Journal of Industrial Information Integration最新文献

{"title":"Game-theoretic approach to consensus building in multi-objective optimization within multi-scale information systems","authors":"Yibin Xiao ,&nbsp;Jianming Zhan ,&nbsp;Zeshui Xu ,&nbsp;Rosa M. Rodríguez","doi":"10.1016/j.jii.2025.100914","DOIUrl":"10.1016/j.jii.2025.100914","url":null,"abstract":"<div><div>In modern industrial management, integrating heterogeneous data and achieving consensus among decision-makers (DMs) are crucial for optimizing complex systems. Multi-scale information systems (MSISs) have emerged as a powerful tool for managing and fusing diverse data sources. However, reaching consensus in multi-scale environments remains challenging due to data complexity and varying DM preferences. This paper proposes a consensus-reaching process (CRP) method based on MSISs, called MSIS-CRP. Specifically, the sequential clustering-based approach for constructing MSISs stands as the bedrock of this innovative framework. Through the meticulous development of a clustering-driven construction strategy, it excels at precisely discerning the surjective connections among various scales. This not only enables comprehensive data integration at a profound level but also paves the way for robust decision-making analysis, laying a reliable groundwork for subsequent steps in the process. Subsequently, scale weights and DMs’ weights are meticulously calculated according to the characteristics of decision information, thereby effectively reflecting the divergent importance levels of different information dimensions. A calculus-based consensus measure is introduced to quantitatively evaluate DMs’ opinions. To facilitate CRP, global and local consensus feedback mechanisms are established using a multi-objective programming model that balances consensus improvement and adjustment costs. The model is solved from a game-theoretic perspective, leveraging equilibrium concepts to enhance robustness. Comparative and experimental analyses demonstrate that MSIS-CRP effectively improves consensus levels while maintaining computational efficiency, outperforming existing approaches by providing more integrated and comprehensive decision results, especially in dynamic environments. Notably, in numerical experiments involving 48 alternatives and 5 DMs, the MSIS-CRP method achieves a group consensus level of 0.9662 after global feedback, followed by local feedback to reach the final consensus. It demonstrates an adjustment distance of 50.8850 and a running time of 3.7031 s, significantly outperforming seven comparative methods in both efficiency and consensus quality. Overall, this research offers a novel solution for complex decision-making challenges in industrial management by integrating MSISs with CRP.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"47 ","pages":"Article 100914"},"PeriodicalIF":10.4,"publicationDate":"2025-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144757960","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-integrated digital twins for process optimization in Industry 5.0","authors":"Carlos Jefferson de Melo Santos,&nbsp;Ava Santana Barbosa,&nbsp;Angelo Marcio Oliveira Sant’Anna","doi":"10.1016/j.jii.2025.100920","DOIUrl":"10.1016/j.jii.2025.100920","url":null,"abstract":"<div><div>This study responds to the challenges of Industry 5.0 by proposing a hybrid model that integrates Ordinary Differential Equations (ODEs) with Machine Learning (ML) algorithms within a Digital Twin (DT) architecture. The proposal is applied to a detergent manufacturing plant, updating processes focusing on sustainability, resilience, and human-centeredness. The study was conducted in a real industrial plant, with operational data collected from SCADA, MES, and ERP systems. This paper proposes a hybrid model that integrates Machine Learning (ML), Ordinary Differential Equations (ODEs), and a Digital Twin framework for process optimization in the manufacturing industry. The variables were treated in modular architecture and tested within the ISO 23247 framework, with real-time visualizations through human-machine interfaces (HMI). The hybrid approach showed significant gains in predicting chemical solutions (R² = 0.80), sulfonic acid consumption (R² = 0.9998), and intelligent reactor allocation (80.7 % accuracy). In addition, the system predicted laboratory delays with 78.1 % accuracy and enabled significant reductions in loading times and operational deviations. In contrast, raw materials such as caustic soda, water, and laurel showed lower predictive performance, reinforcing the need for additional explanatory variables. The model enhances the potential of predictive AI combined with physical modeling for more sustainable, resilient, and human-centered decisions. Integrating ML and ODEs into a DT promotes operational and strategic gains for the detergent industry, aligning with the principles of Industry 5.0. The demonstrated approach is effective, scalable, and capable of transforming industrial data into optimized decisions, directly impacting the production process's efficiency, sustainability, and autonomy.