Two-stage subspace identification for softsensor design and disturbance estimation

Softsensors or virtual sensors are key technologies in industry because important variables such as product quality are not always measured on-line. In the present work, two-stage subspace identification (SSID) is proposed to develop highly accurate softsensors that can take into account the influence of unmeasured disturbances on estimated key variables explicitly. The proposed two-stage SSID method can estimate unmeasured disturbances without the assumptions that the conventional Kalman filtering technique must make. Therefore, it can outperform the Kalman filtering technique when innovations are not Gaussian white noises or the characteristics of disturbances do not stay constant with time. The superiority of the proposed method over the conventional methods is demonstrated through numerical examples and application to an industrial ethylene fractionator.     

Integration of self-organizing feature map and K-means algorithm for market segmentation

Cluster analysis is a common tool for market segmentation. Conventional research usually employs the multivariate analysis procedures. In recent years, due to their high performance in engineering, artificial neural networks have also been applied in the area of management. Thus, this study aims to compare three clustering methods: (1) the conventional two-stage method, (2) the self-organizing feature maps and (3) our proposed two-stage method, via both simulated and real-world data. The proposed two-stage method is a combination of the self-organizing feature maps and the K-means method. The simulation results indicate that the proposed scheme is slightly better than the conventional two-stage method with respect to the rate of misclassification, and the real-world data on the basis of Wilk's Lambda and discriminant analysis.Scope and purposeThe general idea of segmentation, or clustering, is to group items that are similar. A commonly used method is the multivariate analysis [4]. These methods consist of hierarchical methods, like Ward's minimum variance method, and the non-hierarchical methods, such as the K-means method. Owing to increase in computer power and decrease in computer costs, artificial neural networks (ANNs), which are distributed and parallel information processing systems successfully applied in the area of engineering, have recently been employed to solve the marketing problems. This study aims to discuss the possibility of integrating ANN and multivariate analysis. A two-stage method, which first uses the self-organizing feature maps to determine the number of clusters and the starting point and then employs the K-means method to find the final solution, is proposed. This method provides the marketing analysts a more sophisticated way to analyze the consumer behavior and determine the marking strategy. A case study is also employed to demonstrate the validity of the proposed method.     

Joint damage identification using Improved Radial Basis Function (IRBF) networks in frequency and time domain

In this paper, a novel two-stage Improved Radial Basis Function (IRBF) neural network technique is proposed to predict the joint damage of a fifty member frame structure with semi-rigid connections in both frequency and time domain. The effective input patterns as normalized design signature indices (NDSIs) in frequency domain and acceleration responses in time domain are simulated numerically from finite element analysis (FEA) by considering different levels of damage severity using Latin hypercube sampling (LHS) technique. The conventional RBF network is used in the first stage of IRBF network and in the second stage reduced search space moving technique is employed for accurate prediction with less than 3% error. The numerical simulation of the substructural joint damage identification of a fifty member frame structure with and without addition of 5% Gaussian random noise to the input patterns is presented and compared with conventional CPN–BPN hybrid method. The two-stage IRBF method is found to be superior in accuracy to conventional hybrid methods as well as to conventional RBF method. An important benefit of the proposed novel IRBF method is the significant reduction in the computational time with good accuracy of joint damage identification.     

OFDM-IDMA系统中低复杂度的多频偏抑制方法

提出了一种用于上行OFDM-IDMA系统中的低复杂度的多频偏抑制方法。在该方法中,多频偏在频域通过两个步骤得以抑制。频域接收信号分别与每个用户的频域频偏校正因子进行圆周卷积以达到抑制各用户自身频偏的目的,再进一步采取一种低复杂度的信号检测方法来消除其他用户频偏的影响。仿真结果表明,提出的低复杂度的多频偏抑制方法不但能够达到传统方法的性能,而且能有效地降低计算复杂度。     

