Chapter 1

Introductory concept

Concepts of plant, system and control system:

Sure! Here’s a clear breakdown of the concepts of plant, system, and control system:

1. Plant

• In control theory, the plant refers to the part of the system that is to be controlled.

• It is the physical process or device whose behavior you want to influence.

• Examples:

o A motor in a robotic arm

o The temperature inside a furnace

o The position of an airplane

• The plant takes an input (control signal) and produces an output (response or measured
variable).

2. System

• A system is a collection of components or elements that interact to perform a specific

function.

• In general, it can be anything from a mechanical device, an electrical circuit, a biological

process, or even an economic model.

• Systems have inputs, outputs, and sometimes internal states.

• Systems can be classified into:

o Open-loop system: No feedback, output doesn’t affect input.

o Closed-loop system: Output is fed back to input to maintain desired performance.

3. Control System

• A control system is a system designed to regulate or manage the behavior of other

devices or systems.

• Its primary goal is to ensure the output follows the desired reference or setpoint.

• It does this by adjusting inputs based on feedback from the output.

• Types of control systems:

o Open-loop control system: Control action is independent of output (no feedback).

o Closed-loop control system (Feedback control system): Control action depends

on output feedback.

How these relate:

Concept Description Example

Plant The device/process to be controlled Water heater, motor, aircraft
System A set of components working together Heating system, electrical grid
Control System System that manages/controls the plant Thermostat-controlled heater

➢ Control of output voltage of DC generator:

1. Field Flux Control (Adjusting Field Current)

• The output voltage of a DC generator is proportional to the magnetic flux (φ) produced
by the field winding.
 • By varying the field current (If) using a rheostat or automatic voltage regulator (AVR),
the flux changes, thereby controlling the output voltage.

• Increasing field current → increases flux → increases output voltage.

• Decreasing field current → decreases flux → decreases output voltage.

2. Speed Control

• Output 𝑣𝑜𝑙𝑡𝑎𝑔𝑒 𝑉 ∝ 𝜙 × 𝑁𝑉 ∝ 𝜙 × 𝑁𝑉 ∝ 𝜙 × 𝑁, where NNN is the speed (RPM).

• Changing the mechanical input speed NNN changes the output voltage.

• However, speed control is less common as it may affect the mechanical system.

3. Using a Compensating Winding

• Some generators use compensating windings to counteract armature reaction, helping

maintain voltage.

Basic components of a control system:

Component Description Symbol (in

diagrams)
1. Reference Input Desired value of the output (e.g., R(s)R(s) or simply
(Set Point) target speed, temperature, “Set Point”
position).
 2. Error Detector Compares the reference input E(s)=R(s)−B(s)E(s) =
(Comparator) with the feedback signal to R(s) - B(s)
calculate the error.
3. Controller Processes the error signal and PID Controller,
generates a suitable control Amplifier
signal.
4. Actuator Converts the control signal into a Motor, Servo, Relay
physical action (e.g., motor,
valve).
5. Plant (Process) The system or process being DC Motor, HVAC
controlled (e.g., motor, robot system
arm, furnace).
6. Sensor/Feedback Measures the actual output and Tachometer,
Element sends feedback to the Thermocouple
comparator.
7. Feedback Path The path through which the Often includes
output signal is sent back for sensors
comparison.

Classification of control system

➢ Based on Feedback
a) Open-Loop Control System

• No feedback from output to input.

• Control action is independent of the actual output.

• Simple but less accurate; cannot correct for disturbances or errors.
Example: Electric kettle without thermostat (heats for a fixed time regardless of actual water
temperature).

Block Diagram:

b) Closed-Loop Control System (Feedback System)

• Feedback is used to compare actual output with desired output.

• Control action depends on the error signal.

• More accurate and stable; can correct deviations.

Example: Air conditioner with thermostat (adjusts cooling based on room temperature).

Block Diagram:

➢ Based on Control Action

a) Linear Control System

• All system parameters and operations are linear (obey superposition).

• Easier to analyze mathematically.

Example: RLC electrical circuits, linear amplifiers.

b) Nonlinear Control System

• At least one component is nonlinear.

• More complex and realistic; includes saturation, dead zones, friction.
Example: Hydraulic systems, robotic arms with joint limits.

➢ Based on Time Response

a) Time-Invariant System

• Parameters of the system do not change with time.

• Behavior remains the same at any time.

Example: Resistor-based circuits with constant values.

b) Time-Variant System
• Parameters change with time.

• Harder to analyze and predict.

Example: Rocket engine dynamics (mass changes over time).

4. Based on Nature of Signals

a) Continuous-Time Control System

• Input, output, and signals are continuous functions of time.

• Modeled using differential equations.

Example: Analog electronic systems.

b) Discrete-Time Control System

• Signals are defined at specific time intervals.

• Modeled using difference equations.

• Often implemented using digital computers or microcontrollers.

Example: Digital thermostat, microprocessor-based control.

5. Based on Control Strategy

a) Manual Control System

• Human operator controls the system.
Example: Driving a car manually.

b) Automatic Control System

• Operates automatically without human intervention.

Example: Elevator system, autopilot in aircraft.

Summary Table:

Classification Type Categories

Feedback Open-loop, Closed-loop
Control Action Linear, Nonlinear
Time Response Time-invariant, Time-variant
Signal Type Continuous-time, Discrete-time
Control Strategy Manual, Automatic

Servomechanism, Regular, Process control and Disturbance signal

Here’s a clear explanation of the following control system concepts:

1. Servomechanism (Servo System)

Definition:

A servomechanism is a type of automatic control system that uses feedback to control position,
speed, or torque of a mechanical device with high accuracy.

Features:

• Always a closed-loop system.

• Responds quickly to changes in input.

• Common in systems requiring precise control.

Examples:

• Robotic arms
• CNC machines

• Antenna positioning systems

• Camera autofocus systems
Block Diagram (Simple Representation):

2. Regular Control System (General Control System)

Definition:

A regular control system refers to a general-purpose automatic control system that controls
output based on input, not necessarily needing very high precision.
Features:

• May be open-loop or closed-loop.

• Deals with general control tasks like temperature, light, or fluid levels.

• Accuracy and speed may not be as high as in servomechanisms.

Example:

• Room temperature control using a thermostat.

• Water tank level controller.

3. Process Control System

Definition:

A process control system is designed to manage and control industrial processes such as
chemical production, oil refining, power generation, etc.

Features:

• Typically closed-loop.
• Controls variables like temperature, pressure, flow, pH, etc.
 • Involves sensors, controllers (like PID), actuators (valves, motors).

Example:

• Maintaining pressure in a steam boiler.

• Controlling flow rate in a pipeline.

• Maintaining pH in a chemical reactor.

Components:

• Process (Plant)

• Measurement (Sensor)

• Controller (e.g., PLC or PID)

• Final Control Element (e.g., valve, pump)

4. Disturbance Signal
Definition:

A disturbance signal is an undesired input that affects the output of a control system but does
not come from the controller.

Characteristics:

• Comes from the environment or internal system changes.

• Control systems must be designed to reject or minimize the effect of disturbances.

• Acts as a challenge for system stability and performance.

Example:

• Sudden load change in a motor.

• Wind gusts affecting an aircraft.

• Ambient temperature changes affecting a heater system.

In a Block Diagram:
Summary Table:

Term Description Example

Servomechanism High-precision, feedback-based motion Robotic arm, camera gimbal
control
Regular Control General control systems (less precision Fan speed controller
needed)
Process Control Industrial process regulation Chemical plant, oil refinery
Disturbance Undesired input affecting system Wind, load change,
output temperature drift

Feedback in control system and effect of feedback

➢ Importance of feedback
Improves Accuracy

• Feedback continuously compares the actual output with the desired output (setpoint).
• Any error is detected and corrected.

• Result: The system becomes more precise.

Example: In a temperature control system, feedback ensures the room stays close to the target
temperature.

Reduces Sensitivity to Disturbances

• External disturbances (like load changes or noise) affect the output.

• Feedback helps the system automatically compensate for these changes.

Example: In a speed control system of a motor, if the load increases, feedback adjusts the input
to maintain speed.
Enhances Stability

• Properly designed feedback prevents the system from becoming erratic or unstable.

• It keeps system behavior predictable and safe.

• Note: Poorly designed feedback can also introduce instability (e.g., oscillations), so it
must be carefully tuned.

Allows Automatic Operation

• With feedback, systems can self-regulate without human intervention.

• This is essential in automation and robotics.

Example: Cruise control in cars adjusts throttle automatically to maintain constant speed.

Increases Robustness

• Feedback systems can handle variations in system parameters (like aging components,
temperature changes, etc.).

• The system continues to work correctly even if its internal dynamics change slightly.

Reduces Steady-State Error

• In a feedback system, the difference between the desired and actual output can be
minimized over time.

