首页 > 最新文献

2023 International Conference in Advances in Power, Signal, and Information Technology (APSIT)最新文献

英文 中文
p-GaN HEMT-on-SiC Structural Optimization for High Drain Current and High Threshold Voltage 高漏极电流和高阈值电压的p-GaN HEMT-on-SiC结构优化
Kashish Agarwal, G. Khanna, P. Kaushal
Normally-OFF (enhancement type) p-type Gallium Nitride (GaN) gate HEMT-on-Silicon Carbide (SiC) exhibiting a high breakdown voltage and large value of saturation current density is demonstrated in this paper. Benefiting from Aluminium Nitride (AIN) nucleation, Indium Nitride (InN) nucleation and Silcon Nitride (Si3N4) passivation layers with better handling of electric field lines on gate side and low drain leakage current, the structure with gate-to-drain length of 6 Mm shows a breakdown voltage (Vbr) of 840 V at 100 MA/mm drain current. The device shows a threshold voltage (V th) value 1.98 V at a drain current (Ids) of 100 MA/mm, an ON-current/OFF-current ratio (Ion/Ioff) of 1.7×109, a small specific ON-condition resistance (Ron) of 2.5 ohm.cm2, a high value of drain current density (0.316 A/mm) at gate voltage (V gs) of 8 V. A sub-threshold slope of 77 m V /dec is obtained. A high trans-conductance of 69 mS/mm is achieved. When Vgs is 8 V, the device exhibit low gate current (Igs) value (22.3 MA/mm). These results show huge potential of p-GaN gate structure HEMT-on-SiC for power application.
本文展示了一种常关(增强型)p型氮化镓栅极(hemt -on- SiC)具有高击穿电压和大的饱和电流密度值。得益于氮化铝(AIN)成核、氮化铟(InN)成核和氮化硅(Si3N4)钝化层对栅极侧电场线的处理效果较好,漏极漏电流小,栅极到漏极长度为6 Mm的结构在100 MA/ Mm漏极电流下击穿电压(Vbr)为840 V。在漏极电流(Ids)为100 MA/mm时,器件的阈值电压(V th)为1.98 V,通断电流比(Ion/Ioff)为1.7×109,比通状态电阻(Ron)很小,为2.5欧姆。在栅极电压为8v时,漏极电流密度高(0.316 a /mm)。得到了77 m V /dec的亚阈值斜率。实现了69 mS/mm的高跨导。当Vgs为8 V时,器件栅极电流(Igs)值较低(22.3 MA/mm)。这些结果显示了p-GaN栅极结构HEMT-on-SiC在功率应用方面的巨大潜力。
{"title":"p-GaN HEMT-on-SiC Structural Optimization for High Drain Current and High Threshold Voltage","authors":"Kashish Agarwal, G. Khanna, P. Kaushal","doi":"10.1109/APSIT58554.2023.10201729","DOIUrl":"https://doi.org/10.1109/APSIT58554.2023.10201729","url":null,"abstract":"Normally-OFF (enhancement type) p-type Gallium Nitride (GaN) gate HEMT-on-Silicon Carbide (SiC) exhibiting a high breakdown voltage and large value of saturation current density is demonstrated in this paper. Benefiting from Aluminium Nitride (AIN) nucleation, Indium Nitride (InN) nucleation and Silcon Nitride (Si3N4) passivation layers with better handling of electric field lines on gate side and low drain leakage current, the structure with gate-to-drain length of 6 Mm shows a breakdown voltage (Vbr) of 840 V at 100 MA/mm drain current. The device shows a threshold voltage (V th) value 1.98 V at a drain current (Ids) of 100 MA/mm, an ON-current/OFF-current ratio (Ion/Ioff) of 1.7×109, a small specific ON-condition resistance (Ron) of 2.5 ohm.cm2, a high value of drain current density (0.316 A/mm) at gate voltage (V gs) of 8 V. A sub-threshold slope of 77 m V /dec is obtained. A high trans-conductance of 69 mS/mm is achieved. When Vgs is 8 V, the device exhibit low gate current (Igs) value (22.3 MA/mm). These results show huge potential of p-GaN gate structure HEMT-on-SiC for power application.","PeriodicalId":170044,"journal":{"name":"2023 International Conference in Advances in Power, Signal, and Information Technology (APSIT)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128004997","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Sensitivity and Accuracy of Dielectric Measurements of Significantly Improved Coupled Capacitive-Dependent scheelite crystal 显著改进的耦合电容依赖性白钨矿晶体介电测量的灵敏度和精度
Sudhansu Sekhar Hota, Debasish Panda, Ram Naresh Prasad Choudhary
The ability of thermistor to exhibit linear electrical behaviours is crucial for minimising circuit design complexity. To create high performance electronic ceramics, phase formation modulation is crucial. By using a solid-state reaction technique, novel linear high-temperature thermistors based on BaWO4 ceramics were created, resulting in an internal conducting network and linear electrical characteristics. In the temperature range of 573 K to 773 K, the ceramics showed negative temperature coefficient (NTC) thermistor properties. They had an excellent linear resistance-temperature (R-T) combination. The process behind linear electrical behaviours has been analysed using a parallel conductive model in combination with a comprehensive impedance and dielectric study. This strategy might be applied more generally to create linear high-temperature thermistors with a large temperature range.
