e-Prime - Advances in Electrical Engineering, Electronics and Energy最新文献_第10页

Hybrid model for cleaning abnormal data of wind turbine power curve based on machine learning approaches 基于机器学习方法的风力发电功率曲线异常数据清理混合模型

e-Prime - Advances in Electrical Engineering, Electronics and Energy

Pub Date : 2025-06-10 DOI: 10.1016/j.prime.2025.101043

Abdelwahab Ayash Subuh , S. Hr. Aghay Kaboli , Muhammad Waqar , François Vallée

This paper addresses important challenges in wind energy prediction caused by outliers in wind data, which distort the wind turbine power curve and lead to inaccurate performance assessments and suboptimal operation strategies. The major difficulty here is detecting and eliminating these outliers from complex wind datasets, as inaccurate data can significantly impact forecasting and related activities. To overcome this challenge, the paper proposes a hybrid model combining fuzzy C-means clustering, Mahalanobis distance, and Artificial Neural Networks (ANN) to detect and remove outliers far more accurately than any individual method or other traditional hybrid method, decreasing false alarms and misses. It improves data quality and boosts the reliability of turbine performance analysis, resource assessment, and forecasting, supporting more efficient and sustainable wind-power operations. The results show (1) that the proposed hybrid model achieves 15.4 % more accuracy than the other traditional hybrid models in detecting and removing outliers. (2) The proposed hybrid model gives an overall ≈ 116.1 % improvement in outlier-detection accuracy over the individual models. (3) Adding the ANN to the proposed hybrid model boosts the outlier-detection accuracy to about a 69.5 % relative improvement. (4) Detecting and cleaning outliers by the proposed hybrid model cuts the RMSE from 2.38 to 1.27, reducing prediction error by 46.6 %. (5) The advanced hybrid model used in this study for comparison purposes achieves nearly identical accuracy to the proposed hybrid model; it reduces RMSE by ∼0.015 and MAPE by ∼0.04 pp and boosts R² by ∼0.001 while maintaining almost perfect outlier detection (99 % vs. 100 %). Although the advanced model offers a marginal edge in reconstruction quality, the lightweight, scalable proposed hybrid model remains better appropriate for real-world deployment due to its lower computational overhead and more straightforward maintenance.

本文解决了风电数据异常值引起的风能预测的重要挑战，这些异常值扭曲了风电机组的功率曲线，导致不准确的性能评估和次优运行策略。这里的主要困难是从复杂的风数据集中检测和消除这些异常值，因为不准确的数据会严重影响预测和相关活动。为了克服这一挑战，本文提出了一种结合模糊c均值聚类、马氏距离和人工神经网络（ANN）的混合模型，以比任何单一方法或其他传统混合方法更准确地检测和去除异常点，减少了误报和漏报。它提高了数据质量，提高了涡轮机性能分析、资源评估和预测的可靠性，支持更高效和可持续的风力发电运营。结果表明：(1)与其他传统混合模型相比，该混合模型在检测和去除异常点方面的准确率提高了15.4%。(2)与单个模型相比，该混合模型的异常点检测精度总体提高了约116.1%。(3)将人工神经网络加入到混合模型中，异常点检测准确率相对提高了69.5%左右。(4)混合模型对异常点的检测和清理将RMSE从2.38降低到1.27，预测误差降低46.6%。(5)本研究中用于比较的先进混合模型与提出的混合模型的精度几乎相同；它将RMSE降低了~ 0.015，MAPE降低了~ 0.04 pp，将R²提高了~ 0.001，同时保持几乎完美的离群值检测（99% vs. 100%）。尽管先进的模型在重建质量上有一定的优势，但轻量级、可扩展的混合模型仍然更适合实际部署，因为它的计算开销更低，维护更简单。

{"title":"Hybrid model for cleaning abnormal data of wind turbine power curve based on machine learning approaches","authors":"Abdelwahab Ayash Subuh , S. Hr. Aghay Kaboli , Muhammad Waqar , François Vallée","doi":"10.1016/j.prime.2025.101043","DOIUrl":"10.1016/j.prime.2025.101043","url":null,"abstract":"<div><div>This paper addresses important challenges in wind energy prediction caused by outliers in wind data, which distort the wind turbine power curve and lead to inaccurate performance assessments and suboptimal operation strategies. The major difficulty here is detecting and eliminating these outliers from complex wind datasets, as inaccurate data can significantly impact forecasting and related activities. To overcome this challenge, the paper proposes a hybrid model combining fuzzy C-means clustering, Mahalanobis distance, and Artificial Neural Networks (ANN) to detect and remove outliers far more accurately than any individual method or other traditional hybrid method, decreasing false alarms and misses. It improves data quality and boosts the reliability of turbine performance analysis, resource assessment, and forecasting, supporting more efficient and sustainable wind-power operations. The results show (1) that the proposed hybrid model achieves 15.4 % more accuracy than the other traditional hybrid models in detecting and removing outliers. (2) The proposed hybrid model gives an overall ≈ 116.1 % improvement in outlier-detection accuracy over the individual models. (3) Adding the ANN to the proposed hybrid model boosts the outlier-detection accuracy to about a 69.5 % relative improvement. (4) Detecting and cleaning outliers by the proposed hybrid model cuts the RMSE from 2.38 to 1.27, reducing prediction error by 46.6 %. (5) The advanced hybrid model used in this study for comparison purposes achieves nearly identical accuracy to the proposed hybrid model; it reduces RMSE by ∼0.015 and MAPE by ∼0.04 pp and boosts R² by ∼0.001 while maintaining almost perfect outlier detection (99 % vs. 100 %). Although the advanced model offers a marginal edge in reconstruction quality, the lightweight, scalable proposed hybrid model remains better appropriate for real-world deployment due to its lower computational overhead and more straightforward maintenance.</div></div>","PeriodicalId":100488,"journal":{"name":"e-Prime - Advances in Electrical Engineering, Electronics and Energy","volume":"13 ","pages":"Article 101043"},"PeriodicalIF":0.0,"publicationDate":"2025-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144338830","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

