关键词:
Cement and asphalt mortar;Thermal expansion;Thermal shrinkage;Moisture dependence;Size dependence
摘要:
Cement and asphalt (CA) mortar is a key structural material for high-speed railway slab ballastless tracks. To investigate the deformation property of CA mortar in the range of - 20-60 degrees C, a DIL402C thermal expansion instrument and a self-designed thermal deformation tester were used in this paper, and the thermal deformation mechanism was revealed by combining the dynamic thermal analysis technology, the relationship between the deformation and mass under cyclic temperature variation, and the microstructural testing. The results indicated that the thermal expansion deformation of CA mortar decreased as the moisture content increased. Under vacuum-drying, air-drying, and water saturation state, the thermal expansion strain ranges of CA mortar specimens with different sizes were 1.0248-1.4340 x 10-3, 0.4438-1.3669 x 10-3, and - 2.1815-0.5571 x 10-3, respectively. The smaller the specimen size, the more significant the thermal shrinkage deformation caused by the increased humidity. The thermal expansion coefficient of CA mortar increased gradually during the initial heating process and then changed in a complicated manner with changes in the humidity. As a porous material with asphalt as the continuous phase, when the temperature increases, the volume expansion of ice, the melting of ice into water, the migration and evaporation of water, the phase change of asphalt, and the volume expansion of cement mortar jointly affect the overall deformation property of CA mortar.
作者机构:
[代振维; 吴明亮; 方志超; 曲永波; 柳亚峰] College of Engineering, Hunan Agriculture University, Changsha;410128, China;Hunan Provincial Engineering Technology Research Center for Modern Agricultural Equipment, Changsha;Hunan Mechanical & Electrical Polytechnic, Changsha;410151, China
摘要:
Understanding the ecological environment, population abundance, and growth status of marine organisms in the marine fishery is important to promote its sustainability. However, existing manual detection methods can cause some damage to marine ecology and are difficult to meet the demand for fast and accurate detection. In addition, light, shadows, and disturbances in the marine ecosystem can affect the effectiveness of intelligent detection methods. To address these problems, a deep residual convolutional neural network (DRCNN) based on hybrid attention mechanism (HAM) is proposed to detect marine organisms. The hybrid attention mechanism obtains key information from both channel and space dimensions of the input image. And the residual module is added to the deep convolutional neural network to iteratively extract image features while avoiding error accumulation. It is demonstrated experimentally that the HAM-DRCNN model achieves 93.17% image localization accuracy with a processing speed of 20.95 frames/s. Compared with the YOLOv5 and Faster R-CNN, the mean average precision of species classification is 91.36%, which is an improvement of 0.93% and 9.39%, respectively. In addition, excellent results are achieved on two other benchmark datasets. The method can accurately locate and complete the classification of marine organisms in underwater images and has practical application value.
Understanding the ecological environment, population abundance, and growth status of marine organisms in the marine fishery is important to promote its sustainability. However, existing manual detection methods can cause some damage to marine ecology and are difficult to meet the demand for fast and accurate detection. In addition, light, shadows, and disturbances in the marine ecosystem can affect the effectiveness of intelligent detection methods. To address these problems, a deep residual convolutional neural network (DRCNN) based on hybrid attention mechanism (HAM) is proposed to detect marine organisms. The hybrid attention mechanism obtains key information from both channel and space dimensions of the input image. And the residual module is added to the deep convolutional neural network to iteratively extract image features while avoiding error accumulation. It is demonstrated experimentally that the HAM-DRCNN model achieves 93.17% image localization accuracy with a processing speed of 20.95 frames/s. Compared with the YOLOv5 and Faster R-CNN, the mean average precision of species classification is 91.36%, which is an improvement of 0.93% and 9.39%, respectively. In addition, excellent results are achieved on two other benchmark datasets. The method can accurately locate and complete the classification of marine organisms in underwater images and has practical application value.
作者机构:
[彭才望; 孙松林; 宋世圣; 向阳] College of Engineering, Hunan Agricultural University, Changsha, 410128, China;[贺喜] College of Animal Science and Technology, Hunan Agricultural University, Changsha, 410128, China;[许道军] School of Veterinary Medicine, Hunan Agricultural University, Changsha, 410128, China
期刊:
International Journal of Industrial and Systems Engineering,2021年38(2):143-166 ISSN:1748-5037
作者机构:
[Wu M.] College of Engineering, Hunan Agricultural University, Changsha, 410128, China;[Lyu J.; Ma L.; Liu J.; Zhou W.] Institute of Bast Fiber Crops, Chinese Academy of Agricultural Sciences, Changsha, 410205, China;[Xiang W.] College of Engineering, Hunan Agricultural University, Changsha, 410128, China<&wdkj&>Institute of Bast Fiber Crops, Chinese Academy of Agricultural Sciences, Changsha, 410205, China
作者机构:
[彭才望; 周婷; 宋世圣; 孙松林; 向阳] College of Engineering, Hunan Agricultural University, Changsha, 410128, China;[许道军] College of Veterinary Medicine, Hunan Agricultural University, Changsha, 410128, China
摘要:
Calibration transfer is a subtle issue in the practical application of near-infrared (NIR) spectroscopy technique. In this paper, a novel method to calibration transfer based on neighborhood preserving embedding (CTNPE) for correcting spectral differences was proposed. As a manifold learning method, neighborhood preserving embedding (NPE) can not only capture the nonlinear manifold structure, but also retain the linearity and show good generalization ability. Since this approach can reveal low dimensional manifold structure in high dimensional spectroscopic data, it is beneficial to construct the transform relationship between source and target spectra. The performance of CTNPE was assessed and compared to that of piecewise direct standardization (PDS) and other four dimensionality reduction-based methods, including transfer based on target factor analysis (TTFA), spectral space transformation (SST), calibration transfer based on canonical correlation analysis (CTCCA) and based on independent component analysis (CTICA), in two real cases. The results indicated that CTNPE was able to successfully transfer spectra between instruments and samples in different physical states. Furthermore, CTNPE provided lower prediction errors than PDS, TTFA, CTCCA, SST, CTICA and direct prediction without a transfer function. Therefore, the comprehensive investigation carried out in the presented work demonstrates that CTNPE is a promising calibration transfer method for NIR, especially for correcting the variations for samples in different physical states.
摘要:
In order to realise ground clearance and levelling control of plant protection machine in high ground clearance. In this paper, a chassis automatic levelling control system is designed. Position error control method and angle error control method are used to control the chassis automatic levelling control system, which is divided into ground clearance height adjustment and chassis levelling control strategy, respectively. The system is controlled by combining fuzzy control algorithm and preset point levelling method. The experiment was carried out on the chassis of our self-developed multi-functional plant protection machine with high ground clearance. The results show that the automatic levelling system can complete the chassis levelling well. Its average horizontal error is < 0.20°, root mean square error < 0.25°, maximum error is 1.13°, average levelling time < 26 s, and levelling precision < 0.2°. The system can meet the operation requirements of plant protection machine.