显微散焦粒子识别与追踪测速

根据三孔挡板散焦成像的原理,使用高速散焦显微粒子测速装置开展三维显微粒子追踪测速研究。在粒子散焦像识别的过程中利用了其对应三角模型相似的特点,通过散焦像斑灰度呈二维高斯分布特征计算其质心。在粒子三维位置测量算法分析的过程中选择了多达29颗的样品粒子,对29组不同深度的数据采用线性拟合的方式进行粒子深度方向的标定,并用二元多项式对870组数据拟合获得了关于粒子平面位置漂移的补偿函数。针对长直微通道内雷诺数Re分别为0.05和0.1的流场进行了验证性测量,采用20′0.4显微物镜,使用高速CMOS相机对直径为2mm的粒子进行追踪。结果显示,计算出的示踪粒子速度分布与数值仿真曲线吻合良好。     

An image-shifting technique based on grey-scale classification for particle image velocimetry

The image-shifting techniques are used to overcome the directional ambiguity of particle image displacement in the measurement of particle image velocimetry (PIV). This paper proposes an image-shifting technique based on grey-scale classification for PIV. By calculating the unified grey-scale statistical frequency of each interrogated unit, the directional ambiguity is resolved without any special requirement of the camera, and the particle image displacement is calculated synchronously. This image-shifting technique can be realized by controlling the difference in the light intensity of two lasers. Using this new technique, a PIV system was developed and used to measure the diesel spray flow. The displacement vector map of fuel particle in the spray flow was obtained, and the structure of the spray flow was investigated. The application confirmed that the image-shifting technique is viable and effective.     

基于混沌神经网络的盲检测改进新算法

针对Hopfield神经网络的多起点问题,提出了一种新的基于混沌神经网络的盲信号检测算法,实现了二进制移相键控信号盲检测.据此进一步提出双sigmoid混沌神经网络模型,构造了新的能量函数,且证明了该模型的稳定性,并对网络参数进行配置.仿真实验表明:混沌神经网络能够避免局部极小点且具备较强的抗噪性能,双sigmoid混沌神经网络则继承了其所有的优点,且其收敛速度更快,仅需更短的接收数据即可到达全局真实平衡点,从而降低了算法的计算复杂度,减少了运行时间.     

Prediction of airblast-overpressure induced by blasting using a hybrid artificial neural network and particle swarm optimization

Blasting is an inseparable part of the rock fragmentation process in hard rock mining. As an adverse and undesirable effect of blasting on surrounding areas, airblast-overpressure (AOp) is constantly considered by blast designers. AOp may impact the human and structures in adjacent to blasting area. Consequently, many attempts have been made to establish empirical correlations to predict and subsequently control the AOp. However, current correlations only investigate a few influential parameters, whereas there are many parameters in producing AOp. As a powerful function approximations, artificial neural networks (ANNs) can be utilized to simulate AOp. This paper presents a new approach based on hybrid ANN and particle swarm optimization (PSO) algorithm to predict AOp in quarry blasting. For this purpose, AOp and influential parameters were recorded from 62 blast operations in four granite quarry sites in Malaysia. Several models were trained and tested using collected data to determine the optimum model in which each model involved nine inputs, including the most influential parameters on AOp. In addition, two series of site factors were obtained using the power regression analyses. Findings show that presented PSO-based ANN model performs well in predicting the AOp. Hence, to compare the prediction performance of the PSO-based ANN model, the AOp was predicted using the current and proposed formulas. The training correlation coefficient equals to 0.94 suggests that the PSO-based ANN model outperforms the other predictive models.     

人工神经网络在建筑声学中的应用

本文对人工神经网络的历史作了简单回顾，并对它在建筑声学领域中的应用状况作了阐述，同时提出了有待进一步探讨的若干问题。     

Particle sizing by multiangle light-scattering data using the high-order neural networks

The problem of retrieval of size and refractive index of a spherical particle by angular dependence of scattered light in scanning flow cytometry is considered. For its solution, the high-order neural networks are used. We restricted the range of angles available for measurement from 10° to 60°. The retrieval errors of characteristics of nonabsorbing particles were investigated at the ranges of the radius and relative refractive index 0.6–10.6 μm, and 1.02–1.38, respectively.     

