科创中国

针对传统SVM主动学习中批量采样方法的不足,提出了动态可行域划分算法.从特征空间与参数空间的对偶关系入手,深入分析SVM主动学习的本质,将特征空间中对样本的标注视为参数空间中对可行域的划分;通过综合利用当前分类模型和先前标注样本两方面信息,动态地优化可行域划分方案,以确保选取的样本对模型改进的价值,最终实现更为高效的选择性采样.实验结果表明,基于动态可行域划分的SVM主动学习算法能够显著提高所选样本的信息量,从而能够在有限的标注代价下大幅提高其分类性能.

The compliance modeling and rigidity performance evaluation for the lower mobility parallel manipulators are still to be remained as two overwhelming challenges in the stage of conceptual design due to their geometric complexities. By using the screw theory, this paper explores the compliance modeling and eigencompliance evaluation of a newly patented 1T2R spindle head whose topological architecture is a 3-RPS parallel mechanism. The kinematic definitions and inverse position analysis are briefly addressed in the first place to provide necessary information for compliance modeling. By considering the 3-RPS parallel kinematic machine(PKM) as a typical compliant parallel device, whose three limb assemblages have bending, extending and torsional deflections, an analytical compliance model for the spindle head is established with screw theory and the analytical stiffness matrix of the platform is formulated. Based on the eigenscrew decomposition, the eigencompliance and corresponding eigenscrews are analyzed and the platform's compliance properties are physically interpreted as the suspension of six screw springs. The distributions of stiffness constants of the six screw springs throughout the workspace are predicted in a quick manner with a piece-by-piece calculation algorithm. The numerical simulation reveals a strong dependency of platform's compliance on its configuration in that they are axially symmetric due to structural features. At the last stage, the effects of some design variables such as structural, configurational and dimensional parameters on system rigidity characteristics are investigated with the purpose of providing useful information for the structural design and performance improvement of the PKM. Compared with previous efforts in compliance analysis of PKMs, the present methodology is more intuitive and universal thus can be easily applied to evaluate the overall rigidity performance of other PKMs with high efficiency.

Parallel kinematic machines have drawn considerable attention and have been widely used in some special fields.However,high precision is still one of the challenges when they are used for advanced machine tools.One of the main reasons is that the kinematic chains of parallel kinematic machines are composed of elongated links that can easily suffer deformations,especially at high speeds and under heavy loads.A 3-RRR parallel kinematic machine is taken as a study object for investigating its accuracy with the consideration of the deformations of its links during the motion process.Based on the dynamic model constructed by the Newton-Euler method,all the inertia loads and constraint forces of the links are computed and their deformations are derived.Then the kinematic errors of the machine are derived with the consideration of the deformations of the links.Through further derivation,the accuracy of the machine is given in a simple explicit expression,which will be helpful to increase the calculating speed.The accuracy of this machine when following a selected circle path is simulated.The influences of magnitude of the maximum acceleration and external loads on the running accuracy of the machine are investigated.The results show that the external loads will deteriorate the accuracy of the machine tremendously when their direction coincides with the direction of the worst stiffness of the machine.The proposed method provides a solution for predicting the running accuracy of the parallel kinematic machines and can also be used in their design optimization as well as selection of suitable running parameters.

Expandable profile liner(EPL) is a promising new oil well casing cementing technique, and welding is a major EPLs connection technology. Connection of EPL is still in the stage of manual welding so far, automatic welding technology is a hotspot of EPL which is one of the key technologies to be solved. A robot for automatic welding of "8" type EPL is studied. Four quadrants of mathematical equations of the 8-shaped cross-section track of EPL, consisting of multiple arcs, are established. Mechanism program for complex cross-section welding of EPL based on angle detection is proposed according to characteristics of small size, small valleys, and large forming errors, etc. A welding velocity vector control model is established by linkage control of a welding vehicle, a small driven actuator, and a height tracking mechanism. A constant speed control model based on an angle and symmetrical analysis model of rectangular coordinate system for EPL is built. Constraint conditions of constant speed control between each section are analyzed with 4 sections in first quadrant as an example, and cooperation work mechanism of the welding vehicle and the small tracking actuator is established based on pressure detection. The constant speed control model using angle self-test can be used to avoid the need for a precise mathematical model for tracking control and to adapt manufacture and installation deviation of EPL workpiece. The model is able to solve constant speed and trajectory tracking problems of EPL cross-section welding. EPL seams welded by the studied robot are good in appearance, and non-destructive testing(NDT) shows the seams are good in quality with no welding defects. Bulge tests show that the maximum pressure of welded EPL is 35 MPa, which can fulfill expansion performance requirements.

