Pub Date : 2024-08-02DOI: 10.1109/OJIES.2024.3436590
Daniel Bujosa Mateu;Julian Proenza;Alessandro V. Papadopoulos;Thomas Nolte;Mohammad Ashjaei
In order to facilitate the adoption of Time Sensitive Networking (TSN) by the industry, it is necessary to develop tools to integrate legacy systems with TSN. In this article, we propose a solution for the coexistence of different time domains from different legacy systems, each with its corresponding synchronization protocol, in a single TSN network. To this end, we experimentally identified the effects of replacing the communications subsystem of a legacy Ethernet-based network with TSN in terms of synchronization. Based on the results, we propose a solution called TALESS (TSN with Legacy End-Stations Synchronization). TALESS can identify the drift between the TSN communications subsystem and the integrated legacy devices (end-stations) and then modify the TSN schedule to adapt to the different time domains to avoid the effects of the lack of synchronization between them. We validate TALESS through both simulations and experiments on a prototype. We demonstrate that thanks to TALESS, legacy systems can synchronize through TSN and even improve features such as their reception jitter or their integrability with other legacy systems.
{"title":"TALESS: TSN With Legacy End-Stations Synchronization","authors":"Daniel Bujosa Mateu;Julian Proenza;Alessandro V. Papadopoulos;Thomas Nolte;Mohammad Ashjaei","doi":"10.1109/OJIES.2024.3436590","DOIUrl":"10.1109/OJIES.2024.3436590","url":null,"abstract":"In order to facilitate the adoption of Time Sensitive Networking (TSN) by the industry, it is necessary to develop tools to integrate legacy systems with TSN. In this article, we propose a solution for the coexistence of different time domains from different legacy systems, each with its corresponding synchronization protocol, in a single TSN network. To this end, we experimentally identified the effects of replacing the communications subsystem of a legacy Ethernet-based network with TSN in terms of synchronization. Based on the results, we propose a solution called TALESS (TSN with Legacy End-Stations Synchronization). TALESS can identify the drift between the TSN communications subsystem and the integrated legacy devices (end-stations) and then modify the TSN schedule to adapt to the different time domains to avoid the effects of the lack of synchronization between them. We validate TALESS through both simulations and experiments on a prototype. We demonstrate that thanks to TALESS, legacy systems can synchronize through TSN and even improve features such as their reception jitter or their integrability with other legacy systems.","PeriodicalId":52675,"journal":{"name":"IEEE Open Journal of the Industrial Electronics Society","volume":"5 ","pages":"807-822"},"PeriodicalIF":5.2,"publicationDate":"2024-08-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10620612","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141880628","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-30DOI: 10.1109/OJIES.2024.3419133
Jang-Hyun Park;Yeon-Ho Jeong;Do-Kwan Hong
This article presents the design and comprehensive multiphysics analysis of a permanent magnet synchronous motor (PMSM) intended for small electric podded propulsion systems in marine applications. Minimizing vibration related to underwater radiated noise (URN) and ensuring thermal stability to allow prolonged continuous operation are crucial aspects of propulsion motor design. To reduce URN, particular attention is given to the stator vibration mode order, determined by the slot/pole combination (SPC) of the PMSM. Structure-borne noise analysis is used to evaluate the equivalent radiated power level of three designed PMSMs with different stator vibration mode orders. One-way multiphysics analysis using finite element analysis (FEA) is performed in a water environment for the finally-selected PMSM with pod housing structure. URN generated from the electromagnetic force is predicted by structural-acoustics analysis. Through lumped-parameter thermal network (LPTN) and computational fluid dynamics (CFD) analyses, it is proposed that, based on the cylindrical housing shape, the thermal stability of the podded propulsor can be evaluated using LPTN analysis instead of CFD analysis. A prototype motor is fabricated to validate the results obtained using FEA.