Partially connected feedforward neural networks on Apollonian networks

This paper presents a novel and data-independent method to construct a type of partially connected feedforward neural network (FNN). The proposed networks, called Apollonian network-based partially connected FNNs (APFNNs), are constructed in terms of the structures of two-dimensional deterministic Apollonian networks. The APFNNs are then applied in various experiments to solve function approximation, forecasting and classification problems. Their results are compared with those generated by partially connected FNNs with random connectivity (RPFNNs), different learning algorithm-based traditional FNNs and other benchmark methods. The results demonstrate that the proposed APFNNs have a good capacity to fit complicated input and output relations, and provide better generalization performance than traditional FNNs and RPFNNs. The APFNNs also demonstrate faster training speed in each epoch than traditional FNNs.     

Defocus and binocular vision based stereo particle pairing method for 3D particle tracking velocimetry

We propose a new method, based on the depth-from-defocus technique and binocular vision, for solving the stereo particle pairing problem in 3D particle tracking velocimetry (PTV). Firstly, the apparent particle depth is measured with a single camera, using the depth-from-defocus technique. Secondly, a strict mathematical model of the particle-to-particle correspondence relationship between the left and right images, taking into account the refractions at the interfaces in the optical path, is presented, with the assumption that the apparent particle depth is measured. Thirdly, based on the apparent particle depth and particle-to-particle correspondence relationship, the epipoplar line is truncated into a short line segment by cutting off, where the apparent particle depth extends beyond its estimated range. For the first time, the range of the blur circle radius is employed as an additional stereo particle pairing constraint. Finally, the optimal pairing particle is selected by applying the epipolar line segment and blur circle radius constraints. The experimental results show that the rate of correct pairing is significantly improved compared with the epipolar line nearest neighbor analysis, especially when the particle density is increasing.     

基于粒子滤波的多普勒信息辅助目标定位跟踪算法

多基地声呐探测系统主要通过测量回波的时延和方位信息进行目标定位与跟踪,定位精度受声速、时延和方位测量误差的影响较大,可以通过多普勒信息辅助进一步提高定位跟踪精度.现有的多普勒信息辅助定位跟踪算法多适用于单基地声呐系统,多基地中的多普勒测量值与目标状态的关系更为复杂,需要研究新的融合方法.该文提出了一种适用于多基地声呐系...     

Three-dimensional particle image velocimetry: a low-cost 35 mm angular stereoscopic system for liquid flows

A low-cost 35 mm PIV stereoscopic system for liquid flows is presented which has an imaging component cost under US$9000. The system uses an angular configuration, rotating mirror image shifting and in-situ calibration techniques. Image processing algorithms based on cross correlation and bicubic interpolation are also used to calculate the 3D data from the PIV images. Results from an error analysis have shown the system to have in plane errors ranging from 4.15 to 5.95% and out of plane errors of 7.01% providing an f-number of f2 is fixed for all imaging. Subsequent application of the system to a flow field generated by a free falling sphere in wheat syrup have produced results which when compared to previous flow visualisation give good qualitative agreement. Suggested improvements to the PIV system costing US$1300 would allow operation at f-numbers down to f by modifying the cameras for the Scheimpflug condition and using a corrective liquid prism.     

Optical coherence tomography based particle image velocimetry (OCT-PIV) of polymer flows

The measurement of spatially resolved velocity distributions is crucial for modelling flow and for understanding properties of materials produced in extrusion processes. Traditional methods for flow visualization such as particle image velocimetry (PIV) rely on optically transparent media and cannot be applied to turbid polymer melts. Here we present optical coherence tomography as an imaging technique for PIV data processing that allows for measuring a sequence of time resolved images even in turbid media. Time-resolved OCT images of a glass-fibre polymer compound were acquired during an extrusion process in a slit die. The images are post-processed by ensemble cross-correlation to calculate spatially resolved velocity vector fields. The results compared well with velocity data obtained by Doppler-OCT. Overall, this new technique (OCT-PIV) represents an important extension of PIV to turbid materials by the use of OCT.     

