Journal of Industrial Information Integration最新文献_第9页

Self-adaptive solution for industrial integration of AI-based decision-making systems for industrial flows management 基于人工智能的工业流程管理决策系统集成自适应解决方案

IF 10.4 1区计算机科学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Journal of Industrial Information Integration

Pub Date : 2025-10-14 DOI: 10.1016/j.jii.2025.100971

Ivo Perez Colo , Carolina Saavedra Sueldo , Luis Avila , Geraldina Roark , Gerardo G. Acosta , Mariano De Paula

From the perspective of systems theory, a production process can be conceptualized as an organized set of operations that primarily involves managing the flow of materials, goods, energy, and information. Optimal management of industrial flows is a complex decision-making problem that has been addressed for decades, from modeling and optimization theory to today’s artificial intelligence (AI) techniques. However, although many modern AI-based proposals have been successfully tested in various and diverse flow optimization problems, their performance and transferability to industrial plants are strongly dependent on their high-dimensional hyper-parameter settings. Typically, hyper-parameter tuning is still performed by human experts who spend a considerable amount of time conducting trial-and-error heuristic searches for optimal hyper-parameter configurations. This fact, in addition to being inefficient, makes democratization, integration, and scalability towards industrial systems inconvenient, as they commonly have limited qualified expert human resources. Keeping in mind this fact, in this work, we propose a simulation-based Bayesian optimization approach for autonomous optimal hyper-parameter adjustment of black-box AI-based decision-making techniques. Our proposal was tested on two flow optimization problems of very different nature and behavior, and each of them was addressed with different modern AI-based decision-making techniques.

从系统理论的角度来看，生产过程可以被概念化为一组有组织的操作，主要涉及管理材料、货物、能源和信息的流动。工业流程的优化管理是一个复杂的决策问题，从建模和优化理论到今天的人工智能（AI）技术，已经解决了几十年。然而，尽管许多现代基于人工智能的建议已经成功地在各种各样的流动优化问题中进行了测试，但它们的性能和可转移性在很大程度上依赖于它们的高维超参数设置。通常，超参数调优仍然由人类专家执行，他们花费相当多的时间进行试错启发式搜索，以获得最优的超参数配置。除了效率低下之外，这一事实还不利于工业系统的民主化、集成和可扩展性，因为它们通常只有有限的合格专家人力资源。考虑到这一事实，在本工作中，我们提出了一种基于模拟的贝叶斯优化方法，用于基于黑盒人工智能的决策技术的自主最优超参数调整。我们的建议在两个性质和行为非常不同的流程优化问题上进行了测试，每个问题都使用不同的现代基于人工智能的决策技术来解决。

{"title":"Self-adaptive solution for industrial integration of AI-based decision-making systems for industrial flows management","authors":"Ivo Perez Colo , Carolina Saavedra Sueldo , Luis Avila , Geraldina Roark , Gerardo G. Acosta , Mariano De Paula","doi":"10.1016/j.jii.2025.100971","DOIUrl":"10.1016/j.jii.2025.100971","url":null,"abstract":"<div><div>From the perspective of systems theory, a production process can be conceptualized as an organized set of operations that primarily involves managing the flow of materials, goods, energy, and information. Optimal management of industrial flows is a complex decision-making problem that has been addressed for decades, from modeling and optimization theory to today’s artificial intelligence (AI) techniques. However, although many modern AI-based proposals have been successfully tested in various and diverse flow optimization problems, their performance and transferability to industrial plants are strongly dependent on their high-dimensional hyper-parameter settings. Typically, hyper-parameter tuning is still performed by human experts who spend a considerable amount of time conducting trial-and-error heuristic searches for optimal hyper-parameter configurations. This fact, in addition to being inefficient, makes democratization, integration, and scalability towards industrial systems inconvenient, as they commonly have limited qualified expert human resources. Keeping in mind this fact, in this work, we propose a simulation-based Bayesian optimization approach for autonomous optimal hyper-parameter adjustment of black-box AI-based decision-making techniques. Our proposal was tested on two flow optimization problems of very different nature and behavior, and each of them was addressed with different modern AI-based decision-making techniques.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"48 ","pages":"Article 100971"},"PeriodicalIF":10.4,"publicationDate":"2025-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145362790","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}

引用次数: 0

Distillation anomaly and fault detection based on clustering algorithms 基于聚类算法的蒸馏异常与故障检测

IF 10.4 1区计算机科学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Journal of Industrial Information Integration

Pub Date : 2025-10-14 DOI: 10.1016/j.jii.2025.100970

F.M. Martínez-García , A. Molina García , F.C. Gómez de León , M. Alarcón

Anomaly detection in production processes is essential for ensuring reliability and efficiency in the industrial sector. In this way, system optimization requires advanced monitoring strategies such as predictive maintenance and intelligent fault detection. Traditional diagnostic methods rely on retrospective data analysis and deterministic cause-effect models, while machine learning approaches enable real-time monitoring and data-driven modeling to detect deviations from normal operation. This study proposes a scalable anomaly detection framework based on clustering algorithms, specifically applied to batch distillation processes—critical operations in chemical manufacturing that remain underexplored in real-world applications, particularly in multiproduct plants. The methodology was validated through an industrial case study at a chemical facility in El Palmar, Murcia (Spain), operated by a multinational corporation. Over 300,000 data points were collected over three years, focusing on critical variables governing distillation unit performance. Clustering techniques including k-means, DBSCAN, and hierarchical clustering were applied to identify deviations from standard operating conditions. Results demonstrate the effectiveness, flexibility, and scalability of the proposed approach, detecting anomalies in real time due to equipment faults, unstable conditions, or operator error. Integration of this system reduces unplanned shutdowns, improves energy efficiency, safety, and product quality, and provides operators with a real-time dashboard for decision support. Statistical evaluation of algorithms ensures adaptability across product types, while the custom application enables graphical monitoring of process deviations. Future work includes integrating performance indicators and ERP/MES connectivity. This framework serves as a reference model for deploying scalable anomaly detection systems across diverse industrial environments.

