Journal of Industrial Information Integration最新文献

{"title":"Research on multi-twin collaborative system for human-machine collaborative manufacturing","authors":"Lili Dong ,&nbsp;Tianliang Hu ,&nbsp;Keyi Zhou ,&nbsp;Tianyi Sun ,&nbsp;Songhua Ma","doi":"10.1016/j.jii.2026.101092","DOIUrl":"10.1016/j.jii.2026.101092","url":null,"abstract":"<div><div>With the development of intelligent manufacturing towards deep flexibility, intelligence, and human-centricity, human-machine collaborative manufacturing (HMCM) has become a crucial mode for enhancing manufacturing system effectiveness. To realize the vision of human-machine integration, it is necessary to construct a collaborative architecture that supports deep integration of multiple entities, which can not only fully leverage the unique advantages of different entities, but also realize mutual understanding and dynamic collaboration among them. Digital twin (DT), as an enabling technology for cyber-physical fusion, provides a feasible path towards this goal. Although current research has made progress in the digital modeling and behavior characterization of entities, there remains a deficiency in dynamic interaction and collaborative decision mechanisms among multi-twin models, which is difficult to support for system-level human-machine integration. To address this issue, a multi-twin collaborative system architecture for HMCM is proposed. Firstly, the architecture for HMCM is designed, which includes the human digital twin (HDT), robot digital twin (RDT), equipment digital twin (EDT), product digital twin (PDT), and collaborative application interaction center (CAIC). Correspondingly, an experimental platform for rotary vector (RV) reducer assembly is designed to provide empirical support. Secondly, a multi-twin collaborative system for human-machine collaborative assembly is implemented. Finally, the feasibility and effectiveness of the proposed architecture are verified by this assembly experiment. The experimental results demonstrate that the proposed architecture facilitates the fundamental transformation of the collaborative robot from a \"mechanical executor\" to an \"intuitive collaborator\", providing a reusable technical pathway and system architecture for realizing deep human-machine integration in intelligent manufacturing.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"51 ","pages":"Article 101092"},"PeriodicalIF":10.4,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146134524","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":"Event camera-based high-efficiency transient sparking fault detection in Hall thrusters","authors":"Yibo Zhang ,&nbsp;Jing Jin ,&nbsp;Wenzhe Zheng ,&nbsp;Yihao Zhou ,&nbsp;Zhucheng Tan ,&nbsp;Yan Shen ,&nbsp;Chenyang Shi","doi":"10.1016/j.jii.2026.101085","DOIUrl":"10.1016/j.jii.2026.101085","url":null,"abstract":"<div><div>This paper presents a novel approach to detecting sparking phenomena in Hall thrusters using an event camera. The method addresses challenges associated with propulsion system reliability in the aerospace industry. Hall thrusters, commonly used in commercial satellites and deep space exploration, require reliable operation. The sparking phenomenon, one of the key faults of Hall thrusters, disrupts the normal behavior of the plume and poses multiple risks to thruster operation and mission success. Therefore, detecting sparking is essential. Compared with traditional diagnostic methods, visual sensing achieves finer spatial characterization but frame-based cameras remain limited in dynamic perception and on-orbit practicality. Event cameras, with microsecond-level time resolution, low power consumption, and a wide dynamic range, offer great potential for transient sparking detection. This paper is the first to utilize event cameras for detecting transient sparking in Hall thrusters. A novel detection method based on event rate bursts and ambient diffusion optical flow estimation is proposed. When plume fluctuations cause the event rate to exceed a defined threshold, optical flow computation is triggered for spark verification. Ground experiments show that the method can efficiently detect sparks with an average throughput of 334.77 kHz, achieve 95.7% detection accuracy, and continuously record the spark process. Comparative results with high-speed cameras confirm the superior performance of the event camera. The reliability and scalability of the method are also examined. These advances lay a significant foundation for future on-orbit fault detection and monitoring of Hall thrusters.