ABSTRACT Integrating digital representations into industrial automation offers substantial benefits, particularly in enhancing the understanding and optimization of manufacturing processes during runtime, as exemplified by the KI.Fabrik (translated as AI.Factory) at the Deutsches Museum in Munich (https://kifabrik.mirmi.tum.de/). Two use cases illustrate these advantages: dynamic fault handling, where strategies are identified and evaluated within the digital twin (DT) to maintain operational continuity, and dynamic task scheduling optimization based on the real-time status of the field-level system. Beyond enabling new use cases by integrating a live DT into industrial automation, strict hard real-time and reliability requirements should be met, posing significant challenges because of various factors. Among the challenges, the stringent requirements for real-time performance and reliability create a bottleneck in the volume of data that can be utilized. Consequently, an exact integration between data exploration processes within the DT and its response is essential to meet these demands. Addressing these challenges cannot be achieved through a single technology alone but requires a collective approach involving multiple domains, operational phases, and a holistic perspective on signal flow and processing. This paper presents a DT architecture that integrates concepts from skill-based systems, multi-agent systems (MAS), and DT technologies across the entire lifecycle of an automated production plant. It is demonstrated through two use cases, showing how DTs can be used at runtime. The use cases are embedded within a field-level control architecture based on programmable logic controllers, utilizing open platform communications unified architecture and message queuing telemetry transport (MQTT) as representative industry-standard communication protocols.
ABSTRACT Conventional pretreatment methods used in metallic textile printing are associated with high water consumption, intensive chemical use, and significant wastewater generation. This study investigates low-pressure air plasma treatment as an environmentally sustainable pretreatment strategy for metallic pigment printing on cotton fabrics. Gray and bleached woven cotton fabrics were exposed to air plasma at 200 W for 3 and 5 min before screen printing with gold- and silver-based metallic pigments. The effects of plasma treatment on fabric surface chemistry and morphology were evaluated using contact angle measurements, attenuated total reflectance-Fourier transform infrared spectroscopy, scanning electron microscopy (SEM), and X-ray photoelectron spectroscopy (XPS). Plasma treatment significantly increased the hydrophilicity of both cotton substrates, reducing liquid penetration time from 61 s to less than 10 s for bleached cotton and from more than 20 min to 6 s for gray cotton. ATR-FTIR and XPS analyses confirmed the formation of oxygen-containing functional groups, whereas SEM images showed surface etching and increased roughness that enhanced pigment anchorage. The improved surface functionality translated into superior metallic print performance. Plasma-treated fabrics exhibited enhanced color fastness to washing, rubbing, perspiration, and light compared with untreated fabrics. The greatest improvement was observed after 5 min of plasma exposure, particularly for gold pigment prints. However, SEM analysis revealed that prolonged exposure (5 min) may lead to increased surface erosion, highlighting the need for careful optimization to balance surface activation with the preservation of fiber integrity. Ultraviolet-visible spectroscopy of wash effluents demonstrated lower pigment release from plasma-treated samples, confirming improved pigment retention and reduced wastewater contamination. The results demonstrate that low-pressure air plasma treatment can replace conventional wet chemical pretreatments for metallic textile printing, offering substantial reductions in water use, chemical consumption, and pigment discharge. The approach provides a practical route toward cleaner and more sustainable textile production, particularly for emerging textile industries.
ABSTRACT Digital twin (DT) technology has demonstrated advantages in various industries, including manufacturing, service, and healthcare. In particular, the significance of this technology has grown substantially in the manufacturing sector, particularly in light of Industry 4.0 developments. In the past ten years, much research has been conducted on the framework and methods for DT implementation in a manufacturing system. However, the current status of DT implementation remains unclear, particularly about the level of integration, which refers to the extent and direction of data exchange between the physical system and its digital counterpart, and the extent of coverage across manufacturing system components such as machines, tools, workers, and control systems. This study presents a systematic literature review to examine the current status of DT implementation about key manufacturing system components and provides directions for future research. It first explores the purpose and historical background of DTs, as well as the key challenges associated with their implementation. Based on these insights, the study then proposes a four-step planning framework for implementing an intelligent DT in manufacturing systems.
