Journal of Industrial Information Integration最新文献_第2页

Multi-source domain adaptation via evidence-based target pseudo-labels for human–computer collaboration fault diagnosis 基于循证目标伪标签的多源领域自适应人机协同故障诊断

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

Journal of Industrial Information Integration

Pub Date : 2026-01-29 DOI: 10.1016/j.jii.2026.101077

Jilun Tian , Hao Luo , Pengfei Yan , Xinyu Qiao , Shimeng Wu , Jiusi Zhang

Existing data-driven fault diagnosis methods imply the decision-making automatically, but lack adaptation and trustworthiness for varying working conditions. Unsupervised domain adaptation (UDA) relies on the cross-domain distribution disparity to achieve high-performance diagnostics. However, it struggles in complex multi-domain and diverse-source scenarios, which currently lack in-depth analysis. The proposed approach implements a novel multi-source domain adversarial network (MSDA) architecture via evidence-based target pseudo-label learning (ETPL) with dynamic multi-loss weightings. Specifically, MSDA constrains the disparity of diverse source–target pairs to obtain generalized domain-invariant features via an adversarial mechanism, and ETPL performs target pseudo-label learning while applying Dempster–Shafer (DS) evidence theory to assign sample-wise weights through MSDA and an unsupervised algorithm. Meanwhile, this study provides a theoretical analysis including a detailed generalization error bound for multi-source scenarios and target pseudo-labels, illustrating its dependence on distribution discrepancy and pseudo-label quality metrics. Human–computer collaboration approach is adopted to strengthen both advantages from human and machines by sample-wise analysis. Sufficient experimental results on two real-world case studies validate the effectiveness, successfully accomplishing complex cross-domain fault diagnosis and illustrating its potential applications in industrial settings.

现有的数据驱动故障诊断方法意味着自动决策，但缺乏对不同工况的适应性和可靠性。无监督域自适应（UDA）依赖于跨域分布差异来实现高性能诊断。然而，它在复杂的多领域、多源场景中存在困难，目前缺乏深入的分析。该方法通过动态多损失加权的基于证据的目标伪标签学习（ETPL）实现了一种新的多源域对抗网络（MSDA）架构。具体而言，MSDA通过对抗机制约束不同源-目标对的差异以获得广义域不变特征，ETPL在进行目标伪标签学习的同时，通过MSDA和无监督算法应用Dempster-Shafer （DS）证据理论分配样本权值。同时，本文对多源场景和目标伪标签的泛化误差界进行了理论分析，说明了其对分布差异和伪标签质量指标的依赖关系。采用人机协作的方法，通过样本分析强化人与机器的优势。两个实际案例的充分实验结果验证了该方法的有效性，成功地完成了复杂的跨域故障诊断，并说明了其在工业环境中的潜在应用。

{"title":"Multi-source domain adaptation via evidence-based target pseudo-labels for human–computer collaboration fault diagnosis","authors":"Jilun Tian , Hao Luo , Pengfei Yan , Xinyu Qiao , Shimeng Wu , Jiusi Zhang","doi":"10.1016/j.jii.2026.101077","DOIUrl":"10.1016/j.jii.2026.101077","url":null,"abstract":"<div><div>Existing data-driven fault diagnosis methods imply the decision-making automatically, but lack adaptation and trustworthiness for varying working conditions. Unsupervised domain adaptation (UDA) relies on the cross-domain distribution disparity to achieve high-performance diagnostics. However, it struggles in complex multi-domain and diverse-source scenarios, which currently lack in-depth analysis. The proposed approach implements a novel multi-source domain adversarial network (MSDA) architecture via evidence-based target pseudo-label learning (ETPL) with dynamic multi-loss weightings. Specifically, MSDA constrains the disparity of diverse source–target pairs to obtain generalized domain-invariant features via an adversarial mechanism, and ETPL performs target pseudo-label learning while applying Dempster–Shafer (DS) evidence theory to assign sample-wise weights through MSDA and an unsupervised algorithm. Meanwhile, this study provides a theoretical analysis including a detailed generalization error bound for multi-source scenarios and target pseudo-labels, illustrating its dependence on distribution discrepancy and pseudo-label quality metrics. Human–computer collaboration approach is adopted to strengthen both advantages from human and machines by sample-wise analysis. Sufficient experimental results on two real-world case studies validate the effectiveness, successfully accomplishing complex cross-domain fault diagnosis and illustrating its potential applications in industrial settings.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"50 ","pages":"Article 101077"},"PeriodicalIF":10.4,"publicationDate":"2026-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146071634","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

Deep acoustic–visual fusion for robust material recognition in intelligent robotic perception 基于深度声视融合的智能机器人感知材料鲁棒识别

