[{"data":1,"prerenderedAt":555},["ShallowReactive",2],{"content-query-Vy0VUR4WSE":3},{"_path":4,"_dir":5,"_draft":6,"_partial":6,"_locale":7,"title":8,"description":9,"date":10,"cover":11,"type":12,"state":13,"body":14,"_type":549,"_id":550,"_source":551,"_file":552,"_stem":553,"_extension":554},"/activities/zh/1971","zh",false,"","加入昇思MindSpore Elec AI SIG，共同构建智能电磁技术","神经网络具有万能逼近和高效推理能力，这使得神经网络在求解微分方程时具有潜在的优势。为此，昇思MindSpore Elec AI  专项兴趣小组（简称：智能电磁AI SIG）正式成立，并面向开源社区招募志同道合的伙伴。","2022-11-25","https://obs-mindspore-file.obs.cn-north-4.myhuaweicloud.com/file/2022/11/29/5bc66186bdb84d31a791a5d136c894f8.png","activities",1,{"type":15,"children":16,"toc":546},"root",[17,25,31,36,41,46,51,56,61,66,75,80,85,93,98,103,108,113,121,126,131,139,144,149,154,162,170,175,183,188,193,201,212,226,240,256,273,292,312,334,357,382,390,398,403,408,413,418,423,428,433,438,443,451,456,463,471,482,490,499,509,514,519,524,529,534,539],{"type":18,"tag":19,"props":20,"children":22},"element","h1",{"id":21},"加入昇思mindspore-elec-ai-sig共同构建智能电磁技术",[23],{"type":24,"value":8},"text",{"type":18,"tag":26,"props":27,"children":28},"p",{},[29],{"type":24,"value":30},"电磁场看不见、摸不着，却在日常生活中无处不在。电磁场的产生主要源于自然和人工两类。自然产生的电磁场有地磁场、太阳光以及一切物体热辐射产生的电磁波等等。自然电磁场催生并推动了人类的文明：由于太阳光的存在，人类可以在温度适宜的地球居住，可以通过植物的光合作用获取充足的食物；利用地磁场人类可以进行导航，进而迎来了大航海和全球化时代。",{"type":18,"tag":26,"props":32,"children":33},{},[34],{"type":24,"value":35},"随着科技的发展，人类已经不满足于自然产生的电磁场，开始主动向环境中发射电磁场，并充分挖掘电磁场的应用潜力。如通信领域中利用无线电波收听广播、利用高频微波进行手机通话等；又如地质勘探中利用电磁波的回波探明煤炭存储等。",{"type":18,"tag":26,"props":37,"children":38},{},[39],{"type":24,"value":40},"电磁场的应用不胜枚举，为了能够更好的利用电磁场，人们通过实验、理论以及计算等手段研究电磁场的机理。实验方面，1820年奥斯特在一次讲座上偶然发现通电的导线让小磁针发生偏转，从而发现了电能生磁的现象。",{"type":18,"tag":26,"props":42,"children":43},{},[44],{"type":24,"value":45},"1831年，法拉第在实验中发现变化的磁场可以产生电场，即磁也能够生电。麦克斯韦总结前人的工作，提出了位移电流假说（变化的电场能够产生磁场），完善了电生磁的理论。最终，麦克斯韦将电磁场理论用给简洁、对称和完美的数学形式表示出来，即麦克斯韦方程组。",{"type":18,"tag":26,"props":47,"children":48},{},[49],{"type":24,"value":50},"随着计算机技术的发展，人们采用数值计算的方式去求解麦克斯韦方程组,模拟电磁场在空间中的分布。这样即可以节省实验的成本，也可以通过仿真设计出更加符合需求的电子设备。传统的电磁计算方法包括精确的全波方法和高频近似方法。全波方法如时域有限差分（Finite-Difference Time-Domain method，FDTD），有限元（Finite-Element-Method，FEM）、矩量法（Method of MoMents，MoM）等；高频近似方法如几何光学法（Geometrical Optics，GO）、物理光学法(physical optics，PO)等。",{"type":18,"tag":26,"props":52,"children":53},{},[54],{"type":24,"value":55},"数值计算较好地辅助了电子产品的设计，但传统的数值方法仍存在许多缺陷，如需要进行复杂的网格剖分、迭代计算，计算过程复杂、计算周期长。神经网络具有万能逼近和高效推理能力，这使得神经网络在求解微分方程时具有潜在的优势。为此，昇思MindSpore Elec AI",{"type":18,"tag":26,"props":57,"children":58},{},[59],{"type":24,"value":60},"专项兴趣小组（简称：智能电磁AI SIG）正式成立，并面向开源社区招募志同道合的伙伴。",{"type":18,"tag":26,"props":62,"children":63},{},[64],{"type":24,"value":65},"1",{"type":18,"tag":26,"props":67,"children":68},{},[69],{"type":18,"tag":70,"props":71,"children":72},"strong",{},[73],{"type":24,"value":74},"MindSpore Elec AI SIG****的使命",{"type":18,"tag":26,"props":76,"children":77},{},[78],{"type":24,"value":79},"围绕实际生产中的各类电磁应用场景，在昇思MindSpore框架下探索和研究基于AI的电磁正问题以及反问题。