New Development in Nonlinear System Modeling

非线性系统建模的新进展

• 批准号: 14550447
• 负责人: UOSAKI Katsuji
• 金额: $ 2.18万
• 依托单位: Osaka University
• 依托单位国家: 日本
• 项目类别: Grant-in-Aid for Scientific Research (C)
• 财政年份: 2002
• 资助国家: 日本
• 起止时间: 2002 至 2004
• 项目状态: 已结题
• 来源: https://kaken.nii.ac.jp/grant/KAKENHI-PROJECT-14550447/
• 关键词: nonlinear systems; system identification; evolutionary computation; local modeling; regime selection; block oriented models; RBF network; particle filter; 非線形モデル; ブロック指向モデル; 進化計算; パラメータ推定; 進化的計算; 多目的最適化; 非線形時系列; 進化型計算法; ウィナーモデル; ハンマーシュタイン

Since there exist nonlinearities in natal, social and industrial systems, nonlinear system modeling is ubiquitous for analysis, design, control, and optimization of such systems. In this we have developed new methodologies for nonlinear system modeling based on the idea of local modeling and evolutionary computation. The topics investigated are :1. Automatic operating regime selection in local modelingSince the performance of the global model is highly affected by the choice of the local operating regimes in which the local models are identified, automatic selection algorithms of suitable local regimes have been developed.2. Identification of block oriented nonlinear modelsUsing evolutionary computation approaches, identification method for block oriented nonlinear models, in which nonlinear static part and linear dynamic part are in cascade connection.3. Nonlinear modeling by Radial basis function networkIdentification of radial basis function network for nonlinear modeling has been discussed from the multi-objective optimization problem.4. Evolution strategies based particle filter for nonlinear filteringA novel nonlinear filter called evolution strategies based nonlinear filter has been developed combining particle filter based on the importance filtering in Monte Carlo method and evolution strategies in evolutionary computation.

由于自然界、社会和工业系统中存在着非线性，非线性系统建模在这类系统的分析、设计、控制和优化中是普遍存在的。在这方面，我们基于局部建模和进化计算的思想，发展了非线性系统建模的新方法。1.局部模型运行状态的自动选择由于局部模型运行状态的选择对全局模型的性能有很大的影响，因此，本文提出了适合局部模型运行状态的自动选择算法。面向块的非线性模型辨识采用进化计算方法，对非线性静态部分和线性动态部分级联的面向块的非线性模型进行辨识。基于径向基函数网络的非线性建模从多目标优化问题出发，讨论了用于非线性建模的径向基函数网络辨识问题。基于进化策略的粒子滤波用于非线性滤波将基于蒙特卡罗方法中重要性过滤的粒子滤波与进化计算中的进化策略相结合，提出了一种新的基于进化策略的非线性过滤器。

项目成果

Multi-objective structure selection for radial basis function networks based on genetic algorithm

• DOI: 10.1109/cec.2003.1299790
• 发表时间: 2003-12
• 期刊: The 2003 Congress on Evolutionary Computation, 2003. CEC '03.
• 作者: T. Hatanaka;N. Kondo;K. Uosaki

Katsuji Uosaki, Toshiharu Hatanaka, Norio Manabe: "Optimal segmentation of nonlinear time series"Proceeding of European Control Conference ECC 2003. WE-12-1 (2003)

Katsuji Uosaki、Toshiharu Hatanaka、Norio Manabe：“非线性时间序列的优化分割”欧洲控制会议 ECC 2003 论文集。WE-12-1 (2003)

K.Uosaki, T.Hatanaka, N.Manabe: "Automatic regime selection in local modeling"Proc. 15^<th> IFAC World Congress on Automatic Control. T-We-M21 (2002)

K.Uosaki、T.Hatanaka、N.Manabe：“局部建模中的自动机制选择”Proc。

Simultaneous state and parameter estimation of nonlinear models by evolution strategies based particle filter

基于粒子滤波器的进化策略对非线性模型进行同步状态和参数估计

• 发表时间: 2005
• 期刊: Proc.of 10th International Symposium on Artificial Life and Robotics
• 作者: K.Uosaki;T.Hatanaka
• 通讯作者: T.Hatanaka

Structure identification in Takagi-Sugeno fuzzy modeling

Takagi-Sugeno 模糊建模中的结构识别

• 发表时间: 2002
• 期刊: Proc.of 2002 IEEE International Conference on Fuzzy Systems, FUZZ-IEEE 2002
• 作者: K.Uosaki;Y.Kimura;T.Hatanaka;T.Hatanaka;T.Hatanaka
• 通讯作者: T.Hatanaka