Journal of Industrial Information Integration最新文献

{"title":"Intelligent prognostics of syngas pipeline elbow erosion via a hybrid machine learning–digital twin framework","authors":"Yangyang Bao ,&nbsp;Zeyang Shi ,&nbsp;Xian Li ,&nbsp;Yan An ,&nbsp;Wenming Song ,&nbsp;Yuge Li ,&nbsp;Wei Wu ,&nbsp;Liping Wei ,&nbsp;Yuan Yan ,&nbsp;Debiao Li","doi":"10.1016/j.jii.2025.101006","DOIUrl":"10.1016/j.jii.2025.101006","url":null,"abstract":"<div><div>In modern energy and process industries, the growing demand for continuous, safe, and reliable operation poses increasing challenges to the structural integrity of critical equipment. Erosion, caused by complex gas–solid interactions, is a typical degradation mechanism that affects the service life and operational stability of components such as elbows in syngas pipelines. However, existing monitoring and prediction methods often have limited spatiotemporal resolution, poor robustness, and weak real-time capability. These limitations make it difficult to accurately capture and predict erosion evolution under fluctuating operating conditions. To overcome these challenges, this study develops a digital twin–based framework for erosion monitoring, forecasting, and risk assessment (DT-FEMR) that combines physical constraints with data-driven modeling. The framework establishes a complete process from physical sensing to predictive maintenance. It consists of three core modules for erosion field reconstruction, future condition prediction, and lifetime evaluation. Through this hybrid physics–data design, DT-FEMR enables real-time visualization of erosion morphology, prediction of future gas velocity trends, and probabilistic assessment of remaining life and risk levels. The proposed framework offers a scalable and transferable approach for integrating multi-source data, physical simulations, and machine learning models. It enhances the interpretability, adaptability, and reliability of erosion analysis, providing a foundation for intelligent monitoring and predictive maintenance of critical industrial equipment.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"48 ","pages":"Article 101006"},"PeriodicalIF":10.4,"publicationDate":"2025-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145442129","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":"A sustainable electric vehicle smart production with work-in-process inventory of outsourced spare parts","authors":"Biswajit Sarkar ,&nbsp;Rekha Guchhait ,&nbsp;Mitali Sarkar","doi":"10.1016/j.jii.2025.100998","DOIUrl":"10.1016/j.jii.2025.100998","url":null,"abstract":"<div><div>Electric vehicle production has recently gained popularity due to increasing emissions. The research on electric vehicle production concerning technical, economic, and environmental aspects is very less compared to the traditional vehicle. This research studies a mixed-type electric vehicle production system that produces spare parts and finally assembles all spare parts for the vehicle. The spare parts production combines in-line production with returnable items and outsourcing. An automated inspection for both spare parts and vehicles is included within the system. Two different types of machines work for the production process: Machine 1 for spare parts and Machine 2 for vehicles. As the basic purpose is to provide an ecofriendly logistics facility, the manufacturing company takes care of carbon emissions from the system, customer satisfaction, and the green quality of vehicles. Necessary and sufficient conditions of classical optimization find global optimum solutions. Results show that green technology and customer satisfaction are two important factors for vehicle production. Comparative discussions, sensitivity, and robust analysis are provided to validate the theoretical contributions. The proposed mixed-type production model earns 85.32% more profit than a traditional production model. The electric vehicle provides a 96% customer satisfaction with an increase of 68.97% profit without customer satisfaction.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"49 ","pages":"Article 100998"},"PeriodicalIF":10.4,"publicationDate":"2025-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145424057","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":"A review of applications of AI in monitoring, inspection, and maintenance of railway tracks","authors":"Amin Khajehdezfuly ,&nbsp;Hadi Azizipour ,&nbsp;Sakdirat Kaewunruen","doi":"10.1016/j.jii.2025.101005","DOIUrl":"10.1016/j.jii.2025.101005","url":null,"abstract":"<div><div>With the advancement of Artificial Intelligence (AI)-based methods and the establishment of diverse databases, significant research has been conducted on the application of AI in railway track monitoring, inspection and maintenance. Although several review studies exist in this field, each has been confined to a limited scope, focusing on specific data types, data collection methods, or AI-based techniques. To date, no comprehensive review has been published that encompasses all data types, data collection methods, and AI-based approaches to assess prior research holistically. This