{"currentpage":1,"firstResult":0,"maxresult":10,"pagecode":5,"pageindex":{"endPagecode":5,"startPagecode":1},"records":[{"abstractinfo":"对生产中常见的低碳铝镇静钢冷轧板孔洞<span style=\"color:red\">缺陷</span><span style=\"color:red\">特征</span>进行了宏观和微观分析。结果表明：孔洞大致可分为三大类，正常拉裂类孔洞主要与基板中的夹杂有关；疤块孔洞与坑状孔洞为钢基掉块或异物压入基板形成，其它类孔洞形成主要与轧制工艺过程相关。","authors":[{"authorName":"方淑芳","id":"468f706e-1d26-46a3-bd60-a3ffe8017745","originalAuthorName":"方淑芳"},{"authorName":"邱涛","id":"5651b369-b850-4f89-aa24-f9b80e892661","originalAuthorName":"邱涛"},{"authorName":"曾庆江","id":"134d9327-7581-41dd-9664-14f77dc779bb","originalAuthorName":"曾庆江"},{"authorName":"陈兴元","id":"c36b1692-59a8-4f4a-97c7-85e6d8db3bf1","originalAuthorName":"陈兴元"},{"authorName":"王政","id":"62ac8ae6-40e2-4dc2-94ae-1a5befea8720","originalAuthorName":"王政"},{"authorName":"周渝","id":"2fe203bf-30fd-4e28-82da-4dba63f0a06a","originalAuthorName":"周渝"}],"doi":"10.3969/j.issn.1004-7638.2001.01.008","fpage":"40","id":"55f8ebd6-3b93-4d42-85ad-514460ae2d22","issue":"1","journal":{"abbrevTitle":"GTFT","coverImgSrc":"journal/img/cover/gtft1.jpg","id":"28","issnPpub":"1004-7638","publisherId":"GTFT","title":"钢铁钒钛"},"keywords":[{"id":"13be31a7-b360-4e70-abe7-d55f4b2cf2ce","keyword":"低碳铝镇静钢","originalKeyword":"低碳铝镇静钢"},{"id":"e7ba9d06-d909-4a9e-899e-1aec5ac5d341","keyword":"冷轧板","originalKeyword":"冷轧板"},{"id":"3f47ec8a-5d26-4bbc-ab46-5254cf3da55c","keyword":"<span style=\"color:red\">缺陷</span><span style=\"color:red\">特征</span>","originalKeyword":"缺陷特征"}],"language":"zh","publisherId":"gtft200101008","title":"低碳铝镇静钢冷轧板中孔洞<span style=\"color:red\">缺陷</span><span style=\"color:red\">特征</span>分析","volume":"22","year":"2001"},{"abstractinfo":"为了自动获得最具区分力的多维融合<span style=\"color:red\">特征</span>,提出了改进的ReliefF算法对带钢多维混合<span style=\"color:red\">特征</span>进行自动评估选择.针对ReliefF算法不能去除冗余<span style=\"color:red\">特征</span>的缺点,引入最大信息压缩准则去除冗余<span style=\"color:red\">特征</span>.在此基础上,采用遗传神经网络建立带钢<span style=\"color:red\">缺陷</span>识别的知识库,遗传算法可以自主地辨识最小的包含最优解的搜索空间,再由BP算法按负梯度方向进行权值及阈值的修正.研究结果表明:改进ReliefF算法为后续分类识别提供了最优的<span style=\"color:red\">特征</span>向量,减少了数据的运算量和存储量;遗传神经网络算法获得了在满足准确性前提下更高网络识别<span style=\"color:red\">缺陷</span>的效率.","authors":[{"authorName":"韩英莉","id":"9e79a8c5-930c-4e36-9bfc-0e5ca4e1b00d","originalAuthorName":"韩英莉"}],"doi":"10.13228/j.boyuan.issn1001-0963.20140168","fpage":"29","id":"292227f5-bd97-4cf9-a07b-ba76990885e1","issue":"6","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":"79bf1d0d-16f3-4a98-a6b6-9bf4e1bbd49b","keyword":"带钢表面<span style=\"color:red\">缺陷</span>","originalKeyword":"带钢表面缺陷"},{"id":"db9154fa-8328-4a24-810b-ae752ac2cfe3","keyword":"<span