UD分解与偏差补偿结合用于变量带误差模型辨识

本文提出一种基于UD(upper-diagonal)分解与偏差补偿结合的辨识方法,用于变量带误差(errors-in-variables,EIV)模型辨识.考虑单输入单输出(single input and single output,SISO)线性动态系统,当输入和输出含有零均值、方差未知的高斯测量白噪声时,该类系统的模型参数估计是一种典型的EIV模型辨识问题.为了获得这种EIV模型参数的无偏估计,本文先推导出最小二乘模型参数估计偏差量与输入输出噪声方差以及最小二乘损失函数与输入输出噪声方差的关系,然后采用UD分解方法递推获得模型参数估计值,再利用输入输出噪声方差估计值补偿模型参数估计偏差,以此获得模型参数的无偏估计.本文还讨论了算法实现过程中遇到的一些问题及修补方法,并通过仿真例验证了所提辨识方法的有效性.     

Augmented hybrid method for continuous process identification from sampled data with coloured noise

The identification of a linear continuous-time model for a multivariable dynamic system from sampled input-output observations is considered. An augmented hybrid parametric method is proposed to overcome the interference of the coloured output noise in the sampled output. The parameters of the continuous-time process model are estimated from an augmented input-output realization which utilizes the dynamic information of the discrete-time noise model. Numerical examples are presented to illustrate how to obtain an adequate dynamic process model, considering the coloured output noise, by using a discrete-time noise model.     

Selection of outputs for distributed parameter systems by identifiability analysis in the time-scale domain

A method of sensor location selection is introduced for distributed parameter systems. In this method, the sensitivities of spatial outputs to model parameters are computed by a model and transformed via continuous wavelet transforms into the time-scale domain to characterise the shape attributes of output sensitivities and accentuate their differences. Regions are then sought in the time-scale plane wherein the wavelet coefficient of an output sensitivity surpasses all the others’ as indication of the output sensitivity’s distinctness. This yields a comprehensive account of identifiability each output provides to the model parameters as the basis of output selection. The proposed output selection strategy is demonstrated for a numerical case of pollutant dispersion by advection and diffusion in a two-dimensional area.     

A cumulant based algorithm for the identification of input-output quadratic systems

The identification of a special class of polynomial models is pursued in this paper. In particular a parameter estimation algorithm is developed for the identification of an input-output quadratic model excited by a zero mean white Gaussian input and with the output corrupted by additive measurement noise. Input-output crosscumulants up to the fifth order are employed and the identification problem of the unknown model parameters is reduced to the solution of successive triangular linear systems of equations that are solved at each step of the algorithm. Simulation studies are carried out and the proposed methodology is compared with two least squares type identification algorithms, the output error method and a combination of the instrumental variables and the output error approach. The proposed cumulant based algorithm and the output error method are tested with real data produced by a robotic manipulator.     

钢球磨煤机制粉过程的混合智能建模

钢球磨煤机制粉系统是一个具有多变量强耦合性、强非线性、大时滞特性的对象,很难建立它的精确数学模型.针对该问题,提出钢球磨煤机制粉系统的混合智能建模策略.通过机理建模方式建立钢球磨煤机制粉系统的入口负压、磨机差压、出口温度的模型.针对机理模型输出的出口温度与现场实际误差大的问题,增加了出口温度的补偿模型.为更好反映磨机负荷,建立磨音的神经网络模型.通过与现场实验数据的对比验证了模型的有效性.     

Stable haptic interaction using a damping model to implement a realistic tooth-cutting simulation for dental training

It is difficult to implement a stable and realistic haptic simulation for cutting rigid objects that is based on a damping model because of an inevitable conflict between stability and high output force. This paper presents passivity techniques to show that an excessive damping coefficient causes the output stiffness to exceed the maximum output stiffness of the haptic device, leading to instability. By analysing the damping model of a haptic dental-training simulator, we construct a relationship among the damping coefficient, position resolution, sampling frequency, human operation, and the maximum achievable device stiffness that will still maintain device stability. A method is also provided to restrict the output stiffness of the haptic device to ensure stability while enabling the realistic haptic simulation of cutting rigid objects (teeth) that is based in a damping model. Our analysis and conclusions are verified by a damping model that is constructed for a dental-training haptic display. Three types of haptic devices are used in our analysis and experiments.     

基于参考模型法的双闭环调速系统参数优化

调节器是双闭环调速系统的核心,传统的工程设计方法不仅烦琐、复杂,而且不够精确.为解决上述问题,提出了基于参考模型法的调节器参数优化方法:首先根据系统指标要求选择典型的最佳模型作为参考,然后以改进单纯形法为优化算法,通过比较控制系统和参考模型在同一输入信号下的输出偏差对调节器参数进行优化,使得在某种意义下偏差尽可能小,实现控制系统的输出响应跟踪或逼近参考模型特征.实验表明,方法不仅使设计工作大为简化,并且使控制系统较好地复现参考模型的特征,有效地提高了系统的性能.     

