一种基于GA-BP-MC神经网络的高铁桥墩沉降预测模型     

冯绍权  花向红  陶武勇  宣伟  吴伟  续东 《测绘通报》2019,(7):50-53,82

提出一种基于马尔科夫链修正的遗传BP神经网络预测模型（GA-BP-MC），利用遗传算法的全局寻优能力初始化BP神经网络权值和阈值，初步建立GA-BP神经网络预测模型，结合马尔科夫链的无后效性修正模型预测值，形成高精度GA-BP-MC神经网络变形预测模型。结合高铁桥墩沉降数据，分别与BP神经网络、GA-BP神经网络预测模型进行对比，结果表明，该预测模型精度最高。  相似文献   

平原地区机载激光雷达数据的抽稀算法分析   总被引：1，自引：0，他引：1  

杨明军  苏春梅  康冰锋  张珣  曹殿才 《测绘通报》2019,(1):101-107

目前，机载激光雷达点云数据在测绘行业中的应用还存在较多的瓶颈。为了使机载激光雷达点云数据更好地服务等值线等数据的生产，发挥其高效和高精度的优势，本文归纳、总结了国内外现有的LiDAR点云数据抽稀算法，并通过对比分析现有LiDAR点云数据抽稀算法存在的优缺点，如系统抽稀、格网抽稀、TIN抽稀和坡度抽稀等算法，结合平原地区激光点云在实际生产中的应用，研究了更适合平原地区点云数据的抽稀方法，通过大量的数据测试和试生产。结果表明，该方法可以在应用项目精度约束下保证数据质量，减少了后期数据处理应用的难度，提升了后续成果数据的质量，提高了作业生产效率，对机载激光雷达点云数据在测绘行业中的应用推广具有重要的现实意义。  相似文献   

一种顾及道路影响的点要素注记配置遗传禁忌搜索算法   总被引：1，自引：0，他引：1  

李娟  朱勤东 《测绘通报》2019,(2):80-85

为使地图上点要素注记配置更美观易读，利用遗传算法的全局寻优能力和禁忌搜索算法的"爬山能力"，在考虑传统点要素注记配置约束条件的同时，考虑点要素与道路间的关系，提出了一种顾及道路要素影响的遗传禁忌搜索算法，并从解算精度、运行效率及稳健性3个方面对该算法进行评价。本文以福建省泉州市惠安县1：20万比例尺的乡村点状地形图数据进行试验，试验结果表明，与遗传算法、禁忌搜索算法和ArcGIS软件相比，该算法的算法精度和稳健性均有所提高，但是计算效率略低于禁忌算法，且点要素注记与点要素、道路要素的压盖量最少，与点要素、道路要素注记的交叉量最少。  相似文献   

运用人工鱼群算法的3D扫描碎片重建探究     

刘恩盛  程效军  黄玉花 《测绘通报》2019,(3):137-140

针对传统三维碎片拼接匹配过程中依赖单一特征及存在误差累积的问题，提出了一种运用鱼群算法的全局最优匹配方法。该方法先对碎片点云数据进行多特征提取，结合纹理、专家经验信息对混合在一起的多种类型碎片进行粗糙集分类，之后采用鱼群算法的最优解求得最佳匹配方案。实例验证所提全局匹配方法具有能力强、与初始位置无关及较强的稳健性等特点，为三维碎片的全局匹配提供了一种有效的解决方案。  相似文献   

高光谱图像波段选择的改进二进制布谷鸟算法     

宋广钦  杜正舜  贺智 《测绘通报》2019,(4):43-48

波段选择是高光谱遥感图像分类的重要前提，本文提出了一种用于高光谱遥感图像波段选择的改进二进制布谷鸟算法，通过使用混合二进制编码算法更新子代鸟巢和使用遗传算法交叉方式更新被发现鸟巢两个方面对二进制布谷鸟算法进行改进，找出在图像中起主要作用且相关性低的波段，实现对高光谱遥感图像降维。将本文算法运用于PaviaU数据集和AVIRIS数据集，并与二进制布谷鸟算法、二进制粒子群算法、最小冗余最大相关算法、Relief算法等进行对比分析。结果表明，改进二进制布谷鸟算法波段特征选择效率更高，且选取的波段更具代表性，能够较好地提高后续分类精度。  相似文献   

Development of detachable replaceable links for eccentrically braced frames     

Mehmet Bakır Bozkurt  Sina Kazemzadeh Azad  Cem Topkaya 《地震工程与结构动力学》2019,48(10):1134-1155

Eccentrically braced frames (EBFs) can be repaired after a major earthquake by replacing the links. The link replacement is not a straightforward process and is influenced by the type of the link and the amount of residual frame deformations. The past decade has witnessed the development of different types of replaceable links such as end-plated links, web connected links, bolted flange and web spliced links, and collector beam and brace spliced links. All of the developed replaceable link details, except the web connected links, are not suitable for link replacement under residual frame drift. In this paper, a detachable replaceable link detail which is based on splicing the link at its mid-length is proposed. The detail is well suited for installation under residual frame drifts. In addition, the weight and size of the members to be transported and erected are reduced significantly, thereby facilitating the replacement procedure. Performance of this proposed replaceable link is studied by conducting six nearly full scale EBF tests under quasi-static cyclic loading. The link length ratio, type of end-plated mid-splice connection, and the amount of residual drift are considered as test variables. The test results revealed that the inelastic rotation capacity of the detachable replaceable links exceeds the requirements of the AISC Seismic Provisions for Structural Steel Buildings. No failures are observed in the end-plated mid-splice connections demonstrating the potential of the proposed details. The detachable replaceable links are investigated by numerical analysis as well to further validate their applicability and to develop design recommendations.  相似文献   