style=\"color:red\">特征</span>提取","originalKeyword":"特征提取"},{"id":"ab05b59a-3c7b-4168-ba3a-cdd8454bd621","keyword":"分类识别","originalKeyword":"分类识别"},{"id":"0edb09d3-3dc8-4c1c-aece-6cd1e51ae6a1","keyword":"人工神经网络","originalKeyword":"人工神经网络"}],"language":"zh","publisherId":"gtyjxb201506006","title":"带钢表面<span style=\"color:red\">缺陷</span>多维混合<span style=\"color:red\">特征</span>提取及识别","volume":"27","year":"2015"},{"abstractinfo":"为研究电缆终端主绝缘含气隙<span style=\"color:red\">缺陷</span>下的局部放电(PD)及<span style=\"color:red\">缺陷</span>表面的形貌<span style=\"color:red\">特征</span>，通过在10 kV电缆终端上制作典型的气隙<span style=\"color:red\">缺陷</span>，利用电缆附件电热老化平台模拟终端的实际运行工况并加速老化，利用罗戈夫基线圈传感器提取终端在不同老化时刻下的PD数据，并用扫描电镜（SEM）对气隙<span style=\"color:red\">缺陷</span>的表面形貌<span style=\"color:red\">特征</span>进行观察。结合气隙<span style=\"color:red\">缺陷</span>内部的电场分布进一步分析终端PD的发展规律。结果表明：电缆终端的PD及气隙<span style=\"color:red\">缺陷</span>表面的形貌<span style=\"color:red\">特征</span>在不同老化时刻下呈现明显差异，<span style=\"color:red\">缺陷</span>表面XLPE的碳化过程提高了气隙<span style=\"color:red\">缺陷</span>的表面电导率，加快了<span style=\"color:red\">缺陷</span>表面电荷的耗散速度。","authors":[{"authorName":"吴科","id":"ac84b72e-f3ea-472d-8656-be031319959f","originalAuthorName":"吴科"},{"authorName":"马春亮","id":"c20d03a6-d4cc-42ee-a778-ddcf87f81526","originalAuthorName":"马春亮"},{"authorName":"周凯","id":"b67a9c6e-e63c-4cef-8dae-32c3d95e0bd0","originalAuthorName":"周凯"},{"authorName":"万利","id":"213363d2-43ac-43da-a23b-8136afdaf370","originalAuthorName":"万利"}],"doi":"","fpage":"38","id":"16ef9d40-1490-4ae3-844a-eedc68cba107","issue":"7","journal":{"abbrevTitle":"JYCL","coverImgSrc":"journal/img/cover/JYCL.jpg","id":"50","issnPpub":"1009-9239","publisherId":"JYCL","title":"绝缘材料"},"keywords":[{"id":"b96b07f4-7790-455b-9b25-ea85e5712172","keyword":"电缆终端","originalKeyword":"电缆终端"},{"id":"c94bde87-a06b-489e-a6fc-1aebe9b6564d","keyword":"气隙<span style=\"color:red\">缺陷</span>","originalKeyword":"气隙缺陷"},{"id":"2468a55e-c443-4768-a2d5-9b3f2c2fb823","keyword":"局部放电","originalKeyword":"局部放电"},{"id":"80477e27-7aee-42ff-9dc1-fb45d09e16e0","keyword":"电场分布","originalKeyword":"电场分布"},{"id":"fe19d134-7a7f-4775-a6eb-e48de015db55","keyword":"表面电导率","originalKeyword":"表面电导率"}],"language":"zh","publisherId":"jycltx201507008","title":"10 kV电缆终端绝缘气隙<span style=\"color:red\">缺陷</span>的局部放电及<span style=\"color:red\">缺陷</span>表面烧蚀<span style=\"color:red\">特征</span>","volume":"","year":"2015"},{"abstractinfo":"推导出一维掺杂声子晶体的转移矩阵,研究了一维掺杂声子晶体的<span style=\"color:red\">缺陷</span>模特性.结果表明一维声子晶体掺杂后会在禁带中心处出现<span style=\"color:red\">缺陷</span>模.