Team19

Optimizing Energy Efficiency, Material Removal Rate,
Temperature, Tool Wear, and Vibration in Machining
Submitted by Team No. 19
P Sai Sankeerthan Reddy (BL.EN.U4CSE23038)
G Lohith Venkat Reddy (BL.EN.U4CSE23011)
M Vivek Charan (BL.EN.U4CSE23026)
Presented to: Ms. Mamatha.TM

INDEX
1. Introduction and Literature survey

2. Methodology
3. Static Constraints
4. Simulation outcomes
5. Future scope
6. Conclusion
INTRODUCTION
Optimizing Motorized Spindle Systems for Sustainable Machining
•Modern machining demands precise control of spindle speed, feed rate, and cooling rate to enhance energy
efficiency, material removal rate (MRR), and system durability.
•Traditional methods focus on individual aspects like energy efficiency or thermal stability, often neglecting
holistic system performance.
•This study uses NSGA-II to optimize five competing objectives: energy efficiency, thermal stability, MRR,
tool wear, and vibration amplitude.
•By integrating real-world constraints, this approach provides a balanced and sustainable solution for precise
and cost-effective machining.
LITERATURE SURVEY
Several studies laid the foundation for this work:
J. Xu et al. (2015):
This study optimizes spindle speed and feed rate in machining processes to improve energy efficiency. It provides insights into reducing
energy consumption while maintaining machining performance.
A.Smith et al. (2017):

Empirical models predicting energy consumption in CNC machining are developed, highlighting factors that influence energy usage and
offering strategies to minimize waste.
H. Zhang et al. (2018):

Real-time optimization of machining parameters is explored to enhance energy efficiency. The study uses dynamic adjustments based on real-
time data for improved machining operations.
Y. Zhou et al. (2020):

Thermal modeling and optimized cooling strategies are proposed to manage heat in machining processes. This work contributes to energy
management by addressing thermal inefficiencies.
R. Kumar et al. (2021):

The study focuses on controlling vibration and tool wear in CNC machining, offering solutions to enhance energy efficiency and improve the
quality of machined products.
STATIC CONSTRAINTS
Machining Practices: Industry standards for machining processes often use predefined
constraints derived from experiments and theoretical models.
In the context of our optimization problem, dynamic constraints are not required as the system
operates within predefined and predictable parameter ranges. The constraints are based on
industry-standard machine specifications, ensuring safe and optimal performance. Since there are
no real-time variables influencing the process, the static constraints are sufficient to prevent
invalid solutions while maintaining computational simplicity. Testing has shown that the results
obtained under these static constraints meet all objectives without needing adjustments during the
optimization process.
Continuation...
• Our objective is to to enhance machining performance by optimizing key parameters for energy efficiency,
material removal, thermal stability, vibration control, and tool wear. This project employs advanced
optimization techniques to achieve sustainable and precise machining solutions
• Objective Functions and Constraints:
Objective functions:
Material Removal Rate(MRR) = Vnc ∗ F ∗ Anp ∗ wn

o Energy Efficiency(η) = P_useful / P_input
o
o Thermal Stability(Tavg) = (Pheat-Qcool)*Rth + Tambient
o Vibration Amplitude(Av ) = Fm / (k - m * ω^2).
o Tool Wear(Tw) = C / (Vc^n).
Constraints:
o 1500 rpm ≤ Spindle Speed ≤ 2000 rpm
o 10 mm/rev ≤ Feed Rate ≤ 50 mm/rev
o 1 L/min ≤ Cooling Rate ≤ 5 L/min
o 200 m/min ≤ Cutting Speed ≤ 400m/min
METHODOLOGY(PYTHON)
• Objective: A Multi-Objective Genetic Algorithm for Optimizing Energy Efficiency, Material Removal Rate,
Temperature, Tool Wear, and Vibration in Machining
Techniques Used:
• NSGA-II (Non-Dominated Sorting Genetic Algorithm II)
A multi-objective evolutionary algorithm used to handle conflicting objectives, generating a Pareto-
optimal front to analyze trade-offs between objectives.
Time Complexity : O(G(N*M^2)).
• Categorization of Metrics
To classify the performance of individuals into categories such as "Best," "Good," and "Average" for
each metric (e.g., Energy Efficiency, MRR, etc.).
• Parameter Repair
Ensures that individuals' attributes (e.g., spindle speed, feed rate, cooling rate, cutting speed, mass) remain within
realistic and feasible ranges during crossover , mutation and omits negative values in the inputs.
Continuation...
• Pareto Front Visualization
To visually represent the evolution of the Pareto front over generations, highlighting the trade-offs
between conflicting objectives.
• Handling Conflicting Objectives
To balance conflicting objectives (e.g., improving MRR may increase tool wear or vibration
amplitude). NSGA-II facilitates this by identifying solutions where improving one objective doesn’t
excessively degrade another.
Continuation...
Libraries and Modules Used
random: For generating random values for initialization, mutation, and crossover.
numpy: For numerical operations .
matplotlib.pyplot: For visualizing the Pareto front evolution.
deap:
- base: Provides the base toolbox for defining genetic algorithms.
- creator: Used to define custom classes for individuals and fitness functions.
- tools: Includes various tools for selection, mutation, crossover, and sorting.
tabulate: For formatting the results into a readable table format.

