Soft Computing Techniques in Electrical Engineering (SCTEE)
About This Course
1. Course Overview
This course introduces learners to Soft Computing paradigms that mimic the human brain and biological systems to solve complex engineering problems. Students will explore Artificial Neural Networks (ANN), Fuzzy Logic Systems (FLS), Genetic Algorithms (GA), and Particle Swarm Optimization (PSO) — emphasizing their architectures, learning methods, and real-world applications.
2. Course Objectives
By the end of this course, learners will:
-
Gain insight into Artificial Neural Networks, Fuzzy Logic, Genetic Algorithms, and Particle Swarm Optimization.
-
Understand neural architectures, learning rules, and biological inspirations.
-
Study the structure and working of fuzzy inference systems including fuzzification and defuzzification.
-
Learn about genetic operators and their role in solving optimization problems.
-
Get introduced to PSO and its variants.
3. Course Outcomes (COs)
After successful completion, students will be able to:
| CO No. | Course Outcome | Bloom’s Level |
|---|---|---|
| CO1 | Explain how nature-inspired algorithms like ANN, Fuzzy Logic, GA, and PSO solve engineering problems. | Understand |
| CO2 | Develop and train Artificial Neural Networks using different algorithms. | Apply |
| CO3 | Explain fuzzy sets, membership functions, fuzzification, and defuzzification processes. | Understand |
| CO4 | Design and implement fuzzy controllers for practical systems. | Apply |
| CO5 | Apply Genetic Algorithms and PSO to real-world optimization problems. | Analyze |
4. Course Articulation Matrix (with Program Outcomes)
| CO | PO1 | PO2 | PO3 | PO4 | PO5 | PO6 |
|---|---|---|---|---|---|---|
| CO1 | 3 | – | 2 | 3 | – | – |
| CO2 | 3 | – | 2 | 3 | – | – |
| CO3 | 3 | – | 2 | 3 | – | – |
| CO4 | 3 | – | 2 | 3 | – | – |
| CO5 | 3 | – | 3 | 3 | – | – |
5. Detailed Syllabus
Module I – Artificial Neural Networks
-
Introduction and Benefits of Neural Networks
-
Biological Neuron and Artificial Models
-
Activation Functions and Network Architectures
-
Learning Processes:
-
Error Correction
-
Hebbian
-
Competitive
-
Boltzmann
-
Supervised, Unsupervised, and Reinforcement Learning
-
Module II – ANN Paradigms
-
Single Layer and Multi-Layer Perceptron
-
Backpropagation Algorithm (BPA)
-
Self-Organizing Maps (SOM)
-
Radial Basis Function Networks (RBFN)
-
Applications of ANN in Electrical Engineering
Module III – Fuzzy Logic
-
Introduction to Fuzzy vs. Crisp Logic
-
Fuzzy Sets and Membership Functions
-
Fuzzy Set Operations and Properties
-
Cartesian Product and Operations on Fuzzy Relations
-
Fuzzification and Defuzzification Methods
Module IV – Fuzzy Logic Controllers
-
Fuzzy Inference Systems: Mamdani, Sugeno, and Tsukamoto Models
-
Rule-Based Systems
-
Fuzzy Control Systems and their Industrial Applications
Module V – Genetic Algorithms and Particle Swarm Optimization
-
Genetic Algorithms:
-
Encoding Methods
-
Fitness Function
-
Selection, Crossover, Mutation, and Elitism
-
Algorithm Steps and Applications (e.g., Economic Load Dispatch)
-
-
Particle Swarm Optimization (PSO):
-
Pbest, Gbest, and Parameter Tuning
-
Convergence and PSO Variants
-
Suggested Learning Resources
-
Simon Haykin, Neural Networks, Pearson Education.
-
Timothy J. Ross, Fuzzy Logic with Engineering Applications, 2nd Ed., Wiley.
-
D.E. Goldberg, Genetic Algorithms, Addison-Wesley, 1999.
-
S. Rajasekaran & G.A.V. Pai, Neural Networks, Fuzzy Logic & Genetic Algorithms, PHI, 2003.
Evaluation Components
| Component | Marks | Description |
|---|---|---|
| Continuous Internal Evaluation (CIE) | 40 | Assignments, Quizzes, Midterm Tests |
| Semester End Examination (SEE) | 60 | Final Exam (3 Hours) |
Curriculum
Module – I Artificial Neural Networks
Module – I Artificial Neural Networks Class Notes
Module -II ANN Paradigms
Module – III Fuzzy Logic
Module-IV Fuzzy Logic Controller
Module -V Genetic Algorithms (GA) and Particle Swarm Optimization (PSO)
Your Instructors
Mallesham G
Professor
Dr. G. Mallesham is a Professor in the Department of Electrical Engineering, University College of Engineering, Osmania University. He possesses expertise in Control Engineering, Smart Grid Technologies, Renewable Energy Systems, and Artificial Intelligence Systems. Having undergone advanced academic exposure in both India and the USA, he has also served in several key leadership positions at Osmania University.
