Pub Date : 2024-10-31DOI: 10.1016/j.compeleceng.2024.109823
Jun-Hyeok Kim
This study proposes and validates an artificial intelligence (AI)-based method for estimating the water content in the insulating oil of distribution-level transformers. The methodology includes data augmentation using noise addition, outlier removal via Isolation Forest, and data normalization through square root transformation. A Random Forest (RF) model is developed to estimate water content based on the usage period of the transformer. Correlation analyses identified the usage period as the key variable affecting water content. The model demonstrated high estimation accuracy with an R-squared value of 0.83, closely aligning estimated values with measured data. This approach provides a practical solution for real-world applications, expanding the focus to distribution-level transformers and ensuring reliable estimations through validation with actual field data. Despite limitations due to a dataset comprising 100 samples of transformer usage and oil analysis data, the method shows promise for accurate transformer lifespan assessment and efficient asset management. Future research will enhance model performance by incorporating diverse environmental conditions and comparative analyses with other machine learning (ML) algorithms, aiming to optimize estimation reliability and safety for distribution-level transformers. Consistency in the methodology description and actual models used will be maintained to avoid discrepancies.
{"title":"A study on the water content in distribution pole transformer using random forest model","authors":"Jun-Hyeok Kim","doi":"10.1016/j.compeleceng.2024.109823","DOIUrl":"10.1016/j.compeleceng.2024.109823","url":null,"abstract":"<div><div>This study proposes and validates an artificial intelligence (AI)-based method for estimating the water content in the insulating oil of distribution-level transformers. The methodology includes data augmentation using noise addition, outlier removal via Isolation Forest, and data normalization through square root transformation. A Random Forest (RF) model is developed to estimate water content based on the usage period of the transformer. Correlation analyses identified the usage period as the key variable affecting water content. The model demonstrated high estimation accuracy with an R-squared value of 0.83, closely aligning estimated values with measured data. This approach provides a practical solution for real-world applications, expanding the focus to distribution-level transformers and ensuring reliable estimations through validation with actual field data. Despite limitations due to a dataset comprising 100 samples of transformer usage and oil analysis data, the method shows promise for accurate transformer lifespan assessment and efficient asset management. Future research will enhance model performance by incorporating diverse environmental conditions and comparative analyses with other machine learning (ML) algorithms, aiming to optimize estimation reliability and safety for distribution-level transformers. Consistency in the methodology description and actual models used will be maintained to avoid discrepancies.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"120 ","pages":"Article 109823"},"PeriodicalIF":4.0,"publicationDate":"2024-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142561223","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-31DOI: 10.1016/j.compeleceng.2024.109830
Iman Firmansyah , Bambang Setiadi , Agus Subekti , Heri Nugraha , Edi Kurniawan , Yoshiki Yamaguchi
The increasing demand for real-time data processing in Internet of Things (IoT) applications necessitates the development of efficient and flexible data acquisition systems capable of receiving and processing data from various sensor types. In conjunction with OpenCL, field-programmable gate arrays (FPGAs) have recently emerged as powerful platforms for accelerating data-intensive tasks. This study explored the implementation of an FPGA for data acquisition using OpenCL, aiming to design and implement an efficient data acquisition system tailored for IoT applications. Utilizing OpenCL for FPGA-based data acquisition offers several advantages that contribute to system efficiency, particularly in hardware interfaces between FPGA and external devices used in IoT applications. OpenCL abstracts the complexity of the FPGA hardware interface to external DDR memory for storing temporary data and a communication interface to the host CPU for transferring the collected data and enabling remote access, enabling developers to focus on algorithm design and functionality. To enable data reading from an external analog-to-digital converter (ADC) chip for IoT applications, we developed a component module that utilizes the Avalon-streaming interface and can stream the data to the OpenCL kernel. An experiment was conducted to demonstrate the performance of our proposed design. According to the findings of the experiments, a data acquisition implementation based on an FPGA and OpenCL can simultaneously read analog signals via a multichannel ADC. The proposed design provides a foundation for designing efficient data acquisition solutions, addressing the increasing needs of FPGA-based data acquisition in various IoT environments.