{"title":"Design and Comprehensive Multiphysics Analysis of Permanent Magnet Synchronous Motor for Podded Propulsion in Marine Applications","authors":"Jang-Hyun Park;Yeon-Ho Jeong;Do-Kwan Hong","doi":"10.1109/OJIES.2024.3419133","DOIUrl":"10.1109/OJIES.2024.3419133","url":null,"abstract":"This article presents the design and comprehensive multiphysics analysis of a permanent magnet synchronous motor (PMSM) intended for small electric podded propulsion systems in marine applications. Minimizing vibration related to underwater radiated noise (URN) and ensuring thermal stability to allow prolonged continuous operation are crucial aspects of propulsion motor design. To reduce URN, particular attention is given to the stator vibration mode order, determined by the slot/pole combination (SPC) of the PMSM. Structure-borne noise analysis is used to evaluate the equivalent radiated power level of three designed PMSMs with different stator vibration mode orders. One-way multiphysics analysis using finite element analysis (FEA) is performed in a water environment for the finally-selected PMSM with pod housing structure. URN generated from the electromagnetic force is predicted by structural-acoustics analysis. Through lumped-parameter thermal network (LPTN) and computational fluid dynamics (CFD) analyses, it is proposed that, based on the cylindrical housing shape, the thermal stability of the podded propulsor can be evaluated using LPTN analysis instead of CFD analysis. A prototype motor is fabricated to validate the results obtained using FEA.","PeriodicalId":52675,"journal":{"name":"IEEE Open Journal of the Industrial Electronics Society","volume":"5 ","pages":"1011-1028"},"PeriodicalIF":5.2,"publicationDate":"2024-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10614771","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141869134","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-30DOI: 10.1109/OJIES.2024.3435956
Ikhlaq Ahmed;Naima Iltaf;Rabia Latif;Nor Shahida Mohd Jamail;Zafran Khan
Retrieval of a product with desired modifications from a vast inventory of online industrial platforms is frequently encountered in our daily life. This study presents a specialized framework to retrieve user's queried product with its desired changes incorporated. To facilitate interaction between the end-user and agent in such scenarios, a multimodal content-based image retrieval system is essential. The system extracts textual and visual attributes, combining them through inductive learning to a unified representation. It is based on an in-depth understanding of visual characteristics that are modified by textual semantics. Lastly, a novel reverse reranking (RR) algorithm arranges the joint representation of dual modality queries and their corresponding target images for efficient retrieval. The proposed framework is novel compared to earlier methodologies. First, it achieves successful fusion of two different modalities. Second, it introduces a RR algorithm in the inference stage for efficient retrieval. The proposed framework's enhanced performance has been assessed using the Fashion-200 K and MIT-States real-world benchmark datasets. The proposed system can be used in real-world applications subject to its practical implications, such as generalization to diverse domains, availability of domain specific data, nature of the data and queries, and availability of computational resources.
在我们的日常生活中，经常会遇到从大量的在线工业平台中检索带有所需修改的产品的情况。本研究提出了一个专门的框架，用于检索用户查询的产品，并将其所需的修改纳入其中。为了促进终端用户和代理在这种情况下的互动，一个基于多模态内容的图像检索系统是必不可少的。该系统提取文本和视觉属性，并通过归纳学习将它们组合成统一的表示形式。该系统基于对视觉特征的深入理解，而视觉特征是由文本语义修改而来的。最后，一种新颖的反向重新排序（RR）算法将双模态查询及其相应的目标图像进行联合表示，以实现高效检索。与早期的方法相比，所提出的框架具有新颖性。首先，它实现了两种不同模态的成功融合。其次，它在推理阶段引入了 RR 算法，以实现高效检索。我们使用 Fashion-200 K 和 MIT-States 真实世界基准数据集对拟议框架的增强性能进行了评估。提议的系统可用于现实世界的应用中，但需考虑其实际影响，如对不同领域的通用性、特定领域数据的可用性、数据和查询的性质以及计算资源的可用性。
{"title":"Dual Modality Reverse Reranking (DM-RR) Based Image Retrieval Framework","authors":"Ikhlaq Ahmed;Naima Iltaf;Rabia Latif;Nor Shahida Mohd Jamail;Zafran Khan","doi":"10.1109/OJIES.2024.3435956","DOIUrl":"10.1109/OJIES.2024.3435956","url":null,"abstract":"Retrieval of a product with desired modifications from a vast inventory of online industrial platforms is frequently encountered in our daily life. This study presents a specialized framework to retrieve user's queried product with its desired changes incorporated. To facilitate interaction between the end-user and agent in such scenarios, a multimodal content-based image retrieval system is essential. The system extracts textual and visual attributes, combining them through inductive learning to a unified representation. It is based on an in-depth understanding of visual characteristics that are modified by textual semantics. Lastly, a novel reverse reranking (RR) algorithm arranges the joint representation of dual modality queries and their corresponding target images for efficient retrieval. The proposed framework is novel compared to earlier methodologies. First, it achieves successful fusion of two different modalities. Second, it introduces a RR algorithm in the inference stage for efficient retrieval. The proposed framework's enhanced performance has been assessed using the Fashion-200 K and MIT-States real-world benchmark datasets. The proposed system can be used in real-world applications subject to its practical implications, such as generalization to diverse domains, availability of domain specific data, nature of the data and queries, and availability of computational resources.","PeriodicalId":52675,"journal":{"name":"IEEE Open Journal of the Industrial Electronics Society","volume":"5 ","pages":"886-897"},"PeriodicalIF":5.2,"publicationDate":"2024-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10614798","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141869132","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-30DOI: 10.1109/OJIES.2024.3435862
