Kiyoshi Wada

• Kyushu University

This paper investigates the problem of identifying errors-in-variables (EIV) models, where the both input and output measurements are corrupted by white noises, and addresses a new efficient recursive algorithm. The identification problem of EIV models with unknown noise variances has been extensively studied and several methods have been proposed....

This paper investigates the problem of identifying errors-in-variables (EIV) models, where the both input and output measurements are corrupted by white noise, and addresses a new method to solve the problem. The identification problem of EIV models with unknown noise variances has been extensively studied and several methods have been proposed. To...

This paper addresses the problem of identifying errors-in-variables models, where the input measurement is corrupted by white noise whereas the output measurement is corrupted by colored noise. The Koopmans-Levin method is one of possible methods for identifying errors-in-variables models. However, it requires a priori knowledge of the measurement...

Artificial respirators are widely used in various scenes. Doctors are required to pay scrupulous attention for the use of the artificial respirators. The ideal setting method of artificial respirator is a setting method in consideration of the pulmonary characteristic of the patient. However, we cannot know the pulmonary characteristic of the patie...

This paper shows the feature extraction for gas discrimination from the transient response of a gas sensor using a subspace-based system identiication technique. We have proposed an approximation and analysis method for the transient response using a subspace-based identiication method. This is based on Prony's method and can extract time constants...

In this paper, the methods of consistent estimation for identification of linear discrete-time system in the presence of input and output noises, which is usually called “errors-in-variables” (EIV) models, are studied. It is well known that the least squares (LS) method gives biased parameter estimates for EIV situations. To solve this bias problem...

In this paper, feature extraction based on a subspace-based identification technique for a transient response of a semiconductortype gas sensor is proposed. A typical gas sensor response can be interpreted as the sum of step responses of the first- or high-order lag system, and we have investigated the feature extraction method of the sensor output...

Pulmonary characteristics differ in patients, and the suitable setting of ventilation condition is needed for every patient in the artificial respiration. The pulmonary elastance is one of the important features of lung, and it is a basis for deciding the airway pressure limit value. To get the pulmonary elastance of the of the patient from measure...

This paper considers the output-tracking control problem of feedback linearizable nonlinear systems in the presence of external disturbances and modeling errors. A robust output feedback nonlinear controller is designed to achieve excellent output-tracking performance. By exploiting the cascade features of backstepping design, a simple disturbance...

This technical note presents a unified framework for bias compensation principle (BCP)-based methods applied for identification of linear systems subject to correlated noise. By introducing a non-singular matrix and an auxiliary vector uncorrelated with the noise, the unified framework is established. Since there are rich possibilities of the choic...

Pulmonary characteristics differ in patients, and the suitable setting of ventilation condition is needed for every patient in the artificial respiration. The pulmonary elastance is one of the important features of lung, and it is a basis for deciding the air-way pressure limit value. In this study, an estimation method for pulmonary elastance is p...

In this paper, a consistent estimation method for "errors-in- variables" (EIV) models is studied. The extended generalized least-correlation (EGLC) method has been proposed for the EIV models identification in the case where the input and output measurements are corrupted by white noises. To obtain more stable and accurate estimates, we introduce t...

To perform artificial respiration safely and comfortably, it is necessary to get the information on characteristics of patient respiratory system timely, and to set the ventilation conditions fitted to each patient under the information. Based on our earlier works on modeling and estimation of respiratory system, in this paper, data averaging metho...

In this paper, a consistent estimation method for “errors-in-variables” (EIV) models is studied. The extended generalized least-correlation (EGLC) method has been proposed for the EIV models identification in the case where input and output measurements are corrupted by white noise. To obtain more stable and accurate estimates, we introduce the pre...

This paper addresses identification of Hammerstein nonlinear ARMAX model by using a numerical algorithm for subspace state space system identification method. When the static memoryless nonlinear block of Hammerstein models is considered as the sum of some known functions, the ARMAX model of the linear part can be estimated as a multi-input single-...

Parameter adaptation and disturbance observer (DOB) have been considered as two contrastively different approaches to handle uncertainties in motion control problems. The purpose of this brief is to merge both techniques into one control design with theoretically guaranteed performance. It is shown that the DOB compensates low-passed components of...