• This leads to better long-term performance.

Summary Table
Benefit Explanation
Improved Accuracy Reduces error between desired and actual output
Disturbance Rejection Minimizes effect of external disturbances
Enhanced Stability Maintains consistent, stable behavior
Automatic Adjustment Enables systems to self-correct without manual input
Robustness Handles system parameter variations
Reduced Steady-State Error Minimizes long-term error between output and input

Real-Life Examples of Feedback Systems:

• Thermostat-controlled HVAC system
 • Cruise control in cars

• Voltage regulation in power supplies

• Automatic washing machines

• Camera autofocus system

Chapter 2
Modeling a control system transfer function
approach

Introduction :
We have discussed in the previous chapter that a control system consists of a number of sub-
systems. All the sub-systems work in unison to achieve a desired output for a given input.
Mathematical modelling of sub-systems and also of the whole system is required for carrying out
performance studies. In this chapter, modelling of a control system using transfer function
approach has been dealt with.

Transfer Function:
In control theory, transfer functions are commonly used to characterize the input-output
relationship of components or systems that can be described by linear, time-invariant differential
equations. The relationship between input and output is represented by a diagram known as
block.

Definition of transfer Function

The transfer function of a linear, time-invariant system is defined as the ratio of Laplace transform
of the output to the Laplace transform of the input, under the assumption that all initial
conditions are zero.

Suppose the input–output dynamics are

The ratio of the Laplace transform of the output to the Laplace transform of the input, with all
initial conditions set to zero.

This is the most crucial concept to remember.

Equation:
ℒ[𝑜𝑢𝑡𝑝𝑢𝑡(𝑡)] 𝑌(𝑠)
𝐺(𝑠) = =
ℒ[𝑖𝑛𝑝𝑢𝑡(𝑡)] 𝑋(𝑠)

• 𝐺(𝑠) = 𝑇𝑟𝑎𝑛𝑠𝑓𝑒𝑟𝐹𝑢𝑛𝑐𝑡𝑖𝑜𝑛

• Y(s) = Laplace transform of the output signal y(t)

• X(s) = Laplace transform of the input signal x(t)

• All initial conditions are assumed to be zero.

2. Prerequisite: The Laplace Transform

The Laplace transform is the tool that converts functions of time (t) into functions of a complex
variable (𝑠 = σ + 𝑗ω). It is particularly powerful because it converts differential
equations (which are hard to solve) into algebraic equations (which are easy to solve).

A few key transforms needed for derivation:

• ℒ[𝑥(𝑡)] = 𝑋(𝑠)
dx(t)
• ℒ[ ] = 𝑠𝑋(𝑠) − 𝑥(0) (Initial condition 𝑥(0) is set to zero)
dt

𝑑𝑛 𝑥(𝑡)
• ℒ[ ] = 𝑠 𝑛 𝑋(𝑠) (with zero initial conditions)
𝑑𝑡 𝑛

1
• ℒ[∫ 𝑥(𝑡)𝑑𝑡] = 𝑠 𝑋(𝑠)

3. Step-by-Step Derivation from a Differential Equation

Most physical systems (electrical, mechanical, etc.) can be modeled by linear ordinary
differential equations (ODEs). Let's start with a general 𝑛𝑡ℎ order ODE:

𝑑𝑛 𝑦(𝑡) 𝑑𝑛−1 𝑦(𝑡) 𝑑𝑦(𝑡)

𝑎𝑛 𝑛
+ 𝑎 𝑛−1 𝑛−1
+ ⋯ + 𝑎1 + 𝑎0 𝑦(𝑡)
𝑑𝑡 𝑑𝑡 𝑑𝑡
𝑑𝑚 𝑥(𝑡) 𝑑 𝑚−1 𝑥(𝑡) 𝑑𝑥(𝑡)
= 𝑏𝑚 𝑚
+ 𝑏𝑚−1 𝑚−1
+ ⋯ + 𝑏1 + 𝑏0 𝑥(𝑡)
𝑑𝑡 𝑑𝑡 𝑑𝑡
Where:

• 𝑦(𝑡) is the system output

• 𝑥(𝑡) is the system input

 • 𝑎𝑛 , … , 𝑎𝑛−1 𝑎𝑛𝑑 𝑏𝑚 , … , 𝑏𝑚−1 are system parameters (e.g., mass, resistance, spring
constant)

Step 1: Take the Laplace Transform of both sides.

Apply the transform to each term, remembering to set all initial conditions to zero
𝑑𝑦
(𝑦(0) = 0, (0) =, 𝑒𝑡𝑐. )
𝑑𝑡

𝑑𝑛 𝑦 𝑑 𝑛−1 𝑦 𝑑𝑚 𝑥 𝑑𝑚−1 𝑥
ℒ [𝑎𝑛 𝑛 + 𝑎𝑛−1 𝑛−1 + ⋯ + 𝑎0 𝑦] = ℒ [𝑏𝑚 𝑚 + 𝑏𝑚−1 𝑚−1 + ⋯ + 𝑏0 𝑥]
𝑑𝑡 𝑑𝑡 𝑑𝑡 𝑑𝑡

Step 2: Use the linearity property of the Laplace transform.

The transform of a sum is the sum of the transforms.

𝑑𝑛 𝑦 𝑑 𝑛−1 𝑦 𝑑𝑚 𝑥 𝑑 𝑚−1 𝑥
𝑎𝑛ℒ [ 𝑛 ] + 𝑎𝑛−1ℒ [ 𝑛−1 ] + ⋯ + 𝑎0ℒ [𝑦] = 𝑏𝑚ℒ [ 𝑚 ] + 𝑏𝑚−1ℒ [ 𝑚−1 ] + ⋯ + 𝑏0ℒ [𝑥]
𝑑𝑡 𝑑𝑡 𝑑𝑡 𝑑𝑡

Step 3: Apply the derivative property.

With zero initial conditions,

𝑑𝑘 𝑦
ℒ [ 𝑘 ] = 𝑠 𝑘 𝑌(𝑠)
𝑑𝑡

𝑎𝑛 𝑠 𝑛 𝑌(𝑠) + 𝑎𝑛−1 𝑠 𝑛−1 𝑌(𝑠) + ⋯ + 𝑎1 𝑠𝑌(𝑠) + 𝑎0 𝑌(𝑠)

= 𝑏𝑚 𝑠 𝑚 𝑋(𝑠) + 𝑏𝑚−1 𝑠 𝑚−1 𝑋(𝑠) + ⋯ + 𝑏1 𝑠𝑋(𝑠) + 𝑏0 𝑋(𝑠)

Step 4: Factor out Y(s) and X(s).

(𝑎𝑛 𝑠 𝑛 + 𝑎𝑛−1 𝑠 𝑛−1 + ⋯ + 𝑎1 𝑠 + 𝑎0 )𝑌(𝑠) = (𝑏𝑚 𝑠 𝑚 + 𝑏𝑚−1 𝑠 𝑚−1 + ⋯ + 𝑏1 𝑠 + 𝑏0 )𝑋(𝑠)

Step 5: Solve for the ratio Y(s)/X(s).

This ratio is, by definition, the transfer function $G(s)$.

𝑌(𝑠) 𝑏𝑚 𝑠 𝑚 + 𝑏𝑚−1 𝑠 𝑚−1 + ⋯ + 𝑏1 𝑠 + 𝑏0

𝐺(𝑠) = =
𝑋(𝑠) 𝑎𝑛 𝑠 𝑛 + 𝑎𝑛−1 𝑠 𝑛−1 + ⋯ + 𝑎1 𝑠 + 𝑎0

4. Standard Form and Terminology

The derived equation is the general form of a transfer function. It is often rewritten by factoring
the coefficients:

𝐾(𝑠 − 𝑧1 )(𝑠 − 𝑧2 ) … (𝑠 − 𝑧𝑚 )
𝐺(𝑠) =
(𝑠 − 𝑝1 )(𝑠 − 𝑝2 ) … (𝑠 − 𝑝𝑛 )
 • Zeros (𝒛𝟏 , 𝒛𝟐 , … , 𝒛𝒏 ): The roots of the numerator polynomial. Values of 𝑠 that make
𝐺(𝑠) = 0

• 𝑷𝒐𝒍𝒆𝒔(𝒑𝟏 , 𝒑𝟐 , … , 𝒑𝒏 ): The roots of the denominator polynomial. Values of 𝑠 that make

𝐺(𝑠) → 0.
𝑏𝑚
• 𝑮𝒂𝒊𝒏(𝑲): A scalar value that scales the output. 𝐾 = in the general form.
𝑎𝑛

The poles and zeros completely define the dynamic behavior of the system (stability, speed of
response, oscillations), while the gain defines the overall scaling.

5. Concrete Example: Mass-Spring-Damper System

Let's derive the transfer function for a classic mechanical system.

