To address the challenge of identifying the primary causes of energy consumption fluctuations and accurately assessing the influence of various factors in the converter unit of an iron and steel plant,the focus is pla...To address the challenge of identifying the primary causes of energy consumption fluctuations and accurately assessing the influence of various factors in the converter unit of an iron and steel plant,the focus is placed on the critical components of material and heat balance.Through a thorough analysis of the interactions between various components and energy consumptions,six pivotal factors have been identified—raw material composition,steel type,steel temperature,slag temperature,recycling practices,and operational parameters.Utilizing a framework based on an equivalent energy consumption model,an integrated intelligent diagnostic model has been developed that encapsulates these factors,providing a comprehensive assessment tool for converter energy consumption.Employing the K-means clustering algorithm,historical operational data from the converter have been meticulously analyzed to determine baseline values for essential variables such as energy consumption and recovery rates.Building upon this data-driven foundation,an innovative online system for the intelligent diagnosis of converter energy consumption has been crafted and implemented,enhancing the precision and efficiency of energy management.Upon implementation with energy consumption data at a steel plant in 2023,the diagnostic analysis performed by the system exposed significant variations in energy usage across different converter units.The analysis revealed that the most significant factor influencing the variation in energy consumption for both furnaces was the steel grade,with contributions of−0.550 and 0.379.展开更多
在室内可见光通信中符号间干扰和噪声会严重影响系统性能,K均值(K-means)均衡方法可以抑制光无线信道的影响,但其复杂度较高,且在聚类边界处易出现误判。提出了改进聚类中心点的K-means(Improved Center K-means,IC-Kmeans)算法,通过随...在室内可见光通信中符号间干扰和噪声会严重影响系统性能,K均值(K-means)均衡方法可以抑制光无线信道的影响,但其复杂度较高,且在聚类边界处易出现误判。提出了改进聚类中心点的K-means(Improved Center K-means,IC-Kmeans)算法,通过随机生成足够长的训练序列,然后将训练序列每一簇的均值作为K-means聚类中心,避免了传统K-means反复迭代寻找聚类中心。进一步,提出了基于神经网络的IC-Kmeans(Neural Network Based IC-Kmeans,NNIC-Kmeans)算法,使用反向传播神经网络将接收端二维数据映射至三维空间,以增加不同簇之间混合数据的距离,提高了分类准确性。蒙特卡罗误码率仿真表明,IC-Kmeans均衡和传统K-means算法的误码率性能相当,但可以显著降低复杂度,特别是在信噪比较小时。同时,在室内多径信道模型下,与IC-Kmeans和传统Kmeans均衡相比,NNIC-Kmeans均衡的光正交频分复用系统误码率性能最好。展开更多
为了对铁路电气设备进行智能检测,并提升检测精度,采用了You Only Look Once version 4算法,并从特征获取、全局信息获取和损失函数三个角度对其进行初步改进。基于提升模型检测速度的目的,又引入了K均值算法及深度可分离卷积。经过测...为了对铁路电气设备进行智能检测,并提升检测精度,采用了You Only Look Once version 4算法,并从特征获取、全局信息获取和损失函数三个角度对其进行初步改进。基于提升模型检测速度的目的,又引入了K均值算法及深度可分离卷积。经过测试发现,在实际应用中,检测模型的准确率和召回率最大值分别为93.83%和94.61%,耗时和内存占用率最小值分别为22.61 ms和5.8%。所设计的智能检测模型具有良好的检测精度和速度,能够较好地对现实中的铁路电气设备进行检测。展开更多
本文提出了一种基于密度聚类的三支K-Means算法。针对传统的K-Means算法在选取初始聚类中心时往往依赖于随机选择和无法处理不确定性数据对象的问题,本文采用基于密度聚类算法优化初始聚类中心的选择,并优化了截断距离的选取,最后使用...本文提出了一种基于密度聚类的三支K-Means算法。针对传统的K-Means算法在选取初始聚类中心时往往依赖于随机选择和无法处理不确定性数据对象的问题,本文采用基于密度聚类算法优化初始聚类中心的选择,并优化了截断距离的选取,最后使用三支决策的方法对聚类结果进行处理。实验结果表明,与传统的K-Means算法相比,改进的K-Means算法在聚类中表现出更高的聚类精度和稳定性。This paper proposes a three-branch K-Means algorithm based on density clustering. In view of the problem that the traditional K-Means algorithm often relies on random selection and cannot handle uncertain data objects when selecting initial clustering centers, this paper uses a density-based clustering algorithm to optimize the selection of initial clustering centers, and optimizes the selection of truncation distance. Finally, a three-branch decision method is used to process the clustering results. The experimental results show that the improved K-Means algorithm exhibits higher clustering accuracy and stability in clustering compared to the traditional K-Means algorithm.展开更多
基金financial support from the National Key R&D Program of China(Grant No.2020YFB1711100).
