Cascade Network Based Bolt Inspection In High-Speed Train

( Xiaodong Gu ),( Ji Ding ) 한국인터넷정보학회 2021 KSII Transactions on Internet and Information Syst Vol.15 No.10

The detection of bolts is an important task in high-speed train inspection systems, and it is frequently performed to ensure the safety of trains. The difficulty of the vision-based bolt inspection system lies in small sample defect detection, which makes the end-to-end network ineffective. In this paper, the problem is resolved in two stages, which includes the detection network and cascaded classification networks. For small bolt detection, all bolts including defective bolts and normal bolts are put together for conducting annotation training, a new loss function and a new boundingbox selection based on the smallest axis-aligned convex set are proposed. These allow YOLOv3 network to obtain the accurate position and bounding box of the various bolts. The average precision has been greatly improved on PASCAL VOC, MS COCO and actual data set. After that, the Siamese network is employed for estimating the status of the bolts. Using the convolutional Siamese network, we are able to get strong results on few-shot classification. Extensive experiments and comparisons on actual data set show that the system outperforms state-of-the-art algorithms in bolt inspection.

Power Quality Early Warning Based on Anomaly Detection

Gu, Wei,Bai, Jingjing,Yuan, Xiaodong,Zhang, Shuai,Wang, Yuankai The Korean Institute of Electrical Engineers 2014 Journal of Electrical Engineering & Technology Vol.9 No.4

Different power quality (PQ) disturbance sources can have major impacts on the power supply grid. This study proposes, for the first time, an early warning approach to identifying PQ problems and providing early warning prompts based on the monitored data of PQ disturbance sources. To establish a steady-state power quality early warning index system, the characteristics of PQ disturbance sources are analyzed and summed up. The higher order statistics anomaly detection (HOSAD) algorithm, based on skewness and kurtosis, and hierarchical power quality early warning flow, were then used to mine limit-exceeding and abnormal data and analyze their severity. Cases studies show that the proposed approach is effective and feasible, and that it is possible to provide timely power quality early warnings for limit-exceeding and abnormal data.

Green algae dominance quickly switches to cyanobacteria dominance after nutrient enrichment in greenhouse with high temperature

Xiaodong Wang,Xingguo Liu1,Boqiang Qin,Zhaojun Gu,Hao Xu,Hao Zhu,Guofeng Cheng,Huang Liu 한국생태학회 2015 Journal of Ecology and Environment Vol.38 No.3

In order to understand the mechanisms of conversion between different algal dominance, an experiment was performed in a greenhouse from 22 June to 10 July 2011. The experiment included a treatment group subjected to three instances of nutrient enrichment and a control with no nutrient enrichment. The initial water was dominated by Ankistrodesmus of Chlorophyta. The average water temperature at 08:30 h and 14:00 h during the experiment was 31.6°C and 34.6°C, respec¬tively. The results showed that the total nitrogen (TN), total phosphorus (TP), dissolved total nitrogen (DTN), dissolved total phosphorus (DTP), and soluble reactive phosphorus (SRP) concentrations in the treatment were significantly higher than in the control (P < 0.05). However, the TN/TP and DTN/DTP in the control was higher than in the treatment (P < 0.05). The dominant algae in the control did not change during the experiment, while the dominant algae in the treat¬ment switched to Planktothrix of Cyanophyta on day 9. The chlorophyll a (Chl-a), wet weight of all algae, wet weight of Cyanophyta, and percentage of Cyanophyta in the control were all significantly lower than in the treatment (P < 0.05). Amounts of zooplankton, especially rotifers, were present at the end of the experimental period. The density of rotifers between the control and treatment was not significantly different (P > 0.05), while the copepod density in the treatment was higher than in the control (P < 0.05). We conclude that green algae dominance quickly switches to cyanobacteria dominance after nutrient enrichment in a greenhouse with elevated temperature

Pattern Recognition of Monitored Waveforms from Power Supplies Feeding High-Speed Rail Systems

Gu, Wei,Zhang, Shuai,Yuan, Xiaodong,Chen, Bing,Bai, Jingjing The Korean Institute of Electrical Engineers 2016 Journal of Electrical Engineering & Technology Vol.11 No.1

The development of high-speed rail (HSR) has had a major impact on the power supply grid. Based on the monitored waveforms of HSR, a pattern recognition approach is proposed for the first time in this paper to identify the operating conditions. To reduce the data dimensions for monitored waveforms, the principal component analysis (PCA) algorithm was used to extract the characteristics and their waveforms from the monitored waveforms data. The dynamic time wrapping (DTW) algorithm was then used to identify the operating conditions of the HSR. Cases studies show that the proposed approach is effective and feasible, and that it is possible to identify the real-time operating conditions based on the monitored waveforms.

