SRI RAMAKRISHNA ENGINEERING COLLEGE
[Educational Service: SNR Sons Charitable Trust]
[Autonomous Institution, Reaccredited by NAAC with ‘A+’ Grade]
[Approved by AICTE and Permanently Affiliated to Anna University, Chennai]
[ISO 9001:2015 Certified and all eligible programmes Accredited by NBA]
VATTAMALAIPALAYAM, N.G.G.O. COLONY POST, COIMBATORE – 641 022
20ME224
AI for Mechanical Engineers
Semester - 6
B.E Mechanical Engineering
Academic Year : 2024-25
19-01-2026 SREC-MECH 1
VISION & MISSION OF THE INSTITUTE
Vision of the Institute
To become a world-class university excelling in multidisciplinary
engineering education through cutting-edge technologies and impactful
societal contributions for sustainable development.
Mission of the Institute
• Provide quality education that builds strong technical, analytical and
managerial skills for future professionals.
• Nurture creativity, innovation and research ecosystem for local and
global needs
• Foster ethics, leadership, entrepreneurial and life skills for holistic
development
• Develop technological solutions that enhance sustainability and
societal well-being through collaborations
19-01-2026 SREC-MECH 2
VISION AND MISSION OF THE DEPARTMENT
Vision of the Department
To be globally recognized for Mechanical Engineering Education and
Research.
Mission of the Department
• To design the Curriculum for the Mechanical Engineering program and
its effective implementation by integrating technical, managerial and
soft skills for successful professional career.
• To have active collaboration with distinguished alumni, industry experts
and academic experts for developing sustainable engineering
solutions.
• To empower individuals with holistic development; through innovation,
research, Entrepreneurial skills, and lifelong learning.
19-01-2026 SREC-MECH 3
PROGRAM EDUCATIONAL OBJECTIVES (PEOS)
The graduates of this program after three to five years will,
PEO1:
Pursue a successful career in mechanical engineering and
allied disciplines by providing innovative, effective, and
ethical engineering solutions to real-world challenges.
PEO2:
Exhibit professionalism, leadership, and entrepreneurial
skills, contributing towards sustainable technological and
societal advancement.
PEO3:
Collaborate effectively in interdisciplinary teams and
engage in lifelong learning to adapt to emerging
technologies .
19-01-2026 SREC-MECH 1
PROGRAMME OUTCOMES (POS)
Engineering Knowledge:
PO1 Apply knowledge of mathematics, natural science, computing, engineering
fundamentals and an engineering specialization as specified in WK1 to WK4
respectively to develop to the solution of complex engineering problems
Problem Analysis:
PO2 Identify, formulate, review research literature and analyse complex engineering
problems reaching substantiated conclusions with consideration for sustainable
development (WK1 to WK4)
Design/Development of Solutions:
PO3 Design creative solutions for complex engineering problems and design/ develop
systems/ components/processes to meet identified needs with consideration for the
public health and safety, whole-life cost, net zero carbon, culture, society and
environment as required (WK5)
Conduct Investigations of Complex Problems:
PO4 Conduct investigations of complex engineering problems using research-based
knowledge including design of experiments, modelling, analysis & interpretation of
data to provide valid conclusions (WK8)
19-01-2026 SREC-MECH 1
PROGRAMME OUTCOMES (POS)
Engineering Tool Usage:
PO5 Create, select and apply appropriate techniques, resources and modern engineering
& IT tools, including prediction and modelling recognizing their limitations to solve
complex engineering problems (WK2 and WK6)
The Engineer and The World:
PO6 Analyze and evaluate societal and environmental aspects while solving complex
engineering problems for its impact on sustainability with reference to economy,
health, safety, legal framework, culture and environment (WK1, WK5, and WK7)
Ethics:
PO7 Apply ethical principles and commit to professional ethics, human values, diversity
and inclusion; adhere to national & international laws (WK9)
Individual and Collaborative Team work:
PO8 Function effectively as an individual, and as a member or leader in
diverse/multi-disciplinary teams
Communication:
PO9 Communicate effectively and inclusively within the engineering community and
society at large, such as being able to comprehend and write effective language, and
learning differences
19-01-2026 SREC-MECH 1
PROGRAMME OUTCOMES (POS)
Project Management and Finance:
PO10 Apply knowledge and understanding of engineering management principles and
economic decision-making and apply these to one’s own work, as a member and
leader in a team, and to manage projects and in multidisciplinary environments
Life-Long Learning:
PO11 Recognize the need for, and have the preparation and ability for i) independent
and life-long learning ii) adaptability to new and emerging technologies and iii)
critical thinking in the broadest context of technological change (WK8)
19-01-2026 SREC-MECH 1
Program Specific Outcomes (PSOs)
Graduates of Mechanical Engineering at the time of graduation will be able to
PSO 1:
Design mechanical and allied systems using engineering principles,
computational tools and emerging technologies.
