摘要：The fundamental idea of materials genome initiative is the integration of computing platform,experimental platform,and data platform to speed up the material innovation hence reduce time and *** paper describes the basic concept of building an integrated computational platform and data platform for material innovation from the perspective of high-throughput simulation and materials knowledge *** material data platform that can integrate material database,heterogeneous material data,various scripts,and open-source material simulation code together is particularly *** metallic materials as an example,a brief introduction to metallic materials data management is given,and how to manage the semi-structure and unstructured iron and steel material data is also presented.

摘要：高通量计算与材料数据库推动了数据驱动的机器学习方法的发展.机器学习已经成为材料计算研究的重要方法,在分析材料数据、加速材料计算、预测材料性质、推进新材料发现、筛选和设计等方面展现出极大的潜力.众多与材料计算相交叉的机器学习方法、模型以及框架不断涌现.本文综述了近年来光电半导体材料计算设计领域内机器学习方法的最新进展与应用.介绍了机器学习的流程与类型,基于不同材料表示方法的浅层模型、集成模型和深度神经网络,以及相关材料数据库和相关工具.我们还讨论了这些模型在预测材料稳定性与光电性质、材料逆向设计、构建材料构效关系等方面的应用.最后,本文对目前机器学习方法存在的机遇与挑战,即数据数量与质量、材料的表示、材料逆向设计做了进一步总结与讨论.

摘要：Rational composition design of trimetallic phosphide catalysts is of significant importance for enhanced surface reaction and efficient catalytic ***,hierarchical Co_(x)Ni_(y)Fe_(z)P with precise control of stoichiometric metallic elements(x:y:z=(1-10):(1-10):1)has been synthesized,and Co_(1.3)Ni_(0.5)Fe_(0.2)P,as the most optimal composition,exhibits remarkable catalytic activity(η=320 mV at 10 mA cm^(−2))and long-term stability(ignorable decrease after 10 h continuous test at the current density of 10 mA cm^(−2))toward oxygen evolution reaction(OER).It is found that the surface P in Co_(1.3)Ni_(0.5)Fe_(0.2)P was replaced by O under the OER *** density function theory calculations before and after long-term stability tests suggest the clear increasing of the density of states near the Fermi level of Co_(1.3)Ni_(0.5)Fe_(0.2)P/Co_(1.3)Ni_(0.5)Fe_(0.2)O,which could enhance the OH−adsorption of our electrocatalysts and the corresponding OER performance.

摘要：Materials informatics has emerged as a promisingly new paradigm for accelerating materials discovery and *** exploits the intelligent power of machine learning methods in massive materials data from experiments or simulations to seek new materials,functionality,and principles,*** specialized facilities to generate,collect,manage,learn,and mine large-scale materials data is crucial to materials *** herein developed an artificial-intelligence-aided data-driven infrastructure named Jilin Artificial-intelligence aided Materials-design Integrated Package(JAMIP),which is an open-source Python framework to meet the research requirements of computational materials *** is integrated by materials production factory,high-throughput first-principles calculations engine,automatic tasks submission and monitoring progress,data extraction,management and storage system,and artificial intelligence machine learning based data mining *** have integrated specific features such as an inorganic crystal structure prototype database to facilitate high-throughput calculations and essential modules associated with machine learning studies of functional *** demonstrated how our developed code is useful in exploring materials informatics of optoelectronic semiconductors by taking halide perovskites as typical *** obeying the principles of automation,extensibility,reliability,and intelligence,the JAMIP code is a promisingly powerful tool contributing to the fast-growing field of computational materials informatics.

