Sign in to use this feature.

Years

Between: -

Subjects

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Journals

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Article Types

Countries / Regions

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Search Results (599)

Search Parameters:
Keywords = smart factory

Order results
Result details
Results per page
Select all
Export citation of selected articles as:
29 pages, 9177 KiB  
Article
Smart Manufacturing Application in Precision Manufacturing
by Amr T. Sufian, Badr M. Abdullah and Oliver J. Miller
Appl. Sci. 2025, 15(2), 915; https://doi.org/10.3390/app15020915 (registering DOI) - 17 Jan 2025
Viewed by 254
Abstract
Industry 4.0 presents an opportunity to gain a competitive advantage through productivity, flexibility, and speed. It also empowers the manufacturing sector to drive the sustainability revolution to achieve net zero carbon by reducing emissions in operations. In this paper, the aim is to [...] Read more.
Industry 4.0 presents an opportunity to gain a competitive advantage through productivity, flexibility, and speed. It also empowers the manufacturing sector to drive the sustainability revolution to achieve net zero carbon by reducing emissions in operations. In this paper, the aim is to demonstrate a practical implementation of a smart manufacturing application using a systematic approach based on conceptual six-gear smart factory roadmap with connectivity, integration and analytics stages to build a smart production management ecosystem using off-the-shelf technologies applied in precision manufacturing. Business benefits from the smart manufacturing application implementation are realized in terms of operational performance, economic benefits, and environmental sustainability over a period of three years (before and after smart manufacturing). The productivity improves as a result of the 47% improvement made to the machines’ utilization and the 53% reduction in the total downtime waste. Economic benefits are realized in terms of a cost saving of GBP 420 K that could cost the business and the returns of the financial investment made, which is recovered within a year. An environmental sustainability impact is realized by a reduction in the total greenhouse gas (GHG) emissions by 43%, mostly due to the reduction in the Scope 2 emissions in operations by 50%, which is significantly impacted by the reduction of energy consumption and better power consumption management. The significance of this work is the bridging of the gap between theory and practice by rapidly applying the six-gear smart factory roadmap to start, scale, and sustain the implementation of smart manufacturing applications in the manufacturing industry. This roadmap can serve as a strategic framework tool for smart manufacturing implementations. The technical architecture can serve as a guide for the practical implementation of smart manufacturing applications to reduce the complexity of development. This work also bridges the gap in academia and in industry by showcasing a real-world actual business benefits realized from smart manufacturing, as well as showcasing the practical implementations, limitations, and opportunities of smart manufacturing applications in the precision manufacturing industry, all of which reduce the internal barriers and challenges facing smart manufacturing and industry 4.0 adoption. The value realized in gaining a competitive advantage and driving environmental sustainability from smart manufacturing in this study can serve as a case study for academics and for industry business leaders, digital champions, and digital lighthouses to support value creation and to drive and accelerate smart manufacturing applications, digital transformation initiatives, and industry 4.0 adoption across the value chain. Full article
(This article belongs to the Special Issue Advancement in Smart Manufacturing and Industry 4.0)
Show Figures

Figure 1

22 pages, 3424 KiB  
Article
A Line of Sight/Non Line of Sight Recognition Method Based on the Dynamic Multi-Level Optimization of Comprehensive Features
by Ziyao Ma, Zhongliang Deng, Zidu Tian, Yingjian Zhang, Jizhou Wang and Jilong Guo
Sensors 2025, 25(2), 304; https://doi.org/10.3390/s25020304 - 7 Jan 2025
Viewed by 333
Abstract
With the advent of the 5G era, high-precision localization based on mobile communication networks has become a research hotspot, playing an important role in indoor emergency rescue in shopping malls, smart factory management and tracking, as well as precision marketing. However, in complex [...] Read more.
With the advent of the 5G era, high-precision localization based on mobile communication networks has become a research hotspot, playing an important role in indoor emergency rescue in shopping malls, smart factory management and tracking, as well as precision marketing. However, in complex environments, non-line-of-sight (NLOS) propagation reduces the measurement accuracy of 5G signals, causing large deviations in position solving. In order to obtain high-precision position information, it is necessary to recognize the propagation state of the signal before distance measurement or angle measurement. In this paper, we propose a dynamic multi-level optimization of comprehensive features (DMOCF) network model for line-of-sight (LOS)/NLOS identification. The DMOCF model improves the expression ability of the deep model by adding a res2 module to the time delay neural network (TDNN), so that fine-grained feature information such as weak reflections or noise in the signal can be deeply understood by the model, enabling the network to realize layer-level feature processing by adding Squeeze and Excitation (SE) blocks with adaptive weight adjustment for each layer. A mamba module with position coding is added to each layer to capture the local patterns of wireless signals under complex propagation phenomena by extracting local features, enabling the model to understand the evolution of signals over time in a deeper way. In addition, this paper proposes an improved sand cat search algorithm for network parameter search, which improves search efficiency and search accuracy. Overall, this new network architecture combines the capabilities of local feature extraction, global feature preservation, and time series modeling, resulting in superior performance in the 5G channel impulse response (CIR) signal classification task, improving the accuracy of the model and accurately identifying the key characteristics of multipath signal propagation. Experimental results show that the NLOS/LOS recognition method proposed in this paper has higher accuracy than other deep learning methods. Full article
Show Figures

