基于改进飞蛾扑火优化算法的MIMO雷达相位编码信号集设计

提出一种MIMO雷达相位编码信号集设计方法，该方法对飞蛾扑火优化算法进行改进，利用改进的飞蛾扑火算法优化相位编码信号集，提高其正交性.在改进方法中，增加对火焰的更新过程，使火焰不仅能够保存最优飞蛾位置还具有搜索最优解的功能.优化过程以自相关函数旁瓣峰值和、互相关函数峰值和，以及自相关函数旁瓣能量、互相关函数能量作为算法适应度函数.仿真实验结果表明，改进方法明显提高了飞蛾扑火优化算法的收敛速度和收敛精度，且优化得到的信号集具有较低的自相关旁瓣值和互相关值.     

CLOI-NET: Class segmentation of industrial facilities’ point cloud datasets

Shape segmentation from point cloud data is a core step of the digital twinning process for industrial facilities. However, it is also a very labor intensive step, which counteracts the perceived value of the resulting model. The state-of-the-art method for automating cylinder detection can detect cylinders with 62% precision and 70% recall, while other shapes must then be segmented manually and shape segmentation is not achieved. This performance is promising, but it is far from drastically eliminating the manual labor cost. We argue that the use of class segmentation deep learning algorithms has the theoretical potential to perform better in terms of per point accuracy and less manual segmentation time needed. However, such algorithms could not be used so far due to the lack of a pre-trained dataset of laser scanned industrial shapes as well as the lack of appropriate geometric features in order to learn these shapes. In this paper, we tackle both problems in three steps. First, we parse the industrial point cloud through a novel class segmentation solution (CLOI-NET) that consists of an optimized PointNET++ based deep learning network and post-processing algorithms that enforce stronger contextual relationships per point. We then allow the user to choose the optimal manual annotation of a test facility by means of active learning to further improve the results. We achieve the first step by clustering points in meaningful spatial 3D windows based on their location. Then, we apply a class segmentation deep network, and output a probability distribution of all label categories per point and improve the predicted labels by enforcing post-processing rules. We finally optimize the results by finding the optimal amount of data to be used for training experiments. We validate our method on the largest richly annotated dataset of the most important to model industrial shapes (CLOI) and yield 82% average accuracy per point, 95.6% average AUC among all classes and estimated 70% labor hour savings in class segmentation. This proves that it is the first to automatically segment industrial point cloud shapes with no prior knowledge at commercially viable performance and is the foundation for efficient industrial shape modeling in cluttered point clouds.     

基于机器视觉的玻璃缺陷检测

随着科学技术的进步,高端显示屏产品对平板玻璃的质量要求越来越高,玻璃的表面缺陷检测技术也因此备受关注。传统的人眼检测方法工作量大且准确率低,已经无法满足生产实际要求。研究了一种基于机器视觉的玻璃质量检测系统,采用先进的CCD成像技术和背光式照明获取图像,用MATLAB图像处理工具箱对采集到的图像进行灰度值化、滤波降噪和阈值分割处理,实现对缺陷区域的特征提取和识别。最后用BP神经网络对玻璃表面的三种缺陷进行分类,该神经网络识别的平均误差率为9.84%,表明此检测方法具有一定的应用价值。     

Suppression of diamond tool wear in machining of tungsten carbide by combining ultrasonic vibration and electrochemical processing

As an important ceramic material, tungsten carbide (WC) is utilized as the typical mold in precision glass molding, which has replaced conventional grinding and polishing to provide a highly replicative process for mass manufacturing of optical glass components. Ultra-precision grinding, which is time consuming and has low reproducibility, is the only method to machine such WC molds to high profile accuracy. Although diamond turning is the most widely used machining method for fabrication of optical molds made of metals, diamond turning of WC is still considered challenging due to fast abrasive wear of the diamond tool caused by high brittleness and hardness of WC. Ultrasonic vibration cutting has been proven to be helpful in realizing ductile-mode machining of brittle materials, but its tool life is still not long enough to be utilized in practical diamond turning of optical WC molds. In the current study, a hybrid method is proposed to combine electrochemical processing of WC workpiece surface into the diamond turning process. Cutting tests on WC using poly-crystalline diamond tools were conducted to evaluate its effect on improvement of tool wear and surface quality. Validation cutting tests using single crystal diamond tools has proven that the proposed hybrid method is able to significantly reduce the diamond tool wear and improve the surface quality of machined ultra-fine grain WC workpiece compared to ultrasonic vibration cutting without electrochemical processing.     

