Digital Twin Modeling in Virtual Enterprises and Autonomous Manufacturing Systems: Deep Learning and Neural Network Algorithms, Immersive Visualization Tools, and Cognitive Data Fusion Techniques.

• Author: Robinson, Rachel

1. Introduction

   Enterprise resource planning and manufacturing execution systems require machine-readable semantic data in digital twin modeling. The purpose of my systematic review is to examine the recently published literature on deep learning and neural network algorithms, immersive visualization tools, and cognitive data fusion techniques and integrate the insights it configures on digital twin modeling in virtual enterprises and autonomous manufacturing systems. By analyzing the most recent (2022) and significant (Web of Science, Scopus, and ProQuest) sources, my paper has attempted to prove that digital twin techniques and technologies develop on augmented reality and reinforcement learning algorithms, real-time robot motion control and planning, and resource scheduling by harnessing computer-generated virtual objects. The actuality and novelty of this study are articulated by addressing digital twin-based smart production management, that is an emerging topic involving much interest. My research problem is whether cognitive data mining algorithms and predictive analytics assist digital twin technology across smart manufacturing plants (Andronie et al., 2021a, b, c; Lazaroiu et al., 2017) as regards operational performance, real-time operational and product development processes, and product lifecycle management.

   In this review, prior findings have been cumulated indicating that the digital twin of manufacturing system can monitor and enhance the product development process. The identified gaps advance the relationship between artificial intelligence technology, deep learning and neural network algorithms, and digital twin systems. My main objective is to indicate that data mining tools, prescriptive and predictive analytics, and cognitive data fusion techniques enable proactive maintenance in smart factories. This systematic review contributes to the literature on digital twin-enabled smart industrial systems by clarifying that product design and manufacturing digitalization can carry out product validation and seamless data transmission in virtual space by use of machine tools and intelligent process planning algorithms. This research endeavors to elucidate whether by integrating data mapping and processing, simulated behavior of production systems can be optimized in virtual enterprises and autonomous manufacturing systems. My contribution is by integrating research findings indicating that machine learning algorithms can assist in smart process manufacturing by harnessing visualization capabilities and data mining tools.

2. Theoretical Overview of the Main Concepts

   Digital twin-driven smart manufacturing systems and machine tools require plant equipment diagnosis and sensor data while simulating and forecasting production processes in a virtual environment. Computational prediction tools and algorithms integrate real-time sensor data to assist in simulation modeling throughout automated manufacturing processes. The manuscript is organized as following: theoretical overview (section 2), methodology (section 3), machine tools and intelligent process planning algorithms in digital twin technology (section 4), sensing data in digital twin simulation modeling (section 5), digital twin-driven smart manufacturing systems and machine tools (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

   Throughout March 2022, I performed a quantitative literature review of the Web of Science, Scopus, and ProQuest databases, with search terms including "digital twin modeling" + "virtual enterprises," "autonomous manufacturing systems," "deep learning and neural network algorithms," "immersive visualization tools," and "cognitive data fusion techniques." The search terms were determined as being the most employed words or phrases across the analyzed literature. As I inspected research published in 2022, only 148 articles satisfied the eligibility criteria. By eliminating controversial findings, outcomes unsubstantiated by replication, too imprecise material, or having similar titles, I decided upon 21, generally 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, Dedoose, ROBIS, and SRDR (Figures 1-6).

4. Machine Tools and Intelligent Process Planning Algorithms in Digital Twin Technology

   Digital twin-based monitoring can synchronize real-time machine data, predict lifecycle and maintenance, and track and visualize product location (Huang et al., 2022; Saavedra Sueldo et al., 2022; Son et al., 2022) across autonomous manufacturing. Digital twins develop on discrete-event simulators and automatic devices to articulate production process modeling across virtual robotic environments in smart manufacturing plants. Product design and manufacturing digitalization can carry out product validation and seamless data transmission in virtual space by use of machine tools and intelligent process planning algorithms.

   Digital twin applications integrate machine monitoring, data analytics, product design processes, and immersive visualization systems (Bao et al., 2022; Bhandal et al., 2022; Kombaya Touckia et al., 2022; Onaji et al., 2022) across factory floors. Enterprise resource planning and manufacturing execution systems require machine-readable semantic data in digital twin modeling. By integrating data mapping and processing, simulated behavior of production systems can be optimized in virtual enterprises and autonomous manufacturing systems...