IF 15.7 1区计算机科学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Journal of Industrial Information Integration

Pub Date : 2026-01-28 DOI: 10.1016/j.jii.2026.101074

Bo Zhu, Tao Geng, Jia Zhang, Jianlei Cui, Boxin Ren

引用次数: 0

GreenEdge AI: Sustainable federated learning for smart city air quality prediction GreenEdge AI：智能城市空气质量预测的可持续联合学习

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

Journal of Industrial Information Integration

Pub Date : 2026-01-27 DOI: 10.1016/j.jii.2026.101081

Sweta Dey , Rishi Raina , Sudeepta Mishra , Abhinandan S. Prasad , Ramesh Dharavath

Rapid urbanization and industrial growth have intensified air pollution in metropolitan regions, making accurate and energy-efficient Air Quality Index (AQI) prediction critical for sustainable smart city management. Existing centralized and conventional federated learning approaches suffer from high communication overhead, excessive energy consumption, and privacy risks, limiting their applicability in distributed urban sensing environments. This paper proposes GreenEdge AI, a green federated learning framework integrating a green-aware custom LSTM (GA-CLSTM) model with energy-aware training, adaptive aggregation, and a hybrid loss function for decentralized AQI forecasting. The framework enables edge-level learning across heterogeneous IoT-based air quality and meteorological sensors while preserving data privacy and minimizing cloud dependency. Sustainability is explicitly incorporated through green metrics, including energy consumption, Energy–Delay Product (EDP), Energy Efficiency Ratio (EER), and Power-to-Performance Ratio (PPR), which guide both model optimization and federated aggregation. Experimental results on real-world hourly AQI data from five major metropolitan cities demonstrate that GreenEdge AI achieves up to 60% improvement in prediction accuracy and approximately 37% reduction in energy consumption compared to conventional baseline models, while significantly reducing peak power usage and communication overhead compared to centralized and conventional federated baselines. These findings underscore the practical value of GreenEdge AI for municipalities and environmental agencies, motivating future research on scalable, energy-aware federated intelligence for smart city applications.

快速的城市化和工业增长加剧了大都市地区的空气污染，使得准确和节能的空气质量指数（AQI）预测对可持续的智慧城市管理至关重要。现有的集中式和传统的联邦学习方法存在通信开销大、能耗大、隐私风险大等问题，限制了它们在分布式城市传感环境中的适用性。本文提出了GreenEdge AI，这是一个绿色联邦学习框架，将绿色感知自定义LSTM （GA-CLSTM）模型与能量感知训练、自适应聚合和用于分散AQI预测的混合损失函数集成在一起。该框架支持跨异构物联网空气质量和气象传感器的边缘级学习，同时保护数据隐私并最大限度地减少对云的依赖。可持续性通过绿色指标明确地纳入，包括能源消耗、能源延迟产品（EDP）、能源效率比（EER）和功率性能比（PPR），这些指标指导模型优化和联合聚合。来自五个主要城市的真实小时AQI数据的实验结果表明，与传统基线模型相比，GreenEdge AI的预测精度提高了60%，能耗降低了约37%，同时与集中式和传统联邦基线相比，显著降低了峰值功耗和通信开销。这些发现强调了GreenEdge人工智能对市政当局和环境机构的实用价值，推动了未来针对智慧城市应用的可扩展、能源感知的联合智能的研究。

{"title":"GreenEdge AI: Sustainable federated learning for smart city air quality prediction","authors":"Sweta Dey , Rishi Raina , Sudeepta Mishra , Abhinandan S. Prasad , Ramesh Dharavath","doi":"10.1016/j.jii.2026.101081","DOIUrl":"10.1016/j.jii.2026.101081","url":null,"abstract":"<div><div>Rapid urbanization and industrial growth have intensified air pollution in metropolitan regions, making accurate and energy-efficient Air Quality Index (AQI) prediction critical for sustainable smart city management. Existing centralized and conventional federated learning approaches suffer from high communication overhead, excessive energy consumption, and privacy risks, limiting their applicability in distributed urban sensing environments. This paper proposes <em>GreenEdge AI</em>, a green federated learning framework integrating a green-aware custom LSTM (GA-CLSTM) model with energy-aware training, adaptive aggregation, and a hybrid loss function for decentralized AQI forecasting. The framework enables edge-level learning across heterogeneous IoT-based air quality and meteorological sensors while preserving data privacy and minimizing cloud dependency. Sustainability is explicitly incorporated through green metrics, including energy consumption, Energy–Delay Product (EDP), Energy Efficiency Ratio (EER), and Power-to-Performance Ratio (PPR), which guide both model optimization and federated aggregation. Experimental results on real-world hourly AQI data from five major metropolitan cities demonstrate that <em>GreenEdge AI</em> achieves up to 60% improvement in prediction accuracy and approximately 37% reduction in energy consumption compared to conventional baseline models, while significantly reducing peak power usage and communication overhead compared to centralized and conventional federated baselines. These findings underscore the practical value of <em>GreenEdge AI</em> for municipalities and environmental agencies, motivating future research on scalable, energy-aware federated intelligence for smart city applications.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"50 ","pages":"Article 101081"},"PeriodicalIF":10.4,"publicationDate":"2026-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146072129","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

