RBF神经网络在动物动态称重中的研究

针对动物动态称重数据样本不平稳,真实信号淹没在噪声中导致动物体重难以快速准确测量的问题,通过将RBF神经网络引入到动态称重数据的处理中,结合经验模态分解（EMD）算法处理动态称重数据的对比试验,得出RBF神经网络能有效降低干扰信号影响的结论。EMD算法处理数据的平均相对误差为9.51%,RBF算法处理数据的平均相对误差为5.86%。实验结果表明,RBF算法处理动态称重数据的平均相对误差比EMD算法高了近一倍,证实了RBF算法应用于动物动态称重数据比EMD算法更有效。     

汽车动态称重信号的自适应校正应用研究

提出一种通过自适应补偿提高长秤台汽车动态称重系统精度的方法.根据汽车动态称重两自由度模型,利用零、极点对消原理,设计校正滤波器,改善信号响应特性,使信号快速达到平稳状态.实验结果表明,本方法能有效地缩短信号衰减时间,改善称重精度,并具有很好的自适应性.     

RBF神经网络在表面粗糙度光纤传感器中的应用

本文提出了以径向基函数（RBF）神经网络处理表面粗糙度光纤传感器输出信号的方法,将传感器的输出信号及作为光源的激光强信号同时加在RBF神经网络的输入端,利用RBF神经网络能够以任意精度逼近非线函数地能力的优点,同时实现对传感器的非线性补偿及减轻激光器输出光强变化带来的影响,采用这种方法的表面粗糙度光纤传感器,降低了对激光器输出功率稳定性的要求,具有测量范围大,精度高的特点。     

汽车动态称重信号的自适应校正应用研究

提出一种通过自适应补偿提高长秤台汽车动态称重系统精度的方法。根据汽车动态称重两自由度模型,利用零、极点对消原理,设计校正滤波器,改善信号响应特性,使信号快速达到平稳状态。实验结果表明,本方法能有效地缩短信号衰减时间,改善称重精度,并具有很好的自适应性。     

汽车动态称重信号的自适应校正应用研究

提出一种通过自适应补偿提高长秤台汽车动态称重系统精度的方法。根据汽车动态称重两自由度模型，利用零、极点对消原理，设计校正滤波器，改善信号响应特性，使信号快速达到平稳状态。实验结果表明，本方法能有效地缩短信号衰减时间，改善称重精度，并具有很好的自适应性。     

基于小波变换与BP神经网络的模拟电路故障诊断

利用小波与改进算法的BP神经网络相结合的方法进行模拟电路故障诊断,该方法使用小波分解作为预处理工具,对信号进行消噪和小波分解,然后提取特征信息,进行归一化处理,并作为BP神经网络的输入样本进行模式识别。该方法减少了神经网络的输入维数,提高了收敛速度和辨识故障的能力。仿真结果表明,该方法能准确快速地定位故障,且可有效地进行故障识别、改善神经网络结构以及提高故障诊断精度与速度。     

速度与加速度对动态称重系统的影响

为研究速度、加速度对动态称重的影响,将繁复的汽车振动模型进行简化,利用Matlab对B级路面情况下不同速度的动载荷进行仿真;从力学角度利用达朗贝尔原理,研究加速度因素对动态称重结果的影响。由分析知:速度值越大,动载荷频率、幅度越高,对称重精度影响越大;加速度不等于零时,单轴称重瞬时值会产生与加速度成正比的误差,并使称重结果产生较大偏差。速度与加速度的影响分析,为进一步提高动态汽车衡精度研究提供了理论依据。     

基于最大电源噪声门级模型的遗传算法电源噪声估计

提出一种能够综合考虑IR drop和di/dt噪声的门级电路模型.实验表明,利用这种模型进行电源噪声估计,可以比传统模型提高5.3%的精度,同时运算时间降低10.7%.根据输入信号对最大电源噪声的影响,还提出了关键输入信号模型.实验表明,在进行电源噪声估计中,基于这些模型的遗传算法,能够比传统的遗传算法提高最多19.0%的精度,并且收敛更加迅速.     

基于最大电源噪声门级模型的遗传算法电源噪声估计

提出一种能够综合考虑IR drop和di/dt噪声的门级电路模型.实验表明,利用这种模型进行电源噪声估计,可以比传统模型提高5.3%的精度,同时运算时间降低10.7%.根据输入信号对最大电源噪声的影响,还提出了关键输入信号模型.实验表明,在进行电源噪声估计中,基于这些模型的遗传算法,能够比传统的遗传算法提高最多19.0%的精度,并且收敛更加迅速.     

