Journal of Industrial Information Integration最新文献

{"title":"Industrial robot system state simulation and risk utilization test environment design","authors":"Wenqi Jiang,&nbsp;Xiaosheng Liu,&nbsp;Zhongwei Li,&nbsp;Xianji Jin,&nbsp;Wenhao Liu,&nbsp;Qingyang Li","doi":"10.1016/j.jii.2025.100953","DOIUrl":"10.1016/j.jii.2025.100953","url":null,"abstract":"<div><div>Network-connected industrial robot systems (IRS) are increasingly exposed to security risks. However, existing testing environments lack the flexibility, modularity, and generalizability of models required for accurate risk simulation. To address these challenges, this paper proposes the IRS State Simulation and Risk Utilization Test Environment (IRSSRE), a novel framework for cost-effective, scalable, and customizable IRS risk analysis. IRSSRE displays the operational states of IRS through Modelica-based modeling at both the component and system levels, ensuring realistic data interactions and state transitions. It also enhances risk management by modularly designing Risk Trigger Modules that explicitly define potential threats, reducing modeling overheads and facilitating the validation of risk utilization scenarios. The capabilities of IRSSRE are demonstrated by simulating a small-scale IRS and replicating the states of both normal and compromised systems through the analysis of four representative attack types and the comparison of device model state curves. The efficiency and effectiveness of the IRSSRE framework are experimentally evaluated, and a comparative analysis with existing alternatives is performed, further demonstrating IRSSRE’s superior performance with respect to low resource overhead and high scalability. IRSSRE offers significant value through the integration of operational and security attributes, enhanced configurability and validation efficiency enabled by modular risk management, and support for simulation replication and granular state-level threat analysis. These contributions advance the field of IRS security testing and provide a scalable foundation for future research in cyber-physical system security.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"48 ","pages":"Article 100953"},"PeriodicalIF":10.4,"publicationDate":"2025-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145096358","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":"HCDA: A hidden cross-domain authentication protocol for embodied intelligence in smart manufacturing","authors":"Huaiyao Yang ,&nbsp;Xiangwei Meng ,&nbsp;Jiale Liang ,&nbsp;Yanrong Zhang ,&nbsp;Keqin Li","doi":"10.1016/j.jii.2025.100946","DOIUrl":"10.1016/j.jii.2025.100946","url":null,"abstract":"<div><div>In smart manufacturing utilizing embodied intelligent robots, frequent cross-domain data transmissions introduce significant challenges on key management. While existing authentication protocols for cross-domain smart manufacturing offer certain advantages in terms of key storage security, their complex network structures and the necessity for repeated session key updates introduce risks related to master key loss, as well as elevated computation cost and communication overhead. To overcome these challenges, this paper proposes a hidden cross-domain authentication (HCDA) protocol for embodied intelligence in smart manufacturing. The domain servers in intelligent manufacturing, functioning as consensus nodes, collaboratively establish a blockchain consortium to securely record public keys and public authentication parameters. Besides, the HCDA protocol based on encryption migration method to reduce the authentication delay of embodied intelligent robots. Specifically, embodied intelligent robots perform symmetric-key encryption/decryption operations and one-way hash functions for authentication request, while domain servers execute the Elliptic Curve Cryptography (ECC) algorithm to generate session key. The security of HCDA protocol is proved by informal analysis. Finally, the simulation results for computation cost and communication overhead demonstrate that the HCDA protocol exhibits significant performance advantages compared with the related protocols.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"48 ","pages":"Article 100946"},"PeriodicalIF":10.4,"publicationDate":"2025-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145096335","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":"Vision language model-enhanced embodied intelligence for digital twin-assisted human-robot collaborative assembly","authors":"Changchun Liu ,&nbsp;Dunbing Tang ,&nbsp;Haihua Zhu ,&nbsp;Zequn Zhang ,&nbsp;Liping Wang ,&nbsp;Yi Zhang","doi":"10.1016/j.jii.2025.100943","DOIUrl":"10.1016/j.jii.2025.100943","url":null,"abstract":"<div><div>Recently, embodied intelligence has emerged as a viable approach to achieving human-like perception, reasoning, decision-making, and execution capacities within human-robot collaborative (HRC) assembly contexts. Due to the lack of generalized enabling technologies and disconnections from physical control systems, embodied intelligence requires repetitive training of various