基于HALCON的发票号字符识别研究

为了解决人工方式识别发票号效率低下、费时费力的问题,以HALCON软件为平台,对发票号进行识别,首先,对读取的图像进行图像预处理,包括把原图像转化成单通道图像、图像增强、高斯滤波、阈值分割和连通区域分割,然后对预处理后的图像进行数学形态学处理,接着把粘连的数字拆分开,最后用基于多层感知分类器(MLP)对发票号数字进行识别.通过与人工方式的方法对比,结果表明,用基于HALCON的方法,发票号数字能被快速、精确的识别出来,有效的减少了人员的工作量,提高了工作效率.     

基于切片反射采样的风电并网系统可用输电能力概率风险评估

如何全面地考虑风电功率的波动性和随机性,提高风电场出力概率分布采样的速度及精度,进而有效评估可用输电能力(ATC)成为亟待解决的问题。为此,提出基于切片反射采样(RSS)的改进方法对风电并网系统的ATC进行概率风险评估。对风电场出力进行优化建模,利用RSS对模型进行采样并构建样本空间,将样本值代入潮流方程进行最优潮流计算,并对ATC评估指标进行统计分析。含有风电场模型的IEEE 30节点系统仿真结果表明,与常规Gibbs采样算法相比,所提方法在确保计算效率的同时显著提高了采样方法的准确度。     

Effect of prestressed ultrasonic peen forming parameters on bending curvature and spherical deformation of plate

The elastic prestressed ultrasonic peen forming (UPF) was adopted in order to solve problems of insufficient bending deformation and large spherical deformation of plate during free UPF. The theoretical analysis of prestressed UPF and the influence of elastic prebending moment on deformation were analyzed. Spherical deformation coefficient was defined to quantificationally describe the spherical deformation. Experiments were conducted to compare the differences between free UPF and prestressed UPF processes and the effects of processing parameters on bending curvature and spherical deformation coefficient were studied. The results show that peening trajectory in chordwise direction is beneficial to enlarging spanwise bending deformation and decreasing spherical deformation coefficient. Large prebending curvature is helpful to increase spanwise bending deformation and decrease chordwise deformation, thereby obviously decreasing spherical deformation coefficient. Large spanwise deformation can be obtained under large firing pin velocity, small plate thickness and small offset distance. Large firing pin velocity plays a positive role in decreasing spherical deformation, while plate thickness and offset distance have little effect on it. Above all, prebending curvature and peening trajectory are the most important factors during prestressed UPF process. This study provides guidance for parameters optimization of prestressed UPF for wing plate with large thickness.     

塑性强化材料矫直反弯特性研究

为了深入研究塑性强化材料在平行辊式矫直过程中一次反弯与二次反弯特性的关系,根据工程弹塑性力学的基本原理,建立基于强化弹塑性材料辊式矫直弯曲力学模型。通过解析法描述两次反弯过程中的应力关系,给出辊式矫直过程中截面弯曲过程材料残余应力分布、弯矩比、加载应力变化过程。证明两次反弯过程中经历一次反弯后,二次反弯截面弯矩比与曲率比不再是原有简单M-C关系,而是与一次弯曲曲率比、二次弯曲曲率比与强化系数相关的函数。理论上证明原有弯曲理论不再完全适用于多次连续反弯矫直过程。解析结果表明,辊式矫直过程中经历二次反弯的材料截面弹性极限弯矩值下降,矫直弯曲减小,回弹比增大。同种材料考虑强化与不考虑强化矫直后残余应力均方差分别为71.2与65.6,回弹比均值分别为0.49和0.43。     

基于FDTD的粗糙地面宽带前向电磁散射研究

采用指数型分布粗糙面模拟实际的粗糙地面,运用FDTD方法研究了超宽带高斯脉冲电磁波入射粗糙地面时的宽带前向电磁散射问题;通过数值计算得到前向散射系数随频率的变化曲线,并与时谐场源激励下的结果进行了对比;分析了不同的粗糙地面高度起伏相关长度、均方根高度,土壤湿度和入射角下前向散射系数随频率的变化关系,得到了指数型分布粗糙地面的宽带前向电磁散射特性。数值计算结果表明各参数的变化对前向电磁散射系数的影响比较明显,入射波不同极化方式下的前向散射系数也有显著变化。     

