Sensing, Smart, and Sustainable Technologies in Big Data-driven Manufacturing.

AuthorClarke, George
  1. Introduction

    Industry 4.0 integrates data and digital technologies within production systems to enhance output and coherence. (Lewis Bowler et al., 2020) Harnessing sensor data, the manufacturing system progress can be supervised, reinforcing the constitution, implementation, and refashioning of an instantaneous feedback control. (Chen et al., 2020) Digital twin combines both real and simulated data to supply more findings as regards the forecast of machine availability and assists in identifying disturbances by correlating the physical machine with its perpetually streamlined digital equivalent synchronously, initiating opportune rearrangement when required. (Zhang et al., 2020) Smart production and digital twin applications should analyze extensive data produced by the integrated manufacturing cycle. (Sun et al., 2020)

  2. Conceptual Framework and Literature Review

    Groundbreaking technologies can shape multi-tier supplier-customer links (Dusmanescu et al., 2016; Lazaroiu et al., 2020; Majerova et al., 2020; Popescu et al., 2017; Sekera, 2018) and corresponding developments in adjacent sectors. (Culot et al., 2020) Demand planning and digitization configure the production setting with sensors, processors, and actuators gathering instantaneous data concerning machines (Andrei et al., 2016a, b; Ionescu, 2018; Kowo and Akinbola, 2019; Nica et al., 2014; Popescu et al., 2018), and thus facilitating interaction between machines and sharing the input across the supply chain network (Chapman, 2018; Lazaroiu et al., 2019; Krizanova et al., 2019; Pera, 2019; Schinckus, 2018) to maintain long-term and demanding partners informed as regards diverse operations. (Schniederjans et al., 2020) Digital twin models can be harnessed for expediting the training phase in machine learning by producing applicable training datasets and by self-activating labeling through the simulation tool chain and consequently smoothing user's participation throughout practice. Such synthetic datasets can be improved and cross-substantiated with wide-ranging operative input. (Alexopoulos et al., 2020)

  3. Methodology and Empirical Analysis

    I inspected, used, and replicated survey data from Accenture, Capgemini, PwC, Software AG, and we.CONECT, performing analyses and making estimates regarding sensing, smart, and sustainable technologies. Structural equation modeling was used to analyze the data and test the proposed conceptual model.

  4. Results and Discussion

    Industry 4.0 catalyzes sustainability by computerizing supply chains and furthering their assimilation throughout value networks. (Ghobakhloo, 2020) To configure a machine tool adequate for Industry 4.0, cutting-edge advancement should be performed in a coherent way instead of the improvised deployment of activating technologies. (Jeon et al., 2020) Product lifecycles tend to be reduced now as a result of unlimited and inconstant customer demands, accordingly necessitating reconfigurable and multipurpose manufacturing systems bolstering up the pivotal components of smart factories. (Kim et al., 2020) While heterogeneous rules and technologies facilitate more significant access to data, determining data processing and sharing may be challenging given the growing diversity of input from incongruous sources in large-scale manufacturing networks. (Helu et al., 2020) (Tables 1-6)

  5. Conclusions and Implications

    The pivotal objective of recurrently organizing systems is to get the full...

To continue reading

Request your trial