{"title":"Enhancing IoT data acquisition efficiency via FPGA-based implementation with OpenCL framework","authors":"Iman Firmansyah , Bambang Setiadi , Agus Subekti , Heri Nugraha , Edi Kurniawan , Yoshiki Yamaguchi","doi":"10.1016/j.compeleceng.2024.109830","DOIUrl":"10.1016/j.compeleceng.2024.109830","url":null,"abstract":"<div><div>The increasing demand for real-time data processing in Internet of Things (IoT) applications necessitates the development of efficient and flexible data acquisition systems capable of receiving and processing data from various sensor types. In conjunction with OpenCL, field-programmable gate arrays (FPGAs) have recently emerged as powerful platforms for accelerating data-intensive tasks. This study explored the implementation of an FPGA for data acquisition using OpenCL, aiming to design and implement an efficient data acquisition system tailored for IoT applications. Utilizing OpenCL for FPGA-based data acquisition offers several advantages that contribute to system efficiency, particularly in hardware interfaces between FPGA and external devices used in IoT applications. OpenCL abstracts the complexity of the FPGA hardware interface to external DDR memory for storing temporary data and a communication interface to the host CPU for transferring the collected data and enabling remote access, enabling developers to focus on algorithm design and functionality. To enable data reading from an external analog-to-digital converter (ADC) chip for IoT applications, we developed a component module that utilizes the Avalon-streaming interface and can stream the data to the OpenCL kernel. An experiment was conducted to demonstrate the performance of our proposed design. According to the findings of the experiments, a data acquisition implementation based on an FPGA and OpenCL can simultaneously read analog signals via a multichannel ADC. The proposed design provides a foundation for designing efficient data acquisition solutions, addressing the increasing needs of FPGA-based data acquisition in various IoT environments.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"120 ","pages":"Article 109830"},"PeriodicalIF":4.0,"publicationDate":"2024-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142561222","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-31DOI: 10.1016/j.compeleceng.2024.109841
Hesam addin Yousefian, Abolfazl Jalilvand, Amir Bagheri
The climatic circumstances of the world have altered due to the world warming up, and this issue has increased high-impact and low-probability (HILP) events more than before. Supplying energy requirements has turned into one of the main challenges of utilities especially electrical distribution companies considering the frequency and intensity of HILP events. On the other hand, developments in storing electricity have varied expectations and will change the solutions leading to resilient electrical distribution networks (EDNs). Some researchers have studied and analyzed numerous aspects of resilient EDNs but hybridization of different types of energy storage systems (ESSs) has not evaluated before. This paper considers energy management of emergency-operated EDNs equipped with two different types of energy storage systems which are batteries and flywheels. Convex equations in all parts of the problem, including different types of energy storage systems are proposed and modeled as an MIQCP to optimize the resilient networks considering all limitations. The proposed framework is developed in GAMS software and the results are provided in the form of Pareto optimal solutions. Applicability of the conducted model is evaluated by the IEEE 33-bus test system aiming at outstanding the effects of flywheels in improving the resiliency of electrical distribution networks. The proposed model analyzed by various energy storing scenarios based on technical and economical limitations. Results showed that among the considered case studies, the 50 % of the cases included with flywheel while batteries participated in 30 % that were the most expensive ones. On the other hand, the lowest amount of objective function belongs to the case that is only included with flywheels. Accordingly, by considering flywheels as a newly born energy storage system in the emergency-operated EDNs, the flexibility of energy management is facilitated and can be developed economically.
{"title":"Multi-type energy conversion for managing the consumption by enhancing the resiliency of electrical distribution networks","authors":"Hesam addin Yousefian, Abolfazl Jalilvand, Amir Bagheri","doi":"10.1016/j.compeleceng.2024.109841","DOIUrl":"10.1016/j.compeleceng.2024.109841","url":null,"abstract":"<div><div>The climatic circumstances of the world have altered due to the world warming up, and this issue has increased high-impact and low-probability (HILP) events more than before. Supplying energy requirements has turned into one of the main challenges of utilities especially electrical distribution companies considering the frequency and intensity of HILP events. On the other hand, developments in storing electricity have varied expectations and will change the solutions leading to resilient electrical distribution networks (EDNs). Some researchers have studied and analyzed numerous aspects of resilient EDNs but hybridization of different types of energy storage systems (ESSs) has not evaluated before. This paper considers energy management of emergency-operated EDNs equipped with two different types of energy storage systems which are batteries and flywheels. Convex equations in all parts of the problem, including different types of energy storage systems are proposed and modeled as an MIQCP to optimize the resilient networks considering all limitations. The proposed framework is developed in GAMS software and the results are provided in the form of Pareto optimal solutions. Applicability of the conducted model is evaluated by the IEEE 33-bus test system aiming at outstanding the effects of flywheels in improving the resiliency of electrical distribution networks. The proposed model analyzed by various energy storing scenarios based on technical and economical limitations. Results showed that among the considered case studies, the 50 % of the cases included with flywheel while batteries participated in 30 % that were the most expensive ones. On the other hand, the lowest amount of objective function belongs to the case that is only included with flywheels. Accordingly, by considering flywheels as a newly born energy storage system in the emergency-operated EDNs, the flexibility of energy management is facilitated and can be developed economically.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"120 ","pages":"Article 109841"},"PeriodicalIF":4.0,"publicationDate":"2024-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142561221","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-30DOI: 10.1016/j.compeleceng.2024.109786
Rohit Beniwal, Pavi Saraswat
