Journal of Industrial Information Integration最新文献

{"title":"A computer vision-based approach for identification of non-metallic inclusions in the steel industry products","authors":"Surya Prakash Mishra ,&nbsp;Ashok Kamaraj ,&nbsp;V Rajinikanth ,&nbsp;M R Rahul","doi":"10.1016/j.jii.2025.100860","DOIUrl":"10.1016/j.jii.2025.100860","url":null,"abstract":"<div><div>Identification of microstructures is the core of materials engineering. Artificial intelligence's application in materials engineering has recently shown the possibility of realizing complicated tasks. Identifying elemental distribution in microstructure requires experimentation or computationally intensive modeling techniques. The current work focuses on the question, can artificial intelligence predict elemental distribution in a microstructure? The case study was selected from the steel industry. Making steel will cause different inclusions; identifying them is essential for qualifying the steel for applications. The current study develops a unique computer vision-based architecture by integrating Swin Transformer and U-Net architecture to identify the inclusions. The developed model can predict the type of inclusion in the steel by generating the elemental distribution images. The model is compared with the possible available architectures in the literature. The new model shows the lowest mean absolute error of 0.0529, root mean squared error of 0.0902, mean squared error of 0.0081, and the highest structural similarity (SSim) value of 0.68965 and an intersection over union (IoU) of 1 when images are binarised.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"46 ","pages":"Article 100860"},"PeriodicalIF":10.4,"publicationDate":"2025-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143923717","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Exploring the applicability of industry 4.0 technologies in oil and gas pipeline leakage monitoring: Results from an empirical study","authors":"Ismail W.R. Taifa,&nbsp;Rehema Adam Mahundi,&nbsp;Victoria Mahabi","doi":"10.1016/j.jii.2025.100857","DOIUrl":"10.1016/j.jii.2025.100857","url":null,"abstract":"<div><div>This study explored the applicability of Industry 4.0 (I4.0) technologies in oil and gas (O&amp;G) pipeline leakage monitoring (PLM) in Tanzania. Specific objectives identified factors affecting the adoption of I4.0 technologies in the O&amp;G PLM, evaluated the maturity of I4.0 within the industry, and proposed strategies to enhance the adoption of I4.0 technologies for PLM. A mixed-methods design gathered qualitative and quantitative data. One hundred and seven (107) experts purposively selected were engaged in exploring the applicability of I4.0 technologies. IBM SPSS 26 and AMOS 23 software analysed the gathered data. The analysis revealed six pillars of I4.0 technologies applicable for monitoring O&amp;G pipelines. Those pillars included autonomous robots, augmented reality, additive manufacturing, the Internet of Things, cloud computing and artificial intelligence. The O&amp;G pipeline's maturity level was 3.1, indicating that the industry has begun integrating some I4.0 technologies into pipeline monitoring or leakage detection. Strategies obtained through experts' responses and 80–20 % analysis that tackle technological, financial, regulatory, and psychological constraints were proposed to enhance I4.0ʼs full adoption in PLM. Strategies developed were building international partnerships, building international cooperation, building a workforce, creating digital platforms, promoting a friendly industry culture and state support for investors. The study only identified applicable I4.0 technologies for pipeline monitoring or leakage detection. Further study can be conducted to analyse to what extent they are utilised and can be utilised in O&amp;G PLM. Furthermore, there has been limited literature on the O&amp;G industry; hence, further studies can explore the industry in the downstream and midstream sections.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"46 ","pages":"Article 100857"},"PeriodicalIF":10.4,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143916505","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Inland waterway autonomous transportation: System architecture, infrastructure and key technologies","authors":"Hualong Chen ,&nbsp;Yuanqiao Wen ,&nbsp;Yamin Huang ,&nbsp;Lihang Song ,&nbsp;Zhongyi Sui","doi":"10.1016/j.jii.2025.100858","DOIUrl":"10.1016/j.jii.2025.100858","url":null,"abstract":"<div><div>With the rapid development of intelligent inland waterway shipping and autonomous vessel, the development of inland waterway autonomous transportation has become a hot topic in the shipbuilding industry and the maritime field. This study comprehensively discusses the development trends and technical challenges of inland waterway autonomous transportation from three aspects: system architecture, advanced infrastructure, and key technologies. Firstly, based on the Cyber-Physical-System theory, we propose a hierarchical architecture for the inland waterway autonomous transportation system. Second, based on the full-life-cycle management and control theory, we put forward the autonomous operation process for the planning, design, construction, operation, management, and control of the inland waterway autonomous transportation system. Then, we discuss the advanced infrastructure of the inland waterway autonomous transportation system, including perception, communication, computing, navigation scene maps, high-precision positioning, and so on. Finally, we summarize the key technologies and development challenges for implementing the inland waterway autonomous transportation system, such as autonomous vessels, the Internet of Ships, cloud-edge collaborative computing, artificial intelligence, communication, and channel geographic information systems. This research provides a potential framework and technical solutions for the inland waterway autonomous transportation system, contributing to the rapid development of the inland waterway shipping economy.