the highest while the one of (5,5) combination is the lowest among four kinds of feature dimension combinations. Moreover,PSO can obviously improve the classification performance of SVM. Specifically,all the average recognition rates of PSO-SVM are higher than 94.43%and the maximum value comes to 97.67%. Therefore,the feature sets extracted by ST and (2D) 2PCA can not only achieve dramatic dimension reduction,but also retain the major information of original data. It is proved that the proposed algorithm can obtain ideal results in PD pattern recognition.     

空间开发适宜性分析与管制分区——以铜陵市为例

在市域空间利用规划过程中进行开发适宜性分区评价,明确市域开发适宜程度及空间分布,为市域空间利用规划中土地开发利用方向的确定和空间布局的划分提供科学依据,以更好地协调开发建设和生态环境保护的关系。借鉴国内外城市区域空间开发与管制的研究理论,以空间开发适宜性分析为基础,以高分辨率航空影像、统计年鉴、实地考察为数据源,从自然生态约束条件、经济发展支撑能力2个系统层面建立了包括9个要素、20个因子的评价指标体系;利用组合赋权法确定各评价因子的权重值,以栅格为评价单元,通过GIS空间分析技术构建一整套完整的市域空间管制分区技术体系。从而确定市域各评价单元的工业和城市开发适宜程度,进而划定各类管制区。以铜陵市为例进行实证研究,根据其自然生态约束及经济开发需求与支撑能力的综合空间分析,拟将铜陵市市域空间分为适宜建设区、较适宜建设区、限制建设区与禁止建设区,制定了分区管制措施,提出了空间利用建议,旨在促进铜陵形成经济发展与人口资源环境相协调的空间均衡格局,为铜陵市空间利用规划提供指导。     

基于GIS的广西暴雨灾害风险实时评估技术研究

为了科学应对广西暴雨灾害频发、影响日趋严重这一问题,选用广西自动站实时降雨量数据、历年暴雨灾情数据、广西社会经济数据及基础地理数据,采用主成分分析法、层次分析法等方法,结合GIS技术,研究了暴雨灾害危险度实时评估的技术方法,并基于暴雨灾害实时危险度、孕灾环境脆弱度、承灾体易损度和抗灾力等4个因子,构建了广西农业暴雨灾害风险度实时评估模型,选择2011年的一次暴雨过程对模型进行验证,验证结果表明：评估结果与实际灾情较为吻合,模型实践检验效果较好。     

Capacitive Coupler Used for Detecting Partial Discharge in GIS

The coaxial configuration of gas-insulated substations is of great advantages transmitting the electromagnetic wave excitated by partial discharge and of great advantages of partial discharge detection. Based the characteristics of configuration of GIS and PD signals inside, the authors design a disc coupler and a loop coupler for continuous monitoring of partial discharge in GIS, and analyze the sensor's characteristics theoretically. The frequency response (FR) characteristics of the disc coupler and the loop coupler are analyzed by the simulation and measurement realistically of square wave response. In addition, the measured results of partial discharge by the sensors designed in GIS are given, and it is shown that the sensors designed are available for the measurement of partial discharge in GIS.     

基于光谱特征与PLSR结合的叶面积指数拟合方法的无人机画幅高光谱遥感应用

以冬小麦LAI为研究对象,利用孕穗期、开花期和灌浆期获取的无人机UHD185高光谱影像以及同步测定的地面数据(冬小麦冠层ASD反射率和冬小麦LAI),论证光谱特征(红边参数或植被指数)与偏最小二乘回归算法结合的改进型LAI拟合方法在无人机画幅高光谱遥感LAI探测方面的应用价值。首先,从光谱反射率相关性和植被指数相关性两方面比较UHD185与ASD,验证UHD185数据精度;结果表明,第3~第96波段(458~830 nm)的无人机UHD185高光谱数据具有较好的光谱质量,适宜探测冬小麦LAI。其次,分析光谱特征(6种植被指数和4种红边参数)与LAI的相关性,并通过独立验证和交叉验证方法,依次对基于红边参数或植被指数的传统LAI拟合方法和改进型LAI拟合方法的冬小麦LAI预测精度进行评价,相比于传统LAI拟合方法,改进型LAI拟合方法能大幅度提高冬小麦LAI的预测精度,特别是PLSR+REP。研究结果证实,改进型LAI拟合方法能更加充分地利用无人机UHD185高光谱数据预测冬小麦LAI,可望为无人机高光谱遥感的作物理化参数探测提供几点可借鉴的思路。     

