摘要:
The state of angle cocks determines the air connectivity of freight trains, and detecting their state is helpful to improve the safety of the running trains. Although the current research for fault detection of angle cocks has achieved high accuracy, it only focuses on the detection of the closed state and non-closed state and treats them as normal and abnormal states, respectively. Since the non-closed state includes the fully open state and the misalignment state, while the latter may lead to brake abnormally, it is very necessary to further detect the misalignment state from the non-closed state. In this paper, we propose a coarse-to-fine localization method to achieve this goal. Firstly, the localization result of an angle cock is obtained by using the YOLOv4 model. Following that, the SVM model combined with the HOG feature of the localization result of an angle cock is used to further obtain its handle localization result. After that, the HOG feature of the sub-image only containing the handle localization result continues to be used in the SVM model to detect whether the angle cock is in the non-closed state or not. When the angle cock is in the non-closed state, its handle curve is fitted by binarization and window search, and the tilt angle of the handle is calculated by the minimum bounding rectangle. Finally, the misalignment state is detected when the tilt angle of the handle is less than the threshold. The effectiveness and robustness of the proposed method are verified by extensive experiments, and the accuracy of misalignment state detection for angle cocks reaches 96.49%.
期刊:
Surfaces and Interfaces,2023年40:103145 ISSN:2468-0230
通讯作者:
Li, SZ;Gao, Jinwei;Wu, SJ
作者机构:
[Zhao, Xu; Li, Shaozhen] Wuhan Polytech Univ, Sch Elect & Elect Engn, Wuhan 430023, Peoples R China.;[Wu, Sujuan; Gao, Jinwei; Wu, SJ; Wu, Shengcheng; Yun, Tong; Yang, Jiajun] South China Normal Univ, Inst Adv Mat, South China Acad Adv Optoelect, Guangzhou 510006, Peoples R China.;[Wu, Sujuan; Gao, Jinwei; Wu, SJ; Wu, Shengcheng; Yun, Tong; Yang, Jiajun] South China Normal Univ, South China Acad Adv Optoelect, Guangdong Prov Key Lab Quantum Engn & Quantum Mat, Guangzhou 510006, Peoples R China.
通讯机构:
[Gao, JW; Wu, SJ ] S;[Li, SZ ] W;Wuhan Polytech Univ, Sch Elect & Elect Engn, Wuhan 430023, Peoples R China.;South China Normal Univ, Inst Adv Mat, South China Acad Adv Optoelect, Guangzhou 510006, Peoples R China.;South China Normal Univ, South China Acad Adv Optoelect, Guangdong Prov Key Lab Quantum Engn & Quantum Mat, Guangzhou 510006, Peoples R China.
关键词:
Dual-additive;Low-temperature process;Stability;Carbon-basedCsPbIBr2 Perovskite solar cells
摘要:
The internal non-radiative recombination and high trap-state density (Ntrap) in perovskite layer have severely limited the progress of low-temperature processed CsPbIBr2 perovskite solar cells (PSCs). In this work, cesium acetate (CsAc) and hydrogen lead triiodide (HPbI3) dual-additives are employed to tune the properties of CsPbIBr2 film prepared by low-temperature process. The CsAc material is used to modify CsPbIBr2 surface and optimize the CsPbIBr2/carbon electrode interface, while HPbI3 additive is employed to dope perovskite layer. The dual-additive strategy is used to optimize the microstructure and regulate the optoelectrical characteristics of carbon-based CsPbIBr2 PSCs. It is found that CsAc can passivate the vacancy defect of Br−, reduce the energy loss (Eloss) and enhance the open-circuit voltage (Voc) of PSCs. The HPbI3 additive works to optimize the crystallization process, resulting in the high-quality CsPbIBr2 films with better crystallinity and morphology. The modified films by CsAc and HPbI3 dual-additive demonstrate smaller band gap, better light absorption, reduced trap-state density (Ntrap) and suppressed carrier recombination. The optimized carbon-based PSCs modified by the dual-additive achieve a champion power conversion efficiency of 9.18% with a Voc of 1.334 V, more matched energy-level, reduced Eloss and promoted charge transfer. Moreover, the modified PSCs without encapsulation show improved long-term humid stability. Our work provides a facilitated method to prepare an efficient and stable CsPbIBr2 PSCs by low-temperature process.