Dim moving target tracking algorithm based on particle discriminative sparse representation

The small dim moving target usually submerged in strong noise, and its motion observability is debased by numerous false alarms for low signal-to-noise ratio (SNR). A target tracking algorithm based on particle filter and discriminative sparse representation is proposed in this paper to cope with the uncertainty of dim moving target tracking. The weight of every particle is the crucial factor to ensuring the accuracy of dim target tracking for particle filter (PF) that can achieve excellent performance even under the situation of non-linear and non-Gaussian motion. In discriminative over-complete dictionary constructed according to image sequence, the target dictionary describes target signal and the background dictionary embeds background clutter. The difference between target particle and background particle is enhanced to a great extent, and the weight of every particle is then measured by means of the residual after reconstruction using the prescribed number of target atoms and their corresponding coefficients. The movement state of dim moving target is then estimated and finally tracked by these weighted particles. Meanwhile, the subspace of over-complete dictionary is updated online by the stochastic estimation algorithm. Some experiments are induced and the experimental results show the proposed algorithm could improve the performance of moving target tracking by enhancing the consistency between the posteriori probability distribution and the moving target state.     

Study of interactions between liquid vortices and bubbles by simultaneous particle image velocimetry and laser-induced fluorescence tracking

Extensive experimental research has been conducted using the particle image velocimetry (PIV), laser-induced fluorescence (LIF) imaging and backlit photographic recordings to study the complex interactions between coherent vortex structures created in the shear layer of jets and the bubbles. Triggering of the naturally-developing instabilities of the shear layer by a thin, pulsed annular flow surrounding the jets allowed the creation of large, orderly structures with controllable frequency and phase. Synchronization of the triggering with data acquisition permitted phase averaging of the data and revealed several interesting phenomena. In particular, the evolution of large vortices and bubble fields could be tracked and the interactions could be studied. The horizontal and vertical velocity components of the liquid and bubble fields and the vertical velocity of both the vortex and bubble rings that were created were measured by the PIV. LIF and image recordings have been combined to visualize bubble trapping inside large eddy structures.     

基于自归一化神经网络的脉冲星候选体选择

脉冲星候选体选择是脉冲星搜寻任务中的重要步骤.为了提高脉冲星候选体选择的准确率,提出了一种基于自归一化神经网络的候选体选择方法.该方法采用自归一化神经网络、遗传算法、合成少数类过采样这三种技术提升对脉冲星候选体的筛选能力.利用自归一化神经网络的自归一化性质克服了深层神经网络训练中梯度消失和爆炸的问题,大大加快了训练速度.为了消除样本数据的冗余性,利用遗传算法对脉冲星候选体的样本特征进行选择,得到了最优特征子集.针对数据中真实脉冲星样本数极少带来的严重类不平衡性,采用合成少数类过采样技术生成脉冲星候选体样本,降低了类不平衡率.以分类精度为评价指标,在3个脉冲星候选体数据集上的实验结果表明,本文提出的方法能有效提升脉冲星候选体选择的性能.     

Infrared small target tracking based on sample constrained particle filtering and sparse representation

Infrared search and track technology for small target plays an important role in infrared warning and guidance. In view of the tacking randomness and uncertainty caused by background clutter and noise interference, a robust tracking method for infrared small target based on sample constrained particle filtering and sparse representation is proposed in this paper. Firstly, to distinguish the normal region and interference region in target sub-blocks, we introduce a binary support vector, and combine it with the target sparse representation model, after which a particle filtering observation model based on sparse reconstruction error differences between sample targets is developed. Secondly, we utilize saliency extraction to obtain the high frequency area in infrared image, and make it as a priori knowledge of the transition probability model to limit the particle filtering sampling process. Lastly, the tracking result is brought about via target state estimation and the Bayesian posteriori probability calculation. Theoretical analyses and experimental results show that our method can enhance the state estimation ability of stochastic particles, improve the sparse representation adaptabilities for infrared small targets, and optimize the tracking accuracy for infrared small moving targets.     

