Engineering Research Express最新文献_第9页

Micro-expression recognition based on euler video magnification and 3D residual network under imbalanced sample 不平衡样本下基于欧拉视频放大和三维残差网络的微表情识别

Engineering Research Express Pub Date : 2024-07-03 DOI: 10.1088/2631-8695/ad5f14

Liangyu Zhu, Yujun He, Xiaoqing Yang, Hui Li, Xiangqian Long

{"title":"Micro-expression recognition based on euler video magnification and 3D residual network under imbalanced sample","authors":"Liangyu Zhu, Yujun He, Xiaoqing Yang, Hui Li, Xiangqian Long","doi":"10.1088/2631-8695/ad5f14","DOIUrl":"https://doi.org/10.1088/2631-8695/ad5f14","url":null,"abstract":"\u0000 A student's verbal behavior plays a crucial role in education, while nonverbal behavior, such as micro-expressions, significantly improves teaching quality. To address the problem of small facial expression movements, imbalanced data categories, and lack of temporal information in static expressions, a micro-expression recognition method is proposed based on Eulerian Video Magnification (EVM) and a 3D Residual Network (3D ResNet) under imbalanced samples. Firstly, face detection in the Dlib library is used to locate the face in the micro-expression video sample and crop it. Secondly, the EVM is used to magnify the motion features in micro-expressions. Then, the 3D ResNet is used to extract spatio-temporal information from micro-expression video samples, and the Cyclical Focal Loss (CFL) function is introduced in the network training process to solve the class imbalance problem in micro-expression datasets. Finally, the roles of the EVM and the CFL function in recognizing micro-expressions by the 3D ResNet are analyzed. The experimental results on the Spontaneous Micro-expression Database (SMIC) and Chinese Academy of Sciences Micro-expression Database II (CASME II) demonstrate the effectiveness and superiority of this method. The proposed method can assist in teaching evaluation and promote the development of smart classrooms, and further research is needed on the storage and computing of the proposed method on devices.","PeriodicalId":505725,"journal":{"name":"Engineering Research Express","volume":"13 S15","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141683432","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

Pattern classification of bearing faults in PMSM based on time domain feature ensembles 基于时域特征集合的 PMSM 轴承故障模式分类

Engineering Research Express Pub Date : 2024-07-03 DOI: 10.1088/2631-8695/ad5f06

G. G, Geethanjali Purushothaman

{"title":"Pattern classification of bearing faults in PMSM based on time domain feature ensembles","authors":"G. G, Geethanjali Purushothaman","doi":"10.1088/2631-8695/ad5f06","DOIUrl":"https://doi.org/10.1088/2631-8695/ad5f06","url":null,"abstract":"\u0000 This paper aims to identify an effective pattern classification method that can be employed using vibration and current data to identify bearing conditions. The authors attempted non-conventional time-domain features to detect the bearing conditions in permanent magnet synchronous motors (PMSM). This study uses two case studies with eight datasets from Paderborn University to identify the bearing conditions of 3 and 12 classes. Support vector machine, k-nearest neighbor, random forest, decision tree, and naive Bayes classifiers are attempted with 10% holdout validation for 4 data sets with 31 feature ensembles. Also, this paper investigates the Henry Gas Solubility Optimization (HGSO) feature selection approach for identifying the most discriminant features. The effectiveness of these discriminant features is verified with three bearing conditions diagnosis. Results have shown, that four feature ensembles with 2 to 10 features outperformed support vector machine, k-nearest neighbor, and random forest classifiers. In contrast to previous relevant studies, the proposed features are useful in identifying PMSM-bearing conditions with excellent accuracy in vibration and combined current signals under a wide range of operating conditions.","PeriodicalId":505725,"journal":{"name":"Engineering Research Express","volume":" 28","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141681023","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

Transformer Oil Temperature Sensing Utilizing Bundle Plastic Optical Fiber Sensor 利用捆绑式塑料光纤传感器传感变压器油温

Engineering Research Express Pub Date : 2024-07-03 DOI: 10.1088/2631-8695/ad5f15

Sazlan Kadar, N. Ngajikin, Maslina Yaacob, Muhammad Zakir Md Yasin, Mohd Aizam Talib, N. A. Cholan

引用次数: 0

Single channel speech enhancement using time-frequency attention mechanism based nested U-net model 利用基于嵌套 U 网模型的时频注意机制增强单声道语音