Due to the psychological strain that depression causes, there has been a noticeable increase in the number of persons compromising their lives in recent years. Social media platforms provide researchers with an entirely novel viewpoint on identifying individuals who are depressed. Previous research on automatic learning models for depression detection revealed low detection accuracy and an absence of optimizing techniques that could enhance detection accuracy. Furthermore, there is no such dataset, and very little study has been done on the multimodal pure Hindi and code-mixed Hinglish language domains. In light of this, we developed a Hindi dataset and suggested reliable methods for depression detection based on multimodal data, i.e., text and images, using the Hindi and Hinglish languages. This study aims to accomplish three things: first, it will evaluate text data using an effective Bidirectional Encoder Representations from Transformers (BERT) approach and compare it with other transfer learning variants; second, it will analyze image data by suggesting a Convolutional Neural Network (CNN) optimized with a nature-inspired algorithm, namely Particle Swarm Optimization (PSO), or CPSO; and third, it will classify the multimodal data into depressive and non-depressive posts by suggesting a hybrid of the best-performing models on text and images, namely BERT-CPSO (BTCPSO). The results produced with the BERT model showed the best accuracy of 95% for text data, in contrast to RoBERTa, DistilBERT, and XLNet. Further, CPSO outperforms other Machine Learning (ML) and Deep Learning (DL) algorithms for image data with an accuracy of 95%. Additionally, comparing the proposed CPSO with a basic CNN revealed that integrating the PSO technique with CNN increased the model's accuracy in detecting depressed posts by 5%. In conclusion, hybrid BERT-CPSO outperforms other BERT combinations with ML and DL algorithms for multimodal data, achieving 97%, 95%, 98%, and 96%, respectively, in accuracy, recall, precision, and F1-scores. As a result, the findings of comparing the suggested technique with the earlier models show the effectiveness of the approach that has been provided and can help medical professionals diagnose depression with precision.
{"title":"A hybrid BERT-CPSO model for multi-class depression detection using pure hindi and hinglish multimodal data on social media","authors":"Rohit Beniwal, Pavi Saraswat","doi":"10.1016/j.compeleceng.2024.109786","DOIUrl":"10.1016/j.compeleceng.2024.109786","url":null,"abstract":"<div><div>Due to the psychological strain that depression causes, there has been a noticeable increase in the number of persons compromising their lives in recent years. Social media platforms provide researchers with an entirely novel viewpoint on identifying individuals who are depressed. Previous research on automatic learning models for depression detection revealed low detection accuracy and an absence of optimizing techniques that could enhance detection accuracy. Furthermore, there is no such dataset, and very little study has been done on the multimodal pure Hindi and code-mixed Hinglish language domains. In light of this, we developed a Hindi dataset and suggested reliable methods for depression detection based on multimodal data, i.e., text and images, using the Hindi and Hinglish languages. This study aims to accomplish three things: first, it will evaluate text data using an effective Bidirectional Encoder Representations from Transformers (BERT) approach and compare it with other transfer learning variants; second, it will analyze image data by suggesting a Convolutional Neural Network (CNN) optimized with a nature-inspired algorithm, namely Particle Swarm Optimization (PSO), or CPSO; and third, it will classify the multimodal data into depressive and non-depressive posts by suggesting a hybrid of the best-performing models on text and images, namely BERT-CPSO (BTCPSO). The results produced with the BERT model showed the best accuracy of 95% for text data, in contrast to RoBERTa, DistilBERT, and XLNet. Further, CPSO outperforms other Machine Learning (ML) and Deep Learning (DL) algorithms for image data with an accuracy of 95%. Additionally, comparing the proposed CPSO with a basic CNN revealed that integrating the PSO technique with CNN increased the model's accuracy in detecting depressed posts by 5%. In conclusion, hybrid BERT-CPSO outperforms other BERT combinations with ML and DL algorithms for multimodal data, achieving 97%, 95%, 98%, and 96%, respectively, in accuracy, recall, precision, and F1-scores. As a result, the findings of comparing the suggested technique with the earlier models show the effectiveness of the approach that has been provided and can help medical professionals diagnose depression with precision.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"120 ","pages":"Article 109786"},"PeriodicalIF":4.0,"publicationDate":"2024-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142552125","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-30DOI: 10.1016/j.compeleceng.2024.109821
Rui Fei, Jianwen Cui
This study presents a cooperative paradigm for energy hub systems (EHSs) where a network of interconnected hubs cooperates in exploiting the resources with the purpose of economic saving. In such an architecture, each hub provided with various sources of energy, such as combined heat and power (CHP), hot water tanks, renewable sources, electric chillers, and absorption chillers, will integrate all these sources for more adaptability and efficiency to the system. Moreover, the integration of energy storage systems (ESSs) is considered to enhance the flexibility of the energy hub concerning power, heating, and cooling. Recognizing the complexity associated with incorporating multiple constraints, the improved grasshopper optimization algorithm (IGOA) is introduced to effectively address this challenge. By leveraging this algorithm, the study aims to overcome the intricacies involved in considering various constraints and achieve an optimal outcome. The IGOA improves the efficiency and effectiveness of local and national searches in solving complex energy hub optimization problems. Reducing the likelihood of getting stuck in suboptimal solutions, enhances the algorithm's ability to find optimal solutions considering multiple constraints, thereby enhancing the overall performance and cost-effectiveness of EHSs. The issue is defined as a planning challenge, and by collaborative efforts, the expenses associated with the network energy hubs are reduced, illustrating the efficacy of this concept. The findings indicate the influence of the suggested cooperative technique, with operating cost reductions of 19.09 %, 13.27 %, and 8.75 % for Hub 1, Hub 2, and Hub 3, respectively. Furthermore, the cooperative framework eradicates energy deficits and disruptions, in contrast to 1,198.21 kWh of unfulfilled demand and 22 interruptions in the non-cooperative scenario. These results underscore the significant advantages of the collaborative technique in improving cost-efficiency, reliability, and resource utilization.
