检索结果-南通市图书馆

Real-time temperature prediction of electric machines using machine learning with physically informed features

Energy and AI 2023年第4期14卷 415-425页

作者： ryan hughes Thomas Haidinger Xiaoze Pei Christopher Vagg University of Bath UK AVL List GmbH Austria

Accurate estimation of the internal temperatures of electric machines is critical to increasing their power density and reliability since key temperatures,such as magnet temperature,are often difficult to *** work presents a new machine learning based modelling approach,incorporating novel physically informed feature engineering,which achieves best-in-class accuracy and reduced training *** different features introduced are proportional to sources of machine losses and require no prior knowledge of the machine,hence the models are completely data *** using a standard experimental dataset shows that modelling errors can be reduced by up to 82.5%,resulting in the lowest mean squared error recorded in the literature of 2.40 K^(2).Additionally,models can be trained with less training data and have lower sensitivity to data ***-ically,it was possible to train a loss enhanced multilayer perceptron model to a mean squared error<5 K^(2) with 90 h of training data,and an enhanced ordinary least squares model with just 60 h to the same *** inference time of the model can be 1–2 orders of magnitude faster than competing models and requires no time to optimise hyperparameters,compared to weeks or months for other state-of-the-art prediction *** results are highly important for enabling low-cost real-time temperature monitoring of electric machines to improve operational efficiency,safety,reliability,and power density.

关键词： Thermal model Real-time Electric machine Machine learning Losses

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Mako:A Graph-based Pattern Growth Approach to Detect Complex Structural Variants

引用

Genomics, Proteomics & Bioinformatics 2022年第1期20卷 205-218页

作者： Jiadong Lin Xiaofei Yang Walter Kosters Tun Xu Yanyan Jia Songbo Wang Qihui Zhu Mallory ryan Li Guo Chengsheng Zhang The Human Genome Structural Variation Consortium Charles Lee Scott E.Devine Evan E.Eichler Kai Ye School of Automation Science and Engineering Faculty of Electronic and Information EngineeringXi’an Jiaotong UniversityXi’an 710049China MOE Key Lab for Intelligent Networks&Networks Security Faculty of Electronic and Information EngineeringXi’an Jiaotong UniversityXi’an 710049China Genome Institute the First Affiliated Hospital of Xi’an Jiaotong UniversityXi’an 710061China Leiden Institute of Advanced Computer Science Faculty of ScienceLeiden UniversityLeiden 2311EZNetherland School of Computer Science and Technology Faculty of Electronic and Information EngineeringXi’an Jiaotong UniversityXi’an 710049China The Jackson Laboratory for Genomic Medicine FarmingtonCT 06032USA Precision Medicine Center the First Affiliated Hospital of Xi’an Jiaotong UniversityXi’an 710061China Institute for Genome Sciences University of Maryland School of MedicineBaltimoreMD 21201USA Department of Genome Sciences University of Washington School of MedicineSeattleWA 98119USA Howard hughes Medical Institute University of WashingtonSeattleWA 98195USA The School of Life Science and Technology Xi’an Jiaotong UniversityXi’an 710049China 不详

Complex structural variants(CSVs) are genomic alterations that have more than two breakpoints and are considered as the simultaneous occurrence of simple structural ***,detecting the compounded mutational signals of CSVs is challenging through a commonly used model-match *** a result,there has been limited progress for CSV discovery compared with simple structural ***,we systematically analyzed the multi-breakpoint connection feature of CSVs,and proposed Mako,utilizing a bottom-up guided model-free strategy,to detect CSVs from paired-end short-read ***,we implemented a graph-based pattern growth approach,where the graph depicts potential breakpoint connections,and pattern growth enables CSV detection without pre-defined *** evaluations on both simulated and real datasets revealed that Mako outperformed other ***,validation rates of CSVs on real data based on experimental and computational validations as well as manual inspections are around 70%,where the medians of experimental and computational breakpoint shift are 13 bp and 26 bp,***,the Mako CSV subgraph effectively characterized the breakpoint connections of a CSV event and uncovered a total of 15 CSV types,including two novel types of adjacent segment swap and tandem dispersed *** analysis of these CSVs also revealed the impact of sequence homology on the formation of *** is publicly available at https://***/xjtu-omics/Mako.

关键词： Next-generation sequencing Complex structural variant Pattern growth Graph mining Formation mechanism

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

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：