Memristor augmented ReRAM circuit- a versatile approach 忆阻器增强的ReRAM电路-一种通用的方法

e-Prime - Advances in Electrical Engineering, Electronics and Energy

Pub Date : 2025-06-07 DOI: 10.1016/j.prime.2025.101042

Shaik Deneyaz , Satyajeet Sahoo , Aswini Kumar Samantaray

This work presents a novel circuit design that improves the efficiency of data reading in a memristor-augmented ReRAM circuit. The proposed design replaces the standard sense amplifier with a bulk driven transistor for reading the data. The validity of our proposed design has been confirmed by the utilisation of the SPICE Memristor model and CMOS process technology such as 180 nm, 90 nm,45 nm. Hardware implementations on FPGA platforms confirm the effectiveness of the approach under process variation, ensuring reliable deployment in practical settings. In order to enhance the performance of the proposed ReRAM cell, an SSC-MCAM (Store Sense Compare) cell has been developed and tested to confirm its ability to match and not match conditions. Furthermore, a novel CAM architecture has been suggested that eliminates the need for two memristors to store both bit (B) and bitbar (BB). Instead, it only stores bit B and utilises a bulk driven transistor to sense the data. This design allows for the elimination of the match-line Sense Amplifier in our architecture, resulting in a reduction in the number of transistors and ultimately decreasing the die area.

本文提出了一种新颖的电路设计，提高了忆阻器增强型ReRAM电路的数据读取效率。提出的设计取代了标准的感测放大器与一个整体驱动晶体管读取数据。采用SPICE忆阻器模型和180nm、90nm、45nm等CMOS工艺技术，验证了设计的有效性。FPGA平台上的硬件实现证实了该方法在工艺变化下的有效性，确保了在实际环境中的可靠部署。为了提高所提出的ReRAM单元的性能，已经开发并测试了SSC-MCAM（存储感知比较）单元，以确认其匹配和不匹配条件的能力。此外，还提出了一种新的CAM架构，该架构消除了存储位(B)和位条（BB）的两个忆阻器的需要。相反，它只存储位B，并利用一个体驱动晶体管来感知数据。该设计允许在我们的架构中消除匹配线感测放大器，从而减少晶体管数量并最终减少芯片面积。

{"title":"Memristor augmented ReRAM circuit- a versatile approach","authors":"Shaik Deneyaz , Satyajeet Sahoo , Aswini Kumar Samantaray","doi":"10.1016/j.prime.2025.101042","DOIUrl":"10.1016/j.prime.2025.101042","url":null,"abstract":"<div><div>This work presents a novel circuit design that improves the efficiency of data reading in a memristor-augmented ReRAM circuit. The proposed design replaces the standard sense amplifier with a bulk driven transistor for reading the data. The validity of our proposed design has been confirmed by the utilisation of the SPICE Memristor model and CMOS process technology such as 180 nm, 90 nm,45 nm. Hardware implementations on FPGA platforms confirm the effectiveness of the approach under process variation, ensuring reliable deployment in practical settings. In order to enhance the performance of the proposed ReRAM cell, an SSC-MCAM (Store Sense Compare) cell has been developed and tested to confirm its ability to match and not match conditions. Furthermore, a novel CAM architecture has been suggested that eliminates the need for two memristors to store both bit (B) and bitbar (BB). Instead, it only stores bit B and utilises a bulk driven transistor to sense the data. This design allows for the elimination of the match-line Sense Amplifier in our architecture, resulting in a reduction in the number of transistors and ultimately decreasing the die area.</div></div>","PeriodicalId":100488,"journal":{"name":"e-Prime - Advances in Electrical Engineering, Electronics and Energy","volume":"13 ","pages":"Article 101042"},"PeriodicalIF":0.0,"publicationDate":"2025-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144270146","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

Advanced machine learning algorithms for reactive power forecasting in electric distribution systems 配电系统无功预测的先进机器学习算法

e-Prime - Advances in Electrical Engineering, Electronics and Energy

Pub Date : 2025-06-07 DOI: 10.1016/j.prime.2025.101019

Gülizar Gizem Tolun , Ömer Can Tolun , Kasım Zor

Due to the rising penetration of distributed generators into the current microgrids, reactive power management has become a crucial concern in terms of voltage stability and resilience of smart grids. In this regard, reactive power forecasting (RPF) is an essential tool for maintaining the reactive power management and planning of active electric distribution systems in which power flow is bidirectional. Machine learning (ML)-based algorithms are frequently applied to electric load forecasting owing to the fact that these methods achieve more accurate results in the short-term horizon. RPF is one of the challenging implementations of electric load forecasting and it can be characterised as a nonlinear problem with a variety of explanatory variables such as active and lagging reactive power values. In this paper, a real-time short-term RPF using ML-based algorithms including long short-term memory (LSTM) networks, random forest (RF), and extreme gradient boosted decision trees (XGBoost) were employed for an electric distribution system located in the North of England, UK. The study also incorporated convolutional neural network (CNN), gated recurrent unit (GRU) networks, and light gradient boosting machine (LightGBM) for benchmarking with the main selected methods. The experimental results demonstrated that LightGBM outperformed other models by achieving the highest accuracy with an R

^{2}

of 95.37% and the lowest root mean squared scaled error (RMSSE) of 0.541 while maintaining the shortest computation time of 0.396 s. These findings highlighted the potential of ML-based RPF techniques for improving voltage stability, optimising reactive power compensation, and enhancing energy efficiency in modern smart grids. To the best of our knowledge, there is a lack in the current literature for real-time applications of RPF and this paper is considered to fill this deficiency to create a path for aspiring researchers in the field.