study aims to address this critical gap by covering both passenger and freight railway transport systems. Firstly, the available databases used for AI applications in railway track inspection and maintenance were categorized and reviewed, distinguishing between peer-reviewed and non-peer-reviewed sources. Secondly, this review introduces a novel three-level classification framework, based on data acquisition method (including track response methods, on-board data approaches, and remote data methods), target railway track component or feature, and input data type, to systematically organize and analyze 567 studies the field published between 2005 and 2025. The findings reveal that the majority of research in this field (88 %) is concentrated on on-board data methods. Approximately 90 % of these studies focus on railway track components, specifically their identification or damage detection. Among the track components, rails and fastening systems, being both critical and vulnerable, have been the primary focus of most research efforts. Image data emerges as the most prevalent and widely utilized data type in on-board data approaches for all railway track components. An in-depth gap analysis was conducted on the literature to identify the limitations of previous studies and outline a roadmap for future research and open directions from multiple perspectives. A comprehensive review of the literature indicates a pressing need for the development of AI-based methods capable of processing multiple data types simultaneously to identify both internal and external damages across all railway track components. The limited number of studies addressing the integration of multiple data types underscores the significant research opportunities in this area. This review not only synthesizes AI-based methods for railway track monitoring and maintenance but also highlights their role in advancing industrial information integration by enabling scalable and intelligent fusion of multi-source data for real-time decision-making.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"48 ","pages":"Article 101005"},"PeriodicalIF":10.4,"publicationDate":"2025-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145424060","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":"Shared steering control framework based on visual-haptic compliance information for mitigating human–machine conflict","authors":"Xuyang Wang,&nbsp;Wanzhong Zhao,&nbsp;Chunyan Wang,&nbsp;Ziyu Zhang,&nbsp;Xiaochuan Zhou,&nbsp;Yukai Chu","doi":"10.1016/j.jii.2025.100989","DOIUrl":"10.1016/j.jii.2025.100989","url":null,"abstract":"<div><div>To mitigate the adverse impact of human–machine conflict on driving safety, this paper proposes an indirect shared steering control framework that leverages drivers’ visual and haptic compliance as multimodal embodied cues for adaptive authority allocation. A novel dual-modal compliance index is defined by fusing visual and haptic signals, and a real-time estimation system is implemented alongside a driving risk prediction module. These components serve as inputs to a parallel fuzzy inference mechanism for dynamic authority distribution. A human–machine mutual-adaptation robust control strategy is then developed based on a cybernetic driver model with coordinated visual-haptic feedback. Within an integrated driver-vehicle-road framework, a multiobjective robust tube model predictive controller is designed to jointly optimize conflict mitigation and path-tracking performance. Driver-in-the-loop experiments conducted on a four-degree-of-freedom motion platform demonstrate that the proposed framework effectively reduces human–machine conflict while enhancing vehicle stability and tracking accuracy. The results highlight the utility of multimodal compliance fusion as an embodied intelligence mechanism for adaptive shared control and suggest its broader applicability to complex human-machine systems. Moreover, the embodied-intelligence-based cooperative mechanism provides transferable insights for multimodal information fusion and adaptive collaboration in industrial information integration.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"48 ","pages":"Article 100989"},"PeriodicalIF":10.4,"publicationDate":"2025-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145383858","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":"AI-based data-driven framework optimizing smart manufacturing in industrial systems","authors":"Mohammed Salem Basingab","doi":"10.1016/j.jii.2025.100996","DOIUrl":"10.1016/j.jii.2025.100996","url":null,"abstract":"<div><div>Integrating Agent-Based Modeling (ABM) with the Industrial Internet of Things (IIoT) is reshaping how industries manage complexity, automate decision-making, and improve operational intelligence. This study presents a data-centric ABM–IIoT framework that strengthens the efficiency and responsiveness of industrial systems, particularly in manufacturing and planning domains. The framework supports dynamic simulation and predictive maintenance while assisting decision-making by integrating real-time sensor data with AI-powered analytics. Experimental