Results 71 to 80 of about 10,917 (169)
, 2022 针对在强烈背景噪声影响下的滚动轴承故障特征提取困难，提出了一种基于变分模态分解与卷积神经网络融合的滚动轴承故障诊断方法。将原始振动信号分解为多个模态分量，结合皮尔逊相关系数作为自动分解终止阈值和最优模态分量选取指标；针对轴承故障特征构建卷积神经网络，将最优模态分量作为输入以提取、分类故障类型。试验结果表明，所提方法能够精确诊断滚动轴承故障 ...
刘春阳 +5 more
core +1 more source
野生动物学报, 2023 为了解全球海蛇（Hydrophiinae）的地理分布格局对陆上温度的响应，进一步研究其生存环境与分布丰度模式的关系。从GBIF网站收集全球71种海蛇地理分布信息，划分全球海蛇的高中低丰度区，并划分海蛇的“广布种”和“特有种”，用GIS技术建立物种丰富度模式，获取气候变量数据，对分布丰度和陆上温度生态位宽度进行统计分析。结果显示：有8个区域可被定义为“高丰度区”，22种海蛇可被定义为“广布种”。在高丰度区，部分海蛇加宽陆上温度生态位，部分则收窄生态位；1个物种的局部陆上温度生态位存在地理变异 ...
王湘君 +4 more
doaj
High-Precision Fault Diagnosis Method for Energy Storage Inverter Signals [PDF]
Owing to the global trends of energy transition and carbon neutrality, ensuring the stability of energy storage inverters as key components is crucial.
Yu WANG, Qi QI, Chun WANG, Cai XU
core +1 more source
Research on Fault Diagnosis Method of Photovoltaic Arrays Based on Improved Grey Wolf Algorithm Optimized Extreme Learning Machine [PDF]
ObjectivesPhotovoltaic arrays operating under complex outdoor conditions encounter various fault types with varying degrees of severity. To accurately assess the working status of photovoltaic arrays, a fault diagnosis method based on an improved grey ...
HAN Maolin +4 more
core +1 more source
, 2020 针对齿轮箱的滚动轴承故障信号因噪声干扰，难以进行有效提取的问题，提出了基于变分模态分解与快速谱峭图相结合的轴承故障特征提取方法。首先，利用变分模态分解（Variational Mode Decomposition，VMD）将振动信号分解成若干个本征模态分量（Intrinsic Mode Function，IMF），通过相关峭度计算选取故障信息最突出的分量信号；然后，利用快速谱峭图自适应地确定带通滤波；最后，对滤波后的信号进行平方包络谱分析，提取出故障信息。通过公开数据分析和齿轮箱轴承故障实验 ...
康建设, 池阔, 迭旭鹏
core +1 more source
Efficient Seismic Denoising Transformer with Gradient Prediction and Parameter-Free Attention [PDF]
Suppression of random noise can effectively improve the signal-to-noise ratio (SNR) of seismic data. In recent years, convolutional neural network (CNN)-based deep learning methods have shown significant performance in seismic data denoising.
GAO Lei, QIAO Haowei, LIANG Dongsheng, MIN Fan, YANG Mei
core +1 more source
基于多级特征提取和IHHO-KELM的变压器油中溶解气体体积分数预测
Gaoya dianqi油中溶解气体分析是变压器早期故障诊断的主要方法，准确预测未来特征气体体积分数有助于提前获取变压器的运行状态。为此提出了一种基于多级特征提取和IHHO-KELM的变压器油中溶解气体体积分数预测方法。首先，通过自适应白噪声完全集合经验模态分解将气体体积分数序列分解为多个子序列，利用奇异谱分析对子序列做进一步降噪处理，降低其非平稳性；其次，建立核极限学习机预测模型分别对各子序列进行预测，再将各子序列的预测结果叠加得到油中溶解气体体积分数的最终预测结果，并通过改进哈里斯鹰算法优化其超参数；最后，通过算例验证表明，
傅雨晨 +5 more
doaj
Zhendong Ceshi yu Zhenduan为解决变分模态分解（variational mode decomposition，简称VMD）在噪声情况下提取风电机组故障特征时因参数设置的人为经验不足而带来的误差问题及耗费时间的问题，提出一种基于自适应变分模态分解（adaptive variational mode decomposition，简称AVMD）算法的风电机组故障诊断方法。首先，将包络熵‑峭度‑互信息准则（envelope entropy，kurtosis and mutual information，简称EKM）作为黏菌算法（slime
doaj +1 more source
基于用最小二乘法改进的EMD与能量熵融合的断路器机械故障诊断方法
Gaoya dianqi, 2014 笔者针对经验模态分解（EMD）分解结果的准确性对实验结果的影响,利用最小二乘法对EMD进行改进,有效地缓解了EMD固有的端点效应对实验结果的影响。分别对断路器操动机构的正常振动信号和连接臂松动信号进行EMD和小波变换分解,并将能量熵分别应用到改进EMD与小波变换中。通过能量熵值计算分析表明,改进的EMD能量熵值明显大于小波能量熵,因此改进的EMD与能量熵融合法为断路器机械状态识别提供了有益的帮助。
许丹, 于龙, 王玉梅
doaj
Multi-target vital sign estimation based on sparse representation under complex scenes [PDF]
Focusing on the issue that millimeter-wave radar was difficult to accurately estimate the vital signs of multiple moving targets in complex indoor scenes, a multi-target vital sign estimation method based on sparse representation under complex scenes was
HUANG Zifeng, MA Jiakang, WANG Hongyan
core +1 more source