Distribution transformers play a vital role in power distribution systems,and their reliable operation is crucial for grid stability.This study presents a simulation-based framework for active fault diagnosis and earl...Distribution transformers play a vital role in power distribution systems,and their reliable operation is crucial for grid stability.This study presents a simulation-based framework for active fault diagnosis and early warning of distribution transformers,integrating Sample Ensemble Learning(SEL)with a Self-Optimizing Support Vector Machine(SO-SVM).The SEL technique enhances data diversity and mitigates class imbalance,while SO-SVM adaptively tunes its hyperparameters to improve classification accuracy.A comprehensive transformer model was developed in MATLAB/Simulink to simulate diverse fault scenarios,including inter-turn winding faults,core saturation,and thermal aging.Feature vectors were extracted from voltage,current,and temperature measurements to train and validate the proposed hybrid model.Quantitative analysis shows that the SEL–SO-SVM framework achieves a classification accuracy of 97.8%,a precision of 96.5%,and an F1-score of 97.2%.Beyond classification,the model effectively identified incipient faults,providing an early warning lead time of up to 2.5 s before significant deviations in operational parameters.This predictive capability underscores its potential for preventing catastrophic transformer failures and enabling timely maintenance actions.The proposed approach demonstrates strong applicability for enhancing the reliability and operational safety of distribution transformers in simulated environments,offering a promising foundation for future real-time and field-level implementations.展开更多
The acoustic emission (AE) method could be used to detect and locate partial discharges (PD) in cast-resin dry-type transformers.However,due to the high sound attenuation in the filled epoxy,the signal is prone to int...The acoustic emission (AE) method could be used to detect and locate partial discharges (PD) in cast-resin dry-type transformers.However,due to the high sound attenuation in the filled epoxy,the signal is prone to interference from external noises and thus,in practice,there is little possibility of detecting PD.In this study,two techniques were developed to alleviate the shortcomings of the AE method.First,a waveguide is installed on the high-voltage (HV) windings,so that the acoustic signals of PD will propagate to the AE sensors that are installed on both terminals of the waveguide.The location of the winding that has PD can then be detected from the difference in arrival time of the acoustic signals.Test results indicate that the waveguide technique is able to enhance the safety of a measurement system and offers the advantages of easy installation and higher flexibility.Second,a specially designed AE sensor pair is used to distinguish whether acoustic signals are generated by PD inside the HV winding or by the corona outside the transformers.Using these two techniques of waveguide and AE sensor pair not only greatly improves sensitivity but also increases the reliability of the measurement system.Practical test results show that the new techniques can be used to locate precisely the PD in HV windings.展开更多
critical for guiding treatment and improving patient outcomes.Traditional molecular subtyping via immuno-histochemistry(IHC)test is invasive,time-consuming,and may not fully represent tumor heterogeneity.This study pr...critical for guiding treatment and improving patient outcomes.Traditional molecular subtyping via immuno-histochemistry(IHC)test is invasive,time-consuming,and may not fully represent tumor heterogeneity.This study proposes a non-invasive approach using digital mammography images and deep learning algorithm for classifying breast cancer molecular subtypes.Four pretrained models,including two Convolutional Neural Networks(MobileNet_V3_Large and VGG-16)and two Vision Transformers(ViT_B_16 and ViT_Base_Patch16_Clip_224)were fine-tuned to classify images into HER2-enriched,Luminal,Normal-like,and Triple Negative subtypes.Hyperparameter tuning,including learning rate adjustment and layer freezing strategies,was applied to optimize performance.Among the evaluated models,ViT_Base_Patch16_Clip_224 achieved the highest test accuracy(94.44%),with equally high precision,recall,and F1-score of 0.94,demonstrating excellent generalization.MobileNet_V3_Large achieved the same accuracy but showed less training stability.In contrast,VGG-16 recorded the lowest performance,indicating a limitation in its generalizability for this classification task.The study also highlighted the superior performance of the Vision Transformer models over CNNs,particularly due to their ability to capture global contextual features and the benefit of CLIP-based pretraining in ViT_Base_Patch16_Clip_224.To enhance clinical applicability,a graphical user interface(GUI)named“BCMS Dx”was developed for streamlined subtype prediction.Deep learning applied to mammography has proven effective for accurate and non-invasive molecular subtyping.The proposed Vision Transformer-based model and supporting GUI offer a promising direction for augmenting diagnostic workflows,minimizing the need for invasive procedures,and advancing personalized breast cancer management.展开更多