<span style=\"color:red\">缺陷</span>模随杂质厚度的变化呈周期性地出现,在同一周期内,<span style=\"color:red\">缺陷</span>模的频率随杂质厚度增加近似呈线性减小,但<span style=\"color:red\">缺陷</span>模的半高宽近似不变.<span style=\"color:red\">缺陷</span>模的半高宽随两介质声阻抗的差值的减少而增大.","authors":[{"authorName":"刘启能","id":"ccf9cb9d-e67a-4265-8395-c746a11dd896","originalAuthorName":"刘启能"}],"doi":"","fpage":"87","id":"eafdd479-071a-4b9a-b7a7-04f298c27948","issue":"Z2","journal":{"abbrevTitle":"CLDB","coverImgSrc":"journal/img/cover/CLDB.jpg","id":"8","issnPpub":"1005-023X","publisherId":"CLDB","title":"材料导报"},"keywords":[{"id":"49026211-d926-4fb0-b561-9f36a5ae6112","keyword":"声子晶体","originalKeyword":"声子晶体"},{"id":"dc0937d8-5e6b-4f66-9d55-cee508b64b0e","keyword":"转移矩阵","originalKeyword":"转移矩阵"},{"id":"f096337e-f2d2-4b26-ae7c-e44de8159f09","keyword":"<span style=\"color:red\">缺陷</span>模","originalKeyword":"缺陷模"}],"language":"zh","publisherId":"cldb2008Z2026","title":"一维声子晶体的<span style=\"color:red\">缺陷</span>模<span style=\"color:red\">特征</span>","volume":"22","year":"2008"},{"abstractinfo":"分析了钢管<span style=\"color:red\">缺陷</span>几何大小与<span style=\"color:red\">缺陷</span>漏磁信号(MFL)<span style=\"color:red\">特征</span>量之间关系,建立了一组全方位的钢管<span style=\"color:red\">缺陷</span>信号<span style=\"color:red\">特征</span>量,并将人工神经网络理论和算法应用于钢管<span style=\"color:red\">缺陷</span>预测.通过实验取得样本,在对网络进行训练的基础上,建立了基于钢管<span style=\"color:red\">缺陷</span>漏磁信号<span style=\"color:red\">特征</span>量和神经网络的<span style=\"color:red\">缺陷</span>预测模型,继而根据漏磁信号对<span style=\"color:red\">缺陷</span>进行定量预测.给出了实验结果,结果表明采用这种方法能够较好地实现管道<span style=\"color:red\">缺陷</span>的定量识别.","authors":[{"authorName":"杨涛","id":"705a6658-9a32-4ffa-b742-f59cbdcf7f0b","originalAuthorName":"杨涛"},{"authorName":"王太勇","id":"b68a09ca-a603-4e65-89fa-0452fad05f60","originalAuthorName":"王太勇"},{"authorName":"秦旭达","id":"816a2e3d-6124-4d07-b20e-14867572ad77","originalAuthorName":"秦旭达"},{"authorName":"蒋奇","id":"397c9c99-2a80-4272-837b-1929d7f9a6b9","originalAuthorName":"蒋奇"}],"doi":"","fpage":"50","id":"4cee99d1-18e4-4809-8e1e-50e58295f923","issue":"9","journal":{"abbrevTitle":"GT","coverImgSrc":"journal/img/cover/GT.jpg","id":"27","issnPpub":"0449-749X","publisherId":"GT","title":"钢铁"},"keywords":[{"id":"1952398c-32ef-416d-986f-ecbe6872fa81","keyword":"漏磁检测","originalKeyword":"漏磁检测"},{"id":"4b1f0817-8b78-4115-91e5-7bc1fdc4c64a","keyword":"钢管","originalKeyword":"钢管"},{"id":"5f1f5207-9b3a-42df-8cbb-5618a667ad78","keyword":"神经网络","originalKeyword":"神经网络"},{"id":"1888b356-9e42-478f-aa6e-43d87313735e","keyword":"<span style=\"color:red\">特征</span>量","originalKeyword":"特征量"},{"id":"86fa4129-377f-47c3-b633-b4a5b36b479b","keyword":"预测模型","originalKeyword":"预测模型"}],"language":"zh","publisherId":"gt200409012","title":"基于<span style=\"color:red\">特征</span>量和神经网络的钢管<span style=\"color:red\">缺陷</span>预测模型","volume":"39","year":"2004"},{"abstractinfo":"对冷轧板中发现的条痕<span style=\"color:red\">缺陷</span><span style=\"color:red\">特征</span>进行了分析,探讨了该<span style=\"color:red\">缺陷</span>的形成原因.