[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"$fsM4ex5TMpfDDpNrCjrD3HjnfS0nPiMWO0ood8v5hWL0":3,"$fAVBhJV3SZy5j-1S4UEmtlj9ytcYPxwM45-SrrpcJFD8":39,"$fFHwC0WvJBJov0guR33oAqsBBcZLVQayOatzJOlPOs4g":87,"$fsBZLSoEFv7n0656gv20WnNGgyysuc6sxP959lNI-A9s":139},{"ads":4,"bookConfig":37,"enableAds":13,"enableAdsVpn":13,"enableAdsVps":13,"userConfig":38},[5,12,19,25,31],{"coverImage":6,"description":7,"id":8,"image":9,"link":10,"title":11},"https://cdn.alltool.top/image/detail/fanai_ad.jpg","一顿饭AI 提供 ChatGPT Plus、Claude 等主流 AI 会员服务，支持支付宝直接付款，价格实在，开通简单。",7,"https://alltool.top/image/detail/chatgpt_logo.png","/blog/5a43","ChatGPT Plus低价代充｜支持支付宝",{"coverImage":13,"description":14,"id":15,"image":16,"link":17,"title":18},null,"1核1G内存30G SSD，每月1TB流量，美国节点，可以用来部署专属VPN、小型网站、博客。",2,"https://alltool.top/image/detail/cloudcone_favicon.png","https://cgfw.top/selfvpn.html","全球最便宜的VPS云服务器(13元/月)",{"coverImage":13,"description":20,"id":21,"image":22,"link":23,"title":24},"2核2G内存40G SSD云服务器，3M带宽，1个外网IPv4地址，超高性价比！",1,"https://img.alicdn.com/tfs/TB1_ZXuNcfpK1RjSZFOXXa6nFXa-32-32.ico","https://pdfs.top/blog/pt4s#ad","阿里云99元/年服务器专享购买链接",{"coverImage":13,"description":26,"id":27,"image":28,"link":29,"title":30},"免费下载电子书阅读器，支持Windows、安卓、IOS、MacOS等系统",5,"https://alltool.top/image/detail/ebook.png","https://pan.xunlei.com/s/VOLZuDZRhtvQUgIxeq96Mu9pA1?pwd=abn7","EPUB、PDF电子书阅读器下载",{"coverImage":13,"description":32,"id":33,"image":34,"link":35,"title":36},"最强PDF工具，支持编辑、签名、加密、OCR识别等25种功能。",3,"https://alltool.top/image/detail/adobe_acrobat.png","https://pdfs.top/blog/n7gq#ad","Adobe Acrobat Pro 2025绿色版","{\"bookQa\":[{\"question\":\"能否在线阅读？\",\"answer\":\"跳转到网盘下载页面，可以在线阅读，觉得不错再转存到自己的网盘。\"},{\"question\":\"如何下载？\",\"answer\":\"先将文件夹转存到自己的网盘（一定要转存整个文件夹，否则文件更新不会提醒），然后在网盘下载文件。\"},{\"question\":\"不知道下载哪种格式？\",\"answer\":\"移动端阅读推荐EPUB格式；电脑端如果阅读技术书籍，推荐PDF，阅读文学作品推荐EPUB格式。\"},{\"question\":\"个别PDF文档预览一直提示“文档打开失败”\",\"answer\":\"网盘自身问题，下载后可正常阅读。也可先转存到自己的网盘，再用客户端预览。\"},{\"question\":\"每天的下载次数是多少？\",\"answer\":\"每人每天可以下载5本不同的书籍，已经下载过的不占用下载次数。⚠️通过技术手段恶意频繁下载会被封禁！\"}]}","{\"enableResourceRequest\":true,\"enableAds\":true,\"enableAdsVpn\":false,\"enableAdsVps\":false,\"indexTopCount\":15,\"indexTopLatestCount\":15,\"indexStickCount\":10,\"indexLatestCount\":20}",{"author":40,"bookTags":41,"bookVersion":13,"categoryIds":47,"categoryNames":50,"code":53,"coverImageUrl":54,"createTime":55,"description":56,"doubanUrl":57,"files":58,"indexId":13,"isbn":66,"isbn10":13,"language":67,"name":68,"publishDate":69,"publisher":70,"pv":71,"recommendation":72,"score":73,"seoDescription":74,"seoKeywords":75,"seoTitle":76,"series":77,"tags":78,"title":83,"toc":84,"translator":77,"updateTime":85,"updateTimeDesc":86},"吴军 等",[42,43,44,45,46],"人工智能","工业AI","设备监测","故障预测","智能运维",[48,49],140,792,[51,52],"计算机","深度学习","gw18o","/image/cover/gw18o.jpg","2026-05-04 11:57:25","\u003Cp>《深度学习在复杂系统健康监测中的应用》由吴军编写，围绕深度学习在工业领域的落地应用展开。