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"51 ","pages":"Article 101085"},"PeriodicalIF":10.4,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146110397","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":"Enhanced hyper-node faster relational YOLO dwarf mongoose graph attention network for multi-target detection in smart IoT edge-cloud surveillance systems","authors":"Aishwarya D,&nbsp;R.I. Minu","doi":"10.1016/j.jii.2026.101086","DOIUrl":"10.1016/j.jii.2026.101086","url":null,"abstract":"<div><div>The demand for multi-target detection within an IoT-based edge-cloud surveillance system is increasing. This is particularly the case in real-world scenarios where there could be several targets in varied lighting and several very mobile objects. Even with the best possible models, object detection models collapse when presented with the randomness of real-world environments, including clutter and the detection of multiple objects within a scene. A new innovation, the Enhanced Hyper-node Faster Relational YOLO Dwarf Mongoose (IHnode-FRYDM) Graph Attention Network (GAN) for multi-target detection in IoT-based innovative edge-cloud surveillance systems is presented herein. The new method uses the PASCAL VOC dataset to create a more efficient detection framework. It starts with the Iterative Dependable Peak-Aware Directed Filtering (IDPADF), a newer technique for pre-processing images, that considerably improves both the input image and feature representation quality. The real detection then executes the Faster-YOLO architecture, which is essential since it strives to balance speed and accuracy for real-time IoT operations. Moreover, it uses a Hyper-node Relational Graph Attention Network (HRGAT) to perform effective relational feature learning and correct identification of multiple targets in intricate and dynamic environments. IDMO's performance maximizes the rate of convergence and stability of the model to meet the computational loads of IoT edge devices. The resultant evaluation provides a mAP of 99.6% and an F1-score of 99.5%, while offering a processing time reduction of 32% in comparison to other traditional approaches. The results suggest that the new framework can be successfully deployed into new IoT edge-cloud surveillance processes with an efficient and accurate process to fulfill technical demands of multi-target surveillance applications.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"51 ","pages":"Article 101086"},"PeriodicalIF":10.4,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146095831","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":"High-level reasoning while low-level actuation in cyber–physical systems: How efficient is it?","authors":"Burak Karaduman ,&nbsp;Baris Tekin Tezel ,&nbsp;Moharram Challenger","doi":"10.1016/j.jii.2026.101090","DOIUrl":"10.1016/j.jii.2026.101090","url":null,"abstract":"<div><div>The growing complexity of industrial information integration systems requires software technologies that support intelligent behaviour, real-time responsiveness, and efficient development. Despite the proliferation of programming languages and frameworks, there remains a limited amount of empirical evidence to guide engineers in selecting the most suitable tools for developing advanced industrial applications. This study addresses that gap by measuring and comparing worst-case execution time (WCET) and development time across six languages: C<span><math><mrow><mo>+</mo><mo>+</mo></mrow></math></span>, Java, Jade, Jason, and fuzzy Jason BDI with loosely and tightly coupled integration. These technologies represent a progression from procedural and object-oriented programming to agent-oriented frameworks that support symbolic and fuzzy reasoning. Instead of relying on broad or ambiguous notions such as paradigms or orientation, we adopt a developer-centred approach based on measurable outcomes. Our structured comparative analysis explores how increasing levels of abstraction and reasoning capabilities influence both the time required to develop applications and their runtime performance. By examining these dimensions, we reveal practical trade-offs among development effort and execution efficiency. Our findings demonstrate how different abstraction levels and reasoning mechanisms influence both system performance and engineering effort. These results provide practical insights for designing intelligent, agent-based systems that operate under real-time constraints and complex decision-making processes. The study contributes to the ongoing discourse on software selection in industrial informatisation by providing evidence-based guidance that aligns with integration efficiency, software maintainability, and system responsiveness. This work supports future research into the relationship between language features, development dynamics, and runtime behaviour in the context of industrial-oriented cyber–physical and smart manufacturing systems.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"51 ","pages":"Article 101090"},"PeriodicalIF":10.4,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146160923","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":"Retraction notice to \"Lightweight multiparty privacy set intersection protocol for internet of medical things\": [Journal of Industrial Information Integration 47 (2025) 100863]","authors":"Zhuang Shan, Leyou Zhang, Qing Wu, Fatemeh Rezaeibagha","doi":"10.1016/j.jii.2026.101111","DOIUrl":"https://doi.org/10.1016/j.jii.2026.101111","url":null,"abstract":"This article has been retracted: please see Elsevier policy on Article Correction, Retraction and Removal (<ce:inter-ref xlink:href=\"https://www.elsevier.com/about/policies-and-standards/article-withdrawal\" xlink:type=\"simple\">https://www.elsevier.com/about/policies-and-standards/article-withdrawal</ce:inter-ref>).","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"53 1","pages":""},"PeriodicalIF":15.7,"publicationDate":"2026-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147587637","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 thorough assessment of the non-IID data impact in