PSO 2:
Select suitable manufacturing processes for production of
components/systems considering quality, economy and sustainability.
PSO 3:
Apply the principles of thermodynamics and heat transfer to design
sustainable solutions for thermal systems.
19-01-2026 SREC-MECH 1
SYLLABUS
AI FUNDAMENTALS 6
Introduction - Definition - Examples of AI - History of AI - Future of AI - Intelligent Agents -
Rational Agent - Nature of Environment - Structure of Agents - AI Applications
PROBLEM SOLVING APPROACH TO AI PROBLEMS 8
Problem Solving Methods - Problem Formulation - Toy Problems - Real World Problems -
Search Strategies - Uninformed - Informed - Heuristics -Game Playing
KNOWLEDGE REPRESENTATION 8
Logical Agents - Knowledge based Agents -Propositional Logic- First Order Predicate
Calculus, Resolution Refutation Proofs and Answer Extraction.
PLANNING & LEARNING 8
Planning- State Space Search-Planning Graph-Real World Example for Planning (Air Cargo
Transport, Spare Tire problem, Block’s world) - Learning-Supervised &Unsupervised
Learning- Introduction to Reinforcement Learning.
Total Periods: 30
19-01-2026 SREC-MECH 1
Text Books
TEXT BOOKS
1. S. Russell and P. Norvig; Artificial Intelligence: A Modern Approach”, Prentice Hall, Fourth
Edition, 2020.
2. Nils J Nilson, “Principles of Artificial Intelligence”, Narosa Publishing House, Reprint
2002.
REFERENCES
1. Janet Finlay, “An Introduction to Artificial Intelligence”, CRC Press, 2020
2. Vinod Chandra S.S., Anand Hareendran S., “Artificial Intelligence: Principles and
Applications”, PHI Learning Private Limited, Second Edition.
NPTEL: [Link]
19-01-2026 SREC-MECH 1
Course Outcomes
CO CO Description PO
CO 1 Summarize the fundamentals of AI, the types of PO1
agents and its applications.
CO 2 Identify suitable search algorithms to solve PO1, PO4, PO12
problems using artificial intelligence techniques.
CO 3 Outline the concept of knowledge representation PO1, PO4, PO12
and predicate logic and transform the real-life
information
CO 4 Analyze the plan with the knowledge PO1, PO4, PO12
representation to solve real world problems.
CO 5 Utilize the learning model to model machines. PO1, PO4, PO12
19-01-2026 SREC-MECH 1
Module 1
AI Fundamentals
19-01-2026 SREC-MECH 1
Introduction
INTELLIGENCE
We call ourselves Homo
sapiens—man the
wise—because our intelligence
is so important to us
ARTIFICIAL INTELLIGENCE
It attempts not just to understand
but also to build intelligent
entities
19-01-2026 SREC-MECH 1
What is AI?
Artificial Intelligence (AI) is a branch of computer science that focuses on
creating machines capable of intelligent behavior—that is, systems that can
perceive, reason, learn, and act to achieve goals.
Systems that think like Systems that think rationally
humans Use logical reasoning and
Aim to model human thought computational models to arrive at
processes such as learning, correct conclusions.
problem-solving, and
decision-making.
Systems that act like humans Systems that act rationally
– Aim to perform tasks that Design intelligent agents that
normally require human choose actions that maximize goal
intelligence (e.g., understanding achievement based on available
language, recognizing images). information.