过采样方法在动态轴重式汽车衡中的应用

为了提高动态轴重式汽车衡称重的精度,提出一种采用过采样的方式提高A/D转换有效位数方法.M/D转换的位数决定了信噪比,提高信噪比可以提高A/D转换的精度.在利用相同的A/D采样速率的条件下,采用过采样技术可减小量化误差,并获得与高分辨率相应的信噪比,增加被测数据的有效位数,提高A/D的分辨率.对实验结果的分析表明:通过过采样方法处理后的采样信号,可使动态轴重式汽车衡在保证其称量达1%精度时,提高称重过车速度.     

Detection of nonlinear distortion in audio signals

Nonlinear distortion of a signal passing through a system may be caused by a number of factors. One of those factors, a limiter like transfer function, is considered. The nonlinear distortion causes a change in the probability density function (PDF) of the signal. The PDF of the signal can be characterized by the coefficients of a fifth-order polynomial fitted to the PDF curve. The coefficients are used as a vector input to an artificial neural network trained to classify the vector as belonging to a distorted or undistorted audio signal. Results show that the artificial neural network is able to classify signals, with PDFs indicating the presence of significant high amplitude components, into distorted or undistorted. A low amplitude signal will not be distorted during its passage through a nonlinear system and therefore the output will be classified as "not distorted". This gives rise to, what seem to be, errors in the classification of signals. However, the technique developed identifies distortion in the signal and not in the system through which the signal has passed.     

应用深度神经网络和集成学习的电台个体识别

提出了一种基于深度神经网络的个体智能识别方法,可用于电台个体分类识别.该方法构建集成多子网络的一维深度卷积模型,以电台时序信号作为模型输入,进行电台个体分类.利用深度神经网络自动特征化的能力,该方法从时序信号中自动获取个体特征,从而以端到端的形式实现从电台信号识别电台个体.该方法能够免去基于专家知识的特征提取工作,自动提取的个体深度特征还有助于区分传统特征无法区分的高度相似电台个体.实验证明,该方法能有效降低模型调参设计难度,能减轻单一网络带来的特征提取识别过拟合问题,能提高电台个体识别算法的泛化能力与鲁棒性.在信噪比12 dB的条件下,对10类电台8PSK调制信号进行特征提取与识别,整体正确率91.83％,平均正确率为89.12％;对MSK调制信号进行特征提取与识别,平均分类精度为89.1％.     

基于复数网络与注意力机制的信号调制识别

通信信号调制识别作为管理、监测电磁频谱的重要手段,具有重要的研究价值和应用前景。本文利用调制信号的频域信息,提出一种基于复数神经网络的信号调制识别方法。首先将I、Q两路信号组合成复信号,经过快速傅里叶变换(FFT)后把得到的实部和虚部组合起来作为输入网络的数据集。其次,设计了一种复数神经网络结构,并引入了注意力机制对网络结构进行改良。仿真结果表明,本文提出的方法可以有效识别9种调制方式,在信噪比为6 dB时,平均正确识别率达到96.33%。     

基于RBF神经网络的虚拟仪器测试系统动态补偿方法

测试系统存在着动态测试误差,为了准确地复现出被测量的原始信号,提出了基于RBF神经网络的虚拟仪器测试系统动态补偿方法.该方法不依赖于测试系统的数学模型,而是根据测试系统的输入和响应数据,利用神经网络的强非线性逼近能力获得补偿系统的模型参数,通过LabVIEW构造出测试系统的动态补偿系统.实验结果表明,将RBF神经网络和虚拟仪器相结合,对测试系统进行动态补偿具有良好的效果.     

Wavelet packet feature extraction for vibration monitoring

Condition monitoring of dynamic systems based on vibration signatures has generally relied upon Fourier-based analysis as a means of translating vibration signals in the time domain into the frequency domain. However, Fourier analysis provided a poor representation of signals well localized in time. In this case, it is difficult to detect and identify the signal pattern from the expansion coefficients because the information is diluted across the whole basis. The wavelet packet transform (WPT) is introduced as an alternative means of extracting time-frequency information from vibration signatures. The resulting WPT coefficients provide one with arbitrary time-frequency resolution of a signal. With the aid of statistical-based feature selection criteria, many of the feature components containing little discriminant information could be discarded, resulting in a feature subset having a reduced number of parameters without compromising the classification performance. The extracted reduced dimensional feature vector is then used as input to a neural network classifier. This significantly reduces the long training time that is often associated with the neural network classifier and improves its generalization capability     