由于分布式发电机在当前微电网中的渗透率不断提高，无功功率管理已成为智能电网电压稳定性和弹性方面的关键问题。在这方面，无功功率预测（RPF）是维持有功配电系统无功功率管理和规划的重要工具，其中功率流是双向的。基于机器学习（ML）的算法经常应用于电力负荷预测，因为这些方法在短期内可以获得更准确的结果。RPF是一个具有挑战性的电力负荷预测实现之一，它可以被描述为一个具有各种解释变量（如有功和滞后无功值）的非线性问题。本文采用基于ml的长短期记忆（LSTM）网络、随机森林（RF）和极端梯度增强决策树（XGBoost）算法，对英国英格兰北部的一个配电系统进行了实时短期RPF。该研究还结合了卷积神经网络（CNN）、门控循环单元（GRU）网络和光梯度增强机（LightGBM）对主要选择的方法进行了基准测试。实验结果表明，LightGBM的准确率最高，R2为95.37%，RMSSE（均方根误差）最低为0.541，计算时间最短为0.396 s，优于其他模型。这些发现突出了基于ml的RPF技术在改善电压稳定性、优化无功补偿和提高现代智能电网能效方面的潜力。据我们所知，目前文献中缺乏RPF的实时应用，本文被认为填补了这一不足，为有抱负的研究人员在该领域开辟了一条道路。

{"title":"Advanced machine learning algorithms for reactive power forecasting in electric distribution systems","authors":"Gülizar Gizem Tolun , Ömer Can Tolun , Kasım Zor","doi":"10.1016/j.prime.2025.101019","DOIUrl":"10.1016/j.prime.2025.101019","url":null,"abstract":"<div><div>Due to the rising penetration of distributed generators into the current microgrids, reactive power management has become a crucial concern in terms of voltage stability and resilience of smart grids. In this regard, reactive power forecasting (RPF) is an essential tool for maintaining the reactive power management and planning of active electric distribution systems in which power flow is bidirectional. Machine learning (ML)-based algorithms are frequently applied to electric load forecasting owing to the fact that these methods achieve more accurate results in the short-term horizon. RPF is one of the challenging implementations of electric load forecasting and it can be characterised as a nonlinear problem with a variety of explanatory variables such as active and lagging reactive power values. In this paper, a real-time short-term RPF using ML-based algorithms including long short-term memory (LSTM) networks, random forest (RF), and extreme gradient boosted decision trees (XGBoost) were employed for an electric distribution system located in the North of England, UK. The study also incorporated convolutional neural network (CNN), gated recurrent unit (GRU) networks, and light gradient boosting machine (LightGBM) for benchmarking with the main selected methods. The experimental results demonstrated that LightGBM outperformed other models by achieving the highest accuracy with an R<span><math><msup><mrow></mrow><mrow><mn>2</mn></mrow></msup></math></span> of 95.37% and the lowest root mean squared scaled error (RMSSE) of 0.541 while maintaining the shortest computation time of 0.396 s. These findings highlighted the potential of ML-based RPF techniques for improving voltage stability, optimising reactive power compensation, and enhancing energy efficiency in modern smart grids. To the best of our knowledge, there is a lack in the current literature for real-time applications of RPF and this paper is considered to fill this deficiency to create a path for aspiring researchers in the field.</div></div>","PeriodicalId":100488,"journal":{"name":"e-Prime - Advances in Electrical Engineering, Electronics and Energy","volume":"13 ","pages":"Article 101019"},"PeriodicalIF":0.0,"publicationDate":"2025-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144313141","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

On the impact of various mobility concepts on integrated energy systems 各种流动性概念对综合能源系统的影响

e-Prime - Advances in Electrical Engineering, Electronics and Energy

Pub Date : 2025-06-06 DOI: 10.1016/j.prime.2025.101041

Henning Meschede, Lukas Knorr

Integrated energy systems are a key towards sustainable energy supply. Sector coupling enables the use of renewable electricity in so far not electrified sectors to replace current use of fossil fuel-based energy supply. One of such sectors is the mobility sector, in which currently mostly fossil fuel-based engines are used. However, various different possible mobility concepts are discussed aiming on less greenhouse gas emissions in the transport sector. From an energy system’s perspective, these options have different impacts regarding their energy efficiency, their suitability as flexible loads, or their suitability to act as bidirectional energy storage. In this study, we therefore analyse the impact of different mobility concepts, including also new concepts like shared autonomous electric vehicles (SAEV), and thus go beyond a continuation of the current dominance of motorised individual transport. For this purpose, we model different scenarios for the case of a German city using linear optimisation for charging. Our results underline the different opportunities for single concepts and the role of modal split in the overall energy system. The wide use of SAEV might reduce the final energy transport due to higher efficiency, but as long as individual motorised transport by cars dominates the mobility sector, effective defossilisation without electrified cars is not possible. Best results regarding energy efficiency as well as utilisation of renewables can be reached in scenarios considering a mixture of motorised individual transport, public transport as well as non-motorised or reduced transport.