基于机器视觉的航空铆钉尺寸检测技术

航空铆钉的尺寸偏差会增加航空事故发生的可能性。为了实现航空铆钉尺寸检测的高精度与智能化,提出一种基于机器视觉的航空铆钉尺寸检测方法。通过边缘检测算法对铆钉进行自动识别与检测,可减少航空铆钉尺寸的误差。基于航空铆钉产品规范,分析得出各项尺寸参数要求与事件流程,使用OpenCV作为开发平台,采用阈值分割算法与分水岭算法进行图像分割;同时,通过平滑处理、形态学、轮廓提取算法完成图像处理。实测结果表明,在±0.005mm精度下,铆钉尺寸检测结果与实际值的吻合度达到90%以上。     

模型驱动的大数据流水线框架PiFlow

复杂流程的大数据处理多依托于流水线系统，但大数据处理的流水线系统在易用性、功能复用性、扩展性以及处理性能等方面存在不足。针对上述问题，为提高大数据处理环境的构建与开发效率,优化处理流程，提出了一种模型驱动的大数据流水线框架PiFlow。首先，将大数据处理过程抽象为有向无环图；然后，开发一系列组件用于构建数据处理流水线，并设计了流水线任务执行机制。同时，为规范和简化流水线框架的描述，设计了基于模型驱动的大数据流水线描述语言——PiFlowDL，该语言以模块化、层次化的方式对大数据处理任务进行描述。PiFlow以所见即所得(WYSIWYG)的方式配置流水线，集成了状态监控、模板配置、组件集成等功能，与Apache NiFi相比有2~7倍的性能提升。     

多共振分量融合CNN的行星齿轮箱故障诊断

针对行星齿轮箱中各部件所激起的振动成分混叠、早期故障特征经常被较强的各级齿轮谐波成分以及环境噪声所湮没的问题，提出一种多共振分量融合卷积神经网络（multi-resonance component fusion based convolutional neural network，简称MRCF-CNN）的行星齿轮箱故障诊断方法。首先，对振动信号进行共振稀疏分解，得到包含齿轮谐波成分的高共振分量和可能包含轴承故障冲击成分的低共振分量；其次，构建多共振分量融合卷积神经网络，将得到的高、低共振分量和原始振动信号进行自适应的特征级融合，通过有监督的方式训练模型并进行行星齿轮箱故障诊断。对行星齿轮箱实验数据的分析结果表明，该方法能够有效分类行星齿轮箱中滚动轴承和齿轮的故障，成功对行星齿轮箱故障进行诊断，同时能够进一步增强卷积神经网络对振动信号所蕴含的故障信息的辨识能力。     

AG2.0型超声波蒸发传感器遇低温结冰时记录的处理

文章分析了3a马尔康国家基准气候站AG2.0型超声波蒸发传感器观测数据,结果表明:蒸发传感器遇低温结冰时段自动观测数据偏大。对1d中部分时间段内蒸发水结冰、融化以及冬季全天结冰期很短的观测数据进行了分析,分析认为数据偏大主要是因为蒸发桶和测量筒的材料物理性质以及测量的水体面积不同。最后提出了数据记录处理建议。     

市政污泥与水泥生料混合热重及动力学分析

为研究水泥窑协同处置市政污泥的燃烧动力学特性,采用热重分析方法分别对市政污泥、煤和水泥生料及三者混合样品进行热动力学分析,求解了反应活化能和机理函数。结果表明:市政污泥燃烧有4个阶段,有机物分解和部分挥发分析出阶段活化能为69.87 kJ/mol、机理函数为(-ln(1-α))~4,剩余挥发分析出和固定碳燃尽阶段活化能为78.94 kJ/mol、机理函数为(-ln(1-α))~3;煤和水泥生料热重分析过程分为煤燃烧和生料分解2个阶段,反应活化能分别为43.58、118.21 kJ/mol,机理函数分别为(1-α)~(-1)-1、((1+α)~(1/3)-1)~2;市政污泥替代20%煤后,第1阶段活化能基本不变,机理函数由(1-α)~(-1)-1变为(1-2α/3)-(1-α)~(2/3),反应机理由"化学反应"变为"圆柱对称型三维扩散",第2阶段活化能降低,机理函数表达式由((1+α)~(1/3)-1)~2变为((1+α)~(-1/3)-1)~2,反应机理不变。     

Self-learning residual model for fast intra CU size decision in 3D-HEVC

As an extension of the High Efficiency Video Coding (HEVC) standard, 3D-HEVC requires to encode multiple texture views and depth maps, which inherits the same quad-tree coding structure as HEVC. Due to the distinct properties of texture views and depth maps, existing fast intra prediction approaches were presented for the coding of texture views and depth maps, respectively. To further reduce the coding complexity of 3D-HEVC, a self-learning residual model-based fast coding unit (CU) size decision approach is proposed for the intra coding of both texture views and depth maps. Residual signal, which is defined as the difference between the original luminance pixel and the optimal prediction luminance pixel, is firstly extracted from each CU. Since residue signal is strongly correlated with the optimal CU partition, it is used as the feature of each CU. Then, a self-learning residual model is established by intra feature learning, which iteratively learns the features of the previously encoded coding tree unit (CTU) generated by itself. Finally, a binary classifier is developed with the self-learning residual model to early terminate CU size decision of both texture views and depth maps. Experimental results show the proposed fast intra CU size decision approach achieves 33.3% and 49.3% encoding time reduction on average for texture views and depth maps with negligible loss of overall video quality, respectively.