Ferulic acid in extracts of raw herbs was separated by capillary zone electrophoresis in the buffer solution of 10 mmol/L Na(2)B(4)O(7). The simple and rapid method was linear, ranging from 5 to 100 microg/mL, and had a good reproducibility with the RSD below 2%. The contents of ferulic acid in Angelica sinensis and Chuanxiong could be easily determined within 15 min with no pretreatment and no interference.
Tetrahydropalmatine in Rhizoma corydalis and its preparations were separated and determined with no pretreatment in the buffer solution of 50 mmol/L of sodium acetate in methanol containing 2 mol/L acetic acid.
Object detection plays an important role in autonomous driving systems. LiDAR is widely used in autonomous driving vehicles and robots as a sensor for environmental perception. Recently, the development of computational power and deep learning technology makes it possible to classify and locate objects from LiDAR point cloud in a single end-to-end learnable network. However, objects are sparsely distributed in large point cloud field, and are always been partly scanned by LiDAR, which pose a challenge for accurate and rapid object positioning and classification from the raw point cloud. In this paper, we introduce a new single-shot refinement neural network for fast and accurate 3D object detection from the raw LiDAR point cloud. Firstly, we exploit self-attention mechanism in main object detection branch to enhance object feature representation. Secondly, we apply deformable convolution for learning adaptive receptive fields to fully capture the features of rotating and partially visible objects. Thirdly, an object refinement branch is introduced to produce a finer regression of objects upon the primary estimation from the main detection branch. All proposed modules have been proven to effectively improve the accuracy of object detection. Our method is evaluated on KITTI 3D detection benchmark and achieves state-of-the-art results while maintains real-time efficiency. Furthermore, real-time test in autonomous driving vehicle demonstrates that our method is robust to 16 channels LiDAR and can meet the demands of accuracy, efficiency, and visibility of object detection in various urban scenarios.
In sheet metal forming, free deformation of the sheet takes place frequently without contact with forming tools. The pre-straining resulting from the free deformation leads to a surface roughening of the sheet metal. It is assumed that the roughening has an influence on friction and wear behavior of the following forming process as well as the painting quality after the manufacturing. In this paper, a numerical prediction based on a polycrystalline model is first proposed to predict the effect of surface roughing based on the material data of the as-received state of the sheet metal. Different states of strain are analyzed and the numerical result is validated through experimental evaluation. Besides the numerical prediction, the friction behavior after pre-straining is evaluated in strip drawing tests and the coefficient of friction (COF) is calculated. For interpretation of the measured COF, the surface roughness after the friction test and the surface image are evaluated by a transparent toolset. It is shown that the surface transformation as a result of pre-straining has a negative influence on the lubricating effect of the sheet metal and degrades the friction behavior. Finally, the influence of the strain-induced surface roughening on wear is discussed based on wear testing in strip drawing test with draw bead geometry.
As one of the most popular sports, football has been a subject to growth and advancements in technology. The combination of football and artificial intelligence is expected to be used for intelligent football analysis. Image semantic segmentation is an important basis for image analysis and understanding. This paper proposes a deep learning-based image segmentation model for pixel-level classification of the video recordings frames of football matches. Every pixel of football video frame is classified into one of the 10 classes, e.g., players, ball, goal bar and several background scenes. In this paper, we first test a variety of CNN architectures and pre-trained models and select the MobileNet-UNet architecture as our baseline. We note the severe unbalanced data distribution in football scene segmentation. To solve this problem, the weighted multi-class cross-entropy loss is adopted in training of MobileNet-UNet to redistribute the weights of classification loss, focusing on smaller foreground object classes and improving segmentation accuracy. We also propose to use image transformations and a random mixture sampling technique for training data augmentation to reduce model overfitting. The model is trained and validated in the well-annotated Football Semantic Segmentation Open Dataset. The proposed best model achieves 0.96 frequency weighted IoU and 0.90 mean IoU segmentation accuracy on validation set.
A capillary zone electrophoresis method was set up for the separation and determination of glycyrrhizin in Chinese medicinal preparations. Concentrations of Na(2)B(4)O(7) were optimized, which showed that glycyrrhizin in the sample could be separated from interference in the running buffer of 30 mmol/L Na(2)B(4)O(7). Using declofenac as internal standard, the simple method was linear in the range 25-300 microg/mL of glycyrrhizin, and good reproducibility was obtained. The extracts of Radix glycyrrhizae and its preparations could be injected directly for analysis without any pretreatment.
Objective:A rapid capillary zone electrophoresis method was,for the first time,developed for the simul- taneous determination of mangiferin and neomangiferin in the Chinese herbal extract from Artemarrhena asphode- loides Bge.Methods:Optimum separation was achieved with 30 mmoL·L~(-1)Borax at pH 9.18.The applied voltage was 25 kV and the capillary temperature was kept constant at 30℃ and the detected wavelength was 214 nm. Uncoated fused silica capillary column 50μm×50 cm(effective length 41.5 cm).Cinnamic acid was used as the internal standard.Results:Regression equation revealed good linear relationship(correlation coefficient:0.9995 and 0.9994)between the ratio of peak area of each compound(mangiferin and neomangiferin)and its concentration (concentration range:8.1-162.0,5.9-118.0μg·mL~(-1)).The relative standard deviations of relative peak area were less than 4.1%.Conclusion:The contents of the two flavonoids in Anemarrhena asphodeloides Bge.were suc- cessfully determined in 6 min,with satisfactory recovery and repeatability.
This paper presents the factors about selection of sprinter,and expounds the method of selecting sprinter by applying fuzzy integrative evaluation method.Thus the work of selecting sprinter will be more scientific,and the sprinters will be more potential and future development.
With the increasing usage of high-strength steel, tool wear becomes a major challenge in sheet metal forming. As tribological properties are in consequence of the system characteristics, wear prediction is extremely difficult. The wear resistance characteristic curve is introduced in a former publication of the authors to predict wear in sheet metal forming. With the help of this curve, the evaluation of the tool life spans in strip drawing tests under different contact pressures is possible. However, other influencing factors on tool wear should also be taken into account. In this paper, two types of tools made from cold working steel and cast iron are used to investigate the influence of the tool characteristics hardness and surface roughness on the wear behavior and the life span in strip drawing tests with high strength steels. Moreover, the dominating wear mechanisms with respect to different tool properties are also discussed. As a consequence, the wear resistance characteristic curves are derived and new values to characterize the wear resistance in terms of hardness and surface roughness are presented. With the results, more knowledge about the influencing factors on wear is given and the life spans of different tribological systems can be quantitatively predicted. Finally, the wear behavior of the tools after rework is also discussed.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)
