Developing Industrial CPS: A Multi-Disciplinary Challenge

Abstract

Industrial Cyber-Physical System (CPS) is an emerging approach towards value creation in modern industrial production. The development and implementation of industrial CPS in real-life production are rewarding yet challenging. This paper aims to present a concept to develop, commercialize, operate, and maintain industrial CPS which can motivate the advance of the research and the industrial practice of industrial CPS in the future. We start with defining our understanding of an industrial CPS, specifying the components and key technological aspects of the industrial CPS, as well as explaining the alignment with existing work such as Industrie 4.0 concepts, followed by several use cases of industrial CPS in practice. The roles of each component and key technological aspect are described and the differences between traditional industrial systems and industrial CPS are elaborated. The multidisciplinary nature of industrial CPS leads to challenges when developing such systems, and we present a detailed description of several major sub-challenges that are key to the long-term sustainability of industrial CPS design. Since the research of industrial CPS is still emerging, we also discuss existing approaches and novel solutions to overcome these sub-challenges. These insights will help researchers and industrial practitioners to develop and commercialize industrial CPS.

Keywords: artificial intelligence; cyber–physical system; digital twin; industrial AI; industrie 4.0; operator support; powertrain; process industry; robotics; sensors; switchgear.

Figure 6

Pillars of industrial AI and adjacent topics of discussion [39,43].

Figure 1

Concept of components and key technological aspects of a purpose-driven industrial Cyber–Physical System (CPS) and their relations to each other.

Figure 2

The CPS of a medium-voltage switch gear structured along the concept presented in Figure 1. The switch gear cabinets (bottom) are augmented with infrared sensor arrays. The live images, together with engineering know-how of the switchgear (e.g., CAD drawings of the mechanical parts), form a digital twin.

Figure 3

The CPS of an industrial robot structured along the concept presented in Figure 1. The purpose of the CPS for the industrial robot application [21] is to enrich the physical robot with distributed learning and optimization capabilities for non-expert users. Therefore, the digital twin consists of a CAD, simulation and a programming environment.

Figure 4

The CPS of a process plant structured along the concept presented in Figure 1. The purpose of the CPS for the process plant application [23] is to assist the operator by continuously providing essential information about the status of the process. The digital twin here is a tool to automatically identify deviations in the process based on process data.

Figure 5

The CPS of a powertrain structured along the concept presented in Figure 1. External sensors are attached to a motor and bearing, e.g., using an AAS implementation to create a digital twin of their engineering and condition data, on which basis data-based services, like operations optimizations, are provided.

Figure 7

Identified major challenges in developing and managing industrial CPS, structured along the concept proposed in Figure 1.

Figure 8

A CPS combines a vast amount of aspects and can be interpreted as a system of systems. Red marks: existing (sub)systems for existing purposes. Green mark: enhanced (sub)system for enriched purposes.

Figure 9

Physical asset and domain understanding, data and information description as well as first-principles or data-driven modeling have to be combined in a proper way to achieve the next level of sustainable and valuable industrial solutions, i.e., as simple as possible but not simpler.