基于遗传算法的ARMA模型定阶新技术

针对时间序列分析与预测中最为常见的ARMA模型的定阶问题,在分析传统定阶方法缺点的基础上,提出了用遗传算法确定ARMA(n,m)模型的自回归阶数n和滑动平均阶数m的新方法。首先由ARMA模型的预测值与实测值定义平均相对变动值(Average relative variance,ARV),并根据其建立遗传算法的适应度函数;然后选取适当的种群数、交叉效、变异率及进化代数;通过逐代进化,得到最优的ARMA模型。最后,通过太阳黑子数据验证了基于遗传算法的ARMA模型定阶新技术的有效性和实用性。     

基于混合优化策略的自回归-滑动平均模型建模

自回归一滑动平均(ARMA)模型参数估计一直是ARMA模型建模问题的难点和重点,目前的模型参数估计方法都采用传统最小二乘法及其推广算法,预测精度低.采用基于混合优化策略的遗传模拟退火算法进行ARMA模型参数估计,克服了传统算法的缺点,并在此基础上利用遗传模拟退火算法可以确定ARMA阶次的特点,提出基于混合优化策略的ARMA模型建模方法.利用这种建模方法和传统建模方法对组合炮控系统精度进行建模比较,证明基于混合优化策略的ARMA模型建模方法收敛快,精度高.     

基于FARIMA模型的Internet时延预测

针对Internet时延具有自相似性这一特点,采用自回归分数滑动平均模型(fractal autoregressive integrated moving aver-age,FARIMA)对Internet时延建模,提出了基于概率上限的Internet时延预报方法,即保证实际时延按一定概率在预测时延范围之内。通过对实测时延数据进行预测对比,结果表明基于FARIMA模型的预测效果要优于基于ARMA(auto regnessive and mov-ing average)模型的预测效果。     

Adaptive modelling of transient vibration signals

Conventional vibration signal processing techniques are most suitable for stationary processes. However, most mechanical faults in machinery reveal themselves through transient events in vibration signals. Time-series modelling, including autoregressive moving average (ARMA) modelling and autoregressive (AR) modelling, is an efficient approach for transient signal analysis. Based on the adaptive prediction technique, this paper applies the principle of the adaptive line enhancer (ALE) to the modelling of transient vibration signals. The time-series models, adaptive algorithms and the rational time–frequency transfer function are investigated in the paper. Simulation and experimental studies with different time–frequency–amplitude distributions and transient vibration responses are described. The results show that the adaptive modelling method can trace the time–frequency signal and extract dynamic features such as time–frequency distributions and time–amplitude distributions from sample signals. Given the simple programming and potentially easy implementation in on-line applications, this method should have application in machine monitoring and fault diagnosis.     

递进自回归预测方法

提出递进自回归预测方法,其中包括递进自回归模型、递进自回归滑动平均模型、递进时变自回归模型、递进时变自回归滑动平均模型、递进回归一自回归模型。建立时间序列的递进预测公式,给出其最佳无偏预测,并推导出递进均方误差计算公式和高置信水平的递进预测区间估计。该方法是以逐步线性形式表示的一种非线性预测,既具有线性预测的简单性,又具有非线性预测精度高的特点。它不但可用于平稳时间序列预测,而且还可用于非平稳时间序列预测、确定性时间序列预测和小样本预测。此外,文中还给出时问序列线性组合及乘积的预测方法。并通过加权累加、倒数变换等方法,对观测值进行映射变换,使其呈现出更强的规律性,以进一步提高预测精度。     

基于ARMA模型的气固流化床过程监控

基于ARMA模型，提出了一种新的气固流化床流态化过程监控方案。利用Honeywell公司生产的24PC系列压力／差压传感器获取气固流化床压力波动信号，拟合n阶自回归m阶滑动平均模型ARMA(n，m)。通过分析，确定自回归阶数n的阈值，实现流态化过程监控。监控在实验室的气固流化床实验装置上进行，初步实验表明，方案用于气固流化床流态化过程监控是有效的。     

Two-dimensional ARMA model order determination

Determination of the order of a model is the key first step towards modeling any dynamic systems, particularly two-dimensional processes. In this paper, a new method for two-dimensional (2-D) Gaussian ARMA model order determination is proposed. In the proposed method, the AR and MA orders are first independently determined, then the procedure for model order determination of the 2-D ARMA model is outlined. The model is assumed to be causal, stable, linear, and spatial shift-invariant with p₁×p₂ quarter-plane (QP) support. Numerical simulations are presented to show the effectiveness of the proposed new approach.     

Image signal-to-noise ratio estimation using Shape-Preserving Piecewise Cubic Hermite Autoregressive Moving Average model

We propose to cascade the Shape-Preserving Piecewise Cubic Hermite model with the Autoregressive Moving Average (ARMA) interpolator; we call this technique the Shape-Preserving Piecewise Cubic Hermite Autoregressive Moving Average (SP2CHARMA) model. In a few test cases involving different images, this model is found to deliver an optimum solution for signal to noise ratio (SNR) estimation problems under different noise environments. The performance of the proposed estimator is compared with two existing methods: the autoregressive-based and autoregressive moving average estimators. Being more robust with noise, the SP2CHARMA estimator has efficiency that is significantly greater than those of the two methods.     