System: A mass m connected to a spring with stiffness K and a damper with damping coefficient
c. An external force F(t) is the input. The position y(t) is the output.

Step 1: Write the Differential Equation.

From Newton's second law:
∑ 𝐹 = 𝑚𝑎
𝑑𝑦 𝑑2𝑦
𝐹(𝑡) − 𝑐 − 𝑘𝑦 = 𝑚 2
𝑑𝑡 𝑑𝑡
Rearrange to standard form:
𝑑2𝑦 𝑑𝑦
𝑚 2
+𝑐 + 𝑘𝑦 = 𝐹(𝑡)
𝑑𝑡 𝑑𝑡
Step 2: Take the Laplace Transform (zero initial conditions).
𝑚(𝑠 2 𝑌(𝑠)) + 𝑐(𝑠𝑌(𝑠)) + 𝑘𝑌(𝑠) = 𝐹(𝑠)

Step 3: Factor and solve for G(s).

(𝑚𝑠 2 + 𝑐𝑠 + 𝑘)𝑌(𝑠) = 𝐹(𝑠)
𝑌(𝑠) 1
𝐺(𝑠) = = 2
𝐹(𝑠) 𝑚𝑠 + 𝑐𝑠 + 𝑘
This is the transfer function for the mass-spring-damper system, relating the output position
Y(s) to the input force F(s).
Summary
Step Action Result
1 Define the system's differential 𝑑𝑛 𝑦 𝑑𝑚 𝑥
𝑎𝑛 + ⋯ + 𝑎 0 𝑦 = 𝑏𝑚 + ⋯ + 𝑏0 𝑥
equation. 𝑑𝑡 𝑛 𝑑𝑡 𝑚
2 Take the Laplace Transform of both 𝑎𝑛 𝑠 𝑛 𝑌(𝑠) + ⋯ + 𝑎0 𝑌(𝑠)
sides. = 𝑏𝑚 𝑠 𝑚 𝑋(𝑠) + ⋯ + 𝑏0 𝑋(𝑠)
3 Factor out Y(s) and X(s). (𝑎𝑛 𝑠 𝑛 + ⋯ + 𝑎0 )𝑌(𝑠)
= (𝑏𝑚 𝑠 𝑚 + ⋯ + 𝑏0 )𝑋(𝑠)
4 𝑌(𝑠)
Solve for the ratio 𝑋(𝑠). 𝑏𝑚 𝑠 𝑚 + ⋯ + 𝑏0
𝐺(𝑠) =
𝑎𝑛 𝑠 𝑛 + ⋯ + 𝑎0
This process provides a powerful method to analyze the behavior of dynamic systems in the
complex frequency domain (s-domain) rather than the time domain.

1. Fundamental Mechanical Elements

The behavior of any complex mechanical system is built from three basic elements:

Element Translational (Linear) Rotational (Angular)

Inertia Mass (m) Moment of Inertia (J)
Opposes acceleration. Opposes angular acceleration.
𝑑2 𝑥 𝑑2 θ
Force: 𝐹 = 𝑚 ⋅ 𝑎 = 𝑚 ⋅ 𝑑𝑡 2 Torque: 𝜏 = 𝐽 ⋅ 𝛼 = 𝐽 ⋅ 𝑑𝑡 2
Friction (Damper) Damper (c) Rotational Damper (c)
Opposes velocity. Opposes angular velocity.
𝑑𝑥 𝑑θ
Force: 𝐹 = 𝑐 ⋅ 𝑣 = 𝑐 ⋅ 𝑑𝑡 Torque: 𝜏 = 𝑐 ⋅ 𝜔 = 𝑐 ⋅ 𝑑𝑡
Spring Spring (k) Torsional Spring (k)
Opposes displacement. Opposes angular displacement.
Force: 𝐹 = 𝑘 ⋅ 𝑥 Torque: 𝜏 = 𝑘 ⋅ 𝜃

Hydraulic system
Core Principle: Pascal's Law

The fundamental principle governing hydraulic systems is Pascal's Law:

Pressure applied to a confined fluid at rest is transmitted undiminished in every direction
throughout the fluid and acts at right angles to the surfaces of the container.

This means a small force (F1) applied to a small area (A1) can generate a much larger
force (F2) on a larger area (A2).
𝐹1 𝐹2 𝐴2
𝑃1 = 𝑃2 ⇒ = ⇒ 𝐹2 = 𝐹1
𝐴1 𝐴2 𝐴1

This force multiplication is the key advantage of hydraulic systems.

Key Components & Their Models

To build a control system model, we need to understand the dynamics of each component.

1. Hydraulic Actuator (Hydraulic Cylinder)

This is the most common output device. It converts fluid power into linear mechanical motion.

o Input: Volumetric Flow Rate, q(t) (m³/s)

o Output: Piston Position, y(t) (m) or Piston Velocity, v(t) (m/s)

Deriving the Transfer Function:

The flow rate q into the cylinder chamber has two jobs:

1. Move the piston: 𝑞𝑑𝑖𝑠𝑝𝑙𝑎𝑐𝑒𝑚𝑒𝑛𝑡 = 𝐴 ∗ 𝑣 = 𝐴 ∗ 𝑑𝑦/𝑑𝑡

2. Compress the fluid (due to fluid compressibility and chamber

flexibility): 𝑞𝑐 𝑜𝑚𝑝𝑟𝑒𝑠𝑠𝑖𝑜𝑛 = (𝑉/𝛽) ∗ 𝑑𝑃/𝑑𝑡

1. V is the volume of fluid under compression (m³)

2. β is the effective Bulk Modulus of the fluid (N/m² or Pa)

The total flow is the sum:

𝑑𝑦 𝑉 𝑑𝑃
𝑞(𝑡) = 𝐴 +
𝑑𝑡 β 𝑑𝑡

The force from the piston is:

𝑑2𝑦 𝑑𝑦
𝐹(𝑡) = 𝐴 ⋅ 𝑃 = 𝑚 2 + 𝑐 + 𝐹𝑙𝑜𝑎𝑑
𝑑𝑡 𝑑𝑡
(where m is the load mass, c is viscous damping, and F_load is an external force)
 Chapter 3
Modeling a control system block diagram
representation
Introduction
Any control system will have a number of control components. A control system can be
represented in block diagram form. For making a block diagram, first the transfer function of the
system components are determined. They are then showed in respective blocks. These blocks are
connected by arrows indicating the direction of flow of signals in the control system whose block
diagram is being represented. The signals can pass only in the direction of arrows represented in
the diagram. The arrow head pointing towards a particular block indicates the input to the system
component and the arrow head leading away from the block indicates the output. All the arrows
in a block diagram are referred to as signals. For complicated systems, the block diagram
interconnecting all the sub-systems becomes a complex one. Reduction of such complex block
diagram makes it easy to determine the overall transfer function of the whole system. Various
techniques are then applied to analyse the performance of the system.

Advantages of Block diagram representation

The following are the main advantages of block diagram representation of control systems.
i) The overall block diagram of a system can be easily drawn by connecting the
blocks according to the signal flow. It is also possible to evaluate the
contribution of each of the components towards the overall performance of the
control system.
ii) Block diagram helps in understanding the functional operation of the system
more readily than examination of the actual control system physically. It may
be noted that block diagram drawn for a system is not unique, that is, there
may be alternative ways of representation of a system in block diagram form.
Block diagram representation of an error detector

In a feedback control system there is one reference input signal which corresponds to the desired
output and one feedback signal. The feedback signal is received from the output (as a fraction of
the output) if there is any deviation of the output from the desired output. Error detector is a
summing device which produces a resultant signal. This signal is the difference between the
reference input and the feedback signal of the control system. As shown in Fig. 3.1, R(s) is the
reference input corresponding to the desired output, C(s) is the desired output, and B(s) is the
feedback signal.

Characteristic equation of a Control System:

What is the Characteristic Equation?

The characteristic equation of a linear time-invariant (LTI) control system is obtained by setting
the denominator of the system's closed-loop transfer function equal to zero.

It is a polynomial in the complex variable s (from the Laplace domain). The roots of this
polynomial are called the poles of the closed-loop system.

2. How to Find the Characteristic Equation

Step 1: Find the Closed-Loop Transfer Function

Consider a standard negative feedback system:

• G(s): Transfer function of the plant

 • H(s): Transfer function of the sensor/feedback path

The closed-loop transfer function T(s) from reference input R(s) to output C(s) is:
𝐶(𝑠) 𝐺(𝑠)
𝑇(𝑠) = =
𝑅(𝑠) 1 + 𝐺(𝑠)𝐻(𝑠)
Step 2: Set the Denominator to Zero
The characteristic equation is:
1 + 𝐺(𝑠)𝐻(𝑠) = 01 + 𝐺(𝑠)𝐻(𝑠) = 0

This is the most important form to remember. G(s)H(s) is called the open-loop transfer
function.

