基于数据质量评价的目标估计

针对目标估计过程需要大量人工参与、自动化程度低的问题，提出了基于数据质量评价的目标估计方法。利用目标数据质量评价方法，对不同传感器得到的目标数据质量进行科学、有效的测度和评价，并根据质量得分动态调整各数据源在目标估计过程中所占的权重，从而减少人工干预，提高目标估计效能。仿真试验结果证明了该方法的有效性。     

Enhanced oxygen evolution reaction kinetics through biochar-based nickel-iron phosphides nanocages in water electrolysis for hydrogen production

Highly-efficient and stable non-noble metal electrocatalysts for overcoming the sluggish kinetics of oxygen evolution reaction (OER) is urgent for water electrolysis. Biomass-derived biochar has been considered as promising carbon material because of its advantages such as low-cost, renewable, simple preparation, rich structure, and easy to obtain heteroatom by in-situ doping. Herein, Ni₂P–Fe₂P bimetallic phosphide spherical nanocages encapsulated in N/P-doped pine needles biochar is prepared via a simple two-step pyrolysis method. Benefiting from the maximum synergistic effects of bimetallic phosphide and biochar, high conductivity of biochar encapsulation, highly exposed active sites of Ni₂P–Fe₂P spherical nanocages, rapid mass transfer in porous channels with large specific surface area, and the promotion in adsorption of reaction intermediates by high-level heteroatom doping, the (Ni_0.75Fe_0.25)₂P@NP/C demonstrates excellent OER activity with an overpotential of 250 mV and a Tafel slope of 48 mV/dec at 10 mA/cm² in 1 M KOH. Also it exhibits a long-term durability in 10 h electrolysis and its activity even improves during the electrocatalytic process. The present work provides a favorable strategy for the inexpensive synthesis of biochar-based transition metal electrocatalysts toward OER, and improves the water electrolysis for hydrogen production.     

南水北调中线总干渠藻类的生态调度

南水北调中线总干渠无在线调蓄水库,对藻类生态调度过程中出现的问题开展生态调度实现策略和实施方式研究。主要实现策略包括:划定自身的调蓄区,隔离生态调度对下游的影响;采用高效的渠池运行方式,减少生态调度时蓄量的反复调整;综合考虑安全、快速、平稳等需求,设定生态调度实施进程和方式。具体实施方式包括:将总干渠划分为流速调控区、调蓄区和正常运行区,分别实施等体积、控制蓄量和闸前常水位方式运行;将生态调度过程划分为充水阶段和泄水阶段,基于流速调控目标值、持续时长和水位降幅约束条件,确定各阶段时长和各分区的闸门群调控方案等。基于2018年3月输水工况,采用明渠一维非恒定流模型,仿真总干渠上游15个渠池的藻类生态调度过程。结果表明,生态调度可在3.5 d内完成,各渠池的平均流速由0.48 m/s增至0.93 m/s,持续时间超过2 h。在整个生态调度过程中,水位变化平稳,水位变幅符合安全阈值要求,下游渠道的正常运行未受生态调度明显影响。     

机器翻译译文质量估计综述

机器翻译译文质量估计(Quality Estimation,QE)是指在不需要人工参考译文的条件下,估计机器翻译系统产生的译文的质量,对机器翻译研究和应用具有很重要的价值。机器翻译译文质量估计经过最近几年的发展,取得了丰富的研究成果。该文首先介绍了机器翻译译文质量估计的背景与意义;然后详细介绍了句子级QE、单词级QE、文档级QE的具体任务目标、评价指标等内容,进一步概括了QE方法发展的三个阶段: 基于特征工程和机器学习的QE方法阶段,基于深度学习的QE方法阶段,融入预训练模型的QE方法阶段,并介绍了每一阶段中的代表性研究工作;最后分析了目前的研究现状及不足,并对未来QE方法的研究及发展方向进行了展望。     

A blockchain-based audit approach for encrypted data in federated learning

The development of data-driven artificial intelligence technology has given birth to a variety of big data applications. Data has become an essential factor to improve these applications. Federated learning, a privacy-preserving machine learning method, is proposed to leverage data from different data owners. It is typically used in conjunction with cryptographic methods, in which data owners train the global model by sharing encrypted model updates. However, data encryption makes it difficult to identify the quality of these model updates. Malicious data owners may launch attacks such as data poisoning and free-riding. To defend against such attacks, it is necessary to find an approach to audit encrypted model updates. In this paper, we propose a blockchain-based audit approach for encrypted gradients. It uses a behavior chain to record the encrypted gradients from data owners, and an audit chain to evaluate the gradients’ quality. Specifically, we propose a privacy-preserving homomorphic noise mechanism in which the noise of each gradient sums to zero after aggregation, ensuring the availability of aggregated gradient. In addition, we design a joint audit algorithm that can locate malicious data owners without decrypting individual gradients. Through security analysis and experimental evaluation, we demonstrate that our approach can defend against malicious gradient attacks in federated learning.     

