Abstract:In the era of big data, data-driven methods mainly based on deep learning have been widely used in the field of intelligent fault diagnosis. Traditional neural networks tend to be more subjective when classifying fault time-frequency graphs, such as pooling layer, and ignore the location relationship of features. The newly proposed neural network named capsules network takes into account the size and location of the image. Inspired by this, capsules network combined with the Xception module (XCN) is applied in… Show more
“…2019, 9, The image is sent to the main network to extract the data, and then the region proposal network is used to find the region of interest. Subsequently, a layer called RoIAlign is adopted, which accurately aligns the extracted features with the input to improve the accuracy of the object mask [38].…”
Section: Pyramid Lk Algorithm Based On Mask-r-cnn and K-meansmentioning
Aiming at enhancing the accuracy and reliability of velocity calculation in vision navigation, an improved method is proposed in this paper. The method integrates Mask-R-CNN (Mask Region-based Convolutional Neural Network) and K-Means with the pyramid Lucas Kanade algorithm in order to reduce the harmful effect of moving objects on velocity calculation. Firstly, Mask-R-CNN is used to recognize the objects which have motions relative to the ground and covers them with masks to enhance the similarity between pixels and to reduce the impacts of the noisy moving pixels. Then, the pyramid Lucas Kanade algorithm is used to calculate the optical flow value. Finally, the value is clustered by the K-Means algorithm to abandon the outliers, and vehicle velocity is calculated by the processed optical flow. The prominent advantages of the proposed algorithm are (i) decreasing the bad impacts to velocity calculation, due to the objects which have relative motions; (ii) obtaining the correct optical flow sets and velocity calculation outputs with less fluctuation; and (iii) the applicability enhancement of the optical flow algorithm in complex navigation environment. The proposed algorithm is tested by actual experiments. Results with superior precision and reliability show the feasibility and effectiveness of the proposed method for vehicle velocity calculation in vision navigation system.
“…2019, 9, The image is sent to the main network to extract the data, and then the region proposal network is used to find the region of interest. Subsequently, a layer called RoIAlign is adopted, which accurately aligns the extracted features with the input to improve the accuracy of the object mask [38].…”
Section: Pyramid Lk Algorithm Based On Mask-r-cnn and K-meansmentioning
Aiming at enhancing the accuracy and reliability of velocity calculation in vision navigation, an improved method is proposed in this paper. The method integrates Mask-R-CNN (Mask Region-based Convolutional Neural Network) and K-Means with the pyramid Lucas Kanade algorithm in order to reduce the harmful effect of moving objects on velocity calculation. Firstly, Mask-R-CNN is used to recognize the objects which have motions relative to the ground and covers them with masks to enhance the similarity between pixels and to reduce the impacts of the noisy moving pixels. Then, the pyramid Lucas Kanade algorithm is used to calculate the optical flow value. Finally, the value is clustered by the K-Means algorithm to abandon the outliers, and vehicle velocity is calculated by the processed optical flow. The prominent advantages of the proposed algorithm are (i) decreasing the bad impacts to velocity calculation, due to the objects which have relative motions; (ii) obtaining the correct optical flow sets and velocity calculation outputs with less fluctuation; and (iii) the applicability enhancement of the optical flow algorithm in complex navigation environment. The proposed algorithm is tested by actual experiments. Results with superior precision and reliability show the feasibility and effectiveness of the proposed method for vehicle velocity calculation in vision navigation system.
“…With similar reaction paths, methane dehydrogenation processes are presented as four competitive reaction steps [36][37][38][39]: methyl (CH 3 ), methylene (CH 2 ), methylidene (CH), and carbon (C) were generated in an orderly fashion during the cracking. The stable configurations of CH 4 -Pd 2 (o), CH 3 -Pd 2 (o), CH 2 -Pd 2 (o), and CH-Pd 2 (o) were obtained by geometry optimization, respectively.…”
Section: Intermediate System In the Reactionmentioning
confidence: 99%
“…All calculations were performed using DFT in generalized gradient approximation (GGA), Perdew Burke, and Ernzerho (PBE) [36]. Exchange correlation was implemented with module DMol3 in Material Studio of Accelrys Inc.…”
A dimer model Pd 2 was established to study the adsorption of CH x (x = 1-4) and CH 4 dehydrogenation, as well as syngas formation using density functional theory (DFT) at the atomic level. Meanwhile, insight into understanding the role of the oxygen atom on the partial oxidation of methane (POM) was also calculated based on a trimer model of Pd 2 O. For the adsorption of CH x , results showed that the presence of an oxygen atom was a disadvantage to the adsorption of CH x (x = 1-3) species. For CH 4 dissociation, the process of CH 2 →CH + H was found to be the rate-limiting step (RSD) on both Pd 2 and Pd 2 O. H 2 was formed by the reaction of CH 2 + 2H→CH 2 + H 2 . For CO formation, it was primarily formed in the process of CH + O→CHO→CO + H on both the Pd 2 and the Pd 2 O catalyst. Thermodynamic and kinetic calculations revealed that formation and maintainance of the oxygen atom on the Pd surface could promote a POM reaction to achieve high H 2 and CO yield and selectivity. Our study provides a helpful understanding of the effect of an adsorbed oxygen atom on a POM reaction with a Pd catalyst.
“…Among renewable and sustainable energies, offshore wind power shows a variety of advantages including high energy density, low turbulence, and low wind shear [1]. Technological advances are also making wind energy competitive from the economic perspective [2][3][4][5][6][7][8][9]. In 2018, 409 new offshore wind turbines were commissioned in Europe, which provided an additional capacity of 2,649 MW, and the cumulative capacity of wind farms was 18,499 MW [10].…”
The dynamic characteristics of an offshore wind turbine with tripod suction buckets are investigated through finite element analysis and full-scale experiments. In finite element analysis, an integrated framework is suggested to create a simple yet accurate high fidelity model. The integrated framework accounts for not only the strain dependency of the soil but also for all dynamics in the seabed, including those of the soil, suction bucket skirt, and cap. Hence, the model accurately describes the coupling effect of translational and rotational motions of the seabed. The prediction results are compared to the experimental results obtained via full-scale testing in four stages during construction and in several operational conditions. The comparison shows that the stiffness of the suction bucket cap and strain dependency of the soil play a significant role in predicting natural frequency, suggesting that these two factors should be considered in finite element analysis for the accurate prediction of dynamic responses of an offshore wind conversion system. Moreover, dynamic analysis of the strain and acceleration measured during operational conditions shows that strain is more robust than acceleration with regard to the characterization of the overall dynamics of an offshore wind conversion system because the natural frequency of an offshore wind turbine is very low. It can be inferred that the measurement of strain is a more effective way to monitor the long-term evolution of dynamic characteristics. The suggested integrated framework and measurement campaign are useful not only to avoid conservatism that may incur additional costs during load calculation and design phases but also to establish an intelligent operation and maintenance strategy with a novel sensing technique.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.