Journal of Industrial Information Integration最新文献

{"title":"Expert opinion aggregation-based decision support for human-robot collaboration digital twin maturity assessment","authors":"Xin Liu ,&nbsp;Gongfa Li ,&nbsp;Feng Xiang ,&nbsp;Bo Tao ,&nbsp;Guozhang Jiang","doi":"10.1016/j.jii.2024.100710","DOIUrl":"10.1016/j.jii.2024.100710","url":null,"abstract":"<div><div>Human-centered smart manufacturing is an essential direction for the future development of manufacturing. Safe and reliable smart human-robot collaboration is the foundation for realizing human-centered smart manufacturing. Digital twin-based human-robot collaboration has been proposed as a new manufacturing paradigm to devise collaborative strategies, simulate collaborative processes, and ensure worker safety. Establishing a maturity model is essential to accurately assess the capabilities of the constructed human-robot collaboration digital twin. This paper aims to contribute to the formalization and standardization of the human-robot collaboration digital twin. It constructs a novel assessment framework for the overall maturity measurement of existing digital twin-based human-robot collaboration projects. The developed human-robot collaboration digital twin maturity model includes 5 evaluation dimensions and 24 evaluation factors. Additionally, 5 maturity levels and their definitions are defined for each evaluation factor for maturity scoring. The expert opinion aggregation approach is proposed to quantify the evaluation factor metrics and ultimately to obtain a maturity level for the human-robot collaboration digital twin. The effectiveness and feasibility of the proposed method are verified through a collaborative assembly case study. This paper provides a generic method for assessing the competency level of human-robot collaboration digital twins, which can provide insights into the maturity of digital twins for practitioners in the human-robot collaboration field to develop targeted strategies for optimizing and upgrading human-robot collaboration digital twins.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"42 ","pages":"Article 100710"},"PeriodicalIF":10.4,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142577924","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":"Consensus reaching-based decision model for assessing resilient urban public health safety ecosystem with social network analysis","authors":"Zelin Wang ,&nbsp;Xiangbin Wang ,&nbsp;Weizhong Wang ,&nbsp;Muhammet Deveci ,&nbsp;Zengyuan Wu ,&nbsp;Witold Pedrycz","doi":"10.1016/j.jii.2024.100716","DOIUrl":"10.1016/j.jii.2024.100716","url":null,"abstract":"<div><div>In 2021, United Nations released the \"Creating Resilient Cities 2030 Project\", which aims to strengthen urban resilience in developing and implementing disaster reduction strategies. Resilient cities are a new type of urban development model that emphasizes the ability of cities to resist natural disasters and social pressures, reduce losses, and allocate resources reasonably to quickly recover from disasters. With the frequent occurrence of public health and safety accidents, the concept of public health safety ecosystem has become increasingly prominent in the field of urban resilience. To effectively manage public health incidents and enhance emergency response capabilities, evaluating the urban public health safety ecosystem is essential. A consensus-based decision-making model that accounts for the social networks among experts to accurately assess urban public health emergency capacity is introduced. To ensure the objectivity of indicator weights, we build up a novel model to calculate the weight of indicators utilizing social network analysis and consensus-reaching process analysis of indicator evaluation value. An illustrative case study on public health emergency capacity in Luoding is presented. This research expands the framework for assessing resilience in urban systems and provides a methodology for improving urban public health and resilience, introducing a novel approach for evaluating the urban public health safety ecosystem through social network analysis.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"42 ","pages":"Article 100716"},"PeriodicalIF":10.4,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142577925","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":"Cross-domain intelligent diagnostics for rotating machinery using domain adaptive and adversarial networks","authors":"Kui Hu ,&nbsp;Yiwei Cheng ,&nbsp;Jun Wu ,&nbsp;Haiping Zhu","doi":"10.1016/j.jii.2024.100722","DOIUrl":"10.1016/j.jii.2024.100722","url":null,"abstract":"<div><div>Accurate fault diagnosis of rotating machinery is critical to avoid catastrophic accidents. However, insufficient fault data seriously limit the performance of fault diagnosis in industrial applications. In this paper, a novel domain adaptive and adversarial network (DAAN) is proposed for data-driven fault diagnosis of the rotating machinery, which consists of a deep feature extractor, a domain classifier, and a label adaptive predictor. The deep feature extractor and domain classifier are constructed to obtain domain-invariant features by domain-adversarial training. Then, in the label adaptive predictor, a domain adaptation technique is used to reduce the feature discrepancy between the source domain and the target domain, so as to establish a mapping relationship between the data feature distribution of the two domains. Furtherly, a new transfer diagnosis method is proposed by using the DAAN, which combines the data generated by experimental simulation with deep transfer learning, to realize end-to-end intelligent fault diagnosis of the in-service machinery with few unlabeled fault samples. The proposed method explores a new solution for applying laboratory data to intelligent fault diagnosis in real scenarios. Several transfer experiments are implemented to verify the effectiveness of the proposed method by using 55 roller bearings and 4 gearboxes under various scenarios. The experimental results show that the diagnostic performance of proposed method is much better than other transfer learning methods and non-transfer learning methods.