期刊文献+
共找到975篇文章
< 1 2 49 >
每页显示 20 50 100
A prediction model for high-geothermal rockburst intensity using a genetic projection pursuit algorithm 认领 引用
1
作者 Meiben Gao Tianbin Li +4 位作者 Shixin Ji Shiming Bai Yan Zhang Zhihao He Liang Zhang 《Journal of Rock Mechanics and Geotechnical Engineering》 SCIE CSCD 2025年第12期7612-7627,共16页
High-temperature rockbursts pose a critical challenge in deep underground engineering and resource exploitation.Consequently,predicting high-geothermal rockbursts has become a key scientific objective.In this paper,a ... High-temperature rockbursts pose a critical challenge in deep underground engineering and resource exploitation.Consequently,predicting high-geothermal rockbursts has become a key scientific objective.In this paper,a genetic projection pursuit algorithm(GPPA)is proposed for the prediction of high-geothermal rockbursts by introducing the coefficient K,and utilizing multiple empirical criteria(Wet index,σc/σt,σθ/σc,andσ1/σc).Four empirical criteria were statistically analyzed for 147 sets of rockburst cases,yielding accuracies of 40%,39%,46%and 29%,respectively.After the implantation of optimal segmentation,there was an enhancement in accuracy by 12%,9%,6%,and 19%,respectively.Theσθ/σc criterion exhibited superior performance,with a baseline accuracy of 46%.The GPPA model was tested and validated using four characteristic parameters(Wet index,σc/σt,σθ/σc,andσ1/σc)as inputs,revealing that the error ranged between 0.07 and 0.41.Successful validation was performed in the Sangzhuling Tunnel(four slight rockbursts)and Qirehataer Diversion Tunnel(one moderate rockburst),which matched field observations.Consequently,the proposed model offers guidance for predicting high-geothermal rockburst hazards. 展开更多
关键词 Rockburst criterion Thermal impacts Genetic projection pursuit algorithm(GPPA) Sangzhuling tunnel Qirehataer diversion tunnel
暂未订购 下载PDF
融合位姿调整与Pure Pursuit算法的清扫机路径跟踪方法 认领 引用
2
作者 王保民 张铭宇 《中国惯性技术学报》 EI CSCD 北大核心 2026年第6期627-636,共10页
为了提高清扫机路径跟踪精度,提升其在狭窄区域的脱困能力,提出一种融合了位姿调整与Pure Pursuit算法的清扫机路径跟踪方法。该方法使用全局规划器将全局导航路径分裂成多个路径点,根据清扫机参数和预设速度确定目标距离。通过局部规... 为了提高清扫机路径跟踪精度,提升其在狭窄区域的脱困能力,提出一种融合了位姿调整与Pure Pursuit算法的清扫机路径跟踪方法。该方法使用全局规划器将全局导航路径分裂成多个路径点,根据清扫机参数和预设速度确定目标距离。通过局部规划器来获得路径点与清扫机间的位置数据,再将数据中的实际跟踪距离与清扫机偏航角信息发送到清扫机底盘,使用底盘处理器的偏航角调整算法修正清扫机位姿,使得清扫机可以更加准确的跟踪全局规划路径的各个目标点。构建狭窄仿真环境与室内实测场景,将所提算法与Pure Pursuit、DWA、TEB算法进行多组对比实验。仿真结果显示,改进算法相比原算法跟踪误差范围缩小8.3%、跟踪点数目减少19.2%;相比TEB算法导航时间节省32%;相比DWA算法全局路径重规划波动幅度降低一个等级。室内实测证明,改进算法相对TEB、DWA算法在狭窄区域脱困成功率更高。 展开更多
关键词 清扫机 Pure Pursuit算法 路径跟踪 位姿调整
暂未订购 下载PDF
基于稀疏度优化的SA-OMP的谐波和间谐波检测方法 认领 引用
3
作者 王漫舒 智泽英 高云广 《现代电子技术》 北大核心 2026年第7期139-144,共6页