Dry-Type Cast Resin Distribution Transformers(CRT)is the secondgeneration of air-cooled distribution transformers where oil is replaced by resin for electrical insulation.CRT transformers may installed indoor adjacent...Dry-Type Cast Resin Distribution Transformers(CRT)is the secondgeneration of air-cooled distribution transformers where oil is replaced by resin for electrical insulation.CRT transformers may installed indoor adjacent to or near residential areas since they are clean and safe comparing to the conventional transformers.But,as it is obvious,noise discrepancy is intrinsically accompanied with all types of transformers and is inevitable for CRT transformers too.Minimization of noise level caused by such these transformers has biological and ergonomic importance.As it is known the core of transformers is the main source of the noise generation.In this paper,experimental and numerical investigation is implemented for a large number of fabricated CRT transformers in IT Co(Iran Transfo Company)to evaluate the effective geometrical parameters of the core on the overall sound level of transformers.Noise Level of each sample is measured according to criteria of IEC60651 and is reported in units of Decibel(dB).Numerical simulation is done using noncommercial version of ANSYS Workbench software to extract first six natural frequencies and mode shapes of CRT cores which is reported in units of Hz.Three novel non-dimensional variables for geometry of the transformer core are introduced.Both experimental and numerical results show approximately similar response to these variables.Correlation between natural frequencies and noise level is evaluated statistically.Pearson factor shows that there is a robust conjunction between first two natural frequencies and noise level of CRTs.Results show that noise level decreases as the two first natural frequencies increases and vice versa,noise level increases as the two natural frequencies of the core decreases.Finally the noise level decomposed to two parts.展开更多
针对地图综合中建筑多边形化简方法依赖人工规则、自动化程度低且难以利用已有化简成果的问题,本文提出了一种基于Transformer机制的建筑多边形化简模型。该模型首先把建筑多边形映射至一定范围的网格空间,将建筑多边形的坐标串表达为...针对地图综合中建筑多边形化简方法依赖人工规则、自动化程度低且难以利用已有化简成果的问题,本文提出了一种基于Transformer机制的建筑多边形化简模型。该模型首先把建筑多边形映射至一定范围的网格空间,将建筑多边形的坐标串表达为网格序列,从而获取建筑多边形化简前后的Token序列,构建出建筑多边形化简样本对数据;随后采用Transformer架构建立模型,基于样本数据利用模型的掩码自注意力机制学习点序列之间的依赖关系,最终逐点生成新的简化多边形,从而实现建筑多边形的化简。在训练过程中,模型使用结构化的样本数据,设计了忽略特定索引的交叉熵损失函数以提升化简质量。试验设计包括主试验与泛化验证两部分。主试验基于洛杉矶1∶2000建筑数据集,分别采用0.2、0.3和0.5 mm 3种网格尺寸对多边形进行编码,实现了目标比例尺为1∶5000与1∶10000的化简。试验结果表明,在0.3 mm的网格尺寸下模型性能最优,验证集上的化简结果与人工标注的一致率超过92.0%,且针对北京部分区域的建筑多边形数据的泛化试验验证了模型的迁移能力;与LSTM模型的对比分析显示,在参数规模相近的条件下,LSTM模型无法形成有效收敛,并生成可用结果。本文证实了Transformer在处理空间几何序列任务中的潜力,且能够有效复用已有化简样本,为智能建筑多边形化简提供了具有工程实用价值的途径。展开更多
文摘Distribution transformers play a vital role in power distribution systems,and their reliable operation is crucial for grid stability.This study presents a simulation-based framework for active fault diagnosis and early warning of distribution transformers,integrating Sample Ensemble Learning(SEL)with a Self-Optimizing Support Vector Machine(SO-SVM).The SEL technique enhances data diversity and mitigates class imbalance,while SO-SVM adaptively tunes its hyperparameters to improve classification accuracy.A comprehensive transformer model was developed in MATLAB/Simulink to simulate diverse fault scenarios,including inter-turn winding faults,core saturation,and thermal aging.Feature vectors were extracted from voltage,current,and temperature measurements to train and validate the proposed hybrid model.Quantitative analysis shows that the SEL–SO-SVM framework achieves a classification accuracy of 97.8%,a precision of 96.5%,and an F1-score of 97.2%.Beyond classification,the model effectively identified incipient faults,providing an early warning lead time of up to 2.5 s before significant deviations in operational parameters.This predictive capability underscores its potential for preventing catastrophic transformer failures and enabling timely maintenance actions.The proposed approach demonstrates strong applicability for enhancing the reliability and operational safety of distribution transformers in simulated environments,offering a promising foundation for future real-time and field-level implementations.
基金supported by the National Science Council,Taiwan (No.NSC 92-2622-E-006-142)the Program of Top 100 Universities Advancement,Ministry of Education,Taiwan
文摘The acoustic emission (AE) method could be used to detect and locate partial discharges (PD) in cast-resin dry-type transformers.However,due to the high sound attenuation in the filled epoxy,the signal is prone to interference from external noises and thus,in practice,there is little possibility of detecting PD.In this study,two techniques were developed to alleviate the shortcomings of the AE method.First,a waveguide is installed on the high-voltage (HV) windings,so that the acoustic signals of PD will propagate to the AE sensors that are installed on both terminals of the waveguide.The location of the winding that has PD can then be detected from the difference in arrival time of the acoustic signals.Test results indicate that the waveguide technique is able to enhance the safety of a measurement system and offers the advantages of easy installation and higher flexibility.Second,a specially designed AE sensor pair is used to distinguish whether acoustic signals are generated by PD inside the HV winding or by the corona outside the transformers.Using these two techniques of waveguide and AE sensor pair not only greatly improves sensitivity but also increases the reliability of the measurement system.Practical test results show that the new techniques can be used to locate precisely the PD in HV windings.