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"42 ","pages":"Article 100722"},"PeriodicalIF":10.4,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142592829","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":"Enabling secure and self-sovereign machine learning model exchange in manufacturing data spaces","authors":"Tharindu Ranathunga,&nbsp;Alan McGibney,&nbsp;Sourabh Bharti","doi":"10.1016/j.jii.2024.100733","DOIUrl":"10.1016/j.jii.2024.100733","url":null,"abstract":"<div><div>With the rapid digital transformation of manufacturing, vast amounts of data are being generated and analyzed to uncover valuable patterns in areas such as energy efficiency, predictive maintenance, production scheduling etc. However, much of this data and the intelligence derived from it remain isolated within individual companies. This is strongly influenced by companies reluctance to share data due to concerns over privacy and security associated with the commercially sensitive information. As a result, the potential shared value that can be derived from a richer, larger pool of data and intelligence across multiple companies remains untapped. While solutions such as federated learning exist to address privacy and security issues, strong governance so that the privacy is preserved is crucial to its successful implementation. Currently, there is a lack of software infrastructure that guarantees data sovereignty and governance for data owners in this space. This paper introduces COllaboRative Data Space (CORDS), a framework that enables companies to engage in a machine learning model-sharing ecosystem, providing full control over the access and usage of their data. Aligned with the European Data Space initiative, CORDS aims to foster trusted collaboration by providing a software infrastructure constituting a set of tools for both intra and inter-organization data asset management and ML model exchange. To the best of our knowledge, CORDS is the first minimum viable data space (MVDS) designed to address the broader challenges of <em>sovereignty, interoperability, compliance &amp; governance</em> in cross-party ML model sharing. This paper also highlights the value of data sharing by applying CORDS to a use-case focused on improving energy efficiency in manufacturing. Extensive performance evaluation showcases CORDS’ utility in securely managing data assets and facilitating machine learning model exchanges. CORDS is available as open-source software, supporting further research and practical applications of trusted data spaces in both academia and industry.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"42 ","pages":"Article 100733"},"PeriodicalIF":10.4,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142723550","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Quantum machine learning: Classifications, challenges, and solutions","authors":"Wei Lu ,&nbsp;Yang Lu ,&nbsp;Jin Li ,&nbsp;Alexander Sigov ,&nbsp;Leonid Ratkin ,&nbsp;Leonid A. Ivanov","doi":"10.1016/j.jii.2024.100736","DOIUrl":"10.1016/j.jii.2024.100736","url":null,"abstract":"<div><div>Recently, research at the intersection of quantum mechanics and machine learning has gained attention. This interdisciplinary field aims to tackle the computational efficiency of machine learning by leveraging quantum computing and to derive novel machine learning algorithms inspired by quantum principles. Despite substantial progress in quantum science research, several challenges persist, including the preservation of quantum coherence, mitigation of environmental constraints, advancing quantum computer development, and formulating comprehensive quantum machine learning algorithms. To date, a comprehensive theoretical framework for quantum machine learning is lacking, with much of the research still in the exploratory and experimental stages. This study conducts a thorough survey on quantum machine learning, with the aim of classifying quantum machine learning algorithms while addressing the existing challenges and potential solutions in this emerging field.