Aqueous Extract of Semen <i> Ziziphi Spinosae</i> Exerts Anxiolytic Effects during Nicotine Withdrawal via Improvement of Amygdaloid CRF/CRF1R Signaling

Gu, Changhong,Zhao, ZhengLin,Zhu, Xiaodong,Wu, Tong,Lee, Bong Hyo,Jiao, Yu,Lee, Chul Won,Jung, Dae Hwa,Yang, Chae Ha,Zhao, Rongjie,Kim, Sang Chan Hindawi 2018 Evidence-based Complementary and Alternative Medic Vol.2018 No.-

<P>Anxiety during nicotine withdrawal (NicW) is a key risk factor for smoking relapse. Semen<I> Ziziphi Spinosae</I> (SZS), which is a prototypical hypnotic-sedative herb in Oriental medicine, has been clinically used to treat insomnia and general anxiety disorders for thousands of years. Thus, the present study evaluated the effects of the aqueous extract of SZS (AESZS) on NicW-induced anxiety in male rats that received subcutaneous administrations of nicotine (Nic) (0.4 mg/kg, twice a day) for 7 d followed by 4 d of withdrawal. During NicW, the rats received four intragastric treatments of AESZS (60 mg/kg/d or 180 mg/kg/d). AESZS dose-dependently attenuated NicW-induced anxiety-like behaviors in the elevated plus maze (EPM) tests and 180 mg/kg/d AESZS inhibited NicW-induced increases in plasma corticosterone. Additionally, the protein and mRNA expressions of corticotropin-releasing factor (CRF) and CRF type 1 receptor (CRF1R) increased in the central nucleus of the amygdala (CeA) during NicW, but these changes were suppressed by 180 mg/kg/d AESZS. A post-AESZS infusion of CRF into the CeA abolished the attenuation of anxiety by AESZS and 180 mg/kg/d AESZS suppressed NicW-induced increases in norepinephrine and 3-methoxy-4-hydroxy-phenylglycol levels in the CeA. The present results suggest that AESZS ameliorated NicW-induced anxiety via improvements in CRF/CRF1R and noradrenergic signaling in the CeA.</P>

Impact of Size on Humidity Sensing Property of Copper Oxide Nanoparticles

Yang Gu,Huina Jiang,Zi Ye,Ning Sun,Xuliang Kuang,Weijing Liu,Gaofang Li,Xiaojun Song,Lei Zhang,Wei Bai,Xiaodong Tang 대한금속·재료학회 2020 ELECTRONIC MATERIALS LETTERS Vol.16 No.1

Three sizes of CuO nanosheets were synthesized by hydrothermal method. The structure and morphology of CuO nanosheets were characterized by X-ray difraction and scanning electron microscopy. Dielectrophoresis nano-manipulation technique was employed to arrange the materials on pre-designed Ti/Au electrodes to fabricate the three humidity sensors, and the sensing properties were then tested. The experimental results show that the sensitivity greatly increases with the decreasing size of CuO nanosheets, the sensitivity of sensor a, b, c are 369%, 3278%, 22,611% in 97.3% RH, respectively. The smaller sized CuO nanomaterials have better response characteristic, the response time of sensor a, b, c under 11.3–97.3% RH are 53 s, 49 s, 32 s, respectively. And correspondingly, hysteresis properties and the repeatability are also a little infuenced. In addition, based on complex impedance spectroscopy and multilayer adsorption theory, the impact of size on humidity sensing property was discussed. The results indicated the feasibility to obtain higher performance of humidity sensor, especially the higher sensitivity, via employment the smaller size sensing nanomaterials.