Engineering Research Express Pub Date : 2024-07-02 DOI: 10.1088/2631-8695/ad5e36

A. Prathipati, A.S.N. Chakravarthy

{"title":"Single channel speech enhancement using time-frequency attention mechanism based nested U-net model","authors":"A. Prathipati, A.S.N. Chakravarthy","doi":"10.1088/2631-8695/ad5e36","DOIUrl":"https://doi.org/10.1088/2631-8695/ad5e36","url":null,"abstract":"\u0000 Deep-learning models have used attention mechanisms to improve the quality and intelligibility of noisy speech, demonstrating the effectiveness of attention mechanisms. We rely on either spatial or temporal-based attention mechanisms, resulting in severe information loss. In this paper, a time-frequency attention mechanism with a nested U-network (TFANUNet) is proposed for single-channel speech enhancement. By using time-frequency attention (TFA), learns the channel, frequency and time information which is more significant for speech enhancement. Basically, the proposed model is an encoder-decoder model, where each layer in the encoder and decoder is followed by a nested dense residual dilated DensNet (NDRD) based multi-scale context aggression block. NDRD involves multiple dilated convolution with different dilatation factors to explore the large receptive area at different scales simultaneously. NDRD avoids the aliasing problem in DenseNet. We integrated the TFA and NDRD blocks into the proposed model to enable refined feature set extraction without information loss and utterance-level context aggregation, respectively. The proposed TFANUNet model results outperform baselines in terms of STOI and PESQ.","PeriodicalId":505725,"journal":{"name":"Engineering Research Express","volume":"34 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141687640","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

Analysis of a passive vibration damper for high-speed superconducting magnetic bearings 高速超导磁轴承被动减振器分析

Engineering Research Express Pub Date : 2024-07-02 DOI: 10.1088/2631-8695/ad5e38

Mostafa Baloochi, T. Espenhahn, M. Hossain, Yves Jesus Perez‐Delgado, A. Abdkader, Michael Beitelschmidt, K. Nielsch, Ruben Hühne

{"title":"Analysis of a passive vibration damper for high-speed superconducting magnetic bearings","authors":"Mostafa Baloochi, T. Espenhahn, M. Hossain, Yves Jesus Perez‐Delgado, A. Abdkader, Michael Beitelschmidt, K. Nielsch, Ruben Hühne","doi":"10.1088/2631-8695/ad5e38","DOIUrl":"https://doi.org/10.1088/2631-8695/ad5e38","url":null,"abstract":"\u0000 Superconducting magnetic bearings (SMB) based on a combination of high temperature superconductors and permanent magnets enable the realization of self-stabilized high-speed devices with significantly reduced friction. However, external vibration might couple in the bearing resulting in large amplitude oscillations due to a resonance case. A dedicated eddy current damper (ECD) might be used to eliminate these oscillations for a stable operation. The influence of such damping elements was studied for a frictionless SMB twisting system designed to speed up the conventional ring spinning process. Therefore, conductive copper rings with different thicknesses were implemented at different positions into the bearing setup as ECD. Afterward, the SMB setup was analyzed during acceleration using an array of laser distance sensors to record the displacement of the levitating permanent magnet ring in radial and axial direction, respectively. Simultaneously, a numerical model was developed to investigate the influence of the ECDs on the dynamic and static behavior of the SMB in more detail. It was shown that the simulated damping coefficients are in good agreement with the measured values, which allows further optimization of the ECD with the developed numerical model.","PeriodicalId":505725,"journal":{"name":"Engineering Research Express","volume":"10 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141687260","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

Implementation of exact thermal analysis in extended Oxley’s predictive machining theory 在扩展的奥克斯利预测加工理论中实施精确热分析

Engineering Research Express Pub Date : 2024-06-14 DOI: 10.1088/2631-8695/ad58a2

Aakash A Dubey, D. I. Lalwani

引用次数: 0

Comparison of different scale indicators and verification of rock mass classification 不同规模指标的比较和岩体分类的验证

Engineering Research Express Pub Date : 2024-06-14 DOI: 10.1088/2631-8695/ad58a6

Yuan Hong, Feifei Zhou, Changjun Li, Ming Li, Chengkun Qu

引用次数: 0

HLG-YOLOv7: Small object detection in conveyor belt damage based on leveraging hybrid local and global features HLG-YOLOv7：基于局部和全局混合特征的传送带损坏中的小物体检测

Engineering Research Express Pub Date : 2024-06-14 DOI: 10.1088/2631-8695/ad58a9

Gongxian Wang, Qiang Yue, Hui Sun, Yu Tian, Yueying Wang, Qiao Zhou

{"title":"HLG-YOLOv7: Small object detection in conveyor belt damage based on leveraging hybrid local and global features","authors":"Gongxian Wang, Qiang Yue, Hui Sun, Yu Tian, Yueying Wang, Qiao Zhou","doi":"10.1088/2631-8695/ad58a9","DOIUrl":"https://doi.org/10.1088/2631-8695/ad58a9","url":null,"abstract":"\u0000 In the industrial production process, the detection of conveyor belt damage plays a crucial role in ensuring the stable operation of the transportation system. To tackle the issues of significant changes in damage size, missed detections, and poor detection ability of small-size objects in conveyor belt surface damage detection, an improved HLG-YOLOv7 (Hybrid Local and Global Features Network) conveyor belt surface defect detection algorithm is proposed. Firstly, Next-VIT is employed as the backbone network to extract local and global features of the damage, enhancing the model's ability to extract features of different-sized damages. Additionally, to deeply utilize the extracted local and global features, the Explicit Visual Center (EVC) feature fusion module is introduced to obtain comprehensive and discriminative feature representations, further enhancing the detection capability of small objects. Lastly, a lightweight neck structure is designed using GSConv to reduce the complexity of the model. Experimental results demonstrate that the proposed method performs better at detecting small objects than existing methods. The improved algorithm achieves mAP and F1 scores of 96.24% and 97.15%, respectively, with an FPS of 28.2.","PeriodicalId":505725,"journal":{"name":"Engineering Research Express","volume":"59 11","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141338649","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