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"42 ","pages":"Article 100736"},"PeriodicalIF":10.4,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142653227","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":"Enhancing mixed gas discrimination in e-nose system: Sparse recurrent neural networks using transient current fluctuation of SMO array sensor","authors":"Namsoo Lim ,&nbsp;Seokyoung Hong ,&nbsp;Jiwon Jung ,&nbsp;Gun Young Jung ,&nbsp;Deok Ha Woo ,&nbsp;Jinwoo Park ,&nbsp;Daewon Kong ,&nbsp;Chandran Balamurugan ,&nbsp;Sooncheol Kwon ,&nbsp;Yusin Pak","doi":"10.1016/j.jii.2024.100715","DOIUrl":"10.1016/j.jii.2024.100715","url":null,"abstract":"<div><div>Despite recent significant advancements in gas sensor array technology, accurately identifying gases in mixed environments remains challenging. This difficulty is primarily due to the rapid and competing processes of gas molecules attaching to (adsorption) and detaching from (desorption) the sensor. In this study, we present a simple method to fabricate a 2 × 4 SMO-based gas sensor array, coupled with a sparse recurrent neural network (SRNN) that employs weight regularization. The recurrent layers of the SRNN process nonlinear information and capture temporal dependencies in the sensor data, while the regularization technique simplifies the model, making it both efficient and easier to interpret. Additionally, we introduce a novel feature: the dynamics of current, labeled as ΔI. This feature enables the SRNN model to efficiently detect the adsorption and desorption of gas molecules. We demonstrate that our model can distinguish between three intuitively indistinguishable datasets of gas species (NO₂, HCHO, and a mixture) with up to 92 % accuracy. By utilizing the fast and competitive adsorption/desorption information of gas molecules, our model can be applied to various gas combination environments, unlike conventional gas sensing data measured over longer periods. By integrating the sensor array with the advanced SRNN model, we pave the way for sophisticated e-nose systems, with potential applications in advanced gas sensing technologies, such as disease diagnosis through exhaled breath analysis and the detection of toxic species in mixed gas environments.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"42 ","pages":"Article 100715"},"PeriodicalIF":10.4,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142554189","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":"Integration of an IoT sensor with angle-of-arrival-based angle measurement in AGV navigation: A reliability study","authors":"Zhen Cai ,&nbsp;Fanhang Zhang ,&nbsp;Yuan Tan ,&nbsp;Stephan Kessler ,&nbsp;Johannes Fottner","doi":"10.1016/j.jii.2024.100707","DOIUrl":"10.1016/j.jii.2024.100707","url":null,"abstract":"<div><div>Automated guided vehicle (AGV), which was initially designed for indoor operations in industry, has been increasingly applied in outdoor heavy-duty logistics tasks. In typical navigation tasks, such as the autonomous tracking of a designated object or a person, relative angle and relative distance between AGV and the target is required. To obtain the necessary information, various on-board sensors are extensively integrated. In this paper, the reliability of measuring the relative angle with the Angle-of-Arrival (AoA) method with two different Internet of Things (IoT) sensor sets from Texas Instrument (TI) and u-blox, according to Bluetooth 5.1 was investigated. The performance of IoT sensors was validated with angle accuracy parameters and received signal strength indicator (RSSI). The better IoT sensor was then integrated into the AGV navigation system, and the information gathered from IoT sensor enabled the AGV to turn toward the direction of the target. The process of AGV turning to the targeted direction based on IoT sensor information was respectively tested in the simulation and actual environment and evaluated by the disparity between the real relative angle and the rotation angle of the AGV. The results showed that this disparity was within ±5° in both simulated and actual environments, and methods for higher accuracy were proposed. In this way, the reliability and performance of Angle of Arrival (AoA) sensors in measuring the relative angle, which remains unexplored by other researchers, was systematically assessed contributing to extending the usability of AoA sensors in complex, real-world applications.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"42 ","pages":"Article 100707"},"PeriodicalIF":10.4,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142573311","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Evaluating municipal solid waste management with a confidence level-based decision-making approach in q-rung orthopair picture fuzzy environment","authors":"Prayosi Chatterjee,&nbsp;Mijanur Rahaman Seikh","doi":"10.1016/j.jii.2024.100708","DOIUrl":"10.1016/j.jii.2024.100708","url":null,"abstract":"<div><div>Municipal solid waste (MSW) management is a critical aspect of urban planning and public health. As societies strive towards environmental sustainability and socio-economic development, robust techniques to transform waste into energy become paramount. Assessment of waste-to-energy (WTE) techniques is based on a spectrum of criteria that are often vague and imprecise. The current study addresses this multi-criteria group decision-making problem of assessing and evaluating WTE methods for MSW management using q-rung orthopair picture fuzzy (qRPF) numbers. The study proposes an innovative combination of the Defining Interrelationships Between Ranked-criteria (DIBR) and Compromise Ranking of Alternatives from Distance to Ideal Solution (CRADIS) methods. The criteria are assessed using the recently developed DIBR method, while the alternatives are assessed using a popular distance-based method, namely CRADIS. Moreover, new confidence level-based aggregation operators for qRPF numbers are proposed and used to aggregate fuzzy data, while a novel triangular divergence-based distance measure is proposed and used to modify the existing CRADIS method. The results show that anaerobic digestion and pyrolysis are the two most preferred WTE methods for MSW management. An extensive comparative analysis demonstrates the applicability of the proposed methodology, while an exhaustive sensitivity analysis confirms the proposed method’s stability. The results of Spearman’s correlation coefficient validate the model’s practicality. The findings of this research yield significant insights beneficial to policymakers, industry stakeholders, and researchers alike. By implementing sustainable waste management strategies, municipalities can improve recycling rates, minimize landfill use, and promote a cleaner, healthier environment for urban populations.