Example:
𝐾
Let 𝐺(𝑠) = 𝑠(𝑠+4) 𝑎𝑛𝑑 𝐻(𝑠) = 1 (unity feedback).

𝐾
• Open-loop transfer function: 𝐺(𝑠)𝐻(𝑠) = 𝑠(𝑠+4)

• Characteristic equation: 1 + 𝐺(𝑠)𝐻(𝑠) = 0

𝐾
1+ =0
𝑠(𝑠 + 4)
Multiply through by s(s+4) to get:
𝑠(𝑠 + 4) + 𝐾 = 0
𝑠2 + 4𝑠 + 𝐾 = 0𝑠2 + 4𝑠 + 𝐾 = 0 <-- This is the characteristic equation.

Rules of block diagram simplification:

1. Series (Cascade) Blocks

Blocks connected in series can be combined by multiplying their transfer functions.

Rule: 𝐺𝑒𝑞 = 𝐺1 ⋅ 𝐺2

2. Parallel Blocks

Blocks connected in parallel can be combined by adding or subtracting their transfer functions.
Rule: 𝐺𝑒𝑞 = 𝐺1 ± 𝐺2
3. Moving a Summing Junction

• Moving a summing junction AFTER a block: You must add the same block in the other
path.

• Moving a summing junction BEFORE a block: You must add the same block in the other
path.

4. Moving a Pickoff Point

 • Moving a pickoff point AFTER a block: You must add the same block in the feedback
path.

• Moving a pickoff point BEFORE a block: You must add the same block in the feedback
path.

5. Feedback Loop Reduction (Most Important Rule)

This is the fundamental rule for closing loops. It reduces a feedback structure to a single block.
𝐺
Rule: 𝐺𝑒𝑞 = 1∓𝐺𝐻

• Use 𝟏 + 𝑮𝑯 for negative feedback.

• Use 𝟏 − 𝑮𝑯 for positive feedback.

Step-by-Step Simplification Procedure

The goal is to repeatedly apply the rules above to collapse the diagram. Follow these steps:

1. Combine Cascade Blocks: Multiply blocks in series.

2. Combine Parallel Blocks: Add or subtract blocks in parallel.

3. Eliminate Feedback Loops: Apply the feedback rule to inner loops. Start from the
innermost loop and work your way outward.

4. Shift Summing Junctions and Pickoff Points: Use the moving rules to get summing
junctions and pickoff points into positions that allow you to apply rules 1, 2, and 3. This
is often the key to solving tricky diagrams.

5. Repeat: Continue until the diagram is a single block.

Block diagram representation of an electrical network:

The process involves two main steps:
1. Modeling: Find the transfer function of the electrical network using circuit laws (Ohm's
Law, Kirchhoff's Laws) and Laplace transforms.
2. Representation: Express this transfer function as a block diagram, often revealing
internal feedback paths within the circuit itself.

Step 1: Modeling the Electrical Network

The goal is to derive the transfer function, typically relating an input voltage ($V_{in}(s)$) to an
output voltage (𝑉𝑜𝑢𝑡 (𝑠)) or current.

Key Principle: Use Impedance (𝒁(𝒔))

In the Laplace domain (s-domain), passive elements have "impedance":

• Resistor (R): 𝑍𝑅 (𝑠) = 𝑅

1
• Capacitor (C): 𝑍𝐶 (𝑠) = 𝑠𝐶

• Inductor (L): 𝑍𝐿 (𝑠) = 𝑠𝐿

Circuit analysis (using voltage divider rule, Kirchhoff's laws, etc.) becomes algebraic, making it
easy to find transfer functions.

Step 2: Block Diagram Representation

Once you have the transfer function, you can represent it as a single block. However, for more
complex circuits or to understand internal dynamics, we break it down into smaller functional
blocks, which often show natural feedback loops within the circuit.

A common technique is to use summing junctions for Kirchhoff's Voltage Law (KVL)
and integrators (1/s) for capacitors.

Worked Example 1: RC Low-Pass Filter

Let's derive the block diagram for a simple RC filter.

Circuit:
Input voltage 𝑉𝑖𝑛 (𝑡) applied to a series combination of a resistor R and capacitor C. Output
voltage 𝑉𝑜𝑢𝑡 (𝑡) is taken across the capacitor.

Step 1: Derive the Transfer Function

1. The impedance of R is R.

2. The impedance of C is 1/(𝑠𝐶).

3. Using the voltage divider rule in the s-domain:

1
𝑍𝐶 (𝑠)
𝑉𝑜𝑢𝑡 (𝑠) = 𝑉𝑖𝑛 (𝑠) ⋅ = 𝑉𝑖𝑛 (𝑠) ⋅ 𝑠𝐶
𝑍𝑅 (𝑠) + 𝑍𝐶 (𝑠) 1
𝑅 + 𝑠𝐶

4. Simplify:
𝑉𝑜𝑢𝑡 (𝑠) 1
𝐺(𝑠) = =
𝑉𝑖𝑛 (𝑠) 1 + 𝑠𝑅𝐶

Step 2: Create the Block Diagram

We can represent this transfer function as a single block:

text

[𝑉𝑖 𝑛(𝑠)]−→ [1/(1 + 𝑠𝑅𝐶)]−→ [𝑉𝑜 𝑢𝑡(𝑠)]

More Insightful Representation:

Let's derive it from the circuit's differential equation to see the feedback structure.
𝑑𝑣𝑜𝑢𝑡
1. The current 𝑖(𝑡) through the circuit is 𝑖(𝑡) = 𝐶 .
𝑑𝑡

𝑑𝑣𝑜𝑢𝑡
2. The voltage across the resistor is 𝑉𝑅 (𝑡) = 𝑖(𝑡)𝑅 = 𝑅𝐶 𝑑𝑡

𝑑𝑣𝑜𝑢𝑡
3. From KVL: 𝑉𝑖𝑛 (𝑡) = 𝑉𝑅 (𝑡) + 𝑉𝑜𝑢𝑡 (𝑡) = 𝑅𝐶 + 𝑉𝑜𝑢𝑡 (𝑡)
𝑑𝑡
 𝑑𝑣𝑜𝑢𝑡
4. Rearrange: 𝑅𝐶 = 𝑉𝑖𝑛 (𝑡) − 𝑉𝑜𝑢𝑡 (𝑡)
𝑑𝑡

5. Write in terms of the derivative:

𝑑𝑣𝑜𝑢𝑡 1
= (𝑉 (𝑡) − 𝑉𝑜𝑢𝑡 (𝑡))
𝑑𝑡 𝑅𝐶 𝑖𝑛
This equation has a direct block diagram interpretation:

• Summing Junction: Calculates the error (𝑉𝑖𝑛 − 𝑉𝑜𝑢𝑡 )

1
• Gain Block: multiplies the error by 𝑅𝐶
𝑑𝑣𝑜𝑢𝑡
• Integrator Block: integrates the derivative 𝑡𝑜 𝑔𝑒𝑡 𝑣𝑜𝑢𝑡
𝑑𝑡

Final Block Diagram:

This shows the RC circuit is itself a closed-loop system! The output voltage is fed back and
compared to the input. The "plant" is an integrator (the capacitor), and the controller is a simple
gain (1/RC).

Worked Example 2: RLC Series Circuit

Circuit: Input voltage 𝑉𝑖𝑛 (𝑡)applied to a series R, L, C. Output is voltage across the capacitor,
𝑉𝑜𝑢𝑡 (𝑡)

Step 1: Derive the Transfer Function

1
1. Total impedance: 𝑍𝑡𝑜𝑡𝑎𝑙 (𝑠) = 𝑅 + 𝑠𝐿 + 𝑠𝐶
1
2. Output impedance: 𝑍𝑜𝑢𝑡 (𝑠) = 𝑠𝐶

3. Transfer function:
1
𝑉𝑜𝑢𝑡 (𝑠) 𝑠𝐶 1
𝐺(𝑠) = = =
𝑉𝑖𝑛 (𝑠) 1 2
𝑅 + 𝑠𝐿 + 𝑠𝐶 𝐿𝐶𝑠 + 𝑅𝐶𝑠 + 1
Step 2: Create the Block Diagram (from Dynamics)
Let's find a more detailed block diagram. The mesh current is 𝐼(𝑠)
1
1. From KVL: 𝑉𝑖𝑛 (𝑠) = 𝐼(𝑠) ⋅ (𝑅 + 𝑠𝐿 + 𝑠𝐶)
1
2. Output: 𝑉𝑜𝑢𝑡 (𝑠) = 𝐼(𝑠) ⋅ 𝑠𝐶

We can break this into operations:

• The voltage across the inductor is 𝑉𝐿 (𝑠) = 𝑠𝐿𝐼(𝑠)

• The voltage across the resistor is 𝑉𝑅 (𝑠) = 𝑅𝐼(𝑠)

𝐼(𝑠)
• The voltage across the capacitor is 𝑉𝑜𝑢𝑡 (𝑠) = 𝑠𝐶

From KVL: 𝑉𝑖𝑛 (𝑠) − 𝑉𝐿 (𝑠) − 𝑉𝑅 (𝑠) − 𝑉𝑜𝑢𝑡 (𝑠) = 0

Simplified Representation:
The most common representation is the single transfer function block:

text

[𝑉𝑖𝑛 (𝑆)] → [1/(𝐿𝐶𝑠 2 + 𝑅𝐶𝑠 + 1)] → [𝑉𝑜𝑢𝑡 (𝑠)]

1
This block immediately tells us it's a second-order system with a natural frequency ω𝑛 =
√𝐿𝐶
𝑅 𝐶
and damping ratio 𝜁 = 2 √𝐿 , which is crucial for control analysis.

