Dissertation > Excellent graduate degree dissertation topics show
System Identification Based on Weighted Multi-Innovation Approach
Author: ChangLiang
Tutor: WuAiGuo
School: Harbin Institute of Technology
Course: Control Science and Engineering
Keywords: multi-innovation identification method system identification weighting matrix forgetting factor
CLC: N945.14
Type: Master's thesis
Year: 2010
Downloads: 73
Quote: 0
Read: Download Dissertation
Abstract
|
Compared with some existing identification methods such as traditional leastsquares, stochastic gradient algorithm that uses the single-innovation modificationtechnology , the multi-innovation identification method possesses betterconvergent performance. Therefore, it is theoretically and practically important toinvestigate such a kind of identification method. The main results of this thesis areas follows.1. By introducing a weighting matrix into the multi-innovation identificationmethod, this thesis presents weighted multi-innovation identificationgradient identification algorithm. By some numerical simulation examplesit is shown that through selecting proper weighting matrix, weightedmulti-innovation identification methods have faster convergence speedrate and better parameter estimation accuracy than ordinary multi-innovation identification algorithm under the same innovation length. Inaddition, some brief discussions on the effect of the weighting matrix aregiven.2. For time-varying systems, weighted multi-innovation identificationmethods with forgetting factors are presented. The effectiveness of theproposed algorithm is verified by a numerical example.3. For the controlled autoregressive moving average model (CARMA model)with colored noise, in this thesis, the multi-innovation augmentedstochastic gradient identification algorithm is proposed, the advantagesover some existed algorithms are shown by some numerical examples.4. For a more complex system model, dynamic adjusting model (DA model),the thesis proposes multi-innovation generalized augmented stochasticgradient identification. Some numerical examples are given to verify theweighted multi-innovation generalized augmented stochastic gradient identification method has faster convergence rate than the regular multi-innovation generalized augmented stochastic gradient identificationmethod.
|
Related Dissertations
- Robust Stability Analysis of gene regulatory networks,TP13
- Variable data reuse factor affine projection algorithm,TN713
- Analysis and Synthesis for Time-Delay Systems with Actuator Saturation,TP13
- The Research of Theories and Methods of Dependent of Uncertain Time-Delay Systems,TP13
- Batch Process Monitoring Based on Multi-way Independent Principal Component Analysis Methods,TP277
- Complex process control system design and control strategy,TP273
- VSCF doubly-fed wind turbine maximum power point tracking control,TM614
- Research on Decoupling Technology of AUV Based on State Feedback and General Predictive Control,TP242
- Research on Parameter Identification for Train Control Model and Its Online Learning Algorithms,U284.48
- The Inference of the Inhibition of 3-Hydroxypropionaldehyde to the Two Enzymes Based on Robustness Analysis,TQ920.1
- Based on Support Vector Machine Internal Model Control for Nonlinear Systems,TP11
- Research on Performance of Electro-hydraulic Control Multi-axis Vehicle with Full-wheel Steering Mode,U463.4
- Constrained motion mechanism control performance and design requirements estimated,TM921.541
- Double Rough Integrals and Recognition of the System,O159
- MPCE experimental device three level system modeling and control algorithms,TP273
- The Modeling and Implementation of Reflow Temperature Control System,TG43
- Design of Integral Test System of Dynamically Tuned Gyroscope,V241.5
- Study on Building Envelope Comprehensive Thermal Performance Based on System Identification Theory,TU111.4
- Model-based rapid test method equipment,TJ06
- Macro- micro dual-drive platform for the realization of high-precision two-dimensional motion,TH703
- Identification of the civil justice system in our country Reflection and Reconstruction,D918.9
CLC: > SCIENCE AND > Journal of Systems Science > Systems Engineering > Systems Analysis > System identification
© 2012 www.DissertationTopic.Net Mobile
|