Power Quality Early Warning Based on Anomaly Detection

Wei Gu,Jingjing Bai,Xiaodong Yuan,Shuai Zhang,Yuankai Wang 대한전기학회 2014 Journal of Electrical Engineering & Technology Vol.9 No.4

Different power quality (PQ) disturbance sources can have major impacts on the power supply grid. This study proposes, for the first time, an early warning approach to identifying PQ problems and providing early warning prompts based on the monitored data of PQ disturbance sources. To establish a steady-state power quality early warning index system, the characteristics of PQ disturbance sources are analyzed and summed up. The higher order statistics anomaly detection (HOSAD) algorithm, based on skewness and kurtosis, and hierarchical power quality early warning flow, were then used to mine limit-exceeding and abnormal data and analyze their severity. Cases studies show that the proposed approach is effective and feasible, and that it is possible to provide timely power quality early warnings for limit-exceeding and abnormal data.

Green algae dominance quickly switches to cyanobacteria dominance after nutrient enrichment in greenhouse with high temperature

Wang, Xiaodong,Liu, Xingguo,Qin, Boqiang,Gu, Zhaojun,Wu, Zongfan,Xu, Hao,Zhu, Hao,Cheng, Guofeng,Liu, Huang The Ecological Society of Korea 2015 Journal of Ecology and Environment Vol.38 No.3

In order to understand the mechanisms of conversion between different algal dominance, an experiment was performed in a greenhouse from 22 June to 10 July 2011. The experiment included a treatment group subjected to three instances of nutrient enrichment and a control with no nutrient enrichment. The initial water was dominated by Ankistrodesmus of Chlorophyta. The average water temperature at 08:30 h and 14:00 h during the experiment was $31.6^{\circ}C$ and $34.6^{\circ}C$, respectively. The results showed that the total nitrogen (TN), total phosphorus (TP), dissolved total nitrogen (DTN), dissolved total phosphorus (DTP), and soluble reactive phosphorus (SRP) concentrations in the treatment were significantly higher than in the control (P < 0.05). However, the TN/TP and DTN/DTP in the control was higher than in the treatment (P < 0.05). The dominant algae in the control did not change during the experiment, while the dominant algae in the treatment switched to Planktothrix of Cyanophyta on day 9. The chlorophyll a (Chl-a), wet weight of all algae, wet weight of Cyanophyta, and percentage of Cyanophyta in the control were all significantly lower than in the treatment (P < 0.05). Amounts of zooplankton, especially rotifers, were present at the end of the experimental period. The density of rotifers between the control and treatment was not significantly different (P > 0.05), while the copepod density in the treatment was higher than in the control (P < 0.05). We conclude that green algae dominance quickly switches to cyanobacteria dominance after nutrient enrichment in a greenhouse with elevated temperature.

Pattern Recognition of Monitored Waveforms from Power Supplies Feeding High-Speed Rail Systems

Wei Gu,Shuai Zhang,Xiaodong Yuan,Bing Chen,Jingjing Bai 대한전기학회 2016 Journal of Electrical Engineering & Technology Vol.11 No.1

The development of high-speed rail (HSR) has had a major impact on the power supply grid. Based on the monitored waveforms of HSR, a pattern recognition approach is proposed for the first time in this paper to identify the operating conditions. To reduce the data dimensions for monitored waveforms, the principal component analysis (PCA) algorithm was used to extract the characteristics and their waveforms from the monitored waveforms data. The dynamic time wrapping (DTW) algorithm was then used to identify the operating conditions of the HSR. Cases studies show that the proposed approach is effective and feasible, and that it is possible to identify the real-time operating conditions based on the monitored waveforms.

Power Quality Warning of High-Speed Rail Based on Multi-Features Similarity

Bai, Jingjing,Gu, Wei,Yuan, Xiaodong,Li, Qun,Chen, Bing,Wang, Xuchong The Korean Institute of Electrical Engineers 2015 Journal of Electrical Engineering & Technology Vol.10 No.1

As one type of power quality (PQ) disturbance sources, high-speed rail (HSR) can have major impacts on the power supply grid. Providing timely and accurate warning information for PQ problems of HSR is important for the safe and stable operation of traction power supply systems and the power supply grid. This study proposes a novel warning approach to identify PQ problems and provide warning prompts based on the monitored data of HSR. To embody the displacement and status change of monitored data, multi-features of different sliding windows are computed. To reflect the relative importance degree of these features in the overall evaluation, an analytic hierarchy process (AHP) is used to analyse the weights of multi-features. Finally, a multi-features similarity algorithm is applied to analyse the difference between monitored data and the reference data of HSR, and PQ warning results based on dynamic thresholds can be analysed to quantify its severity. Cases studies demonstrate that the proposed approach is effective and feasible, and it has now been applied to an actual PQ monitoring platform.