19-01-2026 SREC-MECH 1
What is Acting humanly: The Turing test?
Turing (1950) \Computing machinery and intelligence":
Operational test for intelligent behavior: the Imitation Game
The test checks how a machine behaves, not whether it actually thinks or
understands.
Human: “What do you do if you feel sad?”
Chatbot: “I’m sorry you’re feeling that
way. Talking to someone you trust can
help.”
An AI-based fault diagnosis system
monitors vibration data from a rotating
ELIZA (1966) and Eugene Goostman machine and outputs:
(2014) “Bearing failure detected. Recommend
replacement.”
An AI system can diagnose machine faults accurately using data patterns without
actually understanding mechanical concepts, proving that intelligence is judged
by behavior, not understanding.
19-01-2026 SREC-MECH 1
Thinking humanly: Cognitive Science
1960s \cognitive revolution": information-processing psychology replaced prevailing
orthodoxy of behaviorism
Requires scientific theories of internal activities of the brain
What level of abstraction? “Knowledge" or circuits"?
How to validate? Requires
1)Predicting and testing behavior of human subjects (top-down)
2)Direct identification from neurological data (bottom-up)
Both approaches (roughly, Cognitive Science and Cognitive Neuroscience) are now
distinct from AI
Both share with AI the following characteristic:
the available theories do not explain (or engender)
anything resembling human-level general intelligence
Hence, all three fields share one principal direction!
• Introspection
• Psychological experiments
• Brain imaging
19-01-2026 SREC-MECH 1
Thinking rationally: Laws of Thought
Normative (or prescriptive) rather
than descriptive
solving a problem “in principle” and solving
Aristotle: what are correct
arguments/thought processes?
Several Greek schools developed
various forms of logic:
notation and rules of derivation
for thoughts;
Direct line through mathematics and
philosophy to modern AI
Socrates is a man; all men are mortal; therefore Socrates is a mortal
it in practice
Problems:
1) Not all intelligent behavior is mediated by logical deliberation
2) What is the purpose of thinking? What thoughts should I have
out of all the thoughts (logical or otherwise) that I could have?
19-01-2026 SREC-MECH 1
Acting rationally
Rational behavior: doing the right thing
The right thing: that which is expected to maximize goal achievement, given the available
information.
An agent is just something that acts
A rational agent is one that acts so as to achieve the best outcome or, when there is uncertainty,
the best expected outcome.
Aristotle (Nicomachean Ethics): Every art and every inquiry, and similarly every action and
pursuit, is thought to aim at some good
19-01-2026 SREC-MECH 1
Foundations of AI
Philosophy logic, methods of reasoning mind as physical system
foundations of learning, language, rationality
• Can formal rules be used to draw valid conclusions?
• How does the mind arise from a physical brain?
• Where does knowledge come from?
• How does knowledge lead to action?
Mathematics formal representation and proof algorithms, computation,
(un)decidability, (in)tractability probability
• What are the formal rules to draw valid conclusions?
• What can be computed?
• How do we reason with uncertain information?
Economics Formal theory of rational decisions
• How should we make decisions so as to maximize payoff?
• How should we do this when others may not go along?
• How should we do this when the payoff may be far in the
future?
19-01-2026 SREC-MECH 1
Foundations of AI
Psychology Adaptation phenomena of perception and motor control
experimental techniques (psychophysics, etc.)
How do humans and animals think and act?
Linguistics Knowledge representation grammar
How does language relate to thought?
Neuroscience Plastic physical substrate for mental activity
How do brains process information?
Control theory Homeostatic systems, stability simple optimal agent design
How can we build an efficient computer?
19-01-2026 SREC-MECH 1
Examples of AI
• Manufacturing robots
• Self-driving cars
• Smart assistants
• Healthcare management
• Automated financial investing
• Virtual travel booking agent
• Social media monitoring
• Marketing chatbots
19-01-2026 SREC-MECH 1
Intelligent Agents
19-01-2026 SREC-MECH 1
Agents and environments
Agent: An agent is anything that can be viewed as:
– perceiving its environment through sensors and
– acting upon that environment through actuators
An agent program runs in cycles of: (1)perceive, (2)think, and (3)act
Agent = Architecture + Program
19-01-2026 SREC-MECH 1
Agents and environments
Human agent:
– Sensors: eyes, ears, and other organs.
