Journal of Industrial Information Integration最新文献

{"title":"DeepPipe: A multi-stage knowledge-enhanced physics-informed neural network for hydraulic transient simulation of multi-product pipeline","authors":"Jian Du ,&nbsp;Haochong Li ,&nbsp;Kaikai Lu ,&nbsp;Jun Shen ,&nbsp;Qi Liao ,&nbsp;Jianqin Zheng ,&nbsp;Rui Qiu ,&nbsp;Yongtu Liang","doi":"10.1016/j.jii.2024.100726","DOIUrl":"10.1016/j.jii.2024.100726","url":null,"abstract":"<div><div>In the chemical pipelining industry, owing to the high-pressure transportation process, an accurate hydraulic transient simulation tool plays a central role in preventing the slack line flow and overpressure from causing pipeline operation treacherous. Nevertheless, the current model-driven method often faces challenges in balancing computational efficiency with accuracy, and the existing data-driven models struggle to produce explainable results from the physics perspectives since insufficient theoretical principles are incorporated into the model training. Additionally, the existing physics-informed learning architecture fails to achieve a gradient-balanced training, resulting from the significant magnitude difference in outputs and multiple loss terms. Consequently, a Multi-Stage Knowledge-Enhanced Physics-Informed Neural Network (MS-KE-PINN) is proposed for the hydraulic transient simulation of multi-product pipelines. To enforce the neural network producing simulation results with high consistency to physical laws, the governing equations, boundary, and initial condition are incorporated into the training process for an efficient mesh-free simulation. Then, considering that the significant magnitude difference between outputs can easily lead to deficient performance in the gradient descent, the magnitude conversion on the outputs and the equivalent conversion of the governing equations are implemented to enhance the training effect of the neural network. Subsequently, to tackle the imbalanced gradient of multiple loss terms with fixed weights, a multi-stage hierarchical training strategy is designed to improve the approximation capacity of the neural network. Numerical simulation cases demonstrate a better approximation function of the proposed model than the state-of-art models, while the mean absolute percentage errors yielded by MS-KE-PINN are reduced by 77.4 %, 88.7 %, and 87.8 % in three simulation operation conditions for pressure prediction. Furthermore, experimental investigations from a real-world multi-product pipeline suggest that the proposed model can still draw accurate simulation results even under complex and dynamic hydraulic transient scenarios in practice, with root mean squared errors reduced by 94.8 % and 80 % than that of the physics-informed neural network. To this end, the proposed model can conduct accurate and effective hydraulic transient analysis, thus ensuring the safe operation of the pipeline.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"42 ","pages":"Article 100726"},"PeriodicalIF":10.4,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142653225","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":"EDLIoT: A method for decreasing energy consumption and latency using scheduling algorithm in Internet of Things","authors":"Arash Ghorbannia Delavar,&nbsp;Hamed Bagheri","doi":"10.1016/j.jii.2024.100719","DOIUrl":"10.1016/j.jii.2024.100719","url":null,"abstract":"<div><div>Decreasing energy consumption in networks with limited resources, such as the Internet of Things, has always been one of the main challenges in guaranteeing network performance. In this article, cooperative game theory is employed to improve the cooperation patterns of fog computing resources. The EDLIoT method consists of two main steps: “Topology Construction” and “Determining Optimal Fog Computing Resources to Process IoT Object Tasks”. In the first step of the proposed method, the set of reliable communications in the network is identified to establish connections between IoT objects and fog computing resources in the form of a tree structure. Then, in the second step, a model based on cooperative game theory and the cost function is used to determine the optimal computing resources in the fog layer for outsourcing the processing tasks of IoT objects. In EDLIoT, active IoT objects perform computation in the fog layer instead of locally, to conserve energy. This is done so that IoT objects, if possible, discover the most suitable processing resources in the fog based on characteristics such as energy consumption, delay, and processing power of the computing resource. The efficiency of the proposed method has been evaluated in a simulated environment, and the results have been compared with those of previous algorithms. The results demonstrate that using the EDLIoT method, in addition to decreasing energy consumption and delay, more computing tasks can be processed through fog resources, thereby increasing the quality of service for IoT users.