민감도 분석

실험계획법(DOE), 몬테카를로, 상관 기법을 사용하여 모델 파라미터에 대한 비용 함수 민감도를 분석합니다.

민감도 분석을 사용하여 Simulink^® 모델의 파라미터와 상태가 모델 출력 또는 모델 설계 요구 사항에 어떤 영향을 미치는지 평가할 수 있습니다. 민감도 분석기 또는 명령줄에서 모델을 평가할 수 있습니다. 병렬 연산 또는 빠른 재시작을 사용하여 계산 속도를 높일 수 있습니다. 민감도 분석기에서 민감도 분석을 수행한 후 분석 결과를 파라미터 추정기 앱 또는 응답 최적화기 앱으로 내보낼 수 있습니다. 민감도 분석 및 응용 사례에 대한 자세한 내용은 민감도 분석이란? 항목을 참조하십시오.

앱

민감도 분석기

설계 공간을 탐색하고 가장 영향력 있는 모델 파라미터 확인

함수

모두 확장

파라미터 샘플 생성하기

파라미터 공간 지정하기

`sdo.ParameterSpace`	Specify probability distributions for model parameters
`sdo.GriddedSpace`	Specify discrete grids of sample values for model parameters (R2023a 이후)
`combine`	Combine parameter spaces defined for sensitivity analysis (R2023a 이후)
`makedist`	확률 분포 객체 생성
`truncate`	확률 분포 객체 절단
`setDistribution`	Set distribution of parameter in `sdo.ParameterSpace` object
`addParameter`	Add parameter to `sdo.ParameterSpace` or `sdo.GriddedSpace` object
`removeParameter`	Remove parameter from `sdo.ParameterSpace` or `sdo.GriddedSpace` object
`setValues`	Set grid values of parameters in gridded parameter space (R2023a 이후)

샘플 생성하기

`sdo.sample`	Generate parameter samples for sensitivity analysis
`sdo.scatterPlot`	Scatter plot of samples
`sdo.SampleOptions`	Parameter sampling options for `sdo.sample`
`sdo.GriddingOptions`	Options for sampling gridded parameters with `sdo.sample` (R2023a 이후)

비용 함수 구성하기

시뮬레이션 시나리오 생성하기

`sdo.SimulationTest`	Simulation scenario description
`setup`	Configure simulation scenario and model for optimization and evaluation (R2024a 이후)
`restore`	Restore simulation scenario and model to their previous state (R2024a 이후)

시간 영역 요구 사항 지정하기

`sdo.requirements.SignalBound`	Piecewise-linear amplitude bound
`sdo.requirements.SignalTracking`	Reference signal to track
`sdo.requirements.StepResponseEnvelope`	Step response bound on signal
`sdo.requirements.PhasePlaneEllipse`	Impose elliptic bound on phase plane trajectory of two signals
`sdo.requirements.PhasePlaneRegion`	Impose region bound on phase plane trajectory of two signals

파라미터 요구 사항 지정하기

`sdo.requirements.FunctionMatching`	Impose function matching constraint on variable
`sdo.requirements.MonotonicVariable`	Impose monotonic constraint on variable
`sdo.requirements.RelationalConstraint`	Impose relational constraint on pair of variables
`sdo.requirements.SmoothnessConstraint`	Impose bounds on gradient magnitude of variable

주파수 영역 요구 사항 지정하기

`sdo.requirements.BodeMagnitude`	Bode magnitude bound
`sdo.requirements.ClosedLoopPeakGain`	Closed loop peak gain bound
`sdo.requirements.GainPhaseMargin`	Gain and phase margin bounds
`sdo.requirements.OpenLoopGainPhase`	Nichols response bound
`sdo.requirements.PZDampingRatio`	Damping ratio bound
`sdo.requirements.PZNaturalFrequency`	Natural frequency bound
`sdo.requirements.PZSettlingTime`	Settling time bound
`sdo.requirements.SingularValue`	Singular value bound

비용 함수 평가 구성하기

`sdo.evaluate`	Evaluate cost function for samples
`sdo.EvaluateOptions`	Cost function evaluation options for `sdo.evaluate`
`sdo.OperatingPointSetup`	Set up steady-state operating point computation
`sdo.getParameterFromModel`	Get design variables for optimization
`sdo.getStateFromModel`	Initial state for estimation from Simulink model
`sdo.getModelDependencies`	List of model file and path dependencies
`sdo.setValueInModel`	Set design variable value in model
`evalRequirement`	Evaluate design requirement

