Pengaruh Parameter Pencetakan dan Getaran terhadap Prediksi Nilai Surface Roughness dan Hardness Menggunakan Machine Learning pada FDM 3D Printer dengan Material PLA+

Setyawan, Naufal Alfandra (2024) Pengaruh Parameter Pencetakan dan Getaran terhadap Prediksi Nilai Surface Roughness dan Hardness Menggunakan Machine Learning pada FDM 3D Printer dengan Material PLA+. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 2038201041-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 October 2026. Download (4MB) | Request a copy

Abstract

Seiring berkembangnya teknologi additive manufacturing (AM), semakin banyak jenis
printer 3D, terutama FDM desktop 3D printer. Setiap merek dan tipe memiliki spesifikasi
berbeda, seperti motion system, konstruksi frame, dan transmisi, yang mempengaruhi kestabilan
dan akurasi cetakan. Oleh karena itu, setiap 3D printer memerlukan perlakuan dan pengaturan
tersendiri untuk mendapatkan hasil cetak berkualitas. Untuk mendapatkan hasil cetak yang
baik, diperlukan sistem monitoring dan alat bantu pemodelan prediktif.
Penelitian ini melakukan analisis pengaruh 3 parameter pencetakan yaitu layer height,
print speed, dan extruder temperature terhadap hasil uji surface roughness dan hardness pada
benda hasil cetak. Selama proses pencetakan dilakukan monitoring getaran yang digunakan
oleh model machine learning (ML) untuk dapat memprediksi kualitas hasil cetak (Surface
Roughness & Hardness) yang hasilnya dapat diakses menggunakan user interface sehingga
lebih mudah digunakan.
Dari hasil penelitian diketahui pengaruh setting parameter layer height yang rendah
terhadap surface roughness pada setting variasi layer height 0,05 mm disimpulkan dapat
menurunkan nilai surface roughness secara signifikan yaitu pada rerata 2,7µm. Berdasarkan
korelasi Pearson, parameter pencetakan layer height memiliki 0,56 koefisien korelasi linier
positif dengan hardness. Lalu untuk model ML, R² Test untuk prediksi surface roughness
menghasilkan nilai 0,96. Sedangkan R² Test untuk prediksi hardness menghasilkan nilai 0,84.

============================================================

As additive manufacturing (AM) technology develops, there are more and more types
of 3D printers, especially FDM desktop 3D printers. Each brand and type have different
specifications, such as motion system, frame construction, and transmission, which affect the
stability and accuracy of the print. Therefore, each 3D printer requires its own treatment and
settings to obtain high quality prints. To obtain good print results, a monitoring system and
predictive modelling tools are required.
This research analyses the effect of 3 printing parameters, i.e. layer height, print speed,
and extruder temperature towards the results of surface roughness and hardness tests on printed
objects. During the printing process the vibration is monitored and then the data used by the
machine learning (ML) model to predict the quality of printing results (Surface Roughness &
Hardness) which can be accessed using a user interface for ease of use.
From the research results, it is concluded that the effect of low layer height parameter
settings on surface roughness at a layer height variation setting of 0.05 mm can significantly
reduce the surface roughness value in the range of 2,7µm. Based on Pearson correlation, the
layer height printing parameter has a positive linear correlation with hardness equivalent to 0.56
pearson coefficient. Then for ML, the R² Test value for predicting surface roughness results in
a value of 0.96. While the R² Test value for hardness prediction generated a value of 0.84

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Fused Deposition Modeling (FDM), Vibration, Roughness, Hardness, Machine Learning.
Subjects:	T Technology > T Technology (General) > T174 Technological forecasting T Technology > TS Manufactures T Technology > TS Manufactures > TS156 Quality Control. QFD. Taguchi methods (Quality control)
Divisions:	Faculty of Vocational > Mechanical Industrial Engineering (D4)
Depositing User:	Naufal Alfandra Setyawan
Date Deposited:	02 Aug 2024 08:30
Last Modified:	02 Aug 2024 08:30
URI:	http://repository.its.ac.id/id/eprint/111641

Actions (login required)

View Item