共查询到20条相似文献,搜索用时 203 毫秒
1.
改进的变步长LMS自适应滤波算法 总被引:1,自引:1,他引:0
《舰船科学技术》2015,(10):115-118
针对解决LMS(Least Mean Square)自适应滤波算法收敛速度及未知系统时变跟踪速度与稳态误差的矛盾,改进步长因子μ(n)与误差信号e(n)的非线性映射关系,提出一种新的变步长LMS算法。执行该算法时系统初始阶段或未知系统时变阶段步长自动增大,而稳态时步长缓慢变小,提高了收敛速度和时变跟踪能力,克服了稳态误差偏大的缺点。理论分析及实验结果表明,新算法的收敛、跟踪速度及稳态误差性能均优于现有常见的几种LMS算法。 相似文献
2.
本文提出了改进的BP算法,并应用于军事指挥决策知识的处理。对于BP算法的改进,本文根据军事知识树的特点构造了BP神经网络,并对影响BP网络学习速度和效果的隐节点构造、收敛速度和活跃函数等问题进行了研究和改进。 相似文献
3.
针对杂波情况下的舰艇防空作战中对单机动目标跟踪问题,提出了一种变结构数据关联算法.通过自适应网格算法实现对多种运动模式的机动目标进行自适应跟踪,用概率数据关联算法对杂波下目标进行状态估计,将变结构算法的自适应能力和概率数据关联的杂波跟踪能力相结合.通过模拟跟踪典型反舰导弹机动轨迹,将该算法与标准IMMPDA算法相比较.仿真结果表明,该算法具有较高的关联精度和更短的跟踪时间,对于提升舰艇防空效能和增强生命力有着积极意义. 相似文献
4.
基于BFGS法的BP神经网络算法研究 总被引:2,自引:0,他引:2
张伟标 《上海海运学院学报》1999,20(3):122-126
在把BFGS法运用于BP神经网络权的训练中,通过基于不同算法的神经网络对实际问题进行了学习,并根据学后获取的非线性机理结合预测的实例进行对比分析,表明基于BFGS法的BP神经网络算法对加快网络训练速度,提高网络预测的能力方面是有效的。 相似文献
5.
首次提出将分离矩阵用于对在线盲分离算法中步长自适应控制,并在认真分析相关固定步长和变步长EASI算法的基础上,将其加以运用,提出了一种新的步长自适应EASI算法。该算法步长是基于分离矩阵的,其学习速率由信号的分离程度自适应地选取,因而能很好地解决收敛速度和稳态误差之间的矛盾。计算机仿真结果与理论分析相一致,证实了该算法明显优于其他固定步长或变步长的EASI算法。 相似文献
6.
在一种变步长LMS算法的基础上,引进动量因式,提出了一种新的改进LMS的算法。新算法整体性能优于变步长LMS算法以及LMS算法。通过理论分析,比较了新的算法和变步长LMS算法以及LMS算法的收敛性和稳态性,提出了一种设想以提高新算法的稳态性。仿真试验证明了新算法的优越性以及设想的在仿真条件下的正确性。 相似文献
7.
泄露变步长最小均方算法是一种改进型LMS算法,克服了LMS算法无法同时兼顾收敛速度和稳态误差的的固有缺陷。提出一种基于泄露变步长LMS算法的汽车车内噪声主动控制方法,并将基于LMS算法和泄露变步长LMS算法的汽车车内噪声主动控制结果进行比较,结果表明:与LMS算法相比,泄露变步长LMS算法具有更快的算法收敛速度和较小的稳态误差,可有效进行汽车车内噪声主动控制。 相似文献
8.
9.
10.
基于对时域变步长LMS算法、频域块LMS算法的研究分析,给出了一种新的基于变步长频域块LMS的干扰抑制算法,仿真结果和分析表明能实现更好的收敛速度和更小的有用信号损失,并且计算复杂度低,利于工程实现。 相似文献
11.