Investigation of liquid water heterogeneities in large area proton exchange membrane fuel cells using a Darcy two-phase flow model in a multiphysics code

Proper management of the liquid water and heat produced in proton exchange membrane (PEM) fuel cells remains crucial to increase both its performance and durability. In this study, a two-phase flow and multicomponent model, called two-fluid model, is developed in the commercial COMSOL Multiphysics® software to investigate the liquid water heterogeneities in large area PEM fuel cells, considering the real flow fields in the bipolar plate. A macroscopic pseudo-3D multi-layers approach has been chosen and generalized Darcy's relation is used both in the membrane-electrode assembly (MEA) and in the channel. The model considers two-phase flow and gas convection and diffusion coupled with electrochemistry and water transport through the membrane. The numerical results are compared to one-fluid model results and liquid water measurements obtained by neutron imaging for several operating conditions. Finally, according to the good agreement between the two-fluid and experimentation results, the numerical water distribution is examined in each component of the cell, exhibiting very heterogeneous water thickness over the cell surface.     

Prediction of fish quality level with machine learning

In this study, sea bream, sea bass, anchovy and trout were captured and recorded using a digital camera during refrigerated storage for 7 days. In addition, their total viable counts (TVC) were determined on a daily basis. Based on the TVC, each fish was classified as ‘fresh’ when it was <5 log cfu per g, and as ‘not fresh’ when it was >7 log cfu per g. They were uploaded on a web-based machine learning software called Teachable Machine (TM), which was trained about the pupils and heads of the fish. In addition, images of each species from different angles were uploaded to the software in order to ensure the recognition of fish species by TM. The data of the study indicated that the TM was able to distinguish fish species with high accuracy rates and achieved over 86% success in estimating the freshness of the fish species tested.     

Experimental investigation on the heat and water transfer enhancement in a membrane-based air-to-air humidifier at insulation condition

In the present study, a membrane-based air-to-air planar humidifier (MAPH) with baffle-blocked flow channels and a common MAPH are fabricated, tested and compared. These MAPHs are well thermal insulated from their surroundings. Polyoxymethylene (POM) plates with some unique properties such as large tensile and flexural strength, high chemical resistance and high stiffness are used to create channels at dry and humid sides of MAPHs. The obtained findings revealed that the higher heat and water transfer rates and smaller dew point approach temperature (DPAT) in entire tested flow rates occurs in baffle-blocked MAPH. To evaluate the MAPH performance with considering the pressure drop, a dimensionless parameter, performance evaluation criteria (PEC), is introduced. At flow rates less than 1 m³/h, PEC is less than 1, indicating a decline in MAPH performance with considering the pressure drop. In baffle-blocked MAPH using water trap in the inlet of dry side leads to the performance deterioration. Additionally, the increased relative humidity (RH) of humid side inlet causes an increase in DPAT, consequently, the performance deterioration.     

Novel proton-conducting layered perovskite based on BaLaInO4 with two different cations in B-sublattice: Synthesis,hydration, ionic (O2−, H+) conductivity

The present study focused on the novel material with significantly improved properties for the application in the area of clean energy. The new complex oxide BaLaIn_0·5Y_0·5O₄ with layered perovskite structure was obtained for the first time. It was proved that the introduction of Y³⁺ ions in the perovskite layer of BaLaInO₄ leads i) to the rise of the oxygen-ionic conductivity due to the increase in mobility of oxygen ions as a result of the expand of the cell volume and ii) to the enhancement of protonic conductivity due to the increase in the proton concentration and mobility. The sample BaLaIn_0·5Y_0·5O₄ is nearly pure proton conductor below 400 °C and has the protonic conductivity value 1.6?10^?5 S/cm at this temperature.     

Wavelength-dependent photoactivity of ZnxCd1−xS and ZnCo2O4/ZnxCd1−xS for H2 and H2O2 production

Zinc cadmium sulfide (Zn_xCd_1?xS) is a good photocatalyst for hydrogen evolution reaction (HER), but an optimum x (x_m) at which a maximum HER rate is reached varies from one report to another. In this work, we examine the effect of light wavelength, not only for the HER to H₂ in the presence of Na₂S and Na₂SO₃, but also for oxygen reduction reaction (ORR) without addition of any sacrifices. For the HER under a 365 and 420 nm LED lamp, the x_m were 0.9 and 0.7, respectively. For the HER under a 330 and 395–515 nm cut-off xenon lamp, the x_m were 0.7 and 0.5, respectively. For the ORR under a 420 nm cut-off halogen lamp, a maximum production of H₂O₂ was observed at x = 0.3. Furthermore, after 4% ZnCo₂O₄ loading, Zn_xCd_1?xS had an increased activity and stability, either for the HER or for the ORR. Through a (photo)electrochemical measurement, it is proposed that the photocatalytic activity of Zn_xCd_1?xS is determined by its light absorptivity and electron reactivity. The improved performance of n-type Zn_xCd_1?xS by p-type ZnCo₂O₄ is due to formation of a p-n junction, promoting the HER (ORR) on Zn_xCd_1?xS, and the sulfide (water) oxidation on ZnCo₂O₄. This work highlights that Zn_xCd_1-xS is a promising photocatalyst for H₂ and H₂O₂ production, respectively.