摘要：在传统化学回热分布式供能系统中,汽化水需要消耗大量中高温烟气余热,降低了系统的制冷潜力,大量中高温烟气余热将贬值为水的低温潜热,为此,该文提出一种新型化学回注沼气分布式供能系统。将部分烟气回注重整器为甲烷重整反应提供大量的氧化剂(O_(2)、H_(2)O和CO_(2))和热量,重整器内部发生甲烷三重整反应,通过回热空气有效回收另一部分烟气热量。在设计工况下,新系统提高122.40 kW(13.17%)的发电量和538.85 kW(160.52%)的制冷量,(火用)效率提高16.90%。化学回热系统在为沼气池保温方面更具有优势,新系统与化学回热系统所能满足的最低环境温度分别为9.90和7.44℃,当环境温度为7.44℃时,与化学回热系统相比,新系统(火用)效率仍能提高7.41%。研究结果可为沼气在分布式供能领域的运用提供一种新的技术方案。

摘要：针对催化裂化(fluid catalytic cracking,FCC)分馏系统在网络攻击和系统故障具有相似特征情况下难以辨识的问题,提出了一种基于跨域因果图的攻击故障辨识方法。首先,将数据驱动和拓扑知识融合以构建跨域因果图,涵盖物理层和信息层的变量节点和设备节点;其次,结合多源异常证据集,设计了基于弗洛伊德的异常因果传播路径搜索算法,得到异常节点间的因果传播路径;最后根据必经点约束、单点异常约束、必经点最大数量约束等条件,结合异常发生时间,得到异常传播路径的最小树型图,根据根节点位置判断系统异常类型。该方法在FCC分馏仿真系统上验证了有效性,结果表明其辨识准确率为94.84%,对正常工况、故障工况和攻击工况的检测召回率分别为97.11%、93.25%、95.30%,相比同类方案,该方法不仅解决了相似特征带来的辨识难题,还能在保证较高的辨识准确率的同时,给出异常传播路径,为安全防护提供报警信息。

摘要：教育数字化转型背景下,传统作业设计模式面临着适应性危机,难以满足学生个性化的学习需求和数字素养培养要求。聚焦生成式人工智能支持下的作业设计模式重构,推动教学范式的深层变革,构建了一个包含作业目标、内容、形式和评价四个子系统的整合性框架,形成了动态协同的目标设定机制、分层生成的内容创制策略、交互式创新的形式设计方法和闭环优化的评价模式。此模式可推动教师角色转型、学生主体性增强,促进教育评价方式的系统性变革。

摘要：针对现有防腐涂料研发成本高、研发效率低的问题,通过数据输入、特征选择、测试集比例选择、机器学习算法种类选择、模型训练/评估等步骤,训练出可进行耐老化性能预测的人工智能(AI)模型。研究了不同模型参数对AI模型预测效果的影响,得到了适宜的模型参数。在AI模型复用及验证的过程中,创新性地采用“AI预测+正交设计”的方法进行新型防腐配方优化设计和验证,相较基于经验试错法、正交试验法,采用新方法所需的实验量分别减少93%、78%,显著提升新型涂料研发效率,降低研发成本,有助于解决材料智能研发面临的“小样本”难题。

摘要：日本正仓院所见诸多“含绶鸟”纹,是以唐、萨珊为代表的亚欧大陆文明对当时日本社会产生深刻影响的一处缩影,亦是在亚欧丝绸之路上广泛分布的“含绶鸟”图像的皇权征途的最东端。“含绶鸟”纹以“绶带”为核心元素,展示了古代亚欧地区共通的权力崇拜心理和普遍的权位等级意识。而纹饰形成背后所蕴含的思维模式则与自古以来世界各地均存在的神话思维息息相关,显示出具象性、情感性等特征。

摘要：日本平安时期“松喰鹤”纹样开始流行,这种脱胎于“绶带鸟”的图案,凭借与永生意象的结合,迅速拥有了最为广泛的群众基础,在日本乃至整个东亚地区迅速取代了象征权力的“绶带鸟”纹的地位,成为平安时期日本化浪潮中“和样化”纹饰的代表,至今仍是日本典型的传统图案之一。该纹凝炼了大和人质朴而深刻的神道教生死观,通过多层赋意,进入到现象学中所谓的多重世界构造里,体现了人类图像意识中的模像关系和同一性原理。