{"title":"Cooperative resource sharing and cost minimization in energy hub systems using an improved grasshopper optimization algorithm approach","authors":"Rui Fei, Jianwen Cui","doi":"10.1016/j.compeleceng.2024.109821","DOIUrl":"10.1016/j.compeleceng.2024.109821","url":null,"abstract":"<div><div>This study presents a cooperative paradigm for energy hub systems (EHSs) where a network of interconnected hubs cooperates in exploiting the resources with the purpose of economic saving. In such an architecture, each hub provided with various sources of energy, such as combined heat and power (CHP), hot water tanks, renewable sources, electric chillers, and absorption chillers, will integrate all these sources for more adaptability and efficiency to the system. Moreover, the integration of energy storage systems (ESSs) is considered to enhance the flexibility of the energy hub concerning power, heating, and cooling. Recognizing the complexity associated with incorporating multiple constraints, the improved grasshopper optimization algorithm (IGOA) is introduced to effectively address this challenge. By leveraging this algorithm, the study aims to overcome the intricacies involved in considering various constraints and achieve an optimal outcome. The IGOA improves the efficiency and effectiveness of local and national searches in solving complex energy hub optimization problems. Reducing the likelihood of getting stuck in suboptimal solutions, enhances the algorithm's ability to find optimal solutions considering multiple constraints, thereby enhancing the overall performance and cost-effectiveness of EHSs. The issue is defined as a planning challenge, and by collaborative efforts, the expenses associated with the network energy hubs are reduced, illustrating the efficacy of this concept. The findings indicate the influence of the suggested cooperative technique, with operating cost reductions of 19.09 %, 13.27 %, and 8.75 % for Hub 1, Hub 2, and Hub 3, respectively. Furthermore, the cooperative framework eradicates energy deficits and disruptions, in contrast to 1,198.21 kWh of unfulfilled demand and 22 interruptions in the non-cooperative scenario. These results underscore the significant advantages of the collaborative technique in improving cost-efficiency, reliability, and resource utilization.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"120 ","pages":"Article 109821"},"PeriodicalIF":4.0,"publicationDate":"2024-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142552026","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-30DOI: 10.1016/j.compeleceng.2024.109714
Liang Ning
Distributed generation sources provide self-governing power during outages, making microgrids and islanded distribution networks vital for service endurance, superior power quality, reliability, and operative efficiency. However, microgrids structure are difficult to control, particularly in islanded mode where no main power source exists if the main grid fails. Fast responses from discrete generation sources using power electronics can undermine the grid during faults or normal operations without proper regulations. The double-fed induction generator (DFIG) has become the preferred wind turbine generator owing to its low cost and flexibility to varying wind speeds. This paper presents a probabilistic scheduling for day-ahead microgrid programming that includes EV parking lots and dispersed generation resources. The microgrid works in both normal and islanded modes depending on main grid conditions. The uncertainty in EV parking lot usage is modeled hourly using the Z-number method, while wind and solar generation, market prices, and loads are modeled using the Monte Carlo method. Scenario-based incidents in the upstream grid that lead to microgrid islanding are considered, focusing on the time and duration of impact. The optimization model accounts for uncertainty, EV charging/discharging, and operational costs under normal and fault conditions. The fault ride-through (FRT) method for maintaining DFIG stability in islanded microgrids are proposed. In this technique stabilizes terminal voltage during faults by employing a resistor in series with the DFIG stator, enhancing voltage stability and FRT capability. Without these methods, the DFIG may lose stability after clearing transient errors, risking generator loss and threatening microgrid stability, particularly in islanded mode. The effectiveness of these control and protection strategies is validated through comprehensive simulations in MATLAB.
