期刊文献+
任意字段
题名或关键词
题名
关键词
摘要
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息
共找到1,282篇文章
< 1 2 … 65 >
每页显示 20 50 100
已选0条
引用分析
参考文献
引证文献
 统计分析
检索结果
已选文献
显示方式：
Residual Strength Prediction of Corroded Pipelines Based on Sparrow Search Algorithm-Optimized Kernel Extreme Learning Machine 认领 引用
1
作者 Zixuan Zong Tingting Long +3 位作者 Huaqing Dong Guoqiang Huang Xiao Meng Mohammadamin Azimi 《Structural Durability & Health Monitoring》 EI 2026年第3期480-495,共16页
This paper proposes a novel approach for predicting the residual strength of corroded pipelines by combining the Kernel Extreme Learning Machine(KELM)with Sparrow Search Algorithm(SSA)optimization.The proposed SSA-KEL... This paper proposes a novel approach for predicting the residual strength of corroded pipelines by combining the Kernel Extreme Learning Machine(KELM)with Sparrow Search Algorithm(SSA)optimization.The proposed SSA-KELM model addresses the limitations of traditional evaluation methods and single machine learning models in residual strength prediction.A dataset comprising 80 samples from burst tests and finite element simulations was used to validate the model.Results demonstrate that the SSA-KELM model achieves superior prediction accuracy with a maximum relative error of 13.54%and minimum relative error of 0.20%.The model’s mean absolute error(MAE),root mean square error(RMSE),and mean absolute percentage error(MAPE)are 0.658%,0.780%,and 4.38%,respectively,significantly outperforming conventional machine learning models and traditional assessment methods.This research provides a reliable tool for evaluating pipeline integrity and maintenance planning. 展开更多
关键词 Pipeline corrosion residual strength prediction kernel extreme learning machine sparrow search algorithm machine learning
暂未订购 下载PDF
Amplitude phase control for electro-hydraulic servo system based on normalized least-mean-square adaptive filtering algorithm 认领 引用 被引量：6
2
作者 姚建均 富威 +1 位作者 胡胜海 韩俊伟 《Journal of Central South University》 SCIE EI CAS 2011年第3期755-759,共5页
The electro-hydraulic servo system was studied to cancel the amplitude attenuation and phase delay of its sinusoidal response,by developing a network using normalized least-mean-square (LMS) adaptive filtering algorit... The electro-hydraulic servo system was studied to cancel the amplitude attenuation and phase delay of its sinusoidal response,by developing a network using normalized least-mean-square (LMS) adaptive filtering algorithm.The command input was corrected by weights to generate the desired input for the algorithm,and the feedback was brought into the feedback correction,whose output was the weighted feedback.The weights of the normalized LMS adaptive filtering algorithm were updated on-line according to the estimation error between the desired input and the weighted feedback.Thus,the updated weights were copied to the input correction.The estimation error was forced to zero by the normalized LMS adaptive filtering algorithm such that the weighted feedback was equal to the desired input,making the feedback track the command.The above concept was used as a basis for the development of amplitude phase control.The method has good real-time performance without estimating the system model.The simulation and experiment results show that the proposed amplitude phase control can efficiently cancel the amplitude attenuation and phase delay with high precision. 展开更多