Figure 1

24 pages, 4641 KiB  
Article
Development of a Novel Retrofit Framework Considering Industry 4.0 Concepts: A Case Study of a Modular Production System
by Rafael S. Mendonca, Mariélio da Silva, Florindo A. C. Ayres, Iury V. Bessa, Renan L. P. Medeiros and Vicente F. Lucena
Processes 2025, 13(1), 136; https://doi.org/10.3390/pr13010136 - 7 Jan 2025
Viewed by 506
Abstract
Retrofitting legacy systems provides significant advantages by addressing compatibility issues with new devices and technologies, meeting current process requirements, and increasing security and regulatory compliance. The process starts by collecting requirements and evaluating the legacy system’s attributes and limitations, followed by integrating modern [...] Read more.
Retrofitting legacy systems provides significant advantages by addressing compatibility issues with new devices and technologies, meeting current process requirements, and increasing security and regulatory compliance. The process starts by collecting requirements and evaluating the legacy system’s attributes and limitations, followed by integrating modern technologies to improve efficiency, streamline processes, and enhancing performance and interoperability while leveraging existing facilities to reduce costs. A systematic approach ensures that updates align with modern technological standards, with performance evaluations conducted via qualitative and quantitative methods and system maturity assessed according to the Reference Architecture Model for Industries 4.0 (RAMI 4.0 model’s) criteria for intelligent factories. By incorporating digital twin (DT) capabilities, which replicate the physical state of systems and provide real-time data updates, the retrofit strategy aligns the physical system with Industry 4.0 contexts, facilitating continuous improvement and seamless integration with modern processes. The goal is to advance the legacy system technologically to ensure seamless integration with contemporary processes, validated through RAMI criteria analysis for smart factories. As part of this process, digital twin architecture was built. This architecture was the basis for building and operating digital twins in the process. The methodology was used to enhance and transform legacy systems, creating the foundation for creating a fully digital twin. Using this method, these systems can be updated to meet the requirements of Industry 4.0. This ensures that they can work with new systems and share data in real time, which improves general operations. Full article
(This article belongs to the Section Advanced Digital and Other Processes)
Show Figures

Figure 1

20 pages, 15263 KiB  
Article
An Efficient Cluster-Based Mutual Authentication and Key Update Protocol for Secure Internet of Vehicles in 5G Sensor Networks
by Xinzhong Su and Youyun Xu
Sensors 2025, 25(1), 212; https://doi.org/10.3390/s25010212 - 2 Jan 2025
Viewed by 353
Abstract
The Internet of Vehicles (IoV), a key component of smart transportation systems, leverages 5G communication for low-latency data transmission, facilitating real-time interactions between vehicles, roadside units (RSUs), and sensor networks. However, the open nature of 5G communication channels exposes IoV systems to significant [...] Read more.
The Internet of Vehicles (IoV), a key component of smart transportation systems, leverages 5G communication for low-latency data transmission, facilitating real-time interactions between vehicles, roadside units (RSUs), and sensor networks. However, the open nature of 5G communication channels exposes IoV systems to significant security threats, such as eavesdropping, replay attacks, and message tampering. To address these challenges, this paper proposes the Efficient Cluster-based Mutual Authentication and Key Update Protocol (ECAUP) designed to secure IoV systems within 5G-enabled sensor networks. The ECAUP meets the unique mobility and security demands of IoV by enabling fine-grained access control and dynamic key updates for RSUs through a factorial tree structure, ensuring both forward and backward secrecy. Additionally, physical unclonable functions (PUFs) are utilized to provide end-to-end authentication and physical layer security, further enhancing the system’s resilience against sophisticated cyber-attacks. The security of the ECAUP is formally verified using BAN Logic and ProVerif, and a comparative analysis demonstrates its superiority in terms of overhead efficiency (more than 50%) and security features over existing protocols. This work contributes to the development of secure, resilient, and efficient intelligent transportation systems, ensuring robust communication and protection in sensor-based IoV environments. Full article
(This article belongs to the Special Issue Advances in Security for Emerging Intelligent Systems)
Show Figures