热敏电阻表现出线性电行为的能力对于最小化电路设计复杂性至关重要。为了制造高性能电子陶瓷,相位形成调制是至关重要的。利用固相反应技术,制备了基于BaWO4陶瓷的新型线性高温热敏电阻,获得了内部导电网络和线性电特性。在573 ~ 773 K温度范围内,陶瓷表现出负温度系数(NTC)热敏电阻特性。它们具有优异的线性电阻-温度(R-T)组合。线性电学行为背后的过程已经用一个并联的导电模型结合全面的阻抗和介电研究进行了分析。这种策略可以更普遍地应用于制造具有大温度范围的线性高温热敏电阻。
{"title":"Sensitivity and Accuracy of Dielectric Measurements of Significantly Improved Coupled Capacitive-Dependent scheelite crystal","authors":"Sudhansu Sekhar Hota, Debasish Panda, Ram Naresh Prasad Choudhary","doi":"10.1109/APSIT58554.2023.10201719","DOIUrl":"https://doi.org/10.1109/APSIT58554.2023.10201719","url":null,"abstract":"The ability of thermistor to exhibit linear electrical behaviours is crucial for minimising circuit design complexity. To create high performance electronic ceramics, phase formation modulation is crucial. By using a solid-state reaction technique, novel linear high-temperature thermistors based on BaWO4 ceramics were created, resulting in an internal conducting network and linear electrical characteristics. In the temperature range of 573 K to 773 K, the ceramics showed negative temperature coefficient (NTC) thermistor properties. They had an excellent linear resistance-temperature (R-T) combination. The process behind linear electrical behaviours has been analysed using a parallel conductive model in combination with a comprehensive impedance and dielectric study. This strategy might be applied more generally to create linear high-temperature thermistors with a large temperature range.","PeriodicalId":170044,"journal":{"name":"2023 International Conference in Advances in Power, Signal, and Information Technology (APSIT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130075395","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 5
TSPSO: Enhanced Task Scheduling using Optimized Particle Swarm Algorithm in Cloud Computing Environment 基于优化粒子群算法的云计算环境下增强任务调度
Swarnendra Kumar Behera, Saroja Kumar Rout, R. Tiwari
The most significant constraint in cloud computing infrastructure is job/task scheduling which affords the vital role of efficiency of the entire cloud computing services and offerings. Job/ task scheduling in cloud infrastructure means that to assign the best appropriate cloud resources for the given job/task by considering different factors: execution time and cost, infrastructure scalability and reliability, platform availability and throughput, resource utilization, and make span. The proposed enhanced task scheduling algorithm using particle swarm optimization considers the optimization of makes pan and scheduling time. We propose the proposed model by using dynamic adjustment of parameters with discrete positioning (DAPDP) based algorithm to schedule and allocate cloud jobs/tasks that ensure optimized makes pan and scheduling time. DAPDP can witness a substantial role in attaining reliability by seeing the available, scheduled, and allocated cloud resources. Our approach DAPDP compared with other existing particle swarm and optimization job/task scheduling algorithms to prove that DAPDP can save in makes pan, scheduling, and execution time.
