{"currentpage":1,"firstResult":0,"maxresult":10,"pagecode":5,"pageindex":{"endPagecode":5,"startPagecode":1},"records":[{"abstractinfo":"以4200 mm轧机轧制71块钢板的实测数据为基础，利用Matlab<span style=\"color:red\">神经网络</span>工具箱，分别建立了轧制变形区的<span style=\"color:red\">应力</span><span style=\"color:red\">状态</span><span style=\"color:red\">系数</span>与轧前厚度、轧后厚度及轧辊直径对应关系的Elman<span style=\"color:red\">神经网络</span>预测<span style=\"color:red\">模型</span>和RBF<span style=\"color:red\">神经网络</span>预测<span style=\"color:red\">模型</span>。结果表明，所建立的两种<span style=\"color:red\">网络</span><span style=\"color:red\">模型</span>均建立了金属<span style=\"color:red\">应力</span><span style=\"color:red\">状态</span><span style=\"color:red\">系数</span>输入和输出关系，RBF<span style=\"color:red\">神经网络</span><span style=\"color:red\">模型</span>比Elman<span style=\"color:red\">网络</span><span style=\"color:red\">模型</span>数据稳定，性能更优，实现了与实测结果的高度拟合。并得出不同轧辊直径对<span style=\"color:red\">神经网络</span><span style=\"color:red\">模型</span>精度的<span style=\"color:red\">影响</span>规律，对轧制工艺规程的制定提出了合理建议。","authors":[{"authorName":"徐如松","id":"9df3fc95-44b1-430d-a21e-8ae98b59899f","originalAuthorName":"徐如松"},{"authorName":"孟令启","id":"14bb533c-e2d9-48ba-8b4d-2db7cb49c727","originalAuthorName":"孟令启"}],"categoryName":"|","doi":"","fpage":"55","id":"b2a3e4ef-9780-4445-9b96-05705ac05087","issue":"5","journal":{"abbrevTitle":"GTYJXB","coverImgSrc":"journal/img/cover/GTYJXB.jpg","id":"30","issnPpub":"1001-0963","publisherId":"GTYJXB","title":"钢铁研究学报"},"keywords":[{"id":"8d18c41a-5e6e-4cce-86f4-0eead09de347","keyword":"<span style=\"color:red\">应力</span><span style=\"color:red\">状态</span><span style=\"color:red\">影响</span><span style=\"color:red\">系数</span>;<span style=\"color:red\">神经网络</span>;<span style=\"color:red\">模型</span>","originalKeyword":"应力状态影响系数;神经网络;模型"}],"language":"zh","publisherId":"1001-0963_2009_5_10","title":"基于<span style=\"color:red\">神经网络</span>的金属<span style=\"color:red\">应力</span><span style=\"color:red\">状态</span><span style=\"color:red\">系数模型</span>","volume":"21","year":"2009"},{"abstractinfo":"以4200 mm轧机轧制71块钢板的实测数据为基础,利用Matlab<span style=\"color:red\">神经网络</span>工具箱,分别建立了轧制变形区的<span style=\"color:red\">应力</span><span style=\"color:red\">状态</span><span style=\"color:red\">系数</span>与轧前厚度、轧后厚度及轧辊直径对应关系的Elman<span style=\"color:red\">神经网络</span>预测<span style=\"color:red\">模型</span>和RBF<span style=\"color:red\">神经网络</span>预测<span style=\"color:red\">模型</span>.结果表明,所建立的两种<span style=\"color:red\">网络</span><span style=\"color:red\">模型</span>均建立了金属<span style=\"color:red\">应力</span><span style=\"color:red\">状态</span><span style=\"color:red\">系数</span>输入和输出关系,RBF<span style=\"color:red\">神经网络</span><span style=\"color:red\">模型</span>比Elman<span style=\"color:red\">网络</span><span style=\"color:red\">模型</span>数据稳定,性能更优,实现了与实测结果的高度拟合.