Nonlinear adaptive prediction of nonstationary signals

We describe a computationally efficient scheme for the nonlinear adaptive prediction of nonstationary signals whose generation is governed by a nonlinear dynamical mechanism. The complete predictor consists of two subsections. One performs a nonlinear mapping from the input space to an intermediate space with the aim of linearizing the input signal, and the other performs a linear mapping from the new space to the output space. The nonlinear subsection consists of a pipelined recurrent neural network (PRNN), and the linear section consists of a conventional tapped-delay-line (TDL) filter. The nonlinear adaptive predictor described is of general application. The dynamic behavior of the predictor is demonstrated for the case of a speech signal; for this application, it is shown that the nonlinear adaptive predictor outperforms the traditional linear adaptive scheme in a significant way     

Linear and nonlinear ARMA model parameter estimation using anartificial neural network

Addresses parametric system identification of linear and nonlinear dynamic systems by analysis of the input and output signals. Specifically, the authors investigate the relationship between estimation of the system using a feedforward neural network model and estimation of the system by use of linear and nonlinear autoregressive moving-average (ARMA) models. By utilizing a neural network model incorporating a polynomial activation function, the authors show the equivalence of the artificial neural network to the linear and nonlinear ARMA models. They compare the parameterization of the estimated system using the neural network and ARMA approaches by utilizing data generated by means of computer simulations. Specifically, the authors show that the parameters of a simulated ARMA system can be obtained from the neural network analysis of the simulated data or by conventional least squares ARMA analysis. The feasibility of applying neural networks with polynomial activation functions to the analysis of experimental data is explored by application to measurements of heart rate (HR) and instantaneous lung volume (ILV) fluctuations     

一种基于互相关神经网络的声呐盲波束形成方法研究

针对水声环境和水声信号的特点，提出了一种基于神经网络的声呐盲波束形成算法。该方法利用水声信号的循环平稳特性把波束形成权向量的求解问题转化为阵列接收信号互相关函数的奇异值分解问题；引入一种互相关神经网络求解阵列接收信号相关函数的奇异值，从而减小了运算的代价，可高效实现盲波束形成。提出的改进互耦Hebbian学习规则有效地提高了神经网络权值的更新速度，为问题的实时求解提供了有效的途径。该方法还能抑制噪声和干扰的影响，表现出较强的顽健性。仿真实验验证了算法的正确性。     

无波前传感自适应光学神经网络控制方法

针对无波前探测自适应光学系统,研究了基于神经网络的波前控制方法。建立了无波前探测自适应光学仿真模型,分别采用卷积神经网络(Convolution Neural Network,CNN)和普通神经网络(General Neural Network,GNN)作为控制算法,远场光斑图像为神经网络的输入信号,一定阶数的泽尼克模式系数为神经网络的输出,分析了波前校正效果。仿真结果表明,经过充分训练后的神经网络可以快速、准确地从远场光斑图像中复原出入射波前的低阶泽尼克模式系数,CNN的效果优于GNN,二者的损失函数值分别为0.015 8和0.037 6。相比于传统的迭代式寻优控制方法,神经网络控制方法能够基于远场光斑图像快速得到控制信号,在实时性方面有明显优势。     

NNERVE: Neural Network Extraction of Repetitive Vectors forElectromyography. I. Algorithm

Artificial neural network (ANN) based signal processing methods have been shown to have significant robustness in processing complex, degraded, noisy, and unstable signals. A novel approach to automated electromyogram (EMG) signal decomposition, using an ANN processing architecture, is presented here. Due to the lack of a priori knowledge of motor unit action potential (MUAP) morphology, the EMG decomposition must be performed in an unsupervised manner. An ANN classifier, consisting of a multilayer perceptron neural network and employing a novel unsupervised training strategy, is proposed. The ANN learns repetitive appearances of MUAP waveforms from their suspected occurrences in a filtered EMG signal in an autoassociative learning task. The same training waveforms are fed into the trained ANN and the output of the ANN is fed back to its input, giving rise to a dynamic retrieval net classifier. For each waveform in the data, the network discovers a feature vector associated with that waveform. For each waveform, classification is achieved by comparing its feature vector with those of the other waveforms. Firing information of each MUAP is further used to refine the classification results of the ANN classifier. Then, individual MUAP waveform shapes are derived and their firing tables are created