Prof. Tadanobu Sato Profile

Prof. Tadanobu Sato

at Kyoto Univ

SPIE Involvement:

Author

Proceedings Article | 11 April 2006 Paper

Linear and nonlinear structural identifications using the support vector regression

Jian Zhang, Tadanobu Sato

Proceedings Volume 6174, 61743D (2006) https://doi.org/10.1117/12.658419

KEYWORDS: Structural health monitoring, Data modeling, System identification, Neural networks, Sensors, Bismuth, Motion models, Control systems, Interference (communication), Statistical analysis

Read Abstract +

Robust and efficient identification methods are necessary to study in the structural health monitoring field, especially when the I/O data are accompanied by high-level noise and the structure studied is a large-scale one. The Support vector Regression (SVR) is a promising nonlinear modeling method that has been found working very well in many fields, and has a powerful potential to be applied in system identifications. The SVR-based methods are provided in this article to make linear large-scale structural identification and nonlinear hysteretic structural identifications. The LS estimator is a cornerstone of statistics but less robust to outliers. Instead of the classical Gaussian loss function without regularization used in the LS method, a novel e-insensitive loss function is employed in the SVR. Meanwhile, the SVR adopts the 'max-margined' idea to search for an optimum hyper-plane separating the training data into two subsets by maximizing the margin between them. Therefore, the SVR-based structural identification approach is robust and accuracy even though the observation data involve different kinds and high-level noise. By means of the local strategy, the linear large-scale structural identification approach based on the SVR is first investigated. The novel SVR can identify structural parameters directly by writing structural observation equations in linear equations with respect to unknown structural parameters. Furthermore, the substrutural idea employed reduces the number of unknown parameters seriously to guarantee the SVR work in a low dimension and to focus the identification on a local arbitrary subsystem. It is crucial to make nonlinear structural identification also, because structures exhibit highly nonlinear characters under severe loads such as strong seismic excitations. The Bouc-Wen model is often utilized to describe structural nonlinear properties, the power parameter of the model however is often assumed as known even though it is unknown in the real world. In the case of unknown-power parameter, the nonlinear structural identification problem is more intricate and few approaches are dedicated to this problem. In this article, a model selection strategy is proposed to determine the unknown power parameter of the Bouc-Wen model. Meanwhile, the optimum SVR parameters are automatically selected instead of tuning manually. Based on the produced power parameter and optimum SVR parameters, the SVR is executed to identify nonlinear hysteretic structural parameters accurately and robustly. The numerical examples for two linear large-scale structures and a five-DOF nonlinear hysteretic structure provided illustrates that the proposed technique has excellent performance in robustness and accuracy for linear and nonlinear structural identifications, even when the noise exits in I/O measurements is high-level and non-Gaussion. Moreover, an incremental training algorithm utilized to solve SVR formulation in a sequential way not only significantly reduces the computation time, but also makes the structural health monitoring on-line.

Proceedings Article | 17 May 2005 Paper

Auxiliary particle filtering for structural system identification

He-Sheng Tang, Tadanobu Sato

Proceedings Volume 5765, (2005) https://doi.org/10.1117/12.598117

KEYWORDS: Particle filters, Particles, System identification, Digital filtering, Filtering (signal processing), Nonlinear filtering, Monte Carlo methods, Statistical analysis, Electronic filtering, Systems modeling

Read Abstract +

Proceedings Article | 17 May 2005 Paper

Support vector regression for structural identification

Jian Zhang, Tadanobu Sato

Proceedings Volume 5765, (2005) https://doi.org/10.1117/12.598384

KEYWORDS: Systems modeling, Data modeling, Structural dynamics, Neural networks, Error analysis, System identification, Machine learning, Motion models, Mathematical modeling, Autoregressive models

Read Abstract +

Proceedings Article | 21 July 2004 Paper

Efficient system identification algorithm using Monte Carlo filter and its application

Yohei Tanaka, Tadanobu Sato

Proceedings Volume 5394, (2004) https://doi.org/10.1117/12.541737

KEYWORDS: Particles, Monte Carlo methods, Data modeling, Algorithm development, System identification, Genetic algorithms, Particle filters, Data processing, Motion models, Computing systems

Read Abstract +

Proceedings Article | 21 July 2004 Paper

Nonlinear structural system identification using shaking table test data of five-story model building

Kazuki Ogiyama, Tadanobu Sato

Proceedings Volume 5394, (2004) https://doi.org/10.1117/12.541724

KEYWORDS: Data modeling, System identification, Filtering (signal processing), Complex systems, Digital filtering, Electronic filtering, Nonlinear filtering, Lead, Motion models, Data processing

