SOINN-Based Abnormal Trajectory Detection for Efficient Video Condensation

With the evolution of video surveillance systems, the requirement of video storage grows rapidly; in addition, safe guards and forensic officers spend a great deal of time observing surveillance videos to find abnormal events. As most of the scene in the surveillance video are redundant and contains no information needs attention, we propose a video condensation method to summarize the abnormal events in the video by rearranging the moving trajectory and sort them by the degree of anomaly. Our goal is to improve the condensation rate to reduce more storage size, and increase the accuracy in abnormal detection. As the trajectory feature is the key to both goals, in this paper, a new method for feature extraction of moving object trajectory is proposed, and we use the SOINN (Self-Organizing Incremental Neural Network) method to accomplish a high accuracy abnormal detection. In the results, our method is able to shirk the video size to 10% storage size of the original video, and achieves 95% accuracy of abnormal event detection, which shows our method is useful and applicable to the surveillance industry.     

含不凝性气体蒸汽浸没射流冷凝压力振荡实验研究

实验研究了不凝性气体（空气）含量、水温和蒸汽质量流速对蒸汽浸没射流冷凝压力振荡特性的影响，实验工况横跨冷凝振荡（CO）区和稳定冷凝（SC）区。结果表明：对于纯蒸汽射流，压力振荡主频随水温的升高而降低，振荡强度随水温的升高而升高；在CO区，振荡主频和振荡强度均随蒸汽质量流速的升高而升高；在SC区，振荡主频随蒸汽质量流速的升高而降低，振荡强度基本上不随蒸汽质量流速的变化而发生改变；对于含空气射流，随空气质量分数的增加，振荡主频总体呈下降趋势，振荡强度先迅速下降后小幅上升，在空气质量分数为0.05～0.1区域内振荡主频和振荡强度均存在极小值。     

Logarithmic decrease of adhesion force with lateral dynamic revealed by an AFM cantilever at different humidities

Adhesion forces between a tipless cantilever and an Au film were determined to investigate the influence of lateral velocity by recording force curves with an atomic force microscope at 20%–90% relative humidities. The sample was moved laterally, forth and back, with a frequency of 0.001–100 Hz and scan distances of 0.8, 8, and 80 μm to achieve a velocity ranging over 7 orders of magnitude. Experimental results show that at low lateral velocities (between 1.6 nm/s and 1–10 μm/s), the adhesion force either increases or decreases or remains stable with the lateral velocity without a certain characteristic trend. However, after a critical velocity, the adhesion force decreases logarithmically with the lateral velocity (between 1–10 and 16,000 μm/s). The decreasing magnitude can be as large as 97.3% of the maximum adhesion force. This decrease is well-explained by the contact time dependence of water bridges formed by capillary condensation.     

基于数据辩识算法的燃气热水锅炉运行特性研究

搭建了以泡沫铜翅片换热器为核心的烟气水分回收实验台，研究了冷却水进口温度、烟气雷诺数及烟气中水蒸气体积分数对该换热器水回收特性和换热特性的影响,基于实验数据，利用多元回归拟合得到对流换热的关联式，其预测值与实验值误差在6%以内。结果表明：水蒸气体积分数增大可以显著提升水回收特性，而冷却水进口温度及烟气雷诺数对其影响很小；冷却水进口温度与烟气雷诺数对换热效率的影响较大，冷却水进口温度与换热效率成反比，烟气雷诺数与之成正比，而水蒸气体积分数对其影响较小；实验获得的最大冷凝水产率为7.68 kg/h，最大冷凝率为56.94%，最大换热效率为96.95%。     

针织物节能减排漂染工艺探讨

将新开发的高效前处理、染色助剂应用于针织物实用高效漂染工艺,探讨其应用工艺、产品质量及节能减排效果。分析各类前处理碱氧一浴工艺的特点、应用特性及节能减排效果;阐述涤棉针织物练染一浴工艺,免还原清洗工艺,棉针织物活性染色与抛光一浴工艺及活性染色后皂洗酶后处理工艺。并与相应的传统工艺对比其工艺曲线、质量水平、节能减排效果及污染物浓度降低情况。客观评价各类工艺的优缺点,建议生产厂家根据产品质量要求,选用相应高效助剂,并结合实际生产设备优化工艺后使用,节能减排效果将更加显著。     