Summary Table: Electrical Element to Block Diagram Concept

Electrical Element Dynamic Behavior Block Diagram Representation

Resistor (R) Static Gain [R] (Gain Block)
Capacitor (C) Integration [1/(sC)] (Integrator Block)
Inductor (L) Differentiation [sL] (Differentiator Block, often avoided)
KVL Sum of voltages = 0 [Summing Junction] (with negative feedback)
Voltage Divider Algebraic relationship [Gain Block] or [Feedback Loop]
The power of this approach is that it converts a physical electrical system into a standard
feedback control model, allowing engineers to use all the tools of control theory (like stability
analysis, PID tuning, etc.) to design and analyze circuit
 Chapter 7
TIME RESPONSE ANALYSIS

Introduction
Time response analysis is also called time domain analysis. Here, we study the response, i.e. the
output as a function of time. Total time response c(t) of a control system consists of transient
response (dynamic response ct (t) and steady state response css (t).

𝑐(𝑡) = 𝑐𝑡(𝑡) + 𝑐𝑠𝑠(𝑡)

Where,

𝑡𝑐 (𝑡) = 𝑡𝑜𝑡𝑎𝑙𝑡𝑖𝑚𝑒𝑟𝑒𝑠𝑝𝑜𝑛𝑠𝑒

𝑐(𝑡) = 𝑡𝑟𝑎𝑛𝑠𝑖𝑒𝑛𝑡𝑟𝑒𝑠𝑝𝑜𝑛𝑠𝑒

𝑐𝑠𝑠(𝑡) = 𝑠𝑡𝑒𝑎𝑑𝑦 − 𝑠𝑡𝑎𝑡𝑒𝑟𝑒𝑠𝑝𝑜𝑛𝑠𝑒

The transient state of the system remains for a very short time while steady-state is that stage
of the system as time t approaches infinity. A feedback control system has the inherent
capabilities that its parameters can be adjusted to alter both its transient and steady-state
behaviour. In order to analyse the transient and steady-state behaviour of control systems, we
obtain a mathematical model of the system. For any specific input signal, a complete time
response expression can then be obtained through the Laplace transform inversion. This
expression yields the steady-state behaviour of the system with time tending to infinity. In case
of simple deterministic signals, steady-state response expression can be calculated by the use of
the fi nal value theorem. Before proceeding with the time response analysis of a control system,
it is necessary to test stability of the system through indirect tests without actually obtaining the
transient response. In case a system happens to be unstable, hence of no practical use, we need
not proceed with its transient response analysis.

Typical test signals that is, signals which can be generated in the laboratory are:

i) Unit step
ii) Unit ramp
iii) Parabolic
iv) Sinusoidal
 The nature of the transient response of a system is dependent upon system
poles only and not on the type of input. Therefore, we shall analyse the
transient response to one of the standard test signals. A step signal is
generally used for this purpose. The time consuming transient analysis need
not be carried out for all the test signals by the final value.

First-Order System Step Response Analysis

1. The Standard First-Order System

A first-order system is characterized by a first-order differential equation. Its standard transfer

function is:

𝒀(𝒔) 𝑲
=
𝑼(𝒔) 𝛕𝒔 + 𝟏
Where:

• 𝒀(𝒔) is the output (Laplace domain).

• 𝑼(𝒔) is the input (Laplace domain).

• 𝑲 is the DC Gain (or steady-state gain). It's the ratio of the output change to the input
change at steady state.

• 𝛕 (tau) is the Time Constant. This is the most important parameter, defining the speed of
the system's response.

2. The Step Input

• A step input represents an instantaneous change from one value to another at

time $t=0$. A common example is a unit step.
• Mathematical Definition:
𝑢(𝑡) = 𝐴 ⋅ 𝟏(𝒕)
where 𝐴 is the amplitude of the step and 𝟏(𝒕) is the unit step function.
In Laplace Domain:
𝐴
𝑈(𝑠) =
𝑠

3. Finding the Time Response y(t)

We will derive the output y(t) for a step input of amplitude A.
 Step 1: Write the output in the Laplace domain.
𝐾 𝐴
𝑌(𝑠) = 𝐺(𝑠) ⋅ 𝑈(𝑠) = ⋅
τ𝑠 + 1 𝑠

Step 2: Perform Partial Fraction Expansion.

We need to break Y(s) into simpler parts that we can inverse Laplace transform.
𝐾⋅𝐴 𝐶1 𝐶2
= +
𝑠(𝜏𝑠 + 1) 𝑠 𝜏𝑠 + 1

Solving for the constants 𝐶1 and 𝐶2 :

𝐾 ⋅ 𝐴 = 𝐶1 (𝜏𝑠 + 1) + 𝐶2 (𝑠)

Let 𝑠 = 0: 𝐾 ⋅ 𝐴 = C1 (1) → C1 = 𝐾 ⋅ 𝐴
Let 𝑠 = −: 𝐾 ⋅ 𝐴 = 𝐶2 (−1/𝜏) → 𝐶2 = −𝐾 ⋅ 𝐴
Therefore:
𝐾⋅𝐴 𝐾⋅𝐴⋅𝜏 𝐾⋅𝐴 𝐾⋅𝐴
𝑌(𝑠) = − = −
𝑠 𝜏𝑠 + 1 𝑠 1
𝑠+𝜏

1. The Standard Second-Order System

The canonical form of a second-order system's transfer function is:

𝒀(𝒔) 𝜔𝒏𝟐
= 𝟐
𝑹(𝒔) 𝒔 + 𝟐𝜁𝜔𝒏 𝒔 + 𝜔𝒏𝟐

Where:

• Y(s) is the Output (Laplace domain).

• R(s) is the Input (Laplace domain).

• 𝜔𝒏 (omega_n) is the Undamped Natural Frequency [rad/s]. It is the frequency of

oscillation if no damping was present.

• 𝜁 (zeta) is the Damping Ratio. This is the most important parameter as it determines
the nature of the response (oscillatory or not).

2. The Step Input

 1
• We will analyze the response to a unit step input 𝑅(𝑠) = 𝑠

• The output becomes:

𝜔𝑛2
𝑌(𝑠) =
𝑠(𝑠 2 + 2𝜁𝜔𝑛 𝑠 + 𝜔𝑛2 )
• The form of the time response 𝑦(𝑡) depends entirely on the value of the damping
ratio 𝜁. There are four key cases:

Case Damping Ratio (𝜁) Type of System Response Characteristics

1 𝜁= 0 Undamped Sustained Oscillation
2 0 < 𝜁< 1 Underdamped Oscillations, Overshoot
3 𝜁= 1 Critically Damped Fastest response without oscillation
4 𝜁> 1 Overdamped Slow, sluggish, no oscillation

characteristic equation and Position of Roots/Poles

The Characteristic Equation

The Characteristic Equation is the equation obtained by setting the denominator of a system's
transfer function equal to zero.

• For a Transfer Function:

Given a general closed-loop transfer function:
T(s)=N(s)D(s)T(s)=D(s)N(s)
where 𝑁(𝑠) is the numerator polynomial and 𝐷(𝑠) is the denominator polynomial.

The Characteristic Equation is:

D(s)=0D(s)=0

• Why is it important?
The roots of the characteristic equation (the values of 𝑠 that satisfy 𝐷(𝑠) = 0) are
the poles of the system. The location of these poles in the complex s-plane completely
determines the stability and the natural (transient) response of the system. The
numerator only affects the amplitude of the response.

Poles (Roots) and Their Meaning

Poles are the values of s that make the transfer function approach infinity. They represent the
system's natural modes of behavior.

A pole is a complex number and is represented as:

𝑠 = 𝜎 + 𝑗𝜔𝑠 = 𝜎 + 𝑗𝜔
 • 𝜎 (Real part): Determines the rate of decay (if 𝜎 < 0) or growth (if 𝜎 > 0) of the
response.

• 𝒋𝜔 (Imaginary part): Determines the frequency of oscillation of the response.