Ali Sharida;Abdullah Berkay Bayindir;Sertac Bayhan;Haitham Abu-Rub
Inverse model predictive control (IMPC) is a control technique that was recently proposed for power electronic converters. IMPC inherits the advantages of model predictive control (MPC) in terms of ability to handle complex and nonlinear systems and achieving multiple control objectives, while adhering to various constraints. Unlike MPC, IMPC offers a significantly reduced computational burden by omitting the iterative computations of the cost functions and states predictions. Nevertheless, both IMPC and MPC rely significantly on the dynamic model of the power converter. This makes them susceptible to uncertainties and disturbances. This article presents a novel technique to enhance the reliability and robustness of the IMPC for electric vehicle chargers by treating the converter's dynamic model as a black box. Then, an adaptive estimation strategy employing a recursive least square algorithm is proposed for online dynamic model estimation, which is then used by the IMPC for optimal switching states prediction. The key benefit of the proposed technique is the utilization of an accurate and real-time estimated dynamic model, which facilitates a reliable states prediction by the IMPC. The effectiveness of the proposed technique is demonstrated through extensive simulations and experimental validation for a three-phase three-level T-type rectifier.
{"title":"Enhanced Inverse Model Predictive Control for EV Chargers: Solution for Rectifier-Side","authors":"Ali Sharida;Abdullah Berkay Bayindir;Sertac Bayhan;Haitham Abu-Rub","doi":"10.1109/OJIES.2024.3435862","DOIUrl":"10.1109/OJIES.2024.3435862","url":null,"abstract":"Inverse model predictive control (IMPC) is a control technique that was recently proposed for power electronic converters. IMPC inherits the advantages of model predictive control (MPC) in terms of ability to handle complex and nonlinear systems and achieving multiple control objectives, while adhering to various constraints. Unlike MPC, IMPC offers a significantly reduced computational burden by omitting the iterative computations of the cost functions and states predictions. Nevertheless, both IMPC and MPC rely significantly on the dynamic model of the power converter. This makes them susceptible to uncertainties and disturbances. This article presents a novel technique to enhance the reliability and robustness of the IMPC for electric vehicle chargers by treating the converter's dynamic model as a black box. Then, an adaptive estimation strategy employing a recursive least square algorithm is proposed for online dynamic model estimation, which is then used by the IMPC for optimal switching states prediction. The key benefit of the proposed technique is the utilization of an accurate and real-time estimated dynamic model, which facilitates a reliable states prediction by the IMPC. The effectiveness of the proposed technique is demonstrated through extensive simulations and experimental validation for a three-phase three-level T-type rectifier.","PeriodicalId":52675,"journal":{"name":"IEEE Open Journal of the Industrial Electronics Society","volume":"5 ","pages":"795-806"},"PeriodicalIF":5.2,"publicationDate":"2024-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10614823","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141869136","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-29DOI: 10.1109/OJIES.2024.3434442
Ignacio Álvarez-Gariburo;Héctor Sarnago;José M. Burdío;Oscar Lucia
In a multitude of industrial and biomedical applications, the need for arbitrary waveform generators is essential, serving the purpose of load characterization and excitation, among others. Historically, these generators have had limitations in terms of voltage, current, and frequency output, primarily related with constraints associated with the power devices and circuit topologies. However, notable advancements in semiconductor technology have introduced a new era, enabling the creation of highly versatile waveform generators capable of superior performance, and extended operational capabilities. In this article, a versatile AWG based on switched modules is proposed. In contrast to the previous ones, whose implementation was based on linear amplifiers, it enables arbitrary waveform generation, higher efficiency, and very low output impedance. In addition, it is also presented as a novelty that the voltage in each of the modules is different, following a digital to analog converter (DAC) structure, which allows us to obtain a lower total harmonic distortion (THD) in the output waveform than with conventional methods. The design will take advantage of wide band gap devices to be able to switch in the MHz range to achieve a high bandwidth. Furthermore, in addition to the design and implementation of a high-performance generator, a comparative analysis between the conventional and the proposed DAC-based modulation pattern is performed based on a comparative analysis of the THD and switching losses.