通过对热轧板中发现的条状<span style=\"color:red\">缺陷</span><span style=\"color:red\">特征</span>分析,以及对条状<span style=\"color:red\">缺陷</span>热轧板的冷轧试验和热轧板酸洗出口处进行的<span style=\"color:red\">缺陷</span>跟踪,认为热轧板中的条状<span style=\"color:red\">缺陷</span>可以形成冷轧板中的条痕<span style=\"color:red\">缺陷</span>.综合分析认为连铸坯中的气泡是形成冷轧板表面条痕<span style=\"color:red\">缺陷</span>的主要原因.","authors":[{"authorName":"方淑芳","id":"35ae612f-6993-482e-9bde-7a6a93604b6b","originalAuthorName":"方淑芳"}],"doi":"10.3969/j.issn.1004-7638.2002.02.013","fpage":"59","id":"0c52ae59-33e8-4d39-9524-5daca01f7a38","issue":"2","journal":{"abbrevTitle":"GTFT","coverImgSrc":"journal/img/cover/gtft1.jpg","id":"28","issnPpub":"1004-7638","publisherId":"GTFT","title":"钢铁钒钛"},"keywords":[{"id":"c51fbd57-3bf5-4e09-bbac-7d056cda4598","keyword":"冷轧板","originalKeyword":"冷轧板"},{"id":"e845ccfe-48e0-4b5d-a421-a7bb16d4167c","keyword":"条痕<span style=\"color:red\">缺陷</span>","originalKeyword":"条痕缺陷"},{"id":"ecd963d5-2a51-4749-97dc-fc2743a1ecbc","keyword":"<span style=\"color:red\">特征</span>","originalKeyword":"特征"},{"id":"12d06005-d13e-4d1b-b584-f7ed25330263","keyword":"形成原因","originalKeyword":"形成原因"}],"language":"zh","publisherId":"gtft200202013","title":"冷轧板条痕<span style=\"color:red\">缺陷</span>的<span style=\"color:red\">特征</span>及形成原因探讨","volume":"23","year":"2002"},{"abstractinfo":"针对带钢表面的划痕、黑斑、翘皮、辊印、褶皱和压印6种典型<span style=\"color:red\">缺陷</span>,提取了样本图像的灰度、纹理和几何形状<span style=\"color:red\">特征</span>等32维<span style=\"color:red\">特征</span>向量。基于遗传算法对32维<span style=\"color:red\">特征</span>向量进行降维优化选择,选择了其中的20维以进行<span style=\"color:red\">缺陷</span>图像类型的分类。利用BP神经网络对降维前后的6种典型带钢表面<span style=\"color:red\">缺陷</span>分类进行对比识别,并同主成分降维方法进行了对比,验证了所提取的带钢表面<span style=\"color:red\">缺陷</span>图像<span style=\"color:red\">特征</span>及其遗传算法降维的有效性。","authors":[{"authorName":"汤勃","id":"53421a1d-f709-4542-bd11-515b8c1253c5","originalAuthorName":"汤勃"},{"authorName":"孔建益","id":"227f3406-95a0-4843-9165-3fb8dab6a583","originalAuthorName":"孔建益"},{"authorName":"王兴东","id":"f5c6af80-8589-4e6c-ad06-e96ce6e9965e","originalAuthorName":"王兴东"},{"authorName":"侯宇","id":"28be5fc5-0a32-4014-b2c7-9356ae5fca1c","originalAuthorName":"侯宇"}],"doi":"","fpage":"59","id":"0a168b7a-26f5-44e5-b634-d9434aa3f312","issue":"9","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":"6ea993bf-8d9c-4a9d-ab21-71c26091d684","keyword":"带钢表面<span