生产过程中的异常检测对于确保工业部门的可靠性和效率至关重要。在这种情况下，系统优化需要先进的监控策略，如预测性维护和智能故障检测。传统的诊断方法依赖于回顾性数据分析和确定性因果模型，而机器学习方法可以实现实时监控和数据驱动建模，以检测与正常操作的偏差。本研究提出了一种基于聚类算法的可扩展异常检测框架，特别适用于批量蒸馏过程-化学制造中的关键操作，在实际应用中仍未得到充分探索，特别是在多产品工厂中。该方法在穆尔西亚El Palmar（西班牙）一家跨国公司经营的化学设施的工业案例研究中得到证实。在三年中收集了超过300,000个数据点，重点关注控制蒸馏装置性能的关键变量。包括k-means、DBSCAN和分层聚类在内的聚类技术被用于识别与标准操作条件的偏差。结果证明了该方法的有效性、灵活性和可扩展性，可以实时检测由于设备故障、不稳定条件或操作员错误导致的异常。该系统的集成减少了意外停机，提高了能源效率、安全性和产品质量，并为作业者提供了实时仪表板，为决策提供支持。算法的统计评估确保了跨产品类型的适应性，而自定义应用程序允许对过程偏差进行图形化监控。未来的工作包括整合绩效指标和ERP/MES连接。该框架可作为在不同工业环境中部署可伸缩异常检测系统的参考模型。

{"title":"Distillation anomaly and fault detection based on clustering algorithms","authors":"F.M. Martínez-García , A. Molina García , F.C. Gómez de León , M. Alarcón","doi":"10.1016/j.jii.2025.100970","DOIUrl":"10.1016/j.jii.2025.100970","url":null,"abstract":"<div><div>Anomaly detection in production processes is essential for ensuring reliability and efficiency in the industrial sector. In this way, system optimization requires advanced monitoring strategies such as predictive maintenance and intelligent fault detection. Traditional diagnostic methods rely on retrospective data analysis and deterministic cause-effect models, while machine learning approaches enable real-time monitoring and data-driven modeling to detect deviations from normal operation. This study proposes a scalable anomaly detection framework based on clustering algorithms, specifically applied to batch distillation processes—critical operations in chemical manufacturing that remain underexplored in real-world applications, particularly in multiproduct plants. The methodology was validated through an industrial case study at a chemical facility in El Palmar, Murcia (Spain), operated by a multinational corporation. Over 300,000 data points were collected over three years, focusing on critical variables governing distillation unit performance. Clustering techniques including k-means, DBSCAN, and hierarchical clustering were applied to identify deviations from standard operating conditions. Results demonstrate the effectiveness, flexibility, and scalability of the proposed approach, detecting anomalies in real time due to equipment faults, unstable conditions, or operator error. Integration of this system reduces unplanned shutdowns, improves energy efficiency, safety, and product quality, and provides operators with a real-time dashboard for decision support. Statistical evaluation of algorithms ensures adaptability across product types, while the custom application enables graphical monitoring of process deviations. Future work includes integrating performance indicators and ERP/MES connectivity. This framework serves as a reference model for deploying scalable anomaly detection systems across diverse industrial environments.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"48 ","pages":"Article 100970"},"PeriodicalIF":10.4,"publicationDate":"2025-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145362793","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}

引用次数: 0

Enabling human–CPS cognitive interoperability: Cognitive architectures as technologies for human-like cognitive digital twins 实现人类- cps认知互操作性：作为类人认知数字孪生技术的认知架构

IF 10.4 1区计算机科学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Journal of Industrial Information Integration

Pub Date : 2025-10-13 DOI: 10.1016/j.jii.2025.100969

Al Haj Ali Jana , Ben Gaffinet , Mario Lezoche , Hervé Panetto , Yannick Naudet

Cognition, the set of mental processes that enable humans to perceive, reason, learn and decide, plays an essential role in effective collaboration between humans and Cyber–Physical Systems (CPSs). To achieve seamless cognitive interoperability between humans and CPSs, it is necessary to integrate a Cognitive Digital Twin (CDT) and a Human Digital Twin (HDT) to provide digital representations of both physical assets and human cognitive states. In this article, we first analyse the three essential functions of CDT and HDT: emulation, cognition and simulation, and review the state-of-the-art technologies for each of them, from supervised learning and knowledge graphs to deep reinforcement learning. Focusing on the cognitive layer, we review the state of the art in cognitive architectures, describing their symbolic, sub-symbolic and hybrid types and reporting on their real-world implementations in different domains. We then assess the relevance of these architectures for the integration of human-like reasoning in CDTs. Finally, we identify the main technological challenges and gaps that need to be addressed in order to implement fully operational CDTs.