{"title":"A Versatile Switched-Mode Large-Signal GaN-Based Low-Distortion Arbitrary Waveform Generator","authors":"Ignacio Álvarez-Gariburo;Héctor Sarnago;José M. Burdío;Oscar Lucia","doi":"10.1109/OJIES.2024.3434442","DOIUrl":"10.1109/OJIES.2024.3434442","url":null,"abstract":"In a multitude of industrial and biomedical applications, the need for arbitrary waveform generators is essential, serving the purpose of load characterization and excitation, among others. Historically, these generators have had limitations in terms of voltage, current, and frequency output, primarily related with constraints associated with the power devices and circuit topologies. However, notable advancements in semiconductor technology have introduced a new era, enabling the creation of highly versatile waveform generators capable of superior performance, and extended operational capabilities. In this article, a versatile AWG based on switched modules is proposed. In contrast to the previous ones, whose implementation was based on linear amplifiers, it enables arbitrary waveform generation, higher efficiency, and very low output impedance. In addition, it is also presented as a novelty that the voltage in each of the modules is different, following a digital to analog converter (DAC) structure, which allows us to obtain a lower total harmonic distortion (THD) in the output waveform than with conventional methods. The design will take advantage of wide band gap devices to be able to switch in the MHz range to achieve a high bandwidth. Furthermore, in addition to the design and implementation of a high-performance generator, a comparative analysis between the conventional and the proposed DAC-based modulation pattern is performed based on a comparative analysis of the THD and switching losses.","PeriodicalId":52675,"journal":{"name":"IEEE Open Journal of the Industrial Electronics Society","volume":"5 ","pages":"769-780"},"PeriodicalIF":5.2,"publicationDate":"2024-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10613446","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141869135","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-26DOI: 10.1109/OJIES.2024.3434341
Ali Dabbous;Riccardo Berta;Matteo Fresta;Hadi Ballout;Luca Lazzaroni;Francesco Bellotti
Structural health monitoring (SHM) is key in civil engineering because of the importance and the aging of the infrastructure. We argue that applying leading-edge, data-driven methods of large-scale complex industrial systems may be beneficial, particularly for accuracy and responsiveness. A fundamental step concerns the identification of the best tools to extract meaningful information from the vibrational raw signals. To this end, we study the application of two convolutional neural network architectures that have emerged in the literature for efficient feature extraction from time series, namely WaveNet and MINImally RandOm Convolutional KErnel Transform (MiniRocket). The test bench is the Z24 bridge progressive damage test classification dataset. Results show that a model based on WaveNet reaches state-of-the-art performance, also reducing model size and computational complexity. WaveNet proves perfectly suited to interpret the bridge vibration waveforms directly in the time domain, without any specific preprocessing. On the other hand, MiniRocket excels for ease of configuration (only two hyperparameters are to be tweaked), overall training efficiency, and model size, lending itself as a valuable agile alternative (e.g., for rapid prototyping). Our main advancement is, thus, the identification and characterization of highly effective feature extraction methods, employable in different SHM tasks. We have assessed the performance of the models on two embedded platforms, proposing a smart sensor system where a local hub collects the signals from a constellation of inertial sensors and infers damage assessment onsite, allowing the bridge to self-assess its health state without resorting to connectivity nor cloud resources.