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"47 ","pages":"Article 100920"},"PeriodicalIF":10.4,"publicationDate":"2025-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144757961","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":"Graph reinforcement learning based dynamic scheduling for human-machine symbiosis manufacturing considering multi-type disturbance events","authors":"Yuxin Li ,&nbsp;Jinlong Zhou ,&nbsp;Youjie Yao ,&nbsp;Qihao Liu ,&nbsp;Xinyu Li ,&nbsp;Liang Gao","doi":"10.1016/j.jii.2025.100917","DOIUrl":"10.1016/j.jii.2025.100917","url":null,"abstract":"<div><div>Human-machine symbiosis manufacturing (HMSM) is widely used in aviation, aerospace, and marine industries due to its powerful production capacity. However, lots of manufacturing resources and multi-type disturbance events bring high complexity and strong uncertainty, which makes scheduling difficult. Meanwhile, deep reinforcement learning (DRL) is a promising information-driven decision-making technology. Therefore, this paper proposes a novel graph reinforcement learning method for the dynamic scheduling problem of HMSM. Specifically, a Markov decision process is established, in which the environment transition mechanism uses four key time points to solve the rarely studied constraints: calendar, normal commuting, and three-shifts. Then, a novel hierarchical aggregation graph neural network is designed, in which the subgraph cutting technology based on node type reduces the difficulty of graph calculation, and an aggregation architecture based on subgraph importance and attention mechanism is designed to achieve effective fusion of heterogeneous node information. Finally, a DRL algorithm with end-to-end action space is proposed, and a response mechanism for nine disturbance events is designed based on the state-action decision-making logic of DRL. Experimental results show that the proposed method outperforms scheduling rule, genetic programming, and two popular DRL methods, and can maintain stable production under uncertain environments.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"47 ","pages":"Article 100917"},"PeriodicalIF":10.4,"publicationDate":"2025-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144779726","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":"From deterministic to Bayesian: Adapting pre-trained models for human-computer collaborative fault diagnosis via post-hoc uncertainty","authors":"Yiming Xiao ,&nbsp;Haidong Shao ,&nbsp;Jie Wang ,&nbsp;Baoping Cai ,&nbsp;Bin Liu","doi":"10.1016/j.jii.2025.100921","DOIUrl":"10.1016/j.jii.2025.100921","url":null,"abstract":"<div><div>Existing fault diagnosis research focuses on improving accuracy, implying that decisions are made by the model alone. This can lead to models providing untrustworthy predictions without the user’s knowledge. Moreover, there are dual pitfalls of black-box effects and imperfect accountability mechanisms. Human-computer collaborative paradigm promises to address these issues by including humans in the decision-making loop, leveraging the strengths of both parties to provide safer decisions. To establish such a paradigm, a support is required and predictive uncertainty is a suitable candidate, which is often captured by constructing Bayesian neural network based on variational inference or deep ensemble. However, these ante-hoc uncertainty methods, which require prior adjustment of the model structure and training the model from scratch, suffer from many limitations: (1) Modification of model structure for uncertainty estimation may sacrifice accuracy or task-specific requirements. (2) These methods multiply the number of parameters and lead to a significant increase in training cost. (3) Retraining a model when a pre-trained model is available can be a waste of resources. Therefore, we propose a post-hoc uncertainty method based on Laplace approximation that quickly and easily switches any pre-trained model from deterministic to Bayesian mode, avoiding heavy computational burden and loss of predictive performance. The proposed method is validated by conducting calibration and OOD detection tasks in both in-domain and cross-domain scenarios, and the experimental results show that the proposed method has comparable or even better uncertainty estimation quality than ante-hoc methods.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"47 ","pages":"Article 100921"},"PeriodicalIF":10.4,"publicationDate":"2025-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144770647","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 structural health monitoring driven by multi-fidelity time-series surrogate models","authors":"Lingkang Li ,&nbsp;Haokun Li ,&nbsp;Ru Wang ,&nbsp;Yulin Liu ,&nbsp;Guoxin Wang ,&nbsp;Yan Yan","doi":"10.1016/j.jii.2025.100918","DOIUrl":"10.1016/j.jii.2025.100918","url":null,"abstract":"<div><div>In structural health monitoring (SHM), real-time observation of a system's structural performance is conventionally undertaken. This involves the utilization of indirect measurement techniques to monitor targets that are not directly quantifiable through sensor readings. The digital twin (DT) concept offers a novel comprehensive structural performance monitoring approach by establishing a virtual-to-physical mapping. Nevertheless, challenges persist in predicting autocorrelated time-series data in dynamic systems and achieving a balance between the costs and modeling accuracy. This paper proposes a Digital Twin framework based on a multi-fidelity time-series surrogate mode. Taking the real-time monitoring of the suspension structure stress of an autonomous mobile robot (AMR) as an example, the application process of this framework is illustrated. First, a load identification model was constructed based on measured data to recognize the load applied to the suspension structure, providing input parameters for the subsequent stress prediction model. The second stage involves the construction of an autoregressive least squares multi-fidelity Gaussian process regression model. Incorporating an autoregressive term within this model enables the integration of the autocorrelation characteristics of the data during prediction whilst simultaneously automating the optimization of hyperparameters based on heuristic rules. This process mitigates the influence of initial hyperparameter settings on the model's training. Finally, a DT of the AMR suspension structure was constructed, and its effectiveness in real-time stress monitoring of the suspension structure was verified under five different working conditions. The work improves the prediction accuracy of time-series monitoring targets in dynamic systems, offering a new solution for applying DT in SHM processes.