style=\"color:red\">缺陷</span>","originalKeyword":"带钢表面缺陷"},{"id":"3348e640-1c29-47ca-a0da-015bba94f283","keyword":"<span style=\"color:red\">特征</span>提取","originalKeyword":"特征提取"},{"id":"23830f4c-8766-46c2-a239-ffc746585544","keyword":"降维","originalKeyword":"降维"},{"id":"fe89f3cb-051d-45ce-a315-d45161d8e919","keyword":"识别与分类","originalKeyword":"识别与分类"}],"language":"zh","publisherId":"gtyjxb201109016","title":"基于遗传算法的带钢表面<span style=\"color:red\">缺陷</span><span style=\"color:red\">特征</span>降维优化选择","volume":"23","year":"2011"},{"abstractinfo":"针对带钢表面的划痕、黑斑、翘皮、辊印、褶皱和压印6种典型<span style=\"color:red\">缺陷</span>，提取了样本图像的灰度、纹理和几何形状<span style=\"color:red\">特征</span>等32维<span style=\"color:red\">特征</span>向量。基于遗传算法对32维<span style=\"color:red\">特征</span>向量进行降维优化选择，选择了其中的20维以进行<span style=\"color:red\">缺陷</span>图像类型的分类。利用BP神经网络对降维前后的6种典型带钢表面<span style=\"color:red\">缺陷</span>分类进行对比识别，并同主成分降维方法进行了对比，验证了所提取的带钢表面<span style=\"color:red\">缺陷</span>图像<span style=\"color:red\">特征</span>及其遗传算法降维的有效性。","authors":[{"authorName":"汤勃，孔建益，王兴东，侯宇","id":"5f55df69-1afa-4835-ae80-b7a044435ae8","originalAuthorName":"汤勃，孔建益，王兴东，侯宇"}],"categoryName":"|","doi":"","fpage":"59","id":"e329cbab-8fef-4b61-b9c1-e80c93453223","issue":"9","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":"cdb019af-35cd-44af-97cc-aab2a5028d01","keyword":"带钢表面<span style=\"color:red\">缺陷</span> ","originalKeyword":"带钢表面缺陷 "},{"id":"2629f769-19f7-4a3b-83b8-738e6d7212ec","keyword":" feature extraction ","originalKeyword":" feature extraction "},{"id":"3579e3d4-f92e-45f7-9ef0-2c56afbeb729","keyword":" dimensions reduction ","originalKeyword":" dimensions reduction "},{"id":"57fd1697-8f83-4f0b-ae97-5e405c8fb56c","keyword":" recognition and classification","originalKeyword":" recognition and classification"}],"language":"zh","publisherId":"1001-0963_2011_9_7","title":"基于遗传算法的带钢表面<span style=\"color:red\">缺陷</span><span style=\"color:red\">特征</span>降维优化选择","volume":"23","year":"2011"},{"abstractinfo":"为了将金属磁记忆检测技术应用于焊缝不同典型<span style=\"color:red\">缺陷</span>的定性和定量评价上,对Q235钢未焊透和固体夹渣两种<span style=\"color:red\">缺陷</span>进行实验研究,通过比较0、150和230 kN不同载荷级别下的磁记忆信号检测结果,提取了焊缝未焊透和夹渣两种<span style=\"color:red\">缺陷</span>的不同磁记忆信号<span style=\"color:red\">特征</span>,结果表明,未焊透的磁记忆<span style=\"color:red\">特征</span>信号波宽D的变化更为突出,而固体夹渣的磁记忆<span style=\"color:red\">特征</span>信号梯度K变化明显,并进一步从磁记忆机理的角度加以推导分析.