并得出不同轧辊直径对<span style=\"color:red\">神经网络</span><span style=\"color:red\">模型</span>精度的<span style=\"color:red\">影响</span>规律,对轧制工艺规程的制定提出了合理建议.","authors":[{"authorName":"徐如松","id":"acb55e8c-8825-4cc1-85c6-1343e4b4725e","originalAuthorName":"徐如松"},{"authorName":"孟令启","id":"80251291-4874-45c8-b54f-283d50d51977","originalAuthorName":"孟令启"}],"doi":"","fpage":"55","id":"22eef291-d0e4-4a26-b2e1-66fc2d88d2ab","issue":"5","journal":{"abbrevTitle":"GTYJXB","coverImgSrc":"journal/img/cover/GTYJXB.jpg","id":"30","issnPpub":"1001-0963","publisherId":"GTYJXB","title":"钢铁研究学报"},"keywords":[{"id":"26427d76-f3ee-4edf-9b9b-98d6209782fb","keyword":"<span style=\"color:red\">应力</span><span style=\"color:red\">状态</span><span style=\"color:red\">影响</span><span style=\"color:red\">系数</span>","originalKeyword":"应力状态影响系数"},{"id":"6416b5e4-08ab-49d4-9c72-88db946dc91a","keyword":"<span style=\"color:red\">神经网络</span>","originalKeyword":"神经网络"},{"id":"2711891c-4fcf-431f-b296-76f9b84572c0","keyword":"<span style=\"color:red\">模型</span>","originalKeyword":"模型"}],"language":"zh","publisherId":"gtyjxb200905013","title":"基于<span style=\"color:red\">神经网络</span>的金属<span style=\"color:red\">应力</span><span style=\"color:red\">状态</span><span style=\"color:red\">系数模型</span>","volume":"21","year":"2009"},{"abstractinfo":"利用<span style=\"color:red\">神经网络</span>方法确定灵敏度<span style=\"color:red\">系数</span>,建立了冷轧厚度预测<span style=\"color:red\">模型</span>.该<span style=\"color:red\">模型</span>能很好地克服外界干扰或参数扰动,是一种能确定厚度控制参数的算法,通过一个单机架上的应用实例表明该方案具有好的应用前途.","authors":[{"authorName":"王春刚","id":"8019dc59-f411-4cc7-9254-d11c2166882b","originalAuthorName":"王春刚"},{"authorName":"方一鸣","id":"a3b3305c-7212-4fe5-a09f-ce75a1696d46","originalAuthorName":"方一鸣"},{"authorName":"范之远","id":"b02a7716-1024-483e-9dc6-44254932588b","originalAuthorName":"范之远"},{"authorName":"高文达","id":"c196d524-5475-4ee1-9610-9870e740f560","originalAuthorName":"高文达"}],"doi":"","fpage":"45","id":"464e65cd-953c-4c8a-9911-25a080e55c42","issue":"2","journal":{"abbrevTitle":"GTYJ","coverImgSrc":"journal/img/cover/GTYJ.jpg","id":"29","issnPpub":"1001-1447","publisherId":"GTYJ","title":"钢铁研究"},"keywords":[{"id":"4626b2cc-8ddc-4a7e-92a1-ced9d1ebcb17","keyword":"BP<span style=\"color:red\">神经网络</span>","originalKeyword":"BP神经网络"},{"id":"004aa3e9-8322-4544-82c5-6174cf2d3207","keyword":"灵敏度<span style=\"color:red\">系数</span>","originalKeyword":"灵敏度系数"},{"id":"847e79d0-ef93-4037-86e8-f7637f604ce3","keyword":"厚度预测<span style=\"color:red\">模型</span>","originalKeyword":"厚度预测模型"},{"id":"61d84f5a-4fa5-4a1b-b437-81afe9560815","keyword":"相关<span style=\"color:red\">系数</span>","originalKeyword":"相关系数"}],"language":"zh","publisherId":"gtyj200902013","title":"用<span style=\"color:red\">神经网络</span>方法确定冷轧厚度预测<span style=\"color:red\">模型</span>灵敏度<span style=\"color:red\">系数</span>","volume":"37","year":"2009"},{"abstractinfo":"在Geeble-1500热模拟机上对7055铝合金进行热压缩试验,基于热压缩试验数据,建立流变<span style=\"color:red\">应力</span>的反向传播(BP)<span style=\"color:red\">神经网络</span>预测<span style=\"color:red\">模型</span>和加工图.