evaluation demonstrates consistent improvements, including approximately 20 % higher operational performance and a 15 % reduction in resource consumption, along with observable gains in decision-making accuracy and process efficiency compared with conventional IoT-based approaches. The framework also maintains stable operation under uncertainty, confirming its adaptability and reliability in dynamic industrial environments. A Monte Carlo-based sensitivity analysis was conducted under varied industrial workloads and uncertainty conditions to validate the robustness and flexibility of the proposed system. Comparative evaluations against AI-only and rule-based models indicate stronger adaptability and awareness of complex system interactions when using agent-based approaches. The architecture further enables distributed decision-making through intelligent agents that replicate human and machine behaviors in industrial ecosystems. This study contributes to industrial systems design by linking predictive analytics with system-level modeling, providing a practical framework tailored for Industry 4.0 applications. The results suggest that ABM–IIoT integration can enhance automation and resilience while supporting more reliable decision-making in smart manufacturing environments.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"48 ","pages":"Article 100996"},"PeriodicalIF":10.4,"publicationDate":"2025-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145382975","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":"Transition for transdisciplinary, human-centric industrial applications: design theories and applications","authors":"Josip Stjepandić ,&nbsp;Margherita Peruzzini ,&nbsp;John P.T. Mo ,&nbsp;Pisut Koomsap","doi":"10.1016/j.jii.2025.101011","DOIUrl":"10.1016/j.jii.2025.101011","url":null,"abstract":"","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"48 ","pages":"Article 101011"},"PeriodicalIF":10.4,"publicationDate":"2025-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145515806","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":"AI agent-based virtual model development, diagnosis, and calibration for building digital twins","authors":"Jiteng Li ,&nbsp;Jabeom Koo ,&nbsp;Jeyoon Lee ,&nbsp;Yuxin Li ,&nbsp;Jiwan Song ,&nbsp;Peng Wang ,&nbsp;Tianyi Zhao ,&nbsp;Sungmin Yoon","doi":"10.1016/j.jii.2025.100990","DOIUrl":"10.1016/j.jii.2025.100990","url":null,"abstract":"<div><div>Building digital twins (BDTs) can enhance reliability by integrating real-time data with virtual model, yet most studies still treat virtual model development, fault diagnosis, and in-situ calibration as isolated stages, resulting in fragmented workflows, low automation, and limited interpretability. To address these issues, this study introduces a novel LLM-based AI agent method integrating virtual model development, diagnosis, and calibration throughout the entire lifecycle in BDTs. During implementation, domain-specific AI agent is developed by knowledge engineering (prompt information, basic information, tool information, and building information) to avoid hallucinations. Then, different toolkits are used to automatically develop virtual models using the MLP algorithm, detect and diagnose faults through comparing the residual with threshold based on a period of time, and perform Bayesian in-situ calibration to ensure accuracy. Finally, the multi-level interpretable results are generated. A case study on a building HVAC system demonstrates the effectiveness of this method: the virtual models of return temperature of chilled water and supply air temperature achieve high accuracy with RMSE of 0.17 °C and 0.21 °C, faults are diagnosed with 10 consecutive residuals greater than the threshold of 1.16 °C, and calibration successfully reduces RMSE from 1.04 °C to 0.30 °C. Importantly, the LLM-based AI agent not only executes all stages with user prompts but also generates interpretable reports, reducing reliance on expert knowledge. By enabling integrated, automated, and explainable BDTs, this study highlights the methodological novelty of employing LLM-based AI agents to advance intelligent building automation systems.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"48 ","pages":"Article 100990"},"PeriodicalIF":10.4,"publicationDate":"2025-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145382970","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":"Analysis of models and methods and perspectives for corridor allocation problem: a literature review","authors":"Zeqiang Zhang ,&nbsp;Zongxing He ,&nbsp;Junqi Liu ,&nbsp;Dan Ji ,&nbsp;Shuai Chen ,&nbsp;Silu Liu","doi":"10.1016/j.jii.2025.100987","DOIUrl":"10.1016/j.jii.2025.100987","url":null,"abstract":"<div><div>This review systematically investigates the corridor allocation problem (CAP) as an important branch of the facility layout problem under the smart manufacturing context. Its aim is to summarise the modeling and variants, classify the solution methods, and identify future trends. We analyse 87 papers published between 2012 and 2024. By systematically categorising and organising these papers, CAP can be