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"47 ","pages":"Article 100918"},"PeriodicalIF":10.4,"publicationDate":"2025-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144770642","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":"Design an enhanced granulation-degranulation mechanism using group-exchange particle swarm optimization","authors":"Peng Nie,&nbsp;Yuan Gan,&nbsp;Qiang Yu","doi":"10.1016/j.jii.2025.100919","DOIUrl":"10.1016/j.jii.2025.100919","url":null,"abstract":"<div><div>The information granulation-degranulation mechanism is a fundamental content in granular computing theory. For the traditional fuzzy granulation-degranulation mechanism, it is a randomness in the initialization selection of prototypes, which can affect the results by abnormal data and the obtained results of prototypes are not optimal. Besides, the process of granulation-degranulation is accompanied by the generation of reconstruction data errors. In this study we propose a group-exchange particle swarm optimization (GPSO) to enhance the granulation-degranulation mechanism and improve the search strategy for data prototypes. The prototype plays a crucial role in generating reconstruction errors during the granulation-degranulation process. The GPSO can continuously drive the exchange of particle information between different groups to obtain the prototypes and membership matrix that optimize the performance indicators of the granulation-degranulation model. It can minimize the reconstruction errors and obtain optimal solutions from the best set of data prototypes in the solution space, accelerating the process of searching for the best data prototypes, reducing reconstruction errors of the granulation-degranulation mechanism. The experimental results indicate that the performance of our proposed GPSO granulation-degranulation model is improved by 6.81% -45.77%, 2.64% -30.00%, and 10.93% -50.10% compared to the granulation-degranulation models constructed based on FCM algorithm, PSO algorithm, and Boolean algorithm on the testing dataset of different datasets, respectively.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"47 ","pages":"Article 100919"},"PeriodicalIF":10.4,"publicationDate":"2025-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144738953","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":"Industrial digital twins based on enterprise modeling: architecture, methodology, and engineering applications","authors":"Mengjin Qu,&nbsp;Yining Yao,&nbsp;Minhui Sun,&nbsp;Xinran Chang,&nbsp;Qing Li","doi":"10.1016/j.jii.2025.100912","DOIUrl":"10.1016/j.jii.2025.100912","url":null,"abstract":"<div><div>As AI technology increasingly permeates industrial applications, scenario management within the context of industrial intelligence presents a complex, multidisciplinary, and spatiotemporally coupled challenge. The integration characteristics of cyber-physical-social systems make Digital Twins (DT) a promising solution. However, constructing an effective DT model for such scenarios necessitates the incorporation of detailed industrial knowledge related to the corresponding data. Formal modeling serves as a unified cognitive approach and a robust foundation for system development. Hence, this paper focuses on the scenario management challenges within the industrial intelligence context and introduces the concept of using formal modeling languages as the foundation for DTs. We propose a model management architecture and a modeling methodology tailored for scenario-specific digital twins and provide a corresponding metamodel for the modeling approach. To validate the efficacy of our architecture and models, we analyze a multi-enterprise network collaboration scenario in remote maintenance of engineering machinery. This exploration not only demonstrates the validity of the proposed models and architecture but also offers a conceptual DT model for enhancing remote machinery maintenance.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"47 ","pages":"Article 100912"},"PeriodicalIF":10.4,"publicationDate":"2025-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144738954","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":"Green-resilient supplier selection via a new integrated rough multi-criteria framework","authors":"Alptekin Ulutaş ,&nbsp;Ayşe Topal ,&nbsp;Fatih Ecer","doi":"10.1016/j.jii.2025.100913","DOIUrl":"10.1016/j.jii.2025.100913","url":null,"abstract":"<div><div>Initially, companies focused solely on the economic aspects of business processes; now, they have begun to prioritize environmental and social issues to mitigate adverse impacts on the ecology and community. Furthermore, resilience is crucial in ensuring the supply chain remains uninterrupted. Therefore, evaluating the suppliers' sustainability and resilience performance is paramount. A unique mathematical tool is required to integrate resilience and sustainability considerations into supplier selection decisions. Hence, the research fulfills this necessity by introducing a novel, multi-criteria rough methodology. The studies in the literature primarily assess suppliers from either a green or resilient perspective, employing fuzzy MCDM methods to address uncertainty. However, they struggle to cope with uncertainty when faced with limited information. To address this gap, this study proposes a novel approach based on rough set theory to handle interpersonal ambiguity and vagueness flexibly without requiring additional information. It determines the weights of criteria used for