2. Overall Description
2.1 Product Perspective 2.2 Product Features 2.3 User Classes and Characteristics 2.4 Operating Environment 2.4.1 Software Requirements 2.4.2 Hardware Requirements With reason 2.5 Design and Implementation Constraints 2.6 User Documentation 2.7 Assumptions & Dependencies
3. System Features 4. External Interface Requirements
4.1 User Interfaces 4.2 Hardware Interfaces 4.3 Software Interfaces 4.4 Communications Interfaces
5. Other Non-functional Requirements
5.1 Performance Requirements 5.2 Safety Requirements 5.3 Security Requirements 5.4 Software Quality Attributes 5.5 Test Requirements 5.5.1 Testing System 5.5.2 Test System 5.5.3 Test Cases
This project is mainly useful for the department of defence where the missile needs to hit the target at which it is aimed at. Here the target could be an aircraft flying in the air. The objective of this project is to write software for classifying the aircrafts from other objects that are moving in the sky using artificial neural networks that perform tasks based on the process called learning. This classification is done so that the surface-to-air missiles hit the target correctly. The purpose of the project is to analyse the input and map it perfectly to the desired output. It is a logical program which is based on set of conditions on which testing is done and output is derived. The software classifies the aircrafts based on the assumptions we make. The task is locate the aircraft and differentiate it from the other moving objects such as chaffs, clouds, birds etc. Chaffs are nothing but small metal strips, thrown into the air to confuse radar.
1.2 Document Conventions
Standards used for the documentation are as follows: Top Level Heading: Normal, Times, 18 Sub Level Heading: Normal, Times, 14 Body Text: Normal, Times, 12
1.3 Intended Audience and Reading Suggestions
Intended audience are project supervisor Dr. Niraj Upadayaya , IT HOD Mr. CH. Srinivasulu , project guide Mr. Jacob ,external examiner appointed by JNTU and students of IT department .
1.4 Project Scope
This software can be developed in JESS, JNNL, and LISP & PROLOG. Here we will be using prolog as it is more convenient than any other platforms. The software developed would help the missile to identify the targeted aircraft in fuzzy conditions. The benefit of the software is that it always checks that the missile never misses the target inspite of availability of unclear or incomplete data .Here we write a program based on certain assumptions that would probably be the characteristics of the aircraft targeted. For example we take into consideration the speed of the aircraft that would obviously be different from that of the other flying objects in the sky. Basically we start off by assuming that the speed of the aircraft is zero. Later as we are using the concept of neural networks we will gradually increase the speed. There are many other such assumptions that we would be using while coding the program. Assumptions can be many in number but we will be using only few of them here.
1.6 Overview (From abstract)
This program helps the missile in identifying the aircraft in fuzzy conditions where the availability of data is unclear or incomplete. The program basically maps sensors to actuators that are it converts sensors to actions. This is done in a particular environment. Here we require the knowledge of P.E.A.S where P stands for percept or performance, E stands for environment. A stands for actuator and S stands for sensor.
Percept is a program which maps sensors to actions. That is it converts sensors into actions.
It is the environment in which the agent operates. They are described with the following main properties:
Fully observable vs. partially observable (Accessible vs. inaccessible):
If an agent's sensory apparatus gives it access to the complete state of the environment, then we say that the environment is accessible to that agent. An environment is effectively accessible if the sensors detect all aspects that are relevant to the choice of action. An accessible environment is convenient because the agent need not maintain any internal state to keep track of the world.
Deterministic vs. stochastic (non-deterministic):
If the next state of the environment is completely determined by the current state of the actions selected by the agents, then we say the environment is deterministic. In principle, an agent need not worry about uncertainty in an accessible, deterministic environment. If only actions of other agents are nondeterministic, the environment is called strategic.
Episodic vs. sequential (non-episodic):
In an episodic environment, the agent's experience is divided into "episodes". Each episode consists of a subsequence of percepts and actions that can be grouped together in a straightforward manner. The quality of its action depends just on the episode itself, because subsequent episodes do not depend on what actions occur in previous episodes. Episodic environments are much simpler because the agent does not need to think ahead.
Static vs. dynamic:
If the environment can change while an agent is deliberating, then we say the environment is dynamic for that agent; otherwise it is static. Static environments are easy to deal with because the agent need not keep looking at the world while it is deciding on an action, nor need it worry about the passage of time. If the environment does not change with the passage of time but the agent's performance score does, then we say the environment is semi-dynamic.
Discrete vs. continuous:
If there are a limited number of distinct, clearly defined percepts and actions we say that the environment is discrete. Chess is discrete - there are a fixed number of possible moves on each turn. Taxi driving is continuous - the speed and location of the taxi and the other vehicles sweep through a range of continuous values.
Single-Agent vs. Multi-Agent:
As the names suggest, a single agent environment is one which consists of only one agent. This means that this one agent does not have to account for other agents in the environment and can be solely concerned only with how its own actions affect the world. In a multi-agent environment on the other hand, agents need to account for the actions of other agents. In particular, if the other agents are directly in competition with each other, it is said that the environment is competitive, whereas if the agents are existing in unity, it is said that the environment is cooperative.