Based on polynomial interpolation and approximation theory, a novel feed-forward neural network, the feed-forward neural network with Chebyshev orthogonal basis function, is proposed for black-box modeling of ship manoeuvring motion. The neural model adopts a three-layer structure, in which the hidden layer neurons are activated by a group of Chebyshev orthogonal polynomial activation functions and the other two layers’ neurons use identity mapping as activation functions. Weight update formulas are derived by employing the standard back-propagation (BP) training method. With the simulated 15º/15º zigzag test data as input and calculated values of the hydrodynamic forces and moment as output, the feed-forward neural network with Chebyshev orthogonal basis function and the BP neural network are applied to identify the nonlinear functions in the nonlinear hydrodynamic model of ship manoeuvring motion. With the simulated 20º/20º zigzag test data and 35º turning test data as input, the hydrodynamic forces and moment are predicted by using the identified nonlinear functions. Comparison between the calculated and predicted hydrodynamic forces and moment shows that the feed-forward neural network with Chebyshev orthogonal basis function is superior to the BP neural network in identifying the nonlinear functions of the nonlinear hydrodynamic model of ship manoeuvring motion and is an effective method to conduct the black-box modeling of ship manoeuvring motion. 相似文献
12.
基于自适应变异 PSO-BP算法的船舶横摇运动预测 总被引:1,自引:0,他引:1
为了准确高效预测船舶在海上的航行状态,以保证人员、货物和船舶的安全,提出一种自适应变异的粒子群优化算法(self-adapting particle swarm optimization algorithm,SAPSO),将该算法与误差反传(back propaga-tion,BP)神经网络结合。SAPSO-BP预测模型使用SAPSO算法优化BP网络的网络参数。克服传统BP神经网络对初始权值阈值敏感,容易陷入局部极小值的缺点,同时也克服了传统PSO算法早熟收敛、搜索准确度低及迭代效率低等缺点。运用该模型对科研教学船“育鲲”轮在海上航行的横摇情况进行实时预测实验,验证该方法的可行性与有效性具有较高的预测精度。 相似文献
13.
14.
15.
16.
17.
通过对自航模运行特点的研究,研制出一套利用伺服系统驱动的单台摄像机自动跟踪系统,主要由水平旋转伺服系统、垂直旋转伺服系统和安装在伺服系统之上的工业相机组成。系统对图像进行采集和处理,并与伺服系统形成闭环。当船模成像到达图像正中心后,采集当前水平与垂直伺服系统的角度,计算当前船模坐标,并与上一坐标点进行关联,绘制运行路径。通过实际测试,该系统运行稳定,轨迹定位精度满足工程要求。 相似文献
18.
19.
《船舶与海洋工程学报》2019,(3)
Swarm robotics in maritime engineering is a promising approach characterized by large numbers of relatively small and inexpensive autonomous aquatic crafts(AACs) to monitor marine environments. Compared with a single, large aquatic manned or unmanned surface vehicle, a highly distributed aquatic swarm system with several AACs features advantages in numerous real-world maritime missions, and its natural potential is qualified for new classes of tasks that uniformly feature low cost and high efficiency through time. This article develops an inexpensive AAC based on an embedded-system companion computer and open-source autopilot, providing a verification platform for education and research on swarm algorithm on water surfaces. A topology communication network, including an inner communication network to exchange information among AACs and an external communication network for monitoring the state of the AAC Swarm System(AACSS), was designed based on the topology built into the Xbee units for the AACSS. In the emergence control network, the transmitter and receiver were coupled to distribute or recover the AAC. The swarm motion behaviors in AAC were resolved into the capabilities of go-to-waypoint and path following, which can be accomplished by two uncoupled controllers: speed controller and heading controller. The good performance of velocity and heading controllers in go-to-waypoint was proven in a series of simulations. Path following was achieved by tracking a set of ordered waypoints in the go-to-waypoint. Finally, a sea trial conducted at the China National Deep Sea Center successfully demonstrated the motion capability of the AAC. The sea trial results showed that the AAC is suited to carry out environmental monitoring tasks by efficiently covering the desired path, allowing for redundancy in the data collection process and tolerating the individual AACs' path-following offset caused by winds and waves. 相似文献
20.
运用人工神经网络的方法对某舰用汽轮发电机组的滑油铜含量进行分析,找出铜含量的变化规律,然后与曲线拟合进行数据处理的方法作比较,结果表明,基于遗传算法的BP网络模型比曲线拟合模型的预报精度明显提高,预报结果稳定,且建立模型的过程较为简单。 相似文献