基于PCAU-Net的快速多通道磁共振成像方法

多通道磁共振成像方法采用多个接收线圈同时欠采样k空间以加快成像速度,并基于后处理算法重建图像,但在较高加速因子时,其图像重建质量仍然较差．本文提出了一种基于PCAU-Net的快速多通道磁共振成像方法,将单通道实数U型卷积神经网络拓展到多通道复数卷积神经网络,设计了一种结构不对称的U型网络结构,通过在解码部分减小网络规模以降低模型的复杂度．PCAU-Net网络在跳跃连接前增加了1×1卷积,以实现跨通道信息交互．输入和输出之间利用残差连接为误差的反向传播提供捷径．实验结果表明,使用规则和随机采样模板,在不同加速因子时,相比常规的GRAPPA重建算法和SPIRiT重建方法,本文提出的PCAU-Net方法可高质量重建出磁共振复数图像,并且相比于PCU-Net方法,PCAU-Net减少了模型参数、缩短了训练时间．     

Delay optimization and energy balancing algorithm for improving network lifetime in fixed wireless sensor networks

Since wireless in terms of energy-restricted processes, dispersion radii, processing power limitations, buffers, bandwidth-limited connections, active network topologies, and network stream of traffic outlines, sensor networks provide difficult design issues. The number of hops and latency are decreased if there is a relay mote because it interacts directly with relay motes that are closer to the destination mote. The tremendous intensive research in the area of Wireless Sensor Networks (WSN) has gained a lot of significance among the technical community and research. The job of WSN is to sense the data using sensor motes, pass on the data to the destination detection mote which is associated with a processing center and can be used in multiple spans of Internet of Things (IoT) applications. Wireless sensor network has a set of sensor motes. By making use of sensor mote placement strategy all the sensor motes are spread in an area with each mote having its own exceptional location. Internet of things applications are delay sensitive those applications have a challenge of forming the complete path at a lower delay constraint. The proposal is to modify the game theory energy balancing algorithm by making use of relay motes so that overall network lifetime is increased. It has been proved that modified GTEB is better with respect to existing algorithms in terms of delay, figure of hops, energy depletion, figure of alive motes, figure of dead motes, lifespan ratio, routing overhead and throughput.     

基于声发射和GAN-CNN的铝合金管道法兰 连接松动泄漏检测*

面向管道法兰连接松动引起的泄漏检测需求,为解决数据样本不足和减少特征指标手动选取的繁琐环节。本文,考虑到生成性对抗网络（GAN）作为数据扩充工具,已被证明能够生成与真实数据相似的样本数据。同时,卷积神经网络（CNN）作为一种深度学习方法,为自动提取数据的特征提供了一种有效的方法。开展了基于GAN和CNN的铝合金管道法兰连接松动泄漏检测研究。首先,搭建管道泄漏标定和数据采集实验台,利用声发射技术获取不同等级的原始泄漏信号。其次,采用GAN生成样本数据扩充原始数据。同时,为了评估生成模型的性能,引入统计特评估生成质量。最后,将生成的样本数据与原始数据设置为不同训练集,基于卷积神经网络构建智能分类检测模型,应用于管道泄漏检测。同时,分类检测结果与小样本智能分类方法SVM进行了比较,实验结果表明,基于GAN和CNN构建的智能分类模型可显著提高管道法兰连接松动泄漏检测精度。     

近红外光谱技术快速鉴别地沟油与食用植物油的研究

地沟油检测是我国食品安全最为关注的话题之一,它给人们的生活健康带来了极大的危害。国内现有的检测手段也仅停留在定性检测水平上,只能确定地沟油的有无,还难以进行定量检测。本实验利用近红外光谱技术与光纤传感技术相结合的新方法对勾兑混合油中地沟油的含量进行了定量分析。将煎炸老油与九三大豆油按照一定的体积比进行勾兑,共计50个样本,采集其近红外透射光谱,分别采用偏最小二乘法(PLS)和BP人工神经网络建立了煎炸老油含量的定量分析模型,校正集决定系数分别为0.908和0.934,验证集决定系数分别为0.961和0.952,均方估计残差(RMSEC)为0.184和0.136,预测均方根误差(RMSEP)都为0.111 6,符合应用要求,同时还结合主成分分析法(PCA)对煎炸老油与食用植物油进行了鉴别,识别准确率为100%。实验研究证明近红外光谱技术不仅可以准确快速的定性分析地沟油, 还能定量的检测地沟油的含量,在油脂的检测方面具有很大的应用前景。     

Trigonometrical sums connected with the chiral Potts model,Verlinde dimension formula,two-dimensional resistor network,and number theory

We have recently developed methods for obtaining exact two-point resistance of the complete graph minus N$N$ edges. We use these methods to obtain closed formulas of certain trigonometrical sums that arise in connection with one-dimensional lattice, in proving Scott’s conjecture on permanent of Cauchy matrix, and in the perturbative chiral Potts model. The generalized trigonometrical sums of the chiral Potts model are shown to satisfy recursion formulas that are transparent and direct, and differ from those of Gervois and Mehta. By making a change of variables in these recursion formulas, the dimension of the space of conformal blocks of SU(2)$SU\left(2\right)$ and SO(3)$SO\left(3\right)$ WZW models may be computed recursively. Our methods are then extended to compute the corner-to-corner resistance, and the Kirchhoff index of the first non-trivial two-dimensional resistor network, 2×N$2\times N$. Finally, we obtain new closed formulas for variant of trigonometrical sums, some of which appear in connection with number theory.     

