Analysis of Internet Financial Risks Based on Deep Learning and BP Neural Network

Computational Economics - The study aims to analyze and forecast Internet financial risks based on the model based on deep learning and the Back Propagation Neural Network (BPNN). First, the theory...     

Optimizing Financial Engineering Time Indicator Using Bionics Computation Algorithm and Neural Network Deep Learning

Computational Economics - The present work aims to optimize the time index of financial engineering to improve the efficiency of financial decision-making. A Back Propagation Neural Network (BPNN)...     

Finite element implementation of a thermo-damage-viscoelastic constitutive model for hydroxyl-terminated polybutadiene composite propellant

A thermo-damage-viscoelastic model for hydroxyl-terminated polybutadiene (HTPB) composite propellant with consideration for the effect of temperature was implemented in ABAQUS. The damage evolution law of the model has the same form as the crack growth equation for viscoelastic materials, and only a single damage variable \(S\) is considered. The HTPB propellant was considered as an isotropic material, and the deviatoric and volumetric strain-stress relations are decoupled and described by the bulk and shear relaxation moduli, respectively. The stress update equations were expressed by the principal stresses \(\sigma_{ii}^{R}\) and the rotation tensor \(M\), the Jacobian matrix in the global coordinate system \(J_{ijkl}\) was obtained according to the fourth-order tensor transformation rules. Two models having complex stress states were used to verify the accuracy of the constitutive model. The test results showed good agreement with the strain responses of characteristic points measured by a contactless optical deformation test system, which illustrates that the thermo-damage-viscoelastic model perform well at describing the mechanical properties of an HTPB propellant.     

Effect of Sintering Temperature on Magnetic and Electrical Properties of GdBaCo<Subscript>2</Subscript><Emphasis Type="Italic">O</Emphasis><Subscript>5 + <Emphasis Type="Italic">δ</Emphasis></Subscript>

In this study, we report the results of an investigation into the sintering temperature dependence of magnetic and transport properties for GdBaCo₂ O _{5 + δ} synthesized through a sol-gel method. The lowering of sintering temperature leads to the increase of oxygen content and the reduction of grain size. The increase of oxygen content results in the enhancement of magnetic interactions and the weakening of Coulomb repulsion effect, while the reduction of grain size improves the magnetoresistance effect. Metal-insulator transition accompanied with spin-state transition is observed in all samples.     

Comparison of gas sensing properties based on hollow and porous α-Fe<Subscript>2</Subscript>O<Subscript>3</Subscript> nanotubes

Hollow and porous α-Fe₂O₃ nanotubes were successfully synthesized by single nozzle electrospinning method followed by annealing treatment. The crystal structures and morphologies of the as-prepared materials were characterized by X-ray diffraction and scanning electron microscopy, respectively. The as-prepared materials were applied to construct gas sensor devices which gas sensing properties were further investigated. The obtained results revealed that porous α-Fe₂O₃ nanotube gas sensors exhibit a markedly enhanced gas sensing performance compared with hollow α-Fe₂O₃ nanotube gas sensors, which was about three times higher to 100 ppm acetone at 240 °C. Interestingly, hollow and porous α-Fe₂O₃ nanotube gas sensors both showed fast response–recovery time and good selectivity, but the porous ones possessed the shorter recovery time. The improved properties could be attributed to the unique morphology of porous nanotubes. Thus, further improvement of performance in metal-oxide-semiconductors materials could be realized by preparation the unique porous structures of nanotubes. Moreover, it is expected that porous metal-oxide-semiconductors nanotubes could be further design as promising candidates for gas sensing materials.     

热处理非晶态Ni-P合金镀层的晶化过程

运用电沉积的方法在45钢基体上制备Ni-P合金镀层,使用差示扫描量热法(DSC)和热重法(TG)分析非晶态NiP合金镀层在20℃/min加热速率下的热效应和质量变化。在300℃和400℃分别对镀层进行0,15,30,45,60,75min的热处理,采用扫描电镜(SEM)、能谱仪(EDS)、X射线衍射仪(XRD)、显微硬度计对镀层进行表征。结果表明:Ni-P合金镀层在加热过程中的放热峰出现在284.8℃处,镀层的质量和元素组成稳定;晶化过程经历了非晶态、亚稳态NiP和Ni5P2、稳定态Ni3P的转变;经过热处理后,镀层的显微硬度显著提高,最大值达1036.56HV,约为镀态的2倍;热处理态镀层的耐NaCl溶液腐蚀性能比镀态有所下降,但两者都比45钢基体好。     

小河嘴水电站增效扩容改造电气设备分析

小河嘴水电站已运行四十多年,设备老化,故障多,自动化水平低,对该站进行增效扩容改造是必要的,而且也是可行的。     

Graphene oxide-decorated Fe<Subscript>2</Subscript>(MoO<Subscript>4</Subscript>)<Subscript>3</Subscript> microflowers as a promising anode for lithium and sodium storage

Mixed transition metal oxides (MTMOs) have received intensive attention as promising anode materials for lithium-ion batteries (LIBs) and sodium-ion batteries (SIBs). In this work, we demonstrate a facile one-step water-bath method for the preparation of graphene oxide (GO) decorated Fe₂(MoO₄)₃ (FMO) microflower composite (FMO/GO), in which the FMO is constructed by numerous nanosheets. The resulting FMO/GO exhibits excellent electrochemical performances in both LIBs and SIBs. As the anode material for LIBs, the FMO/GO delivers a high capacity of 1,220 mAh·g^–1 at 200 mA·g^–1 after 50 cycles and a capacity of 685 mAh·g^–1 at a high current density of 10 A·g^–1. As the anode material for SIBs, the FMO/GO shows an initial discharge capacity of 571 mAh·g^–1 at 100 mA·g^–1, maintaining a discharge capacity of 307 mAh·g^–1 after 100 cycles. The promising performance is attributed to the good electrical transport from the intimate contact between FMO and graphene oxide. This work indicates that the FMO/GO composite is a promising anode for high-performance lithium and sodium storage.

Open image in new window

     

MHSACAE-CNN在噪声下的电机轴承故障诊断

电机的运行情况复杂,实际运行工况下会有大量的噪声,导致其轴承故障诊断精度下降。为了改善这一问题,提出了一种基于多头自注意力机制的一维全卷积自编码网络（One-dimensional Fully Convolutional Autoencoding Network Basedon Multi-head Self-attention,MHSACAE）与卷积神经网络（Convolutional Neural Network,CNN）结合的轴承故障诊断方法。该方法先采用MHSACAE网络进行降噪,再通过CNN进行故障诊断。其中MHSACAE去噪网络采用无监督训练的方式,充分考虑了实际工况和序列数据内在联系,在实现对噪声的滤除效果的同时,最大限度地保留下了原始的故障信息,使得CNN可以实现在噪声情况下对电机轴承故障的高精度诊断。通过与其他轴承故障诊断方法在噪声情况下进行对比,证明提出的方法具有更好的效果。