局部轨迹信息的联机手写维吾尔文单词过切分

将手写单词分割成字符是一项艰巨的任务。本文提出一种基于局部轨迹信息的单词过切分方法。该方法中,在不预先对附加笔划进行分组,不确定基线位置和不做倾斜校正的情况下探索单词轨迹的局部信息进行过切分。利用的局部信息包括手写轨迹中的平直点、局部最大和最小、局部最右和最左。探索手写单词原轨迹点序列中的局部最大值和局部最小值的点,从中找出切分点。初步确定的切分块里找到最右边和最左边的点更新切分点。本文提出的方法在5个不同作者的500个无约束手写单词样本上进行测试。平均字符切分召回率和正确率分别为93.35%和69.97%。

基于极小阈值和曲线拟合的垂直投影汉字切分

针对传统汉字切分方法中对粘连汉字和重叠汉字切分不准确的问题,提出了基于极小阈值和曲线拟合的垂直投影汉字切分算法.该算法在传统垂直投影法汉字切分的基础上结合极小阈值和曲线拟合进行切分,实验结果表明:相对于传统汉字切分方法,该算法对含有粘连和重叠现象的手写体汉字文本的切分是有效的,从而可使手写体汉字的切分准确率有较大的提高.

基于贪吃蛇算法和部首识别的手写文本切分

针对手写中文文本交错、粘连、字内过分离等问题,提出一种基于贪吃蛇算法和部首识别的文本切分方法。首先,根据贪吃蛇算法建立文本原始切分轨迹,并依据多重规则优化切分路径;之后,基于粘连字符的轮廓和骨架提取候选粘连点,利用贪吃蛇算法进行二次切分;最后,对过切分字符,进行部首的笔段提取和识别,依据汉字结构确定合并方向,并结合几何置信度和识别置信度完成合并,得到最终正确的文本切分结果。以陕西省某高中试卷中1542行手写文本作为实验数据进行了算法验证,结果表明,该算法切分正确率可达到82.15%。

脱机手写维吾尔文单词的过拆分方法

脱机手写体维吾尔文切分是脱机手写体维吾尔文识别的基础,切分准确率直接影响识别的正确率,该问题的研究对提高识别的系统性能具有重要的意义。提出了一种脱机手写维吾尔文单过切分方法。该方法的基本过程是通过确定单词的主笔划找到单词的基线,再根据基线以上的部分过拆分单词,对该方案进行了实验,实验结果表明该文切分方案具有有效性和可行性。

ECT Image Analysis Methods for Shear Zone Measurements during Silo Discharging Process

The paper covers the electrical capacitance tomography(ECT) data analysis on shear zones formed during silo discharging process.This is due to the ECT aptitude for detection of slight changes of material concentration.On the basis of ECT visualisations,wall-adjacent shear zone profiles are analysed for different wall roughness parameters.The analysis on changes of material concentration,based on ECT images,enables the calculation for the characteristic parameters of shear zones-size and material concentration inside the shear zone in a dynamic process of silo discharging.In order to verify the methodology a series of experiments on gravitational flow of bulk solids under various conditions were conducted with different initial granular material packing densities and silo wall roughness.The investigation shows that the increase in container wall roughness is an effective method for reducing the dynamic effects during the material discharging,since these effects are resulted from the resonance between hopper construction and trembling material.Such effects will damage industrial equipment in practical applications and need further investigation.

Application of a fuzzy analytical hierarchy process to the prediction of vibration during rock sawing

A new predictive model for evaluating the vibration of a sawing machine was developed using a new rock classification system. The predictors are machine parameters and a rock sawability index. The new rock classification system includes four major parameters of the rock： uniaxial compressive strength, abrasiv- ity index, mean MoWs hardness, and Young＇s modulus. The FAHP approach was used when determining the weights of these parameters by six decision makers. Two groups of carbonate rocks were sawn using a fully-instrumented laboratory sawing rig at different feed rates and depths of cut. During the sawing trials system vibration was monitored as a measure of saw performance. Then, a new statistical model was obtained by multiple regression on the machining parameters and the rock sawability index. The model is very useful for the evaluation of the system vibration, and for selecting suitable machining parameters, from a limited set of mechanical properties.