针对传统匹配追踪类算法去噪中存在的问题,文中提出一种结合模拟退火(SA)算法和正交匹配追踪(OMP)算法对稀疏度k优化的谐波和间谐波信号检测方法。在OMP算法中引入SA来优化稀疏度搜索过程,通过SA的随机搜索和退火机制,动态搜索最优稀疏... 针对传统匹配追踪类算法去噪中存在的问题,文中提出一种结合模拟退火(SA)算法和正交匹配追踪(OMP)算法对稀疏度k优化的谐波和间谐波信号检测方法。在OMP算法中引入SA来优化稀疏度搜索过程,通过SA的随机搜索和退火机制,动态搜索最优稀疏度,使信号在特定稀疏变换基下的稀疏表示达到重构误差和稀疏性的平衡,避免了固定k值导致的过拟合(保留过多噪声)或欠拟合(丢失信号关键成分)问题。仿真结果表明:所提算法能够在噪声干扰情况下准确检测出各次谐波和间谐波分量,幅值和相位的最大检测误差分别为0.8%和0.0214 rad。SA-OMP重构的信号与原始信号吻合度很高,不仅在信噪比方面比传统OMP算法有大幅提高,MSE和相对误差也都有所提高,即使在信噪比低至10 dB的情况下,MSE和相对误差也能分别达到0.041和0.18,其去噪效果明显,为谐波和间谐波检测提供了一种有效方法。 展开更多
关键词 谐波 间谐波 信噪比 压缩感知 OMP算法 SA算法 SA-OMP算法
暂未订购 下载PDF
面向去蜂窝网络的基于列正交约束的OMP混合预编码算法 认领 引用
4
作者 张思涵 王安定 《电信科学》 北大核心 2026年第2期59-74,共16页
针对工作在毫米波频段下的去蜂窝大规模多输入多输出(cell-free massive multiple-input multipleoutput,CF-mMIMO)系统中混合预编码设计面临的链路开销大与数值不稳定等问题,提出了一种适配分布式架构的基于列正交约束的正交匹配追踪(o... 针对工作在毫米波频段下的去蜂窝大规模多输入多输出(cell-free massive multiple-input multipleoutput,CF-mMIMO)系统中混合预编码设计面临的链路开销大与数值不稳定等问题,提出了一种适配分布式架构的基于列正交约束的正交匹配追踪(orthogonal matching pursuit,OMP)算法。在模拟预编码阶段,采用基于旋转不变性技术的信号参数最小二乘估计(least squares estimation of signal parameters via rotational invariance technique,LS-ESPRIT)算法,基于接收信号直接估计信号到达角,并重构波束码本,有效压缩了反馈开销;在数字预编码阶段,引入列正交约束并推导了最优因子,重构了优化目标函数,规避了病态矩阵求逆问题,提升了预编码矩阵的数值稳定性与匹配精度。仿真结果表明,该算法在不同接入点分布结构与系统参数设置下均能保持稳定且明显的频谱效率性能提升,验证了其在CF-mMIMO系统中的鲁棒性与优越性。 展开更多
关键词 去蜂窝大规模多输入多输出 毫米波 OMP算法 频谱效率 混合预编码
暂未订购 下载PDF
改进OMP算法下多摄像机慢速动小目标增强检测方法 认领 引用 被引量:1
5
作者 马海林 《计算机测量与控制》 2026年第3期41-49,共9页
针对案件监控视频中慢速运动小目标因长时间曝光或摄像机抖动产生的运动模糊、特征丢失或形变,导致检测精度降低的问题进行了研究;采用了融合高斯、中值滤波与Retinex算法的降噪增强技术,为小目标特征提取提供高质量图像;利用Faster R-... 针对案件监控视频中慢速运动小目标因长时间曝光或摄像机抖动产生的运动模糊、特征丢失或形变,导致检测精度降低的问题进行了研究;采用了融合高斯、中值滤波与Retinex算法的降噪增强技术,为小目标特征提取提供高质量图像;利用Faster R-CNN进行特征提取,通过卷积和池化操作捕捉局部特征,RPN网络生成候选区域,并提出新置信度公式精准确定区域,再通过RoI Pooling获取特征向量;应用改进OMP算法增强小目标特征,引入局部相关性和能量分布并结合非线性变换,提升增强效果与稳定性;在多摄像机小目标关联与信息融合环节,基于特征向量相似度关联小目标,采用加权融合处理信息,形成完整运动轨迹;基于卡尔曼滤波和支持向量机实现慢速动小目标跟踪与检测结果输出,通过初始化状态估计与协方差矩阵,经状态预测、观测更新持续跟踪,再输入SVM判定类别,同时采用可视化技术标注显示结果,包括绘制外接矩形框、标注位置和类别信息、显示视频帧等;经实验测试,该方法应用后视频帧图像对比度最大值达到1.9,小目标特征重构误差最小值达到0.4%,实现了较高的检测精度,满足了准确、清晰地提供慢速动小目标信息的应用需求。 展开更多
关键词 摄像机监控视频 目标增强检测 改进OMP算法 Faster R-CNN 慢速动小目标
暂未订购 下载PDF
基于改进OMP和K-SVD的汽车轴承故障诊断技术研究 认领 引用
6
作者 韩世勋 张丽丽 +1 位作者 金璐 杨晓阳 《机械设计与制造工程》 2026年第7期85-90,共6页
为解决汽车轴承早期微弱故障特征频率提取困难的问题,本文提出一种联合改进正交匹配追踪和改进K-SVD的故障诊断方法。该方法首先利用改进正交匹配追踪算法剔除信号中的谐波和调制成分,并通过时域平均构造初始瞬态字典;然后在此基础上对K... 为解决汽车轴承早期微弱故障特征频率提取困难的问题,本文提出一种联合改进正交匹配追踪和改进K-SVD的故障诊断方法。该方法首先利用改进正交匹配追踪算法剔除信号中的谐波和调制成分,并通过时域平均构造初始瞬态字典;然后在此基础上对K-SVD算法进行改进,并采用改进后算法提取残差信号中的冲击特征;最后通过包络谱分析获取故障频率。仿真和汽车轴承试验结果表明,本文提出的方法能够准确识别故障频率及其高倍频,明显优于对比方法。 展开更多
关键词 瞬态特征提取 正交匹配追踪算法 K-SVD 汽车轴承 故障诊断
暂未订购 下载PDF
基于LCD和OMP稀疏分解的电机轴承故障信号特征提取 认领 引用
7
作者 薛梦琪 马静云 《拖拉机与农用运输车》 2026年第4期23-25,78,共3页
为了解决局部特征尺度分解(LCD)在特征提取过程中可能出现的伪影问题,设计基于LCD和OMP稀疏分解的电机轴承故障信号特征提取方法,并成功应用于电机轴承故障诊断上。对故障信号LCD分解后的内在尺度分量(ISC)实施筛选并重构,采用改进正交... 为了解决局部特征尺度分解(LCD)在特征提取过程中可能出现的伪影问题,设计基于LCD和OMP稀疏分解的电机轴承故障信号特征提取方法,并成功应用于电机轴承故障诊断上。对故障信号LCD分解后的内在尺度分量(ISC)实施筛选并重构,采用改进正交匹配追踪算法(OMP)对重构信号实施稀疏分解并获取故障特征。仿真结果表明:信号重构后时域内冲击信号显著降低,高频干扰得到有效控制,形成明显故障特征频率,获得显著故障特征频率,所提方法对于轴承故障特征提取方面的有效性。 展开更多