This paper addresses identification of Hammerstein systems using wavelet expansion from noise corrupted data. When the static memoryless nonlinear part of Hammerstein systems can be considered as the sum of some known functions, the linear part can be estimated as a multi-input single-output (MISO) system with the numerical algorithm for subspace s...

This paper proposes a novel robust output feedback controller for an electromechanical system in the presence of external disturbance and uncertainties of physical parameters. By exploiting the cascade features of backstepping design, a simple disturbance observer is proposed to suppress the effects of the uncertainties, and a high-gain observer is...

The ability to identify and follow a moving object is not only important for human activities, but it is also critical necessity in the use of robots for automation and manufacturing, security applications and for life sciences. This can be achieved ...

In this paper, the method of consistent estimation of the errors-in-variables (EIV) models based on the quantized input-output measurements is studied. A new bias-compensation based method, named the bias-compensated instrumental variable type (BCIV-type) method, has been proposed for the quantized EIV models identification. The proposed BCIV-type...

Building a precise respiratory model is very helpful for setting appropriate ventilation conditions to fit each patient when artificial respiration is performed on the patient. The authors have proposed two types of second order nonlinear differential equation model of respiratory system. However, these model cannot cover the hysteresis characteris...

A robust non-linear output-feedback controller by the K-filter approach is proposed for position-tracking problem of a magnetic levitation system, where only the position measurement is available for control. Instead of the popular adaptive control techniques, a disturbance observer (DOB) is merged into the K-filter-based output-feedback controller...

This paper addresses identification of Hammerstein systems using the sampled input-output data in frequency domain. When the static memoryless nonlinear part of Hammerstein model can be considered as a polynomial with a known order, the following linear part can be estimated as a multi-input single-output (MISO) systems with the numerical algorithm...

An important and hard problem in signal processing is the estimation of parameters in the presence of observation noise. In this paper, adaptive finite impulse response (FIR) filtering with noisy input-output data is considered and two developed bias compensation least squares (BCLS) methods are proposed. By introducing two auxiliary estimators, th...

The bias eliminated least squares (BELS) method, which is known as efficient for unknown parameter estimation of transfer function in the correlated noise case, has been developed and applied effectively to the closed-loop system identification. In this paper, under the general settings, the realizations of the BELS method as a weighted instrumenta...

This paper deals with the problem of estimating the parameters of Hammerstein systems based on recursive least squares method. Hammerstein systems can be considered as one kind of nonlinear systems, it is applied in many fields. Several identification methods of Hammerstein systems have been developed. We utilize the recursive algorithm to identify...

It is well known that least-squares (LS) method gives biased parameter estimates when the input and output measurements are corrupted by white noises. One possible approach for solving this bias problem is the bias-compensation based method such as the bias-compensated least-squares (BCLS) method. In this paper, a new bias-compensation based method...

This paper proposes a new method of decentralized robust control for large-scale interconnected uncertain nonlinear mechanical systems, by using disturbance observers (DOBs). Rigorous stability analysis is given for the overall nonlinear system. Simulation results on a coupled double pendulum system are presented to confirm the established theoreti...

In this paper, decision of air-pressure limit value in the case of artificial respiration is considered. Air-pressure limit value is an important conditional parameter of artificial respiration. the pulmonary characteristics are very different according to the person. For setting appropriate ventilation conditions fitting to each patient, it is nec...

In many cases it is not possible to remove the feedback during an identification experiment because this may lead to instability. The feedback may also be inherent in many dynamic systems (e.g., economical, biological). In this paper we shall consider the problem of identification of dynamic systems operating under feedback control and propose an i...

We have proposed an interpretation of MOESP types of subspace algorithms by using the Schur complement (SC) of the data product moment and proposed a unified framework for the subspace-based identification. Here we consider the introduction of exponential forgetting factor which windows the data matrices to apply the algorithms to the slowly time-v...

It is well known that the least-squares (LS) method gives biased parameter estimates of transfer functions when the output measurement is corrupted by white noise. One possible approach for solving this bias problem is the total-least-squares (TLS) method. Davila proposed a Recursive TLS (RTLS) algorithm based on minimization of the generalized Ray...

It is well known that least-squares (LS) method gives biased parameter estimates when the input and output measurements are corrupted by white noise. One possible approach for solving this bias problem is the bias-compnesation based method such as the bias-compensated least-squares (BCLS) method. In this paper, a new bias-compensation based method...