A nested goal programming model integrated with an improved genetic bee colony algorithm supported by machine learning methods 基于机器学习的改进遗传蜂群算法的嵌套目标规划模型

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

Journal of Industrial Information Integration

Pub Date : 2026-01-26 DOI: 10.1016/j.jii.2026.101082

N. Gosheh Dezfouli, Behnam Vahdani, E. Mehdizadeh, H.R. Gholami

Formulating engine oil additives is challenging because it requires simultaneously optimizing production efficiency, cost, and compliance with strict quality standards. This study presents an advanced optimization framework for 10W-40 API SL engine oil that combines a nested goal programming model with machine learning (ML) techniques to predict production rates and quality metrics that cannot be expressed in closed-form equations. To address the inability of conventional ML approaches to generate novel additive combinations, we propose an enhanced genetic bee colony algorithm incorporating arithmetic crossover, Makinen–Periaux–Toivanen mutation operators, and a Cauchy distribution-based local search. These modifications significantly improve the algorithm’s ability to explore and evaluate new formulations. The resulting framework achieves 98.76% of nominal production capacity—very close to the theoretical optimum—while reducing quality-related costs by an average of 20.44%. These results represent substantial improvements in production efficiency, cost savings, and overall formulation quality, providing a powerful and practical tool for the engine oil industry.

配制机油添加剂是一项具有挑战性的工作，因为它需要同时优化生产效率、成本，并符合严格的质量标准。本研究提出了一种先进的10W-40 API SL机油优化框架，该框架将嵌套目标规划模型与机器学习（ML）技术相结合，可以预测无法用封闭形式方程表示的生产率和质量指标。为了解决传统机器学习方法无法生成新的加性组合的问题，我们提出了一种增强的遗传蜂群算法，该算法结合了算术交叉、Makinen-Periaux-Toivanen突变算子和基于Cauchy分布的局部搜索。这些修改显著提高了算法探索和评估新公式的能力。最终的框架实现了98.76%的名义产能——非常接近理论最优——同时平均降低了20.44%的质量相关成本。这些结果代表了生产效率、成本节约和整体配方质量的大幅提高，为发动机润滑油行业提供了一个强大而实用的工具。

{"title":"A nested goal programming model integrated with an improved genetic bee colony algorithm supported by machine learning methods","authors":"N. Gosheh Dezfouli, Behnam Vahdani, E. Mehdizadeh, H.R. Gholami","doi":"10.1016/j.jii.2026.101082","DOIUrl":"10.1016/j.jii.2026.101082","url":null,"abstract":"<div><div>Formulating engine oil additives is challenging because it requires simultaneously optimizing production efficiency, cost, and compliance with strict quality standards. This study presents an advanced optimization framework for 10W-40 API SL engine oil that combines a nested goal programming model with machine learning (ML) techniques to predict production rates and quality metrics that cannot be expressed in closed-form equations. To address the inability of conventional ML approaches to generate novel additive combinations, we propose an enhanced genetic bee colony algorithm incorporating arithmetic crossover, Makinen–Periaux–Toivanen mutation operators, and a Cauchy distribution-based local search. These modifications significantly improve the algorithm’s ability to explore and evaluate new formulations. The resulting framework achieves 98.76% of nominal production capacity—very close to the theoretical optimum—while reducing quality-related costs by an average of 20.44%. These results represent substantial improvements in production efficiency, cost savings, and overall formulation quality, providing a powerful and practical tool for the engine oil industry.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"51 ","pages":"Article 101082"},"PeriodicalIF":10.4,"publicationDate":"2026-01-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146048129","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

A multi-level multi-source digital twin model for performance enhancement and optimization decision-making in precision milling machines 精密铣床性能提升与优化决策的多级多源数字孪生模型

IF 15.7 1区计算机科学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Journal of Industrial Information Integration

Pub Date : 2026-01-24 DOI: 10.1016/j.jii.2026.101080

Yang Xie, Shulong Mei, Fei Wang, Chaoyong Zhang

引用次数: 0

A review on machine learning and deep learning techniques for plant leaf disease detection and classification with IoT in agriculture industry 机器学习和深度学习技术在农业物联网植物叶片病害检测与分类中的应用综述