认知是一组使人类能够感知、推理、学习和决策的心理过程，在人类和信息物理系统（cps）之间的有效协作中起着至关重要的作用。为了实现人类和cps之间无缝的认知互操作性，有必要集成认知数字双胞胎（CDT）和人类数字双胞胎（HDT），以提供物理资产和人类认知状态的数字表示。在本文中，我们首先分析了CDT和HDT的三个基本功能：仿真、认知和仿真，并回顾了它们各自的最新技术，从监督学习和知识图到深度强化学习。关注认知层，我们回顾了认知架构的最新进展，描述了它们的符号、子符号和混合类型，并报告了它们在不同领域的实际实现。然后，我们评估了这些架构在cdt中集成类人推理的相关性。最后，我们确定了需要解决的主要技术挑战和差距，以便全面实施可操作的cdt。

{"title":"Enabling human–CPS cognitive interoperability: Cognitive architectures as technologies for human-like cognitive digital twins","authors":"Al Haj Ali Jana , Ben Gaffinet , Mario Lezoche , Hervé Panetto , Yannick Naudet","doi":"10.1016/j.jii.2025.100969","DOIUrl":"10.1016/j.jii.2025.100969","url":null,"abstract":"<div><div>Cognition, the set of mental processes that enable humans to perceive, reason, learn and decide, plays an essential role in effective collaboration between humans and Cyber–Physical Systems (CPSs). To achieve seamless cognitive interoperability between humans and CPSs, it is necessary to integrate a Cognitive Digital Twin (CDT) and a Human Digital Twin (HDT) to provide digital representations of both physical assets and human cognitive states. In this article, we first analyse the three essential functions of CDT and HDT: emulation, cognition and simulation, and review the state-of-the-art technologies for each of them, from supervised learning and knowledge graphs to deep reinforcement learning. Focusing on the cognitive layer, we review the state of the art in cognitive architectures, describing their symbolic, sub-symbolic and hybrid types and reporting on their real-world implementations in different domains. We then assess the relevance of these architectures for the integration of human-like reasoning in CDTs. Finally, we identify the main technological challenges and gaps that need to be addressed in order to implement fully operational CDTs.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"48 ","pages":"Article 100969"},"PeriodicalIF":10.4,"publicationDate":"2025-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145315170","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}

引用次数: 0

Cognitive Digital Twin for industrial maintenance: operational framework for fault detection and diagnosis 工业维护的认知数字孪生：故障检测和诊断的操作框架

IF 10.4 1区计算机科学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Journal of Industrial Information Integration

Pub Date : 2025-10-12 DOI: 10.1016/j.jii.2025.100974

Sofia Zappa , Chiara Franciosi , Adalberto Polenghi , Alexandre Voisin

Digital Twin is a cutting-edge technology designed to address disruptions in manufacturing operations by supporting humans in complex maintenance decisions via advanced data analytics and real-time synchronization. However, as the complexity of decisions increases, enhanced capabilities are required, such as reasoning and context awareness, leading to the Cognitive Digital Twin (CDT) concept. In this context, this work offers two contributions. First, it presents a state-of-the-art review on CDT for maintenance in manufacturing, identifying Fault Detection and Diagnosis (FDD) as a relevant investigation area. Second, it proposes a novel CDT framework specifically tailored to support FDD in industrial maintenance. The contributions are twofold: (i) an ontology that formalises maintenance expert knowledge and supports diagnostic reasoning; and (ii) data-driven algorithms that elaborate data from the physical system, and instantiate or update the proposed ontology. The structured integration of ontology and data analytics into an operational CDT framework enables and properly places all six cognitive capabilities - perception, attention, memory, reasoning, problem-solving, and learning - within a domain-specific framework tailored to maintenance, and especially to support FDD decisions. The CDT output is the augmented information flowing to the maintenance decision-making process, which is held by the maintenance staff, who, after the completion of the FDD activity, can act back on the physical asset with the required maintenance interventions. The CDT framework is finally tested in a laboratory setting, demonstrating its functional effectiveness in supporting maintainers in the FDD decision-making process by formalizing knowledge and guiding reasoning.

Digital Twin是一项尖端技术，旨在通过先进的数据分析和实时同步，支持人类进行复杂的维护决策，从而解决制造操作中的中断问题。然而，随着决策复杂性的增加，需要增强的功能，例如推理和上下文感知，从而产生认知数字孪生（CDT）概念。在此背景下，这项工作提供了两个贡献。首先，它介绍了CDT在制造维修中的最新进展，确定故障检测和诊断（FDD）作为相关的研究领域。其次，它提出了一个新的CDT框架，专门用于支持工业维护中的FDD。贡献是双重的：(i)一个将维护专家知识形式化并支持诊断推理的本体；（ii）数据驱动的算法，这些算法详细说明来自物理系统的数据，并实例化或更新所提出的本体。将本体和数据分析结构化地集成到一个可操作的CDT框架中，可以将所有六种认知能力——感知、注意、记忆、推理、解决问题和学习——适当地放置在为维护量身定制的特定领域框架中，特别是支持FDD决策。CDT输出是流向维护决策过程的增强信息，该决策过程由维护人员持有，维护人员在完成FDD活动后，可以使用所需的维护干预措施对物理资产采取行动。CDT框架最后在实验室环境中进行了测试，通过形式化知识和指导推理，证明了它在支持FDD决策过程中维护人员的功能有效性。