云计算基础设施中最重要的约束是作业/任务调度,它对整个云计算服务和产品的效率起着至关重要的作用。云基础设施中的作业/任务调度是指通过考虑执行时间和成本、基础设施可扩展性和可靠性、平台可用性和吞吐量、资源利用率和make span等不同因素,为给定的作业/任务分配最合适的云资源。提出了一种基于粒子群优化的增强任务调度算法,该算法考虑了调度目标和调度时间的优化。我们提出了采用基于离散定位(DAPDP)算法的参数动态调整来调度和分配云作业/任务的模型,以确保优化的制作盘和调度时间。通过查看可用的、计划的和分配的云资源,DAPDP可以在实现可靠性方面发挥重要作用。将该方法与现有的粒子群算法和优化作业/任务调度算法进行比较,证明了该方法可以节省调度时间、调度时间和执行时间。
{"title":"TSPSO: Enhanced Task Scheduling using Optimized Particle Swarm Algorithm in Cloud Computing Environment","authors":"Swarnendra Kumar Behera, Saroja Kumar Rout, R. Tiwari","doi":"10.1109/APSIT58554.2023.10201736","DOIUrl":"https://doi.org/10.1109/APSIT58554.2023.10201736","url":null,"abstract":"The most significant constraint in cloud computing infrastructure is job/task scheduling which affords the vital role of efficiency of the entire cloud computing services and offerings. Job/ task scheduling in cloud infrastructure means that to assign the best appropriate cloud resources for the given job/task by considering different factors: execution time and cost, infrastructure scalability and reliability, platform availability and throughput, resource utilization, and make span. The proposed enhanced task scheduling algorithm using particle swarm optimization considers the optimization of makes pan and scheduling time. We propose the proposed model by using dynamic adjustment of parameters with discrete positioning (DAPDP) based algorithm to schedule and allocate cloud jobs/tasks that ensure optimized makes pan and scheduling time. DAPDP can witness a substantial role in attaining reliability by seeing the available, scheduled, and allocated cloud resources. Our approach DAPDP compared with other existing particle swarm and optimization job/task scheduling algorithms to prove that DAPDP can save in makes pan, scheduling, and execution time.","PeriodicalId":170044,"journal":{"name":"2023 International Conference in Advances in Power, Signal, and Information Technology (APSIT)","volume":"80 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126776569","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Breast Tumor Detection and Classification Using ABC-ELM Algorithm 基于ABC-ELM算法的乳腺肿瘤检测与分类
Haymanot Derebe Bizuneh, Satyasis Mishra, Workineh Geleta Negassa
Analyzing medical images and deciding on health issues require a hybrid intelligence system. Today, cancer is the illness that kills the most people worldwide. The most common type of tumor sickness is breast cancer. The previously employed algorithms for detecting and classifying breast tumors kept getting better until they produced successful results. Machine learning techniques for detecting and classifying breast tumors have been the subject of numerous studies. For breast tumor identification and classification, we proposed the Artificial Bee Colony Extreme Learning Machine (ABC-ELM) algorithm. We aim to improve the breast tumor identification and classification algorithm using the Morlet wavelet transform for feature extraction and tumor segmentation. Breast images are classified as malignant or non-cancerous by extracting pertinent features and improving the ELM classifier's parameters using the ABC algorithm. As a result, the proposed method performs best compared to earlier comparative research, achieving an accuracy of 98.2%, Sensitivity is 98.5%, and precision 98.5%.
分析医学图像和决定健康问题需要一个混合智能系统。今天,癌症是全世界死亡人数最多的疾病。最常见的肿瘤疾病是乳腺癌。以前用于检测和分类乳腺肿瘤的算法不断改进,直到产生成功的结果。用于检测和分类乳腺肿瘤的机器学习技术一直是许多研究的主题。针对乳腺肿瘤的识别与分类,我们提出了人工蜂群极限学习机(ABC-ELM)算法。本文旨在改进乳腺肿瘤识别与分类算法,利用Morlet小波变换进行特征提取和肿瘤分割。通过提取相关特征并使用ABC算法改进ELM分类器的参数,将乳房图像分类为恶性或非癌性。结果表明,该方法的准确度为98.2%,灵敏度为98.5%,精密度为98.5%。
{"title":"Breast Tumor Detection and Classification Using ABC-ELM Algorithm","authors":"Haymanot Derebe Bizuneh, Satyasis Mishra, Workineh Geleta Negassa","doi":"10.1109/APSIT58554.2023.10201776","DOIUrl":"https://doi.org/10.1109/APSIT58554.2023.10201776","url":null,"abstract":"Analyzing medical images and deciding on health issues require a hybrid intelligence system. Today, cancer is the illness that kills the most people worldwide. The most common type of tumor sickness is breast cancer. The previously employed algorithms for detecting and classifying breast tumors kept getting better until they produced successful results. Machine learning techniques for detecting and classifying breast tumors have been the subject of numerous studies. For breast tumor identification and classification, we proposed the Artificial Bee Colony Extreme Learning Machine (ABC-ELM) algorithm. We aim to improve the breast tumor identification and classification algorithm using the Morlet wavelet transform for feature extraction and tumor segmentation. Breast images are classified as malignant or non-cancerous by extracting pertinent features and improving the ELM classifier's parameters using the ABC algorithm. As a result, the proposed method performs best compared to earlier comparative research, achieving an accuracy of 98.2%, Sensitivity is 98.5%, and precision 98.5%.","PeriodicalId":170044,"journal":{"name":"2023 International Conference in Advances in Power, Signal, and Information Technology (APSIT)","volume":"98 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132713172","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Maximizing Solar Array Output Power Under PS Using Shifting Arrangement Reconfiguration 利用移位排列重构最大化PS下太阳能阵列输出功率