关键词 amplitude attenuation phase delay normalized least-mean-square adaptive filtering algorithm tracking performance electro- hydraulic servo system
暂未订购 下载PDF
An improved YOLOv8 apple leaf disease detection algorithm 认领 引用
3
作者 Xinyu PEI Wei YUAN +1 位作者 Yuexiu ZHANG Lianjun SONG 《Optoelectronics Letters》 EI 2026年第5期314-320,共7页
This paper suggests an improved you only look once version 8n(YOLOv8n)algorithm for apple leaf disease detection,abbreviated as ALWB-YOLOv8n.The model is comprised of four essential components.Initially,arbitrary kern... This paper suggests an improved you only look once version 8n(YOLOv8n)algorithm for apple leaf disease detection,abbreviated as ALWB-YOLOv8n.The model is comprised of four essential components.Initially,arbitrary kernel convolution(AKConv)replaces the convolution module,which significantly decreases both the model’s parameter count and its overall size.Secondly,the large selective kernel network(LSKNet)attention mechanism is added in the Backbone,which can dynamically adjust the spatial sensory domain,and experiments have proved that this method is extremely advantageous for small target detection.Third,a weighted bi-directional feature pyramid network is introduced,which enables the model to achieve multi-scale feature fusion and is more concise and faster.Finally,wise intersection over union(WIoU)is used to replace complete intersection over union(CIoU)in YOLOv8,and the idea of focal loss is introduced,which effectively solves the detection problems in cases such as apple leaves occluding each other and blurred boundaries of diseased leaves.The improved algorithm exhibits superior performance compared to other common object detection algorithms.Compared with YOLOv8n,the improved algorithm achieves 2.3%improvement in precision,3.8%improvement in recall,and 2.5%and 2.7%improvement in mAP0.5 and mAP0.5:0.95,respectively.Compared with YOLOv8n,the improved model reduces the number of parameters and size of the model and realizes real-time monitoring with a frames per second(FPS)of 50.5. 展开更多
关键词 large selective kernel network arbitrary kernel convolution large selective kernel network lsknet attention kernel convolution akconv replaces weighted bi directional feature pyramid network adjust spatial sensory domainand improved YOLOv n algorithm apple leaf disease detection
暂未订购 下载PDF
Cobalt crust recognition based on kernel Fisher discriminant analysis and genetic algorithm in reverberation environment 认领 引用 被引量：2
4
作者 ZHAO Hai-ming ZHAO Xiang +1 位作者 HAN Feng-lin WANG Yan-li 《Journal of Central South University》 SCIE EI CAS CSCD 2021年第1期179-193,共15页