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"42 ","pages":"Article 100719"},"PeriodicalIF":10.4,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142653232","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":"Understanding data quality in a data-driven industry context: Insights from the fundamentals","authors":"Qian Fu,&nbsp;Gemma L. Nicholson,&nbsp;John M. Easton","doi":"10.1016/j.jii.2024.100729","DOIUrl":"10.1016/j.jii.2024.100729","url":null,"abstract":"<div><div>The increasing adoption of commercial-off-the-shelf infrastructure components and the rising integration of sensors into assets have led to a notable proliferation of operational data in industrial systems. As a result, a significant portion of investment and risk management decisions now heavily rely on the provenance and quality of heterogeneous data, sourced both internally and externally from specific industrial systems. This paper presents a review that covers three critical aspects of data quality: first, ensuring data quality through deliberate design; second, understanding the dynamic interplay between data and its users within sociotechnical systems; and third, attributing ongoing value to data resources as their roles evolve. These aspects are examined through a lens encompassing both traditional and the state-of-the-art theoretical frameworks for defining data quality. In addition, we incorporate insights from contemporary empirical research and highlight relevant industry standards and best practice guidelines. The synthesised insights serve as a practical foundation and reference for researchers and industry professionals alike, enabling them to refine and advance their understanding of data quality within the landscape of data-driven industries.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"42 ","pages":"Article 100729"},"PeriodicalIF":10.4,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142653283","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":"Identification of material excavation difficulty and uncertainty analysis based on Bayesian deep learning","authors":"Shijiang Li ,&nbsp;Shaojie Wang ,&nbsp;Xiu Chen ,&nbsp;Gongxi Zhou ,&nbsp;Liang Hou","doi":"10.1016/j.jii.2024.100728","DOIUrl":"10.1016/j.jii.2024.100728","url":null,"abstract":"<div><div>Accurately assessing the difficulty of material excavation is crucial for reducing excavator energy consumption, ensuring operational safety, and optimizing excavator efficiency. Addressing the challenges of uncertain and difficult-to-judge excavation conditions for underground materials, this paper proposes a Bayesian deep learning-based method that integrates excavation process data to identify excavation difficulty. Firstly, we constructed a deep learning model based on Bayesian theory and decomposed the uncertainty of the identification results into aleatory uncertainty and epistemic uncertainty. Next, through a mechanistic analysis of the interaction between materials and the excavator bucket during excavation, we identified the input features for the model. Finally, we validated the effectiveness of the method through experiments. The results show that the proposed method not only accurately identifies the excavation difficulty of the material but also quantifies and decomposes the uncertainty of the identification results, demonstrating both theoretical significance and practical application value.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"42 ","pages":"Article 100728"},"PeriodicalIF":10.4,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142653274","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":"An effective farmer-centred mobile intelligence solution using lightweight deep learning for integrated wheat pest management","authors":"Shunbao Li ,&nbsp;Zhipeng Yuan ,&nbsp;Ruoling Peng ,&nbsp;Daniel Leybourne ,&nbsp;Qing Xue ,&nbsp;Yang Li ,&nbsp;Po Yang","doi":"10.1016/j.jii.2024.100705","DOIUrl":"10.1016/j.jii.2024.100705","url":null,"abstract":"<div><div>Integrated Pest Management (IPM) techniques have been widely used in agriculture to manage pest damage in the most economical way and to minimise harm to people, property and the environment. However, current research and products on the market cannot consolidate this process. Most existing solutions either require experts to visually identify pests or cannot automatically assess pest levels and make decisions based on detection results. To make the process from pest identification to pest management decision making more automated and intelligent, we propose an end-to-end integrated pest management solution that uses deep learning for semi-automated pest detection and an expert system for pest management decision making. Specifically, a low computational cost sampling point generation algorithm is proposed to enable mobile devices to generate uniformly distributed sampling points in irregularly shaped fields. We build a pest detection model based on YoloX and use Pytorch Mobile to deploy it on mobile phones, allowing users to detect pests offline. We develop a standardised sampling specification and a mobile application to guide users to take photos that allow pest population density to be calculated. A rule-based expert system is established to derive pest management thresholds from prior agricultural knowledge and make decisions based on pest detection results. We also propose a human-in-the-loop algorithm to continuously track and update the validity of the thresholds in the expert system. The mean average precision of the pest detection model is 58.17% for 97 classes, 75.29% for 2 classes, and 57.33% for 11 classes on three pest datasets, respectively. The usability of the pest management system is assessed by the User Experience Surveys and achieves a System Usability Scale (SUS) score of 76. The usability of the proposed solution is validated by qualitative field experiments.