federated learning","authors":"Daniel M. Jimenez-Gutierrez,&nbsp;Mehrdad Hassanzadeh,&nbsp;Aris Anagnostopoulos,&nbsp;Ioannis Chatzigiannakis,&nbsp;Andrea Vitaletti","doi":"10.1016/j.jii.2025.101052","DOIUrl":"10.1016/j.jii.2025.101052","url":null,"abstract":"<div><div>Federated learning (FL) allows collaborative machine learning (ML) model training among decentralized clients’ information, ensuring data privacy. The decentralized nature of FL deals with non-independent and identically distributed (non-IID) data. This open problem has notable consequences, such as decreased model performance and longer convergence times. Despite its importance, experimental studies systematically addressing all types of data heterogeneity (a.k.a. non-IIDness) remain scarce. This paper aims to fill this gap by assessing and quantifying the non-IID effect through an empirical analysis. We use the Hellinger Distance (<span>HD</span>) to measure differences in distribution among clients. Our study benchmarks five state-of-the-art strategies for handling non-IID data, including label, feature, quantity, and spatiotemporal skews, under realistic and controlled conditions. This is the first comprehensive analysis of the spatiotemporal skew effect in FL. Our findings highlight the significant impact of label and spatiotemporal skew non-IID types on FL model performance, with notable performance drops occurring at specific <span>HD</span> thresholds. The FL performance is also heavily affected, mainly when the non-IIDness is extreme. Thus, we provide recommendations for FL research to tackle data heterogeneity effectively. Our work represents the most extensive examination of non-IIDness in FL, offering a robust foundation for future research.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"50 ","pages":"Article 101052"},"PeriodicalIF":10.4,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145845120","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":"Federated split learning-driven multimodal physical-virtual integration framework: high-fidelity full-cross-section deformation field reconstruction in precise metal tube bending manufacturing","authors":"Zili Wang ,&nbsp;Xinlei Hu ,&nbsp;Shuyou Zhang ,&nbsp;Lemiao Qiu ,&nbsp;Yaochen Lin ,&nbsp;Liangyou Li ,&nbsp;Yongzhe Xiang ,&nbsp;Jie Li","doi":"10.1016/j.jii.2025.101048","DOIUrl":"10.1016/j.jii.2025.101048","url":null,"abstract":"<div><div>During the metal tube bending (MTB) process, high-fidelity reconstruction of full cross-section (FCS) deformation is critical to the robustness of closed-loop control in tube-bending manufacturing systems. However, the distributed nature of industrial data, the spatiotemporal discontinuity of physical sensing, and the heterogeneity of multimodal physical–virtual data hinder effective integration of distributed sources and precise reconstruction of the transient deformation of tube surfaces. To address these challenges, we propose a Federated Split-Learning–Driven Multimodal Physical–Virtual Integration (FSLD-MPVI) framework. Leveraging a hybrid distributed–centralized architecture with cross-level collaborative fusion, FSLD-MPVI enables efficient integration and knowledge sharing of local high-fidelity visual data, global low-fidelity finite-element (FE) simulation data, and static process parameters that are dispersed across manufacturing nodes. Within the split learning (SL) distributed architecture, three cascaded, heterogeneous subnetworks are deployed, each dedicated to fusing a specific class of hybrid modality inputs, thereby providing the infrastructure needed to integrate modalities originating from different workshops. In the federated learning (FL) layer, a centralized server aggregates the parameters of each subnetwork respectively, mitigating cross-node data isolation while preserving data locality. Experiments demonstrate that FSLD-MPVI achieves high-accuracy global reconstruction (R² = 0.9973); in the 90° bending case, the shape deviation remains within 0.2 mm. These results verify that multimodal physical–virtual integration strongly supports precise global reconstruction of FCS deformation fields and establishes a new paradigm for intelligent process monitoring in advanced manufacturing systems.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"50 ","pages":"Article 101048"},"PeriodicalIF":10.4,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145845121","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":"Mixed objective scheduling optimization in mountain orchards under energy-saving for carbon neutrality","authors":"Zhentao Xue ,&nbsp;Zhigang Ren ,&nbsp;Jian Chen ,&nbsp;Xiqing Wang ,&nbsp;Shuaisong Zhang","doi":"10.1016/j.jii.2025.101049","DOIUrl":"10.1016/j.jii.2025.101049","url":null,"abstract":"<div><div>The air-ground cooperative plant protection unmanned formation can effectively deal with the complex terrain challenges of mountain orchards and ensure the uniformity of plant protection operation coverage. The core of this system lies in the principles of Industrial Information Integration Engineering (IIIE). Through dynamic scheduling optimization, it can alleviate the problems of large energy consumption and long non-operation paths. Aiming at the dynamic scheduling planning problem, this study proposes an energy-saving hybrid target scheduling optimization method based on