例如开发高效精确的AI电磁模型，构建高效的MindSpore Elec基础工具包，提升电子产品的设计效率等。",{"type":18,"tag":26,"props":81,"children":82},{},[83],{"type":24,"value":84},"小组主要开展了如下几个方向的工作：",{"type":18,"tag":26,"props":86,"children":87},{},[88],{"type":18,"tag":70,"props":89,"children":90},{},[91],{"type":24,"value":92},"MindSpore Elec基础工具包构建",{"type":18,"tag":26,"props":94,"children":95},{},[96],{"type":24,"value":97},"基于MindSpore构建MindSpore Elec基础工具包。基础工具包内置有数据构建及转换、仿真计算以及结果可视化等。",{"type":18,"tag":26,"props":99,"children":100},{},[101],{"type":24,"value":102},"1）数据构建及转换：支持CSG （Constructive Solid Geometry，CSG） 模式的几何构建，以及cst和stp数据（CST等商业软件支持的数据格式）的高效张量转换。",{"type":18,"tag":26,"props":104,"children":105},{},[106],{"type":24,"value":107},"2）仿真计算：a) AI电磁模型库：提供物理和数据驱动的AI电磁模型，物理驱动无需额外的标签数据，只需方程和初边界条件即可；数据驱动是指训练需使用仿真或实验等产生的数据。b) 优化策略：数据压缩可以有效地减少神经网络的存储和计算量；多尺度滤波、动态自适应加权可以提升模型的精度，克服点源奇异性等问题；小样本学习主要是为了减少训练的数据量，节省训练的成本。",{"type":18,"tag":26,"props":109,"children":110},{},[111],{"type":24,"value":112},"3）结果可视化：仿真的结果如S参数或电磁场等可保存在CSV、VTK文件中。MindInsight可以显示训练过程中的损失函数变化，并以图片的形式在网页上展示结果；Paraview是第三方开源软件，具有动态展示切片、翻转等高级功能。",{"type":18,"tag":26,"props":114,"children":115},{},[116],{"type":18,"tag":70,"props":117,"children":118},{},[119],{"type":24,"value":120},"AI电磁仿真模型和方法构建",{"type":18,"tag":26,"props":122,"children":123},{},[124],{"type":24,"value":125},"1） 端到端可微的传统电磁仿真方法研究：基于MindSpore构筑传统的电磁仿真方法如FDTD/有限元/矩量法等，形成端到端可微的AI融合方法。这样可以利用MindSpore加速传统的数值方法，生成模型训练的数据，也可以基于自动微分机制，实现数据同化、电磁反演等应用。",{"type":18,"tag":26,"props":127,"children":128},{},[129],{"type":24,"value":130},"2）AI电磁仿真融合算法研究：物理驱动（如PINNs方法）和数据驱动的AI方法，以及物理和数据融合的算法创新等。",{"type":18,"tag":26,"props":132,"children":133},{},[134],{"type":18,"tag":70,"props":135,"children":136},{},[137],{"type":24,"value":138},"AI电磁仿真模型应用",{"type":18,"tag":26,"props":140,"children":141},{},[142],{"type":24,"value":143},"1）正问题：基站天线、雷达天线、射频电路与系统等的电磁仿真；",{"type":18,"tag":26,"props":145,"children":146},{},[147],{"type":24,"value":148},"2）反问题：电磁超材料设计、雷达勘探、电磁成像等。",{"type":18,"tag":26,"props":150,"children":151},{},[152],{"type":24,"value":153},"2",{"type":18,"tag":26,"props":155,"children":156},{},[157],{"type":18,"tag":70,"props":158,"children":159},{},[160],{"type":24,"value":161},"MindSpore Elec SIG****工作计划",{"type":18,"tag":26,"props":163,"children":164},{},[165],{"type":18,"tag":70,"props":166,"children":167},{},[168],{"type":24,"value":169},"前期",{"type":18,"tag":26,"props":171,"children":172},{},[173],{"type":24,"value":174},"以成员学术交流活动为主，每月组织线上交流活动，围绕AI电磁中涉及的问题，介绍研究工作进展，讨论研究工作中的难点。",{"type":18,"tag":26,"props":176,"children":177},{},[178],{"type":18,"tag":70,"props":179,"children":180},{},[181],{"type":24,"value":182},"后期",{"type":18,"tag":26,"props":184,"children":185},{},[186],{"type":24,"value":187},"通过合作开发等模式，在国内高校及企业间开展电磁AI问题的合作研究。",{"type":18,"tag":26,"props":189,"children":190},{},[191],{"type":24,"value":192},"3",{"type":18,"tag":26,"props":194,"children":195},{},[196],{"type":18,"tag":70,"props":197,"children":198},{},[199],{"type":24,"value":200},"MindSpore