MULTICHANNEL IDENTIFICATION OF AIRCRAFT SKELETON STRUCTURES UNDER UNOBSERVABLE EXCITATION: A VECTOR AR/ARMA FRAMEWORK

A comprehensive autoregressive (AR) and linear multistage autoregressive moving average (LMS-ARMA) framework for effective multichannel identification of structures under unobservable excitation is introduced and assessed via the paradigm of aircraft skeleton structure identification. This framework utilises fully parametrised vector AR and ARMA models estimated via linear regression (LR) and a newly developed linear multistage (LMS) method, respectively, statistical model order selection, and structural mode distinction via a dispersion analysis methodology. The framework's effectiveness and limitations are examined via the identification of an experimental and a simulated aircraft skeleton structure, as well as comparisons with non-parametric Welch autospectral density estimation. The results of the study indicate the framework's effectiveness in selecting the necessary model orders, as well as in distinguishing and accurately estimating most structural modes, including closely spaced and ‘local’ modes. The AR an LMS-ARMA methods achieve generally similar accuracy, but the latter leads to lower order models, fewer spurious modes, and less ambiguous ‘stabilisation’ diagrams.     

基于RBF的AR模型在数控振动仿真中的应用

为了更加有效地提高生产效率,数控加工仿真系统在进行几何仿真的同时,还要对加工系统的动态性能进行分析。提出了一个对数控加工过程中振动信号仿真的新方法,可以实现加工状态下的车削振动信号的仿真。该方法应用RBF神经网络预测AR模型的参数,从而建立不同切削条件下的振动仿真模型。实验表明,仿真信号和测量信号可以很好的吻合。     

Statistical modeling of mains zero crossing variation in powerline communication

In this paper, authors investigate statistical modeling of measured mains Zero Crossing (ZC) non idealities in narrowband powerline communication systems (PLC) using time series approach based on autoregressive moving average model (ARMA). For this purpose, Box Jenkins analysis steps are deployed for detected ZC impulsive variations. Estimated models exhibit a good fit based on R-square metric reaching 90%. This modeling approach is extended to three measurement environment: in home, in lab and rural locations. Obtained models are useful for NB-PLC channel emulator implementation.     

TVAR在非平稳工况转子故障诊断中的应用

研究了基于BP网络（ANN）的时变参数自回归模型（TVAR）及其在非平稳工况旋转机械故障诊断中的应用。首先提出了一种基于BP算法的TVAR参数辨识方法，然后利用TVAR方法对一非线性调频仿真信号进行时频分析，并与典型时频分析方法短时傅里叶变换（STFT）及Choi—Williams分布（CWD）的分析结果进行比较。结果表明，TVAR方法具有时频分辨率高、无交叉干扰项及计算速度快等优点。最后利用TVAR方法分析了转子启动过程正常及故障工况下转子实验台的非平稳振动信号。研究表明，TVAR不但能够有效地分析非平稳振动信号，而且具有较强的故障特征提取和抗噪声能力，是在时频域上进行故障诊断的有效方法。     

基于时间序列的GPS定位误差分析

在现代海战场的环境监测中,针对全球定位系统(GPS)的缺陷,采用时间序列分析的方法建立定位误差模型。首先将获得的数据进行平稳化处理,通过依据样本数据的自相关函数和偏相关函数的统计特性确定采用自回归滑动平均(ARMA)模型,然后根据参数的最小二乘估计和AIC准则建立ARMA(4,2)模型。通过对模型的残差分析,得出残差符合白噪声要求,与实际模型拟合程度较高,最后采用预报器对模型进一步预测,根据预报结果修正误差,明显提高了定位的精度。仿真结果表明了时间序列方法可以有效提高GPS的定位精度的有效性。     

一种改进的ARMA模型参数估计方法

针对自回归滑动平均(auto-regressive moving average,简称ARMA)模型参数谱估计容易出现谱峰漂移问题,提出一种基于组合目标函数和遗传算法的ARMA模型参数估计方法.通过最小均方误差准则获得ARMA模型参数初始估计,依据现代谱估计理论和连续函数极值存在的必要条件推导模型参数的频域约束方程,构造组合目标函数并采用遗传算法对模型参数初始估计值进行优化获得模型参数的最优解.将该方法用于车削状态下尾顶尖垂直方向振动加速度时间序列建模和谱估计,结果表明了方法的有效性.     

System identification of smart buildings under ambient excitations

This paper proposes a nonlinear autoregressive moving average (NARMA) model for use in system identification (SI) of high performance smart buildings under ambient excitations. The NARMA model is implemented by including the cross terms of output signals to a linear autoregressive moving average (LARMA) time series model. To demonstrate the effectiveness of the proposed NARMA approach, a three-story building equipped with smart control devices is investigated under a variety of ambient excitations. To access the robustness of the proposed model, it is tested under various levels of measurement noises. It is demonstrated from the extensive simulations that the proposed NARMA model is effective in predicting the ambient vibration responses of the high performance smart buildings with severe measurement noises.     