Dominant closed-loop Poles Of higher order systems

➢ What are Dominant Poles?

In a higher-order system (order 3 or higher), the characteristic equation has multiple roots
(poles). Dominant poles are the poles that have the most significant influence on the transient
response of the system.

Typically, dominant poles are:

1. The slowest poles: The poles closest to the imaginary axis (𝑗𝜔-axis) in the s-plane.

2. Not cancelled by zeros: They must not be nearly cancelled out by a nearby zero.

The response due to poles that are much faster (further to the left in the s-plane) decays away
much more quickly and has a negligible effect on the overall, longer-term shape of the
response.

2. Why Do We Need This Concept?

Analyzing a 4th or 5th order system by hand is very difficult. The concept of dominant poles
allows us to approximate a higher-order system by a lower-order system (usually first or
second order). This simplification lets us use the well-known formulas for rise time, peak time,
overshoot, and settling time.

The Rule of Dominance

A common rule of thumb is that a pole can be neglected if its real part is at least 5-10 times
greater than the real part of the dominant poles.

Mathematically:
If a system has poles at:
𝑠1 , 𝑠2 = −𝜎𝑑 ± 𝑗𝜔𝑑 (Candidate dominant poles)
𝑠3 = −𝜎𝑓 (A faster, non-dominant pole)

Then the pole at 𝑠3 can be ignored if:

𝜎𝒇 > 𝟓𝜎𝒅
The response from the fast pole 𝑠3 will decay to zero roughly 5 times faster than the response
from the dominant poles. After the initial transient, the system's behavior will be dictated
almost entirely by the dominant poles.
 Chapter 8
CONCEPT OF STABILITY AND ROUTH-
HURWITZ CRITERION
CONCEPT OF STABILITY
System stability is one of the most important performance specification of a control system. A
system is considered unstable if it does not return to its initial position but continues to oscillate
after it is subjected to any change in input or is subjected to undesirable disturbance. For any
time invariant control system to be stable the following two conditions need to be satisfied.
These are:

i) The system will produce a bounded output for every bounded input;
ii) If there is no input, the output should tend to be zero, irrespective of any
initial conditions. Stability of a system may be referred to as absolute stability
or in terms of relative stability. The term relative stability is used in relation to
comparative analysis of stability of systems and their operating condition.

Pole-Zero Analysis and Stability Conditions

1. Poles and Zeros: The Basics

In transfer function analysis, any linear time-invariant (LTI) system can be represented by its
transfer function, H(s), in the Laplace domain.

• Transfer Function: 𝐻(𝑠) = 𝑁(𝑠)/𝐷(𝑠)

o N(s) is the numerator polynomial.

o D(s) is the denominator polynomial.

• Zeros: The roots of the numerator polynomial N(s) = 0. Zeros are values of s that make
the transfer function zero. They represent frequencies where the system's output is zero
even for a non-zero input.

• Poles: The roots of the denominator polynomial D(s) = 0. Poles are values of s that
make the transfer function approach infinity. They define the system's natural response
(transient behavior) and are the eigenvalues of the system.
Example:
𝐻(𝑠) = (𝑠 + 2)/(𝑠 2 + 4𝑠 + 3)

• 𝑍𝑒𝑟𝑜: 𝑆𝑜𝑙𝑣𝑒 𝑠 + 2 = 0 → 𝑠 = −2

• 𝑃𝑜𝑙𝑒𝑠: 𝑆𝑜𝑙𝑣𝑒 𝑠 2 + 4𝑠 + 3 = 0 → (𝑠 + 1)(𝑠 + 3) = 0 → 𝑠 = −1, 𝑠 = −3

2. The S-Plane (Complex Plane)

The location of poles and zeros is plotted on the s-plane (or complex plane), where the x-axis is
the real axis (σ) and the y-axis is the imaginary axis (𝑗𝜔). This visualization is key to
understanding system behavior.

• Poles are traditionally marked with an 'X'.

• Zeros are traditionally marked with an 'O'.

Interpretation of Pole Location:

The position of a pole 𝑠 = 𝜎 + 𝑗𝜔 in the s-plane directly tells us about the nature of its
corresponding transient response component.

Pole Location Response Description

(𝒔 = 𝝈 ± 𝒋𝝎) Characteristic
Left-Half Plane Stable The natural response decays exponentially over time.
(LHP) The further left the pole, the faster it decays.
(𝜎 < 0)
Right-Half Plane Unstable The natural response grows exponentially over time.
(RHP) The system output diverges.
(𝜎 > 0)
Imaginary Axis Marginally The natural response is a
(𝜎 = 0) Stable sustained oscillation (sinusoid) that neither decays nor
grows.
Real Axis No Oscillation The response is exponential (e.g., a simple rise or
(𝝎 = 𝟎) decay).
Complex Oscillatory The response is a sinusoid with an exponential
(𝝎 ≠ 𝟎) envelope (damped or undamped).

Zeros affect the amplitude and phase of the response components but do not determine
stability on their own. They can make the system's response faster or slower (e.g., non-
minimum phase systems have RHP zeros).
3. Conditions for Stability

A control system is BIBO (Bounded-Input-Bounded-Output) stable if every bounded input

results in a bounded output.

The Fundamental Stability Criterion:

A linear time-invariant (LTI) system is stable if and only if ALL of its closed-loop poles have
negative real parts (i.e., they are located in the Left-Half of the s-plane).

• Stable: All poles in the LHP (𝜎 < 0).

• Unstable: At least one pole in the RHP (𝜎 > 0) OR a repeated pole on the imaginary
axis.

• Marginally Stable: No poles in the RHP, but non-repeated poles on the imaginary axis
(𝑒. 𝑔. , 𝑠 = 0, 𝑠 = ±𝑗𝜔).

Why? The time-domain response for each pole is of the form 𝑒 (𝑠∗𝑡) . If s has a negative real part
(𝑒 (𝜎𝑡) 𝑤ℎ𝑒𝑟𝑒 𝜎 < 0), this exponential term decays to zero. If the real part is positive, it grows to
infinity. If the real part is exactly zero, it oscillates forever.

4. Relating Open-Loop and Closed-Loop Stability

It's crucial to distinguish between open-loop and closed-loop poles.

• Open-Loop Poles: The poles of G(s)H(s), the loop gain. An open-loop system can be
stable or unstable.

• Closed-Loop Poles: The poles of the closed-loop transfer function T(s) = G(s) / (1 +
G(s)H(s)). They are the roots of the characteristic equation: 1 + G(s)H(s) = 0.

A system can have an unstable open-loop but a stable closed-loop, and vice-versa. The
feedback connection changes the pole locations. The goal of control design is often to place the
closed-loop poles in desirable locations in the LHP.

5. Techniques to Assess Stability (Without Finding Poles Exactly)

Finding the roots of high-order characteristic equations can be difficult. Several methods exist to
determine stability without explicit root-solving:

1. Routh-Hurwitz Criterion:

➢ What it is : A mathematical test that uses the coefficients of the characteristic

polynomial to determine the number of RHP poles.
 ➢ How it works : It constructs the Routh array. The number of sign changes in the first
column of this array equals the number of poles in the RHP.
➢ Use : Provides a simple "yes/no" answer for stability and can also be used to find the
range of controller gains (e.g., K) for which the system remains stable (finding the gain
at the imaginary axis crossover).

2. Root Locus:

➢ What it is: A graphical plot showing how the closed-loop poles move in the s-plane as a
single parameter (almost always the gain K) is varied from 0 to infinity.

➢ How it works: The branches of the root locus start at the open-loop poles (when K=0)
and end at the open-loop zeros (as K→∞).

➢ Use: To visually see if and when the closed-loop poles move into the RHP as gain
increases. It is a powerful tool for control design.

3. Nyquist Criterion (Frequency Domain):

➢ What it is: A more advanced graphical technique that uses the open-loop frequency
response G(jω)H(jω) to determine closed-loop stability.

➢ How it works: It relates the number of encirclements of the Nyquist plot around the
critical point (-1, 0) to the number of RHP poles of the open-loop and closed-loop
systems.

➢ Use: Provides information on stability and relative stability (gain and phase margins).