Multi-focus image fusion based on robust principal component analysis and pulse-coupled neural network

Multi-focus image fusion combines multiple source images with different focus points into one image, so that the resulting image appears all in-focus. In order to improve the accuracy of focused region detection and fusion quality, a novel multi-focus image fusion scheme based on robust principal component analysis (RPCA) and pulse-coupled neural network (PCNN) is proposed. In this method, registered source images are decomposed into principal component matrices and sparse matrices with RPCA decomposition. The local sparse features computed from the sparse matrix construct a composite feature space to represent the important information from the source images, which become inputs to PCNN to motivate the PCNN neurons. The focused regions of the source images are detected by the firing maps of PCNN and are integrated to construct the final, fused image. Experimental results demonstrate that the superiority of the proposed scheme over existing methods and highlight the expediency and suitability of the proposed method.     

Synchronization of time varying delayed complex networks via impulsive control

In this paper, we investigate the problem of synchronization for the time varying delayed complex dynamical networks via impulsive control method, several sufficient synchronization conditions are given, and we consider the impulsive control matrices are time varying delayed matrices. Furthermore, we found impulsive control does not always play an active role in synchronization although impulsive control strategy is cheaper and simpler than other control strategy. Finally, numerical simulations are also given to demonstrate the effectiveness of the proposed schemes.     

Performance enhanced down-stream signalling for next generation long-reach 10 Gbit/s passive optical networks

In this paper, we have analyzed the signal processing methods both in digital and optical domain to enhance the transmission performance of downstream signalling in long reach passive optical networks (LR-PONs). The impact of non-linear (NL) equalization through signal processing, i.e. Volterra Equalization (VE), Digital Backpropagation (BP) and Optical Phase Conjugation with Non-linearity Module (OPC-NM) is investigated, in 10 Gbit/s (XG) DP-QPSK long-reach wavelength division multiplexed (WDM) PONs without midspan repeaters over 120 km standard single mode fibre (SMF) link for down-stream signals. Due to the compensation of optical Kerr effects, the sensitivity penalty is reduced to 2 dB by BP algorithm, 1.5 dB by VE algorithm and 2.69 dB by OPC-NM. Moreover, with the implementation of NL equalization technique we are able to get the transmission distance of 126.6 km SMF for the 1:1024 split-ratio at 5 GHz channel spacing in the non-linear region. Furthermore, the concept of super passive optical network (S-PON) is also evaluated, which involves a repeater stage consisting of optical amplifiers, to study the feasibility for receiver side signal processing and simplification.     

基于脉冲耦合神经网络的弹簧卡箍缺陷检测

传统的弹簧卡箍缺陷多为产后人工全检,存在漏检与缺陷率上升等现象,这不但会使成本上升、也对人力资源提出了考验。为此实现自动实时在线全检就成为急需解决的课题,设计了基于机器视觉的弹簧卡箍在线自动检测系统,该系统安装在弹簧卡箍流水线两侧,搭建特定光源,通过激光传感器外部触发工业相机对其表面进行图像捕获,送上位机进行缺陷判定与定位,最后通过RS485将判定结果送下位机来控制剔除机制。实验结果显示：该系统采用改进的脉冲神经网络(PCNN)能准确提取目标缺陷区域并对缺陷进行判定,可在0.348 s每个零件的速度下,检测出弹簧卡箍表面大于10像素的缺陷。通过对不同弹簧卡箍进行检测验证实验,证明了PCNN算法对缺陷分割的准确性和有效性。     

电机温度时滞耦合系统自抗扰控制仿真研究

电机温度过高会造成绝缘性能老化,电机安全性能下降。电机控制系统是典型的非线性系统,电机温度也因此具有时滞性和耦合性的特点,难以建立准确的数学模型。传统的方法对电机温度的控制精度较差,从而导致电机温度失控。为此,提出基于BP神经网络自抗扰控制算法的电机时滞耦合关系下温度控制方法。将BP神经网络与PID控制方法相结合建立电机温度网络自抗扰控制器模型,利用梯度下降法修正电机温度控制器模型的权值系数,从而实现了BP神经网络自抗扰控制器参数的实时调整。实验结果表明,利用BP神经网络自抗扰算法进行电机时滞耦合关系下温度调整,能够有效提高控制的精确度,缩短了控制过程中的时间延时。