{"title":"Cognitive Digital Twin for industrial maintenance: operational framework for fault detection and diagnosis","authors":"Sofia Zappa , Chiara Franciosi , Adalberto Polenghi , Alexandre Voisin","doi":"10.1016/j.jii.2025.100974","DOIUrl":"10.1016/j.jii.2025.100974","url":null,"abstract":"<div><div>Digital Twin is a cutting-edge technology designed to address disruptions in manufacturing operations by supporting humans in complex maintenance decisions via advanced data analytics and real-time synchronization. However, as the complexity of decisions increases, enhanced capabilities are required, such as reasoning and context awareness, leading to the Cognitive Digital Twin (CDT) concept. In this context, this work offers two contributions. First, it presents a state-of-the-art review on CDT for maintenance in manufacturing, identifying Fault Detection and Diagnosis (FDD) as a relevant investigation area. Second, it proposes a novel CDT framework specifically tailored to support FDD in industrial maintenance. The contributions are twofold: (i) an ontology that formalises maintenance expert knowledge and supports diagnostic reasoning; and (ii) data-driven algorithms that elaborate data from the physical system, and instantiate or update the proposed ontology. The structured integration of ontology and data analytics into an operational CDT framework enables and properly places all six cognitive capabilities - perception, attention, memory, reasoning, problem-solving, and learning - within a domain-specific framework tailored to maintenance, and especially to support FDD decisions. The CDT output is the augmented information flowing to the maintenance decision-making process, which is held by the maintenance staff, who, after the completion of the FDD activity, can act back on the physical asset with the required maintenance interventions. The CDT framework is finally tested in a laboratory setting, demonstrating its functional effectiveness in supporting maintainers in the FDD decision-making process by formalizing knowledge and guiding reasoning.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"48 ","pages":"Article 100974"},"PeriodicalIF":10.4,"publicationDate":"2025-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145362796","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}

引用次数: 0

Manufacturing process scheduling method based on multi-level and cross-chain collaboration under industrial internet environment 工业互联网环境下基于多级跨链协同的制造过程调度方法

IF 10.4 1区计算机科学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Journal of Industrial Information Integration

Pub Date : 2025-10-11 DOI: 10.1016/j.jii.2025.100972

Wenjun Xu , Jinshan Zhong , Jiayi Liu , Shuang Zheng , Xianglong Zou , Feng Liu

Under the industrial internet environment, achieving effective manufacturing process scheduling requires collaboration across the workshop level, production line level, industrial chain, and value chain. This collaboration enables the integration of manufacturing process information, aligning scheduling more closely with practical operations. However, the existing scheduling approaches mainly focus on a single level or a single chain, lacking the ability to address multi-level and cross-chain collaborative optimization. To overcome this limitation, this paper proposes a scheduling method for manufacturing process based on multi-level and cross-chain collaboration (MPMLCC) under the industrial internet environment. Firstly, the mathematical model is established to represent the four key stages of the manufacturing process: parts procurement, transportation, sub-assembly, and final assembly. The optimization model aims to minimize both the makespan and the total cost, reflecting time and cost efficiency across all stages. Then, an improved multi-objective grey wolf optimizer (IMOGWO) is designed to solve the MPMLCC scheduling problem. The algorithm integrates the opposition-based learning (OBL), the multi-neighborhood local search strategy to balance global exploration and local exploitation. Case studies based on the small satellites Oresat0 and Oresat1B are conducted to verify the effectiveness of the proposed method. Experimental results demonstrate that the proposed approach significantly improves solution quality and stability compared to the other multi-objective optimization algorithms. Furthermore, the scheduling outcomes confirm the effectiveness of manufacturing process information integration and collaborative optimization across multiple levels and chains.

在工业互联网环境下，实现有效的制造过程调度需要车间层面、生产线层面、产业链、价值链层面的协同。这种协作能够集成制造过程信息，使调度与实际操作更紧密地结合起来。然而，现有的调度方法主要集中在单一层次或单链上，缺乏解决多层次和跨链协同优化的能力。为了克服这一局限性，本文提出了一种工业互联网环境下基于多级跨链协同的制造过程调度方法。首先，建立了零件采购、运输、分装和总装四个关键制造阶段的数学模型；优化模型的目标是最小化完工时间和总成本，反映所有阶段的时间和成本效率。然后，设计了一种改进的多目标灰狼优化器（IMOGWO）来解决MPMLCC调度问题。该算法结合了基于对立的学习（OBL）和多邻域局部搜索策略，平衡了全局探索和局部开发。以小卫星Oresat0和Oresat1B为例，验证了该方法的有效性。实验结果表明，与其他多目标优化算法相比，该方法显著提高了解的质量和稳定性。此外，调度结果验证了制造过程信息集成和跨层次、跨链协同优化的有效性。

