Results 61 to 70 of about 2,180 (133)
Gaoya dianqi为了提高变压器套管温度的预测精度，提出了一种基于经验模态分解（empirical mode decomposition， EMD）和在线序列极限学习机（online sequential-extreme learning machine，OS-ELM）的变压器套管温度预测方法。首先，采用EMD法对变压器套管温度时序数据进行分解，得到若干内涵模态分量；其次，利用滑动窗口法处理各个分量形成带标签的数据集，并输入OS-ELM模型对各个分量的数据集进行训练；最后 ...
张庆平 +5 more
doaj
Mechanism-learning prediction model for pitting depth of buried pipeline based on HMOGWO-RF [PDF]
Objective China's oil and gas pipeline networks are expected to reach 24×104 km by 2025. Pipeline transportation has become one of the key means of transportation in the country.
Fulin SONG, Hong ZHAO, Xingyuan MIAO
core +1 more source
Zhongguo youzhi为了探索紫外-可见-近红外反射光谱测定油茶籽油掺伪量的方法，按照不同掺伪比例制备了244个油茶籽油掺伪大豆油、菜籽油、花生油、玉米油的样本，以自主搭建的实验平台采集所制备样本在200~1 100 nm范围内的反射光谱。将原始光谱进行Savitzky-Golay(SG)-连续小波变换（CWT）预处理后，利用Kennard-Stone(K-S)算法以2∶ 1的比例将样本划分成校正集和预测集。采用竞争性自适应重加权算法（CARS）、连续投影算法（SPA）、自主软收缩算法（BOSS）、迭代变量子集优化算法 ...
刘强，龚中良，李大鹏，文韬，汪志强，管金伟，郑文峰 LIU Qiang，GONG Zhongliang，LI Dapeng，WEN Tao， WANG Zhiqiang，GUAN Jinwei，ZHENG Wenfeng
doaj +1 more source
Predicting bearing capacity of gently inclined bauxite pillar based on numerical simulation and machine learning [PDF]
Pillar strength is significantly affected by inclination, making accurate prediction of inclined pillar strength crucial for the safety of underground quarries in inclined ore bodies.
Biaobiao YU +3 more
core +1 more source
Blind equalization algorithm based on complex support vector regression [PDF]
, 2019 A new blind equalization algorithm for complex valued signals was proposed based on the framework of complex support vector regression(CSVR).In the proposed algorithm,the error function of multi-modulus algorithm (MMA) was substituted into CSVR to ...
Bin ZHAO +4 more
core +1 more source
Yantu gongcheng xuebaoThe researches on the three-dimensional stability of rock slopes are of important theoretical significance and engineering application prospect. The conventional equivalent Mohr-Coulomb strength parameters used to analyze the stability of rock slopes ...
LU Kunlin 1, MEI Yifan 1, WANG Linfei 2, JIA Senlin 1, QIN Tao 1, ZHU Dayong 3
doaj +1 more source
Gaoya dianqi在光伏接入的配电网中，现有漏电保护装置无法区分光伏设备漏电流与发生生物触电时的故障漏电流，导致系统存在安全隐患。针对此问题，提出一种基于近邻成分分析（neighborhood component analysis，NCA）与核极限学习机（kernel extreme learning machine，KELM）的光伏接入配电网漏电识别方法。首先，构建了9维原始故障特征集，并采用NCA从9维特征集中选择得到4维高相关性特征子集；然后，将得到的4维特征子集作为KELM的输入，建立基于KELM的漏电识别模型 ...
汪自虎 +5 more
doaj
Research on prediction model of landslide creep displacement on genetic algorithm [PDF]
Landslide displacement prediction is an important basis of predicting landslide disasters. Most of the previous landslide displacement prediction models include time series prediction models, BP neural network prediction models, Gaussian fitting ...
Huaien ZENG, Pengfei TU, Yu FENG
core +1 more source
Gaoya dianqi, 2017 为了提高装备电力系统复合电能质量扰动（PQD）识别能力,提出了构建组合特征集用以全面表征装备电力系统电能质量复合扰动的粒子群优化（PSO）极限学习机（ELM）分类新方法。首先,结合S变换和经验模态分解（EMD）两种特征提取手段,构建组合特征向量集,对复合扰动信号特征边界区分更加明显;然后,优化ELM隐含层神经元数目,平衡其分类的实时性和准确性,在PSO适应度函数与ELM训练误差之间建立联系,设置了PSO初始参数,完成了分类器设计。经装备电力系统实测数据验证 ...
尹志勇, 陈永光, 刘金宁, 桑博
doaj
Rapid determination of moisture content of high cellulose and lignin materials by near-infrared diffuse reflectance spectroscopy [PDF]
Objective: To establish a rapid method for moisture detection of high cellulose and lignin materials. Methods: The areca nut, a Chinese herbal medicine containing high cellulose and lignin, was selected.
DAI Hairong +4 more
core +1 more source