{"title":"Bringing Intelligence to the Edge for Structural Health Monitoring: The Case Study of the Z24 Bridge","authors":"Ali Dabbous;Riccardo Berta;Matteo Fresta;Hadi Ballout;Luca Lazzaroni;Francesco Bellotti","doi":"10.1109/OJIES.2024.3434341","DOIUrl":"10.1109/OJIES.2024.3434341","url":null,"abstract":"Structural health monitoring (SHM) is key in civil engineering because of the importance and the aging of the infrastructure. We argue that applying leading-edge, data-driven methods of large-scale complex industrial systems may be beneficial, particularly for accuracy and responsiveness. A fundamental step concerns the identification of the best tools to extract meaningful information from the vibrational raw signals. To this end, we study the application of two convolutional neural network architectures that have emerged in the literature for efficient feature extraction from time series, namely WaveNet and MINImally RandOm Convolutional KErnel Transform (MiniRocket). The test bench is the Z24 bridge progressive damage test classification dataset. Results show that a model based on WaveNet reaches state-of-the-art performance, also reducing model size and computational complexity. WaveNet proves perfectly suited to interpret the bridge vibration waveforms directly in the time domain, without any specific preprocessing. On the other hand, MiniRocket excels for ease of configuration (only two hyperparameters are to be tweaked), overall training efficiency, and model size, lending itself as a valuable agile alternative (e.g., for rapid prototyping). Our main advancement is, thus, the identification and characterization of highly effective feature extraction methods, employable in different SHM tasks. We have assessed the performance of the models on two embedded platforms, proposing a smart sensor system where a local hub collects the signals from a constellation of inertial sensors and infers damage assessment onsite, allowing the bridge to self-assess its health state without resorting to connectivity nor cloud resources.","PeriodicalId":52675,"journal":{"name":"IEEE Open Journal of the Industrial Electronics Society","volume":"5 ","pages":"781-794"},"PeriodicalIF":5.2,"publicationDate":"2024-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10612214","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141770226","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The active neutral-point-clamped five-level converter has drawn much attention in industrial applications. However, common-mode voltage (CMV) suppression, accurate track current, fixed switching frequencies, neutral-point (NP) voltage balance, and flying capacitor (FC) voltage are compulsory in this configuration. Thus, an improved multiobjective model-predictive control (IMMPC) without weighting factors is proposed in this article. First, to suppress CMV, only 61 low-CMV vectors out of 125 vectors were selected. Second, to ensure current tracking performance and reduce computational burden, based on the gh oblique coordinate, three voltage vectors were calculated online in each control period, which can avoid lookup tables. Third, the optimal switching sequence and duty cycles were presented considering the lowest switching numbers and constant switching frequency. A high-quality current was thus obtained, and the NP voltage and the FC voltage were balanced by selecting switching combinations. The IMMPC can be applied to other multilevel converters for current tracking and CMV suppression with a simple adjustment on parameters. Finally, the feasibility and the effectiveness of the proposed method were verified through simulations and experiments.
{"title":"An Improved Multiobjective Model-Predictive Control Method for Active Neutral-Point-Clamped Five-Level Converter","authors":"Qiguang Ren;Chang Liu;Xiangyang Xing;Rui Zhang;Chenghui Zhang","doi":"10.1109/OJIES.2024.3431083","DOIUrl":"10.1109/OJIES.2024.3431083","url":null,"abstract":"The active neutral-point-clamped five-level converter has drawn much attention in industrial applications. However, common-mode voltage (CMV) suppression, accurate track current, fixed switching frequencies, neutral-point (NP) voltage balance, and flying capacitor (FC) voltage are compulsory in this configuration. Thus, an improved multiobjective model-predictive control (IMMPC) without weighting factors is proposed in this article. First, to suppress CMV, only 61 low-CMV vectors out of 125 vectors were selected. Second, to ensure current tracking performance and reduce computational burden, based on the \u0000<italic>gh</i>\u0000 oblique coordinate, three voltage vectors were calculated online in each control period, which can avoid lookup tables. Third, the optimal switching sequence and duty cycles were presented considering the lowest switching numbers and constant switching frequency. A high-quality current was thus obtained, and the NP voltage and the FC voltage were balanced by selecting switching combinations. The IMMPC can be applied to other multilevel converters for current tracking and CMV suppression with a simple adjustment on parameters. Finally, the feasibility and the effectiveness of the proposed method were verified through simulations and experiments.","PeriodicalId":52675,"journal":{"name":"IEEE Open Journal of the Industrial Electronics Society","volume":"5 ","pages":"1158-1173"},"PeriodicalIF":5.2,"publicationDate":"2024-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10605032","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141744176","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The emergence of Industry 4.0 (I4.0) has significantly transformed manufacturing landscapes, introducing interconnected, dynamic, and data-rich environments. This article focuses on the application of industrial machine learning (I-ML) within these evolving manufacturing contexts, exploring both the challenges and future prospects of its integration. A systematic literature review, following the preferred reporting items for systematic reviews and meta-analyzes (PRISMA) guidelines, forms the foundation of our analysis, characterizing the role of machine learning (ML) in modern manufacturing, its current challenges, and future trends. This research delves into the implications of I-ML in various manufacturing scenarios, including predictive maintenance, anomaly detection, and quality control, providing a comprehensive overview of practical applications along with an identification of related emerging technologies and trends. We also address the critical need for sustainable, reproducible, and reliable performance in industrial applications and explore strategies for overcoming barriers to ML adoption in the industry. Recommendations for future research directions are provided, aiming to bridge the gap between ML advancements and their practical, scalable implementation in industrial settings, paving the way to future research in the field. Lastly, we aim to contribute to the identification of challenges and future research directions for the ongoing digital transformation of manufacturing industries, offering insights into how ML can be effectively leveraged in the era of I4.0.