分布式发电在停电期间提供自我管理的电力，这使得微电网和孤岛式配电网络对服务的持久性、卓越的电能质量、可靠性和运行效率至关重要。然而，微电网结构难以控制，特别是在孤岛模式下，如果主电网发生故障，就不存在主电源。在故障或正常运行期间，如果没有适当的规定，使用电力电子设备的离散发电源的快速反应可能会破坏电网。双馈异步发电机（DFIG）因其低成本和适应不同风速的灵活性，已成为风力涡轮发电机的首选。本文介绍了一种用于日前微电网编程的概率调度方法，其中包括电动汽车停车场和分散的发电资源。根据主电网条件，微电网可在正常模式和孤岛模式下工作。电动汽车停车场使用情况的不确定性采用 Z 数法按小时建模，而风能和太阳能发电、市场价格和负荷则采用蒙特卡罗法建模。考虑了上游电网中导致微电网孤岛的情景事件，重点关注影响的时间和持续时间。优化模型考虑了不确定性、电动汽车充电/放电以及正常和故障条件下的运营成本。提出了故障穿越（FRT）方法，用于维持孤岛微电网中 DFIG 的稳定性。该技术通过采用与双馈变流器定子串联的电阻器来稳定故障期间的终端电压，从而提高电压稳定性和故障穿越能力。如果不采用这些方法，DFIG 可能会在清除瞬态误差后失去稳定性，从而导致发电机损耗并威胁微电网的稳定性，尤其是在孤岛模式下。这些控制和保护策略的有效性通过 MATLAB 的全面仿真得到了验证。
{"title":"Probabilistic modeling and optimization of microgrids with EV parking lots and dispersed generation","authors":"Liang Ning","doi":"10.1016/j.compeleceng.2024.109714","DOIUrl":"10.1016/j.compeleceng.2024.109714","url":null,"abstract":"<div><div>Distributed generation sources provide self-governing power during outages, making microgrids and islanded distribution networks vital for service endurance, superior power quality, reliability, and operative efficiency. However, microgrids structure are difficult to control, particularly in islanded mode where no main power source exists if the main grid fails. Fast responses from discrete generation sources using power electronics can undermine the grid during faults or normal operations without proper regulations. The double-fed induction generator (DFIG) has become the preferred wind turbine generator owing to its low cost and flexibility to varying wind speeds. This paper presents a probabilistic scheduling for day-ahead microgrid programming that includes EV parking lots and dispersed generation resources. The microgrid works in both normal and islanded modes depending on main grid conditions. The uncertainty in EV parking lot usage is modeled hourly using the Z-number method, while wind and solar generation, market prices, and loads are modeled using the Monte Carlo method. Scenario-based incidents in the upstream grid that lead to microgrid islanding are considered, focusing on the time and duration of impact. The optimization model accounts for uncertainty, EV charging/discharging, and operational costs under normal and fault conditions. The fault ride-through (FRT) method for maintaining DFIG stability in islanded microgrids are proposed. In this technique stabilizes terminal voltage during faults by employing a resistor in series with the DFIG stator, enhancing voltage stability and FRT capability. Without these methods, the DFIG may lose stability after clearing transient errors, risking generator loss and threatening microgrid stability, particularly in islanded mode. The effectiveness of these control and protection strategies is validated through comprehensive simulations in MATLAB.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"120 ","pages":"Article 109714"},"PeriodicalIF":4.0,"publicationDate":"2024-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142552033","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-30DOI: 10.1016/j.compeleceng.2024.109813
Wenjie Wang , Gang Yuan , Duc Truong Pham , Honghao Zhang , Dekun Wang , Guangdong Tian
The well-accepted three-stage remanufacturing system scheduling aims to achieve intelligent and green remanufacturing by reasonably coordinating limited resources in the system involving disassembly, reprocessing, reassembly production stages. Currently, the lot-streaming production mode is increasingly favoured by scholars and enterprise managers due to its remarkable performance in reducing machines’ idle time and improving production efficiency. This paper investigates an energy-efficient scheduling issue for three-stage remanufacturing systems under the lot-streaming environment where each large-sized lot is split into its constituent small-sized sublots whose sizes may be inequal but remain consistent among various operations. Foremost, a dual-objective optimization mathematical model aiming at concurrently minimizing the makespan and total energy consumption is built. Then, since its NP-hard property, an improved fruit fly optimization (IFFO) algorithm is accordingly introduced. IFFO adopts a problem-specific three-layer encoding mechanism that contains three key pieces of scheduling information, i.e., lot sequence, machine assignment, and lot size splitting. Besides, based on the lot-streaming property, two distinct decoding strategies, i.e., sublot preemption and lot preemption are also correspondingly integrated. In addition, several effective optimization techniques, such as the simulated annealing-based replacement mechanism and Sigma method, are also employed to seek high-quality Pareto solutions. A real case and several designed random small/large-sized instances are tested on IFFO and its peers under three performance indicators. To obtain a convincing and solid conclusion, the Wilcoxon signed-rank statistical test is executed as well. The overall experimental results show that IFFO is feasible and effective in addressing the studied problem.