ARX-NNPLS Model Based Optimization Strategy and Its Application in Polymer Grade Transition Process

Since it is often difficult to build differential algebraic equations (DAEs) for chemical processes, a new data-based modeling approach is proposed using ARX (AutoRegressive with eXogenous inputs) combined with neural network under partial least squares framework (ARX-NNPLS), in which less specific knowledge of the process is required but the input and output data. To represent the dynamic and nonlinear behavior of the process, the ARX combined with neural network is used in the partial least squares (PLS) inner model between input and output latent variables. In the proposed dynamic optimization strategy based on the ARX-NNPLS model, neither parameterization nor iterative solving process for DAEs is needed as the ARX-NNPLS model gives a proper representation for the dynamic behavior of the process, and the computing time is greatly reduced compared to conventional control vector parameterization method. To demonstrate the ARX-NNPLS model based optimization strategy, the polyethylene grade transition in gas phase fluidized-bed reactor is taken into account. The optimization results show that the final optimal trajectory of quality index determined by the new approach moves faster to the target values and the computing time is much less.

Elastoplastic model for discontinuous shear deformation of deep rock mass

Deep rock mass possesses some unusual properties due to high earth stress,which further result in new problems that have not been well understood and explained up to date.In order to investigate the deformation mechanism,the complete deformation process of deep rock mass,with a great emphasis on local shear deformation stage,was analyzed in detail.The quasi continuous shear deformation of the deep rock mass is described by a combination of smooth functions:the averaged distribution of the original deformation field,and the local discontinuities along the slip lines.Hence,an elasto-plastic model is established for the shear deformation process,in which the rotational displacement is taken into account as well as the translational component.Numerical analysis method was developed for case study.Deformation process of a tunnel under high earth stress was investigated for verification.

Numerical simulation of cutting process of the slice components cutting machine

By the use of ANSYS/LS-DYNA FEA software,numerical simulation on the cutting process of cutting plates with a reamer was carried out in the paper. The logical improvement was brought forward and the phenomenon of stress concentration was deceased by weighted analysis. The effects of different cut velocities and cutting thickness on life-spans of reamers were investigated, and the cutting parameters were optimized to satisfy the cutting precision and cutting efficiency. The study will provide a guide for the practical production.

Modeling of Transient Thermal Conditions in Cutting

The thermal conditions like the temperature distribution and the heat fluxes during metal cutting have a major influence on the machinability, the tool lifetime, the metallurgical structure and thus the functionality of the work piece. This in particular applies for manufacturing processes like milling, drilling and turning for high-value turbomachinery components like impellers, combustion engines and compressors of the aerospace and automotive industry as well as energy generation, which play a major role in modern societies. However, numerous analytical and experimental efforts have been conducted in order to understand the thermal conditions in metal cutting, yet many questions still prevail. Most models are based on a stationary point of view and do not include time dependent effects like in intensity and distribution varying heat sources, varying engagement conditions and progressive tool wear. In order to cover such transient physics an analytical approach based on Green＇s functions for the solution of the partial differential equations of unsteady heat conduction in solids is used to model entire transient temperature fields. The validation of the model is carried out in orthogonal cutting experiments not only punctually but also for entire temperature fields. For these experiments an integrated measurement of prevailing cutting force and temperature fields in the tool and the chip by means of high-speed thermography were applied. The thermal images were analyzed with regard to thermodynamic energy balancing in order to derive the heat partition between tool, chips and workpiece. The thus calculated heat flow into the tool was subsequently used in order to analytically model the transient volumetric temperature fields in the tool. The described methodology enables the modeling of the transient thermal state in the cutting zone and particular in the tool, which is directly linked to phenomena like tool wear and workpiece surface modifications.