functional models to operate in dynamic HRC scenarios, thereby struggling to adapt effectively to complex and evolving HRC environments. Hence, this study proposes a vision-language model (VLM)-enhanced embodied intelligence framework for digital twin (DT)-assisted human-robot collaborative assembly. Initially, the mapping between embodied agents and physical robots is established to achieve the encapsulation of embodied agents. Building upon the agent-based architecture, a VLM driven by both domain knowledge and real-time scenario data is constructed with sensory capabilities. Based on this, rapid recognition and response to dynamic HRC environments can be realized. Leveraging the strong generalization of VLMs, repetitive training of multiple perception models is circumvented. Furthermore, by utilizing the cognitive learning and intelligent reasoning capabilities of VLMs, an expert knowledge system for assembly processes is developed to provide task-oriented assistance and solution generation. To enhance the adaptability and generalization of complex HRC decision-making, VLMs support reinforcement learning through flexible configuration of HRC assembly state information processing, decision-action generation and guidance, and reward function design. In addition, a DT model of the HRC scenario is constructed to provide a simulation and deduction engine (i.e., embodied brain) for mitigating collision accidents. The decision results are then fed into the VLM as invocation parameters for corresponding sub-function code modules, generating complete collaborative robot action code to form the embodied neuron. Finally, compared with traditional decision methods (e.g., MA-A2C, DQN and GA) and VLM-enhanced MA-A2C, a series of comparative experiments conducted in a real-world HRC assembly scenario demonstrate that the proposed framework exhibits competitive advantages.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"48 ","pages":"Article 100943"},"PeriodicalIF":10.4,"publicationDate":"2025-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145007638","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":"The next-generation digital twin: from advanced sensing towards artificial intelligence-assisted physical-virtual system","authors":"Jianxiong Zhu ,&nbsp;Yaxin Yang ,&nbsp;Mingxuan Xi ,&nbsp;Shanling Ji ,&nbsp;Luyu Jia ,&nbsp;Tao Hu","doi":"10.1016/j.jii.2025.100942","DOIUrl":"10.1016/j.jii.2025.100942","url":null,"abstract":"<div><div>Due to the emerging technologies of the metaverse and the growth of the Internet of Things(IoTs), digital twin has became compelling research topics along with the field of industrial automation, robotics, etc. To understand the advancement of digital twin relating elements, three issues need to be mentioned. The first technology is the advanced sensing component mainly aiming to objects status identification, functional electronic materials to break detection limitation, and data-enhancement by virtual sensors. Among them, sensing with the ability of self-powered, high-sensitivity, and soft electronic dramatically facilitates digital twin in high-accuracy and fast response. Secondly, the physical-virtual model towards intelligent system in digital twin is summerized to utilize simulating real prototype and virtual reality, especially physical-virtual prototype, subsystems, and artificial intelligent-enhanced digital twin system. Finally, owing to the machine learning and artificial intelligence, the next-generation digital twin system with advnaced sensing, physical-virtual system, and artificial intelligent-enhanced in various applications in one system would be the future trend. This review not only systemly reports digital twin from sensing component, the fundamental theory to the physical-virtual prototype, and artificial intelligence-enhanced technologies, it also presnets the future trajectory of the next-generation of digital twin as well as the challenges for various potential applications.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"48 ","pages":"Article 100942"},"PeriodicalIF":10.4,"publicationDate":"2025-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145007635","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":"Machine learning knowledge driven investigation for immunity infused fractional industrial virus transmission in SCADA systems","authors":"Kiran Asma ,&nbsp;Muhammad Asif Zahoor Raja ,&nbsp;Chuan-Yu Chang ,&nbsp;Muhammad Junaid Ali Asif Raja ,&nbsp;Chi-Min Shu ,&nbsp;Muhammad Shoaib","doi":"10.1016/j.jii.2025.100940","DOIUrl":"10.1016/j.jii.2025.100940","url":null,"abstract":"<div><div>Supervisory control and data acquisition (SCADA) environment is a highly sensitive and crucial industrial control system primarily deployed to monitor, control and automate the critically integrated and interconnected complex networks. Due to revolution in communication technology, SCADA systems encounter escalating cybersecurity threats and mandate proactive safeguard mechanisms to prevent cyberattack surfaces that may interrupt critical core services, maleficent equipment, and