{"title":"Manufacturing process scheduling method based on multi-level and cross-chain collaboration under industrial internet environment","authors":"Wenjun Xu , Jinshan Zhong , Jiayi Liu , Shuang Zheng , Xianglong Zou , Feng Liu","doi":"10.1016/j.jii.2025.100972","DOIUrl":"10.1016/j.jii.2025.100972","url":null,"abstract":"<div><div>Under the industrial internet environment, achieving effective manufacturing process scheduling requires collaboration across the workshop level, production line level, industrial chain, and value chain. This collaboration enables the integration of manufacturing process information, aligning scheduling more closely with practical operations. However, the existing scheduling approaches mainly focus on a single level or a single chain, lacking the ability to address multi-level and cross-chain collaborative optimization. To overcome this limitation, this paper proposes a scheduling method for manufacturing process based on multi-level and cross-chain collaboration (MPMLCC) under the industrial internet environment. Firstly, the mathematical model is established to represent the four key stages of the manufacturing process: parts procurement, transportation, sub-assembly, and final assembly. The optimization model aims to minimize both the makespan and the total cost, reflecting time and cost efficiency across all stages. Then, an improved multi-objective grey wolf optimizer (IMOGWO) is designed to solve the MPMLCC scheduling problem. The algorithm integrates the opposition-based learning (OBL), the multi-neighborhood local search strategy to balance global exploration and local exploitation. Case studies based on the small satellites Oresat0 and Oresat1B are conducted to verify the effectiveness of the proposed method. Experimental results demonstrate that the proposed approach significantly improves solution quality and stability compared to the other multi-objective optimization algorithms. Furthermore, the scheduling outcomes confirm the effectiveness of manufacturing process information integration and collaborative optimization across multiple levels and chains.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"48 ","pages":"Article 100972"},"PeriodicalIF":10.4,"publicationDate":"2025-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145315172","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}

引用次数: 0

Cross-domain zero-shot fault diagnosis method for high-voltage circuit breakers driven by multidomain spatial projection and dual embedded structure 基于多域空间投影和双嵌入结构驱动的高压断路器跨域零弹故障诊断方法

IF 10.4 1区计算机科学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Journal of Industrial Information Integration

Pub Date : 2025-10-11 DOI: 10.1016/j.jii.2025.100976

Yuxiang Liao , Qiuyu Yang , Jiangjun Ruan , Jingyi Xie , Xue Xue , Yuyi Lin

High-voltage circuit breakers (HVCBs) present challenges in cross-domain fault diagnosis under zero-shot scenarios due to their complex mechanisms, diverse failure modes, and scarce fault samples. To address this problem, this paper proposes a cross-domain zero-shot diagnosis method for HVCBs driven by multidomain spatial projection (MSP) and dual embedded structure (DES), named MSP-DES. The proposed method effectively identifies unseen fault categories using only existing fault data and auxiliary knowledge. First, the MSP strategy extracts optimal features from projection subspaces, which are class-specific spaces derived from distinct fault categories. It incorporates a pseudo-labeling mechanism (an unsupervised learning approach) to mine both intra-class and inter-class information within the target domain. Second, fine-grained fault semantic descriptions are constructed based on HVCB fault signal characteristics and mechanical structural variations. Third, the DES establishes bidirectional mappings between fault semantics and features in high-dimensional embedding space. Finally, a loss function balancing intra-class compactness and inter-class separation optimizes the DES. The experimental results demonstrate that MSP-DES achieves both single- and cross-domain fault diagnosis using only historical training data, outperforming suboptimal models with a 10.53% accuracy improvement.

高压断路器由于其机理复杂、故障模式多样、故障样本稀缺等特点，给零射场景下的跨域故障诊断带来了挑战。针对这一问题，本文提出了一种基于多域空间投影（MSP）和双嵌入结构（DES）驱动的hvcb跨域零弹诊断方法，命名为MSP-DES。该方法仅利用现有故障数据和辅助知识就能有效识别未见过的故障类别。首先，MSP策略从投影子空间中提取最优特征，投影子空间是由不同的故障类别派生的类特定空间。它结合了伪标记机制（一种无监督学习方法）来挖掘目标域内的类内和类间信息。其次，基于高压断路器故障信号特征和机械结构变化，构建细粒度故障语义描述；第三，在高维嵌入空间中建立故障语义与特征之间的双向映射。实验结果表明，MSP-DES仅使用历史训练数据即可实现单域和跨域故障诊断，准确率比次优模型提高了10.53%。

{"title":"Cross-domain zero-shot fault diagnosis method for high-voltage circuit breakers driven by multidomain spatial projection and dual embedded structure","authors":"Yuxiang Liao , Qiuyu Yang , Jiangjun Ruan , Jingyi Xie , Xue Xue , Yuyi Lin","doi":"10.1016/j.jii.2025.100976","DOIUrl":"10.1016/j.jii.2025.100976","url":null,"abstract":"<div><div>High-voltage circuit breakers (HVCBs) present challenges in cross-domain fault diagnosis under zero-shot scenarios due to their complex mechanisms, diverse failure modes, and scarce fault samples. To address this problem, this paper proposes a cross-domain zero-shot diagnosis method for HVCBs driven by multidomain spatial projection (MSP) and dual embedded structure (DES), named MSP-DES. The proposed method effectively identifies unseen fault categories using only existing fault data and auxiliary knowledge. First, the MSP strategy extracts optimal features from projection subspaces, which are class-specific spaces derived from distinct fault categories. It incorporates a pseudo-labeling mechanism (an unsupervised learning approach) to mine both intra-class and inter-class information within the target domain. Second, fine-grained fault semantic descriptions are constructed based on HVCB fault signal characteristics and mechanical structural variations. Third, the DES establishes bidirectional mappings between fault semantics and features in high-dimensional embedding space. Finally, a loss function balancing intra-class compactness and inter-class separation optimizes the DES. The experimental results demonstrate that MSP-DES achieves both single- and cross-domain fault diagnosis using only historical training data, outperforming suboptimal models with a 10.53% accuracy improvement.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"48 ","pages":"Article 100976"},"PeriodicalIF":10.4,"publicationDate":"2025-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145315171","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}

引用次数: 0

Towards human digital twin: Reviewing human modelling and simulation 迈向数字孪生：回顾人体建模与仿真

