Filtern
Dokumenttyp
Schlagworte
- machine learning (3)
- Industrie 4.0 (2)
- intelligent manufacturing (2)
- predictive maintenance (2)
- Anwendungssoftware (1)
- Automatisierungssystem (1)
- BiLSTM (1)
- Digitale Transformation (1)
- Digitalisierung (1)
- ECG (1)
- Fördertechnik (1)
- IOTA (1)
- Internationalität (1)
- Internet of Things (1)
- Kooperation (1)
- Kybernetik zweiter Ordnung (1)
- Künstliche Intelligenz (1)
- Medieninformatik (1)
- Medienwissenschaft (1)
- Mehragentensystem (1)
- OEE (1)
- Optimierung (1)
- Programmiersprache (1)
- Robotik (1)
- Schiene (1)
- Softwareplattform (1)
- Theoretische Informatik (1)
- Traktion (1)
- U-Bahn (1)
- Universitäten (1)
- Verkehr (1)
- autonomous driving (1)
- availability (1)
- blockchain (1)
- candlesticks (1)
- classification (1)
- computational intelligence (1)
- cryptocurrencies (1)
- data analysis (1)
- data analytics (1)
- data monitoring (1)
- data preprocessing (1)
- data science (1)
- decision making (1)
- deep learning (1)
- digital identity (1)
- digital twin (1)
- emotion detection (1)
- failure cause identification (1)
- gait energy image (1)
- gait recognition (1)
- human identification (1)
- internet of things (1)
- local binary pattern (1)
- manufacturing (1)
- modularity (1)
- multi-purpose machines (1)
- multisensory data (1)
- natural language processing (1)
- neural network compression (1)
- pattern analysis (1)
- punching (1)
- real-time systems (1)
- recognition (1)
- requirement engineering (1)
- rule-based method (1)
- schedules (1)
- sensitivity (1)
- sensor systems (1)
- services (1)
- silhouette extraction (1)
- smart factory (1)
- smart maintenance (1)
- special machinery (1)
- surveillance systems (1)
- transducer networks (1)
- transfer learning (1)
Institut
Open Access
- kostenlos im WWW (3)
- ja (2)
- ja (Gold) (1)
Begutachtungsstatus
- peer-reviewed (12)
Teil I: Informatik
(2018)
Approaches and Techniques to Improve Machine Learning Performance in Distributed Transducer Networks
(2022)
KI auf Heimcomputern?
(2023)
Maintenance of complex machinery is time and resource intensive. Therefore, decreasing maintenance cycles by employing Predictive Maintenance (PdM) is sought after by many manufacturers of machines and can be a valuable selling point. However, currently PdM is a hard to solve problem getting increasingly harder with the complexity of the maintained system. One challenge is to adequately prepare data for model training and analysis. In this paper, we propose the use of expert knowledge–based preprocessing techniques to extend the standard data science–workflow. We define complex multi-purpose machinery as an pplication domain and test our proposed techniques on real-world data generated by numerous achines deployed in the wild. We find that our techniques enable and enhance model training.