Recognition of substrates in cobalt crust mining areas can improve mining efficiency.Aiming at the problem of unsatisfactory performance of using single feature to recognize the seabed material of the cobalt crust min... Recognition of substrates in cobalt crust mining areas can improve mining efficiency.Aiming at the problem of unsatisfactory performance of using single feature to recognize the seabed material of the cobalt crust mining area,a method based on multiple-feature sets is proposed.Features of the target echoes are extracted by linear prediction method and wavelet analysis methods,and the linear prediction coefficient and linear prediction cepstrum coefficient are also extracted.Meanwhile,the characteristic matrices of modulus maxima,sub-band energy and multi-resolution singular spectrum entropy are obtained,respectively.The resulting features are subsequently compressed by kernel Fisher discriminant analysis(KFDA),the output features are selected using genetic algorithm(GA)to obtain optimal feature subsets,and recognition results of classifier are chosen as genetic fitness function.The advantages of this method are that it can describe the signal features more comprehensively and select the favorable features and remove the redundant features to the greatest extent.The experimental results show the better performance of the proposed method in comparison with only using KFDA or GA. 展开更多
关键词 feature extraction kernel Fisher discriminant analysis(KFDA) genetic algorithm multiple feature sets cobalt crust recognition
暂未订购 下载PDF
A Full-Newton Step Feasible Interior-Point Algorithm for the Special Weighted Linear Complementarity Problems Based on a Kernel Function 认领 引用 被引量：2
5
作者 GENG Jie ZHANG Mingwang ZHU Dechun 《Wuhan University Journal of Natural Sciences》 CAS CSCD 2024年第1期29-37,共9页
In this paper,a new full-Newton step primal-dual interior-point algorithm for solving the special weighted linear complementarity problem is designed and analyzed.The algorithm employs a kernel function with a linear ... In this paper,a new full-Newton step primal-dual interior-point algorithm for solving the special weighted linear complementarity problem is designed and analyzed.The algorithm employs a kernel function with a linear growth term to derive the search direction,and by introducing new technical results and selecting suitable parameters,we prove that the iteration bound of the algorithm is as good as best-known polynomial complexity of interior-point methods.Furthermore,numerical results illustrate the efficiency of the proposed method. 展开更多
关键词 interior-point algorithm weighted linear complementarity problem full-Newton step kernel function iteration complexity
暂未订购 下载PDF
Improved Kernel Possibilistic Fuzzy Clustering Algorithm Based on Invasive Weed Optimization 认领 引用 被引量：1
6
作者 赵小强 周金虎 《Journal of Shanghai Jiaotong university(Science)》 EI 2015年第2期164-170,共7页
Fuzzy c-means(FCM) clustering algorithm is sensitive to noise points and outlier data, and the possibilistic fuzzy c-means(PFCM) clustering algorithm overcomes the problem well, but PFCM clustering algorithm has some ... Fuzzy c-means(FCM) clustering algorithm is sensitive to noise points and outlier data, and the possibilistic fuzzy c-means(PFCM) clustering algorithm overcomes the problem well, but PFCM clustering algorithm has some problems: it is still sensitive to initial clustering centers and the clustering results are not good when the tested datasets with noise are very unequal. An improved kernel possibilistic fuzzy c-means algorithm based on invasive weed optimization(IWO-KPFCM) is proposed in this paper. This algorithm first uses invasive weed optimization(IWO) algorithm