An efficient variable screening method for effective surrogate models for reliability-based design optimization

In the reliability-based design optimization (RBDO) process, surrogate models are frequently used to reduce the number of simulations because analysis of a simulation model takes a great deal of computational time. On the other hand, to obtain accurate surrogate models, we have to limit the dimension of the RBDO problem and thus mitigate the curse of dimensionality. Therefore, it is desirable to develop an efficient and effective variable screening method for reduction of the dimension of the RBDO problem. In this paper, requirements of the variable screening method for deterministic design optimization (DDO) and RBDO are compared, and it is found that output variance is critical for identifying important variables in the RBDO process. An efficient approximation method based on the univariate dimension reduction method (DRM) is proposed to calculate output variance efficiently. For variable screening, the variables that induce larger output variances are selected as important variables. To determine important variables, hypothesis testing is used in this paper so that possible errors are contained in a user-specified error level. Also, an appropriate number of samples is proposed for calculating the output variance. Moreover, a quadratic interpolation method is studied in detail to calculate output variance efficiently. Using numerical examples, performance of the proposed method is verified. It is shown that the proposed method finds important variables efficiently and effectively     

某型导弹系统仿真模型验证

仿真模型验证是仿真可信性研究的重要组成部分，有着极其重要的意义。模型验证就是比较仿真系统输出和实际系统输出的一致性，分为静态性能验证和动态性能验证。该文在分析研究各种仿真模型验证方法的基础上，主要采用工程上常用的bayes方法和窗谱分析法对某型导弹系统仿真模型进行了定量验证，最后给出结论并讨论了这两种方法的局限性。     

Abnormal condition detection in a cement rotary kiln with system identification methods

In this paper, we use system identification methods for abnormal condition detection in a cement rotary kiln. After selecting proper inputs and output, an input–output model is identified for the plant’s normal conditions. A novel approach is used in order to estimate the delays of the input channels of the kiln before identification part. This method eases the identification since with determining the input channels delays, the dimension of search space in the identification part reduces. Afterward, to identify the kiln’s model, Locally Linear Neuro-Fuzzy (LLNF) model is used. This model is trained by LOcally LInear MOdel Tree (LOLIMOT) algorithm which is an incremental tree-structure algorithm. Finally, with the model for normal condition of the kiln, the incident of abnormalities in output are detected based on the length of duration and magnitude of difference between the real output and model’s output. We distinguished three abnormal conditions in the kiln, two of which are known as common abnormal conditions and another one which was not characteristically known for cement experts either.     

Silicon auditory processors as computer peripherals

Several research groups are implementing analog integrated circuit models of biological auditory processing. The outputs of these circuit models have taken several forms, including video format for monitor display, simple scanned output for oscilloscope display, and parallel analog outputs suitable for data-acquisition systems. Here, an alternative output method for silicon auditory models, suitable for direct interface to digital computers, is described. As a prototype of this method, an integrated circuit model of temporal adaptation in the auditory nerve that functions as a peripheral to a workstation running Unix is described. Data from a working hybrid system that includes the auditory model, a digital interface, and asynchronous software are given. This system produces a real-time X-window display of the response of the auditory nerve model.     

Comparison of the closed-loop identification methods in terms of the bias distribution

Several schemes for plant model identification in closed-loop operation including classical direct method, two-step identification and closed-loop output error algorithms are considered. These methods are analyzed and compared in terms of the bias distribution of the estimates for the case that the noise model is estimated as well as the case that a fixed model of noise is considered (output error structure). The problems concerning the filtered direct method which is often used in the iterative identification and control scheme are mentioned. It is shown that these problems may be solved by the closed-loop output error identification method.     

Conditions of exact tracking by the linear system output of the standard model of a reduced order

A problem is considered for an exact tracking by the output of a linear stationary system presented in the space of states of the standard model of a reduced order in comparison with the dimension of the system state vector. A minimum possible order of the standard model is defined, at which it is possible to perform the exact tracking of it by the output, conditions are defined of the exact tracking by the output of the standard model of a reduced order, and also a set of the control laws that ensure the exact tracking and the internal stability of the system. The solution relies on the method of canonization of matrices. A methodical example is given.     