关键词 电机轴承 局部特征尺度分解 正交匹配追踪算法 故障诊断
暂未订购 下载PDF
Application of Projection Pursuit Evaluation Model Based on Real-Coded Accelerating Genetic Algorithm in Evaluating Wetland Soil Quality Variations in the Sanjiang Plain, China 认领 引用 被引量:34
8
作者 FUQIANG XIEYONGGANG WEIZIMIN 《Pedosphere》 SCIE CAS 2003年第3期249-256,共8页
A new technique of dimension reduction named projection pursuit is applied to model and evaluatewetland soil quality variations in the Sanjiang Plain, Helongjiang Province, China. By adopting the im-proved real-coded ... A new technique of dimension reduction named projection pursuit is applied to model and evaluatewetland soil quality variations in the Sanjiang Plain, Helongjiang Province, China. By adopting the im-proved real-coded accelerating genetic algorithm (RAGA), the projection direction is optimized and multi-dimensional indexes are converted into low-dimensional space. Classification of wetland soils and evaluationof wetland soil quality variations are realized by pursuing optimum projection direction and projection func-tion value. Therefore, by adopting this new method, any possible human interference can be avoided andsound results can be achieved in researching quality changes and classification of wetland soils. 展开更多
关键词 evaluation projection pursuit evaluation model real-coded acceleratinggenetic algorithm soil quality variations
暂未订购 下载PDF
Algorithm for source recovery in underdetermined blind source separation based on plane pursuit 认领 引用 被引量:2
9
作者 FU Weihong WEI Juan +1 位作者 LIU Naian CHEN Jiehu 《Journal of Systems Engineering and Electronics》 SCIE CSCD 2018年第2期223-228,共6页
In order to achieve accurate recovery signals under the underdetermined circumstance in a comparatively short time,an algorithm based on plane pursuit(PP) is proposed. The proposed algorithm selects the atoms accordin... In order to achieve accurate recovery signals under the underdetermined circumstance in a comparatively short time,an algorithm based on plane pursuit(PP) is proposed. The proposed algorithm selects the atoms according to the correlation between received signals and hyper planes, which are composed by column vectors of the mixing matrix, and uses these atoms to recover source signals. Simulation results demonstrate that the PP algorithm has low complexity and higher accuracy as compared with basic pursuit(BP), orthogonal matching pursuit(OMP), and adaptive sparsity matching pursuit(ASMP) algorithms. 展开更多
关键词 underdetermined blind source separation(UBSS) source recovery greedy algorithm plane pursuit
暂未订购 下载PDF