综合能源系统是实现可持续能源供应的关键。部门耦合使迄今为止尚未电气化的部门能够使用可再生电力取代目前使用的化石燃料能源供应。其中一个部门是移动部门，目前主要使用基于化石燃料的发动机。然而，为了减少运输部门的温室气体排放，讨论了各种不同的可能的移动概念。从能源系统的角度来看，这些选择对它们的能源效率、作为灵活负载的适用性或作为双向储能的适用性有不同的影响。因此，在本研究中，我们分析了不同移动概念的影响，包括共享自动驾驶电动汽车（SAEV）等新概念，从而超越了当前机动化个人交通的主导地位。为此，我们对德国城市的不同场景进行建模，使用线性优化收费。我们的结果强调了单一概念的不同机会和模态分裂在整个能源系统中的作用。由于效率的提高，SAEV的广泛使用可能会减少最终的能源运输，但只要汽车的个人机动运输主导着交通领域，没有电动汽车的有效去化石化是不可能的。考虑到机动个人交通、公共交通以及非机动或减少交通的混合情况，可以达到能源效率和可再生能源利用的最佳结果。

{"title":"On the impact of various mobility concepts on integrated energy systems","authors":"Henning Meschede, Lukas Knorr","doi":"10.1016/j.prime.2025.101041","DOIUrl":"10.1016/j.prime.2025.101041","url":null,"abstract":"<div><div>Integrated energy systems are a key towards sustainable energy supply. Sector coupling enables the use of renewable electricity in so far not electrified sectors to replace current use of fossil fuel-based energy supply. One of such sectors is the mobility sector, in which currently mostly fossil fuel-based engines are used. However, various different possible mobility concepts are discussed aiming on less greenhouse gas emissions in the transport sector. From an energy system’s perspective, these options have different impacts regarding their energy efficiency, their suitability as flexible loads, or their suitability to act as bidirectional energy storage. In this study, we therefore analyse the impact of different mobility concepts, including also new concepts like shared autonomous electric vehicles (SAEV), and thus go beyond a continuation of the current dominance of motorised individual transport. For this purpose, we model different scenarios for the case of a German city using linear optimisation for charging. Our results underline the different opportunities for single concepts and the role of modal split in the overall energy system. The wide use of SAEV might reduce the final energy transport due to higher efficiency, but as long as individual motorised transport by cars dominates the mobility sector, effective defossilisation without electrified cars is not possible. Best results regarding energy efficiency as well as utilisation of renewables can be reached in scenarios considering a mixture of motorised individual transport, public transport as well as non-motorised or reduced transport.</div></div>","PeriodicalId":100488,"journal":{"name":"e-Prime - Advances in Electrical Engineering, Electronics and Energy","volume":"13 ","pages":"Article 101041"},"PeriodicalIF":0.0,"publicationDate":"2025-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144296865","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

Switched capacitor high voltage gain DC-DC Converters for hydrogen vehicles: a detailed comprehensive analysis 氢燃料汽车用开关电容高压增益DC-DC转换器：详细综合分析

e-Prime - Advances in Electrical Engineering, Electronics and Energy

Pub Date : 2025-06-06 DOI: 10.1016/j.prime.2025.101039

Anusha Gaddala , AVV. Sudhakar , Shaik. Rafikiran , Ram Ragotham Deshmukh , CH Hussaian Basha

At present, Fuel Cell Electric Vehicles (FCEVS) are used worldwide because of their efficiency, clean energy production, and exceptional energy storage capabilities, positioning them as a viable alternative to conventional fossil-fuel-based transportation. However, the low-voltage output of fuel cells requires high-gain DC-DC converters to meet the necessary voltage levels for the DC bus in FCEVS. In this work, the first objective is the analysis of various categories of fuel cell models, and the identification of suitable fuel cells for hydrogen vehicles has been done in terms of operational temperature and efficiency. After that, the identification of the various switched capacitors DC-DC converters for fuel cell voltage enhancement has been studied by considering the parameters, are inductive elements used for the development of converters, capacitors selected for stabilising the voltage levels, and power semiconductor diodes. Also, the converter voltage gains, implementation cost, voltage stress appearing across diodes, advantages, limitations, and design complexity parameters are discussed for hydrogen vehicle systems. Finally, the third objective gives the ongoing trends of advanced control techniques for DC-DC converters, and their importance is discussed by utilising the MATLAB/Simulink environment.

目前，燃料电池电动汽车（fcev）因其高效、清洁能源生产和卓越的储能能力而在全球范围内得到广泛应用，使其成为传统化石燃料交通工具的可行替代方案。然而，燃料电池的低压输出需要高增益DC-DC转换器来满足fcev中直流母线所需的电压水平。在这项工作中，第一个目标是对各种类型的燃料电池模型进行分析，并从工作温度和效率方面确定适合氢燃料汽车的燃料电池。之后，通过考虑参数，研究了用于燃料电池电压增强的各种开关电容器DC-DC变换器的识别，用于变换器开发的电感元件，用于稳定电压水平的电容器和功率半导体二极管。此外，还讨论了氢燃料汽车系统的变换器电压增益、实现成本、二极管间出现的电压应力、优点、局限性和设计复杂性参数。最后，第三个目标给出了DC-DC转换器先进控制技术的发展趋势，并利用MATLAB/Simulink环境讨论了它们的重要性。

