AI Enabling Technologies and Intelligent control

Presentation outline
Definition of Artificial intelligence (AI)

AI algorithm

Applications of AI

Current Enabling Technologies of AI

Artificial Intelligent for control system

By Workagegn T. 1
 Definition of Artificial intelligence

It deals with the creation of intelligent system, that can reason, learn, and act
autonomously

Artificial intelligence is a way of making a machine to think intelligently, in the

similar manner that humans think.

It refers to problem solving, search and control strategies, speech recognition,
natural language understanding, computer vision, expert systems, etc.

AI algorithm includes: Machine learning, Genetic Algorithm, Swarm

optimation , Fuzzy logic control etc..
By Workagegn T. 2
 AI algorithm
AI algorithms are a set of instructions or rules that enable machines to learn, analyze
data and make decisions based on that knowledge.

There are different types of machine learning (ML) learning algorithms:

a) Supervised learning:

b) Unsupervised learning

c) Reinforcement learning

By Workagegn T. 3
 Machine learning algorithm
Supervised learning
Unsupervised learning Reinforcement learning
Teaching a machine using A machine is train using unlabeled An agent is interacting with the
label data data environment by producing action and
discover s error and rewards
Re • Predicting a continuous • Finding pattern and data
to find occurrences b/n
No predefined data
gr quantity Asso them
• Training models through
• Number of possibility • like items that are occurs
es and predict a single
ciati
on together trial and error to learn
sio output . optimal behavior in an
n
Cla environment.
• Predicting a label or class Clus • Division of objects
ssif teri
icat ng • Algorithm:
ion • Linear regression • Algorithm :
Al
• Logistic regression . • Q-learning.
• Support vector machine • K-means
go .
rit • K-nearest neighbor • C-means
• Random forest
h (e.g. in control and medical system
m
e.g., image recognition) (e.g., training robots
By Workagegn T. for navigation) 4
 Applications of AI
 AI has applications in all fields of human study, such as economics, environment, engineering, health center etc..

Some of the applications of AI are listed below:

 Machine vision
 Speech understanding
 Natural Language Processing
 Robotics and cob tics: Intelligent control algorithm , planning, Decision- making and perception
 In game development
 In medical service
 Military operation
 In industry ( Blockchain and distributed data): share information for different people within the
same time

By Workagegn T. 5
 AI for Intelligent Control
Control system classification based on algorithm
 Classical Control Systems : algorithm based on pre-programmed rules and models, struggle with complex
dynamic modeling.
Classical Control Systems:
 Established techniques relying on mathematical models.
 Well-suited for linear systems with well-defined dynamics.
 Limited adaptability to complex or nonlinear systems.
 Intelligent Control Systems: Introduces adaptability, learning, and decision-making capabilities and used in
robust system design.

Intelligent Control Systems:

 Use artificial intelligence for decision making.
 Handle complex, nonlinear systems with imprecise models.
6
 Improved performance, robustness, and learning capabilities. By Workagegn T.
 Intelligent Controls with AI
• Predictive Control: Explain how AI can be used to predict future behavior of
systems and adjust control settings proactively. (e.g., predictive maintenance
in manufacturing)
• Adaptive Control: Discuss how AI can help control systems adapt to
changing environments or unexpected disturbances. (e.g., self-driving cars
adjusting to weather conditions)
• Optimal Control: Explore how AI can be used to optimize control strategies
for achieving desired outcomes efficiently. (e.g., optimizing traffic light
timing for reduced congestion)
• Human-Machine Collaboration: Discuss the potential of AI for assisting
human operators in control tasks, improving decision-making, and reducing
workload.
By Workagegn T. 7
 Examples of AI in Control Systems
1. Self-driving Cars: Use AI for perception, planning, and control
Reference
Trajectory Cost function
generation

P lan t dyn am ics

Control law

Sensors
State
estimation

AI algorithm

By Workagegn T. 8
 cont...
Industrial Robots: Learn from demonstrations and adapt to
variations in production.

Smart Grids: Optimize energy distribution and manage peak

demand.

Medical Systems: Learn user preferences and adjust set-point

settings for comfort and efficiency.

By Workagegn T. 9
 Benefits of AI in control system

a. Improved efficiency and performance: Optimize processes, reduce errors, and achieve
better outcomes.

b. Enhance Adaptability: To learn and adjust control parameters based on environment

changes, internal and external disturbance and failures in sensors readings.

c. Predictive maintenance : Anticipate equipment issues and prevent costly downtime.

d. Decision making : Handle complex situations and make real-time control decisions.

e. Etc..

By Workagegn T. 10
 yo u
h a nk
T

By Workagegn T. 11