Projection pursuit model of vehicle emission on air pollution at intersections based on the improved bat algorithm 认领 引用 被引量:1
10
作者 Hu Qizhou Deng Wei +1 位作者 Tan Minjia Bian Lishuang 《Journal of Southeast University(English Edition)》 EI CAS 2019年第3期389-392,共4页
The projection pursuit model is used to study the assessment of air pollution caused by vehicle emissions at intersections. Based on the analysis of the characteristics and regularities of vehicle emissions at interse... The projection pursuit model is used to study the assessment of air pollution caused by vehicle emissions at intersections. Based on the analysis of the characteristics and regularities of vehicle emissions at intersections, a vehicle emission model based on projection pursuit is established, and the bat algorithm is used to solve the optimization function. The research results show that the projection pursuit model can not only measure the air pollution of vehicle emissions at intersections, but also effectively evaluate the level of vehicle exhaust emissions at intersections. Taking the air pollution caused by vehicle emissions at intersections as the research object and considering the influence factors of vehicle emissions on air pollution comprehensively, the evaluation index system of vehicle emissions at intersections on air pollution is constructed. Based on large data analysis, a prediction model of air pollution caused by vehicle emissions at intersections is constructed, and an improved bat algorithm is used to realize the assessment process. The application results show that the prediction model of vehicle emissions at intersections can define the degree of air pollution caused by vehicle emissions, and it has good guiding significance and practical value for solving the problem of air pollution caused by vehicle emissions. 展开更多
关键词 intersection vehicle emission pollutants projection pursuit bat algorithm
暂未订购 下载PDF
Fast M-fold matching pursuit algorithm for image approximation 认领 引用 被引量:1
11
作者 Gan Tao He Yanmin Zhu Weile 《Journal of Systems Engineering and Electronics》 SCIE EI 2009年第4期883-888,共6页
A simple and effective greedy algorithm for image approximation is proposed.Based on the matching pursuit approach,it is characterized by a reduced computational complexity benefiting from two major modifications.Firs... A simple and effective greedy algorithm for image approximation is proposed.Based on the matching pursuit approach,it is characterized by a reduced computational complexity benefiting from two major modifications.First,it iteratively finds an approximation by selecting M atoms instead of one at a time.Second,the inner product computations are confined within only a fraction of dictionary atoms at each iteration.The modifications are implemented very efficiently due to the spatial incoherence of the dictionary.Experimental results show that compared with full search matching pursuit,the proposed algorithm achieves a speed-up gain of 14.4-36.7 times while maintaining the approximation quality. 展开更多
