Remaining Useful Life Prediction of Rail Based on Improved Pulse Separable Convolution Enhanced Transformer Encoder

In order to prevent possible casualties and economic loss, it is critical to accurate prediction of the Remaining Useful Life (RUL) in rail prognostics health management. However, the traditional neural networks is difficult to capture the long-term dependency relationship of the time series in the modeling of the long time series of rail damage, due to the coupling relationship of multi-channel data from multiple sensors. Here, in this paper, a novel RUL prediction model with an enhanced pulse separable convolution is used to solve this issue. Firstly, a coding module based on the improved pulse separable convolutional network is established to effectively model the relationship between the data. To enhance the network, an alternate gradient back propagation method is implemented. And an efficient channel attention (ECA) mechanism is developed for better emphasizing the useful pulse characteristics. Secondly, an optimized Transformer encoder was designed to serve as the backbone of the model. It has the ability to efficiently understand relationship between the data itself and each other at each time step of long time series with a full life cycle. More importantly, the Transformer encoder is improved by integrating pulse maximum pooling to retain more pulse timing characteristics. Finally, based on the characteristics of the front layer, the final predicted RUL value was provided and served as the end-to-end solution. The empirical findings validate the efficacy of the suggested approach in forecasting the rail RUL, surpassing various existing data-driven prognostication techniques. Meanwhile, the proposed method also shows good generalization performance on PHM2012 bearing data set.

Deep eutectic solvents for separation and purification applications in critical metal metallurgy:Recent advances and perspectives

Solvent extraction,a separation and purification technology,is crucial in critical metal metallurgy.Organic solvents commonly used in solvent extraction exhibit disadvantages,such as high volatility,high toxicity,and flammability,causing a spectrum of hazards to human health and environmental safety.Neoteric solvents have been recognized as potential alternatives to these harmful organic solvents.In the past two decades,several neoteric solvents have been proposed,including ionic liquids(ILs)and deep eutectic solvents(DESs).DESs have gradually become the focus of green solvents owing to several advantages,namely,low toxicity,degradability,and low cost.In this critical review,their classification,formation mechanisms,preparation methods,characterization technologies,and special physicochemical properties based on the most recent advancements in research have been systematically described.Subsequently,the major separation and purification applications of DESs in critical metal metallurgy were comprehensively summarized.Finally,future opportunities and challenges of DESs were explored in the current research area.In conclusion,this review provides valuable insights for improving our overall understanding of DESs,and it holds important potential for expanding separation and purification applications in critical metal metallurgy.

基于常循环码的纠缠辅助量子Maximum-Distance-Separable码的构造

纠缠辅助量子纠错码可以看作是经典量子纠错码的引申,其与经典量子纠错码的差别在于,如果发送者和接收者双方提前共享纠缠态,在不满足对偶包含的的情况下也可以由任意经典线性码构造出来.本文通过研究分圆陪集的结构性质,利用常循环码构造出几类新的具有较小预先共享纠缠态的纠缠辅助量子Maximum-Distance-Separable(MDS)码.

Preparation of magnetically separable mesoporous activated carbons from brown coal with Fe3O4

Magnetically separable mesoporous activated carbon was prepared from brown coal in the presence of Fe3O4 as a bi-functional additive.Magnetic activated carbon(MAC)was characterized by lowtemperature nitrogen adsorption,scanning electron microscopy(SEM),transmission electron microscopy(TEM),X-ray diffraction(XRD),X-ray photoelectron spectroscopy(XPS)and vibrating sample magnetometry(VSM).The evolution behaviors and transition mechanism of Fe3O4 during the preparation of MAC were investigated.The results show that prepared MAC with 6 wt%Fe3O4 addition having a specific surface area and mesopore ratio of 370 m^2·g^-1 and 55.7%,which meet the requirements of adsorption application and magnetic recovery.Highly dispersed iron-containing aggregates with the size of 0.1 lm in the MAC were observed.During the preparation of MAC,Fe3O4 could enhance the escape of volatiles during the carbonization.Fe3O4 could also accelerate burning off the carbon wall during activation,which leads to enlarging micropore size,then resulting in the generation of mesopore and macropore.As a result,a part of Fe3O4 converted into FeO,FeOOH,a-Fe,c-Fe,Fe2SiO4 and compound of Aluminum-iron-silicon.The prepared activated carbon,which was magnetized by both of residual Fe3O4,reduced a-Fe and c-Fe,can be easily separated from the original solution by external magnetic field.

Accuracy analysis of the optimal separable approximation method of one-way wave migration

An approximation for the one-way wave operator takes the form of separated space and wave-number variables and makes it possible to use the FFT, which results in a great improvement in the computational efficiency. From the function approximation perspective, the OSA method shares the same separable approximation format to the one-way wave operator as other separable approximation methods but it is the only global function approximation among these methods. This leads to a difference in the phase error curve, impulse response, and migration result from other separable approximation methods. The difference is that the OSA method has higher accuracy, and the sensitivity to the velocity variation declines with increasing order.