全书系统介绍复杂系统健康监测的理论基础与关键技术，包括数据采集、特征工程以及模型构建等核心环节。\u003C/p>\u003Cp>为了深入实施制造强国战略，我国正加速推动物联网、太数据、人工智能、云计算与制造业的深度融合，促进制造业向数字化、网络化和智能化转型升级。复杂系统健康监测是其中的关键环节之一。随着数据积聚、算法革新与算力提升，以裸度学习为代表的新一代人工智能技术不断取得突破性发展，为复杂系统健康监测技术突破提供新的途径。本书结合作者团队的最新研究成果，论述复杂系统健康监测的内涵、技术体系、研究现状和技术难点，总结卷积神经网络、循环神经网络、深度强化学习和深度迁移学习等深度学习的理论方法与框架，详细介绍 9 种不同的深度学习模型在复杂系统健康监测中的应用，并结合具体的应用案例进行展示.\u003C/p>\u003Cp>本书可作为高等院校机械工程、船舶与海佯工程、人工智能等相关专业本科生和研究生的参考书，也可供从事复杂系统/装备状态监测、故障预测与健康管理、预测性维护、智能运维等相关行业方向的科学研究与工程技术人员参考。\u003C/p>","https://book.douban.com/subject/36660876/",[59],{"code":60,"fileFormat":61,"fileSize":62,"needPassword":63,"netDiskType":64,"pages":65,"remark":13},"0d46c498392a415eb7a615e5dfab8bab","PDF","125.27 MB",true,"Quark",191,"9787030767998","中文","深度学习在复杂系统健康监测中的应用","2023-11-01","科学出版社",141,"\u003Cp>结合深度学习与工业场景，系统讲解复杂系统健康监测方法，适合工程师与AI从业者提升实践能力。\u003C/p>",0,"《深度学习在复杂系统健康监测中的应用》PDF免费下载，作者：吴军 等，ISBN：9787030767998，于2023年11月出版。结合深度学习与工业场景，系统讲解复杂系统健康监测方法，适合工程师与AI从业者提升实践能力。","吴军,深度学习,健康监测,故障诊断,预测性维护,工业人工智能","《深度学习在复杂系统健康监测中的应用》 - PDF下载 - 吴军 等","",[79],{"code":13,"color":80,"name":81,"sort":21,"tip":82},"success","True PDF","纸质书原始版本电子书，质量最高的PDF","《深度学习在复杂系统健康监测中的应用》PDF下载","[{\"title\": \"前言\", \"page\": 1}, {\"title\": \"第1章绪论\", \"page\": 1, \"children\": [{\"title\": \"1.1研究背景\", \"page\": 1}, {\"title\": \"1.2深度学习简介\", \"page\": 3, \"children\": [{\"title\": \"1.2.1深度学习的起源\", \"page\": 3}, {\"title\": \"1.2.2深度学习的内涵\", \"page\": 4}, {\"title\": \"1.2.3深度学习的研究现状\", \"page\": 4}, {\"title\": \"1.2.4深度学习的应用领域\", \"page\": 7}]}, {\"title\": \"1.3复杂系统健康监测简介\", \"page\": 7, \"children\": [{\"title\": \"1.3.1复杂系统健康监测的内涵\", \"page\": 7}, {\"title\": \"1.3.2复杂系统健康监测的技术体系\", \"page\": 8}, {\"title\": \"1.3.3复杂系统健康监测的研究现状\", \"page\": 10}, {\"title\": \"1.3.4复杂系统健康监测的技术难点\", \"page\": 13}]}]}, {\"title\": \"第2章深度学习理论方法\", \"page\": 15, \"children\": [{\"title\": \"2.1人工神经网络\", \"page\": 15, \"children\": [{\"title\": \"2.1.1人工神经网络的内涵\", \"page\": 15}, {\"title\": \"2.1.2人工神经网络的基本原理\", \"page\": 15}, {\"title\": \"2.1.3人工神经网络的结构\", \"page\": 16}]}, {\"title\": \"2.2深度学习模型\", \"page\": 18, \"children\": [{\"title\": \"2.2.1卷积神经网络\", \"page\": 18}, {\"title\": \"2.2.2循环神经网络\", \"page\": 19}, {\"title\": \"2.2.3深度强化学习\", \"page\": 21}, {\"title\": \"2.2.4深度迁移学习\", \"page\": 24}]}, {\"title\": \"2.3深度学习优化算法\", \"page\": 25, \"children\": [{\"title\": \"2.3.1梯度下降法\", \"page\": 25}, {\"title\": \"2.3.2动量梯度下降法\", \"page\": 27}, {\"title\": \"2.3.3AdaGrad\", \"page\": 