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

Journal of Industrial Information Integration

Pub Date : 2026-01-22 DOI: 10.1016/j.jii.2026.101078

Priyadharshini Arputharaj, Kalaivanan Karunanithy

Agriculture serves as a major source of food and plays a key function as the backbone of most countries’ economies. However, farmers are encountering many challenges in this sector, such as drought, flooding, diseases, nutrient deficiency, and so on. The technological advancements in the field of agriculture, also called smart agriculture, are necessary to address the requirements of the expanding population and manage the associated challenges. Among those, plant leaf diseases are the primary concern that severely impacts crop yield and economic stability. This technical review examines various Machine Learning (ML) and Deep Learning (DL) approaches used to identify and classify different plant leaf diseases. This review gives an overview of the current state-of-the-art ML, DL, and IoT-enabled disease prediction systems and their recent advances in developing an intelligent system in smart agriculture. It provides insights into the various technological developments and discusses the benefits and opportunities of AI-based models in plant disease management.

农业是粮食的主要来源，是大多数国家经济的支柱，发挥着关键作用。然而，农民在这一领域面临着许多挑战，如干旱、洪水、疾病、营养缺乏等。农业领域的技术进步，也被称为智能农业，是解决不断增长的人口需求和管理相关挑战所必需的。其中，植物叶片病害是严重影响作物产量和经济稳定的首要问题。本技术综述探讨了用于识别和分类不同植物叶片疾病的各种机器学习（ML）和深度学习（DL）方法。本文综述了当前最先进的机器学习、深度学习和物联网疾病预测系统，以及它们在智能农业中开发智能系统的最新进展。它提供了对各种技术发展的见解，并讨论了基于人工智能的模型在植物病害管理中的好处和机会。

{"title":"A review on machine learning and deep learning techniques for plant leaf disease detection and classification with IoT in agriculture industry","authors":"Priyadharshini Arputharaj, Kalaivanan Karunanithy","doi":"10.1016/j.jii.2026.101078","DOIUrl":"10.1016/j.jii.2026.101078","url":null,"abstract":"<div><div>Agriculture serves as a major source of food and plays a key function as the backbone of most countries’ economies. However, farmers are encountering many challenges in this sector, such as drought, flooding, diseases, nutrient deficiency, and so on. The technological advancements in the field of agriculture, also called smart agriculture, are necessary to address the requirements of the expanding population and manage the associated challenges. Among those, plant leaf diseases are the primary concern that severely impacts crop yield and economic stability. This technical review examines various Machine Learning (ML) and Deep Learning (DL) approaches used to identify and classify different plant leaf diseases. This review gives an overview of the current state-of-the-art ML, DL, and IoT-enabled disease prediction systems and their recent advances in developing an intelligent system in smart agriculture. It provides insights into the various technological developments and discusses the benefits and opportunities of AI-based models in plant disease management.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"50 ","pages":"Article 101078"},"PeriodicalIF":10.4,"publicationDate":"2026-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146033487","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

A survey of integrated multi-layer security for continuous-process industrial control systems: Insights from a steel manufacturing sector 连续过程工业控制系统的集成多层安全调查：来自钢铁制造部门的见解

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

Journal of Industrial Information Integration

Pub Date : 2026-01-22 DOI: 10.1016/j.jii.2026.101072

Fang Wang , Aiai Ren , Jun Cheng , Yijie Zheng , Xu Zhou , Li Qiao , Jun Yan , Fang Dong , Qian Zhao , Jun Shen

Continuous-process industries such as steel operate under tight safety and availability constraints while facing a rapidly expanding attack surface across device, network and behavioural layers. This survey consolidates evidence on legacy endpoints, protocol exposures, and process-level risks in steel manufacturing, and organises it in a structured, multi-layer taxonomy that clarifies how local faults can escalate to plant-wide disruption. Using a transparent literature search and screening protocol, the survey synthesises prior work on device hardening, network segmentation, and anomaly detection, and foregrounds what is distinctive about steel, including near-zero downtime operations and multi-vendor operational technology ecosystems. Building on this synthesis, the survey grounds actionable guidance in established industry standards by linking security controls to recognised programme requirements and mapping adversary techniques to an industrial control systems-focused attack framework, thereby providing plant-ready implementation cues. The survey also distils a phased integration workflow that locates analytics at the industrial edge and couples them with existing safety interlocks and operational change control. Case evidence from steel incidents is used to illustrate typical intrusion chains and to motivate layered mitigations. The review concludes by identifying priority research needs in data governance and benchmarking, as well as the edge-centric and safety-cased deployment of AI models, and supply-chain-aware machine learning operations. Taken together, these contributions provide a domain-grounded roadmap for strengthening resilience in steel-manufacturing industrial control systems while preserving operational continuity, and a transferable template for other continuous-process sectors.