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"46 ","pages":"Article 100858"},"PeriodicalIF":10.4,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143894822","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Integrating LOPCOW-DOBI method and possibilistic programming for two-stage decision making in resilient food supply chain network","authors":"Pavan Sharma ,&nbsp;B. Nila ,&nbsp;Dragan Pamucar ,&nbsp;Jagannath Roy","doi":"10.1016/j.jii.2025.100847","DOIUrl":"10.1016/j.jii.2025.100847","url":null,"abstract":"<div><div>This study focuses on resilient supplier selection and order allocation — two crucial aspects of modern supply chain management (SCM). Globalization and strategic sourcing expose supply chains to disruptions, making resilient sourcing strategies essential for adapting to fluctuations in supply and demand. This paper proposes a novel integrated hybrid model that combines multi-attribute decision-making (MADM) with a possibilistic multi-objective programming model (PMOPM) to enhance decision-making in supply chain resilience (SCR). In the first stage, we present an MADM model that integrates the LOgarithmic Percentage Change-driven Objective Weighting (LOPCOW) and DOmbi Bonferroni (DOBI) methods. The LOPCOW-DOBI method enables decision-makers (e.g., purchasing team) to evaluate and rank multiple suppliers based on normal business criteria (<span><math><mrow><mi>N</mi><mi>B</mi><mi>C</mi></mrow></math></span>) and resilient pillars (<span><math><mrow><mi>R</mi><mi>P</mi><mi>s</mi></mrow></math></span>). In the second stage, a PMOPM is employed to determine optimal order allocations when supply, demand, and cost parameters are fuzzy in nature. The quantitative and qualitative evaluation of decision-makers’ opinions is integrated into mathematical optimization by combining the MADM output with PMOPM. Using the <span><math><mi>ϵ</mi></math></span>-constraint method, the model was optimized to obtain Pareto solutions, with the final solution identified via the global criteria method. A real-world food industry case study validated the MADM-PMOPM model. Our results show that suppliers with higher resilience performance receive larger orders. Sensitivity analysis confirms that the two-stage model consistently delivers stable and adaptable solutions. Comparative analysis further demonstrates that the proposed approach is effective and reliable for rational decision-making.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"46 ","pages":"Article 100847"},"PeriodicalIF":10.4,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143906401","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Assessment model for Industry 5.0: A holistic approach to readiness and integration","authors":"Cesar Cuevas-Lopez-de-Baro,&nbsp;Ignacio Mira-Solves,&nbsp;Antonio Verdú-Jover","doi":"10.1016/j.jii.2025.100855","DOIUrl":"10.1016/j.jii.2025.100855","url":null,"abstract":"<div><h3>Purpose</h3><div>This study proposes a novel assessment model tailored to the unique requirements of Industry 5.0 transformation utilizing Socio-Technical Theory as a framework. The model seeks to give organizations actionable insights into navigating the complex socio-technical dynamics of I5.0, evaluating organizational readiness holistically, and guiding their transition to this new industrial paradigm across different perspectives and dimensions. By fostering this holistic approach to Industry 5.0 adoption, our study aims to impact industry, society, and institutions significantly.</div></div><div><h3>Methodology</h3><div>The model was developed using a two-phase research approach. The first phase involved a detailed systematic literature review and a systematic literature network analysis to identify the perspectives, critical dimensions, and guiding questions for the assessment based on Socio-Technical Theory. The second phase refined the preliminary model through expert feedback from industry specialists.</div></div><div><h3>Findings</h3><div>Our research proposed an assessment model for Industry 5.0, confirmed Socio-Technical Theory as a substantive framework, and identified four core perspectives: strategy, sustainability, human-centricity, and resilience. These perspectives encompass 25 critical dimensions, which were further analyzed through 64 guiding questions. Expert feedback validated the need for the model and highlighted its potential for application from both a strategic and a tactical perspective.