关键词:
small object detection;multi-scale feature fusion;loss function;data augmentation;K-means plus plus
摘要:
The detection of traffic signs is easily affected by changes in the weather, partial occlusion, and light intensity, which increases the number of potential safety hazards in practical applications of autonomous driving. To address this issue, a new traffic sign dataset, namely the enhanced Tsinghua-Tencent 100K (TT100K) dataset, was constructed, which includes the number of difficult samples generated using various data augmentation strategies such as fog, snow, noise, occlusion, and blur. Meanwhile, a small traffic sign detection network for complex environments based on the framework of YOLOv5 (STC-YOLO) was constructed to be suitable for complex scenes. In this network, the down-sampling multiple was adjusted, and a small object detection layer was adopted to obtain and transmit richer and more discriminative small object features. Then, a feature extraction module combining a convolutional neural network (CNN) and multi-head attention was designed to break the limitations of ordinary convolution extraction to obtain a larger receptive field. Finally, the normalized Gaussian Wasserstein distance (NWD) metric was introduced to make up for the sensitivity of the intersection over union (IoU) loss to the location deviation of tiny objects in the regression loss function. A more accurate size of the anchor boxes for small objects was achieved using the K-means++ clustering algorithm. Experiments on 45 types of sign detection results on the enhanced TT100K dataset showed that the STC-YOLO algorithm outperformed YOLOv5 by 9.3% in the mean average precision (mAP), and the performance of STC-YOLO was comparable with that of the state-of-the-art methods on the public TT100K dataset and CSUST Chinese Traffic Sign Detection Benchmark (CCTSDB2021) dataset.
期刊:
IEEE Transactions on Instrumentation and Measurement,2023年72:1-14 ISSN:0018-9456
通讯作者:
Du, F.
作者机构:
[Qiu, Jize; Du, Fujia; Huang, Kang; Hou, Xu] Chinese Academy of Sciences, National Astronomical Observatories, Nanjing Institute of Astronomical Optics and Technology, Nanjing, 210042, China;[Zhong, Xin] Wuhan Polytechnic University, School of Electrical and Electronic Engineering, Wuhan, 430000, China
通讯机构:
[Du, F.] C;Chinese Academy of Sciences, China
关键词:
Comb filter kernel (CF-kernel);convolutional neural network (CNN);fault diagnosis;limited training sample;motor current signal analysis
通讯机构:
[Zhen Xu] S;School of Electrical and Electronic Engineering, Wuhan Polytechnic University, Wuhan 430023, China<&wdkj&>Author to whom correspondence should be addressed.
关键词:
wireless sensor networks;DV-Hop;cyclotomic method;weighted recursive least squares
摘要:
Location information is one of the crucial and essential elements for monitoring data in wireless sensor networks. The distance vector-hop (DV-Hop) localization algorithm is of practical importance in improving its localization performance. To achieve global optimization, a DV-Hop algorithm based on the cyclotomic method and weighted normalization, also known as CMWN-DV-Hop, is nominated in this paper. Therefore, the segmentation and weighting factors are introduced and normalized. The weighted recursive least-squares (WRLS) algorithm is chosen to compute the coordinates of the unknown nodes. The effects of various factors on this algorithm are tested, including the number of nodes, the anchor node ratio, and the communication radius. The simulation results show that the proposed algorithm has a super performance in reducing the localization error.
作者机构:
[Wang, Xiaoqiang; Chen, Xuhao; Zhang, Juanjuan] Lanzhou Univ, Coll Civil Engn & Mech, Key Lab Mech Environm & Disaster Western China, Minist Educ China, Lanzhou 730000, Gansu, Peoples R China.;[Zhang, Juanjuan] Xi An Jiao Tong Univ, State Key Lab Strength & Vibrat Mech Struct, Xian 710049, Shanxi, Peoples R China.;[Fang, Chao] Wuhan Polytech Univ, Dept Elect & Elect Engn, Wuhan 430023, Hubei, Peoples R China.;[Weng, George J.] Rutgers State Univ, Dept Mech & Aerosp Engn, New Brunswick, NJ 08903 USA.
通讯机构:
[Juanjuan Zhang] K;[George J. Weng] D;Key Laboratory of Mechanics on Environment and Disaster in Western China, The Ministry of Education of China, College of Civil Engineering and Mechanics, Lanzhou University, Lanzhou, Gansu 730000, PR China<&wdkj&>State Key Laboratory for Strength and Vibration of Mechanical Structures, Xi’an Jiaotong University, Xi’an, Shanxi 710049, PR China<&wdkj&>Department of Mechanical and Aerospace Engineering, Rutgers University, New Brunswick, NJ 08903, USA
关键词:
0–3 polymer-based ME composites;Effective properties;Interphase effect;ME effect
摘要:
Forward-looking sonar (FLS) images present various challenges in interpretation, recognition, and segmentation due to limitations like low resolution, speckle noise, and low contrast, making them more complex than optical images. Existing methods often focus solely on denoising or enhancement, neglecting the potential benefits of utilizing multi-scale features to create an integrated image processing approach. This paper introduces the Laplacian pyramid-based multi-scale denoising and enhancement (LPMsDE) method tailored for FLS images. The proposed method begins by presenting a novel multiplicative speckle noise model, grounded in the Gaussian distribution, specifically designed for FLS images. Next, the Laplacian pyramid decomposition is utilized to estimate noise variance, with an modified adaptive local filter. Lastly, a combination of the Laplacian pyramid framework, the enhanced adaptive local filter, and Contrast-Limited Histogram Equalization (CLHE) is employed to denoise and enhance images at different resolution levels. Through comprehensive experiments conducted on both simulated and real sonar images, the effectiveness of the LPMsDE method is demonstrated. It surpasses other denoising and enhancement techniques, as evidenced by superior scores in Structural Similarity Index (SSIM), Peak Signal-to-Noise Ratio (PSNR), Contrast-to-Noise Ratio (CNR), Equivalent Number of Looks (ENL), Natural Image Quality Evaluator (NIQE), and Blind/Referenceless Image Spatial Quality Evaluator (BRISQUE).