to seek the optimal solution as the initial clustering centers, and introduces kernel method to make the input data from the sample space map into the high-dimensional feature space. Then, the sample variance is introduced in the objection function to measure the compact degree of data. Finally, the improved algorithm is used to cluster data. The simulation results of the University of California-Irvine(UCI) data sets and artificial data sets show that the proposed algorithm has stronger ability to resist noise, higher cluster accuracy and faster convergence speed than the PFCM algorithm. 展开更多
关键词 data mining clustering algorithm possibilistic fuzzy c-means(PFCM) kernel possibilistic fuzzy c-means algorithm based on invasiv
暂未订购 下载PDF
Semi-supervised kernel FCM algorithm for remote sensing image classification 认领 引用
7
作者 刘小芳 HeBinbin LiXiaowen 《High Technology Letters》 EI CAS 2011年第4期427-432,共6页
These problems of nonlinearity, fuzziness and few labeled data were rarely considered in traditional remote sensing image classification. A semi-supervised kernel fuzzy C-means （SSKFCM） algorithm is proposed to over... These problems of nonlinearity, fuzziness and few labeled data were rarely considered in traditional remote sensing image classification. A semi-supervised kernel fuzzy C-means （SSKFCM） algorithm is proposed to overcome these disadvantages of remote sensing image classification in this paper. The SSKFCM algorithm is achieved by introducing a kernel method and semi-supervised learning technique into the standard fuzzy C-means （FCM） algorithm. A set of Beijing-1 micro-satellite＇s multispectral images are adopted to be classified by several algorithms, such as FCM, kernel FCM （KFCM）, semi-supervised FCM （SSFCM） and SSKFCM. The classification results are estimated by corresponding indexes. The results indicate that the SSKFCM algorithm significantly improves the classification accuracy of remote sensing images compared with the others. 展开更多
关键词 remote sensing image classification semi-supervised kernel fuzzy C-means （SSKFCM）algorithm Beijing-1 micro-satellite semi-supcrvisod learning tochnique kernel method
暂未订购 下载PDF
Kernel Factor Analysis Algorithm with Varimax 认领 引用
8
作者 夏国恩 金炜东 张葛祥 《Journal of Southwest Jiaotong University(English Edition)》 2006年第4期394-399,共6页
Kernal factor analysis （KFA） with vafimax was proposed by using Mercer kernel function which can map the data in the original space to a high-dimensional feature space, and was compared with the kernel principle com... Kernal factor analysis （KFA） with vafimax was proposed by using Mercer kernel function which can map the data in the original space to a high-dimensional feature space, and was compared with the kernel principle component analysis （KPCA）. The results show that the best error rate in handwritten digit recognition by kernel factor analysis with vadmax （4.2%） was superior to KPCA （4.4%）. The KFA with varimax could more accurately image handwritten digit recognition. 展开更多
关键词 Kernel factor analysis Kernel principal component analysis Support vector machine Varimax Algorithm Handwritten digit recognition
暂未订购 下载PDF
Bayesian optimized support vector regression with a Gaussian kernel for accurate prediction of the state of health of lithium-ion batteries used for electric vehicle applications 认领 引用