ABSTRACT Momentum is building to transition from a linear (take-make-use-discard) economy into a more circular one in which materials are kept in the economy through value-retention and -recovery processes. This momentum is taking the form of shifts in consumer demand, policies, and business models. As the producer of products and materials, the manufacturing sector is integral to this transition. Voluntary, consensus-based standards are also key to this shift, as they establish foundational terminology; technical guidance in the form of best practices for production; consistent, measurable, and comparable responses to changing consumer demand and regulatory environments; and transparency for consumers and society on product quality and embedded impacts. Despite ongoing momentum, a 2022 survey and workshop led by ASTM Committee E60 on Sustainability found that there was no cohesive, systematic plan for creating the circular economy standards necessary for the manufacturing sector to remain competitive. Results from the survey and workshop were used to develop a roadmap for manufacturing standards across the product life cycle (i.e., from design through production, use, and end of use). Some of these standards are in development now at organizations like ASTM International and the International Organization for Standardization using a consensus-based process; however, many others require new research and development to reach their full potential. This paper identifies three areas, where additional pre-standardization research is needed—design for circularity, system-level modeling and tools, and digital threads—and presents open research questions for future work in each area. Although the research areas are distinct, they collectively require advances in measurement science to enable a systems approach to the circular economy transition; these advances include the development of comparable metrics, standard test methods, and interoperability standards. Advancing research in these areas will also help manufacturers assess progress toward circularity goals. This paper aims to inspire researchers to answer these research questions and help create voluntary, consensus-based standards to support circular manufacturing.
ABSTRACT The circular economy has emerged as a strategy to address global challenges, such as overconsumption, and is linked to the adoption of consistent business models designed to create, deliver, and adequately capture value. Among circular business models, product-service systems (PSS) are a key strategy to achieve circularity, combining tangible products with intangible services to meet customer needs. However, the sustainability of PSSs is not guaranteed, as the environmental impact depends significantly on their configuration and management. Thus, they must be carefully designed to address potential challenges, such as rebound effects (REs), which could hinder PSSs’ sustainability and are related to additional activities, user behavioral changes, and market transformation, depending on the PSS archetype. Although the literature recognizes the significance of REs in hindering PSSs’ sustainability, further research is needed to deepen the understanding of this phenomenon. Addressing this gap, this study conducts a systematic literature review to investigate and analyze how REs manifest in different PSS archetypes, identify their triggers, and propose potential mitigation strategies. This study has both theoretical and practical implications. From a theoretical perspective, the study systematizes the existing knowledge on REs in PSSs. It proposes a systematization of the current state of the art on the topic and provides a classification of possible REs within PSS implementation, their main triggers, and mitigation strategies. Finally, it proposes potential theory-based avenues for future research in the field. From a practical perspective, the study may help PSS providers in identifying and understanding possible REs and putting in place mitigation strategies.
Over the years, significant advancements have been made in the field of robotics, with a strong emphasis on automating industrial tasks, reducing human effort, and improving work efficiency. Biologically inspired robotics is a subset of robotics that draws inspiration from natural organisms to achieve greater efficiency, flexibility, and maneuverability. Among these, snake robots excel in navigating complex environments where traditional mobile robots struggle. This paper presents the design and development of a serpentine robot for applications such as excavation and inspection. The developed prototype is 3D-printed using poly lactic acid, ensuring a lightweight and customizable design. The robot features a modular structure, enabling serpentine motion through MG995 plastic gear servo motors, which are controlled using an Arduino microcontroller. Additionally, the end effector incorporates a spiral auger, allowing the robot to dig through soil and debris effectively. A radio frequency (RF)-based transmitter and receiver system enables remote control operation. A night-vision spy camera mounted on the robot provides real-time visual feedback via Wi-Fi, further improving its operational capabilities. Furthermore, the modular design allows for the integration of additional sensors in the future to improve perception and adaptability for specific applications. With its ability to navigate narrow and uneven terrains, this robot represents a significant advancement in biologically inspired robotics, offering a versatile platform for various challenging tasks.