摘要:
The theoretical minimum driving power expression for the optical switch based on VO2 thin film is given out in this paper, which is obtained from the phase transition characteristics and thermal structure of the VO2 thin film, and it reveals some key parameters to decide its value. According to the theoretical expression, a kind of simple thermal structure fabricated with a low phase transition VO2 thin film is proposed for low power-consumption optical switch. This kind of optical switch is compact and fast while requiring only a simple driving circuit, and the VO2 thin film is deposited by using reactive ion beam sputtering method and formed by post-annealing process, which is compatible with IC process.
通讯机构:
[Zongyu Huang; Huating Liu] S;School of Physics and Optoelectronic, Hunan Key Laboratory for Micro-Nano Energy Materials and Devices, Xiangtan University, Hunan, People’s Republic of China<&wdkj&>Hunan Key Laboratory of Two-Dimensional Materials, Hunan University, Changsha, People’s Republic of China<&wdkj&>School of Physics and Optoelectronic, Hunan Key Laboratory for Micro-Nano Energy Materials and Devices, Xiangtan University, Hunan, People’s Republic of China<&wdkj&>School of Electrical and Electronic Engineering, Wuhan Polytechnic University, Wuhan, People’s Republic of China
摘要:
Bulk Bi(0.5)Sr(0.5)Fe(0.5)Cr(0.5)O(3) (BSFCO) is a new compound comprising the R3c structure. The structural, magnetic property and exchange bias (EB) details are investigated. The material was in the super-paramagnetic (SP) state at room temperature. Exchange bias usually occurs at the boundary between different magnetic states after field cooling (H(FC)) acts on the sample. Here the result shows that changing H(FC) from 1 to 6T reduces the H(EB) value by 16% at 2K at the same time. Meanwhile, H(EB) diminishes as the ferromagnetic layer thickness increases. The variation of (the thickness of ferromagnetic layer) t(FM) with the change of H(FC) leads to the tuning of H(EB) by H(FC) in BSFCO bulk. These effects are obviously different from the phenomenon seen in other oxide types.
摘要:
We present a statistical study on dense molecular gas tracers of HCN (4-3), HCO+ (4-3) lines and molecular tracers of [C I], and CO observations for a sample of 26 infrared bright star-forming (SF) galaxies. We investigate the dependence of dense gas star formation efficiency traced by HCN (4-3), HCO+ (4-3) (that is L-IR/L-HCN(') (4-3), and LIR/L-HCO+(')(4-3)), and luminosity ratio of L-HCN(')(4-3)/L-HCO+(')(4-3) on [C I]-CO ratios of L-[C (')(I] (1-0))/LCO (1-0), L[C I](2-1)'/L-CO (1-0()') and L-[C I](2-1)(')/L-[C I] (1-0)(') (hereafter R-[CI]) which are sensitive to interstellar medium conditions. Our findings show that both LIR/L ' HCN (4-3) and LIR/L ' HCO+ (4-3) have moderate correlations with L '[C I](2-1)/L ' CO (1-0) and R[CI], while L ' HCN(4-3)/L ' HCO+ (4-3) does not show any significant correlations with any of the [C I]-CO ratios. We compare the L ' HCN (4-3)/L ' HCO+ (4-3) ratios of AGN and SF galaxies, and find that although the higher L ' HCN (4-3)/L ' HCO+ (4-3) ratios are mainly found in AGN, the majority of the L ' HCN (4-3)/L ' HCO+ (4-3) values in SF galaxies are comparable to those in AGN. Based on our findings, it appears that the L ' HCN (4-3)/L ' HCO+ (4-3) ratio may not be a reliable indicator of the presence of an AGN, although further investigation is needed to confirm this conclusion.