Abstract Compressed sensing (CS) techniques have enabled efficient acquisition and recovery of sparse high‐dimensional data via succinct low‐dimensional projections, which usually consist of an encoder and a decoder. Unlike conventional CS techniques with the encoding–decoding architecture, the uncertainty autoencoder (UAE) can sample from the learned input data distribution without an explicit likelihood function and hence avoids potential uninformative latent representations. However, existing works on UAE mainly focus on the encoders and maximize the lower bound of the mutual information between input and measurements, rather than the decoders, which brings the shortcoming that the two may not cope well. In this work, the authors propose a novel training scheme for UAE that blurs the measurements to learn the encoder and decoder simultaneously. Experimental results show that the proposed method improves the reconstruction performances when applied to UAE.
{"title":"An improved uncertainty autoencoder with blurred measurements","authors":"Ke Xu, Weiqiang Wu, Hongguang Xu","doi":"10.1049/tje2.12311","DOIUrl":"https://doi.org/10.1049/tje2.12311","url":null,"abstract":"Abstract Compressed sensing (CS) techniques have enabled efficient acquisition and recovery of sparse high‐dimensional data via succinct low‐dimensional projections, which usually consist of an encoder and a decoder. Unlike conventional CS techniques with the encoding–decoding architecture, the uncertainty autoencoder (UAE) can sample from the learned input data distribution without an explicit likelihood function and hence avoids potential uninformative latent representations. However, existing works on UAE mainly focus on the encoders and maximize the lower bound of the mutual information between input and measurements, rather than the decoders, which brings the shortcoming that the two may not cope well. In this work, the authors propose a novel training scheme for UAE that blurs the measurements to learn the encoder and decoder simultaneously. Experimental results show that the proposed method improves the reconstruction performances when applied to UAE.","PeriodicalId":22858,"journal":{"name":"The Journal of Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135347653","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}
Junpeng Wu, Jiajun Zeng, Yibo Zhou, Ye Zhang, Yiwen Zhang
Abstract In the process of electrical equipment detection based on deep learning, insufficient image samples of the target equipment will lead to detection failure. To solve this problem, an object detection network and two‐stage fine‐tuning approach based on You Only Look Once (YOLO)v4 is proposed in this paper to achieve image recognition of electrical equipment under the condition of small samples. Using the two‐stage and dual‐network method as the training strategy, the data‐rich base class samples are used to train the sample classifier based on the modified cosine similarity in the base class training stage, and the fine‐tuning is carried out in the small sample new class training stage. In the training part, the improved Retinanet network is used for coarse detection and the YOLOv4 network with Convolutional Block Attention Module (CBAM) attentional mechanism module is inserted for fine detection. The experimental results show that the average accuracy of the proposed method under the settings of 5‐shot, 10‐shot, and 30‐shot is 31.6%, 34.3%, and 52.8%, respectively, which greatly improves the ability of electrical equipment identification under the condition of few‐shot.