A. K. Parida, A. Mohapatra, Rudra Narayan Das, Chidurala Saiprakash, Shibanika Panda, Khadija Sajda Khanam
In recent years, there have been several proposed solutions to mitigate the negative impact of Partial shading (PS) on the performance of photovoltaic (PV) systems. Achieving maximum energy harvesting is crucial for increasing solar unit efficiency, but this is influenced by several factors such as power electronic device configuration, climate change, and unit size. Various configurations like series, parallels, series-parallel, total-cross-tied, bridge-linked, and honeycomb can be helpful, but they may also have drawbacks such as low shade dispersion, mismatch, and line losses. To address these issues, array reconfiguration has been successful, and this paper examines the current scenario and improvements in PV system reconfiguration. A new technique called Shifting Arrangement (SA) reconfiguration is proposed here to enhance the output performance of photovoltaic solar panels. A comparison is made between the performance of the proposed physical reconfiguration and conventional array configurations, analyzing their Fill Factor (FF), Mismatch Loss (ML), and Global Maximum Power (GMP).
近年来,人们提出了几种解决方案来减轻部分遮阳(PS)对光伏(PV)系统性能的负面影响。实现最大的能量收集是提高太阳能单元效率的关键,但这受到几个因素的影响,如电力电子设备配置、气候变化和单元大小。各种配置,如串联、并联、串并联、全交叉连接、桥联和蜂窝都是有用的,但它们也可能有缺点,如低色散、不匹配和线路损耗。为了解决这些问题,阵列重新配置已经成功,本文研究了光伏系统重新配置的当前场景和改进。为了提高光伏太阳能板的输出性能,提出了一种位移排列重构技术。比较了提出的物理重构和传统阵列配置的性能,分析了它们的填充因子(FF)、失配损耗(ML)和全局最大功率(GMP)。
{"title":"Maximizing Solar Array Output Power Under PS Using Shifting Arrangement Reconfiguration","authors":"A. K. Parida, A. Mohapatra, Rudra Narayan Das, Chidurala Saiprakash, Shibanika Panda, Khadija Sajda Khanam","doi":"10.1109/APSIT58554.2023.10201714","DOIUrl":"https://doi.org/10.1109/APSIT58554.2023.10201714","url":null,"abstract":"In recent years, there have been several proposed solutions to mitigate the negative impact of Partial shading (PS) on the performance of photovoltaic (PV) systems. Achieving maximum energy harvesting is crucial for increasing solar unit efficiency, but this is influenced by several factors such as power electronic device configuration, climate change, and unit size. Various configurations like series, parallels, series-parallel, total-cross-tied, bridge-linked, and honeycomb can be helpful, but they may also have drawbacks such as low shade dispersion, mismatch, and line losses. To address these issues, array reconfiguration has been successful, and this paper examines the current scenario and improvements in PV system reconfiguration. A new technique called Shifting Arrangement (SA) reconfiguration is proposed here to enhance the output performance of photovoltaic solar panels. A comparison is made between the performance of the proposed physical reconfiguration and conventional array configurations, analyzing their Fill Factor (FF), Mismatch Loss (ML), and Global Maximum Power (GMP).","PeriodicalId":170044,"journal":{"name":"2023 International Conference in Advances in Power, Signal, and Information Technology (APSIT)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133332271","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Comparative Analysis of Dual-edge Triggered and Sense Amplifier Based Flip-flops in 32 nm CMOS Regime 基于32纳米CMOS器件的双边缘触发触发器和感测放大器的比较分析
O. Shah, Shivangi Bansal, Prashant Kumar Mavi, A. Yadav, Satvik Vats, Zaiba Ishrat
The article summarizes the outcomes of extensive research carried out on dual-edge triggered flip-flops (DETFFs) and sense amplifier based flip-flops (SAFFs) in relation to their power consumption, delay measurements and area requirements. The research focused on four of the most advanced flip-flops (FFs) currently available, and simulations were conducted in SPICE using 32 nm CMOS technology. The results showed that Lee's FF had better power efficiency at data activities of greater than 25% whereas Lapshev's FF could be used for circuits with less data activity. Jeong's FF had better speed efficiency at higher voltages. Lee's FF also had the best power delay product (PDP) followed closely by Jeong's FF at nominal conditions. Additionally, Jeong's FF outperformed other designs in terms of area overhead.