27}, {\"title\": \"2.3.4RMSProp\", \"page\": 27}, {\"title\": \"2.3.5Adam\", \"page\": 28}]}, {\"title\": \"2.4深度学习模型评价准则\", \"page\": 29, \"children\": [{\"title\": \"2.4.1分类任务\", \"page\": 29}, {\"title\": \"2.4.2回归任务\", \"page\": 30}]}, {\"title\": \"2.5深度学习框架\", \"page\": 31, \"children\": [{\"title\": \"2.5.1TensorFlow\", \"page\": 32}, {\"title\": \"2.5.2Keras\", \"page\": 35}, {\"title\": \"2.5.3PyTorch\", \"page\": 37}]}]}, {\"title\": \"第3章基于卷积神经网络的损伤状态识别\", \"page\": 40, \"children\": [{\"title\": \"3.1问题描述\", \"page\": 40}, {\"title\": \"3.2卷积神经网络模型及其扩展\", \"page\": 41, \"children\": [{\"title\": \"3.2.1经典CNN的结构\", \"page\": 41}, {\"title\": \"3.2.2CNN结构的发展\", \"page\": 43}, {\"title\": \"3.2.3不同结构的性能对比\", \"page\": 48}]}, {\"title\": \"3.3基于卷积神经网络的损伤状态识别方法\", \"page\": 50}, {\"title\": \"3.4案例分析\", \"page\": 52, \"children\": [{\"title\": \"3.4.1案例说明\", \"page\": 52}, {\"title\": \"3.4.2数据集描述\", \"page\": 54}, {\"title\": \"3.4.3监测数据预处理\", \"page\": 55}, {\"title\": \"3.4.4时频图转换与自动标签\", \"page\": 58}, {\"title\": \"3.4.5模型训练与评估\", \"page\": 60}, {\"title\": \"3.4.6损伤定位结果与讨论\", \"page\": 62}]}]}, {\"title\": \"第4章基于区域卷积神经网络的健康状态评估\", \"page\": 64, \"children\": [{\"title\": \"4.1问题描述\", \"page\": 64}, {\"title\": \"4.2区域卷积神经网络模型及其扩展\", \"page\": 65, \"children\": [{\"title\": \"4.2.1R-CNN\", \"page\": 65}, {\"title\": \"4.2.2Fast R-CNN\", \"page\": 65}, {\"title\": \"4.2.3Faster R-CNN\", \"page\": 66}]}, {\"title\": \"4.3基于Faster R-CNN的健康状态评估方法\", \"page\": 68, \"children\": [{\"title\": \"4.3.1基于Faster R-CNN的健康状态评估流程\", \"page\": 68}, {\"title\": \"4.3.2基于Keras的健康状态评估算法实现\", \"page\": 70}]}, {\"title\": \"4.4案例分析\", \"page\": 72, \"children\": [{\"title\": \"4.4.1案例说明\", \"page\": 72}, {\"title\": \"4.4.2数据集描述\", \"page\": 72}, {\"title\": \"4.4.3模型评价指标\", \"page\": 73}, {\"title\": \"4.4.4模型训练与评估\", \"page\": 74}, {\"title\": \"4.4.5金属板样品的健康评估\", \"page\": 75}]}]}, {\"title\": \"第5章基于多融合卷积神经网络的故障诊断\", \"page\": 77, \"children\": [{\"title\": \"5.1问题描述\", \"page\": 77}, {\"title\": \"5.2多融合卷积神经网络概况\", \"page\": 78, \"children\": [{\"title\": \"5.2.1多融合卷积层\", \"page\": 78}, {\"title\": \"5.2.2池化层\", \"page\": 80}]}, {\"title\": \"5.3基于多融合卷积神经网络的故障诊断方法\", \"page\": 81, \"children\": [{\"title\": \"5.3.1基于多融合卷积神经网络的故障诊断流程\", \"page\": 81}, {\"title\": \"5.3.2数据预处理\", \"page\": 81}, {\"title\": \"5.3.3MFCC矩阵获取\", \"page\": 82}, {\"title\": \"5.3.4基于多融合卷积神经网络的故障诊断\", \"page\": 83}]}, {\"title\": \"5.4案例分析\", \"page\": 84, \"children\": [{\"title\": \"5.4.1案例说明和数据描述概述\", \"page\": 84}, {\"title\": \"5.4.2模型训练与评估\", \"page\": 86}]}]}, {\"title\": \"第6章基于局部二值卷积神经网络的复合故障诊断\", \"page\": 91, \"children\": [{\"title\": \"6.1问题描述\", \"page\": 