classified into four extended problems: multi-objective CAP (Mo-CAP), double-floor CAP (DFCAP), CAP considering material handling position (MHP-CAP), and constrained CAP (cCAP). The solution methods can be categorized into exact methods (e.g., branch-and-bound), heuristics (e.g., neighborhood search), meta-heuristics (e.g., genetic algorithm), and hyper-heuristics (HH) (e.g., reinforcement learning-based HH). We summarise and analyse the model characteristics, typical constraints, solution methods, test cases, strengths and limitations of each problem to present diverse research perspectives. To our knowledge, this is the first structured review that compares Mo-CAP, DFCAP, MHP-CAP, and cCAP with CAP under a unified perspective of modeling assumptions and classification of solution methods. Finally, future research directions are proposed to offer valuable references and insights for academic research and engineering practices in the field of smart manufacturing.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"48 ","pages":"Article 100987"},"PeriodicalIF":10.4,"publicationDate":"2025-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145416548","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":"Behavioral planning and parameter meta learning for embodied intelligence robots in adaptive assembly","authors":"Baotong Chen ,&nbsp;Guangjun Xu ,&nbsp;Lei Wang ,&nbsp;Chun Jiang ,&nbsp;Zelin Zhang ,&nbsp;Zhaohui Wang ,&nbsp;Xuhui Xia","doi":"10.1016/j.jii.2025.100995","DOIUrl":"10.1016/j.jii.2025.100995","url":null,"abstract":"<div><div>Embodied intelligence (EI) is an emerging frontier in robotics that tightly integrates perception, action, and cognition. By continuously interacting with their environments, EI robots can self-evolve and adapt to uncertainties in flexible assembly tasks, thereby enhancing adaptability and execution efficiency. This paper proposes a behavioral planning and parameter meta learning approach for EI robots in adaptive assembly, with the aims of enabling low-code/no-code execution in complex assembly scenarios. This method leverages sensors to capture real-time environmental data and adopts a blackboard mechanism for information storage and sharing, thereby ensuring seamless data flow. The synergistic integration of PDDL-based reasoning with behavior tree orchestration is deployed to achieve dynamic behavior planning. Furthermore, a motion feedback-driven closed loop for parameter meta learning and behavior evolution is constructed based on the PEARL (Probabilistic Embedding for Actor-Critic Reinforcement Learning) and SAC (Soft Actor-Critic) algorithms. The proposed method was validated through a series of hole-and-axis assembly simulations under interference conditions. In addition, we evaluated robustness under different tolerances. The framework maintained a success rate of over 94% and stable adaptive latency under all tolerance levels, with faster adaptation speed, higher precision, and better efficiency.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"49 ","pages":"Article 100995"},"PeriodicalIF":10.4,"publicationDate":"2025-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145383760","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":"A knowledge-driven decision support architecture for sustainable supplier analysis in an infrastructure project","authors":"Song-Shun Lin ,&nbsp;Xin-Jiang Zheng ,&nbsp;Zhao-Yao Bao","doi":"10.1016/j.jii.2025.100994","DOIUrl":"10.1016/j.jii.2025.100994","url":null,"abstract":"<div><div>As supplier analysis becomes increasingly complex, there is a growing need for structured methods that support multi-dimensional evaluation under uncertainty. A knowledge-driven decision support approach (KDDSA) is proposed, leveraging entropy-based interval-valued spherical fuzzy sets to assign criteria weights. Additionally, a weighted coefficient of variation is introduced to measure consensus and account for variability in judgments, strengthening decision-making reliability. The proposed approach addresses the practical challenges of integrating multiple, often conflicting criteria in supplier analysis by incorporating economic, environmental, social, and supplier-specific dimensions, structured across sixteen indicators. To assess its practical applicability, KDDSA is applied to an infrastructure project, where uncertain assessments are integrated and processed through a multi-layered decision structure. The results highlight the critical importance of consensus building and uncertainty management for achieving reliable outcomes. By integrating heterogeneous information with advanced fuzzy modeling, the proposed approach enhances industrial information integration in complex decision-making contexts. The findings reinforce the potential of structured and information-integrated evaluation methods in enhancing supplier management within infrastructure supply chains.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"50 ","pages":"Article 100994"},"PeriodicalIF":10.4,"publicationDate":"2025-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145382969","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}