Analytics and visualization of industrial Asset condition using Asset administration shell submodels.

Abstract

The advent of industry 4.0 necessitates a paradigm shift toward autonomous industrial operations, prompting the integration of digital twin to orchestrate machines and processes within automation systems. The Asset Administration Shell (AAS) emerges as a pivotal digital twin intended to encapsulate an asset’s lifecycle. It comprises of several submodels defining different aspects of machines or processes that in turn empowers continuous autonomy. This potential of AAS opens the scope to extend the standardization of machine processes that are common within a factory. One of these processes is a self-diagnostic and continuous analysis of the state of a machine. This imperative not only mitigates machine downtime but expeditiously detect faults or anomalies in production processes. This study explores the integration of Asset Administration Shell (AAS) into industrial machine analytics, aligning with Industry 4.0 paradigms. It emphasizes the application of AAS submodels for enabling machines to self-diagnose and continuously analyze their state, focusing on a universal analytics approach. This is achieved through a standardized submodel based on ISO 22400-2:2014 Key Performance Indicators (KPIs), facilitating a vendor-agnostic solution for machine analytics. The paper highlights the effectiveness of these standardized submodels in improving machine efficiency, predictive maintenance, and operational effectiveness in industrial processes. It also discusses the challenges and practical applications of these submodels, offering insights into their real-world implementation.