green-resilient supplier selection and evaluates the green-resilient performance of suppliers. To this end, rough logarithmic percentage change-driven objective weighting and rough maximum of criterion frameworks are developed to determine criteria weights, whereas the rough mixed aggregation by the comprehensive normalization technique model is designed to decide alternative rankings. This approach requires less prior information than fuzzy set-based methodologies and offers additional flexibility in handling imprecision. To demonstrate its practicality, a real case study from a garment-textile factory in Turkey is presented. The work is the first study of this issue to employ the introduced methodology. Findings highlight that the impact on the local community is the foremost driver for green-resilient supplier selection, followed by cost and supplier sustainability. The model's reliability is validated by comparative and sensitivity analysis. The research contributes to the field by providing a reliable tool that combines rough sets with resilience and sustainability approaches, thus improving the effectiveness and credibility of supplier selection activities in engineering. The work provides executives with an effective supplier evaluation process that jointly addresses sustainability and resilience assessments under uncertainty.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"47 ","pages":"Article 100913"},"PeriodicalIF":10.4,"publicationDate":"2025-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144721862","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":"Explainable AI for industrial fault diagnosis: A systematic review","authors":"J. Cação ,&nbsp;J. Santos ,&nbsp;M. Antunes","doi":"10.1016/j.jii.2025.100905","DOIUrl":"10.1016/j.jii.2025.100905","url":null,"abstract":"<div><div>The integration of Artificial Intelligence (AI) and Machine Learning (ML) into industrial environments, particularly for optimising fault detection and diagnosis, has accelerated with Industry 4.0 and 5.0. However, the “black-box” nature of these methods hinders practical implementation, as trust, interpretability, and explainability are crucial for informed decision-making. Furthermore, impending regulatory frameworks like the EU AI Act make directly implementing opaque AI for critical industrial tasks infeasible. Explainable AI (XAI) offers a promising solution by enhancing ML model interpretability and auditability through human-understandable explanations. This review comprehensively analyses recent XAI advancements for industrial fault detection and diagnosis, presenting a novel taxonomy for XAI methods and discussing how XAI outputs are generated, conveyed to end-users, and evaluated. It then systematically reviews real-world industrial XAI implementations, highlighting their applications, methods, and output presentation approaches. Key identified trends include the dominance of post-hoc feature attribution methods, widespread use of SHAP and GradCAM, and a strong reliance on graphical explanation tools. Finally, it identifies current challenges and outlines future research directions to promote the development of interpretable, trustworthy, and auditable AI systems in industrial settings.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"47 ","pages":"Article 100905"},"PeriodicalIF":10.4,"publicationDate":"2025-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144664947","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":"Switching fuzzy transfer learning for multimodal reservoir fuzzy echo state networks","authors":"Jiawei Lin ,&nbsp;Fu-lai Chung ,&nbsp;Shitong Wang","doi":"10.1016/j.jii.2025.100911","DOIUrl":"10.1016/j.jii.2025.100911","url":null,"abstract":"<div><div>In this study, an interesting yet previously uncared concept—switching fuzzy transfer learning for multimodal reservoir echo state networks—is proposed from three overwhelming phenomena under multimodal reservoir transfer learning environments. Due to the use of reservoir transition, the first phenomenon that the discrimination between different classes along each modal may perhaps be weakened actually encourages the use of fuzzy classification. And then the second one is that source and target domains may occasionally have more overlapping caused by the randomness of reservoir computing, which actually encourages the use of fuzzy similarity for these two domains. The third one that the similarity between source and target domains along each modal and even across different modals may perhaps be distorted inspires the switching of transfer learning across modals. This study explores a novel switching fuzzy transfer learning (SFTL) framework for multimodal reservoir echo state networks. SFTL begins with the calculation of the theoretically derived fuzzy reservoir Stein discrepancies (fuzzy RSDs) between target domain and source domains in the same and even different modals. After that, SFTL trains each modal’s fuzzy transfer learning classifier by taking the proposed adaptive multimodal source switching strategy for an appropriate source domain selection. Finally, SFTL achieves promising multimodal learning through moving from linear aggregation level of each fuzzy transfer learning classifier to the mixture level of both this linear aggregation and the switching ensemble of multimodal source domains. The comprehensive experiments on 31 adopted datasets demonstrate the superiority of SFTL, achieving an average classification accuracy of 85.00 % in the focused multimodal reservoir transfer learning scenario.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"47 ","pages":"Article 100911"},"PeriodicalIF":10.4,"publicationDate":"2025-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144664925","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}