RESULTS
Best Overall Solution:
Energy Efficiency (η): 69.97564059137994
Material Removal Rate (MRR): 86178.98941982689
Average Temperature (Tavg): 80.0
Tool Wear Rate (Tw): 19.04251526166191
Vibration Amplitude (Av): 10.0
Inputs for Best Overall Solution:
Spindle Speed (rpm): 1723.5797883965374
Feed Rate (mm/rev): 50.0
Cooling Rate (L/min): 1
Cutting Speed (m/min): 360.2943288366304
Mass (kg): 36.8238712757135
RESULTS
A Pareto front graph plot on the energy efficiency data

computed after all iterations.
FUTURE ENHANCEMENT
• Machine Learning Integration:

Train machine learning models (e.g., neural networks) to predict outcomes like tool wear, energy
efficiency, and thermal stability. This will enhance optimization speed and accuracy based on historical and real-
time data.
• Objective Selection for Tailored Optimization:

Enhance the algorithm to optimize user-selected objectives, allowing tailored prioritization and improved
efficiency.
• Hybrid Optimization Algorithms:

Combine NSGA-II with other algorithms like Particle Swarm Optimization (PSO) to improve the quality
of solutions and accelerate convergence.
• Integration with Digital Twins:

Connect the framework to digital twin technology for virtual simulations and optimization of machining
processes, reducing trial-and-error and improving system reliability before implementation
CONCLUSION
• The project integrates advanced optimization techniques and real-time evaluations for enhancing machining
performance in industrial processes.
• NSGA-II Optimization Algorithm and tailored repair mechanisms synergize technical objectives like energy
efficiency, material removal rate, and system stability.
• Balanced Performance: Focus on optimizing parameters like spindle speed, feed rate, cooling rate, and
cutting speed to achieve sustainable and precise machining.
• NSGA-II Evolutionary Optimization: Ensures adherence to constraints on temperature, tool wear, and
vibration amplitude while providing a Pareto-optimal set of solutions.
• Promotes sustainable manufacturing by enhancing energy efficiency, extending tool life, and reducing
operational costs.
• Highlights the potential of combining optimization algorithms and IoT-driven real-time adjustments to set
a benchmark for smart machining solutions.
CONTRIBUTION
• M Vivek Charan - 30%
• G Lohith Venkat Reddy - 30%
• P Sai Sankeerthan Reddy - 40%
THANK YOU

Team19

Uploaded by

Copyright:

Available Formats

Team19

Uploaded by

Document Information

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Team19

Uploaded by

Copyright:

Available Formats

Optimizing Energy Efficiency, Material Removal Rate,

Temperature, Tool Wear, and Vibration in Machining

Submitted by Team No. 19

P Sai Sankeerthan Reddy (BL.EN.U4CSE23038)

G Lohith Venkat Reddy (BL.EN.U4CSE23011)

M Vivek Charan (BL.EN.U4CSE23026)

Presented to: Ms. Mamatha.TM

1. Introduction and Literature survey

Optimizing Motorized Spindle Systems for Sustainable Machining

A.Smith et al. (2017):

H. Zhang et al. (2018):

Y. Zhou et al. (2020):

R. Kumar et al. (2021):

Material Removal Rate(MRR) = Vnc ∗ F ∗ Anp ∗ wn

Libraries and Modules Used

numpy: For numerical operations .

matplotlib.pyplot: For visualizing the Pareto front evolution.

tabulate: For formatting the results into a readable table format.

A Pareto front graph plot on the energy efficiency data

• Machine Learning Integration:

• Objective Selection for Tailored Optimization:

• Hybrid Optimization Algorithms:

• Integration with Digital Twins:

You might also like