Face recognition method with local matching

From human cognition, a face recognition method with local matching based on statistical learning is proposed. The image is divided into several subimages and each subimage is considered as a weak classifier. The Adaboost learning algorithm is used to train the weak classifiers and construct a strong classifier. As a result, all subimages are effectively combined together to explore the best discriminating power and improve the classification accuracy. Compared with the holistic matching methods, the local matching method is robust to variations in illumination, expression, and pose, etc. The experimental results show that the proposed method can improve the face recognition accuracy and is robust to variations in illumination and expression.     

Analysis on Application in Profile Optimizing Based on Genetic Algorithms

In order to achieving the Automation of profile optimization and offering more reasonable schemes,the author proposes a kind of computer method based on hereditary algorithm,which is using mathematic methods to simplify the profile lines as a list of points and using cut-fill gross as aim's function and using restriced conditions to control the profile lines,the authors optimize the list of points of changing slopes,the results of the method are more accurate than the artificial design and can provide many kinds of schemes within short time.In the actual projects we can properly increase the condition restraints to design more high-quality lines.If GIS platform is added to it,the profile can be optimized more effectively and more intuitionisticly.     

Suppression of Periodic Narrowband Interferences in Cable Partial Discharge Detections

There are background noises and interferences in the signal acquired,due to partial discharge(PD) detection system covers a broad frequency band.To suppress periodic narrowband signal which is a quite serious interference in PD measurement,the existing suppression method is introduced,the new method of wavelet packet transform is mainly studied to de-noise the periodic narrowband in XLPE cable PD detection system,which is based on the db4 basic wavelet using soft threshold.The results of the experiment show that wavelet packet transform is effective in restraining the periodic narrowband interferences to extract the PD pulses in XLPE cable PD monitoring system.     

基于自然生态约束评价的县域生态安全格局构建

自然生态条件的空间差异是导致不同地区生态功能差异的重要原因,直接影响区域生态安全。本文以GIS技术为支撑,通过选择地形地貌、特殊生态保护区、区域环境容量等方面的评价指标, 进行自然生态约束的空间分异综合评价,依据评价结果划定生态功能属性不同的地域单元,为建构区域生态安全格局提供方法和理论支撑。文章以安徽无为县为案例进行实证分析,以县域内的23个乡镇为基本评价单元,选择山地、水网密度、湿地、自然保护区、水环境容量、地质灾害等因子,评价自然生态约束的空间差异,结合安徽无为县区域开发的方向,在县域内构建由3个生态源区、5个生态廊道和众多的生态楔构成的县域生态安全格局,最后对县域生态安全格局的建设提出讨论和建议。     

Partial Discharge in Oil-paper Insulation of Transformer

Based on the analysis of defect in oil-paper insulation of transformer, 5 corresponding PD models were made to simulate the actual defects existed in transformers. Aging experiment was carried out at different temperature and test voltage. The developing process of different types of PD was studied and the influence of temperature and voltage on PD in oil-paper insulation, were analyzed. Gray images show differences for different typrs of PD or one type of PD at different precedures. Gray images can be used to recognize PD patterns and discharge stage. The research resalts coutribute for further research on PD pattern recognition and insulation aging of transformer.     

Design method of generatingDICOM Image in the high frequency X ray machine

DICOM3.0 standard is complex and rich in contents. Aiming at the difficulty of software design, a programming method of generating DICOM image file in the high frequency X ray machine is proposed. The data structure of DICOM file is analyzed, and then the programming method of generating DICOM image files is introduced in detail. For the proposed method, a template array of the data structure is constructed to save the eigenvalues, transfer syntax, pixel data and so on of the image. All kinds of the data are stored in the DICOM file successively. The programming method can not only transform a BMP file into a DICOM file, but also transform a JPEG file into a DICOM file. It strictly follows DICOM 3.0 protocol. The generated DICOM files can be displayed with the DICOM file browsing software ezDICOM. The programming design was based on VC++6.0.