91}, {\"title\": \"6.2局部二值卷积神经网络概况\", \"page\": 91, \"children\": [{\"title\": \"6.2.1局部二值模式\", \"page\": 91}, {\"title\": \"6.2.2LBCNN\", \"page\": 92}, {\"title\": \"6.2.3多标签分类策略\", \"page\": 94}]}, {\"title\": \"6.3基于LBCNN的复合故障诊断方法\", \"page\": 95, \"children\": [{\"title\": \"6.3.1复合故障诊断框架\", \"page\": 95}, {\"title\": \"6.3.2信号小波变换\", \"page\": 96}, {\"title\": \"6.3.3最优小波时频图选择\", \"page\": 98}, {\"title\": \"6.3.4LBCNN模型训练与诊断\", \"page\": 98}]}, {\"title\": \"6.4案例分析\", \"page\": 99, \"children\": [{\"title\": \"6.4.1案例1\", \"page\": 99}, {\"title\": \"6.4.2案例2\", \"page\": 107}]}]}, {\"title\": \"第7章基于深度子域残差自适应网络的故障诊断\", \"page\": 113, \"children\": [{\"title\": \"7.1问题描述\", \"page\": 113}, {\"title\": \"7.2深度子域残差自适应网络概况\", \"page\": 114, \"children\": [{\"title\": \"7.2.1残差网络\", \"page\": 114}, {\"title\": \"7.2.2域自适应机制\", \"page\": 117}, {\"title\": \"7.2.3深度子域残差自适应网络\", \"page\": 120}]}, {\"title\": \"7.3基于深度子域残差自适应网络的故障诊断方法\", \"page\": 122}, {\"title\": \"7.4案例分析\", \"page\": 123, \"children\": [{\"title\": \"7.4.1案例1\", \"page\": 123}, {\"title\": \"7.4.2案例2\", \"page\": 126}]}]}, {\"title\": \"第8章基于深度类别增量学习的新生故障诊断\", \"page\": 129, \"children\": [{\"title\": \"8.1问题描述\", \"page\": 129}, {\"title\": \"8.2深度类别增量学习概况\", \"page\": 129, \"children\": [{\"title\": \"8.2.1增量学习概述\", \"page\": 129}, {\"title\": \"8.2.2深度类别增量学习网络结构\", \"page\": 131}]}, {\"title\": \"8.3基于深度类别增量学习的新生故障诊断方法\", \"page\": 132, \"children\": [{\"title\": \"8.3.1基于深度类别增量学习的复杂系统故障智能诊断流程\", \"page\": 132}, {\"title\": \"8.3.2数据预处理\", \"page\": 133}, {\"title\": \"8.3.3类别增量模型更新\", \"page\": 134}, {\"title\": \"8.3.4案例样本库更新\", \"page\": 134}]}, {\"title\": \"8.4案例分析\", \"page\": 134, \"children\": [{\"title\": \"8.4.1实验数据预处理\", \"page\": 135}, {\"title\": \"8.4.2实验结果讨论\", \"page\": 135}]}]}, {\"title\": \"第9章基于深度强化学习的自适应故障诊断\", \"page\": 141, \"children\": [{\"title\": \"9.1问题描述\", \"page\": 141}, {\"title\": \"9.2深度强化学习概况\", \"page\": 142, \"children\": [{\"title\": \"9.2.1Q-learning\", \"page\": 143}, {\"title\": \"9.2.2DQN\", \"page\": 143}, {\"title\": \"9.2.3Dueling DQN\", \"page\": 144}, {\"title\": \"9.2.4Double DQN\", \"page\": 144}, {\"title\": \"9.2.5基于确定性策略搜索的强化学习方法\", \"page\": 144}, {\"title\": \"9.2.6TRPO\", \"page\": 145}, {\"title\": \"9.2.7Capsule DDQN\", \"page\": 148}]}, {\"title\": \"9.3基于Capsule DDQN的自适应故障诊断方法\", \"page\": 148, \"children\": [{\"title\": \"9.3.1Capsule DDQN关键技术\", \"page\": 148}, {\"title\": \"9.3.2基于Capsule DDQN的故障诊断流程\", \"page\": 150}]}, {\"title\": \"9.4案例分析\", \"page\": 152, \"children\": [{\"title\": \"9.4.1案例数据说明\", \"page\": 152}, {\"title\": \"9.4.2模型训练与评估\", \"page\": 