Read Abstract +

Proceedings Article | 21 July 2004 Paper

Structural damage detection using neural network and H(infinity symbol) filter algorithm

Hesheng Tang, Tadanobu Sato

Proceedings Volume 5394, (2004) https://doi.org/10.1117/12.539511

KEYWORDS: Neural networks, Damage detection, Signal to noise ratio, Evolutionary algorithms, Systems modeling, Complex systems, Error analysis, Algorithm development, Detection and tracking algorithms, Nonlinear filtering

Read Abstract +

Proceedings Article | 6 August 2001 Paper

Ground strain measuring system using optical fiber sensors

Tadanobu Sato, Riki Honda, Shunjiro Shibata, Naoki Takegawa

Proceedings Volume 4328, (2001) https://doi.org/10.1117/12.435549

KEYWORDS: Measurement devices, Sensors, Fiber Bragg gratings, Fiber optics sensors, Instrument modeling, Chlorine, Earthquakes, Soil science, Smart materials, Fiber lasers

Read Abstract +

Proceedings Article | 12 June 2000 Paper

Ground strain measuring system using optical fiber sensors

Tadanobu Sato, Riki Honda, Shunjiro Shibata, Naoki Takegawa

Proceedings Volume 3986, (2000) https://doi.org/10.1117/12.388105

KEYWORDS: Measurement devices, Sensors, Fiber Bragg gratings, Fiber optics sensors, Soil science, Prototyping, Finite element methods, Calibration, Earthquakes, Motion models

Read Abstract +

Proceedings Article | 4 June 1999 Paper

Nonlinear structural identification based on H infinity filter algorithm

Tadanobu Sato, Kai Qi

Proceedings Volume 3667, (1999) https://doi.org/10.1117/12.350090

KEYWORDS: Nonlinear filtering, Digital filtering, Filtering (signal processing), Linear filtering, Systems modeling, System identification, Electronic filtering, Motion models, Complex systems, Data modeling

Read Abstract +

Proceedings Article | 31 May 1999 Paper

Ground strain measuring system using optical fiber sensors

Tadanobu Sato, Riki Honda, Shunjiro Shibata

Proceedings Volume 3670, (1999) https://doi.org/10.1117/12.349761

KEYWORDS: Sensors, Fiber Bragg gratings, Measurement devices, Prototyping, Fiber optics sensors, Instrument modeling, Earthquakes, Finite element methods, Calibration, Soil science

Read Abstract +

Proceedings Article | 24 July 1998 Paper

Linear algorithm to identify the nonlinear structural system equations

Tadanobu Sato, Masashi Kikukawa

Proceedings Volume 3323, (1998) https://doi.org/10.1117/12.316296

KEYWORDS: Neural networks, Complex systems, Filtering (signal processing), Algorithm development, Signal processing, Evolutionary algorithms, Systems modeling, System identification, Copper, Data modeling

Read Abstract +

Proceedings Article | 24 July 1998 Paper

Identification algorithm for time-varying structural systems using an adaptive Hoo filter

Kai Qi, Tadanobu Sato

Proceedings Volume 3323, (1998) https://doi.org/10.1117/12.316293

KEYWORDS: Digital filtering, Filtering (signal processing), System identification, Dynamical systems, Complex systems, Electronic filtering, Nonlinear filtering, Systems modeling, Linear filtering, Algorithm development

Read Abstract +

Proceedings Article | 13 June 1997 Paper

Real-time robust identification algorithm for structural systems with time-varying dynamic characteristics

Tadanobu Sato, Kenji Takei

Proceedings Volume 3039, (1997) https://doi.org/10.1117/12.276558

KEYWORDS: Filtering (signal processing), Algorithm development, Dynamical systems, System identification, Electronic filtering, Digital filtering, Error analysis, Stochastic processes, Statistical analysis, Motion models

Read Abstract +

Proceedings Article | 8 May 1995 Paper

Self-learning structural identification algorithm

Tadanobu Sato, Makoto Sato

Proceedings Volume 2443, (1995) https://doi.org/10.1117/12.208287

KEYWORDS: Neural networks, Interference (communication), Filtering (signal processing), Electronic filtering, Signal processing, Algorithm development, Evolutionary algorithms, Chemical elements, Electroluminescence, Nonlinear filtering

Read Abstract +

Proceedings Article | 1 May 1992 Paper

Predictive control of seismic response of structure taking into account the soil-structure interaction

Tadanobu Sato

Proceedings Volume 1777, 17771F (1992) https://doi.org/10.1117/12.2298074

Read Abstract +

Showing 5 of 15 publications

Conference Committee Involvement (5)