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"42 ","pages":"Article 100708"},"PeriodicalIF":10.4,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142577826","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":"Generating the assembly instructions of helicopter subassemblies using the hierarchical pruning strategy and large language model","authors":"Mingjie Jiang,&nbsp;Yu Guo,&nbsp;Shaohua Huang,&nbsp;Jun Pu","doi":"10.1016/j.jii.2024.100723","DOIUrl":"10.1016/j.jii.2024.100723","url":null,"abstract":"<div><div>Assembly instructions are process documents in detail describing the operation steps, materials, tools, fixtures, and assembly sequences in assembly procedures. Due to assembly instructions including numerous contents, and the content being easy for workers to understand, process designers need to spend lots of time thinking and authoring assembly instructions to ensure that workers can complete the assembly task according to the assembly instructions. Focusing on the difficulties of the variety of assembly instructions and the process factors implicit in the standard languages of assembly instructions, a method of assembly instruction generation for helicopter subassemblies is proposed. First, a data representation model of multi-source heterogeneous knowledge and information based on knowledge graphs is designed and established. Then, a hierarchical pruning VF3 algorithm is presented to reuse assembly instructions according to hybrid similarity. Finally, a process factor revision model based on RoBERTa-BiLSTM-CRF is proposed to generate revised assembly instructions. Helicopter subassemblies, which contain 11,240 assembly procedures, are used to evaluate the performance of the method for generating assembly instructions. The proposed method greatly reduces the time cost of assembly instruction authoring and promotes the intelligent development of assembly process design.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"42 ","pages":"Article 100723"},"PeriodicalIF":10.4,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142592832","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A machine learning and fuzzy logic model for optimizing digital transformation in renewable energy: Insights into industrial information integration","authors":"Serkan Eti ,&nbsp;Serhat Yüksel ,&nbsp;Hasan Dinçer ,&nbsp;Dragan Pamucar ,&nbsp;Muhammet Deveci ,&nbsp;Gabriela Oana Olaru","doi":"10.1016/j.jii.2024.100734","DOIUrl":"10.1016/j.jii.2024.100734","url":null,"abstract":"<div><div>The most essential criteria to improve digital transformation in renewable energy projects should be identified. This situation helps the companies to use limited financial budgets and human resources in the most efficient way. Therefore, a new study is needed to analyze the performance indicators of the digital transformation process in renewable energy projects. Accordingly, this study aims to identify the most significant performance indicators of digital transformation for these projects. A three-stage machine learning and fuzzy logic-based decision-making model has been constructed in this process. The first stage includes the weight calculation of the experts by dimension reduction methodology. Secondly, essential factors of digital transformation in renewable energy projects are examined via Fermatean fuzzy criteria importance through intercriteria correlation (CRITIC). The final part consists of the ranking of emerging seven countries with Fermatean fuzzy weighted aggregated sum product assessment (WASPAS). On the other side, combined compromise solution (CoCoSo) method is also taken into consideration in this process to make a comparative evaluation. The main contribution of this study is the generation of novel machine learning and fuzzy logic integrated decision-making model to make evaluation related to the digital transformation of renewable energy projects. In this model, machine learning technique is used to determine the importance weights of the experts. Similarly, integrating Fermatean fuzzy numbers with CRITIC and WASPAS techniques also contributes to the literature by minimizing the uncertainty and identifying the relationship between the items. The findings demonstrate that employing qualified personnel plays the most critical role in increasing digital transformation in renewable energy projects. Additionally, government support is very critical in the successful implementation of digital transformation processes in renewable energy projects.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"42 ","pages":"Article 100734"},"PeriodicalIF":10.4,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142696480","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}