{"title":"Switched capacitor high voltage gain DC-DC Converters for hydrogen vehicles: a detailed comprehensive analysis","authors":"Anusha Gaddala , AVV. Sudhakar , Shaik. Rafikiran , Ram Ragotham Deshmukh , CH Hussaian Basha","doi":"10.1016/j.prime.2025.101039","DOIUrl":"10.1016/j.prime.2025.101039","url":null,"abstract":"<div><div>At present, Fuel Cell Electric Vehicles (FCEVS) are used worldwide because of their efficiency, clean energy production, and exceptional energy storage capabilities, positioning them as a viable alternative to conventional fossil-fuel-based transportation. However, the low-voltage output of fuel cells requires high-gain DC-DC converters to meet the necessary voltage levels for the DC bus in FCEVS. In this work, the first objective is the analysis of various categories of fuel cell models, and the identification of suitable fuel cells for hydrogen vehicles has been done in terms of operational temperature and efficiency. After that, the identification of the various switched capacitors DC-DC converters for fuel cell voltage enhancement has been studied by considering the parameters, are inductive elements used for the development of converters, capacitors selected for stabilising the voltage levels, and power semiconductor diodes. Also, the converter voltage gains, implementation cost, voltage stress appearing across diodes, advantages, limitations, and design complexity parameters are discussed for hydrogen vehicle systems. Finally, the third objective gives the ongoing trends of advanced control techniques for DC-DC converters, and their importance is discussed by utilising the MATLAB/Simulink environment.</div></div>","PeriodicalId":100488,"journal":{"name":"e-Prime - Advances in Electrical Engineering, Electronics and Energy","volume":"13 ","pages":"Article 101039"},"PeriodicalIF":0.0,"publicationDate":"2025-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144290450","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 novel framework for multi-sensor data fusion in bearing fault diagnosis using continuous wavelet transform and transfer learning 基于连续小波变换和迁移学习的轴承故障诊断多传感器数据融合新框架

e-Prime - Advances in Electrical Engineering, Electronics and Energy

Pub Date : 2025-06-06 DOI: 10.1016/j.prime.2025.101025

Iman Makrouf , Mourad Zegrari , Khalid Dahi , Ilias Ouachtouk

Intelligent fault diagnosis (IFD) is crucial in industrial settings, leveraging big data from various sensors and machine learning advancements to monitor critical components such as rolling bearings. While IFD-based deep learning and multi-sensor fusion offer promising solutions, challenges remain in integrating heterogeneous data and managing computational complexity. Transfer learning from pre-trained models can mitigate these issues, particularly with limited labeled datasets common in industrial applications. However, integrating transfer learning with multi-sensor fusion for diagnosing complex fault scenarios, especially combined bearing defects under varying operational conditions, remains underexplored in current research. This paper proposes a novel multi-sensor fusion approach for bearing fault diagnosis that combines vibration and acoustic signals within a transfer learning framework. Continuous Wavelet Transform (CWT) is applied to multi-sensor inputs, and the resulting wavelet coefficients are fused using the Maximum Energy to Shannon Entropy Ratio (ME-to-SER) criterion to fine-tune pre-trained Convolutional Neural Networks (CNNs). The effectiveness of the proposed method is validated on the Spectra Quest Machinery Fault Simulator (MFS) across various bearing fault scenarios, including combined faults, under variable speeds. The proposed approach achieves high accuracy (up to 100%) using multi-modal fused data, outperforming single-modality methods. It excels in complex fault classification and maintains robustness under various operational conditions. The fusion approach efficiently handles heterogeneous data to enhance diagnostic reliability, whereas transfer learning effectively addresses limited labeled datasets and reduces the computational burden of training deep CNNs from scratch.

智能故障诊断（IFD）在工业环境中至关重要，它利用来自各种传感器的大数据和机器学习的进步来监测滚动轴承等关键部件。虽然基于ifd的深度学习和多传感器融合提供了有前途的解决方案，但在集成异构数据和管理计算复杂性方面仍然存在挑战。从预训练模型中迁移学习可以缓解这些问题，特别是在工业应用中常见的有限标记数据集。然而，如何将迁移学习与多传感器融合集成到复杂故障场景的诊断中，特别是在不同工况下组合轴承缺陷的诊断，目前的研究还不够深入。提出了一种在迁移学习框架下结合振动和声信号的轴承故障多传感器融合诊断方法。将连续小波变换（CWT）应用于多传感器输入，并利用最大能量与香农熵比（ME-to-SER）准则对得到的小波系数进行融合，以微调预训练卷积神经网络（cnn）。在spectrum Quest机械故障模拟器（MFS）上验证了该方法的有效性，该故障模拟了各种轴承故障场景，包括变速下的组合故障。该方法使用多模态融合数据实现了高准确度（高达100%），优于单模态方法。该方法具有较好的复杂故障分类能力，并能在各种运行条件下保持鲁棒性。融合方法有效地处理异构数据以提高诊断可靠性，而迁移学习方法有效地处理有限的标记数据集，并减少从头开始训练深度cnn的计算负担。

