KBCNMU TY Mechanical syllabus

KBCNMU · Third Year B.E. Mechanical Engineering · NEP 2020

AI/ML for Mechanical Engineering

ME-606 A · Program Elective III · Semester VI · 3 credits · ISE 40 + ESE 60

One of the Program Elective III options.

  1. Unit 1: Introduction to AI/ML

    9 hours

    Basics of AI and machine learning, supervised, unsupervised and reinforcement learning, AI in predictive maintenance, smart manufacturing and thermal systems, and experimental and sensor datasets.

    Examined in the 60-mark end-semester paper

    • AI, machine learning and deep learning
    • Types of machine learning
    • AI and machine learning in mechanical systems
  2. Unit 2: Mathematical Basics and Data Handling

    9 hours

    Linear regression basics, mean, variance and correlation, data pre-processing (normalisation, missing data) and plots of mechanical data.

    Examined in the 60-mark end-semester paper

    • Statistics for machine learning: mean, variance and correlation
    • Data preprocessing: normalisation and missing values
    • Data visualisation with Python
  3. Unit 3: Machine Learning Algorithms

    9 hours

    Linear regression for performance prediction, decision trees for fault diagnosis, k-means clustering for patterns, and model evaluation: error, accuracy, overfitting and underfitting.

    Examined in the 60-mark end-semester paper

    • Linear regression for performance prediction
    • Decision trees for fault diagnosis
    • K-means clustering
    • Model evaluation: error, accuracy and overfitting
  4. Unit 4: AI Applications in Mechanical Engineering

    9 hours

    AI for heat-exchanger prediction and optimisation, IC engine combustion and emissions, tool wear and quality control, the digital twin and case studies.

    Examined in the 60-mark end-semester paper

    • AI in heat exchangers, IC engines and manufacturing
    • Industry 4.0 and digital twins
  5. Unit 5: Introduction to AI Tools

    9 hours

    Python with NumPy and Pandas, Excel-based ML tools, the ML workflow from data to prediction, and case studies on engine performance, heat exchangers and fault detection.

    Examined in the 60-mark end-semester paper

    • Python for data science: NumPy, Pandas and Matplotlib
    • Machine learning project workflow

Unit contents are summarised from the official KBCNMU syllabus . AiCanCode.org is not affiliated with Kavayitri Bahinabai Chaudhari North Maharashtra University (KBCNMU).