Deep Transfer Learning for Industrial Automation: A Review and Discussion of New Techniques for Data-Driven Machine Learning

被引：72

作者：

Maschler, Benjamin ^{[1
,2
,3
]}

Weyrich, Michael ^{[3
]}

机构：

[1] Univ Stuttgart, Renewable Energies & Sustainable Elect Energy Sup, Stuttgart, Germany

[2] Univ Cape Town, Renewable Energies & Sustainable Elect Energy Sup, Cape Town, South Africa

[3] Univ Stuttgart, Inst Ind Automat & Software Engn, D-70550 Stuttgart, Germany

来源：

IEEE INDUSTRIAL ELECTRONICS MAGAZINE | 2021年 / 15卷 / 02期

关键词：

Deep learning; Training data; Machine learning algorithms; Automation; Feature extraction; Data models; ANOMALY DETECTION;

D O I：

10.1109/MIE.2020.3034884

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

Deep learning has greatly increased the capabilities of "intelligent" technical systems over the last years [1]. This includes the industrial automation sector [1]-[4], where new data-driven approaches to, for example, predictive maintenance [2], computer vision [3], or anomaly detection [4], have resulted in systems more easily and robustly automated than ever before.

引用

页码：65 / 75

页数：11

共 41 条

[1]

[Anonymous], 2019, SENSORS-BASEL, DOI [DOI 10.3390/s19183987, 10.3390/s19183987]

[2] Multi-head CNN-RNN for multi-time series anomaly detection: An industrial case study [J].