摘要在基于深度学习的电气设备检测过程中，目标设备的图像样本不足会导致检测失败。为了解决这一问题，本文提出了一种基于youonly Look Once (YOLO)v4的目标检测网络和两阶段微调方法，实现了小样本条件下电气设备的图像识别。采用两阶段和双网络方法作为训练策略，在基类训练阶段使用数据丰富的基类样本基于修正余弦相似度训练样本分类器，在小样本新类训练阶段进行微调。在训练部分，使用改进的Retinanet网络进行粗检测，并插入带有卷积块注意模块(Convolutional Block Attention Module, CBAM)注意机制模块的YOLOv4网络进行精细检测。实验结果表明，该方法在5‐shot、10‐shot和30‐shot设置下的平均准确率分别为31.6%、34.3%和52.8%，大大提高了在少‐shot条件下的电气设备识别能力。
{"title":"Few‐shot electrical equipment image recognition method based on an improved two‐stage fine‐tuning approach","authors":"Junpeng Wu, Jiajun Zeng, Yibo Zhou, Ye Zhang, Yiwen Zhang","doi":"10.1049/tje2.12313","DOIUrl":"https://doi.org/10.1049/tje2.12313","url":null,"abstract":"Abstract In the process of electrical equipment detection based on deep learning, insufficient image samples of the target equipment will lead to detection failure. To solve this problem, an object detection network and two‐stage fine‐tuning approach based on You Only Look Once (YOLO)v4 is proposed in this paper to achieve image recognition of electrical equipment under the condition of small samples. Using the two‐stage and dual‐network method as the training strategy, the data‐rich base class samples are used to train the sample classifier based on the modified cosine similarity in the base class training stage, and the fine‐tuning is carried out in the small sample new class training stage. In the training part, the improved Retinanet network is used for coarse detection and the YOLOv4 network with Convolutional Block Attention Module (CBAM) attentional mechanism module is inserted for fine detection. The experimental results show that the average accuracy of the proposed method under the settings of 5‐shot, 10‐shot, and 30‐shot is 31.6%, 34.3%, and 52.8%, respectively, which greatly improves the ability of electrical equipment identification under the condition of few‐shot.","PeriodicalId":22858,"journal":{"name":"The Journal of Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134961761","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}
Petra Raussi, Heli Kokkoniemi‐Tarkkanen, Kimmo Ahola, Antti Heikkinen, Mikko Uitto
Abstract 5G network slicing is promising in prioritizing time‐critical protection communication in wireless networks of smart grids. However, network slicing offered by telecommunication providers encompasses all smart grid applications, lacking granularity. Smart grid automation standards provide recommendations on prioritization of protection communication to improve reliability but only for wired connections. Therefore, this paper investigates hierarchical token bucket (HTB) traffic shaping and uplink (UL) bitrate adaptation of a live video stream for prioritizing protection communication within a 5G slice. An experimental setup combines controller‐hardware‐in‐the‐loop (CHIL) with a quality of service (QoS) measurement system for validation. The system under test consists of commercial 5G networks, intelligent electronic devices (IEDs), and merging units for validation with three smart grid applications: fault location, line differential, and intertrip protection. HTB traffic shaping improves protected faults by 47.57% in congested and 1.16% in non‐congested scenarios. UL bitrate of the video stream adaptation by 2 Mbps increases protected faults by 3.69%. HTB traffic shaping even improves prioritization with a wired connection without introducing additional delays. HTB traffic shaping must be deployed in routers to maintain good QoS for critical applications. Collaboration between utilities and telecommunication providers is essential to effectively deploy 5G network slicing on smart grids.
{"title":"Prioritizing protection communication in a 5G slice: Evaluating HTB traffic shaping and UL bitrate adaptation for enhanced reliability","authors":"Petra Raussi, Heli Kokkoniemi‐Tarkkanen, Kimmo Ahola, Antti Heikkinen, Mikko Uitto","doi":"10.1049/tje2.12309","DOIUrl":"https://doi.org/10.1049/tje2.12309","url":null,"abstract":"Abstract 5G network slicing is promising in prioritizing time‐critical protection communication in wireless networks of smart grids. However, network slicing offered by telecommunication providers encompasses all smart grid applications, lacking granularity. Smart grid automation standards provide recommendations on prioritization of protection communication to improve reliability but only for wired connections. Therefore, this paper investigates hierarchical token bucket (HTB) traffic shaping and uplink (UL) bitrate adaptation of a live video stream for prioritizing protection communication within a 5G slice. An experimental setup combines controller‐hardware‐in‐the‐loop (CHIL) with a quality of service (QoS) measurement system for validation. The system under test consists of commercial 5G networks, intelligent