关键词 greedy algorithm image approximation matching pursuit
暂未订购 下载PDF
Dynamic multi-user detection scheme based on CVA-SSAOMP algorithm in uplink grant-free NOMA 认领 引用
12
作者 Xu Lei Tao Shangjin +3 位作者 Bai Shichao Zhang Jian Fang Hongyu Li Xiaohui 《High Technology Letters》 EI CAS 2021年第1期10-16,共7页
In the uplink grant-free non-orthogonal multiple access(NOMA)scenario,since the active user at the sender has a structured sparsity transmission characteristic,the compressive sensing recovery algorithm is initially a... In the uplink grant-free non-orthogonal multiple access(NOMA)scenario,since the active user at the sender has a structured sparsity transmission characteristic,the compressive sensing recovery algorithm is initially applied to the joint detection of the active user and the transmitted data.However,the existing compressed sensing recovery algorithms with unknown sparsity often require noise power or signal-to-noise ratio(SNR)as the priori conditions,which greatly reduces the algorithm adaptability in multi-user detection.Therefore,an algorithm based on cross validation aided structured sparsity adaptive orthogonal matching pursuit(CVA-SSAOMP)is proposed to realize multi-user detection in dynamic change communication scenario of channel state information(CSI).The proposed algorithm transforms the structured sparsity model into a block sparse model,and without the priori conditions above,the cross validation method in the field of statistics and machine learning is used to adaptively estimate the sparsity of active user through the residual update of cross validation.The simulation results show that,compared with the traditional orthogonal matching pursuit(OMP)algorithm,subspace pursuit(SP)algorithm and cross validation aided block sparsity adaptive subspace pursuit(CVA-BSASP)algorithm,the proposed algorithm can effectively improve the accurate estimation of the sparsity of active user and the performance of system bit error ratio(BER),and has the advantage of low-complexity. 展开更多
关键词 non-orthogonal multiple access(NOMA) multi-user detection cross validation structured sparsity(SP) orthogonal matching pursuit(OMP)
暂未订购 下载PDF
Coherence-based performance analysis of the generalized orthogonal matching pursuit algorithm 认领 引用
13
作者 赵娟 毕诗合 +2 位作者 白霞 唐恒滢 王豪 《Journal of Beijing Institute of Technology》 EI CAS 2015年第3期369-374,共6页
