基于PSONN的大坝监控实时预报模型     

闫滨  高真伟 《岩土力学》2006,27(Z2):548-552

将粒子群算法（PSO）引入大坝监测领域,提出一种基于粒子群神经网络（PSONN）的大坝监控预报模型。该模型充分发挥PSO的全局寻优能力和BP神经网络局部细致搜索优势,给BP神经网络提供了良好的初始权值。对逐一粒子群（SPSONN）、整体粒子群（WPSONN）、逐一BP（SBPNN）及整体BP（WBPNN）4种预报模型的对比分析表明：逐一预报模型（SPSONN和SBPNN）的预报精度明显高于对应的整体预报模型（WPSONN和WBPNN）的预报精度;与BP神经网络模型相比,PSONN模型不仅收敛速度明显加快,而且预报精度也有较大提高,尤其是SPSONN模型,其高精度和短历时性完全满足实时预报的需要,可以准确、有效地应用于大坝监测量的实时预报。  相似文献   

Investigation on Touching Sea Bottom by a FPSO in Bohai Oilfield with Shallow Water     

李欣  杨建民范模 《海洋通报(英文版)》2005,7(1):10-20

As one of the key safety problems, the motion performance and touching sea bottom of a FPSO are paid much attention by the ocean oil companies when the FPSO is exposed to survival storms in the shallow-water working areas. In this paper, timedomain numerical simulations are carried out on a 160 kDWT FPSO with a Yoke mooring system moored in the BZ25-1 oilfield with a water depth of 16.7m. The results are compared with those of the corresponding model tests. Good agreement shows that the time-domain simulations can be used to predict the performance of the FPSO in shallow-water reasonably. It is found that the touch of seabed by a fully loaded FPSO occurred few times under survival storm conditions. Therefore, the FPSO should be less loaded than that in the fully loaded condition under the survival storms.  相似文献   

Particle swarm optimization of TMD by non‐stationary base excitation during earthquake     

A. Y. T. Leung  Haijun Zhang  C. C. Cheng  Y. Y. Lee 《地震工程与结构动力学》2008,37(9):1223-1246

There are many traditional methods to find the optimum parameters of a tuned mass damper (TMD) subject to stationary base excitations. It is very difficult to obtain the optimum parameters of a TMD subject to non‐stationary base excitations using these traditional optimization techniques. In this paper, by applying particle swarm optimization (PSO) algorithm as a novel evolutionary algorithm, the optimum parameters including the optimum mass ratio, damper damping and tuning frequency of the TMD system attached to a viscously damped single‐degree‐of‐freedom main system subject to non‐stationary excitation can be obtained when taking either the displacement or the acceleration mean square response, as well as their combination, as the cost function. For simplicity of presentation, the non‐stationary excitation is modeled by an evolutionary stationary process in the paper. By means of three numerical examples for different types of non‐stationary ground acceleration models, the results indicate that PSO can be used to find the optimum mass ratio, damper damping and tuning frequency of the non‐stationary TMD system, and it is quite easy to be programmed for practical engineering applications. Copyright © 2008 John Wiley & Sons, Ltd.  相似文献   

基于Allan方差和SVR的MEMS陀螺仪随机误差分析与预测     

付永恒  张丽杰 《测绘通报》2019,(5):88-92

为了使低成本MEMS陀螺仪数据的精度更高，本文提出了一种混合核函数支持向量回归（SVR）的MEMS陀螺仪随机误差预测模型，并通过粒子群优化（PSO）算法对模型参数和核函数参数进行优化；同时通过Allan方差法对SVR预测前后的MEMS陀螺仪随机误差数据进行分析。试验结果表明：混合核函数SVR对MEMS陀螺仪随机误差的预测准确度可达99.99%；当MEMS陀螺仪所处状态不同，但噪声特性相同时，可采用统一的SVR预测模型预测随机误差，研究结果为进一步用于MEMS陀螺仪的实时误差补偿中提供依据。  相似文献   

基于优化的BP神经网络地层可钻性预测模型          下载免费PDF全文

董青青  梁小丛 《探矿工程》2012,39(11):26-28

提出了一种粒子群算法（PSO）优化的BP网络模型预测地层可钻性的新方法。利用粒子群算法优化BP网络模型的参数,避免了BP网络陷入局部极小值的缺点,提高了模型的预测速度和精度。结合钻探实例,利用测井资料和地层可钻性级别的关系建立了可钻性级别实时预测模型,并将该模型与传统的BP网络进行对比,结果表明,该模型优于BP网络,具有较高的精度和较快的收敛速度,有一定的适用性。  相似文献   