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"42 ","pages":"Article 100705"},"PeriodicalIF":10.4,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142573230","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":"Advance industrial monitoring of physio-chemical processes using novel integrated machine learning approach","authors":"Husnain Ali ,&nbsp;Rizwan Safdar ,&nbsp;Muhammad Hammad Rasool ,&nbsp;Hirra Anjum ,&nbsp;Yuanqiang Zhou ,&nbsp;Yuan Yao ,&nbsp;Le Yao ,&nbsp;Furong Gao","doi":"10.1016/j.jii.2024.100709","DOIUrl":"10.1016/j.jii.2024.100709","url":null,"abstract":"<div><div>With the rapid transition of Industry 4.0 to 5.0, modern industrial physio-chemical processes are characterized by two critical challenges: process safety and the quality of the final product. Traditional industrial monitoring methods have low reliability in accuracy and robustness, and they are inefficiently providing satisfactory results. This paper introduces a novel integration technique that employs machine learning (ML) to tackle the challenges associated with real industrial monitoring in physical and industrial processes. The proposed framework integrates distributed canonical correlation analysis - R-vine copula (DCCA-RVC), global local preserving projection (GLPP), and 2-Dimensional Deng information entropy (2-DDE). The framework's ability and productivity are assessed utilizing existing approaches such as wavelet-PCA, MRSAE, and DALSTM-AE and the new proposed novel integrated machine learning-based (DCCA-RVC) approach as benchmarks for model performance. The proposed novel approach has been validated by testing it on the ethanol-water system distillation column (DC) and Tennessee Eastman Process (TEP), utilizing it as actual industrial benchmarks. The results demonstrate that the novel integration ML-technique (DCCA-RVC) T₂² – GLP monitoring graphs for the fault class type 1 in the distillation column showed a (FAR) of 0 %, a (FDR) of 100 %, a precision of 100 %, F1-score of 100 % and an accuracy of 100 %. However, for the TEP process failure event 13, the (FAR) was 0 %, the (FDR) was 99 %, the accuracy was 100 %, the F1-score was 99.5 %, and the accuracy was 99.5 %.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"42 ","pages":"Article 100709"},"PeriodicalIF":10.4,"publicationDate":"2024-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142529046","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Design and implementation of an active load test rig for high-precision evaluation of servomechanisms in industrial applications","authors":"Alessio Tutarini ,&nbsp;Pietro Bilancia ,&nbsp;Jhon Freddy Rodríguez León ,&nbsp;Davide Viappiani ,&nbsp;Marcello Pellicciari","doi":"10.1016/j.jii.2024.100696","DOIUrl":"10.1016/j.jii.2024.100696","url":null,"abstract":"<div><div>Position-controlled servomechanisms are the core elements of flexible manufacturing plants, primarily utilized to actuate robotic systems and automated machines. To match specific torque and costs requirements, typical servomechanism arrangements comprise precision reducers, which introduce motion errors that heavily limit the final performance achievable. Such errors are complex to model and depend from speed, dynamic loading conditions and temperature. Accurate characterization is fundamental to develop digital twins and advanced control strategies aimed at their active prediction and compensation. To properly assess the servomechanisms behavior and elaborate high-fidelity virtual models, instrumented test rigs have been proposed which can replicate the time-varying working conditions encountered in real industrial environments. In this context, the present paper reports about a novel engineering method for developing an active loading apparatus, namely a programmable mechatronic device that can deliver custom loads in a highly dynamic manner. The proposed system, consisting of a secondary servomotor and related rotating vector reducer, is integrated and synchronized within an existing instrumented test rig and is controlled in torque mode via a programmable logic controller. The paper mainly focuses on the description of the implemented closed-loop control and on the related tuning and calibration processes, demonstrating that the proposed solutions avoid important measurement errors that could compromise the final effectiveness of the system. The study finally explores the potential benefits of introducing a filter to further enhance system performance. At last, to prove the importance of stabilizing the rig and demonstrate the influence of the control parameters on its measurements, a standard test aimed at assessing the reducer transmission error is conducted adopting different parameter settings.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"42 ","pages":"Article 100696"},"PeriodicalIF":10.4,"publicationDate":"2024-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142529045","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":"SCL: A sustainable deep learning solution for edge computing ecosystem in smart manufacturing","authors":"Himanshu Gauttam ,&nbsp;K.K. Pattanaik ,&nbsp;Saumya Bhadauria ,&nbsp;Garima Nain","doi":"10.1016/j.jii.2024.100703","DOIUrl":"10.1016/j.jii.2024.100703","url":null,"abstract":"<div><div>Edge computing empowered Deep Learning (DL) solutions have risen as the foremost facilitators of automation in a multitude of smart manufacturing applications. These models are implemented on edge devices with frozen learning capabilities to execute DL inference task(s). Nevertheless, the data they process is susceptible to intermittent alterations amidst the ever-changing landscape of dynamic smart manufacturing ecosystem. It sparks the demand for model maintenance solution(s) to address adaptability and dynamism issues to enhance the efficiency of smart manufacturing solutions. Moreover, additional issue(s), such as the non-availability of comprehensive data (or the availability of solely contemporary data), near-real-time