Over the last few decades, much research has been conducted to systematically support the facets of the product and process in biologically inspired design (BID). No research identifies or articulates the influential types of knowledge used in the ideation and realization of BID solutions. The objective is to identify the influential types of knowledge (process, product, or combination) in the ideation and realization of BID solutions. Data from a project to develop and demonstrate prototypes of a mobility system of lunar vehicles are used. The design team undertakes a systematic process involving requirements identification, idea generation, concept development, evaluation and selection, prototype development, and testing. The team uses support comprising a systematic framework for designing and Idea-Inspire, which provides process-knowledge and product-knowledge, respectively, to generate ideas for the identified requirements. Twenty concepts are created from these ideas, and two concepts are selected for prototyping. The types of knowledge used: to generate ideas, to generate ideas used in concepts, and to generate ideas used in prototypes, which are chosen from the concepts, are identified, to assess the types of knowledge used in ideation and realization of solutions in BID. The significant findings are as follows: (a) most ideas are generated when Idea-Inspire and the framework are used together and (b) most ideas generated with Idea-Inspire and the framework are used in the 20 concepts created from the pool of ideas and the 2 concepts selected for prototyping. This shows the significance of using process-and product-knowledge together in ideation and realization.
Small and medium enterprises (SMEs) play a vital role in India's manufacturing sector but often struggle with quality control, environmental compliance, and global competitiveness. However, they face significant challenges in achieving operational excellence, sustainability, and global competitiveness. This study explores the integration of six sigma methodologies with sustainable bioinspired manufacturing principles to improve performance and minimize environmental impact. Using a literature review and empirical analysis, the study identifies key critical success factors (CSFs) that influence six sigma implementation in Indian SMEs. Statistical analysis shows that CSFs significantly affect performance, offering insights for strategic six sigma adoption. Based on the best-worst method analysis, "selection of the right project" (weight = 0.3287), "employee training" (0.1862), and "infrastructure availability" (0.1076) emerge as the top-ranked CSFs, collectively contributing over 62 % in improving the operational performance of SMEs. This study uniquely contributes by examining the intersection of six sigma and bioinspired manufacturing specifically within Indian SMEs, an area that remains underexplored in the literature. Unlike prior studies that treat these domains separately, the present work investigates how bioinspired design principles can be practically integrated into six sigma's structured framework to achieve sustainability and quality objectives.
This study investigates the optimization of key process parameters in fused filament fabrication (FFF) to enhance the mechanical performance and material efficiency of additively manufactured Acrylonitrile Butadiene Styrene structures. Three lattice geometries, co-axial joint structure (CAJS), curved wall structure, and mixed star structure, were fabricated whereas varying layer height (LH) (0.1-0.3 mm), infill density (60 %-100 %), and infill pattern (line, grid, and hexagonal). A full factorial design of experiments was employed to analyze the influence of these parameters on compressive strength, surface roughness, and the strength-to-apparent density ratio. Results indicate that infill density is the dominant factor affecting compressive strength, which increased from 42.23 to 83.72 MPa as infill increased from 60 % to 100 %. Surface roughness was primarily governed by LH, rising from 6.86 mu m at 0.1 mm to 30.47 mu m at 0.3 mm attributed to the staircase effect. The highest strength-to-apparent density efficiency occurred at intermediate infill densities (60 %-80 %), indicating improved load-bearing efficiency with reduced material consumption. Multi-objective optimization using the Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) method identified the optimal configuration as CAJS with a 0.1 mm LH, 80 % infill density, and a grid pattern (TOPSIS score = 0.812). Finite element analysis predicted compressive strength with less than a 4 % deviation from experimental results. The study provides an integrated process-structure-property framework for optimizing lightweight and mechanically efficient FFFprinted polymer components.
Although industrial control systems are crucial for enhancing safety and reliability in the chemical process industries (CPI), they also introduce cybersecurity vulnerabilities. This article presents a comprehensive method for prioritizing and exploring these vulnerabilities in CPI process control systems, offering structured strategies for assessing and mitigating cyber risks. Our approach, namely an integrated cyber-risk-based process safety (RBPS) framework, integrates the cybersecurity RBPS management system with cyber process hazard analysis, layer of protection analysis, common vulnerability scoring system, and exploit prediction scoring system. To demonstrate the effectiveness of this method, we assessed the cybersecurity risks associated with a distillation column and its overhead receiver in a refinery. In this case study, we evaluated four threat vectors: data manipulation, denial of service (DoS), privilege escalation, and credential stuffing using the cyber-RBPS framework. The results indicated that privilege escalation posed the highest risk in this specific example. These findings underscore the necessity of a robust defense-in-depth strategy encompassing advanced technological safeguards, continuous monitoring, and workforce training.