electronic devices (IEDs), and merging units for validation with three smart grid applications: fault location, line differential, and intertrip protection. HTB traffic shaping improves protected faults by 47.57% in congested and 1.16% in non‐congested scenarios. UL bitrate of the video stream adaptation by 2 Mbps increases protected faults by 3.69%. HTB traffic shaping even improves prioritization with a wired connection without introducing additional delays. HTB traffic shaping must be deployed in routers to maintain good QoS for critical applications. Collaboration between utilities and telecommunication providers is essential to effectively deploy 5G network slicing on smart grids.","PeriodicalId":22858,"journal":{"name":"The Journal of Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135297926","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}
Abstract Today's healthcare system relies on magnetic resonance imaging (MRI) for early diagnosis and treatment planning. For open MRI systems to achieve resolutions of about a hundred microns, a high voltage is required, as well as a specialized power supply. Negative–positive–zero (NP0) ceramic is selected for the fabrication of adjustable capacitors. Specifically, it stands for which is a classification based on the temperature coefficient of capacitance (TCC) of the ceramic material used in the capacitor. NP0 capacitors have a TCC of 0 ±30 ppm/°C, which means that their capacitance value does not change significantly with temperature and frequency. They are known for their stability and low losses, making them ideal for applications that require high accuracy and reliability, such as timing circuits for radio frequency (RF) applications. Here, MgTiO 3 –CaTiO 3 ceramic is used to make an adjustable capacitor with desired properties for MRI systems. To enhance the dielectric properties of MgTiO 3 ceramics, CaTiO 3 was added in varying concentrations. After pressing and sintering, the resulting samples were tested using a vector network analyzer in the frequency range of 10–130 MHz. The adjustable capacitor fabricated using high co‐fired NP0 ceramic may have been used for MRI applications such as tuning circuits and matching networks, where precise capacitance values and low loss are critical. MRI systems with resonance frequencies of 128 MHz require trimmers with ceramic cores ( V Breakdown = 3 kV @ 128 MHz, C min = 3 pF, C Max = 30 pF, and C variation step = 1.5 pF).
当今的医疗保健系统依赖于磁共振成像(MRI)进行早期诊断和治疗计划。开放的MRI系统要达到大约100微米的分辨率，就需要高电压，以及专门的电源。选用负-正-零(NP0)陶瓷制作可调电容器。具体来说，它代表的是基于电容器所用陶瓷材料的电容温度系数(TCC)的分类。NP0电容器的TCC为0±30 ppm/°C，这意味着它们的电容值不随温度和频率发生显著变化。它们以其稳定性和低损耗而闻名，使其成为需要高精度和可靠性的应用的理想选择，例如射频(RF)应用的定时电路。在这里，mgtio3 - catio3陶瓷被用来制造具有所需性能的可调电容器，用于MRI系统。为了提高mgtio3陶瓷的介电性能，添加了不同浓度的catio3。在压制和烧结后，使用矢量网络分析仪在10-130 MHz的频率范围内对所得样品进行测试。使用高共烧NP0陶瓷制造的可调电容器可能已用于MRI应用，如调谐电路和匹配网络，其中精确的电容值和低损耗至关重要。共振频率为128 MHz的MRI系统需要带有陶瓷芯的微调器(V击穿= 3 kV @ 128 MHz, C min = 3 pF, C Max = 30 pF, C变化步长= 1.5 pF)。
{"title":"Investigating the effects of uniaxial pressure on the preparation of MgTiO<sub>3</sub>–CaTiO<sub>3</sub> ceramic capacitors for MRI systems","authors":"Zaineb Jebri, Mahfoudh Taleb Ali, Isabelle Bord Majek","doi":"10.1049/tje2.12300","DOIUrl":"https://doi.org/10.1049/tje2.12300","url":null,"abstract":"Abstract Today's healthcare system relies on magnetic resonance imaging (MRI) for early diagnosis and treatment planning. For open MRI systems to achieve resolutions of about a hundred microns, a high voltage is required, as well as a specialized power supply. Negative–positive–zero (NP0) ceramic is selected for the fabrication of adjustable capacitors. Specifically, it stands for which is a classification based on the temperature coefficient of capacitance (TCC) of the ceramic material used in the capacitor. NP0 capacitors have a TCC of 0 ±30 ppm/°C, which means that their capacitance value does not change significantly with temperature and frequency. They are known for their stability and low losses, making them ideal for applications that require high accuracy and reliability, such as timing circuits for radio frequency (RF) applications. Here, MgTiO 3 –CaTiO 3 ceramic is used to make an adjustable capacitor with desired properties for MRI systems. To enhance the dielectric properties of MgTiO 3 ceramics, CaTiO 3 was added in varying concentrations. After pressing and sintering, the resulting samples were tested using a vector network analyzer in the frequency range of 10–130 MHz. The adjustable capacitor fabricated using high co‐fired NP0 ceramic may have been used for MRI applications such as tuning circuits and matching networks, where precise capacitance values and low loss are critical. MRI systems with resonance frequencies of 128 MHz require trimmers with ceramic cores ( V Breakdown = 3 kV @ 128 MHz, C min = 3 pF, C Max = 30 pF, and C variation step = 1.5 pF).","PeriodicalId":22858,"journal":{"name":"The Journal of Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135388350","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}