Figure 1

29 pages, 6463 KiB  
Article
A Novel FS-GAN-Based Anomaly Detection Approach for Smart Manufacturing
by Tae-yong Kim, Jieun Lee, Seokhyun Gong, Jaehoon Lim, Dowan Kim and Jongpil Jeong
Viewed by 396
Abstract
In this study, we present the few-shot generative adversarial network (FS-GAN) model, which integrates few-shot learning and a generative adversarial network with an unsupervised learning approach (AnoGAN) to address the challenges of anomaly detection in smart-factory manufacturing environments. Manufacturing processes often encounter malfunctions [...] Read more.
In this study, we present the few-shot generative adversarial network (FS-GAN) model, which integrates few-shot learning and a generative adversarial network with an unsupervised learning approach (AnoGAN) to address the challenges of anomaly detection in smart-factory manufacturing environments. Manufacturing processes often encounter malfunctions or defective parts that disrupt production and compromise product quality. However, collecting and labeling sufficient data to detect anomalies is time-intensive, and abnormal data are rare, leading to data imbalances. The FS-GAN model leverages few-shot learning to enable accurate predictions with minimal data and uses the generative capabilities of AnoGAN to mitigate the scarcity of abnormal data by generating synthetic normal data. Experimental results demonstrate that FS-GAN outperforms existing models in terms of accuracy and learning speed, even with limited datasets, effectively addressing the data imbalance problem inherent in manufacturing. The model reduces dependency on extensive data collection and labeling efforts, making it suitable for real-world applications. Through reliable and efficient anomaly detection, FS-GAN contributes to production reliability, product quality, and operational efficiency in smart factories. This study highlights the potential of FS-GAN to provide a cost-effective and high-performance solution to the challenges of anomaly detection in the manufacturing industry. Full article
(This article belongs to the Section Machines Testing and Maintenance)
Show Figures

Figure 1

19 pages, 8495 KiB  
Article
Design and Development of a Precision Defect Detection System Based on a Line Scan Camera Using Deep Learning
by Byungcheol Kim, Moonsun Shin and Seonmin Hwang
Appl. Sci. 2024, 14(24), 12054; https://doi.org/10.3390/app142412054 - 23 Dec 2024
Viewed by 582
Abstract
The manufacturing industry environment is rapidly evolving into smart manufacturing. It prioritizes digital innovations such as AI and digital transformation (DX) to increase productivity and create value through automation and intelligence. Vision systems for defect detection and quality control are being implemented across [...] Read more.
The manufacturing industry environment is rapidly evolving into smart manufacturing. It prioritizes digital innovations such as AI and digital transformation (DX) to increase productivity and create value through automation and intelligence. Vision systems for defect detection and quality control are being implemented across industries, including electronics, semiconductors, printing, metal, food, and packaging. Small and medium-sized manufacturing companies are increasingly demanding smart factory solutions for quality control to create added value and enhance competitiveness. In this paper, we design and develop a high-speed defect detection system based on a line-scan camera using deep learning. The camera is positioned for side-view imaging, allowing for detailed inspection of the component mounting and soldering quality on PCBs. To detect defects on PCBs, the system gathers extensive images of both flawless and defective products to train a deep learning model. An AI engine generated through this deep learning process is then applied to conduct defect inspections. The developed high-speed defect detection system was evaluated to have an accuracy of 99.5% in the experiment. This will be highly beneficial for precision quality management in small- and medium-sized enterprises Full article
(This article belongs to the Special Issue Future Information & Communication Engineering 2024)
Show Figures

