Artificial Intelligence-based Decision-Making Algorithms, Internet of Things Smart Devices, and Real-Time Process Monitoring in Sustainable Industry 4.0.

• Date: 01 June 2020
• Author: Dobson-Lohman, Elizabeth

1. Introduction

   The Industry 4.0 cutting-edge techniques are being growingly harnessed in the manufacturing, distribution, and commercialization chains on a large scale. (Ruiz-Sarmiento et al., 2020) Artificial intelligence applications developed on machine learning are broadly adopted as groundbreaking technologies in smart production. (Alexopoulos et al., 2020) Internet of Things technology shapes an ample variety of applications (e.g. smart cities and industrial settings). (de Matos et al., 2020) Digital twin represents a resourceful application for the operation and coherent efficiency improvement of sustainable and smart production. (Park et al., 2020)

2. Conceptual Framework and Literature Review

   Artificial intelligence is gradually harnessed in groundbreaking manufacturing systems (Eskridge, 2019; Kliestik et al., 2020; Krizanova et al., 2019; Popescu Ljungholm, 2018) to carry out smart production. (Y ang et al., 2020) Intelligent algorithms can handle particular product data, enhancing the reasoning process significantly. (Feng et al., 2020) The advancement of smart manufacturing business patterns are influenced by fulfilling consumer demands and intelligent algorithms. (Dou et al., 2020) Collected data is integrated within various layers in Industrial Internet of Things systems from cutting-edge sensors and smart devices to edge servers and cloud information centers by furthering search, enhancement, and forecasting algorithms. (Khan et al., 2020) With the growing requirement of data and intricacy of processing algorithms (Cuicui, 2019; Eysenck and Durana, 2019; Kowo and Akinbola, 2019; Lyakina et al., 2019; Nica et al., 2019), digital twins of physical systems can be carried out in diverse manners. (Ganguli and Adhikari, 2020) Innovation ecosystems enable small and medium-sized enterprises to assimilate resources and co-design Industry 4.0 solutions. (Brittes Benitez et al., 2020)

3. Methodology and Empirical Analysis

   I inspected, used, and replicated survey data from Capgemini, CompTIA, IW Custom Research, Kronos, and PAC, performing analyses and making estimates regarding technologies that are important for smart factories. Structural equation modeling was used to analyze the data and test the proposed conceptual model.

4. Results and Discussion

   Industry 4.0 examines sophisticated interconnected Internet of Things-based technologies with the aim of supplying digital solutions. (Brittes Benitez et al., 2020) Industry 4.0 harnesses Industrial Internet of Things and cloud computing, assimilating them into manufacturing systems. (Zolotova et al., 2020) Industry 4.0 digital transformation entails the digital conversion and homogenization of the whole value chain of the product lifecycle. (Ghobakhloo, 2020) Handling smart production data is still a difficult task irrespective of the advancement of the Industrial Internet of Things. (Helu et al., 2020) Internet of Things technologies are harnessed at perception layers to optimize physical objects as smart ones, and carry out the networking and sensing of manufacturing entities. (Guo et al., 2020) The smart teaming of interconnected machines is essential to enhancing the carrying into action of manufacturing systems. (Yang et al., 2019) (Tables 1-7)

5. Conclusions and Implications

   Wireless sensor networks, constituting a vital component of the...