{"title":"Lot-streaming in energy-efficient three-stage remanufacturing system scheduling problem with inequal and consistent sublots","authors":"Wenjie Wang , Gang Yuan , Duc Truong Pham , Honghao Zhang , Dekun Wang , Guangdong Tian","doi":"10.1016/j.compeleceng.2024.109813","DOIUrl":"10.1016/j.compeleceng.2024.109813","url":null,"abstract":"<div><div>The well-accepted three-stage remanufacturing system scheduling aims to achieve intelligent and green remanufacturing by reasonably coordinating limited resources in the system involving disassembly, reprocessing, reassembly production stages. Currently, the lot-streaming production mode is increasingly favoured by scholars and enterprise managers due to its remarkable performance in reducing machines’ idle time and improving production efficiency. This paper investigates an energy-efficient scheduling issue for three-stage remanufacturing systems under the lot-streaming environment where each large-sized lot is split into its constituent small-sized sublots whose sizes may be inequal but remain consistent among various operations. Foremost, a dual-objective optimization mathematical model aiming at concurrently minimizing the makespan and total energy consumption is built. Then, since its NP-hard property, an improved fruit fly optimization (IFFO) algorithm is accordingly introduced. IFFO adopts a problem-specific three-layer encoding mechanism that contains three key pieces of scheduling information, i.e., lot sequence, machine assignment, and lot size splitting. Besides, based on the lot-streaming property, two distinct decoding strategies, i.e., sublot preemption and lot preemption are also correspondingly integrated. In addition, several effective optimization techniques, such as the simulated annealing-based replacement mechanism and Sigma method, are also employed to seek high-quality Pareto solutions. A real case and several designed random small/large-sized instances are tested on IFFO and its peers under three performance indicators. To obtain a convincing and solid conclusion, the Wilcoxon signed-rank statistical test is executed as well. The overall experimental results show that IFFO is feasible and effective in addressing the studied problem.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"120 ","pages":"Article 109813"},"PeriodicalIF":4.0,"publicationDate":"2024-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142552025","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-29DOI: 10.1016/j.compeleceng.2024.109806
Junxian He , Min Tian , Ying Jiang , Haibing Wang , Tengxiao Wang , Xichuan Zhou , Liyuan Liu , Nanjian Wu , Ying Wang , Cong Shi
The era of artificial intelligence of things (AIoT) brings huge challenges on edge visual processing systems under strict processing latency, cost and energy budgets. The emergence of computationally efficient biological spiking neural networks (SNN) and event-driven neuromorphic architecture in recent years have fostered a computing paradigm shift to address these challenges. In this paper, we propose a neuromorphic processor architecture for a multi-layer convolutional SNN (codenamed HMAX SNN model) inspired by human visual cortex hierarchy. The main contributions of this work include: 1) It proposes a fully event-driven, modular, configurable and scalable neuromorphic architecture allowing for flexible tradeoffs among implementation cost, processing speed and visual recognition accuracy with multi-layer convolutional SNNs. 2) It proposes a run-time reconfigurable learning engine enabling fast on-chip unsupervised spike-timing dependent plasticity (STDP) learning for the feature-extraction convolutional layers and also supervised STDP learning for the feature-classification FC layer, in a time-multiplexing way. These techniques greatly improve on-chip learning accuracies beyond 97 % on the Modified National Institute of Standards and Technology database (MNIST) images for the first time among existing edge neuromorphic systems, at reasonable computational and memory costs. Our hardware processor architecture was prototyped on a low-cost Zedboard Zynq-7020 Field-Programmable Gate Array (FPGA) device, and validated on the MNIST, Fashion-MNIST, Olivetti Research Laboratory (ORL) human faces and ETH-80 image datasets. The experimental results demonstrate that the proposed neuromorphic architecture can achieve comparably high on-chip learning accuracy, high inference throughput and high energy efficiency using relatively fewer hardware resource consumptions. We anticipate that the HMAX SNN processor can potentially enhance deployments of edge neuromorphic processors in more practical edge applications.