In the era of Industry 4.0, digital twin (DT) has gained substantial attention across industries for its capability to create dynamic digital representations of physical systems. A DT facilitates continuous data exchange between a physical asset and its virtual counterpart, enabling real-time monitoring and predictive analysis. A critical precursor to developing a full DT is digital shadow (DS), which digitally mirrors the behavior of a physical system using simulation tools. The effectiveness of a DS largely depends on the accuracy and fidelity of the input data. This paper proposes a step-by-step methodology for developing a DS using Discrete event simulation (DES) in FlexSim. The approach begins with a product architecture analysis to identify key process variables, enabling effective product family classification. This is followed by the selection of suitable DES software, with a focus on accommodating high product variability typical in complex manufacturing systems. A dual-mode data acquisition strategy, combining manual time studies with sensor-generated data, is then applied to capture both observable and high-resolution operational data. A comparative case study is conducted using two DS models, one based on manually collected data and the other on high-fidelity sensor data, within a high-mix, high-volume manufacturing setting. Results demonstrate that DS models built with high-fidelity data significantly enhance simulation precision. The second model successfully identified a production line imbalance and provided actionable insights through a micro study of manual activities that were executed in the assembly process. Furthermore, the proposed future state, modeled through the DS, showed a potential 20 % increase in production output, contributing to operational efficiency. This study aims to underscore the value of DS as a reliable and scalable tool for analyzing complex systems, supporting informed decision-making, and serving as a critical step toward the implementation of a complete DT.
Mobile hydraulic cranes play a significant role in dynamic construction sites. With the increased demand for smart manufacturing in the production of large structures such as ships, buildings, and windmills, the need for digital twins (DT) of production systems rises, as well. DTs allow for simulation and monitoring of production processes. Our paper presents a DT of a mobile knuckle boom crane. The system is composed of a mobile knuckle boom crane, a DT-platform and a microcontroller allowing for bidirectional communication between the crane and the DT-platform. In the DT-platform, the desired position of the crane tip can be set in Cartesian space, and the joint values are derived by inverse kinematics. Considering the virtual environment and the control constraints of hydraulic systems, collision free point-to-point motion planning is done. The planned joint positions are piecewise transferred to the microcontroller, which controls the joint positions in real-time via a proportional-integral controller. During the execution of the motion, the physical asset is monitored, and its status is visualized with a digital shadow in the virtual environment. With the introduction of heavy-duty hydraulic equipment into a DT-platform, we enable a data-driven approach to produce large infrastructures, supporting the digitalization of construction workflows.
This study presents a validated multicriteria decision-making (MCDM) framework for supplier selection that integrates large language models (LLMs) to enhance the evaluation process. Traditional supplier selection methods often rely on simplified scoring mechanisms that may overlook nuanced supplier characteristics. We propose a hybrid approach combining weighted scoring methods with DistilGPT-2 to generate interpretable supplier assessments. Using a data set of 362 Vietnamese textile and apparel companies with 64 evaluation features, our method calculates composite scores based on six key performance categories: cost, delivery, quality assurance, service, customer service, and sustainability. The LLM component processes these numerical scores to generate contextual analyses that aid decision-makers in understanding supplier strengths and weaknesses. Validation against expert human evaluations shows 78.3 % agreement in selection decisions, with Cohen's kappa = 0.672 indicating substantial inter-rater reliability. Statistical analysis reveals significant correlations between sustainability and quality assurance (r = 0.543, p < 0.001), and delivery performance with overall supplier acceptability (r = 0.621, p < 0.001). A comparison with the traditional technique for order preference by similarity to the ideal solution and analytic hierarchy process methods demonstrates superior interpretability while maintaining comparable decision accuracy. Results show that 23 suppliers (6.4 %) met selection criteria, whereas 339 (93.6 %) required further evaluation, highlighting the complexity of supplier assessment. This work demonstrates how LLMs can augment traditional MCDM approaches by providing interpretable narratives alongside quantitative metrics.