9
作者 Selvaraj Vedhanayaki Vairavasundaram Indragandhi 《Global Energy Interconnection》 EI CSCD 2025年第5期891-904,共14页
The state of health SoH of lithium ion batteries plays a predominant role in ensuring the safe and reliable operation of electric vehicles.In this,a novel SoH estimation approach using support vector regression with a... The state of health SoH of lithium ion batteries plays a predominant role in ensuring the safe and reliable operation of electric vehicles.In this,a novel SoH estimation approach using support vector regression with a Gaussian kernel optimized using the Bayesian optimization technique(BO-SVR with a Gaussian kernel)was proposed.Unlike,traditional approaches that use the internal resistance,and battery capacity as input parameters,this study utilized the equivalent discharging voltage difference interval and equivalent charging voltage difference interval,as they capture the dynamic voltage characteristics associated with the battery degradation.The model was simulated using MATLAB 2023a.The mean absolute error,R2,root mean squared error,and mean squared error were considered as performance indicators.The simulation results indicated that the proposed BO-SVR with a Gaussian kernel model had superior performance to other kernel SVR and Gaussian Process Regression models,with a reduced RMSE of 0.0082,thus demonstrating its potential to predict the SoH more accurately. 展开更多
关键词 Lithium-ion batteries State of health Machine learning algorithms Bayesian optimization Kernel function
暂未订购 下载PDF
Interior-Point Algorithm for Linear Optimization Based on a New Kernel Function 认领 引用 被引量：2
10
作者 CHEN Donghai ZHANG Mingwang LI Weihua 《Wuhan University Journal of Natural Sciences》 CAS 2012年第1期12-18,共7页
In this paper, we design a primal-dual interior-point algorithm for linear optimization. Search directions and proximity function are proposed based on a new kernel function which includes neither growth term nor barr... In this paper, we design a primal-dual interior-point algorithm for linear optimization. Search directions and proximity function are proposed based on a new kernel function which includes neither growth term nor barrier term. Iteration bounds both for large-and small-update methods are derived, namely, O（nlog（n/c）） and O（√nlog（n/ε））. This new kernel function has simple algebraic expression and the proximity function has not been used before. Analogous to the classical logarithmic kernel function, our complexity analysis is easier than the other pri- mal-dual interior-point methods based on logarithmic barrier functions and recent kernel functions. 展开更多
关键词 linear optimization interior-point algorithms pri- mal-dual methods kernel function polynomial complexity
暂未订购 下载PDF
Rockburst Intensity Prediction based on Kernel Extreme Learning Machine(KELM) 认领 引用 被引量：1
11
作者 XIAO Yidong QI Shengwen +3 位作者 GUO Songfeng ZHANG Shishu WANG Zan GONG Fengqiang 《Acta Geologica Sinica(English Edition)》 SCIE CAS CSCD 2025年第1期284-295,共12页