Differential evolution-based nonlinear system modeling using a bilinear series model

This paper presents a new modeling method for nonlinear dynamic systems based on using bilinear series model. Basically, bilinear model is an extension of infinite impulse response (IIR) filter and belongs to the recursive nonlinear system model, i.e., its past output signals will heavily affect the present output. This kind of model can efficiently approximate a large class of nonlinear systems with fewer parameters than other non-recursive models. To adjust the model kernels, we here adopt an evolutionary computation called the differential evolution (DE) algorithm. This algorithm is based on real-valued manipulations and has a good convergence property for finding the global solution or the near global solution of optimized problem. Design steps of DE-based nonlinear system modeling are clearly given in this study. Finally, two kinds of digital systems are illustrated to demonstrate the efficiency of the proposed method.     

System identification using slow and irregular output samples

Identification of systems with slowly and irregularly sampled output data is considered. The identified models can be used in inferential control or as soft sensor. Dual-rate system with slow output samples is a special case of the problem studied here. In this work, it will be show that an output error method is a natural choice for the problem that can identify the fast rate model directly from the fast input and slow and irregular output data. When the system is in the model set, consistence of the output error model is established and minimum variance property is proved. When the model order is lower than the true order, bias distribution in the frequency domain is given. Simulation studies and industrial data will be used to illustrate the method.     

Model order selection of nonlinear input–output models––a clustering based approach

Selecting the order of an input–output model of a dynamical system is a key step toward the goal of system identification. The false nearest neighbors algorithm (FNN) is a useful tool for the estimation of the order of linear and nonlinear systems. While advanced FNN uses nonlinear input–output data-based models for the model-based selection of the threshold constant that is used to compute the percentage of false neighbors, the computational effort of the method increases along with the number of data and the dimension of the model. To increase the efficiency of this method, in this paper we propose a clustering-based algorithm. Clustering is applied to the product space of the input and output variables. The model structure is then estimated on the basis of the cluster covariance matrix eigenvalues. The main advantage of the proposed solution is that it is model-free. This means that no particular model needs to be constructed in order to select the order of the model, while most other techniques are ‘wrapped' around a particular model construction method. This saves the computational effort and avoids a possible bias due to the particular construction method used. Three simulation examples are given to illustrate the proposed technique: estimation of the model structure for a linear system, a polymerization reactor and the van der Vusse reactor.     

An improved state-space model structure and a corresponding predictive functional control design with improved control performance

Conventional state-space model predictive control requires a state estimator/observer to access the state information for feedback controller design. Its drawbacks are the numerical convergence stability of the observer and closed-loop control performance deterioration with activated plant input/output constraints. The recent direct use of measured input and output variables to formulate a non-minimal state-space (NMSS) model overcomes these problems, but the subsequent controller is too sensitive to model mismatch. In this article, an improved structure of NMSS model that incorporates the output-tracking error is first formulated and then a subsequent predictive functional control design is proposed. The proposed controller is tested on both model match and model mismatch cases for comparison with previous controllers. Results show that control performance is improved. In addition, a linear programming method for constraints dealing and a closed form of transfer function representation of the control system are provided for further insight into the proposed method.     

基于闭环辨识的柴油机模型研究

论文首先分析了柴油机闭环辨识的条件和柴油机的理论数学模型,然后采用ARX模型辨识出柴油机控制系统模型.辨识的输入输出数据分别采用柴油机闭环控制系统的齿条位移和输出转速,模型参数估计采用最小二乘法,最后通过残差分析对模型的正确性进行验证.辨识结果表明该模型能够很好地反映柴油机的动态输出特性,并具有较高的精度,证明了ARX模型辨识算法对于柴油机系统的辨识是可行的.     

A comparison of the balanced matrix method and the aggregation method of model reduction

The balanced matrix method and the aggregation method for model reduction are compared. It is shown that there is a "natural" choice for the aggregated reduced model output matrix that makes the aggregated model comparable to the balanced matrix reduced-order model. This assumes that the eigenvalues retained in the aggregated model are truly dominant and that the orders of the two models are equal. However, there are situations in which the choice of the eigenvalues to be retained in an aggregated model is not obvious. In these cases the balanced matrix method may be superior. The models are compared in two numerical examples.     

Nonlinear influence in the frequency domain: Alternating series

The nonlinear influence on system output spectrum is studied for a class of nonlinear systems which have Volterra series expansion. It is shown that under certain conditions the system output spectrum can be expressed in an alternating series with respect to some model parameters which define system nonlinearities. The magnitude of the system output spectrum can therefore be suppressed by exploiting the properties of alternating series. Sufficient (and necessary) conditions in which the output spectrum can be cast into an alternating series are studied. These results reveal a novel frequency-domain insight into the nonlinear influence on a system, and provide a new method for the analysis and design of nonlinear systems in the frequency domain. Examples are given to illustrate the results.