Identification of linear dynamic systems from noisy input and output measurements is studied. In order to deal with this task, a modified bias compensation least square (BCLS) method is proposed. In the proposed method, the backward output predictor (BOP) is introduced. With the help of analyzing the properties of auto-function of least square (LS)...

In this paper a novel predictive control design method is proposed. Using a modified subspace state-space identification algorithm, lifted state-space models for general dual-rate systems is identified from the input-output data. Based on the estimated lifted system matrices, we establish two predictors which realize the prediction of the output of...

This paper proposes an adaptive robust output-feedback controller for the position-tracking problem of a magnetic levitation system with a current-feedback power amplifier. The system is governed by a single-input single-output second-order nonlinear differential equation which is different from the standard output-feedback form, since there is a p...

In this brief, a novel robust nonlinear motion controller with disturbance observer (DOB) for positioning control of a nonlinear single-input-single-output (SISO) mechanical system is proposed. The controller is designed in a backstepping manner. First, a proportional-integral (PI) controller is designed to stabilize the position error. Consequentl...

The MOESP types of the subspace algorithms which are originally proposed by Verhaegen are considered at the point of view from the weighting of the data matrices. We have proposed an interpretation of these types of subspace algorithms by using the Schur complement (SC) of the data product moment and derive a unified framework for the subspace-base...

It is well known that least-squares (LS) method gives biased parameter estimates when the input and output measurements are corrupted by noise. One possible approach for solving this bias problem is the bias-compensation based method such as the bias-compensated least-squares (BCLS) method. In this paper, a new bias-compnesation based method is pro...

In this paper, we consider the identification problem for a dual-rate system in which the input sampling period may differ from that of the output. Based on the lifting operators, a lifted system which is equivalent to the original dual-rate system can be derived so that a lifted state-space model can be obtained which maps the relations between th...

This paper considers the control problem of a popular magnetic levitation system, which is open-loop unstable and strongly nonlinear associated with the electromechanical dynamics. The system dynamics is governed by a third-order nonlinear differential equation. The overall controller is designed through a backstepping manner by combining both the...

This article considers the adaptive robust control of a class of single-input-single-output nonlinear systems in semi-strict feedback form using radial basis function (RBF) networks. It is well known that the standard backstepping design may suffer from ''explosion of terms''. To overcome this problem, the recently developed dynamic surface control...

The flatness control system is a long time-delay, on-linear, coupled multivariate system with variable parameters. Based on the system features, genetic algorithms which possesses parallel search ability synchronously optimize the fuzzy controller parameters based on combinative coding of membership functions, quantization factors and scale factor....

This paper solves the problem of estimating lifted state-space models for a class of dual-rate systems in which input sampling period is an integer multiple of output sampling period from the input-output data directly. We first derive the lifted model of this class of dual-rate system to prove that the lifted model can be an indirect model for the...

This paper considers the identification problem of multiple input single output (MISO) continuous-time systems with unknown time delays of the inputs, from sampled input–output data. An iterative global separable nonlinear least-squares (GSEPNLS) method which estimates the time delays and transfer function parameters separably is derived to signifi...

Air-pressure limit value is an important conditional parameter of artificial respiration. The pulmonary characteristics are very different according to the person. For setting appropriate ventilation conditions fitting to each patient, it is necessary to establish a mathematical model describing the mechanism of human respiratory system, and to kno...

In this paper, a practical adaptive robust nonlinear controller is proposed for motion control of an SISO nonlinear mechanical system, where the distrubances due to ripple force and friction are compensated by the RBF networks. Rigorous analysis of transient performance and ultimate bound is given. Numerical examples are included to verify the theo...

Least squares (LS) techniques are applied to the identification problem of continuous-time systems from sampled data of input-output measurements. The linear integral filter, which solves the intial condition problem, is employed for handling time derivatives. The asymptotic bias in the LS estimator is derived, and is compensated in a modified LS a...

In this paper the problem of ARMAX model identification is studied and an efficient recursive robust identification algorithm applicable to ARMAX model is proposed. When applying directly LS method to ARMAX model estimation, the asymptotical bias appears. In order to estimate the bias, inspiring from the bias compensation least squares (BCLS) algor...