Elec AI SIG****构成",{"type":18,"tag":26,"props":202,"children":203},{},[204],{"type":18,"tag":70,"props":205,"children":206},{},[207],{"type":18,"tag":70,"props":208,"children":209},{},[210],{"type":24,"value":211},"小组领衔成员",{"type":18,"tag":26,"props":213,"children":214},{},[215],{"type":18,"tag":70,"props":216,"children":217},{},[218],{"type":18,"tag":70,"props":219,"children":220},{},[221],{"type":18,"tag":222,"props":223,"children":225},"img",{"alt":7,"src":224},"https://obs-mindspore-file.obs.cn-north-4.myhuaweicloud.com/file/2022/11/29/8f75fa4cc2264e47939d71bbefafc3fb.png",[],{"type":18,"tag":26,"props":227,"children":228},{},[229],{"type":18,"tag":70,"props":230,"children":231},{},[232],{"type":18,"tag":70,"props":233,"children":234},{},[235],{"type":18,"tag":70,"props":236,"children":237},{},[238],{"type":24,"value":239},"陆卫兵 东南大学科研院 院长/教授",{"type":18,"tag":26,"props":241,"children":242},{},[243],{"type":18,"tag":70,"props":244,"children":245},{},[246],{"type":18,"tag":70,"props":247,"children":248},{},[249],{"type":18,"tag":70,"props":250,"children":251},{},[252],{"type":18,"tag":222,"props":253,"children":255},{"alt":7,"src":254},"https://obs-mindspore-file.obs.cn-north-4.myhuaweicloud.com/file/2022/11/29/422cbbb1ddea4c9683f76cd8c4c173f4.png",[],{"type":18,"tag":26,"props":257,"children":258},{},[259],{"type":18,"tag":70,"props":260,"children":261},{},[262],{"type":18,"tag":70,"props":263,"children":264},{},[265],{"type":18,"tag":70,"props":266,"children":267},{},[268],{"type":18,"tag":70,"props":269,"children":270},{},[271],{"type":24,"value":272},"杨武 东南大学信息科学与工程学院 副研究员",{"type":18,"tag":26,"props":274,"children":275},{},[276],{"type":18,"tag":70,"props":277,"children":278},{},[279],{"type":18,"tag":70,"props":280,"children":281},{},[282],{"type":18,"tag":70,"props":283,"children":284},{},[285],{"type":18,"tag":70,"props":286,"children":287},{},[288],{"type":18,"tag":222,"props":289,"children":291},{"alt":7,"src":290},"https://obs-mindspore-file.obs.cn-north-4.myhuaweicloud.com/file/2022/11/29/b3cbaf627581496e852d4712abada944.png",[],{"type":18,"tag":26,"props":293,"children":294},{},[295],{"type":18,"tag":70,"props":296,"children":297},{},[298],{"type":18,"tag":70,"props":299,"children":300},{},[301],{"type":18,"tag":70,"props":302,"children":303},{},[304],{"type":18,"tag":70,"props":305,"children":306},{},[307],{"type":18,"tag":70,"props":308,"children":309},{},[310],{"type":24,"value":311},"徐勇 江苏浩云连德信息技术有限公司 