As one of the most serious geological disasters in deep underground engineering,rockburst has caused a large number of casualties.However,because of the complex relationship between the inducing factors and rockburst ... As one of the most serious geological disasters in deep underground engineering,rockburst has caused a large number of casualties.However,because of the complex relationship between the inducing factors and rockburst intensity,the problem of rockburst intensity prediction has not been well solved until now.In this study,we collect 292 sets of rockburst data including eight parameters,such as the maximum tangential stress of the surrounding rock σθ,the uniaxial compressive strength of the rockσc,the uniaxial tensile strength of the rock σt,and the strain energy storage index Wet,etc.from more than 20 underground projects as training sets and establish two new rockburst prediction models based on the kernel extreme learning machine(KELM)combined with the genetic algorithm(KELM-GA)and cross-entropy method(KELM-CEM).To further verify the effect of the two models,ten sets of rockburst data from Shuangjiangkou Hydropower Station are selected for analysis and the results show that new models are more accurate compared with five traditional empirical criteria,especially the model based on KELM-CEM which has the accuracy rate of 90%.Meanwhile,the results of 10 consecutive runs of the model based on KELM-CEM are almost the same,meaning that the model has good stability and reliability for engineering applications. 展开更多
关键词 rockburst intensity prediction kernel extreme learning machine genetic algorithm cross-entropy method
暂未订购 下载PDF
Adaptive Kernel Firefly Algorithm Based Feature Selection and Q-Learner Machine Learning Models in Cloud 认领 引用
12
作者 I.Mettildha Mary K.Karuppasamy 《Computer Systems Science & Engineering》 SCIE EI 2023年第9期2667-2685,共19页
CC’s(Cloud Computing)networks are distributed and dynamic as signals appear/disappear or lose significance.MLTs(Machine learning Techniques)train datasets which sometime are inadequate in terms of sample for inferrin... CC’s(Cloud Computing)networks are distributed and dynamic as signals appear/disappear or lose significance.MLTs(Machine learning Techniques)train datasets which sometime are inadequate in terms of sample for inferring information.A dynamic strategy,DevMLOps(Development Machine Learning Operations)used in automatic selections and tunings of MLTs result in significant performance differences.But,the scheme has many disadvantages including continuity in training,more samples and training time in feature selections and increased classification execution times.RFEs(Recursive Feature Eliminations)are computationally very expensive in its operations as it traverses through each feature without considering correlations between them.This problem can be overcome by the use of Wrappers as they select better features by accounting for test and train datasets.The aim of this paper is to use DevQLMLOps for automated tuning and selections based on orchestrations and messaging between containers.The proposed AKFA(Adaptive Kernel Firefly Algorithm)is for selecting features for CNM(Cloud Network Monitoring)operations.AKFA methodology is demonstrated using CNSD(Cloud Network Security Dataset)with satisfactory results in the performance metrics like precision,recall,F-measure and accuracy used. 展开更多