Solar photovoltaic (PV) systems will drive deep electrification of energy systems leading to clean energy 2050. However, connecting large amounts of solar PV systems on direct current (DC) networks, like solar farms and potential future DC distribution systems, would lead to over voltages and loss of solar PV power output due to voltage issues. Further, current PV integration within distribution networks operate exclusively to maximize output using maximum power point tracking algorithms, without network coordination, which may lead to reduced solar output due to voltage issues. Here, a coordinated optimization model for solar PV systems and distribution network voltage regulators is presented. The proposed model optimally controls the settings of voltage controllers (DC‐DC converters), placed at the outputs of solar PV units and selected distribution lines, while maximizing solar power output and minimizing substation power (i.e. system losses). The solar PV systems are modelled using a trained neural network. Testing various systems against uncoordinated situations revealed that the proposed model yielded an increase in solar power of up to 60.06%, in the 28‐bus case. The proposed method will be an excellent tool enabling deep electrification using solar PV system and it overcomes limitations of uncoordinated systems used in practice today.
{"title":"Coordinated optimization model for solar PV systems integrated into DC distribution networks","authors":"Eleonora Achiluzzi, B. Venkatesh","doi":"10.1049/tje2.12295","DOIUrl":"https://doi.org/10.1049/tje2.12295","url":null,"abstract":"Solar photovoltaic (PV) systems will drive deep electrification of energy systems leading to clean energy 2050. However, connecting large amounts of solar PV systems on direct current (DC) networks, like solar farms and potential future DC distribution systems, would lead to over voltages and loss of solar PV power output due to voltage issues. Further, current PV integration within distribution networks operate exclusively to maximize output using maximum power point tracking algorithms, without network coordination, which may lead to reduced solar output due to voltage issues. Here, a coordinated optimization model for solar PV systems and distribution network voltage regulators is presented. The proposed model optimally controls the settings of voltage controllers (DC‐DC converters), placed at the outputs of solar PV units and selected distribution lines, while maximizing solar power output and minimizing substation power (i.e. system losses). The solar PV systems are modelled using a trained neural network. Testing various systems against uncoordinated situations revealed that the proposed model yielded an increase in solar power of up to 60.06%, in the 28‐bus case. The proposed method will be an excellent tool enabling deep electrification using solar PV system and it overcomes limitations of uncoordinated systems used in practice today.","PeriodicalId":22858,"journal":{"name":"The Journal of Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87012747","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}
H. D. Oskouei, Morteza Khoshcheshm, M. M. Shirkolaei, Alireza Mirtaheri
One of the most important components in the radar and microwave industry that provides transmitting and receiving features for an antenna at the same time is called a circulator. Ferrite circulators are passive three‐port devices in which the RF or microwave signal is transmitted from one port to other port without leakage to the third port. One of the main disadvantages of these waveguide elements is their large dimensions and especially their height, which cannot be used in some systems due to the limited workspace. This paper solves this problem by exploiting an incomplete wall waveguide to reduce the height of the circulator by 50%. These changes always reduce the frequency bandwidth of the element, the proposed technique optimizes the dimensions of the ferrite and its magnetic characteristics and increases the bandwidth to 400 MHz in 2.9 GHz, which is the ideal bandwidth required by many radar systems that have been reached. The ferrite circulator designed and built in this article has a port with a width of 72.13 mm and a height of 17 mm in the S‐band. The method results in a low insertion loss which is less than 0.5 decibels and a high isolation which created more than 20 decibels. The designed and optimized elements have been implemented and the test results verify the theoretical results.
