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%.

     

石墨烯负载的氧配位钴单原子稳定金属锂负极

Lithium (Li)-based batteries are the dominant energy source for consumer electronics, grid storage, and electrified transportation. However, the development of batteries based on graphite anodes is hindered by their limited energy density. With its ultrahigh theoretical capacity (3860 mAh∙g⁻¹), low redox potential (−3.04 V), and satisfactorily low density (0.54 g∙cm⁻³), Li metal is the most promising anode for next-generation high-energy-density batteries. Unfortunately, the limited cycling life and safety issues raised by dendrite growth, unstable solid electrolyte interphase, and "dead Li" have inhibited their practical use. An effective strategy is to develop a suitable lithiophilic matrix for regulating initial Li nucleation behavior and controlling subsequent Li growth. Herein, single-atom cobalt coordinated to oxygen sites on graphene (Co-O-G SA) is demonstrated as a Li plating substrate to efficiently regulate Li metal nucleation and growth. Owing to its dense and more uniform lithiophilic sites than single-atom cobalt coordinated to nitrogen sites on graphene (Co-N-G SA), high electronic conductivity, and high specific surface area (519 m²∙g⁻¹), Co-O-G SA could significantly reduce the local current density and promote the reversibility of Li plating and stripping. As a result, the Co-O-G SA based Li anodes exhibited a high Coulombic efficiency of 99.9% at a current density of 1 mA∙cm⁻² with a capacity of 1 mAh∙cm⁻², and excellent rate capability (high current density of 8 mA∙cm⁻²). Even at a high plating capacity of 6 mAh∙cm⁻², the Co-O-G SA electrode could stably cycle for an ultralong lifespan of 1300 h. In the symmetric battery, the Co-O-G SA based Li anode (Co-O-G SA/Li) possessed a stable voltage profile of 18 mV for 780 h at 1 mA∙cm⁻², and even at a high current density of 3 mA∙cm⁻², its overpotential maintained a small hysteresis of approximately 24 mV for > 550 h. Density functional theory calculations showed that the surface of Co-O-G SA had a stronger interaction with Li atoms with a larger binding energy, −3.1 eV, than that of Co-N-G SA (−2.5 eV), leading to a uniform distribution of metallic Li on the Co-O-G SA surface. More importantly, when matched with a sulfur cathode, the resulting Co-O-G SA/lithium sulfur full batteries exhibited a high capacity of 1002 mAh∙g⁻¹, improved kinetics with a small polarization of 191 mV, and an ultralow capacity decay rate of 0.036% per cycle for 1000 cycles at 0.5C (1C = 1675 mA∙g⁻¹) with a steady Coulombic efficiency of nearly 100%. Therefore, this work provides novel insights into the coordination environment of single atoms for the chemistry of Li metal anodes for high-energy-density batteries.     

Electrochemical detection of nitrate,nitrite and ammonium for on-site water quality monitoring

This review examines the most recent electrochemical developments for nitrate, nitrite and ammonium detection for on-site water monitoring. There remains a high demand for effective field-based detection of the dissolved inorganic nitrogen (DIN) analytes to aid in mitigating nitrogen loading. Electrochemical approaches show increasing potential to fill this role as advancements in nanotechnology continually improve analytical performance and on-site applicability. However, translating these improvements into the field still faces the resonating challenges of reaching analytical proficiency (selectivity, sensitivity, robustness, stability), practical end-user functionality, minimal matrix interferences and cost effectiveness. Herein, we elaborate on these challenges via a critical evaluation of current studies and examine how realistic the prospects of on-site nitrate, nitrite and ammonium are. We also present recommendations in addressing these gaps to conclude the review.     

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.     

Direct Estimation of the Surface Location of Immobilized Functional Groups for Concerted Catalysis Using a Probe Molecule

The location of active sites during concerted catalysis by a metal complex and tertiary amine on a SiO₂ surface is discussed based on the interaction between the functionalized SiO₂ surface and a probe molecule, p‐formyl phenylboronic acid. The interactions of the probe molecule with the surface functionalities, diamine ligand, and tertiary amine, were analyzed by FT‐IR and solid‐state ¹³C and ¹¹B MAS NMR. For the catalyst exhibiting high 1,4‐addition activity, the diamine ligand and tertiary amine base exist in closer proximity than in the catalyst with low activity.     