</div></div><div><h3>Originality</h3><div>This study addresses a crucial gap in the literature by presenting a novel assessment model tailored to the unique challenges and opportunities presented by this emerging industrial paradigm. The model’s emphasis on holistic readiness and the integration of business strategies goes beyond conventional approaches by fostering a more nuanced understanding of the socio-technical dynamics shaping the future of industry and society. By applying Socio-Technical Theory (STT), this study provides a more comprehensive understanding of the socio-technical dynamics underlying I5.0 transformation. This innovative approach provides organizations with actionable insights into navigating the intricate interplay between advanced technologies, human factors, sustainability principles, and resilience strategies in complex situations, thus advancing both theoretical and practical knowledge in the field of Industry 5.0.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"46 ","pages":"Article 100855"},"PeriodicalIF":10.4,"publicationDate":"2025-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143912551","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Hybrid deep learning based threat intelligence framework for Industrial IoT systems","authors":"Jahanzaib Malik ,&nbsp;Adnan Akhunzada ,&nbsp;Ahmad Sami Al-Shamayleh ,&nbsp;Sherali Zeadally ,&nbsp;Ahmad Almogren","doi":"10.1016/j.jii.2025.100846","DOIUrl":"10.1016/j.jii.2025.100846","url":null,"abstract":"<div><div>The exponential growth of Industrial Internet of Things (IIoT) is a major driving force behind Industry 4.0. Besides complete automation and transformation, industrial IoT has so far created plenty of opportunities in several sectors 1.3such as smart manufacturing, energy, healthcare, smart agriculture, retail, supply chain, and transportation. However, the increased pervasiveness, reduced human involvement, resource-constrained nature of underlying IoT devices, dynamic and shared spectrum of 4G/5G communication, and reliance on the cloud for outsourced massive storage and computation bring novel security challenges and concerns. A significant challenge currently confronting the Industrial Internet of Things (IIoT) is the increasing prevalence of sophisticated IoT malware threats and attacks. To address this, the authors propose a hybrid threat intelligence framework that is not only highly scalable but also incorporates self-optimizing capabilities, enabling it to counteract a wide range of persistent cyber threats and attacks targeting IIoT systems. For a comprehensive evaluation, the authors utilized the state-of-the-art TON_IIoT dataset, which includes over 3 million instances representing various adversarial patterns and threat vectors. In addition, both standard and extended performance evaluation metrics were employed to ensure a thorough assessment. The proposed approach was also compared against several contemporary deep learning-based architectures and existing benchmark algorithms. The results indicate that the proposed method achieves superior detection accuracy, with only a minimal compromise in speed efficiency. Finally, a 10-fold cross-validation was conducted to provide an unbiased evaluation of the framework’s performance.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"45 ","pages":"Article 100846"},"PeriodicalIF":10.4,"publicationDate":"2025-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143847187","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multi-agent collaboration mechanisms based on distributed online meta-learning for mass personalization","authors":"Ziren Luo ,&nbsp;Di Li ,&nbsp;Jiafu Wan ,&nbsp;Shiyong Wang ,&nbsp;Ge Wang ,&nbsp;Minghao Cheng ,&nbsp;Ting Li","doi":"10.1016/j.jii.2025.100852","DOIUrl":"10.1016/j.jii.2025.100852","url":null,"abstract":"<div><div>Driven by the mass personalization model, online meta-learning has garnered significant attention from resource-constrained agents due to its wide adaptability, continuous learning, and lightweight characteristics. However, as cutting-edge artificial intelligence advances, the intelligence and autonomy of agents are increasingly improving, posing challenges to data synchronization and decision-making consistency in collaborative processes. To this end, this paper proposes a distributed online meta-learning multi-agent collaboration framework based on hybrid parallelism, which meets the needs of synchronous collaboration and asynchronous collaboration in different stages of personalization. To implement this framework, we designed two key algorithms. First, an agent clustering algorithm based on graph theory groups similar agents. Synchronous collaboration within the group satisfies the manufacturing time constraint, while asynchronous collaboration among groups ensures decision consistency. Second, a multi-agent online meta-learning algorithm with gradient tracking monitors global gradients through limited communications, accelerating rapid adaptation to personalization tasks. Finally, we validated our approach through experimental testing on a personalized production platform. The results underscore the effectiveness of the proposed multi-agent collaboration mechanism and implementation algorithms, providing a new solution for multi-agent collaboration based on artificial intelligence in mass personalization environments.