结果表明:用人工<span style=\"color:red\">神经网络</span>能更精确地预测热压缩过程中的流变<span style=\"color:red\">应力</span>,预测精度明显高于线性经验公式的;通过预测<span style=\"color:red\">模型</span>可以获得样本数据值范围内的非样本数据变形条件下的流变<span style=\"color:red\">应力</span>,其预测结果充分反映该合金的高温变形特征;在本实验条件下,7055铝合金在高温变形时存在一个失稳区,即变形温度在实验温度范围内应变速率为0.025 s-1以上的区域;在375～425 ℃的范围内,应变速率小于0.001 s-1的区域,最大功率耗散<span style=\"color:red\">系数</span>为0.45;EBSD技术分析表明在安全区发生部分动态再结晶.利用加工图确定了热变形时的流变失稳区, 并且获得了试验参数范围内热变形的最佳工艺参数, 其热加工温度为350-430 ℃低应变速率区.","authors":[{"authorName":"闫亮明","id":"d02feeca-572f-45ef-8ad6-f471bba5454f","originalAuthorName":"闫亮明"},{"authorName":"沈健","id":"c3db81e5-4bd4-4e6c-bf10-b683c29ccc6b","originalAuthorName":"沈健"},{"authorName":"李周兵","id":"1cb761b3-5ca3-4b2c-89b8-9af0cc68eb21","originalAuthorName":"李周兵"},{"authorName":"李俊鹏","id":"77184f08-7860-4bee-ac6a-75a22ebe7d11","originalAuthorName":"李俊鹏"},{"authorName":"闫晓东","id":"284fe9c3-60d9-4878-a020-91ef0612c13c","originalAuthorName":"闫晓东"},{"authorName":"毛柏平","id":"49534d9e-ee34-4f47-bbbe-f8ce1ee4ada0","originalAuthorName":"毛柏平"}],"doi":"","fpage":"1296","id":"ffacdccd-babb-48f0-a7dd-f2291ea3f83c","issue":"7","journal":{"abbrevTitle":"ZGYSJSXB","coverImgSrc":"journal/img/cover/ZGYSJSXB.jpg","id":"88","issnPpub":"1004-0609","publisherId":"ZGYSJSXB","title":"中国有色金属学报"},"keywords":[{"id":"8c8cdb09-40dc-4908-879a-c3fc59f895f2","keyword":"7055铝合金","originalKeyword":"7055铝合金"},{"id":"9c3503fc-ebc8-44f8-8248-494bb692043a","keyword":"流变<span style=\"color:red\">应力</span>","originalKeyword":"流变应力"},{"id":"41fa2092-df27-48eb-a235-af8ace08a3ea","keyword":"热变形","originalKeyword":"热变形"},{"id":"bcb3e6d5-dbe8-437e-b303-23bddbf28cf3","keyword":"<span style=\"color:red\">神经网络</span>","originalKeyword":"神经网络"},{"id":"143c32c5-edec-48fc-ae8e-589263cf6206","keyword":"加工图","originalKeyword":"加工图"}],"language":"zh","publisherId":"zgysjsxb201007008","title":"基于<span style=\"color:red\">神经网络</span>的7055铝合金流变<span style=\"color:red\">应力</span><span style=\"color:red\">模型</span>和加工图","volume":"20","year":"2010"},{"abstractinfo":"通过Zr-2合金在变形温度为750,800℃,变形速率为0.01,1,10 s-1,变形程度为50%,65%的热压缩试验获得数据,采用模糊<span style=\"color:red\">神经网络</span>方法建立Zr-2合金的晶粒尺寸及流变<span style=\"color:red\">应力</span><span style=\"color:red\">模型</span>.<span style=\"color:red\">模型</span>的输入参数包括变形温度、变形程度、变形速率等热加工参数,<span style=\"color:red\">模型</span>的输出为晶粒尺寸和流变<span style=\"color:red\">应力</span>.结果表明,该<span style=\"color:red\">模型</span>避免了传统经验回归拟合复杂的数学公式计算,是简单而精确的建模方法,可用于优化热加工参数.","authors":[{"authorName":"林国庆","id":"71bdc767-354b-4c74-bf69-3b7028dabf4d","originalAuthorName":"林国庆"},{"authorName":"李颖","id":"e6a0b7d8-5067-4906-a65b-d0b95b0bba54","originalAuthorName":"李颖"},{"authorName":"王新梅","id":"f012acc1-0c4d-46d2-b26c-3efd52aa4a88","originalAuthorName":"王新梅"}],"doi":"","fpage":"464","id":"1fa1a828-e8d6-48e7-99f6-e7c7539614fb","issue":"z1","journal":{"abbrevTitle":"XYJSCLYGC","coverImgSrc":"journal/img/cover/XYJSCLYGC.jpg","id":"69","issnPpub":"1002-185X","publisherId":"XYJSCLYGC","title":"稀有金属材料与工程"},"keywords":[{"id":"3ddcc34e-a056-4935-9878-4a59bddcf262","keyword":"模糊<span