工业 4.0（I4.0）的出现极大地改变了制造业的面貌，引入了互联、动态和数据丰富的环境。本文重点关注工业机器学习（I-ML）在这些不断发展的制造业环境中的应用，探讨其整合所面临的挑战和未来前景。按照系统性综述和荟萃分析（PRISMA）指南的首选报告项目进行的系统性文献综述构成了我们分析的基础，描述了机器学习（ML）在现代制造业中的作用、当前挑战和未来趋势。这项研究深入探讨了 I-ML 在各种制造场景中的影响，包括预测性维护、异常检测和质量控制，对实际应用进行了全面概述，并确定了相关的新兴技术和趋势。我们还探讨了工业应用中对可持续、可重现和可靠性能的迫切需求，并探索了克服行业中采用智能物流障碍的策略。我们对未来的研究方向提出了建议，旨在弥合 ML 进步与其在工业环境中的实际可扩展实施之间的差距，为该领域的未来研究铺平道路。最后，我们旨在为制造业正在进行的数字化转型确定挑战和未来研究方向做出贡献，为如何在 I4.0 时代有效利用 ML 提供见解。
{"title":"Machine Learning Applications in Manufacturing—Challenges, Trends, and Future Directions","authors":"Alexandre Manta-Costa;Sara Oleiro Araújo;Ricardo Silva Peres;José Barata","doi":"10.1109/OJIES.2024.3431240","DOIUrl":"10.1109/OJIES.2024.3431240","url":null,"abstract":"The emergence of Industry 4.0 (I4.0) has significantly transformed manufacturing landscapes, introducing interconnected, dynamic, and data-rich environments. This article focuses on the application of industrial machine learning (I-ML) within these evolving manufacturing contexts, exploring both the challenges and future prospects of its integration. A systematic literature review, following the preferred reporting items for systematic reviews and meta-analyzes (PRISMA) guidelines, forms the foundation of our analysis, characterizing the role of machine learning (ML) in modern manufacturing, its current challenges, and future trends. This research delves into the implications of I-ML in various manufacturing scenarios, including predictive maintenance, anomaly detection, and quality control, providing a comprehensive overview of practical applications along with an identification of related emerging technologies and trends. We also address the critical need for sustainable, reproducible, and reliable performance in industrial applications and explore strategies for overcoming barriers to ML adoption in the industry. Recommendations for future research directions are provided, aiming to bridge the gap between ML advancements and their practical, scalable implementation in industrial settings, paving the way to future research in the field. Lastly, we aim to contribute to the identification of challenges and future research directions for the ongoing digital transformation of manufacturing industries, offering insights into how ML can be effectively leveraged in the era of I4.0.","PeriodicalId":52675,"journal":{"name":"IEEE Open Journal of the Industrial Electronics Society","volume":"5 ","pages":"1085-1103"},"PeriodicalIF":5.2,"publicationDate":"2024-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10605047","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141744181","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-11DOI: 10.1109/OJIES.2024.3426662
Yangyang Chen;Wei Han;Youhao Hu;Yilin Zhang
As renewable energy continues to grow, more inverter-based distributed generators are being integrated into power grids, in which virtual synchronous generator (VSG) is widely adopted to regulate system voltage and stabilize frequency. However, grid voltage imbalances can cause serious oscillations in active power and system frequency, thus severely limiting the effectiveness of VSGs. Consequently, this study proposes an adaptive control strategy to enhance the dynamic performance of VSG under an imbalanced grid voltage. Compared to conventional VSG control methods, the proposed approach enables dynamic adjustment of the inertia and damping coefficients based on the output angular frequency oscillations, so as to shorten the settling time and reduce active power overshoot. The error-driven adaptive mechanism forms a closed-loop control, which effectively keeps the system stable regardless of parameter variations. Additionally, it combines with balanced output current (BOC), constant active power (CAP), and constant reactive power (CRP) control modes to further improve effectiveness. Finally, verifications have been conducted in the MATLAB/SIMULINK and hardware-in-the-loop (HIL) environment to demonstrate the superiority and feasibility of the proposed method.