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"46 ","pages":"Article 100852"},"PeriodicalIF":10.4,"publicationDate":"2025-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143854511","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Integrated IoT-based production, deep learning, and Business Intelligence approaches for organic food production","authors":"Nicola Contuzzi ,&nbsp;Angelo Maurizio Galiano ,&nbsp;Giuseppe Casalino","doi":"10.1016/j.jii.2025.100850","DOIUrl":"10.1016/j.jii.2025.100850","url":null,"abstract":"<div><div>The organic food processing industry grapples with several complex challenges, such as ensuring the ingredients' authenticity, reducing resource consumption, and maintaining consistent product quality despite fluctuating demand and the supply seasonal nature. Previous methodologies often lacked integration of real-time data and advanced predictive analytics, leading to inefficiencies and increased waste. This study proposes a novel framework that combines IoT sensor networks, deep learning algorithms, and business intelligence to optimize production processes in organic tomato processing. By employing a Long Short-Term Memory (LSTM) model, the framework effectively predicts sales, manages raw material procurement and enhances logistics based on real-time data inputs. Findings indicate a 25 % improvement in productivity and a 20 % reduction in waste during production, alongside a 30 % increase in profitability attributed to informed pricing strategies and enhanced supplier quality management. The integration of predictive analytics not only aligns production with consumer demand but also supports sustainable practices by minimizing overproduction and waste. This work addresses the critical intersection of technology and sustainability in food production, ultimately contributing to a more resilient and efficient organic food supply chain. Keywords: Organic food, data mining, deep learning, Business Intelligence</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"46 ","pages":"Article 100850"},"PeriodicalIF":10.4,"publicationDate":"2025-04-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143848418","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Digital twin-enabled regional food supply chain: A review and research agenda","authors":"José Monteiro,&nbsp;João Barata","doi":"10.1016/j.jii.2025.100851","DOIUrl":"10.1016/j.jii.2025.100851","url":null,"abstract":"<div><div>Sustainable, resilient, and efficient Regional Food Supply Chains (RFSCs) are critical to addressing global challenges such as food security, climate change, and resource optimization. Digital Twins (DTs) have emerged as powerful tools for real-time monitoring, predictive analysis, and process optimization, providing actionable insights for the modernization and integration of RFSCs. Our systematic literature review of 133 studies reveals how DTs can transform RFSCs and the challenges and opportunities associated with their adoption. The findings suggest that DTs enhance RFSC management by facilitating informed decision-making, improving resource efficiency, reducing waste, and promoting regional resilience to external disruptions. This work advances the state of the art by identifying the unique role of DTs in optimizing each process within RFSCs, from production to consumption. Key contributions include (1) identifying the potential of DTs to improve sustainability, resilience, and efficiency in RFSCs, (2) analyzing the challenges of DT interoperability, data integration, and cybersecurity, (3) exploring how DTs can foster regional development through improved traceability and logistics, and (4) presenting an annotated research agenda. This review offers a comprehensive theoretical framework and practical guidance for researchers and practitioners leveraging DTs in RFSCs to create sustainable, human-centric, and resilient supply chains at a regional scale.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"45 ","pages":"Article 100851"},"PeriodicalIF":10.4,"publicationDate":"2025-04-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143835273","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Physics-informed Koopman model predictive control of open canal systems","authors":"Ningjun Zeng ,&nbsp;Lihui Cen ,&nbsp;Wentao Hou ,&nbsp;Yongfang Xie ,&nbsp;Xiaofang Chen","doi":"10.1016/j.jii.2025.100845","DOIUrl":"10.1016/j.jii.2025.100845","url":null,"abstract":"<div><div>The physical model of open canal systems is described by the Saint-Venant (S-V) equations, which are partial differential equations without explicit solutions. Consequently, the control problem of open canal systems is not trivial. In this paper, a model predictive control (MPC) method based on the framework of the Koopman operator and the physics-informed neural networks is proposed. A continuous-time Koopman model is obtained by mapping the system states, including water levels and discharges, from the original state space to a raised-dimensional observation space. An autoencoder architecture is developed to approximate the mapping to the raised-dimensional space. Specifically, we established a numerical connection between the Koopman model and the S-V equations, and introduced a physics-informed loss function. A two-stage training strategy is implemented to obtain the optimal approximation of the physics-informed Koopman model. Subsequently, a continuous-time stable MPC method for the physics-informed Koopman model of open canal systems is proposed via control parameterization. The proposed method was validated on a one-reach canal system and a cascaded system. The simulation results demonstrate that the physics-informed Koopman model accurately predicts the future dynamics of open canal systems, and the MPC controller effectively tracks the desired water levels.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"46 ","pages":"Article 100845"},"PeriodicalIF":10.4,"publicationDate":"2025-04-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143859987","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}