本文总结了对双边触发触发器(detff)和基于感测放大器的触发器(sfs)在功耗、延迟测量和面积要求方面进行的广泛研究的结果。该研究集中在目前可用的四种最先进的触发器(ff)上,并使用32纳米CMOS技术在SPICE中进行了模拟。结果表明,Lee的FF在数据活动中具有更好的功率效率,大于25%,而Lapshev的FF可用于数据活动较少的电路。Jeong的FF在更高的电压下具有更好的速度效率。在标称条件下,Lee的FF也具有最佳的功率延迟积(PDP),其次是Jeong的FF。此外,Jeong的FF在面积开销方面优于其他设计。
{"title":"Comparative Analysis of Dual-edge Triggered and Sense Amplifier Based Flip-flops in 32 nm CMOS Regime","authors":"O. Shah, Shivangi Bansal, Prashant Kumar Mavi, A. Yadav, Satvik Vats, Zaiba Ishrat","doi":"10.1109/APSIT58554.2023.10201721","DOIUrl":"https://doi.org/10.1109/APSIT58554.2023.10201721","url":null,"abstract":"The article summarizes the outcomes of extensive research carried out on dual-edge triggered flip-flops (DETFFs) and sense amplifier based flip-flops (SAFFs) in relation to their power consumption, delay measurements and area requirements. The research focused on four of the most advanced flip-flops (FFs) currently available, and simulations were conducted in SPICE using 32 nm CMOS technology. The results showed that Lee's FF had better power efficiency at data activities of greater than 25% whereas Lapshev's FF could be used for circuits with less data activity. Jeong's FF had better speed efficiency at higher voltages. Lee's FF also had the best power delay product (PDP) followed closely by Jeong's FF at nominal conditions. Additionally, Jeong's FF outperformed other designs in terms of area overhead.","PeriodicalId":170044,"journal":{"name":"2023 International Conference in Advances in Power, Signal, and Information Technology (APSIT)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114081586","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
DGA Based Ensemble Learning Approach for Power Transformer Fault Diagnosis 基于DGA的电力变压器故障诊断集成学习方法
Shubham Dadaso Patil, A. Patil, Megharani Dharme, R. Jarial
The power transformer is one of the most ubiquitous and crucial parts of the energy infrastructure. The use of Dissolved Gas Analysis (DGA) to clarify transformer incipient faults via machine learning algorithms is an intriguing engineering strategy. In the interest of discovering more about the fault classification capacity and suitability of multiple Machine learning algorithms, this article makes use of a wide range of numerous and diverse DGA data sets. This research focuses on detecting faults in power transformers by analyzing gases that are dissolved in mineral oil insulation using Machine-Learning algorithms such as the K-nearest neighbors (KNN) classifier, Logistic Regression, Naive Bayes classifier, Decision Tree Classifier, and Ensemble learning algorithm. This research also addresses performance indicators and assesses multiple algorithms to validate the best class algorithms. In addition, a top-performing algorithm is chosen using a collection of effectiveness criteria. This method will be useful for condition monitoring engineers mostly in the diagnosis of transformer insulation, the implementation of monitoring devices for large transformer fleets, and the comprehension of the behavior of insulation oil over the course of years to prevent catastrophic failure.