高级工程师",{"type":18,"tag":26,"props":313,"children":314},{},[315],{"type":18,"tag":70,"props":316,"children":317},{},[318],{"type":18,"tag":70,"props":319,"children":320},{},[321],{"type":18,"tag":70,"props":322,"children":323},{},[324],{"type":18,"tag":70,"props":325,"children":326},{},[327],{"type":18,"tag":70,"props":328,"children":329},{},[330],{"type":18,"tag":222,"props":331,"children":333},{"alt":7,"src":332},"https://obs-mindspore-file.obs.cn-north-4.myhuaweicloud.com/file/2022/11/29/9a93f69067184b9e9a9cedbf3ff8cecc.png",[],{"type":18,"tag":26,"props":335,"children":336},{},[337],{"type":18,"tag":70,"props":338,"children":339},{},[340],{"type":18,"tag":70,"props":341,"children":342},{},[343],{"type":18,"tag":70,"props":344,"children":345},{},[346],{"type":18,"tag":70,"props":347,"children":348},{},[349],{"type":18,"tag":70,"props":350,"children":351},{},[352],{"type":18,"tag":70,"props":353,"children":354},{},[355],{"type":24,"value":356},"李家奇 东南大学物理学院 副教授",{"type":18,"tag":26,"props":358,"children":359},{},[360],{"type":18,"tag":70,"props":361,"children":362},{},[363],{"type":18,"tag":70,"props":364,"children":365},{},[366],{"type":18,"tag":70,"props":367,"children":368},{},[369],{"type":18,"tag":70,"props":370,"children":371},{},[372],{"type":18,"tag":70,"props":373,"children":374},{},[375],{"type":18,"tag":70,"props":376,"children":377},{},[378],{"type":18,"tag":222,"props":379,"children":381},{"alt":7,"src":380},"https://obs-mindspore-file.obs.cn-north-4.myhuaweicloud.com/file/2022/11/29/16dc1214c43a48af80d52b81befc2683.png",[],{"type":18,"tag":26,"props":383,"children":384},{},[385],{"type":18,"tag":70,"props":386,"children":387},{},[388],{"type":24,"value":389},"陈新蕾 南京航空航天大学电子信息工程学院 副教授",{"type":18,"tag":26,"props":391,"children":392},{},[393],{"type":18,"tag":70,"props":394,"children":395},{},[396],{"type":24,"value":397},"小组成员",{"type":18,"tag":26,"props":399,"children":400},{},[401],{"type":24,"value":402},"01、**Kyang，**昇思MindSpore高级工程师",{"type":18,"tag":26,"props":404,"children":405},{},[406],{"type":24,"value":407},"02、**翁瑞，**东南大学信息科学与工程学院 博士生",{"type":18,"tag":26,"props":409,"children":410},{},[411],{"type":24,"value":412},"03、**Adrian Lee，**昇思MindSpore高级工程师",{"type":18,"tag":26,"props":414,"children":415},{},[416],{"type":24,"value":417},"04、**Lulu Zhang，**昇思MindSpore高级工程师",{"type":18,"tag":26,"props":419,"children":420},{},[421],{"type":24,"value":422},"05、**秦洁，**东南大学软件学院 硕士生",{"type":18,"tag":26,"props":424,"children":425},{},[426],{"type":24,"value":427},"06、**张哲，**东南大学软件学院 硕士生",{"type":18,"tag":26,"props":429,"children":430},{},[431],{"type":24,"value":432},"07、**孙丁一，**东南大学-蒙纳士大学苏州联合研究生院 硕士生",{"type":18,"tag":26,"props":434,"children":435},{},[436],{"type":24,"value":437},"08、**苑玉杰，**昇思MindSpore布道师",{"type":18,"tag":26,"props":439,"children":440},{},[441],{"type":24,"value":442},"4",{"type":18,"tag":26,"props":444,"children":445},{},[446],{"type":18,"tag":70,"props":447,"children":448},{},[449],{"type":24,"value":450},"MindSpore Elec