The performance guarantees of generalized orthogonal matching pursuit( gOMP) are considered in the framework of mutual coherence. The gOMP algorithmis an extension of the well-known OMP greed algorithmfor compressed... The performance guarantees of generalized orthogonal matching pursuit( gOMP) are considered in the framework of mutual coherence. The gOMP algorithmis an extension of the well-known OMP greed algorithmfor compressed sensing. It identifies multiple N indices per iteration to reconstruct sparse signals.The gOMP with N≥2 can perfectly reconstruct any K-sparse signals frommeasurement y = Φx if K 〈1/N(1/μ-1) +1,where μ is coherence parameter of measurement matrix Φ. Furthermore,the performance of the gOMP in the case of y = Φx + e with bounded noise ‖e‖2≤ε is analyzed and the sufficient condition ensuring identification of correct indices of sparse signals via the gOMP is derived,i. e.,K 〈1/N(1/μ-1)+1-(2ε/Nμxmin) ,where x min denotes the minimummagnitude of the nonzero elements of x. Similarly,the sufficient condition in the case of G aussian noise is also given. 展开更多
关键词 compressed sensing sparse signal reconstruction orthogonal matching pursuitOMP support recovery coherence
暂未订购 下载PDF
基于K-PSO和StOMP的往复压缩机激振信号盲源分离 认领 引用 被引量:4
14
作者 王金东 马智超 +2 位作者 赵海洋 李彦阳 张宇 《机床与液压》 北大核心 2025年第3期228-234,共7页
在当前信号的盲源分离中,传统“两步法”易陷入局部最优解,并且其准确率会随采集信号数的增加或稀疏性的降低而大幅下降。针对上述问题,提出一种结合K均值-粒子群(K-PSO)和分段正交匹配追踪(StOMP)的稀疏分量分析方法。对采集信号执行K... 在当前信号的盲源分离中,传统“两步法”易陷入局部最优解,并且其准确率会随采集信号数的增加或稀疏性的降低而大幅下降。针对上述问题,提出一种结合K均值-粒子群(K-PSO)和分段正交匹配追踪(StOMP)的稀疏分量分析方法。对采集信号执行K均值聚类算法,将产生的结果反馈至PSO聚类中估计混合矩阵。在获得混合矩阵后,将其源信号矩阵转化成列数为1的向量,再通过分段正交匹配追踪算法重构源信号。将实测的往复压缩机正常信号和3种单一故障信号混合成2种复合故障信号,并对复合故障信号进行试验验证。结果表明:在计算时间方面,相较模糊C均值聚类(0.335 s)和K均值聚类(0.299 s),尽管K-PSO聚类方法牺牲了一部分效率(1.561 s),但在总体角度偏差和归一化均方根误差方面表现更优,具有更好的估计精度;相较最短路径法(0.123 s),StOMP算法同样牺牲效率(2.031 s),却获得更佳的相关系数和均方根误差,表现更好的分离重构能力。这说明,该方法在盲源分离中具有可行性和实际应用价值。 展开更多
关键词 往复压缩机 欠定盲源分离 K均值聚类 粒子群算法 分段正交匹配追踪
暂未订购 下载PDF
Research on the Signal Reconstruction of the Phased Array Structural Health Monitoring Based Using the Basis Pursuit Algorithm 认领 引用 被引量:3
15
作者 Yajie Sun Yanqing Yuan +3 位作者 Qi Wang Lihua Wang Enlu Li Li Qiao 《Computers, Materials & Continua》 SCIE EI 2019年第2期409-420,共12页
The signal processing problem has become increasingly complex and demand high acquisition system,this paper proposes a new method to reconstruct the structure phased array structural health monitoring signal.The metho... The signal processing problem has become increasingly complex and demand high acquisition system,this paper proposes a new method to reconstruct the structure phased array structural health monitoring signal.The method is derived from the compressive sensing theory and the signal is reconstructed by using the basis pursuit algorithm to process the ultrasonic phased array signals.According to the principles of the