style=\"color:red\">神经网络</span>","originalKeyword":"模糊神经网络"},{"id":"3c4796d7-cebd-4d8e-8fef-9d45315a9ab3","keyword":"晶粒尺寸","originalKeyword":"晶粒尺寸"},{"id":"47b03277-efae-4b72-acbe-6890ad827bf7","keyword":"流变<span style=\"color:red\">应力</span>","originalKeyword":"流变应力"}],"language":"zh","publisherId":"xyjsclygc2009z1105","title":"基于模糊<span style=\"color:red\">神经网络</span>的Zr-2合金晶粒尺寸及流变<span style=\"color:red\">应力</span><span style=\"color:red\">模型</span>","volume":"38","year":"2009"},{"abstractinfo":"轧制过程中，针对4200轧机在轧件宽展变化自动预测和控制，分析了轧制过程中宽展变化的<span style=\"color:red\">影响</span>因素。在<span style=\"color:red\">神经网络</span>技术和现场实测数据的基础上，利用Matlab人工<span style=\"color:red\">神经网络</span>工具箱，应用GRNN广义回归<span style=\"color:red\">神经网络</span>建立宽展变化预测<span style=\"color:red\">模型</span>来提高轧制宽展变化预测的精度。结果表明，该方法建立的<span style=\"color:red\">模型</span>可以实现对宽展变化的预测，其预测精度有较大提高。","authors":[{"authorName":"孟令启","id":"0df6bc79-b808-45a1-813c-06824e975af3","originalAuthorName":"孟令启"},{"authorName":"孟梦","id":"7c6ec060-21a0-49d6-b8ae-f6e1d5a9a9f5","originalAuthorName":"孟梦"}],"categoryName":"|","doi":"","fpage":"23","id":"493171aa-6021-4a61-ba7d-c2630f2c623b","issue":"3","journal":{"abbrevTitle":"GTYJXB","coverImgSrc":"journal/img/cover/GTYJXB.jpg","id":"30","issnPpub":"1001-0963","publisherId":"GTYJXB","title":"钢铁研究学报"},"keywords":[{"id":"8d329922-578e-41f6-9d9b-8495f3e98789","keyword":"中厚板轧机;宽展;GRNN<span style=\"color:red\">神经网络</span>","originalKeyword":"中厚板轧机;宽展;GRNN神经网络"}],"language":"zh","publisherId":"1001-0963_2008_3_1","title":"基于GRNN<span style=\"color:red\">神经网络</span>的4200轧机宽展<span style=\"color:red\">模型</span>","volume":"20","year":"2008"},{"abstractinfo":"轧制过程中,针对4200轧机在轧件宽展变化自动预测和控制,分析了轧制过程中宽展变化的<span style=\"color:red\">影响</span>因素.在<span style=\"color:red\">神经网络</span>技术和现场实测数据的基础上,利用Matlab人工<span style=\"color:red\">神经网络</span>工具箱,应用GRNN广义回归<span style=\"color:red\">神经网络</span>建立宽展变化预测<span style=\"color:red\">模型</span>来提高轧制宽展变化预测的精度.结果表明,该方法建立的<span style=\"color:red\">模型</span>可以实现对宽展变化的预测,其预测精度有较大提高.","authors":[{"authorName":"孟令启","id":"1646277a-165a-43e6-a686-c5f2801532f6","originalAuthorName":"孟令启"},{"authorName":"孟梦","id":"6b81b794-74a8-446a-a6f3-4344fb8b50f5","originalAuthorName":"孟梦"}],"doi":"","fpage":"23","id":"6f67305b-2592-4089-848e-6e2f3346da50","issue":"3","journal":{"abbrevTitle":"GTYJXB","coverImgSrc":"journal/img/cover/GTYJXB.jpg","id":"30","issnPpub":"1001-0963","publisherId":"GTYJXB","title":"钢铁研究学报"},"keywords":[{"id":"a5ee9aec-dfbf-47e5-90e2-d0ca7e30b196","keyword":"中厚板轧机","originalKeyword":"中厚板轧机"},{"id":"4b9c5263-90bf-4a4a-8ab0-9e586cec6a05","keyword":"宽展","originalKeyword":"宽展"},{"id":"b8ee4990-0dd4-489f-ab28-33043c3fd9aa","keyword":"GRNN<span style=\"color:red\">神经网络</span>","originalKeyword":"GRNN神经网络"}],"language":"zh","publisherId":"gtyjxb200803006","title":"基于GRNN<span style=\"color:red\">神经网络</span>的4200轧机宽展<span style=\"color:red\">模型</span>","volume":"20","year":"2008"},{"abstractinfo":"基于<span style=\"color:red\">神经网络</span>原理，对微合金钢热轧控制参数的选取进行了研究.