基于FPGA的Separable Gabor滤波器设计

指纹图像滤波是指纹图像增强耗时最大的过程,为提高指纹滤波的实时性,提出了一种Separable Gabor滤波器,将二维的Gabor滤波器分别拆分为一维带通滤波器和一维低通滤波器.两种滤波器在互相垂直的方向上分别对指纹图像进行卷积.该算法用硬件描述语言在可编程逻辑门阵列(FPGA)上实现.为了节省存储空间,引入了坐标变换和方向变换.实验结果表明,对于同一幅指纹图像,Separable Gabor滤波器和Gabor滤波器的处理结果相似,且前者的处理速度是后者的1.9到4倍,存储空间的消耗仅为Gabor滤波器的16.4%,提高了滤波速度的同时极大的降低了硬件成本.

The Centralizer on H-Separable Smash Products

Let H be a finite dimensional Hopf algebra over a field and A an H-module algebra. The H induces an action on the CA#H(A) by adjoint and CA#H(A)H= Z(A # H) = C,where CA#H(A) denotes the centralizer which algebra A in A # H and Z(A # H) the center of A # H.The aim of this paper is to discuss ,the Galois conditions on the centralizer CA# H(A).We prove that CA# H(A)/ZA # H is H* -Galois if and only if CA# H(A)# H/CA# H(A) is H-separable). Furthermore , if H is a finite dimensional semisimple Hopf algebra and CA# H(A)# H is an Azumaya C-algebra or A # H/A is H-separable, CA# H(A) satisfies the double centralizer property in CA# H(A)# H, CA# H(A)/C is separable and there exists a cocommutative left integral t ∈∫1H,then CA# H(A)/C is H*-Galois.

Variable Separation and Derivative-Dependent Functional Separable Solutions to Generalized Nonlinear Wave Equations

Using the generalized conditional symmetry approach, we obtain a number of new generalized (1+1)-dimensional nonlinear wave equations that admit derivative-dependent functional separable solutions.

Novel Visible Light Driven Magnetically Separable Graphene/BiOBr Composite Photocatalysts with Enhanced Photocatalytic Activity

Novel visible light magnetically separable graphene-based BiOBr composite photocatalysts were prepared for the first time. The structures, morphologies and optical properties were characterized by field emission scanning electron microscopy, transmission electron microscopy, X-ray diffraction and ultravioletvisible spectroscopy, respectively. The photocatalytic activity of the resulting samples was evaluated by degradation of tetracycline under visible light irradiation. An appropriate amount of introduced graphene can significantly enhance the photocatalytic activities. The enhanced activities were mainly attributed to the enhanced light absorption and the interfacial transfer of electrons. The corresponding photocatalytic mechanism was proposed based on the results.

Preparation and Photocatalytic Properties of Magnetically Separable TiO_2 Supported on Nickel Ferrite

A magnetically separable photocatalyst TiO2/SiO2/NiFe2O4 （TSN） with a typical ferromagnetic hysteresis was prepared by a liquid catalytic phase transfer method. When the intensity of applied magnetic field weakened to zero, the remnant magnetism of the prepared photocatalyst faded to zero. The photocatalytst can be separated from water when an external magnetic field is added and redispersed into aqueous solution after the external magnetic field is eliminated, that makes the photocatalysts promising for wastewater treatment. Transmission electron microscope （TEM） and X-ray diffractometer （XRD） were used to characterize the structure of the photocatalyst indicating that the magnetic SiOffNiFe204 （SN） particle was compactly enveloped by P-25 titania and Tit2 shell was formed. The magnetic composite showed high photocatalytic activity for the degradation of methyl orange in water. A thin SiO2 layer between NiFe2O4 and TiO2 shell prevented effectively the leakage of charges from TiO2 particles to NiFe2O4, which gave rise to the increase in photocatalytic activity. Moreover, the experiment on recycled use of TSN demonstrated a good repeatability of the photocatalytic activity.

Functional Separable Solutions to Nonlinear Diffusion Equations by Group Foliation Method

We consider the functional separation of variables to the nonlinear diffusion equation with source and convection term： ut = （A（x）D（u）ux）x ＋ B（x）Q（u）, Ax ≠ 0. The functional separation of variables to this equation is studied by using the group foliation method. A classification is carried out for the equations which admit the function separable solutions. As a consequence, some solutions to the resulting equations are obtained.

INVARIANT SUBSPACES AND GENERALIZED FUNCTIONAL SEPARABLE SOLUTIONS TO THE TWO-COMPONENT b-FAMILY SYSTEM

Invariant subspace method is exploited to obtain exact solutions of the two- component b-family system. It is shown that the two-component b-family system admits the generalized functional separable solutions. Furthermore, blow up and behavior of those exact solutions are also investigated.

