5A06-O aluminium–magnesium alloy sheet warm hydroforming and optimization of process parameters

The uniaxial tensile test of the 5A06-O aluminium–magnesium (Al–Mg) alloy sheet was performed in the temperature range of 20–300 °C to obtain the true stress–true strain curves at different temperatures and strain rates. The constitutive model of 5A06-O Al–Mg alloy sheet with the temperature range from 150 to 300°C was established. Based on the test results, a unique finite element simulation platform for warm hydroforming of 5A06-O Al–Mg alloy was set up using the general finite element software MSC.Marc to simulate warm hydroforming of classic specimen, and a coupled thermo-mechanical finite element model for warm hydroforming of cylindrical cup was built up. Combined with the experiment, the influence of the temperature field distribution and loading conditions on the sheet formability was studied. The results show that the non-isothermal temperature distribution conditions can significantly improve the forming performance of the material. As the temperature increases, the impact of the punching speed on the forming becomes particularly obvious; the optimal values of the fluid pressure and blank holder force required for forming are reduced.     

天然气水合物储层泥质细粉砂挡砂介质堵塞规律与微观挡砂机制

中国南海海域部分天然气水合物储层中地层砂为高泥质含量细粉砂，开采防控砂难度较大。针对高泥质细粉砂挡砂机制问题，使用粒度中值为10.13 μm的泥质细粉砂样品，模拟单向气液携砂流动条件，使用绕丝筛板、金属烧结网、金属纤维、预充填陶粒4类挡砂介质在20~80 μm挡砂精度下进行挡砂模拟实验，采用显微成像系统观察挡砂介质内部及表面砂粒沉积与堵塞动态，分析介质流通性能和挡砂性能变化，总结堵塞规律、微观挡砂机制与形态及其控制因素。研究结果表明，不同类型和精度的挡砂介质对泥质细粉砂的堵塞总体呈现堵塞开始、堵塞加剧和堵塞平衡3个阶段。随着驱替进行，挡砂介质渗透率逐渐降低，幅度会高达90%以上；同时过砂速度减缓，最终过砂率为5%~10%。根据堵塞规律和微观图像分析，提出了粗组分分选桥架、局部砂团适度挡砂、整体砂桥阻挡等挡砂介质对泥质细粉砂的3种微观挡砂机制。以粗组分分选桥架挡砂机制为主的挡砂工况下，挡砂介质堵塞渗透率较高，但过砂率超过15%，挡砂效果较差；以整体砂桥挡砂机制为主时，过砂率在10%以下，挡砂性能较好，但各类挡砂介质的堵塞渗透率不足1 D，流通性能较差。局部砂团适度挡砂机制为主时介质挡砂性能及流通性能介于两者之间。挡砂介质对天然气水合物储层泥质细粉砂的微观挡砂机制和形态受挡砂介质类型、精度、地层砂特征以及流动条件等因素控制，其规律对于水合物泥质细粉砂防控砂优化有指导意义。     

Spatiotemporal Magnetocaloric Microenvironment for Guiding the Fate of Biodegradable Polymer Implants

The degradation behavior of implants is significantly important for bone repair. However, it is still unprocurable to spatiotemporally regulate the degradation of the implants to match bone ingrowth. In this paper, a magneto-controlled biodegradation model is established to explore the degradation behavior of magnetic scaffolds in a magnetothermal microenvironment generated by an alternating magnetic field (AMF). The results demonstrate that the scaffolds can be heated by magnetic nanoparticles (NPs) under AMF, which dramatically accelerated scaffold degradation. Especially, magnetic NPs modified by oleic acid with a better interface compatibility exhibit a greater heating efficiency to further facilitate the degradation. Furthermore, the molecular dynamics simulations reveal that the enhanced motion correlation between magnetic NPs and polymer matrix can accelerate the energy transfer. As a proof-of-concept, the feasibility of magneto-controlled degradation for implants is demonstrated, and an optimizing strategy for better heating efficiency of nanomaterials is provided, which may have great instructive significance for clinical medicine.     

Micro-expression recognition from local facial regions

MiE is a facial involuntary reaction that reflects the real emotion and thoughts of a human being. It is very difficult for a normal human to detect a Micro-Expression (MiE), since it is a very fast and local face reaction with low intensity. As a consequence, it is a challenging task for researchers to build an automatic system for MiE recognition. Previous works for MiE recognition have attempted to use the whole face, yet a facial MiE appears in a small region of the face, which makes the extraction of relevant features a hard task. In this paper, we propose a novel deep learning approach that leverages the locality aspect of MiEs by learning spatio-temporal features from local facial regions using a composite architecture of Convolutional Neural Network (CNN) and Long Short Term Memory (LSTM). The proposed solution succeeds to extract relevant local features for MiEs recognition. Experimental results on benchmark datasets demonstrate the highest recognition accuracy of our solution with respect to state-of-the-art methods.     

Exploring Regional Profile of Drought History- a New Procedure to Characterize and Evaluate Multi-Scaler Drought Indices Under Spatial Poisson Log-Normal Model

Water Resources Management - Drought is recurrently occurring in many parts of the globe. In contrast to other natural hazards, drought has complex climatic characteristics. Several environmental...     

One-Dimensional Deep Convolutional Neural Network for Mineral Classification from Raman Spectroscopy

Neural Processing Letters - Raman spectroscopy is often used for the composition determination and rapid classification of materials because it can reflect the molecular information of materials....     

Deep learning-based symbol detection algorithm in IMDD-OOFDM system

In the current research on intensity-modulation and direct-detection optical orthogonal frequency division multiplexing ( IMDD-OOFDM ) system, effective channel compensation is a key factor to improve system performance. In order to improve the efficiency of channel compensation, a deep learning-based symbol detection algorithm is proposed in this paper for IMDD-OOFDM system. Firstly, a high-speed data streams symbol synchronization algorithm based on a training sequence is used to ensure accurate symbol synchronization. Then the traditional channel estimation and channel compensation are replaced by an echo state network (ESN) to restore the transmitted signal. Finally, we collect the data from the system experiment and calculate the signal-to-noise ratio (SNR). The analysis of the SNR optimized by the ESN proves that the ESN-based symbol detection algorithm is effective in compensating nonlinear distortion.     

基于Bert预训练模型的虚假新闻文本检测

虚假新闻剥夺了人们获取真相的权利,也给社会和国家带来了许多危害。文中以虚假新闻文本为例,分析和验证了多种预训练语言模型在虚假新闻文本分类上的分类效果。经实验证明,相较于其他语言模型,Bert预训练语言模型取得了较好的结果,预测准确率为86.97%,召回率为88.12%,F1值为87.54%。