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.     

Dynamic energy and mass balance model for an industrial alkaline water electrolyzer plant process

This paper proposes a parameter adjustable dynamic mass and energy balance simulation model for an industrial alkaline water electrolyzer plant that enables cost and energy efficiency optimization by means of system dimensioning and control. Thus, the simulation model is based on mathematical models and white box coding, and it uses a practicable number of fixed parameters. Zero-dimensional energy and mass balances of each unit operation of a 3 MW, and 16 bar plant process were solved in MATLAB functions connected via a Simulink environment. Verification of the model was accomplished using an analogous industrial plant of the same power and pressure range having the same operational systems design. The electrochemical, mass flow and thermal behavior of the simulation and the industrial plant were compared to ascertain the accuracy of the model and to enable modification and detailed representation of real case scenarios so that the model is suitable for use in future plant optimization studies. The thermal model dynamically predicted the real case with 98.7 % accuracy. Shunt currents were the main contributor to relative low Faraday efficiency of 86 % at nominal load and steady-state operation and heat loss to ambient from stack was only 2.6 % of the total power loss.     

自重湿陷性黄土地基预钻孔浸水处理的可靠度设计方法

为解决传统预浸水法存在的浸水时间长、浸水处理范围难以确定等不足,基于土体中水分运移规律,依据可靠度理论、极限状态设计方法及复合 Poisson 过程原理,提出一种消除黄土湿陷性的处理浸水方法——预钻孔浸水法。给出了利用预钻孔浸水法对自重湿陷性黄土地基进行浸水时,水平向及竖直向浸水影响范围的确定模型;在此基础上结合达西定律给出了浸水孔设计参数如孔深、孔间距及浸水孔个数的确定方法。结合铜川某工程,设计进行了现场预钻孔浸水试验,对该方法的合理性进行了验证,并通过现场钻探、现场勘探、室内湿陷性试验等方法对该方法的处理效果进行了评价。该浸水方法具有浸水时间短、浸水影响范围可根据浸水孔布设进行控制等优点,且浸水处理效果良好,完全符合施工要求。     

电信专业学术英文写作模块化教学实践

学术英文写作是当今电子信息专业研究生必修的一门课程。然而传统的以教师为中心的灌输式教学已不能跟上网络迅猛发展的趋势,尤其是当疫情来临的特殊形势下。此外,现有的学术英文写作教学研究仅提供宏观的设计,缺乏具体的实际可操作性。为此,本文以引言写作逻辑为教学模块案例,探索了如何充分利用网络资源的优势,开展以学生为中心的课前课中课下有机融合的灵活的教学设计。所探索的引言写作技巧和详实的教学设计,为模块化网络教学提供一个切实可行的参考方案。     

120m高钢筋混凝土烟囱爆破拆除

介绍了用定向控制爆破方法拆除吉化电石厂120m钢筋混凝土烟囱的经验。针对该烟囱下部有1个门和3个窗户的特殊结构,选择倒梯形爆破切口,以增强预留支撑面的强度。为防止烟囱落地产生震动和前冲,在倒塌的前方设置了减震带和阻冲挡土墙。文中同时还阐述了参数的选择与计算,以及爆破效果。文中总结的四点经验值得借鉴。     

减振沟对爆破振动加速度峰值减振效应的试验研究

通过对减振沟开挖前后两个阶段爆破振动加速度峰值的监测,采用回归分析的方法,得到两种情况下的萨道夫斯基经验公式。通过对比分析的方法,得到减振沟对振动加速度峰值的减振规律。结果表明,合理的开挖减振沟可有效地降低爆破振动加速度峰值。     

Optimization of PEMFC system operating conditions based on neural network and PSO to achieve the best system performance

PEMFC system is a complex new clean power system. Based on MATLAB/Simulink, this paper develops a system-level dynamic model of PEMFC, including the gas supply system, hydrogen supply system, hydrothermal management system, and electric stack. The neural network fits the electric stack model to the simulation data. The effects of different operating conditions on the PEMFC stack power and system efficiency are analyzed. Combining the power of the reactor and the system efficiency to define the integrated performance index, the particle swarm optimization (PSO) algorithm is introduced to optimize the power density and system efficiency of the PEMFC with multiple objectives. The final optimal operating point increases the power density and system efficiency by 1.33% and 12.8%, respectively, which maximizes the output performance and reduces the parasitic power.     

An active balancer with rapid bidirectional charge shuttling and adaptive equalization current control for lithium-ion battery strings

This article proposes an active balancer, which features bidirectional charge shuttling and adaptive equalization current control, to fast counterbalance the state of charge (SOC) of cells in a lithium-ion battery (LIB) string. The power circuit consists of certain bidirectional buck-boost converters to transfer energy among the different cells back and forth. Owing to the characterization of the open-circuit voltage (OCV) vs SOC in LIB being relatively smooth near the SOC middle range, the SOC-inspected balance strategy can achieve more precise and efficient equilibrium than the voltage-based control. Accordingly, a compensated OCV-based SOC estimation is put forward to take into account the discrepancy of SOC estimation. Besides, the varied-duty-cycle (VDC) and curve-fitting modulation (CFM) methods are devised herein to tackle the problems of slow equalization rate and low balance efficacy, which arise from the diminution in balancing current as the SOC difference between the cells decreases in the later duration of equalization especially. The proposed strategies have taken the battery nonlinear characteristic and circuit parameter nonideality into account and can adaptively modulate the duty cycle with the SOC difference to keep balancing current constant throughout the balancing cycle. Simulated and experimental results are given to demonstrate the feasibility and effectiveness of the same prototype constructed. Compared with the fixed duty cycle and the VDC methods, the proposed CFM has the best balancing efficiency of 81.4%, and the balance time is shortened by 27.1% and 18.6%, respectively.