In recent years, wind power has become more and more important in the energy component. In order to improve the prediction accuracy of wind farms and help management and scheduling, a multi-site short-term wind power spatiotemporal combination forecasting model based on dynamic graph convolution and graph attention is proposed. Firstly, graph convolution is used to realize neighbor aggregation of temporal features between multiple sites, and the graph attention mechanism is used to enhance its ability to extract spatial features. At the same time, in view of the problem that the traditional model cannot deal with the real-time change of graph node correlation, the adjacency matrix is dynamically constructed according to the correlation coefficient and distance between nodes in the graph convolution process. Finally, the Gated Recurrent Unit is used to process the context information of dynamic graph convolution output to complete the prediction of wind power. The experimental results show that the proposed combined model is optimal in the aspects of prediction accuracy, stability and multi-step prediction performance.
In parallel channels of a nuclear reactor core, flow instability can cause a significant decrease in critical heat flux (CHF) or mechanical oscillation of the fuel components, endangering the normal operation of the reactor. The NUMAP software, developed based on the two-fluid six-equation theory and using the Modelica language, is a multi-domain unified modeling and simulation platform for nuclear power plants. In this paper, a parallel dual-channel system model was constructed based on the NUMAP software, referencing a high-temperature and high-pressure steam-water two-phase thermohydraulic experimental device, to simulate flow instability phenomena. The comparison with experimental data validated the transient analysis ability of the NUMAP software for flow instability phenomena. Based on this, the flow instability boundary of a parallel multi-channel system was calculated under the same operating conditions. When the number of parallel channels was 2, 3, and 4, the calculated flow instability boundary error did not exceed ±5%, verifying that a parallel dual-channel structure can be used to obtain the flow instability boundary when there are multiple parallel heating channels.
In this paper, we address the characteristics of various associations implied between fake reviewers and fake reviews, and the ability to construct review network graphs with dependency relationships. Firstly, we use graph neural networks to extract association features between reviews, propose a method to improve graph neural networks based on TrustRank and propose a multi-feature detection framework. Then the graph neural network is used to aggregate neighborhood feature output embeddings and connect them with the paragraph vectors extracted by Doc2vec. Finally, the experiments show that the algorithm in this paper can detect more fake reviews and has a better check-all effect.
Particle swarm optimization (PSO) algorithm has been widely used in large-scale complex problems such as resource allocation in recent years because of its simple implementation and easy operation. However, the slow convergence speed and low solution accuracy of the algorithm also restrict its further application. To solve the above problems, this paper introduces the chromosome crossing characteristics of genetic algorithm (GA), and proposes a comprehensive learning particle swarm optimization based on optimal particle recombination. With the help of the ability of comprehensive learning strategy to efficiently explore the solution space, this method organically combines the excellent information explored by each particle through the optimal particle recombination, so as to obtain a better individual, speed up the convergence speed of the algorithm, and improve the solution accuracy of the problem. The experimental results of benchmark function show that the proposed algorithm has faster convergence speed and optimization accuracy than the original algorithm, and the results of Friedman test and Wilcoxon signed-rank test prove the feasibility of the optimal particle recombination operation in particle swarm optimization.
针对轻量化网络结构从特征图提取有效语义信息不足,以及语义信息与空间细节信息融合模块设计不合理而导致分割精度降低的问题,设计一个深度融合空洞金字塔和一个语义融合模块,以进一步提取语义信息并进行深度融合.主干网络中采用双分支深度融合网络,通过设计的深度融合空洞金字塔结构进一步提取信息,在空间信息与语义信息融合的过程中,采用语义融合模块将深层次的语义信息与浅层次的空间信息进行自底向上逐步融合的方式,从而提高网络语义分割性能.最后,将所设计的网络结构在城市景观数据集上进行实验,取得了77.6%的平均交并比,对比其他网络结构,其能够有效提高分割结果.