{"title":"A novel framework for multi-sensor data fusion in bearing fault diagnosis using continuous wavelet transform and transfer learning","authors":"Iman Makrouf , Mourad Zegrari , Khalid Dahi , Ilias Ouachtouk","doi":"10.1016/j.prime.2025.101025","DOIUrl":"10.1016/j.prime.2025.101025","url":null,"abstract":"<div><div>Intelligent fault diagnosis (IFD) is crucial in industrial settings, leveraging big data from various sensors and machine learning advancements to monitor critical components such as rolling bearings. While IFD-based deep learning and multi-sensor fusion offer promising solutions, challenges remain in integrating heterogeneous data and managing computational complexity. Transfer learning from pre-trained models can mitigate these issues, particularly with limited labeled datasets common in industrial applications. However, integrating transfer learning with multi-sensor fusion for diagnosing complex fault scenarios, especially combined bearing defects under varying operational conditions, remains underexplored in current research. This paper proposes a novel multi-sensor fusion approach for bearing fault diagnosis that combines vibration and acoustic signals within a transfer learning framework. Continuous Wavelet Transform (CWT) is applied to multi-sensor inputs, and the resulting wavelet coefficients are fused using the Maximum Energy to Shannon Entropy Ratio (ME-to-SER) criterion to fine-tune pre-trained Convolutional Neural Networks (CNNs). The effectiveness of the proposed method is validated on the Spectra Quest Machinery Fault Simulator (MFS) across various bearing fault scenarios, including combined faults, under variable speeds. The proposed approach achieves high accuracy (up to 100%) using multi-modal fused data, outperforming single-modality methods. It excels in complex fault classification and maintains robustness under various operational conditions. The fusion approach efficiently handles heterogeneous data to enhance diagnostic reliability, whereas transfer learning effectively addresses limited labeled datasets and reduces the computational burden of training deep CNNs from scratch.</div></div>","PeriodicalId":100488,"journal":{"name":"e-Prime - Advances in Electrical Engineering, Electronics and Energy","volume":"13 ","pages":"Article 101025"},"PeriodicalIF":0.0,"publicationDate":"2025-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144240974","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

Stochastic optimization for siting and sizing of renewable distributed generation and D-STATCOMs 可再生分布式发电和d - statcom选址和规模的随机优化

e-Prime - Advances in Electrical Engineering, Electronics and Energy

Pub Date : 2025-06-04 DOI: 10.1016/j.prime.2025.101026

Alejandro Valencia-Díaz, Sebastián García H., Ricardo A. Hincapie I.

This paper presents a novel methodology for the optimal placement and sizing of distributed renewable generators and D-STATCOMs in electrical distribution systems. The problem is formulated as a mixed-integer second-order cone stochastic model with an objective function that minimizes the investment costs of purchasing and installing D-STATCOMs, wind turbines, photovoltaic systems, and small hydropower plants, as well as the expected value of energy purchase cost by the distribution company. A two-stage stochastic programming formulation addresses uncertainties in electrical demand, energy prices, wind-based distributed generation, solar-based distributed generation, and small hydropower-based distributed generation. Stochastic scenarios are generated using the k-means clustering technique. Moreover, a relaxed convex model is proposed to reduce the number of candidate nodes for installation, significantly improving computational efficiency while ensuring optimality. The proposed methodology’s accuracy, efficiency, and robustness are validated on two benchmark distribution systems with 70 and 136 nodes, respectively. The results demonstrate that the simultaneous integration of distributed renewable generators and D-STATCOMs effectively reduces operational costs and energy losses, achieving a loss reduction of 42.3% and 13.6% for the 70-node and 136-node test systems, respectively, while enhancing voltage regulation and improving the loading of network components. Furthermore, the model estimates the cost reductions required for solar and wind technologies to become economically viable under uncertainty, providing a practical tool for policymakers to design effective financial incentives. This feature is particularly relevant for developing countries, where high capital costs and limited public resources hinder renewable energy integration.

本文提出了一种分布式可再生能源发电机和d - statcom在配电系统中的最佳布局和尺寸的新方法。该问题是一个混合整数二阶锥随机模型，其目标函数是使d- statcom、风力涡轮机、光伏系统和小型水电站的购买和安装投资成本以及配电公司的能源购买成本期望值最小化。一个两阶段随机规划公式解决了电力需求、能源价格、风能分布式发电、太阳能分布式发电和小型水力分布式发电的不确定性。随机场景使用k-means聚类技术生成。此外，提出了一种松弛的凸模型来减少候选节点的安装数量，在保证最优性的同时显著提高了计算效率。在70节点和136节点的基准配电系统上验证了该方法的准确性、效率和鲁棒性。结果表明，分布式可再生能源发电机组与D-STATCOMs同时集成，有效降低了运行成本和能量损耗，70节点和136节点测试系统的损耗分别降低了42.3%和13.6%，同时增强了电压调节能力，改善了网络组件的负载。此外，该模型估计了在不确定性下太阳能和风能技术在经济上可行所需的成本降低，为政策制定者设计有效的财政激励措施提供了实用工具。这一特点对发展中国家尤为重要，在这些国家，高昂的资本成本和有限的公共资源阻碍了可再生能源的整合。

{"title":"Stochastic optimization for siting and sizing of renewable distributed generation and D-STATCOMs","authors":"Alejandro Valencia-Díaz, Sebastián García H., Ricardo A. Hincapie I.","doi":"10.1016/j.prime.2025.101026","DOIUrl":"10.1016/j.prime.2025.101026","url":null,"abstract":"<div><div>This paper presents a novel methodology for the optimal placement and sizing of distributed renewable generators and D-STATCOMs in electrical distribution systems. The problem is formulated as a mixed-integer second-order cone stochastic model with an objective function that minimizes the investment costs of purchasing and installing D-STATCOMs, wind turbines, photovoltaic systems, and small hydropower plants, as well as the expected value of energy purchase cost by the distribution company. A two-stage stochastic programming formulation addresses uncertainties in electrical demand, energy prices, wind-based distributed generation, solar-based distributed generation, and small hydropower-based distributed generation. Stochastic scenarios are generated using the k-means clustering technique. Moreover, a relaxed convex model is proposed to reduce the number of candidate nodes for installation, significantly improving computational efficiency while ensuring optimality. The proposed methodology’s accuracy, efficiency, and robustness are validated on two benchmark distribution systems with 70 and 136 nodes, respectively. The results demonstrate that the simultaneous integration of distributed renewable generators and D-STATCOMs effectively reduces operational costs and energy losses, achieving a loss reduction of 42.3% and 13.6% for the 70-node and 136-node test systems, respectively, while enhancing voltage regulation and improving the loading of network components. Furthermore, the model estimates the cost reductions required for solar and wind technologies to become economically viable under uncertainty, providing a practical tool for policymakers to design effective financial incentives. This feature is particularly relevant for developing countries, where high capital costs and limited public resources hinder renewable energy integration.</div></div>","PeriodicalId":100488,"journal":{"name":"e-Prime - Advances in Electrical Engineering, Electronics and Energy","volume":"13 ","pages":"Article 101026"},"PeriodicalIF":0.0,"publicationDate":"2025-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144253680","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