– Actuators: hands, legs, mouth, and
other
body parts.
Robotic agent:
– Sensors: Cameras and infrared range
finders.
– Actuators: Various motors
Agents everywhere! – Thermostat – Cell phone – Vacuum
cleaner – Robot – Alexa Echo – Self-driving car – Human
19-01-2026 SREC-MECH 1
Vacuum cleaner
Percepts : location and contents e.g., [A, Dirty]
Actions : Left, Right, Suck, NoOp
Agent function : mapping from percepts to actions.
The agent function maps from percept histories to actions:
The agent program runs on the physical architecture to produce f
19-01-2026 SREC-MECH 1
Agent Function
19-01-2026 SREC-MECH 1
Modeling the environment
19-01-2026 SREC-MECH 1
Well-behaved agents
Rational Agent:
“For each possible percept sequence, a rational agent should select an
action that is expected to maximize its performance measure, given the
evidence provided by the percept sequence and whatever built-in
knowledge the agent has.
Rationality
Rationality is relative to a performance measure.
Judge rationality based on:
– The performance measure that defines the criterion of success(P)
– The agent prior knowledge of the environment(E)
– The possible actions that the agent can perform(A)
– The agent’s percept sequence to date(S)
19-01-2026 SREC-MECH 1
Nature of Environment
(Specifying the task environment)
• In Rationality, we specified the performance measure as, the environment,
and the agent’s actuators and sensors as judging parameters.
• We group all these under the heading of the task environment.
• For the acronymically minded, we call this the PEAS (Performance,
Environment, Actuators, Sensors).
To design a rational agent, we must specify the task environment
Consider, e.g., the task of designing an automated taxi:
19-01-2026 SREC-MECH 1
PEAS
Example: Chess player
19-01-2026 SREC-MECH 1
PEAS
19-01-2026 SREC-MECH 1
PEAS
19-01-2026 SREC-MECH 1
Nature of Environment
(Properties of the task environment)
Fully Observable Partially Observable
• Agent’s sensors give it access to • Agent can sense only partial
the complete state of the environment
environment at each point in time
• Convenient because the agent need
• Need to maintain internal state
not maintain any internal state to
keep track of the world
• E.g. Chess • E.g. Driving
An agent with no sensors in all environments then such an environment is
called as unobservable.
19-01-2026 SREC-MECH 1
Nature of Environment
(Properties of the task environment)
Single Agent Multiagent
• An environment consisting of only • An environment involving more
one agent is said to be a than one agent is a multi-agent
single-agent environment. environment.
• E.g., Maze • E.g., Football
19-01-2026 SREC-MECH 1
Nature of Environment
(Properties of the task environment)
Competitive Collaborative
• An agent is said to be in a • An agent is said to be in a
competitive environment when it collaborative environment when
competes against another agent to multiple agents cooperate to
optimize the output. produce the desired output.
• E.g. Chess • E.g. Self-driving cars
19-01-2026 SREC-MECH 1
Nature of Environment
(Properties of the task environment)
Deterministic Stochastic
• When a uniqueness in the agent’s • The stochastic environment is
current state completely determines random in nature which is not
the next state of the agent, the unique and cannot be completely
environment is said to be determined by the agent.
deterministic.
• E.g. Chess • [Link]- Driving cars
• there would be only a few possible
moves for a coin at the current state • the actions of a self-driving car are not
and these moves can be determined. unique, it varies time to time.
19-01-2026 SREC-MECH 1
Nature of Environment
(Properties of the task environment)
Episodic Sequential
• Each of the agent’s actions is divided • The previous decisions can affect all
into atomic incidents or episodes. future decisions.
