Big data analytics – enabled cyber-physical system: model and applications

Abstract

Purpose The purpose of this paper is to propose a comprehensive framework for integrating big data analytics (BDA) into cyber-physical system (CPS) solutions. This framework provides a wide range of functions, including data collection, smart data preprocessing, smart data mining and smart data visualization. Design/methodology/approach The architecture of CPS was designed with cyber layer, physical layer and communication layer from the perspective of big data processing. The BDA model was integrated into a CPS that enables managers to make sound decisions. Findings The effectiveness of the proposed BDA model has been demonstrated by two practical cases − the prediction of energy output of the power grid and the estimate of the remaining useful life of the aero-engine. The method can be used to control the power supply system and help engineers to maintain or replace the aero-engine to maintain the safety of the aircraft. Originality/value The communication layer, which connects the cyber layer and physical layer, was designed in CPS. From the communication layer, the redundant raw data can be converted into smart data. All the necessary functions of data collection, data preprocessing, data storage, data mining and data visualization can be effectively integrated into the BDA model for CPS applications. These findings show that the proposed BDA model in CPS can be used in different environments and applications.

Cyber-physical spatial temporal analytics for digital twin-enabled smart contact tracing

“…Ding et al (2019) adopted the CPS and digital twin technologies to build the interconnection and interoperability of a physical shop floor and corresponding cybershop floor to realize real-time monitoring, simulation and optimization. Luo et al (2019) proposed a comprehensive framework for integrating big data analytics into CPS, where the redundant raw data can be converted into smart data. Tu et al (2018) implemented an IoT-based cyber-physical prototype in a production logistics scenario.…”

Artificial intelligence in safety-critical systems: a systematic review

“…Several definitions of AI in Schwendicke et al (2020), Dobrev (2005a, b) and McCarthy (2004) primarily refer to building intelligent machines that use computer programs to understand human intelligence and better perform human tasks in ways that are not limited to biologically observable methods. At the same time, machine learning (ML), as the core of data science, is the essence of modern AI, which involves the technology, method and approach from big data (Luo et al, 2019;Raut et al, 2021) to intelligence. AI technology has matured to the point where it can provide practical benefits in many applications (Pannu, 2015), including natural language processing (Hirschberg and Manning, 2015), computer vision (Voulodimos et al, 2018) and data mining (Jun Lee and Siau, 2001).…”

Data Quality Affecting Big Data Analytics in Smart Factories: Research Themes, Issues and Methods

“…Furthermore, the interaction and convergence of both physical and virtual manufacturing worlds to achieve symmetry by using digital twins is an inevitable trend in SF, also boosting on big data [2]. On the other hand, big data analytics (BDA) techniques help enterprises extract and discover the patterns, trends and relationships that exist in this large amount of data [3]. The products derived from BDA contribute to digital symmetry and simulation modelling for achieving SF objectives.…”