Figure 1

25 pages, 11322 KiB  
Article
A Triboelectric Nanogenerator Utilizing a Crank-Rocker Mechanism Combined with a Spring Cantilever Structure for Efficient Energy Harvesting and Self-Powered Sensing Applications
by Xinhua Wang, Xiangjie Xu, Tao Sun and Gefan Yin
Electronics 2024, 13(24), 5032; https://doi.org/10.3390/electronics13245032 - 21 Dec 2024
Viewed by 376
Abstract
With the advancement of industrial automation, vibrational energy generated by machinery during operation is often underutilized. Developing efficient devices for vibration energy harvesting is thus essential. Triboelectric nanogenerators (TENGs) based on spring and cantilever beam structures show considerable potential for industrial vibration energy [...] Read more.
With the advancement of industrial automation, vibrational energy generated by machinery during operation is often underutilized. Developing efficient devices for vibration energy harvesting is thus essential. Triboelectric nanogenerators (TENGs) based on spring and cantilever beam structures show considerable potential for industrial vibration energy harvesting; however, traditional designs often fail to fully harness vibrational energy due to their structural limitations. This study proposes a triboelectric nanogenerator (TENG) based on a crank-rocker mechanism and a spring cantilever structure (CR-SC TENG), which combines a crank-rocker mechanism with a spring cantilever structure, designed for both energy harvesting and self-powered sensing. The CR-SC TENG incorporates a spring cantilever beam, a crank-rocker mechanism, and lever amplification principles, enabling it to respond sensitively to low-frequency, small-amplitude vibrations. Utilizing the crank-rocker and lever effects, this device significantly amplifies micro-amplitudes, enhancing energy capture efficiency and making it well suited for low-amplitude, complex industrial environments. Experimental results demonstrate that this design effectively amplifies micro-vibrations and markedly improves energy conversion efficiency within a frequency range of 1–35 Hz and an amplitude range of 1–3 mm. As a sensor, the CR-SC TENG’s dual-generation units produce output signals that precisely reflect vibration frequencies, making it suitable for the intelligent monitoring of industrial equipment. When placed on an air compressor operating at 25 Hz, the first-generation unit achieved an output voltage of 150 V and a current of 8 μA, while the second-generation unit produced an output voltage of 60 V and a current of 5 μA. These findings suggest that the CR-SC TENG, leveraging spring cantilever beams, crank-rocker mechanisms, and lever amplification, has significant potential for micro-amplitude energy harvesting and could play a key role in smart manufacturing, intelligent factories, and the Internet of Things. Full article
Show Figures

Figure 1

25 pages, 9075 KiB  
Article
Optimization of Intelligent Maintenance System in Smart Factory Using State Space Search Algorithm
by Nuttawan Thongtam, Sukree Sinthupinyo and Achara Chandrachai
Appl. Sci. 2024, 14(24), 11973; https://doi.org/10.3390/app142411973 - 20 Dec 2024
Viewed by 610
Abstract
With the continuous growth of Industry 4.0 (I4.0), the industrial sector has transformed into smart factories, enhancing business competitiveness while aiming for the sustainable development of organizations. Machinery is a critical component and key to the success of production in a smart industrial [...] Read more.
With the continuous growth of Industry 4.0 (I4.0), the industrial sector has transformed into smart factories, enhancing business competitiveness while aiming for the sustainable development of organizations. Machinery is a critical component and key to the success of production in a smart industrial factory. Minimizing unplanned downtime (UPDT) poses a significant challenge in designing an effective maintenance system. In the era of Industry 4.0, the most widely adopted maintenance frameworks are intelligent maintenance systems (IMSs), which integrate predictive maintenance with computerized systems. IMSs are intelligent tools designed to efficiently plan maintenance cycles for each machine component in a smart factory. This research presents the application of a search algorithm named state space search (SSS) in conjunction with a newly designed IMS, aimed at optimizing maintenance routines by identifying the optimal timing for maintenance cycles. The design began with the development of a new IMS concept that incorporates three key elements: the automation pyramid standard, Industrial Internet of Things (IIoT) sensors, and a computerized maintenance management system (CMMS). The CMMS collects machine data from the maintenance database, while real-time parameters are gathered via IIoT sensors from the supervisory control and data acquisition (SCADA) system. The new IMS concept provides a summary of the total maintenance cost and the remaining lifetime of the equipment. By integrating with SSS algorithms, the IMS presents optimized maintenance cycle solutions to the maintenance manager, focusing on minimizing costs while maximizing the remaining lifetime of the equipment. Moreover, the SSS algorithms take into account the risks associated with maintenance routines, following factory standards such as failure mode and effects analysis (FMEA). This approach is well suited to smart factories and helps to reduce UPDT. Full article
(This article belongs to the Special Issue Advancement in Smart Manufacturing and Industry 4.0)
Show Figures