Lubrication is crucial for managing the cutting zone temperature during machining, especially in grinding. Conventional cutting fluids, often applied in flood cooling systems, effectively manage temperature and extract heat from the machining interface. However, the high volume and toxic nature of conventional lubricants have negative environmental impact and pose health risks for machine operators. A promising alternative is the use of minimum quantity lubrication (MQL) and nanofluid minimum quantity lubrication (NFMQL) techniques. Although MQL is successful in addressing the environment and machine operator health-related issues, but performance does not yet fully match that of conventional flood cooling. The effectiveness of MQL could be improved by integrating nanoparticles, whereas worker and environmental safety can be improved by using vegetable oils. This study investigates NFMQL with Al2O3 nanoparticles in combination with three vegetable oils for surface grinding of AISI52100 alloy steel, using response surface methodology. Flood cooling and pure MQL strategies were used as benchmarks to compare the outcomes of NFMQL. The results demonstrate that NFMQL effectively improves the grinding ratio (G-ratio) and decreases surface roughness while enhancing surface quality in comparison to pure MQL. Compared with flood cooling, NFMQL resulted in reduced surface roughness and improved surface quality, whereas the G-ratio remained comparable to those of the flood cooling system. The results indicate that the proposed lubrication strategy can enhance cutting efficiency by improving machining quality while also delivering environmental and economic benefits to the industry and reducing potential health risks for workers.
With advances in Industry 4.0 and the growing availability of low-cost sensors, high-frequency data collection has become more accessible for manufacturing industries. These technologies enable the creation of digital shadows (DSs) to visualize and monitor the production processes. In this context, the DS captures the physical manufacturing process in a virtual environment, enhancing process monitoring and providing a dynamic, interactive, and unidirectional flow of data from the real world to the virtual model for performance analysis and maintenance planning. This article presents a modular approach by establishing foundational methods for transitioning towards DS by creating a digital model of a semiautomatic process of polyvinyl chloride (PVC) welding in a manufacturing environment. Utilizing Industrial Internet of Things-enabled sensing systems, the proposed framework follows a modular approach to develop a sensor architecture and demonstrates real-time data acquisition within the production line. The captured operational data, reflecting the operational status of the equipment, can be called the early-stage process DS. These data are then processed into the informationknowledge-modeling structure through live dashboards and analytics and further integrated analytics, ensuring cost-effectiveness and ease of deployment. Real-time monitoring will support performance evaluation and machine metrics tracking, addressing the complexities of for the evolution from DS to DT in PVC welding manufacturing.
Digitalized manufacturing processes necessitate a shift from traditional production control systems to more intelligent frameworks. Existing systems reliant on programmable logical controllers fall short in handling the influx of data generated by the Internet of Things layer and the array of IT systems integral to modern operations. This article presents technical developments made within MESLedger, a collaborative project aiming to enhance manufacturing execution by integrating blockchain technology and artificial intelligence. The first part of our work investigates how deep reinforcement learning, particularly the proposed Dual Attention Network for Multi-Objective Proximal Policy Optimization, can optimize job scheduling by balancing objectives such as makespan and energy consumption. This approach formulates the Flexible Job Shop Scheduling Problem as a Markov decision process and uses actor-critic networks enhanced with dual attention mechanisms to generate adaptive and context-aware scheduling strategies. The second part explores how blockchain technology, specifically Hyperledger Fabric, can be used to secure communication within collaborative industrial environments by managing critical manufacturing processes through smart contracts and decentralized architectures. Together, these components form the foundation of an intelligent manufacturing execution systems environment capable of dynamically analyzing data and orchestrating operations based on customizable performance priorities.
The progress of smart manufacturing systems demands the integration of multiple artificial intelligence (AI) paradigms to support the decision-making process in increasingly complex and dynamic environments. Although data-driven approaches excel in pattern discovery and process optimization, they often lack interpretability and the ability to incorporate specialized knowledge. Conversely, symbolic approaches provide transparency and explainability but may present limitations in adapting to unforeseen scenarios. This article presents toward a hybrid semantic framework for manufacturing intelligence that systematically integrates data-driven and symbolic AI approaches through a three-layer hierarchical structure: physical layer, digital layer, and cognitive layer. The framework incorporates an intelligence orchestration layer and a semantic alignment layer to enable semantic communication between heterogeneous components and harmonize knowledge from diverse sources. The experimental evaluation focuses on aerospace sheet metal manufacturing parts, demonstrating the integration between automated feature extraction and specialized knowledge formalization through ontologies. A conversational interface powered by large language models enables natural language interaction with specialized ontologies, providing automated inference capabilities and explainable decision-making. The results validate the feasibility of combining automated characteristic extraction with semantic knowledge representation, establishing a foundation for hybrid AI systems in manufacturing environments. The proposed framework addresses critical challenges in cyber-physical production systems by enabling adaptability, explainability, and real-time decision-making while maintaining semantic consistency between empirical and formal knowledge sources.