execution of DL model maintenance task, etc., imposes daunting obstructions in devising an efficient DL model maintenance strategy. This work proposes a novel approach that encompasses the merits of Continual Learning (CL) and Split Learning (SL) driven by edge intelligence, amalgamating them into a hybrid solution aptly named <em>Split-based Continual Learning (SCL)</em>. CL ensures the sustained performance of the DL model amidst constraints related to data availability. At the same time, SL empowers near-real-time execution at the edge to achieve improved efficiency. An extension of the <em>SCL</em> scheme, termed as <em>Extended SCL (ESCL)</em>, is implemented to addresses the interaction soundness aspects among the mobile edge devices in a collaborative execution environment. Evaluation of a vision-based product-quality inspection use case in an emulated hardware test-bed setup signifies that the performance of <em>SCL</em> and <em>ESCL</em> schemes have the potential to meet the needs of smart manufacturing. <em>SCL</em> attains an appreciable reduction in the model maintenance cost in the range of 21 to 48 and 12 to 29 percent compared to the ECN-only and basic-SL schemes. The <em>ESCL</em> scheme further improved the performance by 18 to 34 and 20 to 36 percent respectively over the basic-SL and <em>SCL</em>.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"42 ","pages":"Article 100703"},"PeriodicalIF":10.4,"publicationDate":"2024-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142529043","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 smart multiphysics approach for wind turbines design in industry 5.0","authors":"Kambiz Tehrani ,&nbsp;Milad Beikbabaei ,&nbsp;Ali Mehrizi-Sani ,&nbsp;Mo Jamshidi","doi":"10.1016/j.jii.2024.100704","DOIUrl":"10.1016/j.jii.2024.100704","url":null,"abstract":"<div><div>This paper aims to develop a smart multiphysics approach for wind turbine design utilizing Industry 5.0. A new blade profile is developed and optimized by non-dominated sorting genetic algorithm II (NSGA-II) for shape design, and a 3D modeling of wind turbines is proposed. The aerodynamic modeling of a horizontal axis wind turbine (HAWT) is an important step in the design of wind turbines. The blade geometry design plays an important role in a wind turbine to maximize the aerodynamic performance and extract as much kinetic energy as possible from the wind resource. This paper addresses a high-level design and optimization for the parameters of a new blade. Moreover, a 3D modeling of large wind turbines (<span><math><mo>&gt;</mo></math></span>7 MW) is proposed that can be used in wind farms. This approach can be used in real-time design in Industry 5.0 using different data from sensors. Finally, the optimized blade increases the produced power by 10% (from 7.5 MW to 8.2 MW). The proposed approach allows people to work alongside machinery to improve processes and provide personalization for companies manufacturing wind turbines.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"42 ","pages":"Article 100704"},"PeriodicalIF":10.4,"publicationDate":"2024-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142529044","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":"EBH-IoT: Energy-efficient secured data collection and distribution of electronics health record for cloud assisted blockchain enabled IoT based healthcare system","authors":"Anita Sahoo,&nbsp;Srichandan Sobhanayak","doi":"10.1016/j.jii.2024.100702","DOIUrl":"10.1016/j.jii.2024.100702","url":null,"abstract":"<div><div>The integration of Health IoT (H-IoT) and blockchain technologies are being heavily exploited and used in many domains, especially for e-healthcare to collect the data i.e electronic health record (EHR) from the patient. The H-IoT devices have the ability to provide real-time sensory data from patients to be processed and analyzed, and distributed. Blockchain is providing decentralized computation, distribution and storage for EHR data. Therefore, the integration of H-IoT and Blockchain technologies can become a reasonable choice for the design of decentralized H-IoT-based e-healthcare systems. But the H-IoT network has some intrinsic challenges like low computation, energy constraint, security, energy optimization, data storage, and real-time data analytic. Also, conventional EHR-based systems suffer from issues such as the potential loss of data, inadequate security and consensus on the unchangeable nature of health records, fragmented connections between different institutions, and ineffective clinical data retrieval methods, among other challenges. In this article, first, we study the performance of blockchain technology in the healthcare system. Second, we propose an improved Harris Hawk Optimization algorithm (HHO) based clustering mechanism for the collection and sharing of EHR. The proposed system was tested and validated using the Hyperledger-fabric based electronic healthcare record (EHR) sharing system along with Matlab. The proposed system achieves 12%, and 7% incremental improvement in terms of latency, throughput for the Blockchain networks. While the proposed clustering technique achieves 10%, 12%, 14%, and 16% improvements in alive node, energy consumption, throughput and average transmission delay compared to existing state of the art.</div></div>","PeriodicalId":55975,"journal":{"name":"Journal of Industrial Information Integration","volume":"42 ","pages":"Article 100702"},"PeriodicalIF":10.4,"publicationDate":"2024-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142528804","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}