IF 10.4 1区计算机科学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Journal of Industrial Information Integration

Pub Date : 2025-10-11 DOI: 10.1016/j.jii.2025.100975

Enshen Zhu, Sheng Yang

The human digital twin (HDT) is a detailed and personalized digital representation of an individual, encompassing the physical, cognitive, psychological, and social characteristics. HDT, an extension of the traditional digital twin concept from the industrial engineering sector, finds applications in diverse human-centric sectors such as smart manufacturing, medical healthcare, personal fitness, and autonomous driving. Although human modelling and simulation (HMS) are essential for advancing HDT technology, existing literature reviews primarily emphasize general aspects, including the definition, hierarchical frameworks, and various applications of HDT, rather than providing a thorough overview of HMS methods and tools. To fill the gap, this review work is specifically focused on the HMS aspect in HDT, discussing the evolution of digital human simulation, HDT information models, HDT metamodels, and related tools and software. This study also provides a checklist on building the HDT metamodel from the collected human data.

人类数字孪生（HDT）是一种详细的、个性化的个人数字表示，包括身体、认知、心理和社会特征。HDT是工业工程领域传统数字孪生概念的延伸，在智能制造、医疗保健、个人健身和自动驾驶等以人为中心的各种领域都有应用。尽管人类建模和仿真（HMS）对于推进HDT技术至关重要，但现有的文献综述主要强调一般方面，包括HDT的定义、层次框架和各种应用，而不是提供HMS方法和工具的全面概述。为了填补这一空白，本综述工作特别关注HDT中的HMS方面，讨论数字人体模拟、HDT信息模型、HDT元模型以及相关工具和软件的发展。本研究还提供了从收集的人类数据构建HDT元模型的清单。

引用次数: 0

Dynamic product risk management in product lifecycle management of medical products 医疗产品生命周期管理中的动态产品风险管理

IF 10.4 1区计算机科学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Journal of Industrial Information Integration

Pub Date : 2025-10-11 DOI: 10.1016/j.jii.2025.100977

Roberto Antonio Riascos Castaneda , Egon Ostrosi , Josip Stjepandic

Medical device manufacturers must be able to manage risks at several stages of the product development process and throughout the overall lifecycle. Through the implementation of PLM in healthcare, medical device manufacturers can efficiently oversee the complete lifecycle of their medical products. However, traditional PLM approaches do not adequately address integration with risk management. This paper presents a new framework that integrates dynamic risk management within Product Lifecycle Management (PLM) systems specifically for medical devices. This framework proposes a model for continuous risk identification and assessment, considering it as time-dependent. The time-dependent overall risk is defined in relation to time-dependent internal risk and time-dependent external risk. A modular product architecture integrating risk management is also proposed. Considering real-time risk assessment, modular product design allows for the design of medical devices that integrate risk assessment and risk management into the design process. The multi-layered approach enables the assessment of risks related to elementary functions, product functions, individual components, modules, and the entire medical device in real-time throughout the design and development process. A data model for product lifecycle management-based risk management and its implementation in PLM systems allows for a structured approach to handling safety-critical functions and aligning with regulatory requirements effectively. Our findings demonstrate that by embedding real-time risk identification, modular risk assessment, and overall risk tracking into Product Lifecycle Management (PLM) systems, manufacturers of medical devices can significantly improve safety, compliance, and decision-making. The integration of risk management with configuration management in PLM ensures traceability from design to final product, encouraging better collaboration and knowledge sharing across stakeholders.

医疗设备制造商必须能够在产品开发过程的几个阶段和整个生命周期中管理风险。通过在医疗保健领域实施PLM，医疗设备制造商可以有效地监督其医疗产品的整个生命周期。然而，传统的PLM方法不能充分解决与风险管理的集成问题。本文提出了一个新的框架，将动态风险管理集成到产品生命周期管理（PLM）系统中，专门用于医疗设备。该框架提出了一个持续的风险识别和评估模型，考虑到它是时间依赖的。时变总体风险是根据时变内部风险和时变外部风险来定义的。提出了一种集成风险管理的模块化产品体系结构。考虑到实时风险评估，模块化产品设计允许将风险评估和风险管理集成到设计过程中的医疗设备设计。多层方法能够在整个设计和开发过程中实时评估与基本功能、产品功能、单个组件、模块和整个医疗设备相关的风险。基于产品生命周期管理的风险管理数据模型及其在PLM系统中的实现，允许采用结构化方法来处理安全关键功能，并有效地与法规要求保持一致。我们的研究结果表明，通过在产品生命周期管理（PLM）系统中嵌入实时风险识别、模块化风险评估和整体风险跟踪，医疗器械制造商可以显著提高安全性、合规性和决策能力。PLM中的风险管理与配置管理的集成确保了从设计到最终产品的可追溯性，鼓励了利益相关者之间更好的协作和知识共享。