Potential for climate protection in hospitals 医院气候保护的潜力

e-Prime - Advances in Electrical Engineering, Electronics and Energy

Pub Date : 2025-06-02 DOI: 10.1016/j.prime.2025.101037

Oliver Wagner, Lena Tholen

Achieving national and international climate protection targets is a major challenge for many stakeholders. An often overlooked sector in this context is the healthcare sector. This is particularly significant because hospitals play a crucial role in sustainability. On the one hand, climate change poses the greatest global health threat of the 21^st century. Hospitals will inevitably face increasing challenges due to climate change, such as the emergence of new pathogens or if extreme heat exacerbates preexisting cardiovascular conditions, leading to more health complications. On the other hand, hospitals are energy-intensive and significantly contribute to climate change. In Germany, the healthcare sector accounts for 5.2 percent of CO₂ emissions, with hospitals being a major source. The need for energy-efficient modernization in hospitals is urgent, especially since they are part of our critical infrastructure. Ensuring their energy supply, even in crises, is vital for a resilient and independent energy system. Given the importance of climate protection in the healthcare sector, this article analyses which strategies hospitals should pursue to achieve climate protection targets and which measures should be prioritized. In addition, the analysis includes an estimation of the associated costs, providing a basis for understanding the financial implications of climate mitigation efforts in hospital settings. Through stakeholder workshops and a narrative literature review, we have identified 10 suitable climate protection measures for the hospital sector. Our initial cost analysis indicates that implementing these measures would require an investment of approximately 7.1 billion euros for the 315 hospitals in North Rhine-Westphalia.

实现国家和国际气候保护目标是许多利益攸关方面临的重大挑战。在这种情况下，一个经常被忽视的部门是医疗保健部门。这一点尤其重要，因为医院在可持续性方面发挥着至关重要的作用。一方面，气候变化是21世纪最大的全球健康威胁。由于气候变化，医院将不可避免地面临越来越多的挑战，例如出现新的病原体，或者极端高温会加剧原有的心血管疾病，导致更多的健康并发症。另一方面，医院是能源密集型的，对气候变化有很大影响。在德国，医疗保健行业占二氧化碳排放量的5.2%，医院是一个主要来源。医院迫切需要节能现代化，特别是因为它们是我们关键基础设施的一部分。确保他们的能源供应，即使在危机中，对于一个有弹性和独立的能源系统至关重要。鉴于气候保护在医疗保健部门的重要性，本文分析了医院应该采取哪些策略来实现气候保护目标，哪些措施应该优先考虑。此外，该分析还包括对相关费用的估计，为了解医院环境中减缓气候变化工作的财务影响提供了基础。通过利益相关者研讨会和叙述性文献审查，我们为医院部门确定了10项适当的气候保护措施。我们的初步成本分析表明，实施这些措施将需要为北莱茵-威斯特伐利亚州的315家医院投资约71亿欧元。

{"title":"Potential for climate protection in hospitals","authors":"Oliver Wagner, Lena Tholen","doi":"10.1016/j.prime.2025.101037","DOIUrl":"10.1016/j.prime.2025.101037","url":null,"abstract":"<div><div>Achieving national and international climate protection targets is a major challenge for many stakeholders. An often overlooked sector in this context is the healthcare sector. This is particularly significant because hospitals play a crucial role in sustainability. On the one hand, climate change poses the greatest global health threat of the 21<sup>st</sup> century. Hospitals will inevitably face increasing challenges due to climate change, such as the emergence of new pathogens or if extreme heat exacerbates preexisting cardiovascular conditions, leading to more health complications. On the other hand, hospitals are energy-intensive and significantly contribute to climate change. In Germany, the healthcare sector accounts for 5.2 percent of CO<sub>2</sub> emissions, with hospitals being a major source. The need for energy-efficient modernization in hospitals is urgent, especially since they are part of our critical infrastructure. Ensuring their energy supply, even in crises, is vital for a resilient and independent energy system. Given the importance of climate protection in the healthcare sector, this article analyses which strategies hospitals should pursue to achieve climate protection targets and which measures should be prioritized. In addition, the analysis includes an estimation of the associated costs, providing a basis for understanding the financial implications of climate mitigation efforts in hospital settings. Through stakeholder workshops and a narrative literature review, we have identified 10 suitable climate protection measures for the hospital sector. Our initial cost analysis indicates that implementing these measures would require an investment of approximately 7.1 billion euros for the 315 hospitals in North Rhine-Westphalia.</div></div>","PeriodicalId":100488,"journal":{"name":"e-Prime - Advances in Electrical Engineering, Electronics and Energy","volume":"13 ","pages":"Article 101037"},"PeriodicalIF":0.0,"publicationDate":"2025-06-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144253681","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