even threaten the social security in certain circumstances. This work aims to enhance the standard nonlinear industrial virus transmission (NIVT) model with immunity for SCADA systems by incorporating fractional‐order processing and then leveraging machine learning through nonlinear multilayer autoregressive exogenous (NM-ARX) neural networks iteratively trained with Bayesian regularization (BR)—the NM-ARX-BR methodology. The Caputo fractional differentiation operator inspired fractional implicit Adams–Moulton and explicit Adams–Bashforth multistep solvers are used to generate reference simulation dataset for NM-ARX-BR neuroarchitecture in case of fractional kinetic of immunity-based NIVT model with five dynamic states susceptible nodes <em>S</em>, enhanced-susceptible nodes <em>E</em>, latent nodes <em>L</em>, breakout nodes <em>B,</em> and recovered nodes <em>R</em> in the SCADA environment. The rigorous simulation based comprehensive comparative evaluation revealed that the low value of fitness on mean square error (MSE) in the range of 10⁻¹⁴ to 10⁻¹⁶ is achieved by NM-ARX-BR neurocomputational framework for sundry case studies of immunity-based NIVT system and performance is further validated by proximity analysis, cross correlation and autocorrelation analysis, histogram frequency distribution and regression statistics. The presented NM-ARX-BR framework depicts the resilience, accuracy, and consistency in modelling the fractional kinetics of immunity-based nonlinear industrial virus transmission in the SCADA systems by executing single and multiple step-ahead prediction measures during the exhaustive numerical simulations with error ranges of 10⁻¹³ to 10⁻¹⁶. The performance assessment is carried out utilizing three standard error metrics MSE, mean absolute error (MAE), root mean square error (RMSE) and phase space error (PSE). The error values of MSE, MAE, PSE and RMSE are remarkably low 10⁻⁰⁷ to 10⁻⁰⁹, demonstrate the robustness, generalization capability and high fidelity of NM-ARX-BR technique.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"48 ","pages":"Article 100940"},"PeriodicalIF":10.4,"publicationDate":"2025-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145049156","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":"Dynamic modelling and multidisciplinary injury-based design optimization of driver workspace in high-speed train collisions","authors":"Honghao Zhang ,&nbsp;Dongtao Yu ,&nbsp;Lin Hou ,&nbsp;Danqi Wang ,&nbsp;Yong Peng","doi":"10.1016/j.jii.2025.100939","DOIUrl":"10.1016/j.jii.2025.100939","url":null,"abstract":"<div><div>The driver workspace is the closest region to the collision zone, making it the most vulnerable to direct impact during a collision event. Designing optimal parameter configurations for this workspace is critical, as it plays a vital role in the passive safety protection system of trains, ensuring enhanced safety in industrial rail vehicle design and production. To minimize collision risks, this study establishes an authentic driver cabin dynamics model based on the MADYMO and implements a preference-based hybrid optimization strategy for Driver Workspace Layout Optimization (DWLOP). A coupled console-seat-dummy dynamic model employing three-dimensional acceleration profiles from train-to-train collisions as boundary conditions is developed to accurately simulate occupant dynamics in collision scenarios. A comprehensive driver collision injury evaluation index system was established by integrating the Weighted Injury Criteria (WIC), the UK AV/ST9001 standard, and the US FMVSS208 standard. A hybrid preference-based many-objective optimization algorithm strategy, namely S-VI, under interval 2-tuple linguistic sets combining Subspace Segmentation based Co-evolutionary Algorithm (SSCEA) and VIKOR, is proposed to solve the DWLOP. The injury metrics across different body regions are used as the optimization objective to minimize the damage to drivers. The performance comparison demonstrates SSCEA has superior performance in processing DWLOP compared to other algorithms. The optimization result shows significant improvements in head safety performance, with HIC reduced by 83.31 %, and a₃ₘₛ decreased by 54.61 %. The results confirm that the proposed S-VI optimization strategy offers substantial advantages in DWLOP. The integration of these techniques contributes to improve the passive safety protection management of trains and provide reference for the construction of the train production safety industry.