Actuators are the set of devices that the agent can use to perform actions. For a computer, it can be a printer or a screen. For a mechanical robot, it can be an engine. Actuators can be speed regulator, direction navigator, fuel navigator etc.
Sensors allow the agent to collect the percept sequence that will be used for deliberating on the next action. Examples of sensors:-Radio, Audio, Natural light frequency. Sensors can work in both visible as well as invisible environments. Sensor is usually an optical sensor such as camera.
How Guided Missiles Work
A guided missile is an unmanned explosive-carrying vehicle that moves above the earth's surface in a flight path controlled by an external or internal source. ‘Most of the missile body is made of a titanium alloy, which provides high strength and low weight. Inside the missile are hundreds of electronic, digital and mechanical subsystems that perform thousands of operations to guide the missile from its launcher to its target.
Missile Parts and Their Functions
A missile can be divided functionally into 8 sections: radome, guidance, warhead, autopilot, dorsal fins, rocket motor, steering control and control surfaces. A guided missile is a combination of electrical, digital and mechanical parts segregated into sections. Each section has specific functions that must operate accurately and safely; otherwise, the missile mission is electronically aborted and the missile is destroyed. Internal controls monitor each function to assure proper coordination among parts. This information is radioed to the launch controller, so that it knows at all times how well each part of the missile is performing to achieve the missile's ultimate goal of destroying the target.
Working of Missile
Fins Camera Actuator Wind
Missile Launch & Target-destruction Process
The missile launching and target destruction process can be divided into seven stages: long-range and short-range surveillance, target identification, target tracking, missile pre-launch, launch, midcourse guidance, homing, and intercept. 1. Surveillance: A systematic search by the launcher (ship, plane, or ground station) radars and more radars for targets in the hemisphere surrounding it. 2. Identification: "Friend or foe?” All commercial and military airplanes and some weapons and personnel have "transponders", which are receiver- transmitters that receive radio signals on one frequency and return a specific identification (ID) signal on another frequency. When the target code matches a "friendly" code in the launcher electronic library, no launcher action is taken. However, if the ID matches a "foe" code, or if there is no response, the missile launcher assumes a "foe" and prepares to destroy the target. Tragedies can occur when a friendly transponder is inoperable.
3. Pre-launch: The Weapons Officer in charge of missile launch (in airplanes, this would be the pilot) selects a particular missile to attack the target with a push of a button. The selected missile then automatically tests ("checks") hundreds of its subsystems within milliseconds to assure their satisfactory operation. 4. Launch: After a satisfactory self-test, the missile ignites its rocket motor, which provides the force to propel the missile away from its platform. 5. Tracking: The launcher "tracking" radar continuously monitors the target, while 8
computers continuously calculate target location, direction and speed. Human judgment is involved in identification too. 6. Midcourse: During missile flight, target location, direction, and speed are continuously calculated by the launcher radar. This information is transmitted from the ship (or plane, or truck) to the missile via radar, which adjusts its course to intercept the target. 7. Homing: When the missile approaches target vicinity, it activates its own radar and searches for the target itself, so that launcher radar no longer is required. 8. Intercept (target destruction): The missile IR (Infra-Red) "seeker" determines when the target is at the optimum distance for maximum explosive effect, whereupon it sends a signal to the warhead to detonate. The explosive scatters serrated iron fragments or other destroying material in all directions. Some of these fragments are expected to impair target functioning. When that occurs, the target is a "kill".
ARTIFICIAL NEURAL NETWORKS (ANN)
ANN is an adaptive system that changes its structure based on external or internal information that flows through the network during the learning phase. Modern neural networks are non-linear statistical data modelling tools. They are usually used to model complex relationships between inputs and outputs or to find patterns in data. The word network in the term 'artificial neural network' refers to the inter–connections between the neurons in the different layers of each system. The most basic system has three layers. The first layer has input neurons, which send data via synapses to the second layer of neurons, and then via more synapses to the third layer of output neurons. More complex systems will have more layers of neurons with some having increased layers of input neurons and output neurons. The synapses store parameters called "weights" that manipulate the data in the calculations.
2. Overall Description
2.1 Product Perspective
Target product perspective is defence related product like missiles, artillery (cannons).
2.2 Product Features
Trying to work on a less than perfect (fuzzy) condition.
2.3 User Classes and Characteristics
2.4 Operating Environment 2.4.1 Software Requirement
Microsoft Windows 2003 Server SP2 Microsoft Windows Server 2003 R2 SP2 Microsoft Windows XP SP2 (home or professional) Microsoft windows vista ( all versions) Only the 32 bit English version of all these operating systems is supported. Prolog compiler, Any simple editor
2.4.2 Hardware Requirement (Minimum)
Minimum Intel Pentium 600-megahertz (MHz) compatible or faster processor 192 megabytes (MB) of RAM or more Recommended 1-gigahertz (GHz) or faster 512 MB RAM
2.5 Design and Implementation Constraints
Project is based on simulation. Being a defence related project, complete environment will not be known due to the project being in a classified area.
2.6 User Documentation
2.7 Assumptions & Dependencies
3. System Features
4. External Interface Requirements
4.1 User Interfaces
4.2 Hardware Interfaces
4.3 Software Interfaces
4.4 Communications Interfaces
5. Other Non-functional Requirements
5.1 Performance Requirements