The current development of precision plastic injection molding machines mainly focuses on how to save material and improve precision, but the two aims contradict each other. For a clamp unit, clamping precision improving depends on the design quality of the stationary platen. Compared with the parametric design of stationary platen, structural scheme design could obtain the optimization model with double objectives and multi-constraints. In this paper, a SE-160 precision plastic injection molding machine with 1600 kN clamping force is selected as the subject in the case study. During the motion of mold closing and opening, the stationary platen of SE-160 is subjected to a cyclic loading, which would cause the fatigue rupture of the tie bars in periodically long term operations. In order to reduce the deflection of the stationary platen, the FEA method is introduced to optimize the structure of the stationary platen. Firstly, an optimal topology model is established by variable density method. Then, structural topology optimizations of the stationary platen are done with the removable material from 50%, 60% to 70%. Secondly, the other two recommended optimization schemes are given and compared with the original structure. The result of performances comparison shows that the scheme II of the platen is the best one. By choosing the best alternative, the volume and the local maximal stress of the platen could be decreased, corresponding to cost-saving material and better mechanical properties. This paper proposes a structural optimization design scheme, which can save the material as well as improve the clamping precision of the precision plastic injection molding machine.

Due to the large variations of environment with ever-changing background and vehicles with different shapes, colors and appearances, to implement a real-time on-board vehicle recognition system with high adaptability, efficiency and robustness in complicated environments, remains challenging. This paper introduces a simultaneous detection and tracking framework for robust on-board vehicle recognition based on monocular vision technology. The framework utilizes a novel layered machine learning and particle filter to build a multi-vehicle detection and tracking system. In the vehicle detection stage, a layered machine learning method is presented, which combines coarse-search and fine-search to obtain the target using the Ada Boost-based training algorithm. The pavement segmentation method based on characteristic similarity is proposed to estimate the most likely pavement area. Efficiency and accuracy are enhanced by restricting vehicle detection within the downsized area of pavement. In vehicle tracking stage, a multi-objective tracking algorithm based on target state management and particle filter is proposed. The proposed system is evaluated by roadway video captured in a variety of traffics, illumination, and weather conditions. The evaluating results show that, under conditions of proper illumination and clear vehicle appearance, the proposed system achieves 91.2% detection rate and 2.6% false detection rate. Experiments compared to typical algorithms show that, the presented algorithm reduces the false detection rate nearly by half at the cost of decreasing 2.7%–8.6% detection rate. This paper proposes a multi-vehicle detection and tracking system, which is promising for implementation in an on-board vehicle recognition system with high precision, strong robustness and low computational cost.

Steering control of a capsule robot in curve environment by magnetic navigation is not yet solved completely.A petal-shaped capsule robot with less steering resistance based on multiple wedge effects is presented,and an optimization method with two processes for determining the orientation of a pre-applied universal magnetic spin vector is proposed.To realize quick and non-contact steering swimming,a fuzzy comprehensive evaluation method for optimizing the steering driving angle is presented based on two evaluation indexes including the average steering speed and the average steering trajectory deviation,achieving the initial optimal orientation of a universal magnetic spin vector.To further reduce robotic magnetic vibration,a main target method for optimizing its final orientation,which is used for fine adjustment,is employed under the constrains of the magnetic moments.Swimming experimental results in curve pipe verified the effectiveness of the optimization method,which can be effectively used to realize non-contact steering swimming of the petal-shaped robot and reduce its vibration.

The current research of machine center accuracy in workspace mainly focuses on the poor geometric error subjected to thermal and gravity load while in operation,however,there are little researches focusing on the effect of machine center elastic deformations on workspace volume.Therefore,a method called pre-deformation for assembly performance is presented.This method is technically based on the characteristics of machine tool assembly and collaborative computer-aided engineering(CAE)analysis.The research goal is to enhance assembly performance,including straightness,positioning,and angular errors,to realize the precision of the machine tool design.A vertical machine center is taken as an example to illustrate the proposed method.The concept of travel error is defined to obtain the law of the guide surface.The machine center assembly performance is analyzed under cold condition and thermal balance condition to establish the function of pre-deformation.Then,the guide surface in normal direction is processed with the pre-deformation function,and the machine tool assembly performance is measured using a laser interferometer.The measuring results show that the straightness deviation of the Z component in the Y-direction is 158.9%of the allowable value primarily because of the gravity of the spindle head,and the straightness of the X and Y components is minimal.When the machine tool is processed in pre-deformation,the straightness of the Z axis moving component is reduced to 91.2%.This research proposes a pre-deformation machine center assembly method which has sufficient capacity to improving assembly accuracy of machine centers.

详细介绍了SVPWM的原理.采用一种易于数字化实现的SVPWM算法实现三相电压型SVPWM整流器,该整流器采用dq坐标系下的双闭环控制.给出了PI调节器参数,以及主电路电感、电容的计算公式.在Matlab Simulink环境下搭建整流器仿真器模型.仿真结果表明,整流器能实现单位功率因数整流和能量双向流动,验证了SVPWM算法和控制系统设计方法的正确性.

蒸纱机作为纺织行业原料纱线的给湿定形装备,按照《固定式压力容器安全技术监察规程》对压力容器类别的划分,其一般应属于第Ⅰ类压力容器.对上述监察规程中关于压力容器的设计、制造、使用和监督管理等内容作了概述,结合蒸纱机装备发展现状总结了目前行业中存在的问题,并在此基础上对蒸纱机装备的进一步发展提出了建议.