Figure 1

19 pages, 2355 KiB  
Article
Transforming Soil: Climate-Smart Amendments Boost Soil Physical and Hydrological Properties
by Anoop Valiya Veettil, Atikur Rahman, Ripendra Awal, Ali Fares, Nigus Demelash Melaku, Binita Thapa, Almoutaz Elhassan and Selamawit Woldesenbet
Viewed by 591
Abstract
A field study was conducted to investigate the effects of selected climate-smart agriculture practices on soil bulk density (ρ), porosity (β), hydraulic conductivity (Ksat), and nutrient dynamics in southeast Texas. Treatment combinations of two types of [...] Read more.
A field study was conducted to investigate the effects of selected climate-smart agriculture practices on soil bulk density (ρ), porosity (β), hydraulic conductivity (Ksat), and nutrient dynamics in southeast Texas. Treatment combinations of two types of organic manure (chicken and dairy) with three rates (0, 224, and 448 kg N ha−1) and two levels of biochar (2500 and 5000 kg ha−1) were used in a factorial randomized block design. Bulk density and porosity measurements were conducted on undisturbed soil core samples collected from the topsoil (0–10 cm) of a field cultivated with sweet corn. Ksat was calculated from the steady-state infiltration measured using the Tension Infiltrometer (TI). The ANOVA results indicated that the manure application rates, and biochar levels significantly affected the soil properties. Compared to the control, β increased by 15% and 29% for the recommended and double recommended manure rates. Similarly, hydraulic conductivity increased by 25% in the double-recommended rate plots compared to the control. Also, we applied the concept of non-parametric elasticity to understand the sensitivity of soil physical and chemical properties to Ksat. ρ and β are critical physical properties that are highly sensitive to Ksat. Among soil nutrients, Boron showed the highest sensitivity to Ksat. Hydraulic conductivity can be enhanced by employing selected climate-smart practices and improving water management. Future directions for this study focus on scaling these findings to diverse cropping systems and soil types while integrating long-term assessments to evaluate the cumulative effects of climate-smart practices on soil health, crop productivity, and ecosystem sustainability. Full article
(This article belongs to the Special Issue Research on Soil Management and Conservation: 2nd Edition)
Show Figures

Figure 1

15 pages, 1275 KiB  
Article
Integrating Digital Twins and Cyber-Physical Systems for Flexible Energy Management in Manufacturing Facilities: A Conceptual Framework
by Gerrit Rolofs, Fabian Wilking, Stefan Goetz and Sandro Wartzack
Electronics 2024, 13(24), 4964; https://doi.org/10.3390/electronics13244964 - 17 Dec 2024
Viewed by 769
Abstract
This paper presents a conceptual framework aimed at integrating Digital Twins and cyber-physical production systems into the energy management of manufacturing facilities. To address the challenges of rising energy costs and environmental impacts, this framework combines digital modeling and customized energy management for [...] Read more.
This paper presents a conceptual framework aimed at integrating Digital Twins and cyber-physical production systems into the energy management of manufacturing facilities. To address the challenges of rising energy costs and environmental impacts, this framework combines digital modeling and customized energy management for direct manufacturing operations. Through a review of the existing literature, essential components such as physical models, a data platform, an energy optimization platform, and various interfaces are identified. Key requirements are defined in terms of functionality, performance, reliability, safety, and additional factors. The proposed framework includes the physical system, data platform, energy management system, and interfaces for both operators and external parties. The goal of this framework is to set the basis for allowing manufacturers to reduce energy consumption and costs during the lifecycle of assets more effectively, thereby improving energy efficiency in smart manufacturing. The study highlights opportunities for further research, such as real-world applications and sophisticated optimization methods. The advancement of Digital Twin technologies holds significant potential for creating more sustainable factories. Full article
(This article belongs to the Special Issue Digital Twins in Industry 4.0, 2nd Edition)
Show Figures