Summary Table
Concept Description Implication for Stability
Pole 𝑅𝑜𝑜𝑡 𝑜𝑓 𝑑𝑒𝑛𝑜𝑚𝑖𝑛𝑎𝑡𝑜𝑟 𝐷(𝑠) = 0 Primary determinant of stability.
Zero 𝑅𝑜𝑜𝑡 𝑜𝑓 𝑛𝑢𝑚𝑒𝑟𝑎𝑡𝑜𝑟 𝑁(𝑠) = 0 Affects response but not inherent
stability.
LHP Pole 𝑠 = −𝜎 ± 𝑗𝜔 (𝜎 > 0) Stable. Contributes a decaying
transient.
RHP Pole 𝑠 = +𝜎 ± 𝑗𝜔 (𝜎 > 0) Unstable. Contributes a growing
transient.
Imaginary Axis 𝑠 = ±𝑗𝜔 Marginally Stable. Sustained
Pole oscillation.
Stability All closed-loop poles must be in the System is BIBO stable.
Condition LHP.
Instability Any closed-loop pole is in the RHP. System is unstable.
Condition
In essence, the "where" of the poles on the s-plane answers the "if" of system stability. Control
design is the art of using feedback to move these poles to their desired, stable locations.
 Chapter 9

THE ROOT LOCUS TECHNIQUE

INTRODUCTION
We have observed in the previous chapter that there are two related points with respect to study
of stability of a control system. First, all the poles of the closed loop system must lie in the left
hand side of the imaginary axis in the s-plane. The second, the examination that has to be made
as to see how close the poles are with the 𝑗𝑤 − 𝑎𝑥𝑖𝑠 of the s-plane. The second aspect provides
us with information regarding the relative stability of the control system. We have also seen that
the poles are the roots of the characteristic equation. The characteristic equation is obtained by
putting the denominator of the closed loop transfer function to zero. The characteristic equation
is useful in the study of dynamic characteristics of a control system. From the design point of view,
by writing the differential equation of the system and solving the differential equation with
respect to a controlled variable, the time response can be found out. Thus, we will know the
accurate solution of the equation and hence the performance of the system. But this approach of
solution may be difficult for even a slightly complex system. Efforts involved in determining the
roots of the characteristic equation has been avoided by applying Routh-Hurwitz criterion as
described in the previous chapter. But this criterion only tells the designer as to whether a system
is stable or unstable. The designer of a control system cannot remain satisfied with this
information alone, because he is unable to indicate the degree of stability of the system. The
degree of stability will tell about the amount of overshoot, settling time, etc. for an input, say a
step or a ramp input. Root locus technique, described in this chapter, is a powerful graphical
method used for the analysis and design of a control system. This method of analysis not only
indicates whether a system is stable or unstable but also shows the degree of stability of a stable
system

THE ROOT LOCUS CONCEPT

1. The Big Idea: What is a Root Locus?
Imagine you have a feedback control system. You can adjust a parameter, most commonly the
gain K (from 0 to infinity). Changing K changes the location of the closed-loop poles, which in
turn changes the system's behavior (stability, overshoot, settling time).

The Root Locus is the set of all possible points in the s-plane (the complex plane) that are
closed-loop poles for some value of 𝐾 (0 ≤ 𝐾 < ∞).

• It's a "locus" (a path or a curve) that the roots of the closed-loop characteristic equation
follow.

• It's a plot of how the poles of the closed-loop system migrate as the gain is increased
from zero to infinity.

Why is it So Important?
The root locus is an indispensable tool for control engineers because it allows them to:

1. Predict Closed-Loop Behavior: Visually see how characteristics like damping,

frequency, and stability change with gain.
2. Determine Stability: Immediately see for what range of gain K the system is stable
(when the locus is in the Left-Half Plane) and when it becomes unstable (when the locus
crosses into the Right-Half Plane).

3. Design Controllers: Choose a gain K that places the closed-loop poles in a desired
location to meet performance specifications (e.g., a specific overshoot or settling time).

4. Understand Sensitivity: See how sensitive the pole locations are to changes in gain.

The Foundation: The Characteristic Equation

The entire root locus method is based on the closed-loop characteristic equation:

1 + 𝐺(𝑠)𝐻(𝑠) = 0

For a simple system where the controller is just a gain K and the plant is G(s), this becomes:
1 + 𝐾 𝐺(𝑠) = 0

This equation can be rearranged into two key forms:

1. The Magnitude Condition (The "How Much"):

𝐾 |𝐺(𝑠)| = 1

o This equation must be satisfied for a point s to be on the root locus for a specific
value of K.
 2. The Angle Condition (The "Where"):
∠𝐺(𝑠) = ±180° (𝑜𝑟 ± 180° + 𝑛 × 360°)

o This is the fundamental rule. A point s in the complex plane is on the root locus if
and only if the angle of G(s) is an odd multiple of 180°. This is the test we use to
sketch the locus. The Rules for Sketching a Root Locus

You don't always need a computer. Using a set of logical rules, you can quickly sketch the root
locus. Here are the most important ones:

Let 𝐺(𝑠)𝐻(𝑠) = 𝐾 ∗ (𝑠 − 𝑧₁)(𝑠 − 𝑧₂). . ./ (𝑠 − 𝑝₁)(𝑠 − 𝑝₂). .. where zᵢ are zeros

and pᵢ are poles.

1. Number of Branches: The number of branches (paths) equals the number

of poles of 𝐺(𝑠)𝐻(𝑠) (𝑛). Each closed-loop pole moves along its own branch
as K changes.

2. Symmetry: The root locus is always symmetric about the real axis (because complex
poles always come in conjugate pairs).

3. Start and End Points:

o 𝑨𝒔 𝑲 → 𝟎: The branches 𝒔𝒕𝒂𝒓𝒕 (𝑲 = 𝟎) at the open-loop poles (p₁, p₂, ...).

o 𝑨𝒔 𝑲 → ∞: The branches 𝒆𝒏𝒅 (𝑲 = ∞) at the open-loop zeros (z₁, z₂, ...). If

there are more poles (n) than zeros (m), then n - m branches go to infinity.

4. Real Axis Segments: A point on the real axis is part of the root locus if the number of
open-loop poles and zeros to its right is odd.

5. Asymptotes (Behavior at Infinity): The n - m branches that go to infinity

approach asymptotes. The properties of these asymptotes are:

o 𝑪𝒆𝒏𝒕𝒓𝒐𝒊𝒅 (𝝈): 𝜎 = (𝛴𝑝𝑜𝑙𝑒𝑠 − 𝛴𝑧𝑒𝑟𝑜𝑠) / (𝑛 − 𝑚)

o 𝑨𝒏𝒈𝒍𝒆𝒔 (𝜽): 𝜃 = ±180° (2𝑘 + 1) / (𝑛 − 𝑚) 𝑓𝑜𝑟 𝑘 = 0, 1, 2, . ..

6. Breakaway/Break-in Points: These are points on the real axis where two or more
branches meet and then diverge (breakaway from the real axis) or converge (break-in to
the real axis). They are found by solving dK/ds = 0 from the characteristic equation.

7. Imaginary Axis Crossings: The gain K where the locus crosses into the RHP (and the
system becomes unstable) can be found using the Routh-Hurwitz criterion or by
substituting s = jω into the characteristic equation.
5. A Simple Example

𝐿𝑒𝑡′𝑠 𝑠𝑘𝑒𝑡𝑐ℎ 𝑡ℎ𝑒 𝑟𝑜𝑜𝑡 𝑙𝑜𝑐𝑢𝑠 𝑓𝑜𝑟 𝐺(𝑠) = 𝐾 / (𝑠(𝑠 + 2)).

• 𝑶𝒑𝒆𝒏 − 𝑳𝒐𝒐𝒑 𝑷𝒐𝒍𝒆𝒔: 𝑠 = 0, 𝑠 = −2 → 𝑛 = 2

• 𝑶𝒑𝒆𝒏 − 𝑳𝒐𝒐𝒑 𝒁𝒆𝒓𝒐𝒔: 𝑁𝑜𝑛𝑒 → 𝑚 = 0

• 𝑪𝒉𝒂𝒓𝒂𝒄𝒕𝒆𝒓𝒊𝒔𝒕𝒊𝒄 𝑬𝒒: 1 + 𝐾/(𝑠(𝑠 + 2)) = 0 −> 𝑠² + 2𝑠 + 𝐾 = 0

Now, apply the rules:

1. Branches: 2 (since n=2).

2. Symmetry: Yes, about the real axis.

3. Start/End: Starts at s=0 and s=-2. Ends at infinity (since m=0).

4. Real Axis Segment: Check segments:

o 𝐿𝑒𝑓𝑡 𝑜𝑓 𝑠 = −2: 𝑝𝑜𝑙𝑒𝑠 + 𝑧𝑒𝑟𝑜𝑠 𝑡𝑜 𝑟𝑖𝑔ℎ𝑡 = 2 (𝑒𝑣𝑒𝑛) → 𝒏𝒐𝒕 𝒐𝒏 𝒍𝒐𝒄𝒖𝒔.

o 𝐵𝑒𝑡𝑤𝑒𝑒𝑛 𝑠 = −2 𝑎𝑛𝑑 𝑠 = 0: # 𝑡𝑜 𝑟𝑖𝑔ℎ𝑡 = 1 (𝑜𝑑𝑑) → 𝒐𝒏 𝒍𝒐𝒄𝒖𝒔.

o 𝑅𝑖𝑔ℎ𝑡 𝑜𝑓 𝑠 = 0: # 𝑡𝑜 𝑟𝑖𝑔ℎ𝑡 = 0 (𝑒𝑣𝑒𝑛) → 𝒏𝒐𝒕 𝒐𝒏 𝒍𝒐𝒄𝒖𝒔.