连续蓄热式生物质气化/燃烧供热系统

生物质能源是一种环境友好的可再生能源,但也存在能量密度低、含水率高、碱金属含量高等缺点,导致其在热利用的过程中存在易结渣、堵灰及腐蚀、热效率不高等问题。本文结合生物质气化、炉内碱金属/硫固定、两级焦油裂解、蓄热式燃烧,以及冷凝热回收等多项先进技术,设计并搭建了连续蓄热式生物质气化/燃烧供热系统。以海洋贝壳类废弃物作为生物质成型燃料的添加剂和生物质焦油裂解过程的催化剂,在实现海洋废弃资源高值化利用的同时,克服了生物质热利用过程中的多项障碍,能够显著提高生物质能热利用效率,同时大幅度降低当前工业及民用供热过程中CO₂、SO_x、NO_x及烟尘的排放,具有良好的经济性与环保性。     

Efficient multi-criteria optimization on noisy machine learning problems

Recent research revealed that model-assisted parameter tuning can improve the quality of supervised machine learning (ML) models. The tuned models were especially found to generalize better and to be more robust compared to other optimization approaches. However, the advantages of the tuning often came along with high computation times, meaning a real burden for employing tuning algorithms. While the training with a reduced number of patterns can be a solution to this, it is often connected with decreasing model accuracies and increasing instabilities and noise. Hence, we propose a novel approach defined by a two criteria optimization task, where both the runtime and the quality of ML models are optimized. Because the budgets for this optimization task are usually very restricted in ML, the surrogate-assisted Efficient Global Optimization (EGO) algorithm is adapted. In order to cope with noisy experiments, we apply two hypervolume indicator based EGO algorithms with smoothing and re-interpolation of the surrogate models. The techniques do not need replicates. We find that these EGO techniques can outperform traditional approaches such as latin hypercube sampling (LHS), as well as EGO variants with replicates.     

煤 /重油加氢共炼中SDBS对煤担载铁镍催化剂的改性效果

以广西褐煤为载体煤,铁盐和镍盐为活性组分,考察了以十二烷基苯磺酸钠(SDBS)作为表面活性剂,对沉淀-氧化法制备煤担载型铁镍催化剂(FeNi/C)的影响以及制备的催化剂在煤/重油加氢共炼中的反应性能。采用XRD和TEM分析了FeNi和FeNi-SDBS的物相组成与微观形貌变化,并以SEM-mapping手段对比了Fe元素和Ni元素在FeNi/C及FeNi-SDBS/C表面的分散效果,采用高压釜实验评价了不同催化剂的反应性能,并对反应后的固体产物采用元素分析、FTIR和SEM进行组成和结构性质研究。结果表明:SDBS的加入显著降低了催化剂的平均粒径,α/γ-FeOOH和Fe0.67Ni0.33OOH等活性相的晶体结构特征减弱,在载体煤上得到了更好的分散效果;FeNi-SDBS/C催化剂相比FeNi/C催化剂有更高的油收率和干基无灰煤转化率,催化活性明显提高;采用SDBS改性的催化剂反应后得到固体产物的n(H)∶n(C)高、脂肪链长度低、芳环取代度大、结构疏松且平均粒径小,表面改性后的FeNi-SDBS/C催化剂拥有更强的促进煤加氢转化和抑制体系缩合生焦的作用。     

Numerical investigation of thermal and electrical management during hydrogen reversible solid-state storage using a novel heat exchanger based on thermoelectric modules

In order to reduce the costs generated by the hydrogen solid storage tank's accessories such as the heat exchanger, this work was carried out. It shows thermal and electrical investigations of transient hydrogen (H₂) solid storage in a tank filled with porous medium (LaNi₅) to activate a potential PEM automotive fuel cell. For this purpose, we use a novel heat exchanger with a heat sink combined with thermoelectric modules (TEMs). We realize a simulation that helps us verify if thermoelectric exchanger will be an alternative to the conventional ones. The main results are that a thermoelectric cooler and heater with 127 couples of semiconductors coupled with 19 fins heat sink could be used during the reversible hydrogen solid storage. Also, results show that we can avoid the water freezing at negative temperatures when using a conventional heat exchanger by using TEM during hydrogen absorption. Finally, during the endothermic desorption of the hydrogen, TEG use can avoid boiling water used in the heating system. Also, the hydrogen tank will be lighter and compact without fins and water tubes.