In this paper a modified bias compensation recursive least-squares (MBCRLS) method is proposed to deal with the task of adaptive FIR filtering with noisy input-output data. This method is similar to the BCRLS method which is proposed by authors recently in terms of use of introducing an auxiliary estimator but a different form with that one in BCRL...

In this paper, we consider the identification problem for a dual-rate system in which the input sampling period may differ from that of the output. Based on the lifting oper-ators, a lifted system which is equivalent to the original dual-rate system can be derived so that a lifted state-space model can be obtained which maps the relations between t...

Pulmonary elastance provides an important basis for deciding air pressure parameters of mechanical ventilators, and airway resistance is an important parameter in the diagnosis of respiratory diseases. The authors have proposed a second order nonlinear differential equation model of respiratory system whose elastic and resistant coefficients are ex...

It is well-known that the Least Squares (LS) method gives biased estimates for Infinite Impulse Response (IIR) model in the presence of output noise. One of the methods which delivers consistent estimates is the Total Least Squares (TLS) method. In this paper, two types of the recursive TLS algorithms for noisy IIR estimation are discussed.

Recursive updating algorithms of error covariance matrices in subspace identification methods for time-varying systems are derived. The proposed algorithms can be applied to estimate the system parameters which are slowly time-varying. The algorithms are based on the fact that the subspace extraction amounts to computing singular value decompositio...

This paper presents two novel radial basis functions and their comparison. Both radial basis functions are based on an idea of Support Vector Machine (SVM) by mapping data into a high dimensional feature space, which is known as Reproducing Kernel Hilbert Space and then performing Radial Basis Function (RBF) network in the feature space. Orthogonal...

A Dynamic Total Least Squares (DTLS) method can be applied to system identification in the presence of input and output noises. The DTLS problem is a special case of a Structured total least squares (STLS) problem that is an extension of the TLS problem and reduces to nonlinear singular value decomposition (SVD). In this paper, we discuss DTLS meth...

Using a unified approach, recursive algorithms of the error covariance matrices in subspace methods are derived for the MOESP type of subspace methods. The proposed approach is based on the fact that the subspace extraction amounts to computing singular value decomposition of the Schur complement (SC) of the input submatrix in data product moments...

In this paper, a practical and general adaptive robust nonlinear controller is proposed for positioning control of a nonlinear mechanical system. To overcome the main obstacles that prevent the adaptive control techniques from coming into wide use in the industrial side, our attention is focused on the guaranteed transient performance and theoretic...

Using a unified approach, recursive subspace identification algorithms are derived for the MOESP type of subspace methods. The proposed approach is based on the fact that the subspace extraction amounts to computing singular value decomposition of the Schur complement (SC) of the input submatrix in data product moments and the SC can be interpreted...

In this paper, two bias-compensated least-squares (BCLS) methods (BCLS-α method and BCLS-β method) are proposed for identification of linear discrete-time system in the case where the input measurement is corrupted by white noise and the output measurement is corrupted by colored noise. It is well known that BCLS method is based on compensation of...

The present study employs an idea of mapping data into a high dimensional feature space which is known as Reproducing Kernel Hilbert Space (RKHS), then performs Radial Basis Function (RBF) network in the feature space where the new basis function will be obtained and finally, Orthogonal Least Squares (OLS) method is employed to select a suitable se...

The Structured Total Least Squares (STLS) problem is an extension of the Total Least Squares (TLS) problem for solving an overdetermined system of equations Ax ≈ b 1). The Dynamic Total Least Squares (DTLS) problem is a special case of STLS problem. In this paper, we illustrate the TLS singular value problem by defining some vectors from a new view...

An approach to control-oriented uncertainty modeling is presented for a class of elastic vibrating systems such as flexible structures, beams and strings, described by partial differential equations. Uncertainty bounding techniques are developed using upper and lower bounds of the unknown eigenparameters. The result forms a basis for a finite-dimen...

This paper considers the identification problem of continuous-time systems with unknown time delays from sampled input-output data. An iterative global separable nonlinear least-squares (GSEPNLS) method which estimates the time delays and transfer function parameters separably is derived, by using stochastic global-optimization technique to avoid c...

This paper considers the position tracking problem of a popular magnetic levitation system in the presence of modeling errors due to uncertainties of physical parameters. The recently developed dynamic surface control (DSC) technique is modified and applied to the system under study, to overcome the problem of “explosion of terms” associated with t...