钢铁等连续加工行业在严格的安全和可用性限制下运行，同时面临着跨设备、网络和行为层快速扩展的攻击面。该调查整合了钢铁制造中遗留端点、协议暴露和过程级风险的证据，并将其组织在结构化的多层分类法中，以澄清局部故障如何升级为整个工厂的中断。通过透明的文献检索和筛选协议，该调查综合了之前在设备硬化、网络分割和异常检测方面的工作，并展望了钢铁的独特之处，包括近零停机操作和多供应商操作技术生态系统。在此综合基础上，该调查通过将安全控制与公认的程序需求联系起来，并将对手技术映射到以工业控制系统为中心的攻击框架，从而为已建立的行业标准提供可操作的指导，从而提供工厂就绪的实施线索。该调查还提炼出了一个分阶段的集成工作流程，将分析定位于工业边缘，并将其与现有的安全联锁和操作变更控制相结合。来自钢铁事故的案例证据用于说明典型的入侵链，并激励分层缓解。最后，该审查确定了数据治理和基准测试方面的优先研究需求，以及人工智能模型的边缘中心和安全部署，以及供应链感知机器学习操作。综上所述，这些贡献为在保持业务连续性的同时加强钢铁制造业工业控制系统的弹性提供了一个基于领域的路线图，并为其他连续加工部门提供了一个可转让的模板。

{"title":"A survey of integrated multi-layer security for continuous-process industrial control systems: Insights from a steel manufacturing sector","authors":"Fang Wang , Aiai Ren , Jun Cheng , Yijie Zheng , Xu Zhou , Li Qiao , Jun Yan , Fang Dong , Qian Zhao , Jun Shen","doi":"10.1016/j.jii.2026.101072","DOIUrl":"10.1016/j.jii.2026.101072","url":null,"abstract":"<div><div>Continuous-process industries such as steel operate under tight safety and availability constraints while facing a rapidly expanding attack surface across device, network and behavioural layers. This survey consolidates evidence on legacy endpoints, protocol exposures, and process-level risks in steel manufacturing, and organises it in a structured, multi-layer taxonomy that clarifies how local faults can escalate to plant-wide disruption. Using a transparent literature search and screening protocol, the survey synthesises prior work on device hardening, network segmentation, and anomaly detection, and foregrounds what is distinctive about steel, including near-zero downtime operations and multi-vendor operational technology ecosystems. Building on this synthesis, the survey grounds actionable guidance in established industry standards by linking security controls to recognised programme requirements and mapping adversary techniques to an industrial control systems-focused attack framework, thereby providing plant-ready implementation cues. The survey also distils a phased integration workflow that locates analytics at the industrial edge and couples them with existing safety interlocks and operational change control. Case evidence from steel incidents is used to illustrate typical intrusion chains and to motivate layered mitigations. The review concludes by identifying priority research needs in data governance and benchmarking, as well as the edge-centric and safety-cased deployment of AI models, and supply-chain-aware machine learning operations. Taken together, these contributions provide a domain-grounded roadmap for strengthening resilience in steel-manufacturing industrial control systems while preserving operational continuity, and a transferable template for other continuous-process sectors.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"50 ","pages":"Article 101072"},"PeriodicalIF":10.4,"publicationDate":"2026-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146033486","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

Design software network: A collaborative EaaS business model for CNC manufacturers, customers, and designers 设计软件网络：面向CNC制造商、客户和设计师的协同EaaS商业模式

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

Journal of Industrial Information Integration

Pub Date : 2026-01-22 DOI: 10.1016/j.jii.2026.101079

İsmail Yoşumaz , Ali Gülbaşı , Safiye Süreyya Bengül

Purpose

Industry 5.0 accelerates the shift from asset ownership to benefit-based business models. This study develops a collaborative EaaS framework for the CNC sector that simultaneously monetizes the measurable benefit (active machining time or produced part volume) rather than the machine itself, and integrates 3D product designers as active, revenue-generating stakeholders in the value chain.

Design/methodology/approach

A qualitative research design combining document analysis and descriptive content analysis was employed. From 101 documents, 41 were selected through purposive sampling.

Findings

The proposed Design Software Network model establishes a triadic ecosystem connecting CNC manufacturers, customers, and designers. By leveraging existing digital twin and IoT infrastructures for real-time measurement of machining outputs, the Design Software Network model implements pay-per-use pricing for physical equipment while generating an entirely new revenue layer: automated, blockchain-enforced royalties paid to designers for every part produced using their licensed 3D models. This dual monetization mechanism, which combines benefit-based pricing of machine usage with recurring monetization of digital designs, addresses the current exclusion of designers from EaaS value capture and fosters collaborative innovation.

