期刊文献+
共找到3篇文章
< 1 >
每页显示 20 50 100
胆囊息肉样病变的流行病学及危险因素 被引量:32
1
作者 陈善鹏 王智翔 +2 位作者 张小弟 沈乃营 魏志力 《临床肝胆病杂志》 CAS 北大核心 2019年第2期441-443,共3页
胆囊息肉样病变(PLG)临床常见,以非肿瘤性息肉为主,少部分为肿瘤性息肉。总结了PLG的流行病学及相关危险因素,提示PLG的发病是由性别、HBV感染、代谢综合征、内脏肥胖、低密度脂蛋白低水平、胆囊壁增厚、糖尿病等多种因素共同作用所致... 胆囊息肉样病变(PLG)临床常见,以非肿瘤性息肉为主,少部分为肿瘤性息肉。总结了PLG的流行病学及相关危险因素,提示PLG的发病是由性别、HBV感染、代谢综合征、内脏肥胖、低密度脂蛋白低水平、胆囊壁增厚、糖尿病等多种因素共同作用所致。随着PLG的发病率日趋升高,认为今后的研究重点应着眼于运用流行病学研究结果,对高危人群定期进行健康筛查,并对确诊患者进行规范化随访观察,发现并及早干预具有癌变可能的PLG。 展开更多
关键词 胆囊疾病 息肉 流行病学 危险因素 综述
在线阅读 下载PDF
深度学习预测GPS时间序列在探索门源M_S6.4地震前兆中的应用 被引量:3
2
作者 陈善鹏 尹玲 +2 位作者 梁诗明 胡向阳 余小燕 《大地测量与地球动力学》 CSCD 北大核心 2020年第12期1248-1253,共6页
以2016-01-21门源MS6.4地震为例,提出用深度学习预测的GPS时间序列研究地震前兆。用震中附近门源台(QHME)、民乐台(GSML)及古浪台(GSGL)无震时的GPS时间序列训练LSTM神经网络,得到高精度的GPS时间序列预测模型,再分别对该地区无震时和... 以2016-01-21门源MS6.4地震为例,提出用深度学习预测的GPS时间序列研究地震前兆。用震中附近门源台(QHME)、民乐台(GSML)及古浪台(GSGL)无震时的GPS时间序列训练LSTM神经网络,得到高精度的GPS时间序列预测模型,再分别对该地区无震时和地震前一段时间的GPS时间序列进行回溯性预测。对比预测时间序列与真实时间序列发现,震前2条时间序列大部分的相似性指标比无震时低,说明震前预测时间序列与真实时间序列差异明显,同时考虑震前时间序列的趋势异常,认为出现了异常时段;3个台站分别在E、N、U方向出现多个异常日期,且不同台站具有相同的异常日期,说明探索到了地震前兆。 展开更多
关键词 门源地震 GPS时间序列 LSTM神经网络 前兆异常
在线阅读 下载PDF
Early faults prediction of running state of electromechanical systems and reconfigurable integration of series safety monitoring systems 被引量:3
3
作者 Xu Xiaoli Zuo Yunbo +2 位作者 chen Tao Liu Xiuli chen shanpeng 《仪器仪表学报》 EI CAS CSCD 北大核心 2014年第S2期224-232,共9页
Fault prediction technology of running state of electromechanical systems is one of the key technologies that ensure safe and reliable operation of electromechanical equipment in health state. For multiple types of mo... Fault prediction technology of running state of electromechanical systems is one of the key technologies that ensure safe and reliable operation of electromechanical equipment in health state. For multiple types of modern, high-end and key electromechanical equipment, this paper will describe the early faults prediction method for multi-type electromechanical systems, which is favorable for predicting early faults of complex electromechanical systems in non-stationary, nonlinear, variable working conditions and long-time running state; the paper shall introduce the reconfigurable integration technology of series safety monitoring systems based on which the integrated development platform of series safety monitoring systems is built. This platform can adapt to integrated R&D of series safety monitoring systems characterized by high technology, multiple species and low volume. With the help of this platform, series safety monitoring systems were developed, and the Remote Network Security Monitoring Center for Facility Groups was built. Experimental research and engineering applications show that: this new fault prediction method has realized the development trend features extraction of typical electromechanical systems, multi-information fusion, intelligent information decision-making and so on, improving the processing accuracy, relevance and applicability of information; new reconfigurable integration technologies have improved the integration level and R&D efficiency of series safety monitoring systems as well as expanded the scope of application; the series safety monitoring systems developed based on reconfigurable integration platform has already played an important role in many aspects including ensuring safety operation of equipment, stabilizing product quality, optimizing running state, saving energy consumption, reducing environmental pollution, improving working conditions, carrying out scientific maintenance, advancing equipment utilization, saving maintenance charge and enhancing the level of information management. 展开更多
关键词 ELECTROMECHANICAL SYSTEMS EARLY FAULTS safety control monitoring SYSTEMS RECONFIGURABLE INTEGRATION
在线阅读 下载PDF
上一页 1 下一页 到第
使用帮助 返回顶部