• There is no dependency between • The next action of the agent depends
current and previous incidents. on what action he has taken
• In each incident, an agent receives previously and what action he is
input from the environment and then supposed to take in the future.
performs the corresponding action • E.g. Checkers
• E.g. Pick and Place robot
19-01-2026 SREC-MECH 1
Nature of Environment
(Properties of the task environment)
Discrete Continuous
• If an environment consists of a • The environment in which the
finite number of actions that can be actions are performed cannot be
deliberated in the environment to numbered i.e. is not discrete, is said
obtain the output, it is said to be a to be continuous.
discrete environment. • E.g. Self- Driving cars
• E.g. Chess • actions are driving, parking, etc. which
• Finite moves. cannot be numbered.
19-01-2026 SREC-MECH 1
Nature of Environment
(Properties of the task environment)
Known Unknown
• In a known environment, the output • In case of unknown environment,
for all probable actions is given. for an agent to make a decision, it
has to gain knowledge about how
the environment works.
19-01-2026 SREC-MECH 1
Nature of Environment
(Properties of the task environment)
19-01-2026 SREC-MECH 1
Structure of Agents
How it works inside agent?
Job of AI -- design an agent program that implements the agent function—
the mapping from percepts to actions
Architecture - this program will run on some sort of computing device with
physical sensors and actuators
agent = architecture + program
If Program recommends action – walk then architecture should have better legs
The architecture makes the percepts from the sensors available to the program,
runs the program, and feeds the program’s action choices to the actuators as
they are generated
19-01-2026 SREC-MECH 1
Agent Program
• Agent Program
take the current percept as input from the sensors and return an action
to the actuators
• Agent Function
takes the entire percept history
• Agent program takes just the current percept as input because nothing more
is available from the environment
19-01-2026 SREC-MECH 1
Kinds of Agent Programs
4 types
Simple reflex agents
Model-based reflex agents
Goal-based agents
Utility-based agents
19-01-2026 SREC-MECH 1
Simple reflex agents
• Simplest kind of agent
• These agents select actions on the basis of the current percept, ignoring the
rest of the percept history
• E.g. Vacuum Agent(we seen previous topics)
• Simple reflex behaviors occur even in more complex environments
• condition–action rule
if car-in-front-is-braking then initiate-braking
19-01-2026 SREC-MECH 1
Simple reflex agents
19-01-2026 SREC-MECH 1
Simple reflex agents
19-01-2026 SREC-MECH 1
Model-based reflex agents
▪ The most effective way to handle partial observability is for the agent to
keep track of the part of the world it can’t see now.
▪ That is, the agent should maintain some sort of INTERNAL STATE, state
that depends on the percept history and thereby reflects at least some of the
unobserved aspects of the current state.
▪ For this internal state
information about how the world evolves independently of the
agent
information about how the agent’s own actions affect the world
▪ This knowledge about “how the world works”—whether implemented in
simple Boolean circuits or in complete scientific theories—is called a
model of the world.
▪ An agent that uses such a model is called a model-based agent.
19-01-2026 SREC-MECH 1
Model-based reflex agents
19-01-2026 SREC-MECH 1
Model-based reflex agents
19-01-2026 SREC-MECH 1
Goal-based agents
• Current state of the environment is not always enough to decide what to do.
• The agent needs some sort of goal information that describes situations that
are desirable
• The agent program can combine this with the model to choose actions that
achieve the goal
19-01-2026 SREC-MECH 1
Goal-based agents
19-01-2026 SREC-MECH 1
Utility-based agents
• Goals alone are not enough to generate high-quality behavior in most
environments
• An agent’s utility function is essentially an internalization of the
performance measure
• Rational utility-based agent chooses the action that maximizes the expected
utility of the action outcomes
19-01-2026 SREC-MECH 1
Utility-based agents
19-01-2026 SREC-MECH 1
Learning agents
A learning agent can be divided into four conceptual components
learning element - responsible for making improvements
performance element - responsible for selecting external actions
The learning element uses feedback from the critic on how the agent is
doing and determines how the performance element should be
modified to do better in the future
problem generator - responsible for suggesting actions that will lead to
new and informative experiences
19-01-2026 SREC-MECH 1
Learning agents
19-01-2026 SREC-MECH 1