{"title":"Dynamic product risk management in product lifecycle management of medical products","authors":"Roberto Antonio Riascos Castaneda , Egon Ostrosi , Josip Stjepandic","doi":"10.1016/j.jii.2025.100977","DOIUrl":"10.1016/j.jii.2025.100977","url":null,"abstract":"<div><div>Medical device manufacturers must be able to manage risks at several stages of the product development process and throughout the overall lifecycle. Through the implementation of PLM in healthcare, medical device manufacturers can efficiently oversee the complete lifecycle of their medical products. However, traditional PLM approaches do not adequately address integration with risk management. This paper presents a new framework that integrates dynamic risk management within Product Lifecycle Management (PLM) systems specifically for medical devices. This framework proposes a model for continuous risk identification and assessment, considering it as time-dependent. The time-dependent overall risk is defined in relation to time-dependent internal risk and time-dependent external risk. A modular product architecture integrating risk management is also proposed. Considering real-time risk assessment, modular product design allows for the design of medical devices that integrate risk assessment and risk management into the design process. The multi-layered approach enables the assessment of risks related to elementary functions, product functions, individual components, modules, and the entire medical device in real-time throughout the design and development process. A data model for product lifecycle management-based risk management and its implementation in PLM systems allows for a structured approach to handling safety-critical functions and aligning with regulatory requirements effectively. Our findings demonstrate that by embedding real-time risk identification, modular risk assessment, and overall risk tracking into Product Lifecycle Management (PLM) systems, manufacturers of medical devices can significantly improve safety, compliance, and decision-making. The integration of risk management with configuration management in PLM ensures traceability from design to final product, encouraging better collaboration and knowledge sharing across stakeholders.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"48 ","pages":"Article 100977"},"PeriodicalIF":10.4,"publicationDate":"2025-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145362794","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}

引用次数: 0

Effectiveness of debris flow mitigation measures through T-spherical fuzzy Soft Dombi aggregation operators with EDAS-based multi-criteria decision making in mountainous regions 基于edas多准则决策的t球模糊软Dombi聚合算子对山区泥石流减灾措施的有效性研究

IF 10.4 1区计算机科学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Journal of Industrial Information Integration

Pub Date : 2025-10-10 DOI: 10.1016/j.jii.2025.100968

Himanshu Dhumras , Manish Kumar , Rakesh Kumar Bajaj

Debris flows are a significant hazard to human life, infrastructure, and the environment, particularly in mountainous regions where steep terrain and extreme weather intensify their impact. Mitigating these events requires robust decision-making frameworks that can effectively process uncertainty and complex data. This study introduces the score and accuracy functions for T-spherical fuzzy Soft numbers (T-SFSNs) and develops advanced Dombi aggregation operators (including weighted, ordered weighted, hybrid, and geometric forms) along with essential operational laws and properties. To enhance decision-making flexibility and incorporate parameterized uncertainty, the traditional Evaluation Based on Distance from Average Solution (EDAS) method has been systematically refined using the proposed score/accuracy functions and aggregation techniques. The modified EDAS framework expands the decision space, allowing for a more effective evaluation of mitigation measures under uncertain conditions. Additionally, a detailed case study on debris flow mitigation in mountainous regions is presented, demonstrating the effectiveness of the proposed methodology in selecting optimal mitigation strategies. To validate its feasibility, reliability, and superiority, a comparative analysis is conducted against existing multi-criteria decision-making (MCDM) approaches, highlighting the advantages of the enhanced method in handling complex decision scenarios. The results underscore the robustness and adaptability of the proposed framework in mitigating debris flow hazards.

泥石流是对人类生命、基础设施和环境的重大危害，特别是在陡峭地形和极端天气加剧其影响的山区。减轻这些事件需要强大的决策框架，能够有效地处理不确定性和复杂的数据。本文介绍了t球模糊软数（T-SFSNs）的得分和精度函数，并开发了先进的Dombi聚合算子（包括加权、有序加权、混合和几何形式）以及基本的运算规律和性质。为了提高决策的灵活性和纳入参数化的不确定性，本文利用提出的分数/精度函数和聚合技术对传统的基于平均解距离的评价方法进行了系统的改进。修改后的EDAS框架扩大了决策空间，允许在不确定条件下更有效地评估缓解措施。此外，还介绍了山区泥石流缓解的详细案例研究，证明了所提出的方法在选择最佳缓解战略方面的有效性。为了验证该方法的可行性、可靠性和优越性，与现有的多准则决策方法（MCDM）进行了对比分析，突出了该方法在处理复杂决策场景方面的优势。结果表明，所提出的框架在缓解泥石流灾害方面具有鲁棒性和适应性。

{"title":"Effectiveness of debris flow mitigation measures through T-spherical fuzzy Soft Dombi aggregation operators with EDAS-based multi-criteria decision making in mountainous regions","authors":"Himanshu Dhumras , Manish Kumar , Rakesh Kumar Bajaj","doi":"10.1016/j.jii.2025.100968","DOIUrl":"10.1016/j.jii.2025.100968","url":null,"abstract":"<div><div>Debris flows are a significant hazard to human life, infrastructure, and the environment, particularly in mountainous regions where steep terrain and extreme weather intensify their impact. Mitigating these events requires robust decision-making frameworks that can effectively process uncertainty and complex data. This study introduces the score and accuracy functions for T-spherical fuzzy Soft numbers (T-SFSNs) and develops advanced Dombi aggregation operators (including weighted, ordered weighted, hybrid, and geometric forms) along with essential operational laws and properties. To enhance decision-making flexibility and incorporate parameterized uncertainty, the traditional Evaluation Based on Distance from Average Solution (EDAS) method has been systematically refined using the proposed score/accuracy functions and aggregation techniques. The modified EDAS framework expands the decision space, allowing for a more effective evaluation of mitigation measures under uncertain conditions. Additionally, a detailed case study on debris flow mitigation in mountainous regions is presented, demonstrating the effectiveness of the proposed methodology in selecting optimal mitigation strategies. To validate its feasibility, reliability, and superiority, a comparative analysis is conducted against existing multi-criteria decision-making (MCDM) approaches, highlighting the advantages of the enhanced method in handling complex decision scenarios. The results underscore the robustness and adaptability of the proposed framework in mitigating debris flow hazards.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"48 ","pages":"Article 100968"},"PeriodicalIF":10.4,"publicationDate":"2025-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145315173","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}