compressive sensing and signal processing method,non-sparse ultrasonic signals are converted to sparse signals by using sparse transform.The sparse coefficients are obtained by sparse decomposition of the original signal,and then the observation matrix is constructed according to the corresponding sparse coefficients.Finally,the original signal is reconstructed by using basis pursuit algorithm,and error analysis is carried on.Experimental research analysis shows that the signal reconstruction method can reduce the signal complexity and required the space efficiently. 展开更多
关键词 Basis pursuit algorithm compressive sensing phased array signal reconstruction
暂未订购 下载PDF
The application of projection pursuit classification in the process of strategy selection and evaluation based on the real coded accelerating genetic algorithm 认领 引用 被引量:1
16
作者 JIANG Fa-zhu YANG Xiu-feng 《Chinese Business Review》 2008年第1期40-44,64,共5页
During the process of enterprises' strategy evaluation and selection, there are many evaluating indicators, and among them there are some potential correlations and conflicts. Thus it poses the problems to the decisi... During the process of enterprises' strategy evaluation and selection, there are many evaluating indicators, and among them there are some potential correlations and conflicts. Thus it poses the problems to the decision-makers how to conduct correct evaluation on a business and how to make strategy adjustment and selection according to the evaluation. Based on the qualitative and quantitative method, the paper introduces the Projection Pursuit Classification (PPC) model based on the Real-coded Accelerating Genetic Algorithm (RAGA) into the process of enterprises' strategy evaluation and selection. The characteristic of PPC model is that it ultimately overcomes the influence of the proportion of subjectivity and avoids precocious convergence, thus providing a new objective method for strategy evaluation and selection by pursuing the most objective strategy evaluation to make the relatively sensible strategy portfolio and action. 展开更多
关键词 projection pursuit strategy evaluation accelerating genetic algorithm
暂未订购 下载PDF
基于改进NARXNN神经网络的动车组车轮磨耗预测 认领 引用 被引量:3
17
作者 张霞 邓银强 +2 位作者 杨岳 段华东 陈峰 《铁道科学与工程学报》 EI CAS CSCD 北大核心 2026年第2期833-845,共13页
预测车轮的磨耗状态对合理制定维护计划、保障动车组列车安全运行具有重要意义。动车组车轮磨耗属复杂非线性问题,引入机器学习和大数据技术对准确预测车轮磨耗具有显著作用。为预测动车组车轮磨耗,提出了一种改进的带外源输入的非线性... 预测车轮的磨耗状态对合理制定维护计划、保障动车组列车安全运行具有重要意义。动车组车轮磨耗属复杂非线性问题,引入机器学习和大数据技术对准确预测车轮磨耗具有显著作用。为预测动车组车轮磨耗,提出了一种改进的带外源输入的非线性自回归神经网络(nonlinear auto-regressive model with eXogenous inputs neural network,NARXNN)模型。首先,依据采集的动车组车轮磨耗3年连续实测数据,运用快速查找密度峰值聚类算法剔除异常数据,并利用二阶拉格朗日多项式插值处理缺失值,进行数据集预处理。然后,通过相空间重构将一维时间序列车轮直径测量数据扩展至多维,挖掘车轮磨耗参数的演变规律,采用主成分分析法提取影响动车组车轮直径参数指标变化的主要成分,构建了车轮磨耗预测模型的数据集样本。在此基础上,设计了一种带外源输入的非线性自回归神经网络NARXNN模型,采用列文伯格−马夸尔特算法(levenberg-marquardt,LM)优化NARXNN模型的权重和阈值,引入正交匹配追踪算法(orthogonal matching pursuit,OMP),以贪婪迭代的方式优化网络模型结构,在保证性能可靠性的同时删除冗余神经元,最终实现预测网络结构的精简。实验结果表明,LM-OMP算法优化的NARXNN神经网络模型结构简单、性能优越,能够快速稳定收敛。建立了未来2至6个月的车轮轮径磨耗预测模型,与其他经典预测模型对比结果表明,运用LM-OMP算法优化的NARXNN神经网络模型在动车组车轮磨耗预测方面具有更高的准确率和稳定性。运用该方法能够较精准地预测车轮磨耗的发展规律,可为动车组车轮的精准维修和科学使用提供参考。 展开更多
