共查询到20条相似文献,搜索用时 140 毫秒
1.
2.
提出一种基于差分进化算法(DE)的径向基函数神经网络(RBFNN)模型,用于预测直线伺服系统的定位误差.该模型用差分进化算法训练径向基函数(RBF)网络隐层中心位置、宽度和输出层连接权重.为了评价优化后RBF网络预测的精度,运用部分误差样本进行训练和仿真.构建了以数字信号处理器(DSP)为核心的直线电动机定位误差实验平台,根据误差校正值进行误差实时补偿实验.仿真和实验结果表明:经过DE算法训练的神经网络模型对工作台的误差具有良好的学习能力和泛化能力,与单纯RBF网络、基于遗传优化的RBF神经网络相比,该建模方法具有更高的定位精度. 相似文献
3.
本文为了解决现有算法重建超分辨率算法,所需较长训练时间的问题,提出一种更加高效的深度卷积神经网络图像超分辨率重建方法。该方法可以在保证每层卷积层、非线性层基础上,包含20层卷积神经网络,每层级联构建神经网络结构,通过运用此方法于低分辨率图像中,可以提取图像特征,利用此算法残差学习获取高频信息,LIR结合预测高频信息即可重建高频率图像。训练中利用裁剪梯度避免爆破,保证训练平稳与图像重建的高效性。该方法经仿真表明较原始方法图像处理性能明显提升,有效改善主观视觉体验,获取的低分辨率图像重建后PSNR值最大可提升0.19,各客观评价指标也明显提升,证明该方法的有效性。 相似文献
4.
5.
6.
7.
自主式水下机器人自适应区域跟踪控制 总被引:1,自引:0,他引:1
研究自主式水下机器人的区域跟踪控制问题,提出一种基于PD神经滑模的自适应区域跟踪控制方法。针对自主式水下机器人自适应控制器中仅在线调整网络权值的径向基函数神经网络存在收敛性能差的问题,给出同时对径向基函数神经网络权值、径向基函数中心与方差进行自适应调整的方法,使径向基函数神经网络无须离线选取径向基函数中心与方差,即可进行在线自适应学习。考虑到控制器中滑模控制项易引起系统抖振的问题,提出一种基于指数函数的滑模切换增益调节方法,使滑模切换增益能够依据跟踪误差实时调节以降低系统抖振。基于Lyapunov理论对所提自适应区域跟踪控制方法的稳定性进行分析。通过自主式水下机器人的仿真试验与水池试验验证所提方法的有效性。 相似文献
8.
9.
10.
11.
为了进一步提高遥感图像超分辨效果,提高超分辨重建速度。针对以往稀疏超分辨算法中更容易丢失边缘信息和引入噪声的问题,本文改进了特征提取算子,以对称近邻滤波(SNN)代替高斯滤波,重点解决特征空间中的字典学习问题。首先,根据遥感图像退化模型生成训练样本图像,并分别对高、低分辨率遥感图像进行7×7分块,生成字典训练样本。然后,建立连接高、低分辨率图像空间的双参数联合稀疏字典,将字典学习过程中的稀疏系数分解为系数权值和字典原子的乘积,依据字典原子指标训练和更新字典,得到高低分辨率联合字典映射矩阵。最后,进行遥感图像超分辨稀疏重构。实验结果表明:与当前最先进的稀疏表示超分辨算法相比,本文算法得到的超分辨重建遥感图像的主观效果更好,恢复出更多的地物细节信息;客观评价参数峰值信噪比(PSNR)提高约1.7dB,结构相似性(SSIM)提高约0.016。改进的稀疏表示超分辨算法可以有效地提高遥感图像超分辨效果,同时降低重建时间。 相似文献
12.
Image super-resolution reconstruction is an effective method to improve image resolution, but most reconstruction methods rely on the clear low resolution images ignoring the blurred images which are also effective observations of the scene. Aiming at the problem, a super-resolution reconstruction (SRR) method via multi-frame defocused images is proposed. Firstly, according to the image degraded model, we establish the cost function of the point spread function (PSF) and utilize the particle swarm optimization algorithm to estimate it. Then, based on the multi-frame defocused images and PSFs, a joint reconstruction model is established to realize SRR by compressive sensing (CS) theory. In the CS framework, only the interpolated version of the low-resolution image is used for training purpose and the K-Singular Value Decomposition method is used for dictionary training. In addition, to solve the edge effect problem, an internal blur matrix is constructed according to the image blurring process, and a weight coefficient is introduced in the patch splicing process. Experiments show that the proposed algorithm can accurately estimate the defocused image PSF and achieve a good reconstruction effect. 相似文献
13.
A nonlinear method based on a Fuzzy Inference System (FIS) to improve the images obtained from Electrical Capacitance Tomography (ECT) is proposed. Estimation of the molten metal characteristic in the Lost Foam Casting (LFC) process is a novel application in the area of the tomography process. The convergence rate of iterative image reconstruction techniques is dependent on the accuracy of the first image. The possibility of the existence of metal in the first image is computed by the proposed fuzzy system. This first image is passed to an iterative image reconstruction technique to get more precise images and to speed up the convergence rate. The proposed technique is able to detect the position of the metal on the periphery of the imaging area by using just eight capacitive sensors. The final results demonstrate the advantage of using the FIS compared to the performance of the iterative back projection image reconstruction technique. 相似文献
14.
