Learning Physical Concepts in Cyber-Physical Systems: A Case Study

TL;DR

This paper reviews methods for learning physical concepts from sensor time series data in cyber-physical systems, highlighting their interpretability and transferability advantages, with a case study on a three-tank system.

Contribution

It provides a comprehensive overview and analysis of current concept learning methods in CPS, emphasizing their potential for improved interpretability and transferability.

Findings

Concept learning enhances interpretability of ML in CPS

Transferability of learned concepts across systems is feasible

Case study demonstrates practical application and limitations

Abstract

Machine Learning (ML) has achieved great successes in recent decades, both in research and in practice. In Cyber-Physical Systems (CPS), ML can for example be used to optimize systems, to detect anomalies or to identify root causes of system failures. However, existing algorithms suffer from two major drawbacks: (i) They are hard to interpret by human experts. (ii) Transferring results from one systems to another (similar) system is often a challenge. Concept learning, or Representation Learning (RepL), is a solution to both of these drawbacks; mimicking the human solution approach to explain-ability and transfer-ability: By learning general concepts such as physical quantities or system states, the model becomes interpretable by humans. Furthermore concepts on this abstract level can normally be applied to a wide range of different systems. Modern ML methods are already widely used in CPS, but concept learning and transfer learning are hardly used so far. In this paper, we provide an overview of the current state of research regarding methods for learning physical concepts in time series data, which is the primary form of sensor data of CPS. We also analyze the most important methods from the current state of the art using the example of a three-tank system. Based on these concrete implementations1, we discuss the advantages and disadvantages of the methods and show for which purpose and under which conditions they can be used.