考虑风场高维相依性的电网动态经济调度优化算法

大规模风电并网给电力系统的调度运行带来了巨大的挑战.本文提出改进的二阶段带补偿随机优化算法,用于考虑风场出力高维相依性的电网动态经济调度问题求解.首先,利用Copula函数描述多风场出力的高维相依性,获得多风场出力的联合分布;随后,引入二阶段带补偿随机优化算法解耦求解动态经济调度模型中的常规变量与随机变量;求解过程中,针对补偿费用期望值的计算受限于相依性风场维数,且对迭代方向指导不明确,导致算法收敛耗时长的问题,引入基于整体最小二乘的递推动态多元线性回归法对二阶段带补偿随机优化算法进行改进,通过补偿费用期望值的动态更新,促使两阶段模型的迭代求解快速收敛,克服了传统随机优化方法的"维数灾"弊端,使该算法能够用于考虑风场高维相依性的电网动态经济调度模型求解.最后利用IEEE 118节点系统和某省级实际电网系统验证了所提算法的有效性和实用性.     

工业机器人视觉定位系统高精度标定研究

分析了机器人视觉的主要标定方法,并在此基础上改进了传统的两步标定法.该方法先用两步法求出转换矩阵的初值再建立优化数学模型,优化计算采用快速的高斯-牛顿法.该方法不仅具有原来两步法的诸多优点,如自动、快速,而且彻底消除了第二步存在的累积误差,大大提高了标定精度.大量试验表明,标定精度明显优于传统的两步法.􀁽     

A direct synthesis tuning method of unstable first-order-plus-time-delay processes

A direct synthesis tuning method is proposed for the PI controller settings of unstable first-order-plus-time-delay processes. Unlike hitherto-known PI setting rules which often result in overshoots in time response or require the modification of the feedback control structure, this method ensures the overdamped response as desired while retaining the conventional PI control structure. This enhanced performance is possible by introducing a first-order set-point filter and applying simple rules for setting the values of the controller parameters without having any tuning parameters. The comparison with both conventional PI controllers and two-stage IMC method reveals that the proposed method produces not only smooth overdamped closed-loop response for set-point changes, but also fast regulatory control response for load changes. These responses are also shown to be quite robust against the uncertainties of the parameters as well as against the noise in the signal. The stability conditions for the processes having a large time delay or different ratios of time delay/time constant have been investigated as well. ©     

A two-stage MMSE multiuser decision feedback detector using successive/parallel interference cancellation

In this paper, we present a novel two-stage minimum-mean-squared-error (MMSE) multiuser decision feedback detector (DFD) for code division multiple access systems working in the frequency-selective multipath fading environment. The first stage of the proposed cascaded structure is the noise-predictive successive DFD (NP-S-DFD), in which the active users are detected successively using the conventional bell labs layered space-time (BLAST) ordering criterion. The second stage includes an adaptive successive/parallel DFD (SP-DFD), which uses the tentative decisions obtained at the first stage for multiuser interference cancellation and data detection. Therefore, the proposed two-stage DFD may be called noise-predictive successive SP-DFD (NP-S-SP-DFD). Simulation results are presented to demonstrate the substantial improvement in the bit error rate performance of NP-S-SP-DFD over the conventional single-stage and cascaded DFDs. It may be inferred that the proposed DFD provides additional performance gain, when the order in which the users are detected is optimized according to the BLAST ordering based on MMSE criterion.     

Biometric scores fusion based on total error rate minimization

This paper addresses the biometric scores fusion problem from the error rate minimization point of view. Comparing to the conventional approach which treats fusion classifier design and performance evaluation as a two-stage process, this work directly optimizes the target performance with respect to fusion classifier design. Based on a smooth approximation to the total error rate of identity verification, a deterministic solution is proposed to solve the fusion optimization problem. The proposed method is applied to a face and iris verification fusion problem addressing the demand for high security in the modern networked society. Our empirical evaluations show promising potential in terms of decision accuracy and computing efficiency.     

