Scribd
Upload
17 views2 pages

AIM Assignment 2 Report

The assignment focuses on predicting mechanical properties of 3D-printed parts using regression techniques, specifically targeting surface roughness. Students will preprocess data, implement linear and polynomial regression, evaluate model performance with various metrics, and visualize results. A report summarizing the methods, comparisons, and insights gained from the analysis is required for submission.

Uploaded by

bt21mec056
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
17 views2 pages

AIM Assignment 2 Report

The assignment focuses on predicting mechanical properties of 3D-printed parts using regression techniques, specifically targeting surface roughness. Students will preprocess data, implement linear and polynomial regression, evaluate model performance with various metrics, and visualize results. A report summarizing the methods, comparisons, and insights gained from the analysis is required for submission.

Uploaded by

bt21mec056
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

AIM -2025

Assignment no. 2
Name:
Enrolment no.

Assignment Title:

Predicting Mechanical Properties of 3D-Printed Parts Using Regression Techniques

Objective:

To predict mechanical properties (such as surface roughness, tensile strength, and


elongation) of 3D-printed parts using process parameters. Students will implement
two regression techniques and compare their performance using a comprehensive
set of regression metrics.

Dataset Overview:

You are provided with a dataset containing various process parameters and the
resulting mechanical properties of 3D-printed parts.

Process Parameters (Independent Mechanical Properties (Dependent


Variables) Variables)
layer_height roughness
wall_thickness tension_strenght
infill_density elongation
infill_pattern
nozzle_temperature
bed_temperature
print_speed
material
fan_speed

Assignment Tasks:

1. Data Preprocessing:
o Handle missing values and outliers if any.
o Encode categorical variables like infill_pattern and material (e.g., using
one-hot encoding).
o Normalize or standardize the features as needed.
o Split the data into 70% training and 30% testing sets.
2. Target Selection:
 Predict roughness (surface quality deviation).
3. Model Implementation:
o Apply two different regression techniques to predict the selected target:
1. Linear Regression
2. Polynomial Regression

o Use Python libraries like scikit-learn for implementation.


4. Performance Evaluation:
o Compare the models using the following regression metrics:
 Mean Absolute Error (MAE)
 Mean Squared Error (MSE)
 Root Mean Squared Error (RMSE)
 Mean Absolute Percentage Error (MAPE)
 Symmetric Mean Absolute Percentage Error (sMAPE)
 R² (Coefficient of Determination)
 Adjusted R²
 Median Absolute Error (MedAE)
 Relative Absolute Error (RAE)
 Mean Bias Error (MBE)
 Weighted Mean Absolute Percentage Error (wMAPE)
 Explained Variance
5. Visualization:
o Plot predicted vs actual values for both models.
o Create bar charts comparing performance metrics for each method.
6. Analysis and Reporting:
o Discuss which model performed better and why.
o Analyze how different process parameters influence the mechanical
property being predicted.
o Suggest potential optimizations in the 3D printing process based on the
insights gained.

Submission:

1. Python Script/Jupyter Notebook containing:


o Data preprocessing, model training, and evaluation code.
2. Report (3-5 pages) summarizing:
o The preprocessing steps and feature selection.
o Comparison of regression models using performance metrics.
o Visualizations of results and key insights from the analysis.

You might also like