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"48 ","pages":"Article 100939"},"PeriodicalIF":10.4,"publicationDate":"2025-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144933382","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":"Real-time path planning for multi-scenario headland turns in agricultural vehicles using panoramic vision and sequential frame correlation method","authors":"Dongfang Li ,&nbsp;Yu Lei ,&nbsp;Jiali Fan ,&nbsp;Shaoqing Cui ,&nbsp;Jun Wang ,&nbsp;Maohua Xiao ,&nbsp;Yejun Zhu","doi":"10.1016/j.jii.2025.100938","DOIUrl":"10.1016/j.jii.2025.100938","url":null,"abstract":"<div><div>Headland turning poses a significant challenge to the vision-based autonomous navigation of agricultural vehicles. Compared to in-field crop row tracking, headland turning requires a greater variety of maneuvers with larger turning angles. Existing research on agricultural vehicle navigation is limited to using a single front-facing camera as the sensor. However, during turning maneuvers, the field of view of a single front-facing vision sensor is restricted, inevitably losing perception of the headland area. Unfortunately, no practical purely vision-based headland turning method has been proposed yet. To address this critical gap in agricultural automation, which demands robust industrial information integration engineering (IIIE) solutions, a panoramic surround view (PSV) system incorporating four fisheye cameras was developed in this study. The PSV image generated enabled a continuous perception of the relative position between the agricultural vehicle and the headland. Moreover, due to the vast disparity in perceived viewpoints and navigational references, previous methods for detecting navigational lines in the field are no longer applicable. Therefore, leveraging the integrated panoramic data stream, a multi-scenario headland turning path planning algorithm tailored for panoramic vision has been developed by extracting valuable correlations between sequential panoramic frames and integrating deep learning techniques. Robust detection of the headland area in PSV images was accomplished through semantic segmentation. Functional area delineation of the headland was achieved by correlating the headland locations within adjacent frames, thus enabling accurate turn path planning. Leveraging the lightweight model CGNet, the mean intersection over union (mIoU) for the semantic segmentation of the headland reached 92.84%. The average deviation of the detected headland boundary was 5.63 pixels in an image with a resolution of 640×340. The proposed algorithm demonstrated an inference speed of 18.45 frames per second. Field navigation experiments have yielded promising results, demonstrating that the proposed method effectively addresses the practical challenge of vision-only headland turning for agricultural vehicles, thereby laying the groundwork for a fully vision-based IIIE navigation system in agricultural applications, contributing to the broader goals of industrial integration and informatization in agriculture.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"48 ","pages":"Article 100938"},"PeriodicalIF":10.4,"publicationDate":"2025-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145007637","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":"Optimizing production and remanufacturing strategies for a complex smart single stage production system under uncertainty and waste nullification","authors":"Bikash Koli Dey ,&nbsp;Hyesung Seok","doi":"10.1016/j.jii.2025.100936","DOIUrl":"10.1016/j.jii.2025.100936","url":null,"abstract":"<div><div>Market conditions are highly changeable in today’s competitive environment, leading to uncertain demand and distinctive unit costs. Specifically, the information on market demand for newly launched assembled items (e.g., smart mobiles, laptops, etc.) is highly unpredictable. There is limited data available regarding the expenses involved in producing new products/components. Therefore, unlike previous studies used crisp values of demand and manufacturing costs to synthesize the most effective economic production quantity models for management decision-making, it was attempted here to apply fuzzy theory because of the nature of uncertainty in demand and manufacturing costs. In addition, the autonomated inspection and single-stage manufacturing-remanufacturing were considered such that assembling product can be made better quality. The faulty items are randomly generated in the manufacturing but could be detected through autonomated inspection and remanufactured within a single cycle. Such manufacturing and remanufacturing in a single stage are more cost-effective than traditional manufacturing, which separates them into two stages. This study optimizes the production lot size, backorder, and investment for inspection. Autonomation inspection strategy helps to make this production system 5.95% cost-effective. In addition, a budget and a space constraint is used to make this model realistic. Those constraints help to reduce the cost by 34.51%. A numerical experiment and sensitivity are conducted for different defective rates and conditions.