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.     

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.     

Adsorption Site Regulation to Guide Atomic Design of Ni–Ga Catalysts for Acetylene Semi‐Hydrogenation

Atomic regulation of metal catalysts has emerged as an intriguing yet challenging strategy to boost product selectivity. Here, we report a density functional theory‐guided atomic design strategy for the fabrication of a NiGa intermetallic catalyst with completely isolated Ni sites to optimize acetylene semi‐hydrogenation processes. Such Ni sites show not only preferential acetylene π‐adsorption, but also enhanced ethylene desorption. The characteristics of the Ni sites are confirmed by multiple characterization techniques, including aberration‐corrected high‐resolution scanning transmission electron microscopy and X‐ray absorption spectrometry measurements. The superior performance is also confirmed experimentally against a Ni₅Ga₃ intermetallic catalyst with partially isolated Ni sites and against a Ni catalyst with multi‐atomic ensemble Ni sites. Accordingly, the NiGa intermetallic catalyst with the completely isolated Ni sites shows significantly enhanced selectivity to ethylene and suppressed coke formation.     

Visible-Light-Induced Heptacene Generation under Ambient Conditions: Utilization of Single-crystal Interior as an Isolated Reaction Site

The photo-induced generation of unstable molecules generally requires stringent conditions to prevent oxidation and the concomitant decomposition of the products. The visible-light-induced conversion of two heptacene precursors to heptacene was studied. Single crystals of bis- and mono-α-diketone-type heptacene precursors ( 7-DK2 and 7-DK1 , respectively), were prepared to investigate the effect of precursor structure on reactivity. The photoirradiation of a 7-DK2 single crystal cleaved only one α-diketone group, forming an intermediate bearing a pentacene subunit, while that of a 7-DK1 single crystal gave rise to characteristic absorption peaks of heptacene and their increase in intensity with photoirradiation time, indicating the generation of heptacene without decomposition. Heptacene production was not observed when the precursors were photoirradiated in solution, implying that the single crystal interior provided isolation from the external environment, thus preventing heptacene oxidation.     

Study of Endogen Substrates,Drug Substrates and Inhibitors Binding Conformations on MRP4 and Its Variants by Molecular Docking and Molecular Dynamics

Multidrug resistance protein-4 (MRP4) belongs to the ABC transporter superfamily and promotes the transport of xenobiotics including drugs. A non-synonymous single nucleotide polymorphisms (nsSNPs) in the ABCC4 gene can promote changes in the structure and function of MRP4. In this work, the interaction of certain endogen substrates, drug substrates, and inhibitors with wild type-MRP4 (WT-MRP4) and its variants G187W and Y556C were studied to determine differences in the intermolecular interactions and affinity related to SNPs using protein threading modeling, molecular docking, all-atom, coarse grained, and umbrella sampling molecular dynamics simulations (AA-MDS and CG-MDS, respectively). The results showed that the three MRP4 structures had significantly different conformations at given sites, leading to differences in the docking scores (DS) and binding sites of three different groups of molecules. Folic acid (FA) had the highest variation in DS on G187W concerning WT-MRP4. WT-MRP4, G187W, Y556C, and FA had different conformations through 25 ns AA-MD. Umbrella sampling simulations indicated that the Y556C-FA complex was the most stable one with or without ATP. In Y556C, the cyclic adenosine monophosphate (cAMP) and ceefourin-1 binding sites are located out of the entrance of the inner cavity, which suggests that both cAMP and ceefourin-1 may not be transported. The binding site for cAMP and ceefourin-1 is quite similar and the affinity (binding energy) of ceefourin-1 to WT-MRP4, G187W, and Y556C is greater than the affinity of cAMP, which may suggest that ceefourin-1 works as a competitive inhibitor. In conclusion, the nsSNPs G187W and Y556C lead to changes in protein conformation, which modifies the ligand binding site, DS, and binding energy.