Originality

Pay-per-use models have begun to emerge in the CNC sector, remaining strictly limited to the manufacturer–customer dyad. The DSN’s originality lies in extending these established measurement systems to systematically include 3D product designers through scalable, usage-based royalty streams. This integration does not yet exist in the literature or industry implementations. The model thereby completes the transition to a genuinely human-centric, triadic Industry 5.0 ecosystem.

工业5.0加速了从资产所有权到基于利益的商业模式的转变。本研究为CNC行业开发了一个协作的EaaS框架，同时将可衡量的利益（主动加工时间或生产零件量）货币化，而不是机器本身，并将3D产品设计师集成为价值链中活跃的、产生收入的利益相关者。设计/方法/方法采用文献分析和描述性内容分析相结合的定性研究设计。从101篇文献中，通过有目的抽样抽取41篇。所提出的设计软件网络模型建立了一个连接CNC制造商、客户和设计师的三元生态系统。通过利用现有的数字孪生和物联网基础设施实时测量加工输出，设计软件网络模型实现了物理设备的按使用付费定价，同时产生了一个全新的收入层：为使用其许可的3D模型生产的每个部件向设计师支付自动化的、区块链强制的版税。这种双重货币化机制结合了基于收益的机器使用定价和数字设计的循环货币化，解决了目前设计师被排除在EaaS价值获取之外的问题，并促进了协作创新。在CNC领域，按次付费的模式已经开始出现，但仍然严格限于制造商-客户的模式。DSN的独创性在于通过可扩展的、基于使用的版税流，将这些已建立的测量系统扩展到系统地包括3D产品设计师。这种集成在文献或行业实现中还不存在。因此，该模型完成了向真正以人为中心的三元工业5.0生态系统的过渡。

{"title":"Design software network: A collaborative EaaS business model for CNC manufacturers, customers, and designers","authors":"İsmail Yoşumaz , Ali Gülbaşı , Safiye Süreyya Bengül","doi":"10.1016/j.jii.2026.101079","DOIUrl":"10.1016/j.jii.2026.101079","url":null,"abstract":"<div><h3>Purpose</h3><div>Industry 5.0 accelerates the shift from asset ownership to benefit-based business models. This study develops a collaborative EaaS framework for the CNC sector that simultaneously monetizes the measurable benefit (active machining time or produced part volume) rather than the machine itself, and integrates 3D product designers as active, revenue-generating stakeholders in the value chain.</div></div><div><h3>Design/methodology/approach</h3><div>A qualitative research design combining document analysis and descriptive content analysis was employed. From 101 documents, 41 were selected through purposive sampling.</div></div><div><h3>Findings</h3><div>The proposed Design Software Network model establishes a triadic ecosystem connecting CNC manufacturers, customers, and designers. By leveraging existing digital twin and IoT infrastructures for real-time measurement of machining outputs, the Design Software Network model implements pay-per-use pricing for physical equipment while generating an entirely new revenue layer: automated, blockchain-enforced royalties paid to designers for every part produced using their licensed 3D models. This dual monetization mechanism, which combines benefit-based pricing of machine usage with recurring monetization of digital designs, addresses the current exclusion of designers from EaaS value capture and fosters collaborative innovation.</div></div><div><h3>Originality</h3><div>Pay-per-use models have begun to emerge in the CNC sector, remaining strictly limited to the manufacturer–customer dyad. The DSN’s originality lies in extending these established measurement systems to systematically include 3D product designers through scalable, usage-based royalty streams. This integration does not yet exist in the literature or industry implementations. The model thereby completes the transition to a genuinely human-centric, triadic Industry 5.0 ecosystem.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"50 ","pages":"Article 101079"},"PeriodicalIF":10.4,"publicationDate":"2026-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146033485","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 collaboration: A design methodology for future-oriented intelligent industrial systems 认知协作：面向未来的智能工业系统的设计方法

