Application of Machine Learning for Tool Condition Monitoring in Turning

The machining process is primarily used to remove material using cutting tools. Any variation in tool state affects the quality of a finished job and causes disturbances. So, a tool monitoring scheme (TMS) for categorization and supervision of failures has become the utmost priority. To respond, traditional TMS followed by the machine learning (ML) analysis is advocated in this paper. Classification in ML is supervised based learning method wherein the ML algorithm learn from the training data input fed to it and then employ this model to categorize the new datasets for precise prediction of a class and observation. In the current study, investigation on the single point cutting tool is carried out while turning a stainless steel (SS) workpeice on the manual lathe trainer. The vibrations developed during this activity are examined for failure-free and various failure states of a tool. The statistical modeling is then incorporated to trace vital signs from vibration signals. The multiple-binary-rule-based model for categorization is designed using the decision tree. Lastly, various tree-based algorithms are used for the categorization of tool conditions. The Random Forest offered the highest classification accuracy, i.e., 92.6%.

     

Sparse Multicategory Generalized Distance Weighted Discrimination in Ultra-High Dimensions

Distance weighted discrimination (DWD) is an appealing classification method that is capable of overcoming data piling problems in high-dimensional settings. Especially when various sparsity structures are assumed in these settings, variable selection in multicategory classification poses great challenges. In this paper, we propose a multicategory generalized DWD (MgDWD) method that maintains intrinsic variable group structures during selection using a sparse group lasso penalty. Theoretically, we derive minimizer uniqueness for the penalized MgDWD loss function and consistency properties for the proposed classifier. We further develop an efficient algorithm based on the proximal operator to solve the optimization problem. The performance of MgDWD is evaluated using finite sample simulations and miRNA data from an HIV study.     

A novel chaotic image encryption scheme using DNA sequence operations

In this paper, we propose a novel image encryption scheme based on DNA (Deoxyribonucleic acid) sequence operations and chaotic system. Firstly, we perform bitwise exclusive OR operation on the pixels of the plain image using the pseudorandom sequences produced by the spatiotemporal chaos system, i.e., CML (coupled map lattice). Secondly, a DNA matrix is obtained by encoding the confused image using a kind of DNA encoding rule. Then we generate the new initial conditions of the CML according to this DNA matrix and the previous initial conditions, which can make the encryption result closely depend on every pixel of the plain image. Thirdly, the rows and columns of the DNA matrix are permuted. Then, the permuted DNA matrix is confused once again. At last, after decoding the confused DNA matrix using a kind of DNA decoding rule, we obtain the ciphered image. Experimental results and theoretical analysis show that the scheme is able to resist various attacks, so it has extraordinarily high security.     

基于级联卷积神经网络的前列腺磁共振图像分类

针对深度学习训练成本高，以及基于磁共振图像的前列腺癌临床诊断需要大量医学常识且极为耗时的问题，本文提出了一种基于级联卷积神经网络（Convolutional Neural Network，CNN）和磁共振图像的前列腺癌（Prostate Cancer，PCa）自动分类诊断方法，该网络以Faster-RCNN作为前网络，对前列腺区域进行提取分割，用于排除前列腺附近组织器官的干扰；以基于ResNet改进的网络结构CNN40_bottleneck作为后网络，用于对前列腺区域病变进行分类.后网络由瓶颈结构串联组成，其中使用批量标准化（Batch Normalization，BN）、全局平均池化（Global Average Pooling，GAP）进行优化.实验结果证明，本文方法对前列腺癌诊断结果较好，而且缩减了训练时间和参数量，有效降低了训练成本.     

工业SO2及碳黑颗粒紫外成像遥感监测技术

为了准确有效监测工业烟囱排放,基于SO2及碳黑颗粒物的光学特性,设计并研制出一套双通道紫外成像遥感监测系统.该成像系统的两个光谱通道的中心波长分别定于310 nm和330 nm,利用两个通道的光学厚度之差反演SO2浓度图像,颗粒物浓度图像由330 nm通道获取,根据浓度图像结合光流法获取烟羽运动速度,进而计算得出SO2和碳黑颗粒物的排放速率.结果表明,该工业烟囱的SO2及碳黑颗粒物排放速率分别为72.48±3.16 kg/h和6.33±1.18 kg/h.实验采用紫外相机同时对工业烟囱排放的SO2及碳黑颗粒物进行监测,实验表明双通道紫外成像遥感监测兼具高时间分辨率与高空间分辨率,测量结果准确直观,在工业废气污染、船舶尾气污染以及火山喷发污染排放遥感监测中具有非常明显的技术优势及巨大的应用前景.     