人工智能物联网（AIoT）时代在严格的处理延迟、成本和能耗预算下给边缘视觉处理系统带来了巨大挑战。近年来，计算高效的生物尖峰神经网络（SNN）和事件驱动神经形态架构的出现，促进了计算模式的转变，以应对这些挑战。在本文中，我们受人类视觉皮层层次结构的启发，为多层卷积 SNN（代号为 HMAX SNN 模型）提出了一种神经形态处理器架构。这项工作的主要贡献包括1) 它提出了一种完全事件驱动、模块化、可配置和可扩展的神经形态架构，允许在多层卷积 SNN 的实施成本、处理速度和视觉识别准确性之间灵活权衡。2) 它提出了一种运行时可重新配置的学习引擎，能以时间多路复用的方式，对特征提取卷积层进行快速的片上无监督尖峰计时可塑性（STDP）学习，并对特征分类 FC 层进行有监督 STDP 学习。在现有的边缘神经形态系统中，这些技术以合理的计算和内存成本，首次将修改后的美国国家标准与技术研究院（National Institute of Standards and Technology）数据库（MNIST）图像的片上学习准确率大大提高到 97% 以上。我们在低成本的 Zedboard Zynq-7020 现场可编程门阵列（FPGA）设备上搭建了硬件处理器架构原型，并在 MNIST、Fashion-MNIST、Olivetti 研究实验室（ORL）人脸和 ETH-80 图像数据集上进行了验证。实验结果表明，所提出的神经形态架构能以相对较少的硬件资源消耗实现相当高的片上学习精度、高推理吞吐量和高能效。我们预计，HMAX SNN 处理器有可能在更多实际边缘应用中加强边缘神经形态处理器的部署。
{"title":"A visual cortex-inspired edge neuromorphic hardware architecture with on-chip multi-layer STDP learning","authors":"Junxian He , Min Tian , Ying Jiang , Haibing Wang , Tengxiao Wang , Xichuan Zhou , Liyuan Liu , Nanjian Wu , Ying Wang , Cong Shi","doi":"10.1016/j.compeleceng.2024.109806","DOIUrl":"10.1016/j.compeleceng.2024.109806","url":null,"abstract":"<div><div>The era of artificial intelligence of things (AIoT) brings huge challenges on edge visual processing systems under strict processing latency, cost and energy budgets. The emergence of computationally efficient biological spiking neural networks (SNN) and event-driven neuromorphic architecture in recent years have fostered a computing paradigm shift to address these challenges. In this paper, we propose a neuromorphic processor architecture for a multi-layer convolutional SNN (codenamed HMAX SNN model) inspired by human visual cortex hierarchy. The main contributions of this work include: 1) It proposes a fully event-driven, modular, configurable and scalable neuromorphic architecture allowing for flexible tradeoffs among implementation cost, processing speed and visual recognition accuracy with multi-layer convolutional SNNs. 2) It proposes a run-time reconfigurable learning engine enabling fast on-chip unsupervised spike-timing dependent plasticity (STDP) learning for the feature-extraction convolutional layers and also supervised STDP learning for the feature-classification FC layer, in a time-multiplexing way. These techniques greatly improve on-chip learning accuracies beyond 97 % on the Modified National Institute of Standards and Technology database (MNIST) images for the first time among existing edge neuromorphic systems, at reasonable computational and memory costs. Our hardware processor architecture was prototyped on a low-cost Zedboard Zynq-7020 Field-Programmable Gate Array (FPGA) device, and validated on the MNIST, Fashion-MNIST, Olivetti Research Laboratory (ORL) human faces and ETH-80 image datasets. The experimental results demonstrate that the proposed neuromorphic architecture can achieve comparably high on-chip learning accuracy, high inference throughput and high energy efficiency using relatively fewer hardware resource consumptions. We anticipate that the HMAX SNN processor can potentially enhance deployments of edge neuromorphic processors in more practical edge applications.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"120 ","pages":"Article 109806"},"PeriodicalIF":4.0,"publicationDate":"2024-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142539641","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-29DOI: 10.1016/j.compeleceng.2024.109793
Welington G. Rodrigues , Gabriel S. Vieira , Christian D. Cabacinha , Renato F. Bulcão-Neto , Fabrizzio Soares
Forest inventory is a crucial tool for managing forest resources by providing quantitative and qualitative information about a particular region, much of which is collected manually in the field. Using devices such as Light Detection and Ranging (LiDAR) assists in collecting and analyzing various parameters of forest inventory. Adopting artificial intelligence (AI) techniques has sparked interest among forestry engineers seeking to work with forest LiDAR data. In this context, this study presents a Systematic Literature Review (SLR) to identify, evaluate, and interpret the results of primary studies related to the intersection between AI and Forestry Engineering. The automated search strategy retrieved 218 studies, of which 46 were selected after applying inclusion and exclusion criteria and quality assessment. After analyzing and synthesizing the data, the results showed that deep learning is becoming an increasing trend in recent research and that the direct estimation of tree diameter from aerial scans, although critical, has been minimally explored, highlighting an open field for future research.