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

Journal of Industrial Information Integration

Pub Date : 2026-01-20 DOI: 10.1016/j.jii.2026.101071

Hongwei Jiang , Jiapeng You , Zhiyang Chen , Xinguo Ming , Poly Z.H. Sun

Industrial systems are undergoing a paradigm shift from digitalization to intelligentization. However, current practices often suffer from systemic fragmentation and a lack of cognitive capability, creating a gap between high-level intelligence and physical execution. Existing research either focuses on specific algorithms or remains at the level of abstract concepts like cognitive digital twins, lacking a systematic design methodology to bridge this gap. To address this, this paper proposes cognitive collaboration, a novel design methodology guided by the dual-process theory of cognitive science. This paper redefines industrial systems as proactive partners possessing four synergistic capabilities: Intent Insight, Cognitive Evolution, Autonomous Planning, and Embodied Reconfiguration. Distinct from traditional approaches, a rigorous quantitative framework is introduced, including a dual-dimensional design space and a capability priority index (CPI) calibrated by expert-weighted analytic hierarchy process (AHP). Furthermore, to resolve the conflict between generative artificial intelligence (AI)’s creativity and industrial safety, a generator–verifier dual-system architecture is constructed to constrain stochastic outputs within verifiable safety envelopes. The methodology is systematically validated through the reconfiguration of a production line operations and maintenance (O&M) system and a comparative analysis of a complex ship design case. Preliminary quantitative results from a prototype experiment further confirm that the proposed framework effectively bridges the gap between generative flexibility and industrial reliability, offering a verifiable, operable pathway for building the next generation of intelligent industrial systems.

工业系统正经历着从数字化向智能化的范式转变。然而，目前的实践经常受到系统分裂和缺乏认知能力的影响，在高水平的智力和实际执行之间造成了差距。现有的研究要么侧重于具体的算法，要么停留在抽象概念的层面，如认知数字双胞胎，缺乏系统的设计方法来弥补这一差距。为了解决这一问题，本文提出了一种以认知科学的双过程理论为指导的新型设计方法——认知协作。本文将工业系统重新定义为具有四种协同能力的主动合作伙伴：意图洞察、认知进化、自主规划和具体化重构。与传统方法不同，引入了一个严格的定量框架，包括一个二维设计空间和一个由专家加权层次分析法（AHP）校准的能力优先指数（CPI）。此外，为了解决生成式人工智能（AI）的创造力与工业安全之间的冲突，构建了一个生成器-验证者双系统架构，将随机输出约束在可验证的安全信封内。通过生产线操作和维护（O&；M）系统的重新配置和复杂船舶设计案例的比较分析，系统地验证了该方法。原型实验的初步定量结果进一步证实，所提出的框架有效地弥合了生成灵活性和工业可靠性之间的差距，为构建下一代智能工业系统提供了可验证、可操作的途径。

{"title":"Cognitive collaboration: A design methodology for future-oriented intelligent industrial systems","authors":"Hongwei Jiang , Jiapeng You , Zhiyang Chen , Xinguo Ming , Poly Z.H. Sun","doi":"10.1016/j.jii.2026.101071","DOIUrl":"10.1016/j.jii.2026.101071","url":null,"abstract":"<div><div>Industrial systems are undergoing a paradigm shift from digitalization to intelligentization. However, current practices often suffer from systemic fragmentation and a lack of cognitive capability, creating a gap between high-level intelligence and physical execution. Existing research either focuses on specific algorithms or remains at the level of abstract concepts like cognitive digital twins, lacking a systematic design methodology to bridge this gap. To address this, this paper proposes cognitive collaboration, a novel design methodology guided by the dual-process theory of cognitive science. This paper redefines industrial systems as proactive partners possessing four synergistic capabilities: Intent Insight, Cognitive Evolution, Autonomous Planning, and Embodied Reconfiguration. Distinct from traditional approaches, a rigorous quantitative framework is introduced, including a dual-dimensional design space and a capability priority index (CPI) calibrated by expert-weighted analytic hierarchy process (AHP). Furthermore, to resolve the conflict between generative artificial intelligence (AI)’s creativity and industrial safety, a generator–verifier dual-system architecture is constructed to constrain stochastic outputs within verifiable safety envelopes. The methodology is systematically validated through the reconfiguration of a production line operations and maintenance (O&M) system and a comparative analysis of a complex ship design case. Preliminary quantitative results from a prototype experiment further confirm that the proposed framework effectively bridges the gap between generative flexibility and industrial reliability, offering a verifiable, operable pathway for building the next generation of intelligent industrial systems.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"50 ","pages":"Article 101071"},"PeriodicalIF":10.4,"publicationDate":"2026-01-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146014987","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

Semi-supervised cross-domain fault diagnosis via contrastive pre-training and annotation-efficient alignment strategy 基于对比预训练和高效标注对齐策略的半监督跨域故障诊断