电力变压器是能源基础设施中最普遍、最关键的部件之一。利用溶解气体分析(DGA)通过机器学习算法来澄清变压器早期故障是一项有趣的工程策略。为了更多地了解多种机器学习算法的故障分类能力和适用性,本文使用了大量不同的DGA数据集。本研究的重点是通过分析溶解在矿物油绝缘中的气体来检测电力变压器的故障,使用机器学习算法,如k近邻(KNN)分类器、逻辑回归、朴素贝叶斯分类器、决策树分类器和集成学习算法。本研究还讨论了性能指标,并评估了多种算法,以验证最佳类算法。此外,使用一系列有效性标准选择性能最好的算法。该方法将主要用于状态监测工程师对变压器绝缘的诊断,大型变压器机群监测装置的实施,以及对绝缘油在多年过程中的行为的理解,以防止灾难性故障。
{"title":"DGA Based Ensemble Learning Approach for Power Transformer Fault Diagnosis","authors":"Shubham Dadaso Patil, A. Patil, Megharani Dharme, R. Jarial","doi":"10.1109/APSIT58554.2023.10201755","DOIUrl":"https://doi.org/10.1109/APSIT58554.2023.10201755","url":null,"abstract":"The power transformer is one of the most ubiquitous and crucial parts of the energy infrastructure. The use of Dissolved Gas Analysis (DGA) to clarify transformer incipient faults via machine learning algorithms is an intriguing engineering strategy. In the interest of discovering more about the fault classification capacity and suitability of multiple Machine learning algorithms, this article makes use of a wide range of numerous and diverse DGA data sets. This research focuses on detecting faults in power transformers by analyzing gases that are dissolved in mineral oil insulation using Machine-Learning algorithms such as the K-nearest neighbors (KNN) classifier, Logistic Regression, Naive Bayes classifier, Decision Tree Classifier, and Ensemble learning algorithm. This research also addresses performance indicators and assesses multiple algorithms to validate the best class algorithms. In addition, a top-performing algorithm is chosen using a collection of effectiveness criteria. This method will be useful for condition monitoring engineers mostly in the diagnosis of transformer insulation, the implementation of monitoring devices for large transformer fleets, and the comprehension of the behavior of insulation oil over the course of years to prevent catastrophic failure.","PeriodicalId":170044,"journal":{"name":"2023 International Conference in Advances in Power, Signal, and Information Technology (APSIT)","volume":"284 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113997123","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Attention-free based dual-encoder mechanism for Aspect-based Multimodal Sentiment Recognition 基于无注意力的基于方面的多模态情感识别双编码器机制
Pankaj Gupta, Ananya Pandey, Ajeet Kumar, D. Vishwakarma
Multimodal aspect-based sentiment recognition (MABSR) is a recently developed task in sentiment recognition that tries to assess the sentiment associated with text and image pairings by generally extracting the polarity terms from the pairs. Both the pipeline and the unified transformer based technique, which employs the cross-attention only mechanism, have been widely utilized in recent works. However, the alignment between text and picture is not openly and reliably included in these approaches. There is still a minimum threshold of aligned image-text pairings needed for supervised fine-tuning of said universal transformers for MABSR. Motivated by this observation and inspired by the various attention-only mechanisms, we analyze MABSR and propose an attention-free encoder-based transformer architecture. Dual attention-free based backbone encoder models with cross-modal symmetry are utilized in this work. To improve cross-modal performance, we include two new subtasks: aspect-only extraction and polarity feature representation alignment. This motivates both encoders to provide more precise depictions of multiple modalities.
基于多模态方面的情感识别(MABSR)是最近发展起来的一项情感识别任务,它试图通过从文本和图像对中提取极性项来评估与文本和图像对相关的情感。采用交叉关注机制的管道技术和统一变压器技术在近年来得到了广泛的应用。然而,文本和图片之间的对齐并没有公开和可靠地包含在这些方法中。对于MABSR通用变压器的监督微调,仍然需要对齐图像-文本对的最小阈值。基于这一观察结果并受到各种仅关注机制的启发,我们分析了MABSR并提出了一种基于无关注编码器的变压器架构。在这项工作中使用了基于双无注意的骨干编码器模型,该模型具有跨模态对称性。为了提高跨模态性能,我们增加了两个新的子任务:纯方面提取和极性特征表示对齐。这促使两个编码器提供更精确的多模态描述。
{"title":"Attention-free based dual-encoder mechanism for Aspect-based Multimodal Sentiment Recognition","authors":"Pankaj Gupta, Ananya Pandey, Ajeet Kumar, D. Vishwakarma","doi":"10.1109/APSIT58554.2023.10201711","DOIUrl":"https://doi.org/10.1109/APSIT58554.2023.10201711","url":null,"abstract":"Multimodal aspect-based sentiment recognition (MABSR) is a recently developed task in sentiment recognition that tries to assess the sentiment associated with text and image pairings by generally extracting the polarity terms from the pairs. Both the pipeline and the unified transformer based technique, which employs the cross-attention only mechanism, have been widely utilized in recent works. However, the alignment between text and picture is not openly and reliably included in these approaches. There is still a minimum threshold of aligned image-text pairings needed for supervised fine-tuning of said universal transformers for MABSR. Motivated by this observation and inspired by the various attention-only mechanisms, we analyze MABSR and propose an attention-free encoder-based transformer architecture. Dual attention-free based backbone encoder models with cross-modal symmetry are utilized in this work. To improve cross-modal performance, we include two new subtasks: aspect-only extraction and polarity feature representation alignment. This motivates both encoders to provide more precise depictions of multiple modalities.","PeriodicalId":170044,"journal":{"name":"2023 International Conference in Advances in Power, Signal, and Information Technology (APSIT)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123869188","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Generation Scheduling of Grid Connected Microgrid using GAMS 基于GAMS的并网微电网发电调度