TD-SCDMA上行失步条件下一种改进的多用户检测算法

针对TD-SCDMA上行失步及强多址干扰的情况,设计了一种二级信道估计算法以及基于该信道估计算法的解相关干扰消除多用户检测算法。二级信道估计算法可以得到各接入用户主径的幅度以及时延,多用户检测算法根据信道估计的结果对接收数据进行解相关检测以及干扰消除。仿真结果表明,上行失步和强多址干扰情况下,该改进算法的误码率性能较传统的匹配滤波、联合检测以及解相关算法有较大的提升。     

An adaptive image segmentation method with visual nonlinearitycharacteristics

This correspondence is concerned with a method for image segmentation on the visual principle. The inconsistency between the conventional discriminating criterion and the human vision mechanism in perceiving an object and its background is analyzed and an improved discriminating criterion with visual nonlinearity is defined. A new model and an algorithm for image segmentation calculation are proposed based on the spatially adaptive principle of human vision and the relevant hypotheses about object recognition. This is a two-stage process of image segmentation. First, initial segmentation is realized with the bottom-up segmenting algorithm, followed by the goal-driven segmenting algorithm to improve the segmentation results concerning certain regions of interest. Experimental results show that, compared with some conventional and gradient-based segmenting methods, the new method has the excellent performance of extracting small objects from the images of natural scenes with a complicated background.     

面向边缘智能的两阶段对抗知识迁移方法

对抗样本的出现,对深度学习的鲁棒性提出了挑战.随着边缘智能的兴起,如何在计算资源有限的边缘设备上部署鲁棒的精简深度学习模型,是一个有待解决的问题.由于精简模型无法通过常规的对抗训练获得良好的鲁棒性,提出两阶段对抗知识迁移的方法,先将对抗知识从数据向模型迁移,然后将复杂模型获得的对抗知识向精简模型迁移.对抗知识以对抗样本的数据形式蕴含,或以模型决策边界的形式蕴含.具体而言,利用云平台上的GPU集群对复杂模型进行对抗训练,实现对抗知识从数据向模型迁移;利用改进的蒸馏技术将对抗知识进一步从复杂模型向精简模型的迁移,最后提升边缘设备上精简模型的鲁棒性.在MNIST,CIFAR-10和CIFAR-100这3个数据集上进行验证,实验结果表明：提出的这种两阶段对抗知识迁移方法可以有效地提升精简模型的性能和鲁棒性,同时加快训练过程的收敛性.     

A two-stage algorithm integrating genetic algorithm and modified Newton method for neural network training in engineering systems

A two-stage algorithm combining the advantages of adaptive genetic algorithm and modified Newton method is developed for effective training in feedforward neural networks. The genetic algorithm with adaptive reproduction, crossover, and mutation operators is to search for initial weight and bias of the neural network, while the modified Newton method, similar to BFGS algorithm, is to increase network training performance. The benchmark tests show that the two-stage algorithm is superior to many conventional ones: steepest descent, steepest descent with adaptive learning rate, conjugate gradient, and Newton-based methods and is suitable to small network in engineering applications. In addition to numerical simulation, the effectiveness of the two-stage algorithm is validated by experiments of system identification and vibration suppression.     

两级升降伺服运动系统的高精度位置控制

在一种两级升降伺服运动系统的两级机构转换过程中,系统的速度值存在一定突变量,使位移存在一定的偏差,影响系统的定位精度。通过建立系统的动力学方程,分析其动力学特性,提出了运动轨迹规划方法,减小两级机构转换过程中的速度突变带来的冲击影响,采用模糊PID进行定位控制,抑制系统中的扰动。仿真实验验证了所提出的方法是有效的,能够满足系统的高精度定位要求。     