关键词 Cloud analytics machine learning ensemble learning distributed learning clustering classification auto selection auto tuning decision feedback cloud DevOps feature selection wrapper feature selection Adaptive Kernel Firefly Algorithm(AKFA) Q learning
暂未订购 下载PDF
基于GSABO-ICEEMDAN-KELM的局部放电识别方法在气体绝缘开关设备故障诊断中的应用 认领 引用 被引量：2
13
作者 王思涵 马宏忠 +2 位作者 孙维 葛威 陈悦林 《南方电网技术》 CSCD 北大核心 2026年第2期66-77,共12页
气体绝缘开关(gas-insulated switchgear,GIS)设备在生产运行时存在多种绝缘缺陷,准确识别绝缘缺陷导致的局部放电信号对保障GIS设备及电力系统安全有重大意义。采用融合黄金正弦算法(golden sine algorithm,Golden-SA)改进减法优化(sub... 气体绝缘开关(gas-insulated switchgear,GIS)设备在生产运行时存在多种绝缘缺陷,准确识别绝缘缺陷导致的局部放电信号对保障GIS设备及电力系统安全有重大意义。采用融合黄金正弦算法(golden sine algorithm,Golden-SA)改进减法优化(subtraction-average-based optimizer,SABO)算法,得到了融合黄金正弦改进SABO优化算法(GSABO),对改进的完全自适应噪声集合经验模态分解(improved complete ensemble empirical mode decomposition with adaptive noise)与核极限学习机(kernel extreme learning machine)进行参数寻优,以实现对GIS局部放电故障的识别。首先,针对SABO可能陷入局部最优、收敛速度不够理想等问题,引入混沌映射与黄金正弦对其进行改进。然后,搭建实验平台采集4种典型局部放电信号,利用GSABO-ICEEMDAN对其进行分解,并利用相关系数法筛选有效的模态分量。最后计算筛选后模态分量的样本熵形成特征矩阵,将其输入GSABO-KELM进行故障分类识别。通过实验分析表明,相比于未改进的SABO算法,GSABO在跳出局部最优、收敛速度与精度上有明显的优势。结合其他传统算法进行对比,GSABO-ICEEMDAN-KELM的识别准确率可达99.1667%,验证了此算法的准确性与优越性,对于GIS局部放电故障诊断的工程应用具有参考意义。 展开更多
关键词 气体绝缘组合电器 局部放电 ICEEMDAN 改进减法优化算法 黄金正弦算法 核极限学习机 故障诊断
暂未订购 下载PDF
结合深度核学习与高斯过程的边坡稳定性预测方法 认领 引用 被引量：1
14
作者 李书 喻国荣 +1 位作者 付兵杰 鲍海洲 《水力发电》 CAS 2026年第2期40-47,共8页
鉴于边坡特征之间、特征与稳定性判定之间的复杂非线性关系,经典的高斯过程边坡稳定性预测方法在复杂结构建模上表现有限且难以处理大规模的边坡数据,提出一种结合深度核学习与高斯过程的边坡稳定性预测方法。首先,利用多层前馈网络对... 鉴于边坡特征之间、特征与稳定性判定之间的复杂非线性关系,经典的高斯过程边坡稳定性预测方法在复杂结构建模上表现有限且难以处理大规模的边坡数据,提出一种结合深度核学习与高斯过程的边坡稳定性预测方法。首先,利用多层前馈网络对边坡特征进行深度提取,再将隐空间映射到带有径向基函数核的高斯过程,实现非参数不确定性量化。模型通过最大化边缘对数似然函数优化神经网络权重与核超参数,可端到端学习数据驱动的最优核。在公开的Kaggle数据集上的试验表明,所提方法较经典机器学习算法随机森林RF、支持向量机SVM、高斯过程回归GPR,以及深度学习方法门控循环单元GRU、深度神经网络DNN在均方根误差、平均绝对误差和决定系数等指标上均取得最佳结果,为边坡灾害智能预警提供了新的技术支撑。 展开更多
关键词 边坡稳定性 预测算法 深度核学习 高斯过程回归 经典机器学习算法
暂未订购 下载PDF
基于SABO-VMD与改进KELM的水电机组故障诊断 认领 引用 被引量：3
15
作者 张彬桥 高志伟 +1 位作者 陈庆松 章泽生 《人民长江》 北大核心 2026年第6期252-259,276,共8页
为了提高水电机组故障诊断的精度,提出一种由减法平均优化算法(SABO)优化变分模态分解(VMD)及改进蜣螂优化算法(IDBO)-核极限学习机(KELM)联合构建的水电机组故障诊断模型。首先,采用SABO算法来优化VMD的重要参数(惩罚因子α和分解个数... 为了提高水电机组故障诊断的精度,提出一种由减法平均优化算法(SABO)优化变分模态分解(VMD)及改进蜣螂优化算法(IDBO)-核极限学习机(KELM)联合构建的水电机组故障诊断模型。首先,采用SABO算法来优化VMD的重要参数(惩罚因子α和分解个数K);提取SABO-VMD分解排列熵与互信息熵的复合函数最小本征模态分量(IMF)作为最优分量,计算其相关时域特征参数并构建故障信号特征向量;然后引入Tent混沌映射和自适应t分布扰动多种策略对蜣螂优化算法进行改进,并利用IDBO算法对KELM模型进行参数优化,构建IDBO-KELM水电机组故障诊断模型;最后采用转子实验平台模拟机组轴系故障,对模型进行验证。验证结果表明:该方法在水电机组轴系故障诊断方面的准确率达到99.375%。研究成果可为高精度水电机组故障诊断提供思路和方案。 展开更多
关键词 水电机组故障诊断 减法平均优化算法 模态分解 改进蜣螂优化算法 核极限学习机
暂未订购 下载PDF
基于BWO优化VMD和KELM的柔性直流输电线路短路故障定位方法 认领 引用 被引量：3
16
作者 赵岩 王梓毅 徐天 《南方电网技术》 CSCD 北大核心 2026年第3期8-18,31,共11页
针对行波波头标定的精度不足以及智能定位模型拟合性能易受参数影响的问题,提出了一种基于白鲸算法优化变分模态分解和核极限学习机的柔性直流输电线路短路故障定位方法。首先,采用白鲸算法优化变分模态分解的参数,结合小波软阈值去噪... 针对行波波头标定的精度不足以及智能定位模型拟合性能易受参数影响的问题,提出了一种基于白鲸算法优化变分模态分解和核极限学习机的柔性直流输电线路短路故障定位方法。首先,采用白鲸算法优化变分模态分解的参数,结合小波软阈值去噪方法对采集的故障信号进行降噪和分解,再结合希尔伯特变换标定初始行波的到达时刻。其次,将行波的到达时刻作为特征值构建特征数据集,用白鲸算法优化核极限学习机定位模型。最后,将数据集代入到优化后的定位模型中实现故障定位。结果表明,该方法的定位模型拟合程度达到99.4%,具有较高的定位精度和较好的鲁棒性,所提方法对噪声和过渡电阻的耐受性能较高,定位误差在500 m以内。 展开更多
关键词 柔性直流输电线路 变分模态分解 白鲸算法 核极限学习机 故障定位
暂未订购 下载PDF
基于MWMOTE和SSA-KELM的电力系统静态电压稳定评估 认领 引用 被引量：1
17
作者 刘颂凯 曹俊 +4 位作者 苏攀 高坤 吴宇恒 万明 艾迪 《电力科学与技术学报》 CAS CSCD 北大核心 2026年第1期13-22,共10页