引用次数: 0

Information integration-based factor object approach for object classification judgment in the system fault evolution process 基于信息集成的因素对象方法在系统故障演化过程中进行对象分类判断

IF 10.4 1区计算机科学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Journal of Industrial Information Integration

Pub Date : 2025-09-30 DOI: 10.1016/j.jii.2025.100967

Shasha Li , Tiejun Cui

Industrial system fault information is a fusion of fault-related data, where objects represent core fault events and factors quantify their dynamic states. Factor variations directly reflect object characteristics, driving the System Fault Evolution Process (SFEP)—a complex progression of system functionality from normal operation to failure, shaped by temporal changes in object states and factor values. To assess how factors influence object classification during SFEP, this paper proposes the Object Classification Judgment Method Integration-Based Factor-Object (OCJM-IFO), a novel approach rooted in the Neighborhood Preserving Embedding (NPE) algorithm. OCJM-IFO addresses critical limitations of existing methods: it handles sparse data, avoids the curse of dimensionality, and reduces reliance on prior rules by dynamically fusing weights from labelled (intra-class) and unlabelled (inter-class) data via an optimal weight ratio coefficient. This fusion enables comprehensive evaluation of factor impacts. Experiments on electrical systems and MOSFET faults (each involving 6 factors and 100 objects) validate the method: it identifies sets of favorable, uncertain, and unfavorable factors, with results aligning closely with physical fault characteristics. The algorithm requires a data structure composed of time-series objects, supporting real-time dataset updates. Thus, it is particularly well-suited for intelligent real-time monitoring systems in industrial environments, offering universal applicability and easy data accessibility. The construction process of the OCJM-IFO dataset is presented. This study strengthens fault information integration in industrial systems, providing a robust tool for fault diagnosis and preventive maintenance, with proven engineering applicability in enhancing system reliability.

工业系统故障信息是故障相关数据的融合，其中对象代表核心故障事件，因子量化其动态状态。因素变化直接反映对象特征，驱动系统故障演化过程（SFEP）——系统功能从正常运行到故障的复杂过程，由对象状态和因素值的时间变化形成。为了评估SFEP过程中各种因素对目标分类的影响，本文提出了基于邻域保持嵌入（NPE）算法的基于因子-目标集成的目标分类判断方法（OCJM-IFO）。OCJM-IFO解决了现有方法的关键限制：它处理稀疏数据，避免了维度的诅咒，并通过最优权重比系数动态融合标记（类内）和未标记（类间）数据的权重，减少了对先前规则的依赖。这种融合使因子影响的综合评价成为可能。电气系统和MOSFET故障（每个故障涉及6个因素和100个对象）的实验验证了该方法：它识别出有利、不确定和不利因素的集合，结果与物理故障特征密切一致。该算法需要一个由时间序列对象组成的数据结构，支持数据集的实时更新。因此，它特别适合工业环境中的智能实时监控系统，具有普遍适用性和易于访问的数据。介绍了OCJM-IFO数据集的构建过程。本研究加强了工业系统的故障信息集成，为故障诊断和预防性维护提供了一个强大的工具，在提高系统可靠性方面具有工程适用性。

{"title":"Information integration-based factor object approach for object classification judgment in the system fault evolution process","authors":"Shasha Li , Tiejun Cui","doi":"10.1016/j.jii.2025.100967","DOIUrl":"10.1016/j.jii.2025.100967","url":null,"abstract":"<div><div>Industrial system fault information is a fusion of fault-related data, where objects represent core fault events and factors quantify their dynamic states. Factor variations directly reflect object characteristics, driving the System Fault Evolution Process (SFEP)—a complex progression of system functionality from normal operation to failure, shaped by temporal changes in object states and factor values. To assess how factors influence object classification during SFEP, this paper proposes the Object Classification Judgment Method Integration-Based Factor-Object (OCJM-IFO), a novel approach rooted in the Neighborhood Preserving Embedding (NPE) algorithm. OCJM-IFO addresses critical limitations of existing methods: it handles sparse data, avoids the curse of dimensionality, and reduces reliance on prior rules by dynamically fusing weights from labelled (intra-class) and unlabelled (inter-class) data via an optimal weight ratio coefficient. This fusion enables comprehensive evaluation of factor impacts. Experiments on electrical systems and MOSFET faults (each involving 6 factors and 100 objects) validate the method: it identifies sets of favorable, uncertain, and unfavorable factors, with results aligning closely with physical fault characteristics. The algorithm requires a data structure composed of time-series objects, supporting real-time dataset updates. Thus, it is particularly well-suited for intelligent real-time monitoring systems in industrial environments, offering universal applicability and easy data accessibility. The construction process of the OCJM-IFO dataset is presented. This study strengthens fault information integration in industrial systems, providing a robust tool for fault diagnosis and preventive maintenance, with proven engineering applicability in enhancing system reliability.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"48 ","pages":"Article 100967"},"PeriodicalIF":10.4,"publicationDate":"2025-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145324751","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}

引用次数: 0