Community Profile

photo

Rajiv Singh

MathWorks

Last seen: 1日 前 2011 以来アクティブ

Interested in System Identification, Control System Design, Machine Learning, Optimization, Predictive Maintenance

Programming Languages:
Python, C, Java, PHP, R, MATLAB, SQL, HTML, Perl, Fortran
Spoken Languages:
English, Hindi
Professional Interests:

Statistics

All
  • 5-Star Galaxy Level 3
  • Personal Best Downloads Level 1
  • First Review
  • First Submission
  • 6 Month Streak
  • Revival Level 3
  • Knowledgeable Level 4
  • First Answer

バッジを表示

Content Feed

表示方法

回答済み
I would like to edit the properties of the confidence regions plotted using the resid function
The residue plot curves and their standard deviations *that result in the confidence bound patch) are computed in iduis.plots.re...

1日 前 | 0

回答済み
How can I set nonlinear constraints in a nonlinear grey-box model?
Linear or nonlinear constraints are not supported in nlgreyest directly. Depending upon the problem, you can sometimes get away ...

12日 前 | 0

回答済み
How does Matlab System Identification Tool estimate Transfer Fcts?
See the tfest reference page, Algorithms and References sections.

約2ヶ月 前 | 0

回答済み
Online Parameter Indentification of SIMO System in Simulink
There is no multi-output recursive estimator available today in System Identification Toolbox; this is a limitation. What you ne...

約2ヶ月 前 | 0

回答済み
Obtain transfer function from (noisy) measurement data and use this transfer function for control in simulink
Automatic order determination is not easy/trivial in general. The closest we have to this is automatic selection of state-space ...

約2ヶ月 前 | 0

回答済み
How to use arxstruc with multiple input multiple output ( MIMO ) systems?
The order combinations accepted by arxstruc can be generated by using the STRUC command; see: Generate model-order combinations ...

約2ヶ月 前 | 1

回答済み
Mutivariate regression using Regression Learner App
I would recommend looking at the System Identification Toolbox. It provides many functions for performing linear and nonlinear r...

約2ヶ月 前 | 0

回答済み
Transfer Function Models in the System Identification App
The name "Transfer function" is reserved for linear transfer functions (equivalently, linear ODEs) in System Identification Tool...

約2ヶ月 前 | 0

回答済み
Output of Transfer Function in Sys ID App not the same as workspace
In addition to the input, you need to ensure that you are using the same initial conditions. See: Estimate Initial Conditions f...

約2ヶ月 前 | 0

回答済み
How to develop multi variation equation
+1 on Walter Roberson's comments. In the dynamic system modeling area, the additional information, or assumption, rquired is th...

約2ヶ月 前 | 0

回答済み
MOESP algorithm by using n4sid command for discrete time data
The issue is not with the sample time choice but with the system itself. It seems that the data from a system with undamped pole...

約2ヶ月 前 | 0

回答済み
Using System Identification Toolbox More Effectively
If you have input and output signals separately, you will need to filter both identically, so that in the resulting transfer fun...

約2ヶ月 前 | 1

回答済み
parameter optimization in function
See also Classical Pendulum: Some Algorithm-Related Issues - MATLAB & Simulink Example (mathworks.com)

約2ヶ月 前 | 0

回答済み
Simulated and predicted response of time-series idnlgrey model in Matlab
IDNLGREY is an "output-error" model, that is, the noise affacts only the output measurements and not the state updates. Hence th...

3ヶ月 前 | 0

| 採用済み

回答済み
How to train a neural-network-based NARX model with multiple time series, each corresponding to a different value of a control parameter (to be included as additional input)
This use case/requirement seems like an extension of linear parameter varying modeling (LPV) framework.There is a certain parame...

4ヶ月 前 | 0

回答済み
Trying to simulate NLARX model in Simulink throws an error
This appears to be a bug. Please reach out to technical support or use the "Report a bug" link on Bugs Existing in R2022a | Bug ...

4ヶ月 前 | 0

回答済み
Data analysis from measurements (PRBS injected to a system -> how to plot the bode of the system response)
This could be seen as an exercise in system identification. Use functions like TFEST,SSEST, ARX to fit a model to the (u,y) data...

4ヶ月 前 | 0

回答済み
How to use chi2gof in system identification white residual test?
The approach looks fine to me in principle, hard to say more without looking at the data. One thing you can try is call RESID wi...

4ヶ月 前 | 0

| 採用済み

回答済み
Can you please provide a general explanation of how the algorithm implemented in the SSEST function works?
ssest contains multiple algorithms for fitting time- and frequency domain data. Roughtly speaking the time-domain identification...

4ヶ月 前 | 0

回答済み
LOES of a high order state space model
You could attempt this in frequency domain. G = frd(OriginalModel,w) % w is a suitably chosen frequency grid ReducedModel = ss...

約2年 前 | 1

| 採用済み

回答済み
How to build a single input multiple output ARX or ARMAX model with MATLAB
Identification routines want variables to be arranged along the columns, time along rows. Your data "y" is transposed. Also, the...

約2年 前 | 0

| 採用済み

回答済み
Use of modalfrf for operating measurements
This is essentially a system identification problem. You have non-parametric (tfestimate, spa, spafdr, etfe) techniques and para...

約2年 前 | 0

| 採用済み

回答済み
How to remove delay from idtf object?
You will need an invertible realization. Try high order transfer function estimations with no delays. Or, if the estimated model...

約2年 前 | 0

| 採用済み

回答済み
Testing different optimization methods on a state space model by solving ODEs
The closest infrastructure to this style of numerical optimization approach is "grey box identification". See idgrey, idnlgrey, ...

約2年 前 | 0

| 採用済み

回答済み
nlarx model initial conditions
You can prefix estimation data (both input and output signals) with nd zeros, where nd = maximum lag in the model. Initial condi...

約2年 前 | 0

| 採用済み

回答済み
How to force tfest to estimate the process with "only real poles" ?
TFEST cannot guarantee real poles. If you can work with <=3 poles and <=1 zero, try PROCEST. This is a process model estimator...

約2年 前 | 3

| 採用済み

回答済み
What is the difference between FRD and IDFRD
Both FRD and IDFRD are used to store Freqyency Response Data, that is, the complex frequency response vector (Mag.*exp(i*Phase))...

約2年 前 | 1

| 採用済み

回答済み
How to estimate the parameter in a customized transfer function
Grey-box identification is an option. You will need to write a function that takes K0 and a0 as inputs, and returns state-space ...

約2年 前 | 0

回答済み
Minimum input data resolution
Look up Nyquist Sampling Theorem. If you are sampling (hopefully with anti-aliasing) at 1Hz then you cannot theoretically captur...

約2年 前 | 0

| 採用済み

回答済み
Well-identified fitted process model does not behave like data on simulink
You are almost there. Convert the model into state-space form and use it for simulation. For initial conditions, you will need t...

約2年 前 | 0

| 採用済み

もっと読み込む