{"title":"Adaptive Control for Improved Virtual Synchronous Generator Under Imbalanced Grid Voltage","authors":"Yangyang Chen;Wei Han;Youhao Hu;Yilin Zhang","doi":"10.1109/OJIES.2024.3426662","DOIUrl":"10.1109/OJIES.2024.3426662","url":null,"abstract":"As renewable energy continues to grow, more inverter-based distributed generators are being integrated into power grids, in which virtual synchronous generator (VSG) is widely adopted to regulate system voltage and stabilize frequency. However, grid voltage imbalances can cause serious oscillations in active power and system frequency, thus severely limiting the effectiveness of VSGs. Consequently, this study proposes an adaptive control strategy to enhance the dynamic performance of VSG under an imbalanced grid voltage. Compared to conventional VSG control methods, the proposed approach enables dynamic adjustment of the inertia and damping coefficients based on the output angular frequency oscillations, so as to shorten the settling time and reduce active power overshoot. The error-driven adaptive mechanism forms a closed-loop control, which effectively keeps the system stable regardless of parameter variations. Additionally, it combines with balanced output current (BOC), constant active power (CAP), and constant reactive power (CRP) control modes to further improve effectiveness. Finally, verifications have been conducted in the MATLAB/SIMULINK and hardware-in-the-loop (HIL) environment to demonstrate the superiority and feasibility of the proposed method.","PeriodicalId":52675,"journal":{"name":"IEEE Open Journal of the Industrial Electronics Society","volume":"5 ","pages":"722-736"},"PeriodicalIF":5.2,"publicationDate":"2024-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10595133","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141609699","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-10DOI: 10.1109/OJIES.2024.3425934
Lukas Peter Wagner;Alexander Fay
The increasing share of renewable energy generation poses a challenge to maintaining the adequacy of power generation and demand. Planning the operation of flexible energy resources helps stabilize this balance. Optimization models are needed for operation planning. The use of a predefined and validated optimization model avoids modeling errors, but parameterization is still necessary and error-prone. This work presents a methodology for determining parameters of optimization models for various kinds of flexible energy resources. The parameters are derived from time series data of the resource operation after preprocessing. This methodology includes algorithms for determining operational boundaries, the input–output relationship, system states, and parameters for storage systems. Connections of flows between individual resources within a system are extracted from a standardized information model. A case study of a combined heat and power system demonstrates the applicability of the methodology by deriving a set of parameters from time series data and an information model of the system's structure. The model parameterized by means of the methodology shows very good alignment with a validation time series data set with a normalized root mean square error of 1% (generator), respectively, of 6% (heat exchanger).
{"title":"Methodology for Deriving Parameters for Optimization Models of Systems of Flexible Energy Resources","authors":"Lukas Peter Wagner;Alexander Fay","doi":"10.1109/OJIES.2024.3425934","DOIUrl":"10.1109/OJIES.2024.3425934","url":null,"abstract":"The increasing share of renewable energy generation poses a challenge to maintaining the adequacy of power generation and demand. Planning the operation of flexible energy resources helps stabilize this balance. Optimization models are needed for operation planning. The use of a predefined and validated optimization model avoids modeling errors, but parameterization is still necessary and error-prone. This work presents a methodology for determining parameters of optimization models for various kinds of flexible energy resources. The parameters are derived from time series data of the resource operation after preprocessing. This methodology includes algorithms for determining operational boundaries, the input–output relationship, system states, and parameters for storage systems. Connections of flows between individual resources within a system are extracted from a standardized information model. A case study of a combined heat and power system demonstrates the applicability of the methodology by deriving a set of parameters from time series data and an information model of the system's structure. The model parameterized by means of the methodology shows very good alignment with a validation time series data set with a normalized root mean square error of 1% (generator), respectively, of 6% (heat exchanger).","PeriodicalId":52675,"journal":{"name":"IEEE Open Journal of the Industrial Electronics Society","volume":"5 ","pages":"737-757"},"PeriodicalIF":5.2,"publicationDate":"2024-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10592623","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141587889","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：