{"title":"Design and construction of ferrite waveguide circulator with short wall in S band","authors":"H. D. Oskouei, Morteza Khoshcheshm, M. M. Shirkolaei, Alireza Mirtaheri","doi":"10.1049/tje2.12291","DOIUrl":"https://doi.org/10.1049/tje2.12291","url":null,"abstract":"One of the most important components in the radar and microwave industry that provides transmitting and receiving features for an antenna at the same time is called a circulator. Ferrite circulators are passive three‐port devices in which the RF or microwave signal is transmitted from one port to other port without leakage to the third port. One of the main disadvantages of these waveguide elements is their large dimensions and especially their height, which cannot be used in some systems due to the limited workspace. This paper solves this problem by exploiting an incomplete wall waveguide to reduce the height of the circulator by 50%. These changes always reduce the frequency bandwidth of the element, the proposed technique optimizes the dimensions of the ferrite and its magnetic characteristics and increases the bandwidth to 400 MHz in 2.9 GHz, which is the ideal bandwidth required by many radar systems that have been reached. The ferrite circulator designed and built in this article has a port with a width of 72.13 mm and a height of 17 mm in the S‐band. The method results in a low insertion loss which is less than 0.5 decibels and a high isolation which created more than 20 decibels. The designed and optimized elements have been implemented and the test results verify the theoretical results.","PeriodicalId":22858,"journal":{"name":"The Journal of Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90963613","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}
Superheated steam acts as both a heat source and a drying medium. The study sought to predict the evolution of the moisture transport behaviour of the corn kernel at various axial distances at varying instantaneous time. The equations describing the drying phases were solved using numerical solutions with the Eulerian technique in ANSYS software. Cone geometry was used to simulate the corn kernel with initial moisture content at 20% w.b. Steam conditions were similar to what is encountered in industry, with temperatures ranging (from 120–200°C) at 1.5 m s−1 velocity. ANOVA was used to determine if there was difference between the conditions. The temporal change in moisture from the apex to the periphery varied at superheated steam temperatures 120, 160 and 200°C. At 10, 100 and 200 s the drying rate and effective moisture diffusivity of corn kernel from the centre towards the periphery differed. Post‐hoc analysis with Bonferroni adjustment revealed that moisture content (w.b.%) differed between 10 and 100 s, 10 and 200 s and 100 and 200 s. The mean difference was attributed to the drying being in the falling drying phase at 200 s and initial condensation at 10 s. Thus, at high superheated steam temperatures, dry zones can be seen as the axial distance from the apex increases toward the periphery.