首先，制定了一套获取样本数据的实验方案.该方案利用Gleeble-1500热力模拟机提取了轧制温度、应变量、应变速率和相应的<span style=\"color:red\">应力</span>应变曲线，并通过显微观察获取了实验后样品断面的奥氏体晶粒尺寸.通过归一化把实验所得数据进行必要的处理.采用BP算法训练<span style=\"color:red\">网络</span>，对热轧控制参数（轧制温度、应变量、应变速率）和描述微合金钢组织性能的参数（奥氏体晶粒尺寸及流变<span style=\"color:red\">应力</span>）之间的映射关系进行了函数逼近，建立了奥氏体晶粒尺寸及流变<span style=\"color:red\">应力</span><span style=\"color:red\">神经网络</span><span style=\"color:red\">模型</span>.实践证明，将该<span style=\"color:red\">神经网络</span><span style=\"color:red\">模型</span>运用于热轧控制预报,提高了预测精度并取得较好的效果.","authors":[{"authorName":"孙雷剑","id":"8b4d7f8c-0d1f-4686-b62a-160eb22d141a","originalAuthorName":"孙雷剑"},{"authorName":"牛济泰","id":"0eceb4be-a71a-43b3-910d-65c10a83f93f","originalAuthorName":"牛济泰"},{"authorName":"孟庆昌","id":"b1bb52ba-6c37-489e-9ae4-b0e91fa95482","originalAuthorName":"孟庆昌"}],"doi":"10.3969/j.issn.1005-0299.2000.04.004","fpage":"16","id":"56afb655-c1d5-41af-8a3c-674676f317f0","issue":"4","journal":{"abbrevTitle":"CLKXYGY","coverImgSrc":"journal/img/cover/CLKXYGY.jpg","id":"14","issnPpub":"1005-0299","publisherId":"CLKXYGY","title":"材料科学与工艺"},"keywords":[{"id":"eb33e0ca-8892-420d-8aa3-14cd673dec5f","keyword":"微合金钢","originalKeyword":"微合金钢"},{"id":"b6e3ae9b-6150-4252-a236-ebbbac506094","keyword":"奥氏体晶粒尺寸","originalKeyword":"奥氏体晶粒尺寸"},{"id":"022ec565-3693-4c0f-85ca-34bbd69bcd5d","keyword":"流变<span style=\"color:red\">应力</span>","originalKeyword":"流变应力"},{"id":"892d4c1c-dab6-4dd2-8325-4e6347bf0a75","keyword":"<span style=\"color:red\">神经网络</span>","originalKeyword":"神经网络"},{"id":"70a7f606-8963-4aac-af8f-3167d6ba0c98","keyword":"BP算法","originalKeyword":"BP算法"}],"language":"zh","publisherId":"clkxygy200004004","title":"基于<span style=\"color:red\">神经网络</span>的微合金钢热轧奥氏体晶粒尺寸及流变<span style=\"color:red\">应力</span><span style=\"color:red\">模型</span>的研究","volume":"8","year":"2000"},{"abstractinfo":"在实验数据的基础上,用人工<span style=\"color:red\">神经网络</span>建立高Co-Ni二次硬化钢的力学性能预测<span style=\"color:red\">模型</span>,根据<span style=\"color:red\">网络</span>的预测结果讨论了微量元素Nb、Ti对钢力学性能的<span style=\"color:red\">影响</span>,结果证明<span style=\"color:red\">网络</span>的预测同实验基本一致.