Gully erosion spatial modelling: Role of machine learning algorithms in selection of the best controlling factors and modelling process     

《地学前缘(英文版)》2020,11(6):2207-2219

This investigation assessed the efficacy of 10 widely used machine learning algorithms (MLA) comprising the least absolute shrinkage and selection operator (LASSO), generalized linear model (GLM), stepwise generalized linear model (SGLM), elastic net (ENET), partial least square (PLS), ridge regression, support vector machine (SVM), classification and regression trees (CART), bagged CART, and random forest (RF) for gully erosion susceptibility mapping (GESM) in Iran. The location of 462 previously existing gully erosion sites were mapped through widespread field investigations, of which 70% (323) and 30% (139) of observations were arbitrarily divided for algorithm calibration and validation. Twelve controlling factors for gully erosion, namely, soil texture, annual mean rainfall, digital elevation model (DEM), drainage density, slope, lithology, topographic wetness index (TWI), distance from rivers, aspect, distance from roads, plan curvature, and profile curvature were ranked in terms of their importance using each MLA. The MLA were compared using a training dataset for gully erosion and statistical measures such as RMSE (root mean square error), MAE (mean absolute error), and R-squared. Based on the comparisons among MLA, the RF algorithm exhibited the minimum RMSE and MAE and the maximum value of R-squared, and was therefore selected as the best model. The variable importance evaluation using the RF model revealed that distance from rivers had the highest significance in influencing the occurrence of gully erosion whereas plan curvature had the least importance. According to the GESM generated using RF, most of the study area is predicted to have a low (53.72%) or moderate (29.65%) susceptibility to gully erosion, whereas only a small area is identified to have a high (12.56%) or very high (4.07%) susceptibility. The outcome generated by RF model is validated using the ROC (Receiver Operating Characteristics) curve approach, which returned an area under the curve (AUC) of 0.985, proving the excellent forecasting ability of the model. The GESM prepared using the RF algorithm can aid decision-makers in targeting remedial actions for minimizing the damage caused by gully erosion.  相似文献   

MEEMD-Elman神经网络的电离层TEC预报模型     

汤俊  高鑫 《大地测量与地球动力学》2020,40(4):395-399

利用IGS中心提供的不同纬度的电离层TEC值,建立基于改进的集总平均经验模态分解(MEEMD)算法和Elman回归神经网络(ERNN)模型相结合的电离层TEC预报模型。实验结果表明,在低、中、高不同纬度采用本文方法预报5 d电离层TEC的预测值的均方根误差最优可达到0.96 TECu,相对精度最优达到95.4%,精度较EMD-ERNN模型及单一ERNN模型有显著提高。  相似文献   

Dynamic responses of unsaturated half‐space soil to a moving harmonic rectangular load          下载免费PDF全文

Zheng Lu  Ran Fang  Hailin Yao  Cheng Dong  Shaohua Xian 《国际地质力学数值与分析法杂志》2018,42(9):1057-1077

The problem of the dynamic responses of a semi‐infinite unsaturated poroelastic medium subjected to a moving rectangular load is investigated analytical/numerically. The dynamic governing equations are obtained with consideration of the compressibility of solid grain and pore fluid, inertial coupling, and viscous drag as well as capillary pressure in the unsaturated soil, and they can be easily degraded to the complete Biot's theory. Using the Fourier transform, the general solution for the equations is derived in the transformed domain, and then a corresponding boundary value problem is formulated. By introducing fast Fourier transform algorithm, the unsaturated soil vertical displacements, effective stresses, and pore pressures induced by moving load are computed, and some of the calculated results are compared with those for the degenerated solution of saturated soils and confirmed. The influences of the saturation, the load speed, and excitation frequency on the response of the unsaturated half‐space soil are investigated. The numerical results reveal that the effects of these parameters on the dynamic response of the unsaturated soil are significant.  相似文献   

基于萤火虫和蝙蝠群智能算法的瑞雷波频散曲线反演   总被引：1，自引：0，他引：1       下载免费PDF全文

蔡伟  宋先海  袁士川  胡莹 《地球物理学报》2018,61(6):2409-2420

反演瑞雷波频散曲线能有效获取地层横波速度和厚度.但由于其高度的非线性、多参数、多极值等特点，传统的全局搜索方法易出现收敛速度慢、早熟收敛及搜索精度低的问题.鉴于此，本文提出并测试了基于萤火虫优化算法（FA）和带惯性权重的蝙蝠优化算法（WBA）的新的瑞雷波频散曲线反演策略.在瑞雷波频散曲线反演中，FA全局搜索能力强，但后期搜索精度低，而WBA局部搜索能力强，搜索精度高，但易出现早熟收敛.故本文将二者结合，提出了一种新的优化策略，称其为WFBA，即在反演前期使用FA，后期使用WBA，很好地解决了FA后期搜索精度低及WBA早熟收敛的问题.本文首先反演了三个典型理论模型的无噪声、含噪声的数据，验证了WFBA对瑞雷波数据反演的有效性与稳定性.然后将WFBA与WBA、FA单独反演以及不含惯性权重的FBA和粒子群优化算法（PSO）反演的结果进行了对比，说明了WFBA相对于WBA、FA、FBA和PSO具有更稳定、收敛速度更快、求解精度更高等优点.最后，反演了来自美国怀俄明地区的实测资料，检验了WFBA对瑞雷波数据反演的实用性.理论模型试算和实测资料分析表明，WFBA很适用于瑞雷波频散曲线的定量解释，具有很高的实用性价值.  相似文献