Journal of Liaoning Petrochemical University
  Journals
  Publication Years
  Keywords
Search within results Open Search
Please wait a minute...
For Selected: Toggle Thumbnails
An Image Weathering Method Based on Exemplar Propagation
Wang Yuming, Pan Bin, Guo Xiaoming, Yin Li, Zhang Manlin, Jia Fangli
Abstract341)   HTML    PDF (4947KB)(127)      
In order to improve the realism of the simulated scene, weathering the objects of the image is an effective method. Using an image processing method to achieve the fine weathering effect of the objects surface in the image. First of all, use the radial basis function (RBF) method to calculate the weathering degree image. Even if the color of the surface of the object changed greatly, the algorithm could calculate the degree of weathering more accurately. Then, use the image segmentation algorithm to extract the most weathered region as the "weathering exemplar". Finally, the patchmatch image repair algorithm was used to complete the "weathering exemplar", so that the "weathering exemplar" could be propagated seamlessly in the weathering area of the image. The results show that the proposed method can generate various types of weathering effects. Using the method of exemplar propagation can better simulate the weathering image.
2021, 41 (1): 80-85. DOI: 10.3969/j.issn.1672-6952.2021.01.014
Research on Open⁃Circuit Fault Detection and Fault⁃Tolerant Control of Three⁃Phase Three⁃Level PV Inverters
Pan Bin, Wang Youzheng, Chen Mingming, Zhao Yong, Yu Jingxian
Abstract500)   HTML    PDF (4231KB)(177)      
In order to improve the operation reliability of the three⁃level PV inverter, an open⁃circuit fault detection and a voltage space vector redundancy fault⁃tolerant control method based on the improved current flow path were proposed. First, based on the three⁃phase three⁃level PV topology structure, the circuit current flow path after the open⁃circuit fault of each partial power device was analyzed in detail, the fault detection could be carried out by the current size flowing through the clamping diode and the load, the switching state of the switching device, and the fault type could be classified by injecting the under⁃excitation reactive current in a short time. Then, the change of the voltage space vector of the inverter after the open⁃circuit fault of the power device in different positions was theoretically explored. And the fault⁃tolerant control was completed according to the distribution law of the voltage space vector after the inverter fault and the redundancy vector of the inverter. The proposed method was fast in fault detection and fault⁃tolerant control without additional hardware cost and complex calculation. Finally, a prototype with rated power of 10 kW was built to verify the effectiveness and reliability of the proposed method.
2020, 40 (3): 74-82. DOI: 10.3969/j.issn.1672-6952.2020.03.014
An Improved KNN Algorithm Based on Analytic Hierarchy Process
Dai Puwei, Pan Bin, Wang Yuming, Zhu Feng
Abstract491)      PDF (2583KB)(286)      
The KNN classification algorithm is nonparametric, easy to understand and relatively efficient, and is widely used in many fields. In the traditional KNN algorithm, the Euclidean distance method considers the contribution of all the attributes of the sample as the same. But in fact, the contribution of different attributes of the sample is not necessarily the same. To solve this problem, an improved KNN algorithm based on analytic hierarchy process is proposed. In the improved algorithm, firstly, the weights of each attribute of the sample are calculated by using the analytic hierarchy process, and then the sample distance is calculated by using the weighted Euclidean distance, thereby classifying according to the weighted distance. In the experiment, with the increasing number of training samples, the efficiency of AHP-KNN algorithm is improved, and it is gradually better than the efficiency of the FCD-KNN algorithm and the traditional KNN algorithm. The simulation results show that the improved algorithm proposed can effectively improve the classification accuracy of the traditional KNN algorithm, and has certain theoretical and practical value.
2018, 38 (04): 87-92. DOI: :10.3969/j.issn.1672-6952.2018.04.017
Infinitely Many Bounded Nonoscillatory Solutions of a Higher-Order Equation
Liu Yang,Pan Bin
Abstract555)      PDF (1083KB)(260)      
        This paper considers the solvability of a higher-order nonlinear neutral delay difference equation. By using the Banach contraction principle a sufficient condition of the existence of Infinitely many bounded nonoscillatory solutions of the equation is given,which fills a gap in the literature.
2017, 37 (2): 66-70. DOI: 10.3969/j.issn.1672-6952.2017.02.014
Reconstruction of Regular RippedUp Documents
Pan Bin, Guo Xiaoming,Chen Mingming, Yu Jingxian, Zhao Xiaoying,Chen Wei
Abstract399)      PDF (1818KB)(435)      
Reconstruction of rippedup documents was important for judicial authentication,cultural relic reconstruction and military information acquisition,etc.An approach for the reconstruction of regularly rippedup documents was proposed. Firstly, the line spacing of the fragments was automatically extracted. Secondly, meanshift algorithm was adapted to cluster all the fragments. Thirdly, for each cluster, the similarity matrix was constructed based on the grayscale of the edges of the fragments. Lastly, the document with genetic algorithm was reconstructed.Reconstruction of rippedup documents is important for judicial authentication,cultural relic reconstruction and military information acquisition,etc.In this paper,we propose an approach for the reconstruction of regularly rippedup documents. Firstly, the line spacing of the fragments is automatically extracted|Then meanshift algorithm is adapted to cluster all the fragments|Then for each cluster, the similarity matrix is constructed based on the grayscale of the edges of the fragments|Lastly, we reconstruct the document with genetic algorithm.
2014, 34 (5): 70-73,78. DOI: 10.3696/j.issn.1672-6952.2014.05.018