Cover Image

Machine Learning for Cyber-Physical Systems : Selected Papers from the International Conference ML4CPS 2023.

Bibliographic Details
Main Author: Niggemann, Oliver.
Other Authors: Beyerer, Jürgen., Krantz, Maria., Kühnert, Christian.
Format: eBook
Language:English
Published: Cham : Springer, 2024.
Edition:1st ed.
Series:Technologien Für Die Intelligente Automation Series
Subjects:
Electronic books.
Online Access:Click to View
Table of Contents:
  • Intro
  • Preface
  • Contents
  • Causal Structure Learning Using PCMCI+ and Path Constraints from Wavelet-Based Soft Interventions
  • 1 Introduction
  • 2 Related Work
  • 3 Fundamentals
  • 3.1 Causal Graphs
  • 3.2 Causal Structure Learning
  • 4 Wavelet-Based Soft Interventions
  • 5 Applying Wavelet Injections
  • 6 Summary and Conclusion
  • Reinforcement Learning from Human Feedback for Cyber-Physical Systems: On the Potential of Self-Supervised Pretraining
  • 1 Introduction
  • 2 The Potential of Pretraining
  • 3 Discussion and Conclusion
  • Using ML-Based Models in Simulation of CPPSs: A Case Study of Smart Meter Production
  • 1 Introduction and Problem Statement
  • 2 Use Case
  • 3 Proposed Approach
  • 4 Experiments
  • 5 Conclusions and Future Work
  • Deploying Machine Learning in High Pressure Resin Transfer Molding and Part Post Processing: A Case Study
  • 1 Introduction
  • 1.1 Composite Manufacturing by RTM
  • 1.2 Knowledge Extraction in a Complex Network of Cyber-Physical Systems
  • 2 Implemented Approach
  • 2.1 Data Management and Analysis
  • 2.2 Process Monitoring and Predictive Maintenance for serial HP-RTM Production
  • 2.3 Process Monitoring and Quality Assurance in Post-Processing
  • 3 Preliminary Results
  • 3.1 Comparison of Physical to Date-Centric Modelling
  • 4 Conclusions &amp
  • Outlook
  • References
  • Development of a Robotic Bin Picking Approach Based on Reinforcement Learning
  • 1 Introduction
  • 2 Related Work
  • 2.1 Research Issue
  • 2.2 Selection of a Machine Learning Technique
  • 3 Approach
  • 3.1 Robotic Bin Picking Based on Reinforcement Learning
  • 3.2 Training Procedure
  • 3.3 Training Environment
  • 4 Conclusion
  • Control Reconfiguration of CPS via Online Identification Using Sparse Regression (SINDYc)
  • 1 Introduction
  • 2 Related Work
  • 2.1 Model-Based Fault Tolerant Control.
  • 2.2 Online, Closed-Loop System Identification
  • 3 System Description and Modeling
  • 4 Closed-Loop System Identification with SINDYc
  • 4.1 Sparse Identification-SINDYc
  • 4.2 Identifiability in Closed-Loop Systems
  • 5 Control Reconfiguration
  • 6 Results
  • 6.1 Closed-Loop Identification Parameter Study
  • 6.2 Closed-Loop Identification and Control Reconfiguration
  • 7 Limitations and Outlook
  • Using Forest Structures for Passive Automata Learning
  • 1 Introduction
  • 2 Preliminaries
  • 3 Algorithms for Learning of Automata Forests
  • 3.1 Forest Structure
  • 3.2 Forest with Cross Validation (ForestCV)
  • 3.3 Forest with Majority Voting (ForestMV)
  • 4 Experimental Evaluation
  • 4.1 Hyperparameter Tuning
  • 4.2 Analyzing DFAs
  • 4.3 Analyzing Mealy Machines
  • 5 Conclusion
  • Domain Knowledge Injection Guidance for Predictive Maintenance
  • 1 Introduction
  • 2 Related Work
  • 3 Guidance Development
  • 3.1 Knowledge Injection Framework
  • 3.2 Literature Study and Construction of the Knowledge Base
  • 3.3 Guidance Creation
  • 4 Examples for the Application of the Guidance
  • 5 Discussion
  • 6 Conclusion
  • Towards a Systematic Approach for Prescriptive Analytics Use Cases in Smart Factories
  • 1 Introduction
  • 2 State of the Art
  • 2.1 Formalization of Data Analytics Use Cases in Smart Factories
  • 2.2 Product, Process and Resource in Smart Factories
  • 3 Structuring Prescriptive Analytics in a Smart Factory Environment
  • 3.1 Data Analytics View on Use Cases
  • 3.2 Smart Manufacturing View on Use Cases
  • 4 Conclusion
  • References
  • Development of a Standardized Data Acquisition Prototype for Heterogeneous Sensor Environments as a Basis for ML Applications in Pultrusion
  • 1 Introduction
  • 2 Industrial Communication - State of the Art
  • 3 Concept Development for Machine Data Acquisition
  • 3.1 Requirements for a Standardized Data Acquisition.
  • 3.2 Selection of Preferred Standards
  • 3.3 Retrofitting a Standardized Data Acquisition System
  • 3.4 Concept Evaluation
  • 4 Summary and Outlook
  • References
  • A Digital Twin Design for Conveyor Belts Predictive Maintenance
  • 1 Introduction
  • 2 Related Work
  • 3 Framework
  • 3.1 Data Flow
  • 3.2 PLC and Sensors-Physical Twin
  • 3.3 Data Connectivity and Collection-Cyber-Physical System
  • 3.4 Virtual Twin
  • 4 Discussion and Future Work
  • Augmenting Explainable Data-Driven Models in Energy Systems: A Python Framework for Feature Engineering
  • 1 Introduction
  • 1.1 Main Contribution
  • 2 Method
  • 3 Case Study
  • 4 Conclusion.

Similar Items