文摘To address the challenge of identifying the primary causes of energy consumption fluctuations and accurately assessing the influence of various factors in the converter unit of an iron and steel plant,the focus is placed on the critical components of material and heat balance.Through a thorough analysis of the interactions between various components and energy consumptions,six pivotal factors have been identified—raw material composition,steel type,steel temperature,slag temperature,recycling practices,and operational parameters.Utilizing a framework based on an equivalent energy consumption model,an integrated intelligent diagnostic model has been developed that encapsulates these factors,providing a comprehensive assessment tool for converter energy consumption.Employing the K-means clustering algorithm,historical operational data from the converter have been meticulously analyzed to determine baseline values for essential variables such as energy consumption and recovery rates.Building upon this data-driven foundation,an innovative online system for the intelligent diagnosis of converter energy consumption has been crafted and implemented,enhancing the precision and efficiency of energy management.Upon implementation with energy consumption data at a steel plant in 2023,the diagnostic analysis performed by the system exposed significant variations in energy usage across different converter units.The analysis revealed that the most significant factor influencing the variation in energy consumption for both furnaces was the steel grade,with contributions of−0.550 and 0.379.
文摘在高压并联电抗器声纹信号监测系统中,长时海量无标签声纹的高维非平稳性导致特征提取困难、无监督聚类适应性差。由此提出了一种基于深度自适应K-means++算法(deep adaptive K-means++clustering algorithm,DAKCA)的750 kV电抗器声纹聚类方法。首先通过采用两阶段无监督策略微调的改进堆叠稀疏自编码器(stacked sparse autoencoder,SSAE),对快速傅里叶变换后的归一化频域数据提取电抗器原始声纹32维深度特征。进一步提出了依据最近邻聚类有效性指标(clustering validation index based on nearest neighbors,CVNN)的自适应K-means++聚类算法,构建了能自适应确定最优聚类个数的电抗器声纹聚类模型。最后通过西北地区某750 kV电抗器实测声纹数据集进行了验证。结果表明,DAKCA算法对无标签声纹数据在不同样本均衡程度下能够稳定提取32维深度特征,并实现最优聚类,为直接高效利用电抗器无标签声纹数据提供了参考。
文摘在室内可见光通信中符号间干扰和噪声会严重影响系统性能,K均值(K-means)均衡方法可以抑制光无线信道的影响,但其复杂度较高,且在聚类边界处易出现误判。提出了改进聚类中心点的K-means(Improved Center K-means,IC-Kmeans)算法,通过随机生成足够长的训练序列,然后将训练序列每一簇的均值作为K-means聚类中心,避免了传统K-means反复迭代寻找聚类中心。进一步,提出了基于神经网络的IC-Kmeans(Neural Network Based IC-Kmeans,NNIC-Kmeans)算法,使用反向传播神经网络将接收端二维数据映射至三维空间,以增加不同簇之间混合数据的距离,提高了分类准确性。蒙特卡罗误码率仿真表明,IC-Kmeans均衡和传统K-means算法的误码率性能相当,但可以显著降低复杂度,特别是在信噪比较小时。同时,在室内多径信道模型下,与IC-Kmeans和传统Kmeans均衡相比,NNIC-Kmeans均衡的光正交频分复用系统误码率性能最好。
文摘为了对铁路电气设备进行智能检测,并提升检测精度,采用了You Only Look Once version 4算法,并从特征获取、全局信息获取和损失函数三个角度对其进行初步改进。基于提升模型检测速度的目的,又引入了K均值算法及深度可分离卷积。经过测试发现,在实际应用中,检测模型的准确率和召回率最大值分别为93.83%和94.61%,耗时和内存占用率最小值分别为22.61 ms和5.8%。所设计的智能检测模型具有良好的检测精度和速度,能够较好地对现实中的铁路电气设备进行检测。
文摘本文提出了一种基于密度聚类的三支K-Means算法。针对传统的K-Means算法在选取初始聚类中心时往往依赖于随机选择和无法处理不确定性数据对象的问题,本文采用基于密度聚类算法优化初始聚类中心的选择,并优化了截断距离的选取,最后使用三支决策的方法对聚类结果进行处理。实验结果表明,与传统的K-Means算法相比,改进的K-Means算法在聚类中表现出更高的聚类精度和稳定性。This paper proposes a three-branch K-Means algorithm based on density clustering. In view of the problem that the traditional K-Means algorithm often relies on random selection and cannot handle uncertain data objects when selecting initial clustering centers, this paper uses a density-based clustering algorithm to optimize the selection of initial clustering centers, and optimizes the selection of truncation distance. Finally, a three-branch decision method is used to process the clustering results. The experimental results show that the improved K-Means algorithm exhibits higher clustering accuracy and stability in clustering compared to the traditional K-Means algorithm.
