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

This open access proceedings presents new approaches to Machine Learning for Cyber-Physical Systems, experiences and visions. It contains some selected papers from the international Conference ML4CPS – Machine Learning for Cyber-Physical Systems, which was held in Hamburg (Germany), March 29th to 31st, 2023.  Cyber-physical systems are characterized by their ability to adapt and to learn: They analyze their environment and, based on observations, they learn patterns, correlations and predictive models. Typical applications are condition monitoring, predictive maintenance, image processing and diagnosis. Machine Learning is the key technology for these developments. This is an open access book.

Table of Contents:
Causal Structure Learning using PCMCI+ and Path Constraints from Wavelet-based Soft Interventions.- Reinforcement Learning from Human Feedback for Cyber-Physical Systems: On the Potential of Self-Supervised Pretraining.- Using ML-based Models in Simulation of CPPSs: A Case Study of Smart Meter Production.- Deploying machine learning in high pressure resin transfer molding and part post processing: a case study.- Development of a Robotic Bin Picking Approach based on Reinforcement Learning.- Control Reconfiguration of CPS via Online Identification using Sparse Regression (SINDYc).- Using Forest Structures for Passive Automata Learning.- Domain Knowledge Injection Guidance for Predictive Maintenance.- Towards a systematic approach for Prescriptive Analytics use cases in smart factories.- Development of a standardized data acquisition prototype for heterogeneous sensor environments as a basis for ML applications in pultrusion.- A Digital Twin Design for conveyor belts predictive maintenance.- Augmenting explainable data-driven models in energy systems: A Python framework for feature engineering.