过热蒸汽既是热源又是干燥介质。该研究旨在预测玉米籽粒在不同轴向距离和不同瞬时时间下水分输运行为的演变。在ANSYS软件中采用欧拉法对描述干燥阶段的方程组进行数值求解。圆锥几何形状用于模拟初始水分含量为20% w.b.b的玉米仁。蒸汽条件与工业中遇到的相似，温度范围为(120-200°C)，速度为1.5 m s - 1。采用方差分析(ANOVA)确定两种情况之间是否存在差异。在过热蒸汽温度为120、160和200℃时，水汽从顶端到外围的时间变化是不同的。在10、100和200 s时，玉米籽粒从中心向外围的干燥速率和有效水分扩散率不同。经Bonferroni调整后的事后分析显示，水分含量(w.b.%)在10 ~ 100s、10 ~ 200s和100 ~ 200s之间存在差异。平均差异是由于干燥在200秒处于下降干燥阶段，10秒处于初始冷凝阶段。因此，在高过热蒸汽温度下，干区可以看作是从顶点向外围增加的轴向距离。
{"title":"Spatial variation of moisture content along the axial distance of corn at different superheated steam drying temperatures and various instantaneous times","authors":"C. Keter, Mercy Jepchirchir Kimwa","doi":"10.1049/tje2.12297","DOIUrl":"https://doi.org/10.1049/tje2.12297","url":null,"abstract":"Superheated steam acts as both a heat source and a drying medium. The study sought to predict the evolution of the moisture transport behaviour of the corn kernel at various axial distances at varying instantaneous time. The equations describing the drying phases were solved using numerical solutions with the Eulerian technique in ANSYS software. Cone geometry was used to simulate the corn kernel with initial moisture content at 20% w.b. Steam conditions were similar to what is encountered in industry, with temperatures ranging (from 120–200°C) at 1.5 m s−1 velocity. ANOVA was used to determine if there was difference between the conditions. The temporal change in moisture from the apex to the periphery varied at superheated steam temperatures 120, 160 and 200°C. At 10, 100 and 200 s the drying rate and effective moisture diffusivity of corn kernel from the centre towards the periphery differed. Post‐hoc analysis with Bonferroni adjustment revealed that moisture content (w.b.%) differed between 10 and 100 s, 10 and 200 s and 100 and 200 s. The mean difference was attributed to the drying being in the falling drying phase at 200 s and initial condensation at 10 s. Thus, at high superheated steam temperatures, dry zones can be seen as the axial distance from the apex increases toward the periphery.","PeriodicalId":22858,"journal":{"name":"The Journal of Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85168111","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}
Wang Ning, Du Yuan, Haohao Wang, Zhu Tao, Mingxing Wu, Yang Saite
The clearing price in electricity spot market is an important reference guiding market participants to purchase energy. Current electricity price forecasting methods mainly focus on improving numerical accuracy, and the need to optimize economic benefits is ignored. However, higher numerical precision sometimes leads to lower electricity‐purchase gain. To deal with that, this paper proposes a price forecasting method that optimizes economic benefits together with numerical accuracies. A revenue‐optimizing term evaluating the relationship between the predicted price and the cost reference price is introduced to the loss function of the prosumers’ forecasting model. A sequence comparison neural network structure is proposed and added to consumers’ model, so the forecasting model is trained by also considering price trend. By co‐optimizing numerical precision and electricity‐purchase gain, the prediction is more conducive to reducing the cost of purchasing power. Price data in actual electricity market are used to verify the feasibility and improvement of the proposed method.
{"title":"Research on spot market price forecasting method considering the electricity‐purchase gain for demand side","authors":"Wang Ning, Du Yuan, Haohao Wang, Zhu Tao, Mingxing Wu, Yang Saite","doi":"10.1049/tje2.12298","DOIUrl":"https://doi.org/10.1049/tje2.12298","url":null,"abstract":"The clearing price in electricity spot market is an important reference guiding market participants to purchase energy. Current electricity price forecasting methods mainly focus on improving numerical accuracy, and the need to optimize economic benefits is ignored. However, higher numerical precision sometimes leads to lower electricity‐purchase gain. To deal with that, this paper proposes a price forecasting method that optimizes economic benefits together with numerical accuracies. A revenue‐optimizing term evaluating the relationship between the predicted price and the cost reference price is introduced to the loss function of the prosumers’ forecasting model. A sequence comparison neural network structure is proposed and added to consumers’ model, so the forecasting model is trained by also considering price trend. By co‐optimizing numerical precision and electricity‐purchase gain, the prediction is more conducive to reducing the cost of purchasing power. Price data in actual electricity market are used to verify the feasibility and improvement of the proposed method.","PeriodicalId":22858,"journal":{"name":"The Journal of Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77915740","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}
Linear Regression (LR), as one of the essential Machine Learning (ML) models, incurs massive data crunching during the training phase based on many data points. Considering the computationally intensive nature in the LR models, an optimized dedicated hardware IP core design can be very effective. This paper proposes the following novelties: (a) an optimized hardware IP core design of linear regression‐based machine learning model using high‐level synthesis (HLS). More specifically, independent application specific datapath architectures of hardware IP for computing optimal bias and intercepts and cost function in LR‐ML are presented here; (b) an optimized hardware IP core design of LR based ML model by deducing dependency graph from its corresponding mathematical foundation; (c) register transfer level (RTL) design, using HLS, of the optimized LR based ML hardware IP core for computing cost function; (d) linear regression IP core design using multi‐layered tree‐height transformation (THT) and swarm intelligence based architectural exploration for optimized HLS design.