可见人工<span style=\"color:red\">神经网络</span>在材料设计方面有广阔的应用前景,它为高性能材料设计提供了新的手段.","authors":[{"authorName":"刘贵立","id":"534691cb-fe59-43a7-960f-22cf35bc8e5e","originalAuthorName":"刘贵立"},{"authorName":"张国英","id":"94e562b9-d9b1-44ea-a400-05bd08e6f99c","originalAuthorName":"张国英"},{"authorName":"曾梅光","id":"9c93f95d-6f9b-4d88-b847-71562209d2e8","originalAuthorName":"曾梅光"}],"doi":"10.3969/j.issn.1001-1447.2000.01.013","fpage":"48","id":"f2fb4e93-d382-4ca2-b9cf-5c6651a7eb37","issue":"1","journal":{"abbrevTitle":"GTYJ","coverImgSrc":"journal/img/cover/GTYJ.jpg","id":"29","issnPpub":"1001-1447","publisherId":"GTYJ","title":"钢铁研究"},"keywords":[{"id":"25f1ac80-ea6f-4876-9ff2-d8244087060f","keyword":"二次硬化钢","originalKeyword":"二次硬化钢"},{"id":"d9ae2bb1-e602-4e67-b24d-c772f63cc87a","keyword":"人工<span style=\"color:red\">神经网络</span>","originalKeyword":"人工神经网络"},{"id":"17a002fa-01a4-48bd-97e0-10160456fe2c","keyword":"材料力学性能","originalKeyword":"材料力学性能"},{"id":"fb26ba2a-5326-4360-a5ff-4f24aa4e5795","keyword":"微量元素","originalKeyword":"微量元素"}],"language":"zh","publisherId":"gtyj200001013","title":"用人工<span style=\"color:red\">神经网络</span><span style=\"color:red\">模型</span>研究微量元素对钢力学性能的<span style=\"color:red\">影响</span>","volume":"","year":"2000"},{"abstractinfo":"设计2124铝合金单向拉伸时效成形试验(<span style=\"color:red\">应力</span>松弛试验),研究试验件单向拉伸时.初始<span style=\"color:red\">应力</span>水平(σ0)、时效温度(T)、保温时间(t)3因素对试验件<span style=\"color:red\">应力</span>松弛量(p/%)的<span style=\"color:red\">影响</span>.将试验数据作为训练样本.建立单拉<span style=\"color:red\">应力</span>松弛试验BP<span style=\"color:red\">神经网络</span><span style=\"color:red\">模型</span>以预测不同工艺条件下的<span style=\"color:red\">应力</span>松弛量,并通过追加试验数据对该<span style=\"color:red\">神经网络</span><span style=\"color:red\">模型</span>进行检验.检验结果表明:应用该<span style=\"color:red\">神经网络</span><span style=\"color:red\">模型</span>来预测不同因素下试件<span style=\"color:red\">应力</span>松弛量精度满足试验预期要求.","authors":[{"authorName":"甘忠","id":"a0de0958-7325-4380-b81f-0c0461f4dfef","originalAuthorName":"甘忠"},{"authorName":"成武冬","id":"a9ec638a-8794-4dbc-9104-5eebb763e577","originalAuthorName":"成武冬"},{"authorName":"许旭东","id":"64cfa227-a80c-4dac-ac6a-d5ebcd0cfef9","originalAuthorName":"许旭东"},{"authorName":"潘栋杰","id":"c15f093d-1cb6-42c3-a3c2-afb1e00163c8","originalAuthorName":"潘栋杰"}],"doi":"10.3969/j.issn.1004-244X.2009.02.011","fpage":"35","id":"9ff69ec3-0e44-494d-b4ba-17a536877575","issue":"2","journal":{"abbrevTitle":"BQCLKXYGC","coverImgSrc":"journal/img/cover/BQCLKXYGC.jpg","id":"4","issnPpub":"1004-244X","publisherId":"BQCLKXYGC","title":"兵器材料科学与工程   "},"keywords":[{"id":"0040a62d-d58d-4b26-a6e1-514f67314a06","keyword":"时效成形","originalKeyword":"时效成形"},{"id":"f8d64727-8dcc-4667-b773-28cb0586a52d","keyword":"铝合金","originalKeyword":"铝合金"},{"id":"66522e60-7445-4a6b-8259-82ab16565e6b","keyword":"<span style=\"color:red\">应力</span>松弛","originalKeyword":"应力松弛"},{"id":"ffafb792-3837-402c-9c49-9e84b556564b","keyword":"正交试验","originalKeyword":"正交试验"},{"id":"fef880bc-52a1-4563-89c8-ab3ca6d1fe4d","keyword":"BP<span style=\"color:red\">神经网络</span>","originalKeyword":"BP神经网络"}],"language":"zh","publisherId":"bqclkxygc200902011","title":"BP<span style=\"color:red\">神经网络</span>预测铝合金<span style=\"color:red\">应力</span>松弛量研究","volume":"32","year":"2009"}],"totalpage":11267,"totalrecord":112662}