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

Caihua Liu,Shuyang Li,Guochao Peng,Yongxin Kong,Si Chen

doi:10.3390/sym13081440

Caihua Liu, Shuyang Li + Show 3 more

Open Access

https://doi.org/10.3390/sym13081440

Copy DOI

Abstract

Recent years have seen a growing call for use of big data analytics techniques to support the realisation of symmetries and simulations in digital twins and smart factories, in which data quality plays an important role in determining the quality of big data analytics products. Although data quality affecting big data analytics has received attention in the smart factory research field, to date a systematic review of the topic of interest for understanding the present state of the art is not available, which could help reveal the trends and gaps in this area. This paper therefore presents a systematic literature review of research articles about data quality affecting big data analytics in smart factories that have been published up to 2020. We examined 31 empirical studies from our selection of papers to identify the research themes in this field. The analysis of these studies links data quality issues toward big data analytics with data quality dimensions and methods used to address these issues in the smart factory context. The findings of this systematic review also provide implications for practitioners in addressing data quality issues to better use big data analytics products to support digital symmetry in the context of smart factory.

Highlights

The increasing connections of systems produce massive amount of data that support manufacturing decision-making in smart factories (SF) [1]
Since SF is based on a wide range of software and automation systems, this study identifies a corpus of research articles that cover various research fields such as Engineering, information system (IS), Information Management (IM), and Computer Science to establish an exhaustive view on the field of data quality (DQ) for big data analytics (BDA) in SF
Thereafter, we provide the findings derived from the analysis and synthesis of the reviewed studies that address the research questions (RQs) proposed in the systematic literature review (SLR)

Summary

Introduction

The increasing connections of systems produce massive amount of data that support manufacturing decision-making in smart factories (SF) [1]. The interaction and convergence of both physical and virtual manufacturing worlds to achieve symmetry by using digital twins is an inevitable trend in SF, boosting on big data [2]. The products derived from BDA contribute to digital symmetry and simulation modelling for achieving. These products are used for product quality control [4] and predictive maintenance of equipment [5], in order to improve the competitiveness of enterprises. Incomplete and inaccurate data from the maintenance information system (IS) affects the results of the data analysis in SF symmetries and simulations that lead to services being provided to the wrong customers and an increase in maintenance costs [6]. Poor quality of the data employed in BDA for digital symmetry is a significant cost factor for many manufacturing enterprises

Objectives

Methods

Results

Discussion

Conclusion