{"title":"HLS‐based swarm intelligence driven optimized hardware IP core for linear regression‐based machine learning","authors":"A. Sengupta, Rahul Chaurasia, Mahendra Rathor","doi":"10.1049/tje2.12299","DOIUrl":"https://doi.org/10.1049/tje2.12299","url":null,"abstract":"Linear Regression (LR), as one of the essential Machine Learning (ML) models, incurs massive data crunching during the training phase based on many data points. Considering the computationally intensive nature in the LR models, an optimized dedicated hardware IP core design can be very effective. This paper proposes the following novelties: (a) an optimized hardware IP core design of linear regression‐based machine learning model using high‐level synthesis (HLS). More specifically, independent application specific datapath architectures of hardware IP for computing optimal bias and intercepts and cost function in LR‐ML are presented here; (b) an optimized hardware IP core design of LR based ML model by deducing dependency graph from its corresponding mathematical foundation; (c) register transfer level (RTL) design, using HLS, of the optimized LR based ML hardware IP core for computing cost function; (d) linear regression IP core design using multi‐layered tree‐height transformation (THT) and swarm intelligence based architectural exploration for optimized HLS design.","PeriodicalId":22858,"journal":{"name":"The Journal of Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90077711","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}
Developing a method to detect internal leakage in hydraulic cylinder, which is used for Electro‐Hydrostatic Actuators (EHA), is important to prevent serious malfunctions for aircrafts. At present, the internal leakage in an EHA cannot be accurately detected only using operational data. This paper proposed a convolutional neural networks (CNN) based method to detect internal leakage in hydraulic cylinder according to the relationship between operational state parameters of EHA and leakage in the hydraulic cylinder. A method was presented to align multi‐source signals with different forms by using the motor current as a benchmark. Because the number of monitoring signals are relatively small, a feedforward neural network (FFNN) based data augment method is proposed to increase parameters of input data set. A general method on how to detect internal leakage by combining signals alignment, data augmentation and multiscale residual CNN was proposed. The experimental results show that the proposed method can be used to accurately detect internal leakage in a hydraulic cylinder operating under non‐stationary load and velocity conditions, and the detection accuracy reached 99.8%.
{"title":"A method to detect internal leakage of hydraulic cylinder by combining data augmentation and multiscale residual CNN","authors":"Qingchuan He, Huiqi Ruan, Jun Pan, Xiaotian Lyu","doi":"10.1049/tje2.12301","DOIUrl":"https://doi.org/10.1049/tje2.12301","url":null,"abstract":"Developing a method to detect internal leakage in hydraulic cylinder, which is used for Electro‐Hydrostatic Actuators (EHA), is important to prevent serious malfunctions for aircrafts. At present, the internal leakage in an EHA cannot be accurately detected only using operational data. This paper proposed a convolutional neural networks (CNN) based method to detect internal leakage in hydraulic cylinder according to the relationship between operational state parameters of EHA and leakage in the hydraulic cylinder. A method was presented to align multi‐source signals with different forms by using the motor current as a benchmark. Because the number of monitoring signals are relatively small, a feedforward neural network (FFNN) based data augment method is proposed to increase parameters of input data set. A general method on how to detect internal leakage by combining signals alignment, data augmentation and multiscale residual CNN was proposed. The experimental results show that the proposed method can be used to accurately detect internal leakage in a hydraulic cylinder operating under non‐stationary load and velocity conditions, and the detection accuracy reached 99.8%.","PeriodicalId":22858,"journal":{"name":"The Journal of Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89021423","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：