基于数据驱动的电力系统静态电压稳定评估方法通常存在初始数据样本类别不平衡问题,导致数据驱动评估模型的性能受到很大的影响。为此,提出一种基于带多数类权重的少数类过采样技术(majority weighted minority oversampling technique,... 基于数据驱动的电力系统静态电压稳定评估方法通常存在初始数据样本类别不平衡问题,导致数据驱动评估模型的性能受到很大的影响。为此,提出一种基于带多数类权重的少数类过采样技术(majority weighted minority oversampling technique,MWMOTE)和麻雀搜索算法优化核极限学习机(sparrow search algorithm-kernel extreme learning machine,SSA-KELM)的电力系统静态电压稳定评估方法。首先,利用MWMOTE解决样本类别不平衡问题,增加样本多样性;然后,使用SSA优化KELM模型参数,构建基于SSA-KELM的电力系统静态电压稳定评估模型;最后,在新英格兰10机39节点系统上进行验证。测试结果表明,所提方法不仅能够有效应对样本类别不平衡问题,还具有良好的评估准确率和泛化能力。 展开更多
关键词 样本类别不平衡 静态电压稳定评估 带多数类权重的少数类过采样技术 麻雀搜索算法 核极限学习机
暂未订购 下载PDF
基于多源信号融合与BA−SMO的矿山带式输送机故障智能诊断研究 认领 引用 被引量：1
18
作者 李忠飞 刘鹏飞 +4 位作者 孙艳辉 王闯 谭胜虎 马双 张云鹤 《工矿自动化》 CSCD 北大核心 2026年第2期81-90,共10页
目前矿山带式输送机故障诊断研究主要集中在单一信号检测、传统算法建模、多特征融合3个方向。基于振动、电流等单一信号的诊断方法易出现特征提取偏差、诊断结果可靠性不足等问题;部分优化算法存在参数寻优效率低的问题,且对多故障类... 目前矿山带式输送机故障诊断研究主要集中在单一信号检测、传统算法建模、多特征融合3个方向。基于振动、电流等单一信号的诊断方法易出现特征提取偏差、诊断结果可靠性不足等问题;部分优化算法存在参数寻优效率低的问题,且对多故障类型的适配性较差;多特征融合研究缺乏针对性,无法实现多维度信号的互补验证。针对上述问题,提出了一种基于多源信号融合与蝙蝠算法(BA)优化序列最小优化(SMO)算法参数(BA−SMO)的矿山带式输送机故障智能诊断方法。构建了振动−温度−烟雾多源信号协同采集系机制,采用线性趋势去除法与改进卡尔曼滤波完成信号降噪预处理;提出了引入自适应惩罚因子与冗余分量剔除机制的改进变分模态分解(VMD)算法,结合多尺度样本熵实现故障特征的精准量化提取;基于提取的多维度特征向量,构建BA−SMO,通过BA的全局寻优能力优化SMO的核心参数,提升模型的分类精度与环境适应性。实验结果表明:①改进VMD算法的信噪比达27 dB,均方根误差(RMSE)及平均绝对误差(MAE)稳定在0.08以下,在信号分解精度、效率及故障特征频率匹配度上均有显著优势,能够精准分离矿山带式输送机多类型故障的特征频率。②BA−SMO对各类故障的识别准确率较高,轴承内圈故障的识别准确率接近100%,托辊打滑故障的识别准确率在90%以上。③BA−SMO在低、中、高干扰工况下的平均识别准确率依次为99.2%,97.6%,95.3%,漏判率均低于5%,平均识别耗时仅32.6 ms。现场应用结果表明:在为期3个月的现场应用中,所提方法成功识别轴承内圈点蚀、托辊打滑、滚动体磨损等各类故障,诊断准确率为97.8%,较传统人工巡检方法提升25.3%,有效降低了故障漏判率与误判率。 展开更多
关键词 带式输送机 故障诊断 多源信号融合 蝙蝠算法 优化序列最小优化算法 混合核函数 BA−SMO
暂未订购 下载PDF
基于ISWO-KELM模型的煤与瓦斯突出预测 认领 引用 被引量：1
19
作者 阎馨 何海雄 屠乃威 《控制工程》 CSCD 北大核心 2026年第3期454-463,共10页
为了提高煤与瓦斯突出预测的准确性,提出一种采用改进的蜘蛛蜂优化(improved spider wasp optimizer, ISWO)算法优化核极限学习机(kernel extreme learning machine, KELM)的煤与瓦斯突出的预测方法。首先,采用多策略融合的方法改进蜘... 为了提高煤与瓦斯突出预测的准确性,提出一种采用改进的蜘蛛蜂优化(improved spider wasp optimizer, ISWO)算法优化核极限学习机(kernel extreme learning machine, KELM)的煤与瓦斯突出的预测方法。首先,采用多策略融合的方法改进蜘蛛蜂优化算法,并用仿真实验验证算法性能,结果表明,改进后算法的收敛速度加快;然后,采用ISWO算法对KELM的参数进行优化整定;最后,采用仿真实验验证了ISWOKELM模型的预测能力,实验结果表明,相比于其他模型,优化后模型的预测准确度更高、泛化能力更强。 展开更多
关键词 煤与瓦斯突出 多策略融合 改进的蜘蛛蜂优化算法 核极限学习机
暂未订购 下载PDF
基于18种核函数映射的孪生回归支持向量机月径流预测 认领 引用 被引量：1
20
作者 周正道 崔东文 《中国农村水利水电》 北大核心 2026年第4期107-115,共9页
核函数及核函数参数的合理选取对于提升孪生回归支持向量机(TWSVR)性能具有重要意义。为提高月径流时间序列预测精度,对比验证不同核函数映射的TWSVR在月径流预测中的效果,基于小波包变换(WPT)、线性核函数等18种核函数、壮丽细尾鹩莺... 核函数及核函数参数的合理选取对于提升孪生回归支持向量机(TWSVR)性能具有重要意义。为提高月径流时间序列预测精度,对比验证不同核函数映射的TWSVR在月径流预测中的效果,基于小波包变换(WPT)、线性核函数等18种核函数、壮丽细尾鹩莺优化算法(SFOA)和TWSVR,提出18种核函数映射的WPT-SFOA-TWSVR模型,并构建5种常见核函数映射的WPT-SFOA-回归支持向量机(SVR)模型作对比分析,通过云南省滴水、南洞、勐大、南康河水文站月径流预测实例对23种模型进行验证。首先利用WPT对实例月径流时序数据进行分解处理,划分训练集和验证集;然后利用SFOA优化不同核函数映射的TWSVR/SVR超参数;最后利用最优超参数建立不同核函数映射的WPT-SFOA-TWSVR/SVR模型对4个实例月径流各分量进行训练、预测和加和重构。结果表明:①基于线性核函数、高斯核函数、多项式核函数、小波核函数、Sigmoid核函数、神经核函数映射的WPT-SFOA-TWSVR模型预测误差最小、性能最好;基于ANOVA核函数、Bessel核函数、对数核函数、多二次核函数、幂次核函数映射的WPT-SFOATWSVR模型次之;基于T-Student核函数、柯西核函数、有理二次方核函数映射的WPT-SFOA-TWSVR模型预测误差相对较大;基于拉普拉斯核函数、傅里叶核函数、卡方核函数、球形核函数映射的WPT-SFOA-TWSVR模型预测误差最大。②在相同WPT分解和SFOA优化情形下,TWSVR模型性能明显优于SVR。③利用SFOA优化TWSVR超参数,可以显著提升模型性能和计算效率。④不同核函数映射的WPT-SFOA-TWSVR模型具有较好的普适性,为TWSVR核函数的选取和优化应用提供参考和借鉴。 展开更多
关键词 月径流预测 小波包变换 壮丽细尾鹩莺优化算法 核函数 孪生回归支持向量 超参数优化
暂未订购 下载PDF
已选0条
引用分析
参考文献
引证文献
 统计分析
检索结果
已选文献
上一页 1 2 … 65 下一页 到第 页
在线咨询 使用帮助 返回顶部 意见反馈