Figure 1

27 pages, 547 KiB  
Article
Cybersecurity as a Contributor Toward Resilient Internet of Things (IoT) Infrastructure and Sustainable Economic Growth
by Georgia Dede, Anastasia Maria Petsa, Stelios Kavalaris, Emmanouil Serrelis, Spyridon Evangelatos, Ioannis Oikonomidis and Thomas Kamalakis
Information 2024, 15(12), 798; https://doi.org/10.3390/info15120798 - 11 Dec 2024
Viewed by 888
Abstract
This paper investigates the contribution of the various cybersecurity domains to the United Nations’ Sustainable Development Goals (SDGs), emphasizing the critical role of cybersecurity in advancing sustainable economic growth and resilient IoT infrastructure. The paper also examines specific use cases on how cybersecurity [...] Read more.
This paper investigates the contribution of the various cybersecurity domains to the United Nations’ Sustainable Development Goals (SDGs), emphasizing the critical role of cybersecurity in advancing sustainable economic growth and resilient IoT infrastructure. The paper also examines specific use cases on how cybersecurity measures and practices can contribute to achieving SDG 8 and SDG 9 focused on decent work and economic growth and industry, innovations, and infrastructure. In the context of SDG 8 the use case of a smart agriculture network was examined, whereas for SDG 9, the use case focuses on a smart factory processing raw materials. An analysis of the prioritization of the several cybersecurity domains following the MoSCoW method is also presented. This paper offers valuable insights and guidance for enhancing corporate resilience and economic benefits in the Internet of Things (IoT) aligning with the SDGs and contributing to a more sustainable and resilient future for the IoT. Full article
(This article belongs to the Special Issue Technoeconomics of the Internet of Things)
Show Figures

Figure 1

19 pages, 5449 KiB  
Article
Coordinated Motion Control of Mobile Self-Reconfigurable Robots in Virtual Rigid Framework
by Ruopeng Wei, Yubin Liu, Huijuan Dong, Yanhe Zhu and Jie Zhao
Viewed by 617
Abstract
This paper presents a control method for the coordinated motion of a mobile self-reconfigurable robotic system. By utilizing a virtual rigid framework, the system ensures that its configuration remains stable and intact, while enabling modular units to collaboratively track the required trajectory and [...] Read more.
This paper presents a control method for the coordinated motion of a mobile self-reconfigurable robotic system. By utilizing a virtual rigid framework, the system ensures that its configuration remains stable and intact, while enabling modular units to collaboratively track the required trajectory and velocity for mobile tasks. The proposed method generates a virtual rigid structure with a specific configuration and introduces an optimized controller with dynamic look-ahead distance and adaptive steering angle. This controller calculates the necessary control parameters for the virtual rigid structure to follow the desired trajectory and speed, providing a unified reference framework for the coordinated movement of the module units. A coordination controller, based on kinematics and adaptive sliding mode control, is developed to enable each module to track the motion of the virtual rigid structure, ensuring the entire robotic system follows the target path while maintaining an accurate configuration. Extensive simulations and experiments under various configurations, robot numbers, and environmental conditions demonstrate the effectiveness and robustness of the proposed method. This approach shows strong potential for applications in smart factories, particularly in material transport and assembly line supply. Full article
(This article belongs to the Special Issue Industry 4.0: Intelligent Robots in Smart Manufacturing)
Show Figures

