Machine Learning for Cyber Physical Systems : : Selected Papers from the International Conference ML4CPS 2020.

• Superior document: Technologien Für Die Intelligente Automation Series ; v.13
• Author: Beyerer, Jürgen.
• TeilnehmendeR: Maier, Alexander.; Niggemann, Oliver.
• Place / Publishing House: Berlin, Heidelberg : : Springer Berlin / Heidelberg,, 2020.; {copy}2021.
• Year of Publication: 2020
• Edition: 1st ed.
• Language: English
• Series: Technologien Für Die Intelligente Automation Series
• Physical Description: 1 online resource (129 pages)

Table of Contents

Intro -- Preface -- Table of Contents -- 1 Energy Profile Prediction of Milling Processes Using Machine Learning Techniques -- 1 Einleitung -- 2 Methode -- 3 Datenerhebung und -aufbereitung -- 3.1 Gewinnung der Zielwerte Energie- und Zeitbedarf -- 3.2 Gewinnung der Inputparameter für die Regressionsmodelle -- 3.3 Feature Engineering -- 4 Modellbildung -- 5 Ergebnisse und Validierung -- 6 Diskussion und Ausblick -- References -- 2 Improvement of the prediction quality of electrical load profiles with artificial neural networks -- 1 Introduction -- 2 Analysis of the load profiles -- 2.1 Primary data preparation and plausibility check -- 2.2 Data analysis and creation load profile classes -- 2.3 Parameter estimation -- 2.4 Splitting the data sets -- 3 Artificial neural network as prediction model -- 3.1 Research studies -- 3.2 Basic specifications of the model -- 3.3 Investigation scenarios -- 4 Simulation and evaluation of the results -- 5 Conclusion and Outlook -- References -- 3 Detection and localization of an underwater docking station in acoustic images using machine learning and generalized fuzzy hough transform -- 1 Introduction -- 2 Methodology -- 3 Experimental results -- 4 Conclusions and future work -- 5 Acknowledgements -- References -- 4 Deployment architecture for the local delivery of ML-Models to the industrial shop floor -- 1 Introduction -- 2 Aim of the presented work -- 3 Related Work -- 4 Architecture -- 5 Data connectivity and collection -- 6 ML-Model Serving -- 7 Monitoring Strategies -- 8 Lifecycle Management -- 9 Discussion -- 10 Acknowledgement -- References -- 5 Deep Learning in Resource and Data Constrained Edge Computing Systems -- 1 Introduction -- 2 Methods &amp -- Related Work -- 2.1 Variational Autoencoder -- 2.2 Federated Learning -- 3 Results -- 3.1 Clustering and Visualization of Wafermap Patterns.

3.2 Anomaly Detection for Sensor Data of a Furnace -- 3.3 Predictive Maintenance using Federated Learning on Edge Devices -- 4 Conclusion -- References -- 6 Prediction of Batch Processes Runtime Applying Dynamic Time Warping and Survival Analysis -- 1 Introduction -- 2 Dynamic Time Warping -- 3 Survival Analysis -- 4 Data -- 5 Proposed System -- 6 Results -- 7 Conclusion -- References -- 7 Proposal for requirements on industrial AI solutions -- 1 Introduction -- 1.1 Usage of AI in Industrial Production -- 1.2 Industrial AI -- 2 Requirements on industrial AI -- 2.1 Adaption of Industrial AI systems -- 2.2 Engineering of Industrial AI systems -- 2.3 Embedding of Industrial AI system in existing production system landscape -- 2.4 Safety and Security of Industrial AI systems -- 2.5 Trust in functionality of Industrial AI systems -- 3 Discussion -- 4 Conclusion -- Acknowledgements -- References -- 8 Information modeling and knowledge extraction for machine learning applications in industrial production systems -- 1 Introduction -- 2 Information modeling -- 3 Tool chain for knowledge extraction -- 4 Conclusion -- 5 Acknowledgement -- Appendix: Entities of the proposed information model -- References -- 9 Explanation Framework for Intrusion Detection -- 1 Introduction -- 2 Explanations for Intrusion Detection -- 3 The Modular Phases of Explanations -- 4 Experiment -- 5 Summary -- References -- 10 Automatic Generation of Improvement Suggestions for Legacy, PLC Controlled Manufacturing Equipment Utilizing Machine Learning -- 1 Introduction -- 2 Related Works -- 3 Hypothesis -- 4 Evaluation -- 5 Conclusion And Future Works -- References -- 11 Hardening Deep Neural Networks in Condition Monitoring Systems against Adversarial Example Attacks -- 1 Introduction -- 2 Related work -- 3 Solution -- 4 Results -- 5 Conclusion -- References.

12 First Approaches to Automatically Diagnose and Reconfigure Hybrid Cyber-Physical Systems -- 1 Introduction -- 2 State of the Art -- 3 The multiple-tank model -- 4 Diagnosing Hybrid Systems -- 5 Reconfiguration after faults occurred -- 6 Conclusion and future work -- 7 Acknowledgement -- References -- 13 Machine learning for reconstruction of highly porous structures from FIB-SEM nano-tomographic data -- 1 Introduction -- 2 Network architecture and and training the model -- 3 Results -- 4 Conclusion -- References.