an improved Australian wild dog hunting strategy. A novel mountain orchard path coding technology is designed, and an energy consumption model based on the principle of unmanned formation dynamics is established, which provides a scientific basis for formulating efficient energy-saving strategies. The improved Australian wild dog hunting strategy combines the motion constraints of unmanned formation and the requirements of plant protection tasks, and realizes the efficient optimization of the scheduling scheme. Numerical experiments demonstrated the effectiveness of the proposed method, which reduced the objective function to 65.63% of the initial solution in simulations, outperforming the genetic algorithm. This performance was further validated in a real-world scenario, where the value was reduced to 57.34%. This efficient dynamic scheduling optimization serves as a key enabler for agricultural industry integration and informatization.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"50 ","pages":"Article 101049"},"PeriodicalIF":10.4,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145845508","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":"Automating appliance verification in facilities management using a denoised Voltage-Current feature extraction and classification pipeline","authors":"Socretquuliqaa Lee ,&nbsp;Faiyaz Doctor ,&nbsp;Mohammad Hossein Anisi ,&nbsp;Shashank Goud ,&nbsp;Xiao Wang","doi":"10.1016/j.jii.2025.101040","DOIUrl":"10.1016/j.jii.2025.101040","url":null,"abstract":"<div><div>Facilities Management (FM) companies can use load monitoring of electrical appliances (assets) to track energy consumption and predictive maintenance. Reliable algorithms are needed to automatically identify or verify appliances through their energy signatures to improve efficiencies during installation and inspection tasks. Most approaches rely on Voltage-Current (V-I) trajectory. These features are extracted from steady-state current and voltage signals. However, these methods often assume signals are uniformly sampled. In real-world conditions, this assumption does not always hold, leading to misclassified steady-state events when signals are noisy. This paper introduces a novel feature extraction and classification pipeline to ensure the validity of detected steady-state events. The approach measures the approximate entropy of current signals and their correlation with voltage to extract denoised features for appliance type classification. The proposed pipeline is evaluated on a large-scale real-world operational dataset spanning multiple appliance categories. We demonstrate that the extracted denoised features significantly improve the performance of Machine Learning (ML) models used for appliance type classification. Finally, we present a deployment framework for FM settings, enabling digital cataloguing of appliances informing businesses on sustainable choices for appliance requirements.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"50 ","pages":"Article 101040"},"PeriodicalIF":10.4,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145785015","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":"Implementing TinyML in Internet of Things devices: A systematic literature review","authors":"Andrés Felipe Solis Pino ,&nbsp;Daniel Steven Moran Pizarro ,&nbsp;Pablo H. Ruiz ,&nbsp;Vanessa Agredo-Delgado ,&nbsp;Cesar Alberto Collazos ,&nbsp;Fernando Moreira","doi":"10.1016/j.jii.2026.101065","DOIUrl":"10.1016/j.jii.2026.101065","url":null,"abstract":"<div><div>The Internet of Things is at the heart of society and is experiencing rapid expansion. Its integration with Artificial Intelligence and Machine Learning has led to the emergence of Tiny Machine Learning (TinyML), which enables data processing directly on the device, improving efficiency, reducing latency, and increasing data privacy. Despite the growing relevance of TinyML in the Internet of Things, there is a lack of systematic literature reviews providing a holistic understanding of its implementation, advances, and challenges, which hinders a clear understanding of the available empirical evidence and best practices. To bridge this gap, this study presents a systematic literature review, adhering to the PRISMA protocol and employing a multi-database search strategy, identifying 114 primary studies. The review reveals that TinyML is consolidating as a transformative paradigm for the Internet of Things, experiencing significant research growth since 2020. Applications are diverse, with healthcare and environmental monitoring being the most notable examples. Deep learning models, particularly convolutional neural networks, are frequently employed in this context. The main challenges identified include security vulnerabilities, the need to address ethical considerations like algorithmic bias, and hardware limitations related to memory and processing power. Ultimately, this review offers valuable insights into the current state and prospects of TinyML in the Internet of Things, providing a valuable resource for researchers, developers, and decision-makers in this rapidly evolving field.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"50 ","pages":"Article 101065"},"PeriodicalIF":10.4,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145957253","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}