Application of artificial neural networks for the determination of proteins with CPA-pI by rayleigh light scattering technique

The determination of proteins with 2-(4-chloro-2-phosphonophenylazo)-7-(4-iodophenylazo)-1,8-dihydroxynaphthalene-3,6-disulfonic acid (CPA-pI) by Rayleigh light scattering (RLS) was studied in this paper. The weak RLS of CPA-pI and BSA can be enhanced greatly by the addition of Al³⁺ at the pH 5.6 and an enhanced RLS signal was produced at 365-385 nm. Based on the reaction of CPA-pI, Al³⁺ and proteins, a new quantitative determination method for proteins has been developed. The effect of three variables for the determination of proteins was optimized by means of artificial neural networks (ANNs) using extended delta-bar-delta (EDBD) algorithms with the optimal network structure of 3-5-1. This method is very sensitive (2.5-35.4 μg/ml for bovine serum albumin (BSA)), rapid (<2 min), simple (one step) and tolerance of most interfering substances. Six samples of protein in human serum were determined and the maximum relative error is no more than 2% and the recovery is between 95% and 105%.     

Modelling the soundscape quality of urban waterfronts by artificial neural networks

The renewal of the urban waterfronts has become a major focus of attention for politicians and decision makers in the city’s management programs. The recognition of the patterns that define the waterfronts’ identity is essential to select new strategies of intervention for the environmental recovery. In order to create adequate environments for everyday life within a sustainable development, new links between human senses, human perception and design need to be created. Within this wide approach, the landscape and the soundscape play a significant role and can become a key driving force in the implementation of the changes. New techniques have to be tested to identify the sonic and visual parameters capable to explain the specificity of a waterfront. With this purpose, an artificial neural network (ANN) was developed, and the relative importance of the input variables was evaluated. The collected database was also analysed by multiple linear regression (MLR) to compare the outcomes of both models. The urban waterfront of Naples (Italy) was chosen as case study. The results obtained show that the performance of the neural network is better than the one of the linear regression (rANN = 0.949, rMLR = 0.639). The interpretation of the relative importance method is also quite satisfactory in the ANN.     

混沌映射和神经网络互扰的新型复合流密码

提出了一种将新型的神经网络互学习模型和常见的多混沌系统融合互扰的复合流密码方案. 首先利用三个Logistics混沌映射产生的随机序列作为神经网络互学习模型中三个 隐含层神经元的随机输入, 神经网络交互学习达到内部权值同步后, 再将同步权值映射为随机序列并与三个Logistics序列复合产生最终的密钥流. 实验表明, 产生的密钥流具有更好的随机性, 混沌流加密应用效果好. 关键词： 混沌映射 神经网络 权值同步 随机密钥流     

Evaluating practical measurements of fire-induced vent flows with stereoscopic PIV

Stereoscopic particle image velocimetry (SPIV) was applied to a fire-induced doorway flow to provide the velocity field for computations of the mass flow rate of air into an enclosure. For a flow of uniform temperature and concentration, the technique met all of the requirements to provide the best estimate of the mass flow rate. Simultaneous measurements of vertical distributions of velocity and temperature were also conducted with conventional vent flow techniques, bi-directional probes and thermocouples. Correction factors for mass flow rate computations using the conventional techniques were determined based on comparisons to the SPIV results. An average correction factor of unity was determined for the bi-directional probe technique thus further confirming the utilization of velocity distributions acquired using the technique in mass flow rate computations. An average correction factor of 0.69 was determined for mass flow rates computed from vertical temperature distributions inside and outside the enclosure. This agrees with average correction factors determined in previous studies. The results from the present study suggest that the conventional techniques, which are practical and affordable for routine fire testing, may be applied with greater confidence for fires up to 500 kW.     

Random walk particle tracking simulations of non-Fickian transport in heterogeneous media

Derivations of continuum nonlocal models of non-Fickian (anomalous) transport require assumptions that might limit their applicability. We present a particle-based algorithm, which obviates the need for many of these assumptions by allowing stochastic processes that represent spatial and temporal random increments to be correlated in space and time, be stationary or non-stationary, and to have arbitrary distributions. The approach treats a particle trajectory as a subordinated stochastic process that is described by a set of Langevin equations, which represent a continuous time random walk (CTRW). Convolution-based particle tracking (CBPT) is used to increase the computational efficiency and accuracy of these particle-based simulations. The combined CTRW–CBPT approach enables one to convert any particle tracking legacy code into a simulator capable of handling non-Fickian transport.