AI SIG召唤你",{"type":18,"tag":26,"props":452,"children":453},{},[454],{"type":24,"value":455},"扫码加入智能电磁AI SIG交流群",{"type":18,"tag":26,"props":457,"children":458},{},[459],{"type":18,"tag":222,"props":460,"children":462},{"alt":7,"src":461},"https://obs-mindspore-file.obs.cn-north-4.myhuaweicloud.com/file/2022/11/29/d414a769c53b4394b344a5b4c078f6b9.png",[],{"type":18,"tag":26,"props":464,"children":465},{},[466],{"type":18,"tag":70,"props":467,"children":468},{},[469],{"type":24,"value":470},"sig仓：",{"type":18,"tag":26,"props":472,"children":473},{},[474],{"type":18,"tag":475,"props":476,"children":480},"a",{"href":477,"rel":478},"https://gitee.com/mindspore/community/tree/master/sigs/mindelec",[479],"nofollow",[481],{"type":24,"value":477},{"type":18,"tag":26,"props":483,"children":484},{},[485],{"type":18,"tag":70,"props":486,"children":487},{},[488],{"type":24,"value":489},"代码仓：",{"type":18,"tag":26,"props":491,"children":492},{},[493],{"type":18,"tag":475,"props":494,"children":497},{"href":495,"rel":496},"https://gitee.com/mindspore/mindscience/tree/master/MindElec",[479],[498],{"type":24,"value":495},{"type":18,"tag":26,"props":500,"children":501},{},[502],{"type":18,"tag":475,"props":503,"children":506},{"href":504,"rel":505},"http://mp.weixin.qq.com/s?__biz=MzAxMDA1MDM0NQ==&mid=2247566255&idx=1&sn=069bcf18b883acddb94177e5e272477e&chksm=9b55cde9ac2244ffac8a994f3a7faf1a255fb1baac335596e45a2b23116c65a39d72c59e43d9&scene=21#wechat_redirect",[479],[507],{"type":24,"value":508},"昇思MindSpore开源社区算力使能，快来SIG申请你的专属算力",{"type":18,"tag":26,"props":510,"children":511},{},[512],{"type":24,"value":513},"昇思MindSpore为推动SIG发展和开发者活跃，发布社区专属算力使能计划，面向SIG发放海量算力，免费领取。助力开发者了解和掌握全场景AI技术，支撑开发者实践和项目开发，助力开发者全面发展。",{"type":18,"tag":26,"props":515,"children":516},{},[517],{"type":24,"value":518},"关于MindSpore SIG",{"type":18,"tag":26,"props":520,"children":521},{},[522],{"type":24,"value":523},"昇思MindSpore社区欢迎业界专家、学术伙伴在社区成立特别兴趣小组（SIG），作为社区领域技术代言人，打造领域技术品牌，共建昇思MindSpore开源生态。",{"type":18,"tag":26,"props":525,"children":526},{},[527],{"type":24,"value":528},"MindSpore SIG即MindSpore Special Interest Groups，即“昇思特别兴趣小组”，MindSpore社区成立个技术SIG的初衷是为该领域的专家、教授和学生提供一个开放交流的平台，通过会议分享、项目开发等活动促进技术交流、合作共赢，并使得SIG成员的影响力和技术能力得到提升，截止目前，MindSpore SIG共计成立20+。",{"type":18,"tag":26,"props":530,"children":531},{},[532],{"type":24,"value":533},"如果你也想成立一个SIG",{"type":18,"tag":26,"props":535,"children":536},{},[537],{"type":24,"value":538},"扫码添加小助手了解更多",{"type":18,"tag":26,"props":540,"children":541},{},[542],{"type":18,"tag":222,"props":543,"children":545},{"alt":7,"src":544},"https://obs-mindspore-file.obs.cn-north-4.myhuaweicloud.com/file/2022/11/29/dc09f6cd7a754545bd856d241eff15c3.png",[],{"title":7,"searchDepth":547,"depth":547,"links":548},4,[],"markdown","content:activities:zh:1971.md","content","activities/zh/1971.md","activities/zh/1971","md",1776506012095]