{"title":"Applications of artificial intelligence and LiDAR in forest inventories: A Systematic Literature Review","authors":"Welington G. Rodrigues , Gabriel S. Vieira , Christian D. Cabacinha , Renato F. Bulcão-Neto , Fabrizzio Soares","doi":"10.1016/j.compeleceng.2024.109793","DOIUrl":"10.1016/j.compeleceng.2024.109793","url":null,"abstract":"<div><div>Forest inventory is a crucial tool for managing forest resources by providing quantitative and qualitative information about a particular region, much of which is collected manually in the field. Using devices such as Light Detection and Ranging (LiDAR) assists in collecting and analyzing various parameters of forest inventory. Adopting artificial intelligence (AI) techniques has sparked interest among forestry engineers seeking to work with forest LiDAR data. In this context, this study presents a Systematic Literature Review (SLR) to identify, evaluate, and interpret the results of primary studies related to the intersection between AI and Forestry Engineering. The automated search strategy retrieved 218 studies, of which 46 were selected after applying inclusion and exclusion criteria and quality assessment. After analyzing and synthesizing the data, the results showed that deep learning is becoming an increasing trend in recent research and that the direct estimation of tree diameter from aerial scans, although critical, has been minimally explored, highlighting an open field for future research.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"120 ","pages":"Article 109793"},"PeriodicalIF":4.0,"publicationDate":"2024-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142539748","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-29DOI: 10.1016/j.compeleceng.2024.109798
Peng Zhang , Lun Zhao , Yu Ren , Dong Wei , Sandy To , Zeshan Abbas , Md Shafiqul Islam
Efficient detection of defects in riveted joints during the self-piercing riveting (SPR) process will help improve riveting quality. Due to the complexity of SPR defects under actual working conditions, it is difficult for traditional visual technology to detect the forming quality of SPR joints effectively. To detect SPR defects and improve the efficiency of SPR joint forming quality, we proposed a defect detection model based on a multi-attention mechanism, named Multiple Attention Self-Piercing Riveting Network (MA-SPRNet), for the detection of SPR defects. Specifically, to alleviate problems such as unclear object features in complex environments, a multi-level fusion enhancement network (MFEN) is constructed. It fuses features into each level and improves the fusion effect by adding more levels of features. In addition, to alleviate the information redundancy generated during the feature fusion process, the triple attention module (TRAM) and the efficient multi-scale attention module (EMAM) were introduced to enhance the attention of the network to SPR defective. These modules are designed to refine the attention of the network, ensuring a more targeted analysis of riveting features. In addition, the Wise Intersection over Union (WIoU) loss function is introduced, aiming to guide the network to characterize features within the region of interest and to enhance the accurate positioning of riveting defects by the network. Finally, to verify the performance of the MA-SPRNet, an SPR defect dataset was constructed, and a series of experiments based on this dataset were conducted. The detection of MA-SPRNet was 82.83%. The results of experiments show that MA-SPRNet effectively realizes the detection of riveted joint defects.
{"title":"MA-SPRNet: A multiple attention mechanisms-based network for self-piercing riveting joint defect detection","authors":"Peng Zhang , Lun Zhao , Yu Ren , Dong Wei , Sandy To , Zeshan Abbas , Md Shafiqul Islam","doi":"10.1016/j.compeleceng.2024.109798","DOIUrl":"10.1016/j.compeleceng.2024.109798","url":null,"abstract":"<div><div>Efficient detection of defects in riveted joints during the self-piercing riveting (SPR) process will help improve riveting quality. Due to the complexity of SPR defects under actual working conditions, it is difficult for traditional visual technology to detect the forming quality of SPR joints effectively. To detect SPR defects and improve the efficiency of SPR joint forming quality, we proposed a defect detection model based on a multi-attention mechanism, named Multiple Attention Self-Piercing Riveting Network (MA-SPRNet), for the detection of SPR defects. Specifically, to alleviate problems such as unclear object features in complex environments, a multi-level fusion enhancement network (MFEN) is constructed. It fuses features into each level and improves the fusion effect by adding more levels of features. In addition, to alleviate the information redundancy generated during the feature fusion process, the triple attention module (TRAM) and the efficient multi-scale attention module (EMAM) were introduced to enhance the attention of the network to SPR defective. These modules are designed to refine the attention of the network, ensuring a more targeted analysis of riveting features. In addition, the Wise Intersection over Union (WIoU) loss function is introduced, aiming to guide the network to characterize features within the region of interest and to enhance the accurate positioning of riveting defects by the network. Finally, to verify the performance of the MA-SPRNet, an SPR defect dataset was constructed, and a series of experiments based on this dataset were conducted. The detection <span><math><mrow><mi>m</mi><mi>A</mi><msub><mrow><mi>P</mi></mrow><mrow><mn>0</mn><mo>.</mo><mn>5</mn></mrow></msub></mrow></math></span> of MA-SPRNet was 82.83%. The results of experiments show that MA-SPRNet effectively realizes the detection of riveted joint defects.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"120 ","pages":"Article 109798"},"PeriodicalIF":4.0,"publicationDate":"2024-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142539749","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号