Indurekha Shial, Rajat Kanti Samal, Chinmaya Bhuyan
The integrated form of distributed energy resources make a small-scale power grid called microgrid. Based on the production of electrical energy renewable energy sources are integrated especially wind energy which gives various features to the power system. Here a grid-connected mode of microgrid with wind energy resources is used which offers a positive impact on quality of life, climate change and energy efficiency. In this paper an integrated scheduling model is used to find an optimal solution of distributed energy resource network and depository devices in such a way that both cost and emission are reduced by using General Algebraic Modelling System(GAMS). The results show that this system can efficiently synchronize the power generation of distributed energy system and the fluctuations of wind power production is reduced due to the presence of Energy Storage System (ESS). Such that the system is handling uncertainties correctly in electrical microgrid.
分布式能源的集成形式构成了一个小规模的电网,称为微电网。在生产电能的基础上集成了可再生能源,特别是风能,使电力系统具有各种各样的特点。这里使用了风能资源的微电网并网模式,这对生活质量、气候变化和能源效率产生了积极影响。本文利用通用代数建模系统(GAMS),建立了分布式能源网络和储能设备的综合调度模型,在降低成本和降低排放的前提下寻求分布式能源网络和储能设备的最优解。结果表明,该系统可以有效地同步分布式能源系统的发电,并且由于储能系统(ESS)的存在,减少了风力发电的波动。使系统能够正确处理微电网中的不确定性。
{"title":"Generation Scheduling of Grid Connected Microgrid using GAMS","authors":"Indurekha Shial, Rajat Kanti Samal, Chinmaya Bhuyan","doi":"10.1109/APSIT58554.2023.10201791","DOIUrl":"https://doi.org/10.1109/APSIT58554.2023.10201791","url":null,"abstract":"The integrated form of distributed energy resources make a small-scale power grid called microgrid. Based on the production of electrical energy renewable energy sources are integrated especially wind energy which gives various features to the power system. Here a grid-connected mode of microgrid with wind energy resources is used which offers a positive impact on quality of life, climate change and energy efficiency. In this paper an integrated scheduling model is used to find an optimal solution of distributed energy resource network and depository devices in such a way that both cost and emission are reduced by using General Algebraic Modelling System(GAMS). The results show that this system can efficiently synchronize the power generation of distributed energy system and the fluctuations of wind power production is reduced due to the presence of Energy Storage System (ESS). Such that the system is handling uncertainties correctly in electrical microgrid.","PeriodicalId":170044,"journal":{"name":"2023 International Conference in Advances in Power, Signal, and Information Technology (APSIT)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127876637","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
A Model for Enhancing Nested Mobile Nodes Performance 一种提高嵌套移动节点性能的模型
S. Ibrahim, Y. Mohamed
In recent years, IP networks have come to rely heavily on network mobility. In spite of the system's adaptability, it ensures constant connectivity to the internet. NEMO Basic Support Protocol (BSP) was suggested by the Internet Engineering Task Force (IETF) to deal with the problem of mobile systems; however, it has a few drawbacks, including high overhead, high inactivity during handoff, and bundle delay. The topic of wasteful NEMO direction turns out to be an interesting research area, especially for the more commonplace, established portable systems. In a simple setting, a number of portable systems gradually include a large number of movable switches. When the mobile device is out of range, all communications to and from the Mobile Networks Nodes must go via the Mobile Router and Home Agent (MR,HA) tunnel. As a result, the package route will be sped up and the bundle delivery time will increase. Route optimization in a layered mobile network was explored in an Internet Engineering Task Force Request for Comment (IETF RFC 4889) as a means to circumvent such limits. This study proposes a novel paradigm to improve the functionality of layered networks. The approach is built on polling a subset of routers to determine which will be in charge of the routing process, and then directing all communications via those routers rather than using the more complex higher-level mobile networks. The proposed model has less end-to-end latency than NEMO BSP. This model was run with OPNET v14.5, an optimization tool for network simulations. Top-level nested simulations resulted in a 5% reduction in end-to-end latency. Nesting at the intermediate level reduced end-to-end latency by 10%. At the third level of nesting, a 14% reduction in end-to-end latency was realized. All this considering just three levels of nesting, thus, when the nesting depth is raised, the results improve. Using smarter routers, this model may be improved to achieve best-case outcomes, making it one of the best suggested solutions for the routing constraints of layered mobile networks.