针对传统永磁同步电机调速系统面对变负载和大范围调速时,P、I参数需要频繁调整且速度跟踪不理想的问题,提出了一种基于误差反馈学习结构的永磁同步电机有限时间速度控制方法。在对永磁同步电机运动方程分析的基础上,使用非线性PI和径向基神经网络建立了速度环控制器模型。前者保证控制系统收敛和稳定,其输出作为神经网络的误差学习参数;后者基于终端滑模理论设计参数调整律,加快神经网络的参数收敛速度,使得神经网络的输出逐渐取代非线性PI成为控制系统的主要控制器。利用李雅普诺夫稳定判据分析了控制器的收敛性,并在永磁同步电机调速系统上进行了试验。研究结果表明,基于误差反馈学习结构的有限时间控制策略能够减小系统静态误差和抖振,具有一定的抗干扰能力。 相似文献
15.
吉林一号轻型高分辨率遥感卫星光学成像技术 总被引:1,自引:0,他引:1
为了实现吉林一号光学遥感卫星轻量化设计与高分辨率多光谱多模式成像,采用星载一体化设计理念及敏捷多模式成像策略,完成了吉林一号卫星的指标、方案及关键技术的设计与在轨多模式光学成像。吉林一号整星的质量为450kg,有效载荷比高达40%,机动能力达2.1(°)/s,可实现大侧摆、同轨立体与条带拼接等多模式成像,结合星上800GB的FLASH存储能力和X波段双通道600 Mbps的数据传输能力,卫星每天可获取近150 000km~2的图像数据。吉林一号轻型高分辨率光学卫星于2015年发射入轨,运行在656km太阳同步轨道,地面全色和多光谱分辨率分别优于0.72m和2.88m,满足多行业应用及商业化运营的需求。 相似文献
16.
Mende SB 《The Review of scientific instruments》2011,82(1):013102
For optimizing in situ particle and field measurements, auroral research satellites are best operated in a spinning mode. Simultaneous imaging of the optical aurora from such satellites requires either a stable platform or the derotation of the camera itself. Either of these requirements is complex and expensive. Either of these solutions also suffers from the problem that image blur often occurs due to the misalignments between the actual and the nominal spin axes of the satellite. Here we propose a novel solution in which the camera(s) are mounted solidly on the spacecraft to observe parallel to the spin axis of the satellite while a despinning flat 45° mirror directs the field of view toward the spacecraft nadir. The resultant image will appear to rotate in the frame of reference of the detector in the camera. In our scheme the images are exposed rapidly and a derotation algorithm is applied to the coordinates of each pixel in real time before the images are co-added in memory. The derotation algorithm uses only look up tables and integer additions and can be executed rapidly in hardware so that the system can support relatively fast satellite spin cycles. The system was simulated including a 1.8° misalignment between the nominal satellite spin axis (parallel to the mirror rotation axis) and the actual spin axis. It was shown that the look up table based algorithm can despin the images and correct for the axes misalignment, allowing the observation of the aurora at full resolution and with continuous coverage. 相似文献
17.
在电容层析成像(ECT)图像重建迭代类算法中,通常采用线性正问题求解,以加快重建速度,由此产生重建误差。针对这一问题,提出了基于极限学习机(ELM)的非线性ECT正问题求解方法,ELM网络输入为介电常数分布,其输出为预测的电容测量值。将该方法与传统的Landweber迭代算法相结合构成ELM-Landweber迭代算法进行图像重建。为使样本具有较好的代表性,物体分布位置及大小均随机生成,并计算相应的归一化电容值作为ELM网络训练及测试样本,对ELM-Landweber迭代算法进行了仿真与静态实验,并与传统Landweber迭代算法进行比较。实验结果表明,相较于传统Landweber迭代算法,采用ELM-Landweber迭代算法,其算法收敛速度显著提高,重建图像质量得到明显改善。训练样本的平均图像相对误差由0.728减小至0.504,测试样本的平均图像相对误差由0.596减小至0.475。 相似文献
18.
19.
A problem in high magnification microscopy is the blurring in the imaging of an object. In this article, we demonstrate a restoration technique that simultaneously makes use of the confocal image and the wide-field image. These images can be acquired by a modified conventional microscope. In front of the light-source, there is an array of pinholes. There are no pinholes at the detection plane. Instead, one or more pixels from the CCD camera are used, where the pinholes would have been. Using all pixels gives the wide-field image, but using a selected subset can give a confocal image. The array is used to speed up the process of acquiring the image. Note that the speed of acquisition is proportional to the number of pinholes. We show that the restoration from the two images can lead to a better result than using only one of the images. If this is the case, we show that a distance of 5 times the diameter of the pinholes can give the same results as a distance of 20 times after deconvolution. This offers an increase in acquisition time of a factor 16. 相似文献
20.