Digitalisation and servitisation of machine tools in the era of Industry 4.0: a review

Abstract

Machine tools play a pivotal role in the manufacturing world since their performance significantly affects the product quality and production efficiency. In the era of Industry 4.0, machine tools are expected to have a higher level of accessibility, connectivity, intelligence, adaptivity, and autonomy. With the rapid development and application of various Industry 4.0 technologies, digitalisation and servitisation of machine tools have become a new research trend. However, few review articles on the development of machine tools in the context of Industry 4.0 have been reported. To understand the current status of digitalisation and servitisation of machine tools, this paper provides a systematic literature review combining both bibliometric and qualitative analysis. Our review results provide a comprehensive and in-depth understanding of recent advancements of digitalisation and servitisation of machine tools, including the key enabling technologies, methods, standards, architectures, and applications. Furthermore, we propose a novel conceptual framework of Cyber-Physical Machine Tool (CPMT) as a systematic approach to achieving digitalisation and servitisation of next-generation machine tools. Finally, major research issues, challenges, and future research directions are discussed. This work will help researchers and industrial practitioners spark new ideas for developing the next-generation machine tools in the era of Industry 4.0.

Smart and flexible manufacturing systems using Autonomous Guided Vehicles (AGVs) and the Internet of Things (IoT)

“…In the first step, a literature review identified the gaps in previous studies; the review uncovered four key themes and provided insights to guide a follow-up empirical investigation and discussion of the case results. A literature review is suitable for investigating and exploring the most current application developments in Industry 4.0 and finding their future potential (Liu, Zheng, and Xu, 2021;Winkelhaus and Grosse, 2019;Zheng et al, 2020). The second step is a case study investigation of AGV implementation within a manufacturing company aiming to develop a system design model that can be used in smart, flexible manufacturing systems.…”

“…The selected databases provide access to articles related to the topic under investigation and have been used in similar studies (Ghobakhloo et al, 2021;Liu, Zheng, and Xu 2021;Winkelhaus and Grosse, 2019;Zheng et al, 2020). Duplicate results were omitted, and 75 articles were included in the review after reading each article.…”

“…Industry 4.0 as a concept was originally conceived in Germany in 2011 to build the direction of Germany's economic policy based on new technological innovations (Mosconi, 2015). However, soon Industry 4.0 was widely accepted to define the digital transformation of manufacturing systems worldwide (Liu, Zheng, and Xu 2021). Industry 4.0 technologies, such as Autonomous Guided Vehicles (AGVs) and the Internet of Things (IoT), disrupt traditional manufacturing and industrial practices toward flexible manufacturing systems with enhanced productivity and efficiency (Wagner and Walton 2016).…”

A Novel Multiview Sampling-Based Meta Self-Paced Learning Approach for Class-Imbalanced Intelligent Fault Diagnosis

“…In the continuous iteration of the above three steps, the samples with large loss values are regarded as samples with low quality, and they are deleted from the training datasets by assigning them a small weight or 0 to reduce or avoid the negative impact of such samples on the performance of the classifier. Meanwhile, in the self-paced learning model shown in (1), age parameters 𝜆 are hyperparameters that need to be set for self-paced learning. However, the age parameter setting of self-paced learning usually requires priori knowledge of data.…”

“…ITH a prevailing development of the manufacturing industry towards digitization and servitisation [1], datadriven intelligence with advanced analytics has become one of the key enablers for the intelligent manufacturing process, such sampling methods such as Easyensemble [17] and clustering analysis and instance selection [18]. At present, data-level methods have been widely applied to intelligent fault diagnosis.…”