Collision avoidance for a mobile robot based on radial basis function hybrid force control technique

Collision avoidance is always difficult in the planning path for a mobile robot. In this paper, the virtual force field between a mobile robot and an obstacle is formed and regulated to maintain a desired distance by hybrid force control algorithm. Since uncertainties from robot dynamics and obstacle degrade the performance of a collision avoidance task, intelligent control is used to compensate for the uncertainties. A radial basis function (RBF) neural network is used to regulate the force field of an accurate distance between a robot and an obstacle in this paper and then simulation studies are conducted to confirm that the proposed algorithm is effective.     

RBF collocation method and stability analysis for phononic crystals

The mesh-free radial basis function (RBF) collocation method is explored to calculate band structures of periodic composite structures. The inverse multi-quadric (MQ), Gaussian, and MQ RBFs are used to test the stability of the RBF collocation method in periodic structures. Much useful information is obtained. Due to the merits of the RBF collocation method, the general form in this paper can easily be applied in the high dimensional problems analysis. The stability is fully discussed with different RBFs. The choice of the shape parameter and the effects of the knot number are presented.     

基于遗传RBF网络的惯性测量组合模拟电路故障诊断

为解决惯性测量组合模拟电路的诊断不易定位到元件级故障的问题,提出了一种基于遗传RBF网络的智能诊断方法。该方法首先利用RBF神经网络快速准确识别故障的能力,以RBF的训练均方误差为遗传算法的适应度函数,依靠遗传算法强大的全局寻优能力实现故障特征选择。在特征选择的过程中,同时记录使训练均方误差达到最小的最优RBF网络,然后直接利用特征选择过程中训练好的最优RBF网络诊断故障,而无需利用特征选择后的训练数据对RBF网络进行再训练,简化了诊断步骤,同时增强了网络的抗干扰能力。仿真结果表明,该方法能有效去除冗余特征,准确诊断惯性测量组合模拟电路的故障,并有较好的抗噪能力,证明了该方法的有效性和可行性。     

多学科设计优化中常用代理模型的研究

代理模型是多学科设计优化的关键技术之一。本文系统介绍了多项式响应面模型,径向基函数模型和Kriging模型等3种多学科设计优化中常用的代理模型。通过构造某机翼展向气动载荷分布的代理模型,对这3种模型的效果进行了评估,并对这些代理模型的构造方法、基本特性和适用范围进行了分析研究。     

基于IGRA-ISVD约减和RBF的森林火灾消防直升机需求预测模型

针对森林火灾消防直升机需求预测问题,提出了一种基于改进灰色关联分析(IGRA)和改进奇异值分解(ISVD)约简的径向基函数(RBF)神经网络预测模型.首先,基于既有研究梳理了森林火灾消防直升机需求预测指标体系;然后,在改进灰色关联分析和奇异值分解方法的基础上,分别对消防直升机需求预测数据信息进行属性约简和维度约简;最后,利用约简预测数据信息对RBF神经网络进行训练,进而构建消防直升机数量预测模型.案例分析和对比分析表明了本文所提方法的可行性和合理性.     

基于RBF网络的断路器电流自适应保护研究

针对传统断路器电流保护方法存在受系统运行方式影响、整定困难、智能化低等问题,本文提出了基于RBF的断路器电流自适应保护算法,并给出了算法的模型。该算法融合了RBF神经网络的故障检测和电流自适应保护。首先通过RBF网络检测负载线路的电流故障,然后用电流自适应算法进行保护。在对神经网络进行训练时,利用PSO算法对RBF神经网络的参数进行优化以此来提高网络的泛化能力和学习能力;然后采用优化后的PSO-RBF神经网络对电流故障进行诊断。实验表明,该算法较大地提高了断路器智能化管理水平。     

The closed-form particular solutions for Laplace and biharmonic operators using a Gaussian function

Particular solutions play a critical role in solving inhomogeneous problems using boundary methods such as boundary element methods or boundary meshless methods. In this short article, we derive the closed-form particular solutions for the Laplace and biharmonic operators using the Gaussian radial basis function. The derived particular solutions are implemented numerically to solve boundary value problems using the method of particular solutions and the localized method of approximate particular solutions. Two examples in 2D and 3D are given to show the effectiveness of the derived particular solutions.     

EMD结合RBF神经网络新混合模型及股指期货价格预测

中国近4年才成立的股指期货市场价格呈现出非平稳、非线性的信号特征,传统的预测方法无法对长相关序列进行精确预测.将EMD与RBF相结合,建立了一种新的预测方法对我国股指期货日结算价格进行预测.结果显示本模型将原本具有长相关性质的原始序列分解为若干个短相关性质的不同频带,解决了原始序列随机性强,以及因相邻频带的干扰而造成的系统动力信息反映不足的缺陷;并与其他预测模型进行比较,显示出较高的预测精度.     

交通流灰色RBF网络非线性组合预测方法

针对智能交通系统的开发,提出一种基于灰色GM(1,1)模型和RBF网络非线性组合的短时交通流预测方法.该方法采用三层结构的RBF网络将两种单一预测方法(灰色GM(1,1)模型和RBF网络)进行了非线性组合.利用实测数据对组合方法进行了仿真实验,结果表明:非线性组合模型的预测准确性高于单独的RBF网络预测的准确性;组合模型发挥了两种单一方法各自的优势,是短时交通流预测的有效方法.     

Environmental noise classifier using a new set of feature parameters based on pitch range

Automatic Noise Recognition was performed in two stages: (1) feature extraction based on the pitch range, found by analyzing the autocorrelation function and (2) classification using a classifier trained on the extracted features. Since most environmental noise types change their acoustical characteristics over time, we focused on the “pitch range” of the sounds in order to extract features. Two different classifiers, Support Vector Machines (SVM) and k-means clustering, were performed and compared using the proposed features. The SVM and k-means clustering classifiers achieve recognition rates up to 95.4% and 92.8%, respectively. Although both classifiers provided high accuracy, the SVM-based classifier outperformed the k-means clustering classifier by approximately 7.4%.