Brainscape's Knowledge GenomeTM

Browse over 1 million classes created by top students, professors, publishers, and experts.


See full index

TAS > Chapter 1 > Flashcards

Chapter 1 Flashcards

1
Q

What is a model?

A
  • Based on Original System
  • Reflects Relevant Properties
  • Simplification of Reality
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

What are the uses of Models?(8)

A
  • Simulation
  • Control Design and Testing
  • Performance / Behavior Eval.
  • Fundamental Insight
  • Online Controllers
  • Design Assessment / Optimiz.
  • Safety Assessment
  • Certification
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

What are three diagrams used in modelling and what for?

A

Block Diagrams: To model the building blocks of a system

Internal Definition Diagrams: To model interactions between blocks

Sequence Diagrams: To model interactions over time

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

What are some typical properties of a system? (3)

A
  • Inner Structure
  • System Boundaries
  • Interaction with Environment
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

What are Subsystems?

A

Elements within a system that themselves are systems.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

What is System Engineering?

A

Development of systems capable of fulfilling a given task while accounting for certain requirements

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

What does an Aircraft system consist of? (7)

A
  • Flight Control Systems
  • Energy Supply and Distribution
  • Cabin and Payload systems
  • Flight Gear and Doors
  • Propulsion and APU
  • Avionics
  • Safety and Emergency Systems
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

What are the three main types of models?

A
  • Visual
  • Conceptual
  • Mathematical
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

What is a deterministic model?

A
  • Outcome is certain given initial values and boundary conditions
  • Represents an ideal system
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

What is a Probabilistic / Stochastic model?

A
  • Includes random component
  • Outputs are random variables that can take on range of values
  • Same input can lead to different outputs
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

What are data driven and first-principle models?

A

First principle models are physics based

Data driven models are statistical

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

What are properties of statistical data driven models?

A
  • Non-deterministic
  • Based on data generation process
  • Data comes from greater population using sampling (sampling methods used)
  • Hypothesis is made about real data generating process in attempt to capture nature of process using statistical tools
    (what statistical method represents the process best)
  • The goal is to infer statements about real world process
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

What are the purposes of the training and data sets?

A

Training set is used the train the model.

Predictions need to be made in the data set.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

What is the process for creating a data driven statistical model?

A

Train on training set –

Evaluate on validation set – tweak based on results –

Pick model that does best on validation set –

Confirm results on Test Set–

Repeat –

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

What is accuracy and what is precision?

A

Accuracy: Describes how close values are to real value

Precision: Describes how close values are to each other

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

What is model fiedelity?

A
  • Describes how accurately the model can describe the real system in terms of features captured and accuracy of results
17
Q

What is Computational or Algorithm sided complexity?

A
  • Assesses computational time requirement
  • Assesses memory storage requirement
  • Assesses feasibility , duration of simulations
  • Assesses applicability of controllers
18
Q

What is the big O notation from lowest to highest?

A

O(1) < O(log N) < O(N) < O(N log N) < O(N^2) < O(2^N) < O(N!)

19
Q

What does problem-sided / model complexity describe?

A
  • How complex is model structure
  • Number of parameters / predictors / features used
  • Relates to generalization
  • Is model not too complex but complex enough
20
Q

What is overfitting and underfitting in regards to mode Comlexity?

A

Underfitting:
- Not enough features
- Cannot capture relevant effects
- Important aspects neglected

Overfitting:
- Irrelevant info captured
- Overtrained and cannot generalize from training to dataset
- Model degree to high

21
Q

What should be done in case of underfitting?

A
  • Increase order of polynomial
  • Switch to non-linear model
  • Get different dynamics of the system
22
Q

How do you avoid overfitting?

A
  • Decrease order of polynomial
  • Decrease range of factors
  • Increase training sets
23
Q

What is cross-validation error

A

Indicator of generalization quality

24
Q

How do you obtain cross-validating error?

A
  1. Split training and data set into q equal subsets randomly
  2. Remove first subset and fit model to remaining data
  3. Predict removed subset using model fitted to remaining data
  4. Remove second subset from data and fit to remaining data
  5. Predict removed subset using model fitted to remaining data
  6. Iterate till no subsets left

Minimum of 5 sets suggested

25
Q

What is the formula for cross validation error?

A

E_{cv} = \frac{1}{n} * \sum_{i=1}^n (y^i - \hat y^i) ^2

26
Q

What is the degree of abstraction?

A

Refers to how far a physics based model distances itself from reality in terms of physical insight

27
Q

What is white-box modelling?

A
  • Complex understanding of inner working of system
  • Physical law-driven
  • Can be difficult to obtain
28
Q

What are grey box models?

A
  • Limited knowledge of inner systems
  • Capture essential information
  • Partly data-driven
29
Q

What are black box models?

A
  • No knowledge of inner system
  • Only IO behavior
  • Statistics/Machine learning used to build model
  • Can capture complex behaviors
  • Fully data driven
30
Q

What are decision criterion when choosing between white/gray/black box?

A
  • Prior Knowledge of System
  • Complexity of System
  • Accuracy of Requirements
  • Importance of Explainability
  • Importance of Insight
  • Availability of Data
  • Computational Availability
31
Q

What are parametric and non-parametric models?

A

Parametric models:
- Based on finite set of parameters

  • Response is a function of input variables and parameters

Non-parametric models:
- Parameter space is infinite

  • No assumption on distribution data
  • Number of parameters can grow
32
Q

What are continuous and discrete models?

A

Continuous models:
- Output changes over time

  • Assumed behavior of ideal physical models

Discrete models:
- Output changes only at discrete points in time

  • Computer based models are discrete
33
Q

What is a dynamic system?

A

A system whose state evolves over time

34
Q

What are advantages of data driven dynamic models?

A
  • Effective compromise between high accuracy, low complexity and low computational cost
  • Can be used for a variety of aerospace applications
35
Q

What is the system identification process?

A
  1. Do experiment on system to derive data
  2. Use data to do model identification
  3. Validate model using system
36
Q
A

TAS (12 decks)

Brainscape helps you reach your goals faster, through stronger study habits.
© 2024 Bold Learning Solutions. Terms and Conditions