卡尔曼滤波及其在时间序列预测中的应用

根据时间序列预测的特点和要求,分析了传统时间序列预测方法的不足,提出了将卡尔曼滤波应用于时间序列预测。推导了基于卡尔曼滤波的ARMA模型参数实时更新算法,并采用功率谱密度分析方法确定预测模型的形式与阶数。最后,通过对光纤陀螺随机漂移建模进行了实证研究。     

A measure of the bullwhip effect in supply chains with stochastic lead time

In this paper, we exactly quantify the bullwhip effect, the variance amplification in replenishment orders, for cases of stochastic demand and stochastic lead time in a simple two-stage supply chain with one supplier and one retailer. In most of the previous research, the impact of order lead time on the bullwhip effect in supply chains with pre-specified demand processes is investigated mostly for cases of deterministic lead time. In this paper, we deal with a first-order autoregressive, AR(1), demand process and investigate the behavior of a measure for the bullwhip effect with respect to autoregressive coefficient and stochastic order lead time. Extension to a mixed first-order autoregressive-moving average, ARMA(1,1), demand process is also considered.     

相关系数平稳序列滤波、预测和平滑

相关系数平稳序列是从非平稳序列中分离出来的一类工程实际中常见且便于研究的随机序列，文中首先给出相关系数AR(p)、MA(g)和ARMA(p，g)序列可直接测得情况下的预测公式，然后在测量噪声独立和相关两种情况下分别讨论相关系数平稳序列不可直接测得时的滤波、预测和平滑问题。文中方法能够对均值和方差都随时间变化的相关系数平稳序列或信号进行高精度的分析和处理，可广泛应用于通信、自动控制、结构响应分析和故障诊断等领域。     

Investigation on thermal characteristics of heat sinks for power module using STM

The device that controls dynamic motions in a washing machine is called as MICOM. This device includes an IPM that controls the rotation of a tub. Also, the overheating of IPM gives cause for lowering the service life of an applied chip and is directly linked with its faults. A heat sink that is larger than the volume of the applied chip more than 50 times is installed to prevent such overheating. In the operation of the IPM, the temperature specification of the heat sink can be determined as 80°C under the air temperature of 25°C. However, the heat sink used at the present time cannot satisfy this condition, so it is necessary to redesign such a heat sink to satisfy this condition. This study proposes an STM that is able to precisely calculate the temperature applied to IPM in a system level prior to redesigning the heat sink. The STM can be considered as a model that complements a JEDEC analysis model. This model implements a parameter analysis to perform the optimization of a heat sink and verifies the priority of parameters to reduce material costs. Furthermore, it investigates a counterproposal that replaces the conventional cooling methods in which it seeks a counterproposal that performs heat dissipation in a device according to the SoC of chips and is able to suppress EMI. This paper was recommended for publication in revised form by Associate Editor Jae Dong Chung Chung-Hyo Jung acquired the doctoral degree in the Dept. of Science for Open and Enviromental Systems at Keio University in 2003. The specialty in the doctoral course was GSMAC-FEM and studied on MHD (magnetohydrodynamics). Dr. Jung joined Samsung Electronics Co., Ltd. as a CFD engineer in 2003. Also, he has worked at Samsung Advanced Institute of Technology and has charged in the thermal analysis of semi-conductors (system LSI). One of the Dr. Jung’s major concerning fields is the mechanical application of Lie-Groups.     

Adaptive state detection of gearboxes under varying load conditions based on parametric modelling

Conventional vibration monitoring techniques are unable to provide accurate state analysis of a gearbox under varying load condition. This paper proposes a novel technique for state detection of gearbox, which fits a time-varying autoregressive model to the gear motion residual signals applying a noise-adaptive Kalman filter, in the healthy state of the target gear. The optimum autoregressive model order, which provides a compromised model fitting for the healthy gear motion residual signals collected under various load conditions, is determined with the aid of a specific model order selection method proposed in this study. Consequently, a robust statistical measure, which takes the percentage of outliers exceeding the three standard deviation limits is applied to evaluate the state of the target gear, where the standard deviation of autoregressive model residuals takes its maximum in all tested gear motion residual signals for model order selection. The proposed technique is validated using full lifetime vibration data of gearboxes operating from new to failure under four distinct load conditions. The investigated load conditions include: (1) constant load, (2) one jump from 100 to 200% nominal torque level, (3) one jump from 100 to 300% nominal torque level, and (4) constant changed to sinusoidal. In each application, the specific model order selection and comparison of the proposed gear state indicator with three counterparts proposed in recent studies are addressed in detail. The Kolmogorov–Smirnov test is also performed as a complementary statistical analysis. The results show that the proposed technique possesses a highly effective and robust property in the state detection of gearbox, which is independent of varying load condition as well as remarkable stability, early alarm for incipient fault and significant presence of fault effects. The proposed gear state indicator can be directly employed by an on-line maintenance program as a reliable quantitative covariate to schedule optimal maintenance decision for rotating machinery.