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"48 ","pages":"Article 100936"},"PeriodicalIF":10.4,"publicationDate":"2025-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144933383","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":"Dimension Decoupling Vision-Language Transformer for industrial container marking and natural scene text spotting","authors":"Zhangzhao Liang ,&nbsp;Ying Xu ,&nbsp;Yikui Zhai ,&nbsp;Hufei Zhu ,&nbsp;Jiangtao Xi ,&nbsp;Pasquale Coscia ,&nbsp;Angelo Genovese","doi":"10.1016/j.jii.2025.100926","DOIUrl":"10.1016/j.jii.2025.100926","url":null,"abstract":"<div><div>The exceptional performance of Deep Learning has significantly advanced the widespread application of text spotting across various downstream tasks, such as electronic document recognition, traffic sign recognition, and bill number recognition. A challenging and crucial application is Container Marking Text Spotting (CMTS), which aims to swiftly capture logistics information from container surfaces and enhance the overall operational efficiency of logistics systems. Unlike the extensively studied natural scene text, text on container markings typically comprises contextless texts (such as ”45G1”, ”CWFU 1810810”), presenting a unique spotting challenge. In addition, part of the vertical text and the widely used non-end-to-end models in this field also limit the performance of container text spotting. Overall, due to the lack of further research in the task of container text spotting, the performance of the current model is unsatisfactory. This greatly affects the intelligence and informatization of the container industry. Therefore, there is an urgent need for a high-performance and easy to deploy method to improve the spotting accuracy of container surface text. This can not only effectively reduce the cost of obtaining container information, but also improve the overall intelligence level of the industry. In this paper, we propose a Dimension Decoupling Vision-Language Transformer (DVLT) for achieving high-performance in CMTS tasks. To address the challenges of contextless texts, our approach incorporates a Semantic Augmentation Module that leverages prior knowledge without adding computational overhead during inference. Additionally, we introduce center-line proposals to enhance the model’s adaptability to vertical text. Finally, DVLT improves the model’s comprehensive text spotting capabilities through a novel Dimension Decoupling Decoder. DVLT is a completely end-to-end text spotting transformer, which achieved state-of-the-art on the CMTS task (dataset publicly available) and also demonstrated competitive results on well-known benchmarks such as CTW1500, ICDAR2015 and Total-Text. The code and dataset are available at: <span><span>https://github.com/yikuizhai/DVLT</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"48 ","pages":"Article 100926"},"PeriodicalIF":10.4,"publicationDate":"2025-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144898589","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":"Cyber-physical internet spatial-temporal reasoning for production logistics resource recommendation in Industry 4.0","authors":"Jinpeng Li ,&nbsp;Mingyue Sun ,&nbsp;Zhiheng Zhao ,&nbsp;George Q. Huang","doi":"10.1016/j.jii.2025.100935","DOIUrl":"10.1016/j.jii.2025.100935","url":null,"abstract":"<div><div>Production logistics (PL) focuses on planning, allocating, and controlling the material and information flows within production processes. In discrete manufacturing, PL is characterized by significant dynamics and uncertainty due to fluctuating resource demands and operational asynchrony. Reliable PL resource allocation is not only fundamental for improving production efficiency but also serves as a crucial prerequisite for orchestrating various resources to achieve zero inventory or even zero warehousing. Therefore, this paper proposes a recommendation-based PL resource allocation approach that considers the temporal and spatial characteristics of shop floors and production materials. To accurately represent the relationships of various entities and resource allocation history, we borrow the idea from the digital Internet, where the IP address and routing tables contribute to moving data packets, to design the Cyber-Physical Internet (CPI) addresses and routing tables, which represent location areas and resource flow directions, and thereby construct the resource spatial-temporal knowledge graph (RSTKG). Then, a spatial-temporal reasoning mechanism is proposed, which conducts connectivity, contextual, and collaborative reasoning on RSTKG to evaluate the cost-effectiveness between required nodes and available resources and generate the resource allocation recommendation plan. Finally, the allocation decisions will be updated to the related routing table of each node. When new resources arrive, table lookup can be conducted to understand the next transfer direction, reducing the risk of delay during the actual transportation of resources. To evaluate the effectiveness of the proposed approach, we first conduct a laboratory experiment and then conduct a case study on an air conditioning manufacturer. Compared to other resource allocation algorithms, our approach achieves a punctuality rate of over 90%, reduces the average traveling distance, and improves the efficiency of traceability analysis.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"48 ","pages":"Article 100935"},"PeriodicalIF":10.4,"publicationDate":"2025-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144898604","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}