Deep Learning-based Computer Vision Algorithms, Immersive Analytics and Simulation Software, and Virtual Reality Modeling Tools in Digital Twin-driven Smart Manufacturing.

AuthorLyons, Nancy
  1. Introduction

    Data processing capabilities and cognitive data analytics enable immersive virtual reality simulations in a digital twin environment. The purpose of my systematic review is to examine the recently published literature on digital twin-driven smart manufacturing and integrate the insights it configures on deep learning-based computer vision algorithms, immersive analytics and simulation software, and virtual reality modeling tools. By analyzing the most recent (2022) and significant (Web of Science, Scopus, and ProQuest) sources, my paper has attempted to prove that assembly workflow and machining workshop digital twins integrate simulation capabilities and visual editing tools, and leverage virtual equipment in product manufacturing. The actuality and novelty of this study are articulated by addressing virtual manufacturing and digital twin technologies, that is an emerging topic involving much interest. My research problem is whether digital twin-based cyber-physical production systems and industrial automation are instrumental in machining process performance of smart factories.

    In this review, prior findings have been cumulated indicating that digital twin-based cyber-physical production systems deploy smart factory data across virtual environments. The identified gaps advance real-time sensing, virtual twinning techniques, and planning and scheduling data across cloud-based cyber-physical systems. My main objective is to indicate that digital twin technologies further virtual data augmentation to increase production efficiency. This systematic review contributes to the literature on virtual twin modeling by clarifying that observational and simulation data assist computer vision techniques and 3D virtual simulation technology throughout product lifecycle monitoring. This research endeavors to elucidate whether machining operations across intelligent manufacturing environments (Andronie et al., 2021; Lazaroiu et al., 2017; Lazaroiu et al., 2020) necessitate data collection, integration, modeling, and simulation. My contribution is by integrating research findings indicating that digital twin-driven product design and virtual manufacturing systems further product development efficiency.

  2. Theoretical Overview of the Main Concepts

    Smart manufacturing systems and processes necessitate data detection and visualization accuracy, real-time monitoring of operations, and robot learning algorithms. Intelligent manufacturing equipment is pivotal in equipment and process performance monitoring, maintenance planning and scheduling, and production line optimization through seamless data gathering and analysis. Simulating virtual manufacturing systems require data modeling and intelligent sensing devices. Real-time data visualization, coding and identification technology, and analytics capabilities are decisive in real-time remote monitoring of production process in unit operation. Smart manufacturing system planning and control deploy data simulation and diagnosis by use of dynamic digital twins. The manuscript is organized as following: theoretical overview (section 2), methodology (section 3), reconfiguration design, production planning and scheduling, and real-time state monitoring in virtual twin modeling (section 4), digital twin-based cyber-physical production systems and industrial automation (section 5), digital twin and augmented reality-based cyber-physical production systems (section 6), discussion (section 7), synopsis of the main research outcomes (section 8), conclusions (section 9), limitations, implications, and further directions of research (section 10).

  3. Methodology

    I carried out a quantitative literature review of ProQuest, Scopus, and the Web of Science throughout February 2022, with search terms including "digital twin" + "deep learning-based computer vision algorithms," "immersive analytics and simulation software," "virtual reality modeling tools," and "smart manufacturing." The search terms were determined as being the most employed words or phrases across the analyzed literature. As I analyzed research published in 2022, only 154 papers met the eligibility criteria. By removing controversial or unclear findings (scanty/unimportant data), results unsupported by replication, undetailed content, or papers having quite similar titles, I decided on 23, chiefly empirical, sources (Tables 1 and 2). Extracting and inspecting publicly accessible files (scholarly sources) as evidence, before the research began no institutional ethics approval was required. Data visualization tools: Dimensions (bibliometric mapping) and VOSviewer (layout algorithms). Reporting quality assessment tool: PRISMA. Methodological quality assessment tools include: AXIS, Distiller SR, ROBIS, and SRDR (Figures 1-6).

  4. Reconfiguration Design, Production Planning and Scheduling, and Real-Time State Monitoring in Virtual Twin Modeling

    Smart factories integrate real-time sensing, virtual twinning techniques, and planning and scheduling data across cloud-based cyber-physical systems (Hu, 2022; Li et al., 2022a; Son et al., 2022) to optimize shop-floor production management, manufacturing task management, and product lifecycle management. Real-world perceptions and autonomous optimization assist data-enhanced digital twins through sensing action dynamic industrial processes in smart manufacturing and cyber-physical production systems. Smart manufacturing systems and processes necessitate data detection and visualization accuracy, real-time monitoring of operations, and robot learning algorithms.

    Digital twin technology can analyze, monitor, and control machining processes (Kombaya Touckia et al., 2022; Liu et al., 2022; Onaji et al., 2022) by use of virtual mapping tools. Machine learning algorithms, virtual reality-based data analytics tools, and sensor...

To continue reading

Request your trial

VLEX uses login cookies to provide you with a better browsing experience. If you click on 'Accept' or continue browsing this site we consider that you accept our cookie policy. ACCEPT