基于PSO和LM算法的坐标转换新方法     

郑建雷;黄张裕;邱华旭;魏锦德 《东北测绘》2013,(2):183-186

3维坐标的转换精度与坐标转换参数的解算精度密切相关,在不同区域的坐标转换参数不完全相同,为了提高测量的精度,就必须求出适合本地区的坐标转换参数,以提高坐标转换的精度。本文直接从坐标转换的非线性方程出发,根据最优化问题的极值条件,研究采用基于微粒群优化(PSO)和拉凡格氏(LM)组合算法求解3维坐标转换参数。结果表明,该方法具有简单性、高效性和普适性,适合测量中3维坐标的转换解算。  相似文献   

基于主成分分析与粒子群优化的遥感影像变化检测     

许石罗  牛瑞卿  武雪玲  刘超贤 《测绘科学》2017,42(4)

针对变化检测中差异影像上变化阈值选择困难的问题,该文提出了使用粒子群优化算法自动地从差异影像上选择最优变化阈值的方法。该方法首先利用主成分分析法从影像中提取包含最大信息的主分量,利用主分量构建差异影像;在此基础上,使用高斯混合模型估算差异影像的初始阈值,最后通过粒子群算法计算出最优的变化阈值。实验结果表明,该方法能够迅速地获取变化阈值,避免了人工选择时繁琐重复的尝试,且检测结果精度较高。  相似文献   

Simulating urban growth processes by integrating cellular automata model and artificial optimization in Binhai New Area of Tianjin,China     

Fengmei Yao  Cui Hao 《国际地球制图》2016,31(6):612-627

This study presents an optimized algorithm into the cellular automata (CA) models for urban growth simulation in Binhai New Area of Tianjin, China. The optimized CA model by particle swarm optimization (PSO) was compared with the logistic-based cellular automata (LOGIT-CA) model to see the effects of the simulation. The study evaluated the stochastic disturbance in the development of urban growth using the Monte Carlo method; the coefficient d determined the state of urban growth. The validation was conducted by both cross-tabulation test and structural measurements. The results showed that the simulations of PSO-CA were better than LOGIT-CA model, indicating an improvement in the spatio-temporal simulation of urban growth and land use changes in study area. Since the simulations reached their best values when the coefficient was between 1 and 2, the urban growth in the study area was in the period of conversion from spontaneous growth to edge-expansion and infilling growth.  相似文献   

基于多传感器融合式航迹起始算法     

张宇  唐慧佳  鹿小莺  吴昊 《成都信息工程学院学报》2009,24(4):366-369

提出了一种基于聚类分析和Kalman 滤波相结合的多传感器航迹起始算法.根据多传感器同一时刻对同一目标的观测值在空间呈团状的特征,运用聚类的方法解决数据融合问题.采用一种改进的粒子群(PSO)优化算法对多传感器观测数据进行聚类,结合聚类中心和目标预测值,应用Kalman滤波器估计目标状态,从而实现航迹起始.实验结果表明,该方法有效.  相似文献   

在建导管架平台圆管风致涡激振动及减振研究     

刘利琴  陈益群  沈文君  李昊  吴志强 《海洋工程》2021,39(4):1-8

研究了大型导管架平台卧式建造时出现单边约束圆管的风致涡激振动问题。将建造过程中单边约束的导管架圆管简化成悬臂梁模型,采用van der Pol尾流振子模型模拟圆管受到的流体力,建立了圆管风致涡激振动动力学方程。使用伽辽金方法对建立的运动方程进行求解,数值分析了圆管在特定约化风速下的涡激振动特性。在圆管上附加非线性能量阱(NES)作为被动减振装置对圆管进行减振,并采用粒子群优化算法对NES的非线性刚度和阻尼参数进行了优化。结果表明,在约化速度为4.8时,得到的NES优化的非线性刚度和阻尼参数组合可以有效减小悬臂梁自由端风致涡激振动位移。本研究说明采用NES和粒子群优化算法可以有效减小圆管的风致涡激振动,为导管架安全建造提供一定的参考。  相似文献