Data visualization for Industry 4.0: A stepping-stone toward a digital future, bridging the gap between academia and industry

Here, we analyze the potential of advanced data-visualization dashboards as an enabling technology for Industry 4.0. High-dimensional, real-time visualization allows graphical expression complex process variables at a fraction cost full-scale digitalization. It is therefore more achievable goal smaller firms looking to transition digital manufacturing and poses realistic stepping-stone approach undergoing fourth industrial revolution, coined 4.0 (I4.0), seeing implementation cutting-edge technologies such cloud (CM), Internet Things (IoT), cyber-physical systems (CPS), big data analytics (BDA). There significant pressure on industry adopt integrate these push toward “smart factories” that can make intelligent decisions control their own processes. These changes have led data-oriented operations require thoughtful techniques software realize full value data; classical strategies do not work well preserve benefits within changing status quo driven by I4.0. The challenges in implementing I4.0 are multifaceted include obvious technical economic cultural social issues. critical effective improved decision making, ad hoc analysis, collaboration1Sucharitha V. Subash S. Prakash P. Visualization data: its tools challenges.International Journal Applied Engineering Research. 2014; 9: 5277-5290Google Scholar be preserved industry’s transformation. Providing insight into key purpose visualization; it fundamental summarizing large datasets quickly intuitively takes important place manufacturing, where becoming amount generated accelerating exponentially. Moreover, visual analysis used all levels organization, from staff management, so when effectively, knowledge communicated through them far-reaching business impact. “We currently preparing students jobs don't yet exist, using haven't been invented, order solve problems, even know problems yet.” This quote former Education Secretary Richard Riley was featured foreword 2019 report Universities Future2Universities FutureIndustry implications higher education institutions: state-of-maturity competence needs.https://universitiesofthefuture.eu/wp-content/uploads/2019/02/State-of-Maturity_Report.pdfDate: 2019Google attempts identify skills required adapting sentiment felt beyond education, incoming especially existing workforce digitally literate relevant remains challenge. Something exacerbating this challenge aging OECD (Organization Economic Co-operation Development) countries.3Calzavara M. Battini D. Bogataj Sgarbossa F. Zennaro I. Ageing management systems: state art future research agenda.Int. J. Prod. Res. 2020; 58: 729-747https://doi.org/10.1080/00207543.2019.1600759Crossref Scopus (42) Google Retraining demographic science challenge, but current processes invaluable. utilized providing easy-to-use lowers barrier analyzing understanding recruits experience potentially provide valuable troubleshooting or optimizing Manufacturing will continue produce data, lot businesses, particularly small mid-size enterprises (SMEs), lack resources expertise implement solutions take advantage data. A 2020 survey UK firms, which were mostly SMEs, found machine learning ranked high-benefit also high-complexity operations.4Masood T. Sonntag 4.0: Adoption SMEs.Comput. Ind. 121: 103261https://doi.org/10.1016/j.compind.2020.103261Crossref (56) Commercial like Tableau (https://www.tableau.com) offer accessible platforms with minimal programming use aren’t specific industry, could benefit highly predictive maintenance control, reflected survey. move abstract concept simply cannot muster capital jump. Firms scenario left limbo, unable forward themselves, while competitors advantages increased Therefore, disadvantage compared much larger corporation rivals. question becomes, what close gap? answer many lies realm software. importance tool widespread, documented, unfortunately, industries rather slow engaging tools—perhaps because knowledge. involves multivariate systems, high volumes high-velocity therefore, computational requirement compile, analyze, gain significant; many, ability return daunting task. Clearly, development one-stop-shop birds-eye view over massive provides invaluable efficient manner. In world machines talk each other, day-to-day human tasks being automated, interpretation field emphasizes need creative input lateral thinking promotes innovative problem solving. outside-the-box solving ultimately define role operator our routine handed smart-manufacturing counterparts. Employing people’s natural capacity fundamentally intuitive does training handling. thought non-discriminatory—it same level regardless academic fortitude encourages information transparency organizations, reducing appearance barriers between upper engineering experts, operating staff, promoting greater communication. IoT, I4.0, new platform visualization. Significant effort has made describe IoT variations including (IoMT) Semantic Web (SWeTI) architectures series layers.5Zhang Y. Zhang G. Wang Sun Si Yang Real-time capturing integration framework internet things.International Computer Integrated Manufacturing. 2015; 28: 811-822https://doi.org/10.1080/0951192X.2014.900874Crossref (171) Scholar,6Patel Ali M.I. Sheth A. From raw smart manufacturing: AI semantic web things 4.0.IEEE Intell. Syst. 2018; 33: 79-86https://doi.org/10.1109/mis.2018.043741325Crossref top application/interface layers frameworks present opportunities visualizations connected multiple live sources, good support emerging trends dashboards. Dashboards experiencing increasing due monitoring decision-support capabilities combined increase power. Compared established human-machine interface (HMI) counterparts extensively controlling processes, customizable acts allowing access deeper principal-component (PCA), clustering, regression. Advanced dashboard front-end applications show promise handling applicable moving traditional approaches Additionally, they stand investment want afford price point comes paradigm, there needs further how applied different domains, situations, functions. step change way collaborates academia must realized help provides. On one hand, feeling transforming falling behind engage state-of-the-art solutions. other often materializing tangible rooted communication two sectors. Agile collaborative response ensure best turn enhances value, shrinking gap exists theoretically possible novel lives people industry. Wiz, one-stop shop visualization, example collaboration drive I4.0-focused both academia. Scientists non-scientists alike Wiz better understand based, anyone dataset browser without code download freely available https://wiz.shef.ac.uk/ since publication Patterns.7Balzer C. Oktavian R. Zandi Fairen-Jimenez Moghadam P.Z. Wiz: web-based interactive data.Patterns. 1: 100107https://doi.org/10.1016/j.patter.2020.100107Abstract Full Text PDF PubMed (2) Our team developing dynamic would functionalities (e.g., five-dimensional analysis) built-in Siemens’ MindSphere. excellent pave successfully developed settings. displayed enterprise-quality users customize performance indicators (Figure 1). allow user apply execute various analytical statistical methods, dimensionality reduction, noise reduction By combining condition monitoring, algorithms added quality control. Lastly, creating insights created twins data-driven models. clear common well-established commercial-grade focus range properly represent relationships production variables. applicability some areas development, biopharmaceutical production. considered truly standard technology, process-relevant considered. consider workforce. Measures should taken ease accessibility software, upskilling seamless working, bridging main entry conception offers wanting Advancements types shown promising results, before fully guide revolution. P.Z.M. thanks Corporate Information Computing Services (CiCS) Partnerships Regional Engagement University Sheffield partial funds Wiz. John Dale Carl McGrath Stefan Balan David Moss Siemens useful discussions. financial interest Monoclinic Ltd. Tableau, https://www.tableau.com About authors Dr. Peyman Z. lecturer Chemical Biological Department Sheffield, his group leading high-throughput simulations quantitative methods accelerated discovery functional materials. Prior joining he head Adsorption Materials Lab Cambridge 3 years. 2013 2015, did postdoc Northwestern after completing PhD chemical Edinburgh. He published 42 papers (h-index: 27). 2019, P.Z.M.’s won 1st prize competition subsequently front cover Patterns. His leads visualization/analytics applications.