153}]}]}, {\"title\": \"第10章基于深度长短期记忆神经网络的剩余使用寿命预测\", \"page\": 156, \"children\": [{\"title\": \"10.1问题描述\", \"page\": 156}, {\"title\": \"10.2深度长短期记忆神经网络概况\", \"page\": 157, \"children\": [{\"title\": \"10.2.1循环神经网络结构\", \"page\": 157}, {\"title\": \"10.2.2长短期记忆神经网络结构\", \"page\": 158}, {\"title\": \"10.2.3深度长短期记忆神经网络结构\", \"page\": 159}]}, {\"title\": \"10.3基于深度长短期记忆神经网络的剩余使用寿命预测方法\", \"page\": 160, \"children\": [{\"title\": \"10.3.1基于DLSTM模型的RUL预测流程\", \"page\": 160}, {\"title\": \"10.3.2多传感器信号数据预处理\", \"page\": 161}, {\"title\": \"10.3.3DLSTM模型训练中的参数优化\", \"page\": 162}]}, {\"title\": \"10.4案例分析\", \"page\": 163, \"children\": [{\"title\": \"10.4.1案例说明与数据集描述\", \"page\": 163}, {\"title\": \"10.4.2数据预处理\", \"page\": 166}, {\"title\": \"10.4.3模型优化与评估\", \"page\": 169}, {\"title\": \"10.4.4剩余使用寿命预测结果讨论\", \"page\": 170}]}]}, {\"title\": \"第11章基于多维度循环神经网络的剩余使用寿命预测\", \"page\": 174, \"children\": [{\"title\": \"11.1问题描述\", \"page\": 174}, {\"title\": \"11.2多维度循环神经网络概况\", \"page\": 174, \"children\": [{\"title\": \"11.2.1门控循环单元网络结构\", \"page\": 175}, {\"title\": \"11.2.2双向循环神经网络结构\", \"page\": 175}, {\"title\": \"11.2.3多维度循环神经网络结构\", \"page\": 177}]}, {\"title\": \"11.3基于MDRNN的系统RUL预测方法\", \"page\": 179}, {\"title\": \"11.4案例分析\", \"page\": 181}]}, {\"title\": \"参考文献\", \"page\": 186}]","2026-08-23 17:08:30","25天前",[88,97,106,115,123,132],{"author":89,"categories":90,"code":91,"coverImageUrl":92,"description":13,"name":93,"publishDate":94,"pv":95,"score":96},"王海良",[51,52],"odbvr","/image/cover/odbvr.jpg","智能问答与深度学习","2019-01-01 00:00:00",90,6.6,{"author":98,"categories":99,"code":101,"coverImageUrl":102,"description":13,"name":103,"publishDate":104,"pv":105,"score":73},"严伯钧",[51,100],"人工智能(AI)","vhew2","/image/cover/vhew2.jpg","天下一知","2026-01-01 00:00:00",142,{"author":107,"categories":108,"code":109,"coverImageUrl":110,"description":13,"name":111,"publishDate":112,"pv":113,"score":114},"[加] 于非",[51,100],"txaeq","/image/cover/txaeq.jpg","智能简史：从大爆炸到元宇宙","2022-05-01 00:00:00",135,7.1,{"author":116,"categories":117,"code":118,"coverImageUrl":119,"description":13,"name":120,"publishDate":121,"pv":122,"score":73},"[美] 爱德华·拉夫（Edward Raff）",[51,52],"nq8qr","/image/cover/nq8qr.jpg","深度学习精粹与PyTorch实践","2024-08-01 00:00:00",228,{"author":124,"categories":125,"code":127,"coverImageUrl":128,"description":13,"name":129,"publishDate":130,"pv":131,"score":73},"王宇龙",[51,126],"机器学习","y4gbe","/image/cover/y4gbe.jpg","PyTorch高级机器学习实战","2023-02-01 00:00:00",118,{"author":133,"categories":134,"code":135,"coverImageUrl":136,"description":13,"name":137,"publishDate":104,"pv":138,"score":73},"邱锡鹏",[51,100],"0tar8","/image/cover/0tar8.jpg","大模型与智能体",195,[]]