近年来,IP网络越来越依赖于网络的移动性。尽管该系统具有适应性,但它确保了与互联网的持续连接。NEMO基本支持协议(BSP)是互联网工程任务组(IETF)提出的用于处理移动系统问题的协议;然而,它有一些缺点,包括高开销、切换期间的高度不活跃和包延迟。浪费NEMO方向的主题是一个有趣的研究领域,特别是对于更常见的,已建立的便携式系统。在一个简单的设置中,许多便携式系统逐渐包括大量的可移动开关。当移动设备超出范围时,所有与移动网络节点之间的通信都必须通过移动路由器和家庭代理(MR,HA)隧道。因此,包裹路线将加快,捆包交付时间将增加。互联网工程任务组征求意见(IETF RFC 4889)探讨了分层移动网络中的路由优化,作为规避此类限制的一种手段。本研究提出了一种新的范例来改善分层网络的功能。该方法建立在轮询路由器子集的基础上,以确定哪一个路由器将负责路由过程,然后通过这些路由器指导所有通信,而不是使用更复杂的高级移动网络。该模型比NEMO BSP具有更小的端到端延迟。该模型在网络仿真优化工具OPNET v14.5上运行。顶层嵌套模拟使端到端延迟减少了5%。中间级别的嵌套将端到端延迟减少了10%。在嵌套的第三层,实现了端到端延迟减少14%。所有这些都只考虑了三层嵌套,因此,当嵌套深度增加时,结果会得到改善。使用更智能的路由器,该模型可以得到改进,以达到最佳结果,使其成为分层移动网络路由约束的最佳建议解决方案之一。
{"title":"A Model for Enhancing Nested Mobile Nodes Performance","authors":"S. Ibrahim, Y. Mohamed","doi":"10.1109/APSIT58554.2023.10201701","DOIUrl":"https://doi.org/10.1109/APSIT58554.2023.10201701","url":null,"abstract":"In recent years, IP networks have come to rely heavily on network mobility. In spite of the system's adaptability, it ensures constant connectivity to the internet. NEMO Basic Support Protocol (BSP) was suggested by the Internet Engineering Task Force (IETF) to deal with the problem of mobile systems; however, it has a few drawbacks, including high overhead, high inactivity during handoff, and bundle delay. The topic of wasteful NEMO direction turns out to be an interesting research area, especially for the more commonplace, established portable systems. In a simple setting, a number of portable systems gradually include a large number of movable switches. When the mobile device is out of range, all communications to and from the Mobile Networks Nodes must go via the Mobile Router and Home Agent (MR,HA) tunnel. As a result, the package route will be sped up and the bundle delivery time will increase. Route optimization in a layered mobile network was explored in an Internet Engineering Task Force Request for Comment (IETF RFC 4889) as a means to circumvent such limits. This study proposes a novel paradigm to improve the functionality of layered networks. The approach is built on polling a subset of routers to determine which will be in charge of the routing process, and then directing all communications via those routers rather than using the more complex higher-level mobile networks. The proposed model has less end-to-end latency than NEMO BSP. This model was run with OPNET v14.5, an optimization tool for network simulations. Top-level nested simulations resulted in a 5% reduction in end-to-end latency. Nesting at the intermediate level reduced end-to-end latency by 10%. At the third level of nesting, a 14% reduction in end-to-end latency was realized. All this considering just three levels of nesting, thus, when the nesting depth is raised, the results improve. Using smarter routers, this model may be improved to achieve best-case outcomes, making it one of the best suggested solutions for the routing constraints of layered mobile networks.","PeriodicalId":170044,"journal":{"name":"2023 International Conference in Advances in Power, Signal, and Information Technology (APSIT)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117007815","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
期刊
2023 International Conference in Advances in Power, Signal, and Information Technology (APSIT)
全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1