检索结果-南通市图书馆

LSTM-based argument recommendation for non-api methods

Science China(Information Sciences) 2020年第9期63卷 5-26页

作者： Guangjie LI Hui LIU Ge LI Sijie SHEN Hanlin TANG School of Computer Science and Technology Beijing Institute of Technology School of Electronics Engineering and Computer Science Peking University

Automatic code completion is one of the most useful features provided by advanced IDEs. Argument recommendation, as a special kind of code completion, is widely used as well. While existing approaches focus on argument recommendation for popular apis, a large number of non-api invocations are requesting for accurate argument recommendation as well. To this end, we propose an LSTM-based approach to recommending non-api arguments instantly when method calls are typed in. With data collected from a large corpus of open-source applications, we train an LSTM neural network to recommend actual arguments based on identifiers of the invoked method, the corresponding formal parameter, and a list of syntactically correct candidate arguments. To feed these identifiers into the LSTM neural network, we convert them into fixed-length vectors by Paragraph Vector, an unsupervised neural network based learning algorithm. With the resulting LSTM neural network trained on sample applications, for a given call site we can predict which of the candidate arguments is more likely to be the correct one. We evaluate the proposed approach with tenfold validation on 85 open-source C applications. Results suggest that the proposed approach outperforms the state-of-the-art approaches in recommending non-api arguments. It improves the precision significantly from 71.46% to 83.37%.

关键词： argument recommendation LSTM deep learning non-api

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Gas sealing performance test analysis of non-api casing connection with radial cone sealing structure

Gas sealing performance test analysis of non-API casing conn...

引用

2012年海峡两岸破坏科学/材料试验学术会议

作者： XU Zhiqian YAN Yifei JANG Tingting YAN Xiangzhen College of Mechanical and Electronic Engineering China University of Petroleum College of Pipeline and Civil Engineering China University of Petroleum

The metal-to-metal radial interference fit construction is the main sealing structure of the non-api casing connection.The sealing performance of the non-api casing connection is superior to the api casing because of the special sealing structure.So,the air tightness test has been done in order to find the sealing forming conditions and influencing factors.The main processing parameters of the test specimen are like the 7 inch casing connection.The main structure type is the cone-to-cone interference fit between two contact interfaces.The leakage rate was measured in the test under different contact pressure,different contact surface roughness and different contact width.The test results analysis show that the higher initial contact pressure is a necessary requisite to air seal.The contact interface has occurred plastic deformation when the contact pressure close to 2 times metal yield strength.In this condition,the leakage rate is unchanged with the increasing of gas pressure,the gas sealing performance in a stable state. Comparing the gas sealing performance of the different contact surface form processes(turning, grinding and lapping),we find that different surface roughness has different contact pressure in stable sealing state.The higher surface roughness come into stable sealing state much more quickly and easily comparing to the lower.Under the same contact and gas pressure and the same surface roughness,the leakage rate decrease dramatically with the increasing of the contact width, and the effect on the sealing performance comes very small when the contact width more than 10 mm.

关键词： Sealing Performance Leakage Rate non-api Casing Connection Air Tightness Test

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

欢迎您,

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：