基金funded by the Ministry of Higher Education(MoHE)Malaysia through the Fundamental Research Grant Scheme—Early Career Researcher(FRGS-EC),grant number FRGSEC/1/2024/ICT02/UNIMAP/02/8.
文摘critical for guiding treatment and improving patient outcomes.Traditional molecular subtyping via immuno-histochemistry(IHC)test is invasive,time-consuming,and may not fully represent tumor heterogeneity.This study proposes a non-invasive approach using digital mammography images and deep learning algorithm for classifying breast cancer molecular subtypes.Four pretrained models,including two Convolutional Neural Networks(MobileNet_V3_Large and VGG-16)and two Vision Transformers(ViT_B_16 and ViT_Base_Patch16_Clip_224)were fine-tuned to classify images into HER2-enriched,Luminal,Normal-like,and Triple Negative subtypes.Hyperparameter tuning,including learning rate adjustment and layer freezing strategies,was applied to optimize performance.Among the evaluated models,ViT_Base_Patch16_Clip_224 achieved the highest test accuracy(94.44%),with equally high precision,recall,and F1-score of 0.94,demonstrating excellent generalization.MobileNet_V3_Large achieved the same accuracy but showed less training stability.In contrast,VGG-16 recorded the lowest performance,indicating a limitation in its generalizability for this classification task.The study also highlighted the superior performance of the Vision Transformer models over CNNs,particularly due to their ability to capture global contextual features and the benefit of CLIP-based pretraining in ViT_Base_Patch16_Clip_224.To enhance clinical applicability,a graphical user interface(GUI)named“BCMS Dx”was developed for streamlined subtype prediction.Deep learning applied to mammography has proven effective for accurate and non-invasive molecular subtyping.The proposed Vision Transformer-based model and supporting GUI offer a promising direction for augmenting diagnostic workflows,minimizing the need for invasive procedures,and advancing personalized breast cancer management.
文摘Dry-Type Cast Resin Distribution Transformers(CRT)is the secondgeneration of air-cooled distribution transformers where oil is replaced by resin for electrical insulation.CRT transformers may installed indoor adjacent to or near residential areas since they are clean and safe comparing to the conventional transformers.But,as it is obvious,noise discrepancy is intrinsically accompanied with all types of transformers and is inevitable for CRT transformers too.Minimization of noise level caused by such these transformers has biological and ergonomic importance.As it is known the core of transformers is the main source of the noise generation.In this paper,experimental and numerical investigation is implemented for a large number of fabricated CRT transformers in IT Co(Iran Transfo Company)to evaluate the effective geometrical parameters of the core on the overall sound level of transformers.Noise Level of each sample is measured according to criteria of IEC60651 and is reported in units of Decibel(dB).Numerical simulation is done using noncommercial version of ANSYS Workbench software to extract first six natural frequencies and mode shapes of CRT cores which is reported in units of Hz.Three novel non-dimensional variables for geometry of the transformer core are introduced.Both experimental and numerical results show approximately similar response to these variables.Correlation between natural frequencies and noise level is evaluated statistically.Pearson factor shows that there is a robust conjunction between first two natural frequencies and noise level of CRTs.Results show that noise level decreases as the two first natural frequencies increases and vice versa,noise level increases as the two natural frequencies of the core decreases.Finally the noise level decomposed to two parts.
文摘针对地图综合中建筑多边形化简方法依赖人工规则、自动化程度低且难以利用已有化简成果的问题,本文提出了一种基于Transformer机制的建筑多边形化简模型。该模型首先把建筑多边形映射至一定范围的网格空间,将建筑多边形的坐标串表达为网格序列,从而获取建筑多边形化简前后的Token序列,构建出建筑多边形化简样本对数据;随后采用Transformer架构建立模型,基于样本数据利用模型的掩码自注意力机制学习点序列之间的依赖关系,最终逐点生成新的简化多边形,从而实现建筑多边形的化简。在训练过程中,模型使用结构化的样本数据,设计了忽略特定索引的交叉熵损失函数以提升化简质量。试验设计包括主试验与泛化验证两部分。主试验基于洛杉矶1∶2000建筑数据集,分别采用0.2、0.3和0.5 mm 3种网格尺寸对多边形进行编码,实现了目标比例尺为1∶5000与1∶10000的化简。试验结果表明,在0.3 mm的网格尺寸下模型性能最优,验证集上的化简结果与人工标注的一致率超过92.0%,且针对北京部分区域的建筑多边形数据的泛化试验验证了模型的迁移能力;与LSTM模型的对比分析显示,在参数规模相近的条件下,LSTM模型无法形成有效收敛,并生成可用结果。本文证实了Transformer在处理空间几何序列任务中的潜力,且能够有效复用已有化简样本,为智能建筑多边形化简提供了具有工程实用价值的途径。