Optimizing friction stir welding of AA7075 and AA8090 aluminum alloys: a desirability-driven investigation into mechanical and microstructural enhancement 优化 AA7075 和 AA8090 铝合金的搅拌摩擦焊：对机械和微观结构改进的期望值驱动调查

Engineering Research Express Pub Date : 2024-06-14 DOI: 10.1088/2631-8695/ad58a1

Naveen Singh, Meenu Gupta

{"title":"Optimizing friction stir welding of AA7075 and AA8090 aluminum alloys: a desirability-driven investigation into mechanical and microstructural enhancement","authors":"Naveen Singh, Meenu Gupta","doi":"10.1088/2631-8695/ad58a1","DOIUrl":"https://doi.org/10.1088/2631-8695/ad58a1","url":null,"abstract":"\u0000 This research explores the multifaceted analysis of a friction-welded joint, employing Central Composite Design of Response Surface Methodology. The study integrates microstructural investigations and fracture analyses to explain the effect of process parameters on mechanical properties. The optimum settings for Friction Stir Welding of AA7075 and AA8090 were determined by assessing desirability indices. These settings comprised a tool rotation speed of 1927.7 rpm, a tool travel speed of 35 mm/min, and a tool tilt angle of 0.9°. This specific combination yielded a noteworthy combined desirability index of 0.79, considering both Ultimate Tensile Strength (UTS) and Tensile Elongation (TE). Microstructural examinations revealed distinct characteristics in the Heat-Affected Zone (HAZ), Thermo-Mechanically Affected Zone (TMAZ), and Nugget Zone (NZ). Notably, fine grain structure in the NZ was attributed to the stirring effect created by the tool pin. Fracture analyses indicated ductile fractures, with dimple size variation correlating to tensile strength. Lower dimple density in low-strength joints suggested insufficient material mixing during welding. The maximum tensile strength sample exhibited a high dimple density. These findings contribute to a comprehensive understanding of the welding process's influence on microstructure and fracture characteristics, providing valuable insights for optimizing mechanical properties in friction-welded joints.","PeriodicalId":505725,"journal":{"name":"Engineering Research Express","volume":"50 22","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141339582","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

Electro-thermal and mechanical property analysis of powder metallurgy processed, multi-stage ball milled aluminium-copper-multi walled carbon nanotube composite 粉末冶金加工、多级球磨铝铜多壁碳纳米管复合材料的电热和机械性能分析

Engineering Research Express Pub Date : 2024-06-14 DOI: 10.1088/2631-8695/ad58a4

Subham Kundu, S. Mondal

{"title":"Electro-thermal and mechanical property analysis of powder metallurgy processed, multi-stage ball milled aluminium-copper-multi walled carbon nanotube composite","authors":"Subham Kundu, S. Mondal","doi":"10.1088/2631-8695/ad58a4","DOIUrl":"https://doi.org/10.1088/2631-8695/ad58a4","url":null,"abstract":"\u0000 Abstract Aluminium Metal Matrix Composite (Al-MMC) is a favourable option for industries like automotive, aerospace, sports equipment, electronic packaging and renewable energy because of its impressive strength-to-weight ratio, effective thermal and electrical conductivity, abundant availability and reasonable cost of aluminium. Carbon nanotube (CNT) reinforced Al-MMC is popular among researchers due to its impressive strength and stiffness. The electrical and thermal conductivity of Al-CNT is a less focused field with challenges like uniform dispersion and structural integrity of CNT depending on the manufacturing process. In this paper, a novel method of Multistage ball milling (MSBM) was introduced to develop a powder metallurgy processed Al-MMC, consisting of 5-weight percentage (5 wt. %) of copper (Cu) and 0.5 to 1.5 volume percentage (0.5-1.5 vol. %) multi-walled carbon nanotubes (MWCNT). In MSBM, mixing was done in two stages with two different rpms of the ball mill to add the advantages of flake powder metallurgy with lower chances of structural damage and the agglomeration of CNT. Mechanical, electrical, thermal, and microstructure characteristics of the fixed-speed single-stage ball milling (SSBM) process and the MSBM were compared. MSBM-processed Al-5Cu-0.5CNT composites showed higher electrical conductivity (15.03%), thermal conductivity (5.88%) and hardness (9.68%) than SSBM-processed composites. Al-5Cu-0.5CNT developed by the MSBM process achieved superior electrical and thermal conductivity, surpassing pure sintered Al by 138.45% and 9.39%, respectively. Keywords: Aluminum Metal Matrix Composite, Multistage ball milling, Al-5Cu-1.5 CNT, Powder metallurgy","PeriodicalId":505725,"journal":{"name":"Engineering Research Express","volume":"17 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141342619","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