Extension of Variable Separable Solutions for Nonlinear Evolution Equations

We give the generalized definitions of variable separable solutions to nonlinear evolution equations, and characterize the relation between the functional separable solution and the derivative-dependent functional separable solution. The new definitions can unify various kinds of variable separable solutions appearing in references. As application, we classify the generalized nonlinear diffusion equations that admit special functional separable solutions and obtain some exact solutions to the resulting equations.

γ-Fe_2O_3:A magnetic separable catalyst for synthesis of 5-substituted 1H-tetrazoles from nitriles and sodium azide

An efficient route for the synthesis of 5-substituted 1H-tetrazole via[2＋3]cycloaddition of nitriles and sodium azide is reported usingγ-Fe2O3 nanoparticles as a magnetic separable catalyst.Under optimized conditions,the moderate to good yields（71-95%） can be obtained.The catalyst can be easily separated by a magnet and reused for several circles.

SepFE:Separable Fusion Enhanced Network for Retinal Vessel Segmentation

The accurate and automatic segmentation of retinal vessels fromfundus images is critical for the early diagnosis and prevention ofmany eye diseases,such as diabetic retinopathy(DR).Existing retinal vessel segmentation approaches based on convolutional neural networks(CNNs)have achieved remarkable effectiveness.Here,we extend a retinal vessel segmentation model with low complexity and high performance based on U-Net,which is one of the most popular architectures.In view of the excellent work of depth-wise separable convolution,we introduce it to replace the standard convolutional layer.The complexity of the proposed model is reduced by decreasing the number of parameters and calculations required for themodel.To ensure performance while lowering redundant parameters,we integrate the pre-trained MobileNet V2 into the encoder.Then,a feature fusion residual module(FFRM)is designed to facilitate complementary strengths by enhancing the effective fusion between adjacent levels,which alleviates extraneous clutter introduced by direct fusion.Finally,we provide detailed comparisons between the proposed SepFE and U-Net in three retinal image mainstream datasets(DRIVE,STARE,and CHASEDB1).The results show that the number of SepFE parameters is only 3%of U-Net,the Flops are only 8%of U-Net,and better segmentation performance is obtained.The superiority of SepFE is further demonstrated through comparisons with other advanced methods.

Classification and Functional Separable Solutions to Extended Nonlinear Wave Equations

The generalized conditional symmetry approach is applied to study the variable separation of the extended wave equations. Complete classification of those equations admitting functional separable solutions is obtained and exact separable solutions to some of the resulting equations are constructed.

Variable Separation and Exact Separable Solutions for Equations of Type uxt=A（u,ux）uxx＋B（u,ux）

The generalized conditional symmetry is developed to study the variable separation for equations of type uxt = A（u,ux）uxx ＋ B（u, ux）. Complete classification of those equations which admit derivative-dependent functional separable solutions is obtained and some of their exact separable solutions are constructed.

Functional Separable Solutions of Nonlinear Heat Equations in Non-Newtonian Fluids

We study the functional separation of variables to the nonlinear heat equation： ut = （A（x）D（u）ux^n）x＋ B（x）Q（u）, Ax≠0. Such equation arises from non-Newtonian fluids. Its functional separation of variables is studied by using the group foliation method. A classification of the equation which admits the functional separable solutions is performed. As a consequence, some solutions to the resulting equations are obtained.

Entanglement distribution using three-mode separable state with imperfect equipments

We show a scheme to distribute the entanglement by using three-mode separable Gaussian state prepared with imperfect equipments. The scheme achieves the aim that the entanglement is distributed between two distant parties with only Gaussian operations and linear optics elements. Moreover, we analyse the logarithmic negativity of the entanglement shared between the two parties when the systems are imperfect and arrive at the conclusion that the logarithmic negativity is asymptotically stable with fluctuations within a certain space range.

Role of tannin pretreatment in flotation separation of magnesite and dolomite

Flotation separation of magnesite and its calcium-containing carbonate minerals is a difficult problem.Recently,new regulat-ors have been proposed for magnesite flotation decalcification,although traditional regulators such as tannin,water glass,sodium carbon-ate,and sodium hexametaphosphate are more widely used in industry.However,they are rarely used as the main regulators in research because they perform poorly in magnesite and dolomite single-mineral flotation tests.Inspired by the limonite presedimentation method and the addition of a regulator to magnesite slurry mixing,we used a tannin pretreatment method for separating magnesite and dolomite.Microflotation experiments confirmed that the tannin pretreatment method selectively and largely reduces the flotation recovery rate of dolomite without affecting the flotation recovery rate of magnesite.Moreover,the contact angles of the tannin-pretreated magnesite and dolomite increased and decreased,respectively,in the presence of NaOl.Zeta potential and Fourier transform infrared analyses showed that the tannin pretreatment method efficiently hinders NaOl adsorption on the dolomite surface but does not affect NaOl adsorption on the magnesite surface.X-ray photoelectron spectroscopy and density functional theory calculations confirmed that tannin interacts more strongly with dolomite than with magnesite.