基于异构描述子的新型高斯混合模型图像自动标注方法

过去几十年以来,各种图像标注算法相继提出。这些方法要么需要很大的计算量,要么标注效果不理想。论文提出了一种基于异构描述子的新型高斯混合模型图像语义自动标注方法。本文的高斯混合模型是采用异构空间来构建的,不同于其他的高斯混合模型。对于每个标注词,在多个特征空间下分别用高斯模型来描述,形成对应子空间的“标注词分描述子”。由于各个分描述子描述不同标注词的能力有很大差别,因此通过机器学习的方法来融合这些分描述子,形成更加有效的“标注词描述子”,从而提高标注的准确率。论文提出的“标注词描述子”可以有效地建立图像高层语义概念与底层视觉特征之间的对应关系,准确地描述标注词的语义内容,从而提高图像的标注性能。通过在COREL数据集上的测试表明了方法的有效性。     

基于广义S变换的高斯领域时频滤波方法

针对S变换时频滤波局部时频区域选择问题,提出了一种高斯邻域阈值滤波方法。首先,利用S变换的二维时频特性,构建时频分辨率可调的广义S变换,提高分析信号的时频分辨率。然后根据不同时频分布类型,定义了3种不同的高斯邻域时频滤波模型。针对不同模型高斯邻域,对信号中S矩阵高斯邻域内的时频数据采用局部阈值处理,保留有用信息,通过广义S反变换得到滤波后的信号。仿真与实验结果表明,广义S变换高斯邻域时频阈值滤波方法具有较高的滤波精度,该滤波模型能有效减小滤波均方差。     

Capacitor placement of distribution systems using particle swarm optimization approaches

Capacitor placement plays an important role in distribution system planning and operation. In distribution systems of electrical energy, banks of capacitors are widely installed to compensate the reactive power, reduce the energy loss in system, voltage profile improvement, and feeder capacity release. The capacitor placement problem is a combinatorial optimization problem having an objective function composed of power losses and capacitor installation costs subject to bus voltage constraints. Recently, many approaches have been proposed to solve the capacitor placement problem as a mixed integer programming problem. This paper presents a new capacitor placement method which employs particle swarm optimization (PSO) approaches with operators based on Gaussian and Cauchy probability distribution functions and also in chaotic sequences for a given load pattern of distribution systems. The proposed approaches are demonstrated by two examples of application. Simulation results show that the proposed method can achieve an optimal solution as the exhaustive search can but with much less computational time.     

煤气化装置中黑水角阀内部流场优化研究

为解决煤气化装置中黑水角阀阀体损坏严重的问题,建立3种具有不同流动曲面的黑水角阀几何模型,采用CFD软件Fluent中k-ε模型,对黑水角阀内部流场进行了仿真计算和分析。结果表明,通过改变阀体入口和出口的曲率半径,在黑水角阀内部流场的不同位置产生涡流,可改变流体的流动方向,从而影响闪蒸和气蚀的发生位置,避免在阀体处发生气蚀,减轻对阀体的损坏。     

State of health estimation of lithium‐ion batteries: A multiscale Gaussian process regression modeling approach

Accurate state of health (SOH) estimation in lithium‐ion batteries, which plays a significant role not only in state of charge (SOC) estimation but also in remaining useful life (RUL) prognostics is studied. SOC estimation and RUL prognostics often require one‐step‐ahead and long‐term SOH prediction, respectively. A systematic multiscale Gaussian process regression (GPR) modeling method is proposed to tackle accurate SOH estimation problems. Wavelet analysis method is utilized to decouple global degradation, local regeneration and fluctuations in SOH time series. GPR with the inclusion of time index is utilized to fit the extracted global degradation trend, and GPR with the input of lag vector is designed to recursively predict local regeneration and fluctuations. The proposed method is validated through experimental data from lithium‐ion batteries degradation test. Both one‐step‐ahead and multi‐step‐ahead SOH prediction performances are thoroughly evaluated. The satisfactory results illustrate that the proposed method outperform GPR models without trend extraction. It is thus indicated that the proposed multiscale GPR modeling method can not only be greatly helpful to both RUL prognostics and SOC estimation for lithium‐ion batteries, but also provide a general promising approach to tackle complex time series prediction in health management systems. © 2015 American Institute of Chemical Engineers AIChE J, 61: 1589–1600, 2015