5. Asymptotes:

o 𝑛 − 𝑚 = 2

o 𝑪𝒆𝒏𝒕𝒓𝒐𝒊𝒅: 𝜎 = (0 + (−2) − 0) / 2 = −1

o 𝑨𝒏𝒈𝒍𝒆𝒔: 𝜃 = ±180°(2𝑘 + 1)/2 → 𝑓𝑜𝑟 𝑘 = 0: 𝜃 = +90° 𝑎𝑛𝑑 𝜃 = −90°.

6. Breakaway Point: Solve dK/ds = 0. From Char. Eq.: 𝐾 = −𝑠² − 2𝑠. 𝑑𝐾/𝑑𝑠 = −2𝑠 −
2 = 0 −> 𝑠 = −1. This is on the real-axis segment we identified, so it's a valid
breakaway point.

Conclusion of the Sketch:

The two branches start at s=0 and s=-2. They travel towards each other along the real axis
segment between -2 and 0. They meet and break away at s=-1. After breaking away, one branch
goes towards the asymptote at +90° and the other toward -90°, forming a parabola.

As K increases, the poles become complex and move into the LHP (stable but oscillatory). The
system is stable for all K > 0 because the branches never enter the RHP. The damping decreases
as K increases, leading to more oscillation.
 Chapter 10
FREQUENCY RESPONSE ANALYSIS

Introduction
In the previous chapters we have studied the response of a system to step input, ramp input, etc.
Since most of the input signals in practice are sinusoidal inputs, in this chapter; we will consider
the steady state response of a system to a sinusoidal input test signal. The response will also be
sinusoidal for a linear constant coefficient system once the transient die out. The output
sinusoidal signal will also have the same frequency as the input signal. However, the magnitude
and phase of the output will differ from the input signal once the frequency of the input signal is
changed. The frequency response analysis deals with the study of steady state response of a
system to sinusoidal input of variable frequency. Thus, we can defi ne the frequency response of
a system as the steady-state response of the system to a variable frequency sinusoidal input
signal. Analysis involves examining the transfer function G(s) when 𝑠 = 𝑗𝑤 and graphically
displaying 𝐺(𝑗𝑤) as w varies. As mentioned, for analysis of many systems frequency response is
of importance since most of the input signals are either sinusoidal or composed of sinusoidal
components (harmonics). The starting point for frequency response analysis is the determination
of system transfer function. Then in the frequency response the transfer function is expressed in
terms of magnitude and phase angle as 𝑀𝑠 𝑀 ( ) .

Frequency response specifications

➢ The Big Idea: What is Frequency Response?
While time-domain specs (like rise time, overshoot) tell us about the response to a sudden
change (step input), frequency response tells us how a system behaves when subjected
to sinusoidal inputs of different frequencies.

• Key Insight: For a linear time-invariant (LTI) system, a sinusoidal input produces
a sinusoidal output at the same frequency, but with a different amplitude and phase
shift.

• The Change: The amount of amplitude change and phase shift depends on the
frequency (ω) of the input signal.
Frequency response specifications are metrics that quantify this behavior, telling us about the
system's speed, stability, and robustness.

➢ How is it Represented? The Bode Plot

The most common tool for visualizing frequency response is the Bode Plot. It consists of two
separate graphs:

1. Bode Magnitude Plot: Shows the amplitude ratio (gain) between output and input,
in decibels (dB), vs. frequency (on a logarithmic scale).

o 𝑀𝑎𝑔𝑛𝑖𝑡𝑢𝑑𝑒 (𝑑𝐵) = 20 ∗ 𝑙𝑜𝑔₁₀(|𝐺(𝑗𝜔)|)

2. Bode Phase Plot: Shows the phase shift (in degrees) between the output and input
sinusoids vs. frequency (on the same logarithmic scale).

These specifications are read directly from the Bode plot of the open-loop transfer
function, 𝐺(𝑗𝜔)𝐻(𝑗𝜔).

Key Frequency Response Specifications

Here are the most important specifications, what they mean, and why they matter.

1. Gain Margin (GM)

• What it is: A measure of how much the gain can be increased before the system
becomes unstable.

• How to find it:

1. On the Bode plot, find the frequency where the phase angle is −𝟏𝟖𝟎°. This is
called the phase crossover frequency (𝝎_𝒑𝒄).

2. At this frequency (𝜔_𝑝𝑐), look at the magnitude plot.

3. The Gain Margin is the distance (in dB) from the magnitude curve to 𝟎 𝒅𝑩.
𝐺𝑀 (𝑑𝐵) = 0 𝑑𝐵 − |𝐺(𝑗𝜔_𝑝𝑐)| 𝑑𝐵

➢ Correlation Between time response and frequency response

The Core Principle: A System's "Signature"

For a linear time-invariant (LTI) system, the time response and frequency response are two
different ways of looking at the same thing. They are mathematically equivalent descriptions,
linked by the Fourier and Laplace transforms.

• Time Domain: Describes how the system reacts to inputs over time (e.g., step response).
 • Frequency Domain: Describes how the system reacts to inputs at different
frequencies (e.g., sinusoidal inputs).

The characteristics that appear in one domain have direct, predictable counterparts in the
other.

The Bridge: Second-Order Systems

The clearest correlation exists for second-order systems, which are the most common model for
underdamped responses (like a mass-spring-damper or a typical servo motor). The standard
form of its transfer function is:

𝑮(𝒔) = 𝝎ₙ² / (𝒔² + 𝟐𝜻𝝎ₙ𝒔 + 𝝎ₙ²)

Where:

• 𝝎ₙ = Natural Frequency (rad/s)

• 𝜻 (𝑧𝑒𝑡𝑎) = Damping Ratio (unitless)

This simple model provides the Rosetta Stone for translating between domains.

Bandwidth
Bandwidth (BW) is the range of frequencies over which a system can operate effectively. It is a
measure of the system's speed or ability to track rapid changes.

However, its precise definition depends on the context:

• For a Closed-Loop Control System: It is the frequency at which the closed-loop gain
drops to -3 decibels (dB) below its low-frequency (or DC) value.

• For a Filter or Communication Channel: It is the width of the range of frequencies that
can pass through with minimal attenuation.

o 𝑻𝒉𝒆 " − 𝟑 𝒅𝑩 𝑷𝒐𝒊𝒏𝒕": 𝑾𝒉𝒚 𝑻𝒉𝒂𝒕 𝑵𝒖𝒎𝒃𝒆𝒓?

The -3 dB point is not arbitrary. It has a precise mathematical and physical meaning:

• 𝑫𝒆𝒄𝒊𝒃𝒆𝒍𝒔 (𝒅𝑩): 𝐺𝑎𝑖𝑛 (𝑑𝐵) = 20 · 𝑙𝑜𝑔₁₀(𝑀𝑎𝑔𝑛𝑖𝑡𝑢𝑑𝑒)

• −𝟑 𝒅𝑩 𝑪𝒂𝒍𝒄𝒖𝒍𝒂𝒕𝒊𝒐𝒏: 20 · 𝑙𝑜𝑔₁₀(𝑀𝑎𝑔𝑛𝑖𝑡𝑢𝑑𝑒) = −3 𝑑𝐵

o 𝑆𝑜𝑙𝑣𝑖𝑛𝑔 𝑓𝑜𝑟 𝑀𝑎𝑔𝑛𝑖𝑡𝑢𝑑𝑒: 𝑙𝑜𝑔₁₀(𝑀𝑎𝑔𝑛𝑖𝑡𝑢𝑑𝑒) = −3/20 = −0.15

o 𝑇ℎ𝑒𝑟𝑒𝑓𝑜𝑟𝑒: 𝑀𝑎𝑔𝑛𝑖𝑡𝑢𝑑𝑒 = 10⁻⁰ · ¹⁵ ≈ 0.707

This means the -3 dB point is where the output signal's power is halved (since power is
proportional to voltage squared, (0.707)² = 0.5). It is the standard point for defining the
useful limit of a system's frequency range.

➢ How to Find Bandwidth on a Plot

The most common way to visualize bandwidth is on a Closed-Loop Magnitude Bode Plot.

Steps to find BW:

1. Identify the low-frequency gain. For most control systems, this is the gain at ω = 0 rad/s
(DC gain). Let's assume it's 1 (0 dB) for a standard servo system.

2. Find the point where the gain has fallen by 3 dB from that low-frequency gain.

3. Drop a line down from that point on the curve to the frequency axis.

4. The frequency at this point is the Bandwidth (𝝎_𝒃𝒘).