For setting appropriate respiratory conditions to fit each patient who is receiving artificial respiration treatment, it is very important to build a respiratory model of lung that describes the dynamics of respiration. In this paper, a new respiratory model is proposed, which is a second order nonlinear differential equation with elastic and resis...

Building a precise respiration system model is very helpful for setting appropriate ventilation conditions to fit each patient when artificial respiration is performed on the patient. In this paper, a new respiration system model is proposed, which is a second order nonlinear differential equation including volume dependent elastic term described b...

This paper considers the identification problem of continuous-time systems with unknown time delays from sampled input-output data. By using a digital prefilter, an approximated discrete-time estimation model is first derived, in which the system parameters remain in their original form and the time delays need not be an integral multiple of sampli...

The present study employs an idea of mapping data into a high dimensional feature space which is known as Reproducing Kernel Hilbert Space (RKHS), then performs Radial Basis Function (RBF) network in the feature space and finally, Orthogonal Least Squares (OLS) method is employed to select a suitable set of centers (regressors) from a large set of...

In this paper, we show the experimental study on adaptive robust neural network Principal Compo- nent Analysis (PCA) based on a reconstruction er- ror model. Firstly we explain the traditional batch way PCA which is based on eigenvalue decompo- sition and discuss its problems. To overcome such the problems, the adaptive robust neural network Princi...

In this paper, a unified approach for subspace-based identification methods by using Schur complement is proposed. MOESP (MIMO output error state space model identification) type of subspace idenitification methods are well known as an elementary subspace method. The extensions of the MOESP with instrumental variables (IV) have been proposed, which...

In this paper a study is presented on Subspace State Space Identification (4SID) method for the SISO (Single-Input Single-Output) systems. It is seen that an intermediate vector which appears in the 4SID procedure is equal to the parameter of system pulse transfer function. It is also shown that 4SID method is equivalent to Eigenvector (EV) method...

This paper considers the position-tracking problem of a magnetic levitation system in the presence of modeling errors due to uncertainties of physical parameters. A robust nonlinear controller is designed to achieve excellent position-tracking performance. The recently developed dynamic surface control is modified and applied to the system under st...

This paper considers the position tracking problem of a magnetic levitation system in the presence of uncertainties of physical parameters. The dynamic surface control (DSC) technique is modified and applied to the system under study, to overcome the problem of "explosion of terms" associated with the backstepping design procedure. Input-to-state s...

This paper focuses on bias compensation estimation of autoregressive (AR) process in the presence of white noise. It is known that bias compensation principle (BCP) based method requires the estimate of unknown noise variance to compensate the bias of least-squares (LS) estimate to provide consistent AR parameter estimate. In this paper, estimation...

Many identification methods are based on the assumption that input measurement is noise-free. However, this condition is not satisfied in most practical situations. In the presence of input noise, those methods have been shown to give erroneous results. Bias-compensated least-squares method is a consistent estimation method for unknwon parameters o...

This paper considers the identification problem of continuous-time systems with unknown time delay from sampled input-output data. By using a digital pre-filter, an approximated discrete-time estimation model is first derived, in which the system parameters remain in their original form and the time delay need not be an integral multiple of the sam...

This paper considers the identification problem of continuous-time systems with unknown time delay from sampled input-output data. By using a digital pre- filter, an approximated discrete-time estimation model is first derived, in which the system parameters remain in their original form and the time delay need not be an integral multiple of the sa...

This paper shows a new interpretation of the subspace-based identifica- tion methods by using Schur complement approach. MOESP (MIMO output error state space model identification) algorithms are considered. Instead of the data matrices, we start to consider a data product moment consisted of the Hankel matrices of input-output data. It is shown tha...

This paper studies the problem of parameter estimation of ARMAX model from a novel point of view. An efficient bias compensation least squares algorithm is proposed to provide consistent parameter estimate for ARMAX model. The main feature of our proposed algorithm is to introduce the auxiliary least squares linear backward predictors to construct...

In many cases it is not possible to remove the feedback during an identification experiment because this may lead to instability. The feedback may also be inherent in many dynamic systems (e.g., economical, biological). In this paper we shall consider the problem of identification of dynamic systems operating under feedback control and propose an i...

