http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
An Adaptive Neural Sliding Mode Control with ESO for Uncertain Nonlinear Systems
Jianhui Wang,Peisen Zhu,Biaotao He,Guiyang Deng,Chunliang Zhang,Xing Huang 제어·로봇·시스템학회 2021 International Journal of Control, Automation, and Vol.19 No.2
An adaptive neural sliding mode control with ESO for uncertain nonlinear systems is proposed to improve the stability of the control system. Any control system inevitably exists uncertain disturbances and nonlinearities which severely affect the control performance and stability. Neural network can be utilized to approximate the uncertain nonlinearities. Nevertheless, it produces approximate errors, which will become more difficult to deal with as the order of the system increases. Moreover, these errors and uncertain disturbances will result in a consequence that the control system can be unable to converge quickly, and has to deal with a lot of calculations. Therefore, in order to perfect the performance and stability of the control system, this paper combines sliding mode control and ESO, and designs an adaptive neural control method. The simulation results illustrate that the improved system has superior tracking performance and anti-interference ability.
Research on bolt contour extraction and counting of locomotive running gear based on deep learning
Yong Zhang,Bo Long,Huajun Wang,Chunliang Gao 대한기계학회 2022 JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY Vol.36 No.5
The detection of abnormal running gear is essential to a locomotive’s daily maintenance, with the posture and quantity of various small bolts being important indicators to judge whether the locomotive is running safely. Traditional detection algorithms are easily affected by light changes, stain coverage, and image distortion, which is difficult to meet the detection requirements. Thus this paper proposes a deep learning based on bolt detection method that is appropriate for locomotive running gears. First, a bolt segmentation network was developed based on an improved U-netthat compensates the image information loss after multiple cross fusions involving the fusion of front and back convolution layer feature images. Furthermore, the proposed network utilizes the PReLU activation function and employs the concept structure to optimize the convolution method. This strategy aims to improve further the model’s segmentation accuracy and convergence speed. On this basis, we exploited several morphological transformations to improve the contour detection accuracy and ensure the bolt counting accuracy. The experimental results on the mainline running train data highlight that, compared with U-net, the proposed network’s recall rate and the mean intersection over union value are increased by 5.38 and 14.3, respectively. Furthermore, the bolt counting method’s loss function and mean absolute errors are significantly reduced compared with the contour extraction algorithm.
Xiaolong Li,Shubao Geng,Hanjie Chen,정철의,Chunliang Wang,Hongtao Tu,Jinyong Zhang 한국응용곤충학회 2017 Journal of Asia-Pacific Entomology Vol.20 No.1
The apple leafminer, Phyllonorycter ringoniella Matsumura (Lepidoptera: Gracillariidae), is an important insect pest of apple, with four to six generations a year in Korea, Japan, and China. The effect of mass trapping with sex pheromone traps on P. ringoniellawas investigated in apple orchards in 2015 in Yinchuan, China. Trap density treatments were 0, 75, 150, and 225/ha in the Control, T1, T2, and T3 orchard blocks, respectively. Average numbers of male catches permonitoring trapwere significantly lower in T2 and T3 treatments and highest in the control. Control efficiencies estimated fromthe leaf damage were 86.67±4.71, 97.23±3.93, and 100% in T1, T2, and T3, respectively. Significant within-tree migration of the moths from the lower part to the upper part was indicated by the shift of trap catches from lower (1–2 m high) to upper portions (3 m high) of the tree from early August. Mass trapping with sex pheromone traps can be one effective and environmentally friendly method to reduce the P. ringoniella populations in apple orchards. Trap density of 150/ha and hanging at 2 m height was recommended for growers to control and monitor its population, respectively