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

Journal of Industrial Information Integration

Pub Date : 2026-01-20 DOI: 10.1016/j.jii.2026.101076

Lechang Yang , Xianghao Zhang , Feng Zhu , Zhe Wang , Xiaoge Zhang

Cross-domain fault diagnosis is a critical task in predictive maintenance for fleet management. However, existing transfer learning and distribution matching methods are often impractical in real-world scenarios, especially under few-shot conditions, where their diagnostic performance cannot be consistently guaranteed. To address this issue, this study proposes a novel semi-supervised framework for cross-domain fault diagnosis, based on the pre-training–fine-tuning paradigm. In our approach, self-supervised contrastive learning is employed for centralized multi-domain pre-training, followed by supervised fine-tuning and contrastive re-learning to achieve robust model alignment across different machines and operating conditions. To effectively capture temporal dependencies in structured sensor data and improve sample efficiency, we incorporate a time-series contrastive learning method, Time-Series Representation Learning via Temporal and Contextual Contrasting (TS-TCC), as the core component of the pre-training stage. Furthermore, we introduce a two-stage sample selection strategy that enables annotation-efficient model alignment. This design ensures consistently reliable diagnostic performance on the target domain while minimizing labeling effort. We validate our framework using two benchmark datasets: the Prognostics and Health Management Data Challenge 2022 dataset for Hydraulic Rock Drill (HRD) fault classification and the Paderborn University (PU) Bearing dataset. Experimental results demonstrate substantial improvements over existing methods. For the HRD dataset, our approach achieves 96.62% accuracy under Condition 1, representing a 45.79% improvement over the best baseline method. Similarly, for the PU Bearing dataset, we achieve 90.93% accuracy under Condition 1, exceeding the best baseline by 62.62%. Comparable performances are observed across other experimental conditions in both datasets.

跨域故障诊断是机队管理预测性维护中的一项重要任务。然而，现有的迁移学习和分布匹配方法在现实场景中往往是不切实际的，特别是在少射条件下，它们的诊断性能不能得到一致的保证。为了解决这一问题，本研究提出了一种基于预训练-微调范式的跨域故障诊断半监督框架。在我们的方法中，采用自监督对比学习进行集中的多域预训练，然后进行监督微调和对比再学习，以实现跨不同机器和操作条件的鲁棒模型对齐。为了有效捕获结构化传感器数据中的时间依赖性并提高样本效率，我们采用了一种时间序列对比学习方法，即通过时间和上下文对比的时间序列表示学习（TS-TCC），作为预训练阶段的核心组成部分。此外，我们还引入了一种两阶段的样本选择策略，该策略可以实现高效注释的模型对齐。这种设计确保了在目标域上始终可靠的诊断性能，同时最大限度地减少了标记工作。我们使用两个基准数据集验证了我们的框架：用于水力岩石钻机（HRD）故障分类的预测和健康管理数据挑战2022数据集和帕德博恩大学（PU）轴承数据集。实验结果表明，与现有方法相比，有了很大的改进。对于HRD数据集，我们的方法在条件1下达到96.62%的准确率，比最佳基线方法提高了45.79%。同样，对于PU轴承数据集，我们在条件1下实现了90.93%的精度，比最佳基线高出62.62%。在两个数据集的其他实验条件下观察到可比较的性能。

{"title":"Semi-supervised cross-domain fault diagnosis via contrastive pre-training and annotation-efficient alignment strategy","authors":"Lechang Yang , Xianghao Zhang , Feng Zhu , Zhe Wang , Xiaoge Zhang","doi":"10.1016/j.jii.2026.101076","DOIUrl":"10.1016/j.jii.2026.101076","url":null,"abstract":"<div><div>Cross-domain fault diagnosis is a critical task in predictive maintenance for fleet management. However, existing transfer learning and distribution matching methods are often impractical in real-world scenarios, especially under few-shot conditions, where their diagnostic performance cannot be consistently guaranteed. To address this issue, this study proposes a novel semi-supervised framework for cross-domain fault diagnosis, based on the pre-training–fine-tuning paradigm. In our approach, self-supervised contrastive learning is employed for centralized multi-domain pre-training, followed by supervised fine-tuning and contrastive re-learning to achieve robust model alignment across different machines and operating conditions. To effectively capture temporal dependencies in structured sensor data and improve sample efficiency, we incorporate a time-series contrastive learning method, Time-Series Representation Learning via Temporal and Contextual Contrasting (TS-TCC), as the core component of the pre-training stage. Furthermore, we introduce a two-stage sample selection strategy that enables annotation-efficient model alignment. This design ensures consistently reliable diagnostic performance on the target domain while minimizing labeling effort. We validate our framework using two benchmark datasets: the Prognostics and Health Management Data Challenge 2022 dataset for Hydraulic Rock Drill (HRD) fault classification and the Paderborn University (PU) Bearing dataset. Experimental results demonstrate substantial improvements over existing methods. For the HRD dataset, our approach achieves 96.62% accuracy under Condition 1, representing a 45.79% improvement over the best baseline method. Similarly, for the PU Bearing dataset, we achieve 90.93% accuracy under Condition 1, exceeding the best baseline by 62.62%. Comparable performances are observed across other experimental conditions in both datasets.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"50 ","pages":"Article 101076"},"PeriodicalIF":10.4,"publicationDate":"2026-01-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146014988","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