This study explores how various fabrication parameters impact the thermal, rheological, and mechanical properties of composite filaments fabricated with reinforcement of secondary (2 degrees) recycled polylactic acid (PLA) with waste wood dust (WD) using a mechanical blending technique. The filaments were produced by adjusting the temperature, torque, and load a twin-screw extruder for use in applications of three-dimensional (3D) printing. This study demonstrates that melt flow index of filament reduces with an increase in the reinforcement percentage beyond certain limits. In this study, twin-screw extrusion has been used to prepare feedstock filament by reinforcing WD with 6 wt.% to impart required thermal, mechanical, and morphological properties. It has been examined that thermal, mechanical, and morphological properties of 2 degrees PLA reinforced with 6 % by weight of WD exhibits superior peak strength (PS), low porosity percentage, and better thermal stability as compared with other filaments fabricated at different weight percentages on the basis of extrusion parameters. Optimal parameter setting that exhibits maximum PS (31.81 MPa), percentage elongation at break (%BE) (8.86 %) at 7.5-kg load, 175 degrees C temperature, 0.1-Nm torque and 7.5-kg load, 185 degrees C temperature, 0.2-Nm torque, respectively. This study not only emphasizes the impact of fabrication parameters on filament properties but also highlights the sustainable manufacturing aspect of using 2 degrees PLA and WD as reinforcements. By incorporating recycled and waste materials, this approach contributes to reducing plastic waste and promoting sustainable and environmentally responsible manufacturing practices.
Energy, environment, and economy are driving forces behind adopting circular economy principles in industrial production, particularly in the sheet metal industry, where resource optimization and waste reduction are prioritized. Remanufacturing, especially in automotive manufacturing, offers significant material reuse and conservation opportunities. However, challenges persist in developing effective product designs and remanufacturing methods for material recovery. Artificial intelligence (AI), machine learning, and big data analytics present promising solutions to these obstacles, facilitating sustainable practices in metal product re-manufacturing. Predictive models, such as those for incremental sheet forming (ISF), streamline the assessment of remanufacturing feasibility, reducing costs and time associated with technical complexities. Integration of AI enables forecasting potential failures and optimizing remanufacturing processes, resulting in considerable savings in effort, energy, and time while advancing circular economy initiatives. In this study, a series of ISF experiments was conducted using a computer numerically controlled machine to redeform a contoured part. Subsequently, using an experimental dataset, an experimental dataset, three AI classifier models-artificial neural network, random forest, and support vector machine (SVM)-were developed to assess the feasibility of remanufacturing a predeformed sheet metal part. SVM emerged as the top-performing algorithm, demonstrating robust classification capabilities. The present study focuses on a limited parameter set that overlooks other influential factors such as the previous manufacturing processes, material composition, and sheet thickness. Expanding the scope to incorporate these factors will enable more accurate assessments and optimized manufacturing processes, ultimately benefiting the remanufacturing industry.
Since the introduction of Industry 4.0, digital twin technology has advanced dramatically, and its applications have been extensively discussed. Through digital twins, real-time connected production systems are anticipated to be more efficient, resilient, and sustainable, facilitating communication and connectivity between digital and physical systems. However, challenges remain in environmental performance and in integration of virtual reality (VR) and artificial intelligence (AI). Further exploration of digital twin technologies is needed to validate the real-world impact and benefits. This paper investigates these challenges by implementing a real-time digital twin based on the ISO 23247, Automation Systems and Integration-Digital Twin Framework for Manufacturing, (Digital twin framework for manufacturing), connecting the physical factory and simulation software with VR capabilities. This digital twin system provides cognitive assistance and a user-friendly interface for operators, thereby improving cognitive ergonomics. The connection of the Internet of Things platform allows the digital twin for real-time bidirectional communication, collaboration, monitoring, and assistance. A laboratory-scale drone factory was used as the digital twin application to test and evaluate the ISO 23247 standard as well as its potential benefits. Additionally, AI integration and environmental performance key performance indicators have been considered as the next stages to improve VR-integrated digital twins. This paper further discusses how digital twins contribute to the improvement of the environmental performance of production systems, primarily from the perspective of data inventory management. Supported by a solid theoretical foundation and a laboratory-scale demonstration of the VR-integrated digital twins in a drone framework, the paper bridges the gap between possible technological integrations and the advancement of digital twins framework based on ISO 23247.