파라미터와 설계 요구 사항 간의 관계 분석하기

`sdo.analyze`	Analyze how model parameters influence cost function
`sdo.AnalyzeOptions`	Analysis options for `sdo.analyze`

도움말 항목

평가 기본 사항

민감도 분석이란?
Simulink Design Optimization™은 전역 민감도 분석을 수행합니다.
민감도 분석을 위한 파라미터 샘플 생성

민감도 분석기 앱 또는 MATLAB^® 명령줄에서 파라미터 값으로 구성된 임의 샘플을 생성하거나 민감도 분석을 위한 값으로 구성된 그리드를 지정합니다.
- Generate Random Parameter Values
- Generate Gridded Parameter Values
Analyze Relation Between Parameters and Design Requirements
Use visual and statistical analysis techniques to analyze the relationship between the parameters and design requirements.
Validate Sensitivity Analysis
Validate sensitivity analysis by checking generated parameter values, evaluation results, and analysis results.
Write a Cost Function
Write a cost function for parameter estimation, response optimization, or sensitivity analysis. The cost function evaluates your design requirements using design variable values.

앱 및 프로그래밍 워크플로

Identify Key Parameters for Estimation (GUI)
This example shows how to use sensitivity analysis to narrow down the number of parameters that you need to estimate when fitting a model.
Identify Key Parameters for Estimation (Code)
This example shows how to use sensitivity analysis to narrow down the number of parameters that you need to estimate to fit a model.
Design Exploration Using Parameter Sampling (GUI)
This example shows how to sample and explore a design space using the Sensitivity Analyzer.
Design Exploration Using Parameter Sampling (Code)
This example shows how to sample and explore a design space.
Explore Design Reliability Using Parameter Sampling (GUI)
This example shows how to use the Sensitivity Analyzer to explore the behavior of a PI controller for a DC motor.
Examine Component Alternatives Using Multi-Objective Design Space Exploration
This example shows how to identify and analyze combinations of variant components for a System Composer™ model.
Design Optimization for Robustness to Model Component Tolerances
Use sensitivity analysis and response optimization and to evaluate how well a model satisfies design requirements and optimize design variables in the presence of uncertainties in model parameters.
Design Selection Using Multiobjective Tradeoff Analysis
This example shows how to select designs by performing a multiobjective tradeoff analysis using the Sensitivity Analyzer app.

정상 상태 평가

Specify Steady-State Operating Point for Sensitivity Analysis
An operating point of a dynamic system defines the states and root-level input signals of the model at a specific time.

평가 속도 개선

Use Parallel Computing for Sensitivity Analysis
Specify model dependencies and use parallel computing for performing sensitivity analysis in the app, or at the command line.
Use Fast Restart Mode During Sensitivity Analysis
This topic shows how to speed up sensitivity analysis using Simulink fast restart.
시뮬레이션 중 액셀러레이터 모드 사용하기
Simulink Design Optimization은 Normal 시뮬레이션 모드와 Accelerator 시뮬레이션 모드를 지원합니다.
Store Intermediate Data in the App
How to speed up evaluation in the app by storing intermediate data.

민감도 분석기 작업

Specify Parameters for Design Exploration
Select model parameters for sensitivity analysis in the app.
Specify Time-Domain Requirements
Specify time-domain requirements such as signal matching, amplitude bounds, step response bounds, reference signals, elliptical bounds, and custom bounds.
Specify Parameters Requirements
Specify requirements such as monotonic, smoothness, property, and relational constraints on parameters in your model.
Specify Frequency-Domain Requirements
Specify frequency-domain requirements in the Sensitivity Analyzer.
Preprocess Data
Perform preprocessing operations such as removing offsets and filtering the data before you use it.
Create Linearization I/O Sets
Create linearization input/output sets in the Response Optimizer or Sensitivity Analyzer.
Evaluate Design Requirements
Evaluate your design requirements in the Sensitivity Analyzer app.
Use Sensitivity Analysis to Configure Estimation and Optimization
Use the results generated in the Sensitivity Analyzer to configure parameter estimation or response optimization.
Interact with Plots in the Sensitivity Analyzer
Plot and interpret parameter set, requirement, result scatter, contour, and tornado plots.

코드 생성

Generate MATLAB Code for Sensitivity Analysis for Design Space Exploration and Evaluation (GUI)
This example shows how to automatically generate a MATLAB function to solve a Sensitivity Analysis evaluation problem.
Generate MATLAB Code for Sensitivity Analysis Statistics to Identify Key Parameters (GUI)
This example shows how to automatically generate a MATLAB function to solve a Sensitivity Analysis statistics problem.