关键词 动车组车轮 车轮磨耗预测 NARXNN神经网络 LM-OMP算法 相空间重构
暂未订购 下载PDF
基于多尺度的湖南省耕地利用系统韧性及其障碍因子分析 认领 引用 被引量:1
18
作者 胡贤辉 岳冬阳 +2 位作者 文高辉 周浩 周翼 《农业工程学报》 EI CAS CSCD 北大核心 2026年第5期371-382,共12页
为保障中国粮食安全和推动农业绿色转型,科学分析耕地利用系统韧性及其障碍因子时空异质性对抵抗耕地生态风险冲击和稳固农业经济发展具有重要作用。该研究基于“压力—状态—响应”框架构建湖南省耕地利用系统韧性水平测度指标体系,借... 为保障中国粮食安全和推动农业绿色转型,科学分析耕地利用系统韧性及其障碍因子时空异质性对抵抗耕地生态风险冲击和稳固农业经济发展具有重要作用。该研究基于“压力—状态—响应”框架构建湖南省耕地利用系统韧性水平测度指标体系,借助基于量子遗传算法的投影寻踪模型、核密度估计及障碍度模型等,对湖南省耕地利用系统韧性展开深入剖析。结果表明:1)湖南省耕地利用系统韧性水平整体呈波动增长特征,不同农业区走势各异。韧性均值由2008年的1.86上升至2015年的2.18,2022年回落至2.06;湘中南丘岗节水农业区提升显著,湘中南和湘西农业区内部绝对差距加大,长株潭都市农业区两极分化加剧,洞庭湖平湖农业区有收敛趋势。2)湘西地区由于人为扰动弱与灾害响应治理高效,使得其成为高韧性区,湘中南丘岗节水农业区因耕地资源优越获得更多投入,韧性高值随之偏移,长株潭都市农业区耕地保护未受重视,系统抵抗干扰和冲突的能力偏差。3)从准则层看,全省障碍度大小表现为压力层>响应层>状态层,响应层障碍度在减小,状态层障碍度有增大趋势。具体到因子层面,降水距平值、自校准帕尔默干旱指数、人均耕地面积、单位耕地面积农业财政支出、农业受灾治理情况等为主要障碍因子。4)不同农业区障碍因子各异,关键障碍因子呈现空间异质性,并基于此提出“省—农业区—县”三级差异化的韧性提升策略。研究提出差异化耕地利用系统韧性提升策略,为湖南省“省—农业区—县”三级协同耕地保护提供科学参考。 展开更多
关键词 耕地利用系统韧性 量子遗传算法 投影寻踪模型 PSR模型 障碍因子 时空分异
暂未订购 下载PDF
基于加速遗传算法投影寻踪模型的耕地保护政策执行评估研究 认领 引用 被引量:1
19
作者 张晏维 卢新海 《中国生态农业学报(中英文)》 CAS CSCD 北大核心 2026年第3期621-636,共16页
耕地资源安全是维护社会稳定和国家粮食安全的重要保障。耕地保护政策在真正执行之前仅仅是含有价值观念的行动方案,其成效唯有通过实际执行才能得以显现。分析并量化耕地保护政策执行效应,可为完善耕地保护政策执行评估提供数据支撑和... 耕地资源安全是维护社会稳定和国家粮食安全的重要保障。耕地保护政策在真正执行之前仅仅是含有价值观念的行动方案,其成效唯有通过实际执行才能得以显现。分析并量化耕地保护政策执行效应,可为完善耕地保护政策执行评估提供数据支撑和决策支持,拓展土地政策执行评估方法的改进与创新。本文构建了耕地保护政策执行效应的评价指标体系,并运用加速遗传算法投影寻踪模型揭示了中国30个省(自治区、直辖市,未包括香港、澳门、台湾和西藏)耕地保护政策执行效应,同时借助探索性空间分析、空间趋势面分析以及时空跃迁技术等模型探索其时空变化规律。研究结果表明:1)耕地保护政策执行效应呈先下降后上升再下降趋势;2)耕地保护政策执行效应在东西和南北方向上分别呈现“东高西低”和“南高北低”的空间结构特征;3)耕地保护政策执行效应存在空间集聚性和异质性,且表现出路径依赖和空间锁定的特征;4)耕地保护政策执行效应制约因子为耕地生产功能、耕地社会保障功能和耕地督察功能。由此可见,耕地保护政策执行水平有待提升,且受各区域耕地本底条件与环境制约,需因地制宜制定治理策略。 展开更多
关键词 耕地保护 政策执行 效应评估 加速遗传算法投影寻踪模型
暂未订购 下载PDF
基于基追踪去噪的高精度地震反射率反演方法及应用 认领 引用
20
作者 李杰 陈兆明 +5 位作者 刘道理 刘灵 董国辉 刘徐敏 李坤娟 曾婷 《热带海洋学报》 CAS CSCD 北大核心 2026年第2期140-147,共8页
基于基追踪去噪的地震反射率反演通过应用l1范数正则化产生稀疏解,但由于正则化项的存在,基追踪去噪获得的解与真实解之间总是存在偏差。为了减小这种偏差,文章通过在基追踪去噪地震反射率反演中引入“残差回加”的策略,提高了解的准确... 基于基追踪去噪的地震反射率反演通过应用l1范数正则化产生稀疏解,但由于正则化项的存在,基追踪去噪获得的解与真实解之间总是存在偏差。为了减小这种偏差,文章通过在基追踪去噪地震反射率反演中引入“残差回加”的策略,提高了解的准确性。“残差回加”策略通过使用一个适中的权衡因子,迭代执行快速迭代软阈值算法(fast iterative soft thresholding algorithm,FISTA)来求解基追踪去噪的目标函数,而每次求解的残差将会不断加回至原始输入。与使用FISTA单次求解相比,结合“残差回加”策略的FISTA求解得到的解更接近真实解。本文将该方法应用到我国南海珠江口盆地珠一坳陷惠西南古近系的文昌组储层,通过高精度的波阻抗反演结果对钙质砂岩和滩坝砂岩进行了有效划分。 展开更多
关键词 反射率反演 基追踪去噪算法 偏差 波阻抗
暂未订购 下载PDF
上一页 1 2 49 下一页 到第
在线咨询 使用帮助 返回顶部 意见反馈