ID 原文 译文
15155 针对已有绝缘子状态识别模型,以及深层网络尺度和交叉熵损失函数的缺陷,仿照运维人员检修模式,即依据评测结果的可信度动态决策,基于多尺度网络构建了一种绝缘子自曝状态智能认知方法。 In view of the drawbacks of the existing insulator state recognition models, and the scale and softmax loss function of deep network, imitating the mode of personnel operation and maintenance, that is, dynamic decision-making based on the credibility of the evaluation results, this paper constructs an intelligent cognition method of insulator self-blast states based on the multi-scale network.
15156 首先,面向定位归一化化预处理后的绝缘子图像,基于ResNet-18增加不同结构的网络分支提高网络适应不同分辨率的能力,同时在网络末端添加多尺度信息融合模块; Firstly, for the pre-processed insulator images with localization and normalization, based on ResNet-18, branches with different network structure are added to improve the network ability to adapt to different resolutions. At the same time, the multi-scale information fusion module is added at the end of the network.
15157 其次,随机配置网络面向多个尺度特征,构建了泛化的自曝状态分类认知准则; Secondly, facing multiple scale features, stochastic con-figuration network( SCN) constructs a generalized cognition criterion of self-blast state classification.
15158 最后,为了评测自曝状态分类认知结果的可信度,基于定义的误差指标自调节多尺度网络架构,重构不确定认知结果约束下的特征向量和分类认知准则,以进行自曝状态再认知。 Finally, in order to evaluate the credibility of the self-blast state cognition result, based on the defined error index, the multi-scale network architecture is self-ad-justed to reconstruct the feature vector and classification cognition criterion under the constraint of the uncertain cognition result,which carries out the self-blast state renewal cognition.
15159 实验结果显示,与其他方法相比,所提出的智能认知方法增强了模型的泛化能力和认知精度。 The experimental results show that the proposed intelligent cognition method enhances the generalization ability and cognition accuracy compared with other methods.
15160 针对当前流媒体的大量视频资源从而带来的云计算的负载均衡和任务分配问题,在Cloudsim云环境下实现了任务调度的GAAC算法(Greedy And Ant Colony Algorithm,GAAC)。 Aiming at the problem of cloud computing load balancing and task allocation brought about by a large number of video resources in the current streaming media, the task scheduling GAAC algorithm(Greedy And Ant Colony Algorithm,GAAC) is implemented in the Cloudsim cloud environment.
15161 GAAC算法具有迭代学习机制、局部最优和负载均衡的特点。 GAAC algorithm has the characteristics of iterative learning mechanism, local optimization and load balancing.
15162 并在Cloudsim的环境下,完成了对GAAC算法、轮转算法(Round Roll Algorithm,RR)、贪心算法和蚁群算法的仿真比较。 In the context of cloudsim, simulations of GAAC algorithm, Round Roll Algorithm( RR), greedy algorithm and ant colony algorithm were completed.
15163 实验验证,GAAC算法从总体上而言,任务调度所用的时间明显较低于贪心算法和传统的轮转算法和蚁群算法,即其任务执行的时间更短,效率更高。 The experimental verification shows that GAAC algorithm is generally lower in the time spent on task scheduling than greedy algorithm, traditional rotation algorithm and ant colony algorithm.
15164 对于多点定位系统的定位精度受基站几何布局影响的问题,提出基于改进型差分进化算法的布站优化方法。 Aiming at the problem that the geometric layout of the base station of multilateration system directly affects the positioning precision of the target, an optimization method of station layout based on an improved Differential Evolution(DE) algorithm is proposed.