Skip to content

AI and ML for Mechanical Engineering#

Course Overview#

I. Course Title#

AI and ML for Mechanical Engineering

II. Proposed Course Number#

III. Units#

Lecture 2 | Tutorial 0 | Lab 2 | Credit 3

IV. Mode#

Elective

V. Evaluation Scheme#

  • Quiz/Assignment: 15%
  • Mid-Term: 15%
  • End-Term: 40%
  • Lab: 15%
  • Course Project: 15%

VI. Semester#

I - 2023-24

VII. Programme#

Ph.D. open for M.Tech. and Final Year B.Tech.

VIII. Learning Objective#

  • To acquaint the students with the basic concept of AI and ML.
  • To acquaint students with the application of AI and ML in the problems of Mechanical Engineering and Materials.

Detailed Course Content#

Module 1: Introduction to AI and ML#

  • Introduction to Artificial Intelligence (AI) and Machine Learning (ML)
  • Need of AI and ML in Mechanical Engineering
  • Data Understanding, Data Preprocessing, Data Engineering, Data Representation, and Visualization

02 Hours

Module 2: Introduction to AI Approaches#

  • Basics of AI: Search algorithms, heuristic search, and graph-based search algorithms
  • Cybernetics and brain simulation, Symbolic, Sub-symbolic, Statistical

02 Hours

Module 3: Introduction to Approaches to ML#

  • Machine learning: Basic concepts
  • Supervised learning, Unsupervised learning, Reinforcement learning

02 Hours

Module 4: Feature Extraction and Selection#

  • Feature Extraction: Statistical Features, Principal Component Analysis
  • Feature Selection: Ranking, Decision Tree - Entropy reduction and information gain, Exaustive, best first, Greedy forward & backward, Applications of feature extraction and selection algorithmsin Mechanical Engineering.

05 Hours

Module 5: Classification and Regression#

  • Classification: Decision tree, Random Forest, Naive Bayes, Support Vecotro Machine, Neural Networks.
  • Regression: Logistic Regression, Support Vector Regression, Regression Trees: Decision tree, random forest, K-Means, K-Nearest Neighbour (KNN).
  • Clustering algorithms (unsupervised learning): K Means, Agglomerative Hierarchial Clustering.
  • Applications of classification, regression and clustering algorithms in Mechanical Engineering.

Module 7: Introduction to Deep Learning#

Deep learning - why deep learning, deep neural networks. Training a deep learning network. Standard deep learning architectures – AlexNet, VGG, Inception and ResNe models.

02 Hours

Module 8: Application of AI and ML for Mechancial Engineering#

Application examples for implementing AI and ML in Mechanical Engineering such as Fault Diagnosis of Rolling Element Bearing, Fault Diagnosis of Gear and Gear Box, Chatter Detection in Machine Tools, Biomedical Applications.

03 Hours

Module 9: Application of AI and ML for Material Science Physics informed data driven model for materials development, machine learning assisted alloy and composites development (case studies), challenges associated to the machine learning assisted alloys and composites development.

03 Hours

Lab Experiments#

  1. Introduction to Python Programming
  2. Data Processing, Data representation and visualization
  3. To extract features from given data set and establish training data.
  4. To select relevant features using suitable technique.
  5. To use PCA for dimensionality reduction.
  6. To classify features/To develop classification model and evaluate its performance
  7. To develop regression model and evaluate its performance (any one algorithm).
  8. Markov process for modelling manufacturing processes.
  9. Reinforced Learning for optimizing engineering designs
  10. Application example 1
  11. Application example 2

Text and Reference Books#

  1. Steven W. Knox, “Machine Learning: a Concise Introduction”, Wiley, 2018
  2. Deisenroth, Faisal, Ong, Mathematics for Machine Learning, Cambridge University Press, 2020
  3. B Joshi, Machine Learning and Artificial Intelligence, Springer, 2020.
  4. Stuart Russell and Peter Norvig (1995), “Artificial Intelligence: A Modern Approach,” Third edition, Pearson, 2003.
  5. Artificial Intelligence by Elaine Rich, Kevin Knight and Nair, TMH
  6. Mohri, Rostamizdeh, Talwalkar, Foundations of Machine Learning, MIT Press, 2018.
  7. Kumar, Zindani, Davim, Artificial Intelligence in Mechanical and Industrial Engineering, CRC Press, 2021.
  8. Zsolt Nagy - Artificial Intelligence and Machine Learning Fundamentals-Apress (2018)

This course equips students with the fundamental knowledge and skills required to understand and apply AI and ML techniques in Mechanical Engineering. With hands-on lab experiments and extensive reading material, students will delve into various approaches, algorithms, applications, and challenges in the integration of AI and ML in mechanical engineering and materials science.