基于BA-WPHM的滚动轴承两阶段剩余寿命预测方法

为了提高滚动轴承剩余寿命预测的准确性,根据滚动轴承运行过程的两阶段性特点,提出了一种基于蝙蝠算法(BA)和威布尔比例风险模型(WPHM)的滚动轴承两阶段剩余寿命预测方法。首先,构建基于WPHM的剩余寿命预测模型;其次,提出了两阶段极大似然估计法,建立新的似然函数,并利用BA算法进行求解,以提高参数估计的准确性;最后,建立BA-WPHM模型对滚动轴承进行剩余寿命预测。案例分析表明,相比于Newton-Raphson算法、自组织分层猴群算法(SHMA)和独特的自适应粒子群算法(UAPSO),提出的方法参数估计的准确性更高,剩余寿命的预测精度优于支持向量回归(SVR)方法,验证了所提方法的有效性,为滚动轴承维修决策的可行性提供了依据。     

Direction-of-Arrival Estimation of Ultra-Wideband Signals in Narrowband Interference Environment Based on Power Inversion and Complex-Valued Neural Networks

We propose two-stage null-steering direction-of-arrival (DoA) estimation of ultra wideband (UWB) signals with power inversion algorithm and complex spatio-temporal neural network (CVSTNN). This method can estimate DoA more accurately than conventional methods in narrowband interference (NBI) environment. For null steering in UWB systems, it is necessary to adjust the amplitude and phase of tapped delay lines (TDLs) of CVSTNN. However, with a conventional CVSTNN, it often fails to estimate the arrival direction because of the NBI. We aim to reduce the influence of NBI in the learning process to avoid falling into a local solution by setting the initial weights of the TDLs with power inversion. In simulation results, it is shown that the two-stage method can realize higher DoA estimation accuracy than conventional methods.     

精确分类的视角无关人脸检测方法与硬件加速体系结构

为了对垂直于图像平面[-90°,90°]和图像平面内360°范围的人脸姿态进行快速准确的检测分类,提出一种精确分类的视角无关人脸检测方法和可重构硬件体系结构.设计了由多个检测节点组成的树形检测器框架,并将多个姿态区间的分类问题采用向量式共享输出空间的方式统一起来,提出一种两段式Boosting方法对检测节点进行训练;挖掘了检测过程的时间空间并行性,进而设计了一种高度并行的可重构硬件体系结构模板,通过对体系结构模板进行动态配置,实现了硬件代价、检测精度和速度的平衡.实验结果表明,与已有方法相比,文中方法具有较高的精度与速度;对于160×120～800×600分辨率范围内的图像,该方法在FPGA上的硬件实现与在PC上的软件实现的执行时间加速比为14.68～20.86.     

含齿隙双电机伺服系统未知参数的两阶段辨识

针对含齿隙的双电机伺服系统,提出一种两阶段辨识法辨识双电机系统未知参数以及齿隙非线性环节的死区参数.针对电机转动惯量、等效粘性摩擦系数以及齿隙大小未知的情况,运用Legendre多项式将双电机伺服系统中的齿隙模型分段化,根据最小二乘法辨识双电机伺服系统参数.最后,通过仿真验证两阶段辨识法的有效性,验证结果表明,两阶段辨识法能够较准确地辨识电机参数和齿隙参数.     

面向可制造性的两阶段一维优化下料方法

针对诸多优化下料方法片面追求高原材料利用率,而对实际切割加工成本考虑不足的现状,提出一种既维持高原材料利用率又使下料方案可制造性好的一维优化下料方法.下料方案的可制造性从切割方式种类数和每种切割方式中套裁零件种类数两方面来衡量,基于此提出了非定长优化和定长优化相结合的两阶段一维优化下料方法,并采用两阶段列生成算法实现.最后通过实例验证了文中方法的实用性和有效性.     

Closed-loop balancing for a class of non-linear singularly perturbed systems

The aim of this article is to investigate the closed-loop balancing reduction method for a class of non-linear singularly perturbed systems. We show that the well-known two-stage strategy involved commonly within the singular perturbation theory can be used to derive an approximate closed-loop balancing. The proposed two-stage method avoids the difficult task of solving high dimensional and ill conditioned non-linear Hamilton–Jacobi equation due to the presence of the small perturbation parameter.