Junction temperature prediction Model Development with Co-simulation 结合联合仿真的结温预测模型开发

e-Prime - Advances in Electrical Engineering, Electronics and Energy

Pub Date : 2025-06-01 DOI: 10.1016/j.prime.2025.101033

Mustafa Ozden , Gokhan Ozkan , S M Imrat Rahman , Elutunji Buraimoh , Laxman Timilsina , Behnaz Papari , Christopher S. Edrington

This study examines the thermal behavior and junction temperature of MOSFET modules under varying operating conditions using ANSYS/Fluent software, with simulations managed through Python/Jupyter Notebook. Two different approaches are evaluated: the Temperature-Responsive Power Loss Calculation (TRPLC) and the Temperature-Agnostic Power Loss Calculation (TAPLC). In the TRPLC approach, power loss is calculated as a func- tion of the junction temperature, which is updated at each time step. In contrast, the TAPLC approach relies on four predefined power loss curves derived from the MOSFET datasheet, with each curve simulated separately. Unlike TRPLC, this method does not account for the relationship between junction temperature and power loss, resulting in significantly high junction temperature values at higher power loss levels. By dynamically recalculat- ing power loss at every step, the TRPLC approach provides more realistic results compared to TAPLC. These findings underscore the importance of incorporating temperature-dependent calculations to enhance the accuracy of thermal performance predictions under practical operational scenarios.

本研究使用ANSYS/Fluent软件，通过Python/Jupyter Notebook进行模拟，研究了不同工作条件下MOSFET模块的热行为和结温。评估了两种不同的方法：温度响应功率损耗计算（TRPLC）和温度不可知功率损耗计算（TAPLC）。在TRPLC方法中，功耗作为结温的函数计算，结温在每个时间步长更新。相比之下，TAPLC方法依赖于从MOSFET数据表中导出的四条预定义的功率损耗曲线，每个曲线分别进行模拟。与TRPLC不同的是，该方法不考虑结温和功率损耗之间的关系，从而在更高的功率损耗水平下产生显着的高结温值。通过动态地重新计算每一步的功率损耗，与TAPLC相比，TRPLC方法提供了更真实的结果。这些发现强调了结合温度相关计算来提高实际操作场景下热性能预测准确性的重要性。

{"title":"Junction temperature prediction Model Development with Co-simulation","authors":"Mustafa Ozden , Gokhan Ozkan , S M Imrat Rahman , Elutunji Buraimoh , Laxman Timilsina , Behnaz Papari , Christopher S. Edrington","doi":"10.1016/j.prime.2025.101033","DOIUrl":"10.1016/j.prime.2025.101033","url":null,"abstract":"<div><div>This study examines the thermal behavior and junction temperature of MOSFET modules under varying operating conditions using ANSYS/Fluent software, with simulations managed through Python/Jupyter Notebook. Two different approaches are evaluated: the Temperature-Responsive Power Loss Calculation (TRPLC) and the Temperature-Agnostic Power Loss Calculation (TAPLC). In the TRPLC approach, power loss is calculated as a func- tion of the junction temperature, which is updated at each time step. In contrast, the TAPLC approach relies on four predefined power loss curves derived from the MOSFET datasheet, with each curve simulated separately. Unlike TRPLC, this method does not account for the relationship between junction temperature and power loss, resulting in significantly high junction temperature values at higher power loss levels. By dynamically recalculat- ing power loss at every step, the TRPLC approach provides more realistic results compared to TAPLC. These findings underscore the importance of incorporating temperature-dependent calculations to enhance the accuracy of thermal performance predictions under practical operational scenarios.</div></div>","PeriodicalId":100488,"journal":{"name":"e-Prime - Advances in Electrical Engineering, Electronics and Energy","volume":"12 ","pages":"Article 101033"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144212680","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

Advanced signal processing algorithm for fault classification and localization in VSC-HVDC based Offshore wind farm 基于VSC-HVDC的海上风电场故障分类与定位的先进信号处理算法

e-Prime - Advances in Electrical Engineering, Electronics and Energy

Pub Date : 2025-06-01 DOI: 10.1016/j.prime.2025.101031

Rehana Perveen

This work provides real-time validation on the RTDS platform by the use of S-transform, Ensemble Empirical Mode Decomposition (EEMD), and SVM, for quick and reliable detection of AC/DC faults. Next for classification, features extracted through intrinsic mode function decomposed by EMD and EEMD and classified distinctly using support vector machine techniques. The simulation results reveal that S-transform and IMF1-H in association with MPNN and LSSVM can effectively detect and classify AC/DC faults even under raw signal conditions. This paper also presents the fault localization in the high-voltage direct current cable line connected to OWF by traveling wave and EEMD. The detection and classification are carried out on an offshore wind farm (OWF) system integrated to an onshore grid through a voltage source converter-high voltage direct current (VSC-HVDC) in MATLAB, as well as in RTDS(real time digital simulation).

本文通过s变换、集成经验模态分解（EEMD）和支持向量机（SVM）在RTDS平台上进行实时验证，快速可靠地检测交/直流故障。接下来进行分类，通过EMD和EEMD分解内禀模态函数提取特征，使用支持向量机技术进行清晰分类。仿真结果表明，即使在原始信号条件下，s变换和IMF1-H结合MPNN和LSSVM也能有效地检测和分类交/直流故障。本文还介绍了用行波法和EEMD法对连接OWF的高压直流电缆线路进行故障定位的方法。在MATLAB和RTDS（实时数字仿真）中，对通过电压源变换器-高压直流（vcs - hvdc）集成到陆上电网的海上风电场（OWF）系统进行了检测和分类。

引用次数: 0