基于U-Net的盐体识别方法

卷积神经网络在计算机视觉领域取得重大突破，利用其强大的图像处理能力，将地下沉积盐体的识别问题转化为图像语义分割问题，应用深度卷积神经网络实现盐体地震图像的像素级语义分割.本文在U-Net基础上，增加网络深度并同时引入批归一化和Dropout处理，使得神经网络模型具有更高的可信度和更强的泛化能力.通过实验发现，在卷积层之后引入批归一化处理，并在池化层和叠加层之后引入Dropout可以稳定提升模型对盐体图像的分割性能.     

基于PdSe2/GaAs异质结的高灵敏近红外光伏型探测器的制备和图像传感的应用

本文制备了一种基于PdSe₂/GaAs异质结的高灵敏近红外光电探测器，该探测器是通过将多层PdSe₂薄膜转移到平面GaAs上制成的. 所制备的PdSe₂/GaAs异质结器件在808 nm光照下表现出明显的光伏特性，这表明近红外光电探测器可以用作自驱动器件. 进一步的器件分析表明，这种杂化异质结在零偏电压和808 nm光照下具有1.16×10⁵的高开关比. 光电探测器的响应度和比探测度分别约为171.34 mA/W和2.36×10¹¹ Jones. 而且，该器件显示出优异的稳定性和可靠的重复性. 在空气中2个月后，近红外光电探测器的光电特性几乎没有下降，这归因于PdSe₂的良好稳定性. 最后，基于PdSe₂/GaAs的异质结器件还可以用作近红外光传感器.     

基于Retinex理论与概率非局部均值的红外图像增强方法

针对传统红外图像增强算法中细节模糊及过度增强的问题,提出了一种基于Retinex理论与概率非局部均值相结合的红外图像增强方法.首先通过单尺度Retinex方法调整图像中过暗与过亮部分的灰度级;然后利用概率非局部均值对图像进行分解处理得到基本层与细节层,对基本层采用直方图均衡化拉伸对比度,对细节层采用非线性函数进行增强;最后,将不同层次的结果融合得到对比度与细节增强的红外图像.用该方法对多组不同场景的红外图像进行仿真实验,并将其与多种增强方法进行主、客观对比分析,结果表明所提方法在红外图像的细节及对比度增强方面都获得了更好的效果.     

基于图像重组和比特置乱的多图像加密

针对现有多图像加密算法只能同时加密多张同类型同大小的图像,适用范围不广、实用性差等问题,提出一种基于图像重组和比特置乱的多图像加密算法.该算法通过将任意数量、不同大小和不同类型的图像重新组合成新多灰度图,一次完成同时加密,极大提高了加密效率和适用范围.首先,依次提取所有待加密图像像素值重新组合出N张m×n新灰度图,并将其转化成m×n×8N二进制矩阵.然后,采用3D比特置乱方式,对高位页进行行列比特置乱,低位页进行整页比特置乱.最后,进行异或扩散操作,得到密文图像.高低位分开置乱提高了算法的抗噪声能力,最终密文信息熵达到7.999以上,很好地掩盖了明文的统计特性.构造一种新型Logistic与广义三阶Fibonacci级联的混沌系统产生随机序列,增加了初值和控制参数范围,扩大了密钥空间,使其达到8×10^84以上,极大地提高了抗穷举攻击能力.既提高了序列随机性,又同时保留了低维混沌系统的快速性.结合明文哈希值(SHA-256)产生密钥,明文像素值发生微小改变后密文像素值变化率达到0.996以上,极大地提高了的明文敏感性和算法抗选择明文攻击的能力.实验分析表明,提出的多图像加密算法安全性高、实用性强.     

基于多通道盲识别的自适应光学图像事后处理

为实时恢复天文或空间目标的湍流退化成像,提出一种适应大气湍流动态变化的多通道自适应光学图像恢复方法.以自适应光学校正后不同时刻的目标成像作为多个通道,建立求解系统点扩散函数的线性方程,根据解出的点扩散函数利用超拉普拉斯算法,求解待观测目标的估计值.结果表明:不同时刻的点扩散函数之间存在互质关系,满足多通道盲识别的理论要求.利用建立的线性方程求解出的点扩散函数与原点扩散函数的均方误差在10^-30~10^-27量级,采用超拉普拉斯算法恢复出的目标成像与原始目标之间的均方误差在10^-5~10^-4量级.本文研究为湍流退化图像的实时恢复提供了理论基础.