Figure 1

15 pages, 2580 KiB  
Article
Self-Attention (SA)-ConvLSTM Encoder–Decoder Structure-Based Video Prediction for Dynamic Motion Estimation
by Jeongdae Kim, Hyunseung Choo and Jongpil Jeong
Appl. Sci. 2024, 14(23), 11315; https://doi.org/10.3390/app142311315 - 4 Dec 2024
Viewed by 747
Abstract
Video prediction, which is the task of predicting future video frames based on past observations, remains a challenging problem because of the complexity and high dimensionality of spatiotemporal dynamics. To address the problems associated with spatiotemporal prediction, which is an important decision-making tool [...] Read more.
Video prediction, which is the task of predicting future video frames based on past observations, remains a challenging problem because of the complexity and high dimensionality of spatiotemporal dynamics. To address the problems associated with spatiotemporal prediction, which is an important decision-making tool in various fields, several deep learning models have been proposed. Convolutional long short-term memory (ConvLSTM) can capture space and time simultaneously and has shown excellent performance in various applications, such as image and video prediction, object detection, and semantic segmentation. However, ConvLSTM has limitations in capturing long-term temporal dependencies. To solve this problem, this study proposes an encoder–decoder structure using self-attention ConvLSTM (SA-ConvLSTM), which retains the advantages of ConvLSTM and effectively captures the long-range dependencies through the self-attention mechanism. The effectiveness of the encoder–decoder structure using SA-ConvLSTM was validated through experiments on the MovingMNIST, KTH dataset. Full article
(This article belongs to the Special Issue Novel Research on Image and Video Processing Technology)
Show Figures

Figure 1

20 pages, 2541 KiB  
Article
Towards Flexible Control of Production Processes: A Requirements Analysis for Adaptive Workflow Management and Evaluation of Suitable Process Modeling Languages
by Alexander Schultheis, David Jilg, Lukas Malburg, Simon Bergweiler and Ralph Bergmann
Processes 2024, 12(12), 2714; https://doi.org/10.3390/pr12122714 - 1 Dec 2024
Viewed by 624
Abstract
In the context of Industry 4.0, Artificial Intelligence (AI) methods are used to maximize the efficiency and flexibility of production processes. The adaptive management of such semantic processes can optimize energy and resource efficiency while providing high reliability, but it depends on the [...] Read more.
In the context of Industry 4.0, Artificial Intelligence (AI) methods are used to maximize the efficiency and flexibility of production processes. The adaptive management of such semantic processes can optimize energy and resource efficiency while providing high reliability, but it depends on the representation type of these models. This paper provides a literature review of current Process Modeling Languages (PMLs). Based on a suitable PML, the flexibility of production processes can be increased. Currently, a common understanding of this process flexibility in the context of adaptive workflow management is missing. Therefore, requirements derived from the business environment are presented for process flexibility. To enable the identification of suitable PLMs, requirements regarding this are also raised. Based on these, the PMLs identified in the literature review are evaluated. Thereby, based on a preselection, a detailed examination of the seven most promising languages is performed, including an example from a real smart factory. As a result, a recommendation is made for the use of BPMN, for which it is presented how it can be enriched with separate semantic information that is suitable for the use of AI planning and, thus, enables flexible control. Full article
(This article belongs to the Special Issue AI-Supported Methods and Process Modeling in Smart Manufacturing)
Show Figures

Figure 1

28 pages, 4421 KiB  
Communication
Machine Learning Supporting Virtual Reality and Brain–Computer Interface to Assess Work–Life Balance Conditions for Employees
by Dariusz Mikołajewski, Adrianna Piszcz, Izabela Rojek and Krzysztof Galas
Electronics 2024, 13(22), 4489; https://doi.org/10.3390/electronics13224489 - 15 Nov 2024
Viewed by 701
Abstract
The widespread adoption of the Industry 5.0 paradigm puts people and their applications at the center of attention and, with the increasing automation and robotization of work, the need for workers to acquire new, more advanced skills increases. The development of artificial intelligence [...] Read more.
The widespread adoption of the Industry 5.0 paradigm puts people and their applications at the center of attention and, with the increasing automation and robotization of work, the need for workers to acquire new, more advanced skills increases. The development of artificial intelligence (AI) means that expectations for workers are further raised. This leads to the need for multiple career changes from life and throughout life. Belonging to a previous generation of workers makes this retraining even more difficult. The authors propose the use of machine learning (ML), virtual reality (VR) and brain–computer interface (BCI) to assess the conditions of work–life balance for employees. They use machine learning for prediction, identifying users based on their subjective experience of work–life balance. This tool supports intelligent systems in optimizing comfort and quality of work. The potential effects could lead to the development of commercial industrial systems that could prevent work–life imbalance in smart factories for Industry 5.0, bringing direct economic benefits and, as a preventive medicine system, indirectly improving access to healthcare for those most in need, while improving quality of life. The novelty is the use of a hybrid solution combining traditional tests with automated tests using VR and BCI. This is a significant contribution to the health-promoting technologies of Industry 5.0. Full article
Show Figures

Figure 1

Back to TopTop