In this study, we proposed Kernel Principal Component Analysis (KPCA) which is applied for feature selection in a high-dimensional feature space which is nonlinearly mapped from an input space by a Gaussian kernel function. By using Mercer Kernels, we can compute principal components in a high dimensional feature space. Then, the extracted features...

In this paper, an interpretation of subspace-based identification methods with Schur complement approach is proposed. MOESP (MIMO output error state space model identification) algorithms are well known as an elementary subspace method. The extensions of the MOESP with instrumental variables (IV) have been proposed in literatures, which can be usef...

In this paper, we propose an efficient procedure of physical parameter identification of a magnetic levitation system, where the levitated steel ball is controlled by a robust nonlinear controller which is designed based on rough nominal parameters. Design techniques of the robust nonlinear controller are described and parameter identification resu...

According to the demand of practical bidding procedure in the construction field, the paper adapts the K-L information distance to the learning error function of the neural network and improves the traditional BP algorithm. The bidding system's learning ability and generalization ability to various learning algorithms are compared. Simulations illu...

Based on radial basis function neural network (RBFN) and perceptron neural network, this paper built a new four-layer feed-forward neural network named radial basis perceptron network (RBPN). This network can be summarized as follows: (1) It is selective connection between the units of two hidden layers; (2) The number of units of hidden layers is...

In this study, Kernel Principal Component Analysis (KPCA) is applied as feature selection in a high-dimensional feature space which is nonlinearly related to an input space. By using Mercer Kernels, we can compute principal components in a high dimensional feature space. Then, the extracted features by KPCA method are employed as a new kind of regr...

The bias eliminated least squares (BELS) method is one of consistent estimation methods for unknown parameters of transfer function in the presence of colored noise. In this paper, the BELS method is derived in a more general setting by introducing an auxiliary vector and a nonsingular matrix. With the help of matrix-partition technique and matrix...

This paper considers the position tracking problem of a magnetic levitation system in the presence of modelling errors due to uncertainties of physical parameters. The recently developed dynamic surface control is modified and applied to the system under study, to overcome the problem of "explosion of terms" associated with the backstepping design...

The bias eliminated least squares (BELS) method is one of consistent estimation methods for unknown parameters of transfer function in the presence of colored noise. In this paper, a unified form for BELS (UBELS) method is proposed by means of introducing an auxiliary vector and a nonsingular matrix. The introduced nonsingular matrix and auxiliary...

The identification of AR processes whose measurement are corrupted by additive noise is considered. A bias compensated least squares (BCLS) algorithm is derived on the framework of solving nonlinear bias compensation equation (BCE). The framework is convenience for investigating the convergence property of the algorithm. Convergence analysis of the...

This paper considers the position tracking problem of a popular magnetic levitation system in the presence of modeling errors due to uncertainties of physical parameters. The recently developed dynamic surface control (DSC) technique is modified and applied to the system under study, to overcome the problem of ``explosion of terms'' associated with...

In this paper, the identification of AR processes whose measurements are corrupted by additive noise is considered. An approach to consistent estimation of AR processes is proposed that is based on solving eigenvalue problem. A nonlinear bias compensation equation (BCE) is derived via forward and backward LS predictors. By theoretical analysis, it...

In this paper, we will expand and generalize the orthogonal functions as basis functions for dynam- ical system representations. The orthogonal func- tions can be considered as generalizations of, for example, the pulse functions, Laguerre functions, and Kautz functions. A least-squares identifica- tion method is studied that estimates a finite num...

In many areas of signal, system, and control theory, orthogonal functions play an important role in issues of analysis and design. In this paper, we will expand and generalize the orthogonal functions as basis functions for dynamical system representations. The orthogonal functions can be considered as generalizations of, for example, the pulse fun...

In this paper, an interpretation of subspace-based iden-tification methods with Schur complement approach is proposed. MOESP (MIMO output error state space model identification) algorithms are well known as an elementary subspace method. The extensions of the MOESP with instrumental variables (IV) have been proposed in literatures, which can be use...

In this study, we proposed Kernel Principal Component Analysis (KPCA) which is applied for feature selection in a high-dimensional feature space which is nonlinearly mapped from an input space by a Gaussian kernel function. By using Mercer Kernels, we can compute principal components in a high dimensional feature space. Then, the extracted features...