分别以相应载荷级别下焊缝X射线检测结果作为依据,验证了磁记忆<span style=\"color:red\">特征</span>信号在焊缝<span style=\"color:red\">缺陷</span>种类确定和<span style=\"color:red\">缺陷</span>严重程度定量评价上的可行性与有效性.","authors":[{"authorName":"邢海燕","id":"00092de3-71b8-4a61-b863-e49dc6100052","originalAuthorName":"邢海燕"},{"authorName":"徐敏强","id":"3f25d94e-218a-4364-8720-1298c3c06037","originalAuthorName":"徐敏强"},{"authorName":"陈鑫彧","id":"7ff51d1f-3312-48fa-8495-bb1034593d31","originalAuthorName":"陈鑫彧"},{"authorName":"秦萍","id":"bd445742-a4b5-465b-af57-70e8228e3ce6","originalAuthorName":"秦萍"}],"doi":"","fpage":"65","id":"2727e64e-1285-4754-80fd-1f39d932b581","issue":"6","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":"ffd86868-8e52-4628-a240-9d8df60a156f","keyword":"磁记忆检测","originalKeyword":"磁记忆检测"},{"id":"21cb084c-8049-45d1-b316-6c0e61ff1bbf","keyword":"焊缝<span style=\"color:red\">缺陷</span>","originalKeyword":"焊缝缺陷"},{"id":"84212c96-2aca-43c4-af69-28c946f62798","keyword":"信号<span style=\"color:red\">特征</span>","originalKeyword":"信号特征"}],"language":"zh","publisherId":"clkxygy201106012","title":"焊缝两种典型<span style=\"color:red\">缺陷</span>的磁记忆<span style=\"color:red\">特征</span>对比","volume":"19","year":"2011"},{"abstractinfo":"研究了热补仪修理复合材料层压板结构的<span style=\"color:red\">缺陷</span><span style=\"color:red\">特征</span>.金相显微分析结果表明,当修补层数为2层时,样品没有任何<span style=\"color:red\">缺陷</span>产生;当修补层数增加到4层时,修补层内出现气孔<span style=\"color:red\">缺陷</span>;当修补层数增加到6层时,除了修补层内出现大量气孔<span style=\"color:red\">缺陷</span>以外,胶膜层也出现气孔,导致弱粘接/脱粘<span style=\"color:red\">缺陷</span>的产生.超声检测的结果与金相显微分析一致,很好地再现了上述<span style=\"color:red\">缺陷</span>.","authors":[{"authorName":"张婷","id":"db729988-7f85-433b-9f9f-eaf0e12f144f","originalAuthorName":"张婷"},{"authorName":"刘奎","id":"c4e9a18c-1b59-4331-ae32-cd910ea86bea","originalAuthorName":"刘奎"},{"authorName":"王婷婷","id":"8e118aa8-eb42-4f45-abc0-29b040d3dae5","originalAuthorName":"王婷婷"}],"doi":"10.11868/j.issn.1005-5053.2015.1.011","fpage":"66","id":"cd377077-2cd5-4eef-9c86-e639195df897","issue":"1","journal":{"abbrevTitle":"HKCLXB","coverImgSrc":"journal/img/cover/HKCLXB.jpg","id":"41","issnPpub":"1005-5053","publisherId":"HKCLXB","title":"航空材料学报"},"keywords":[{"id":"ee8cc62e-b38f-4d73-8a5b-eeb6497df583","keyword":"复合材料","originalKeyword":"复合材料"},{"id":"fdd88fe2-40dc-42c6-996e-a08247690ee2","keyword":"修理","originalKeyword":"修理"},{"id":"10b39782-2013-43e5-b24c-f6fd626f8af7","keyword":"气孔<span style=\"color:red\">缺陷</span>","originalKeyword":"气孔缺陷"},{"id":"9691b55d-8a41-41f2-8a6a-bba565859a02","keyword":"超声检测","originalKeyword":"超声检测"},{"id":"bbacf987-833c-49ba-b702-e88b7641b7e6","keyword":"金相显微检测","originalKeyword":"金相显微检测"}],"language":"zh","publisherId":"hkclxb201501011","title":"复合材料修理结构的<span style=\"color:red\">缺陷</span><span style=\"color:red\">特征</span>与超声信号","volume":"35","year":"2015"}],"totalpage":1874,"totalrecord":18735}