Ayuningtyas, Regytha Puteri (2026) Pemodelan Faktor-Faktor yang Memengaruhi Nilai Blaine dan Residu pada Semen PCC Menggunakan Model Regresi Semiparametrik Birespon Spline Truncated (Studi Kasus: PT Semen Tonasa). Other thesis, Institut Teknologi Sepuluh Nopember.
![[thumbnail of 5003221025-Undergraduate_Thesis.pdf]](http://repository.its.ac.id/style/images/fileicons/text.png) |
Text
5003221025-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (8MB) | Request a copy |
Abstract
Industri semen nasional saat ini menghadapi tantangan kelebihan pasokan, di mana kapasitas produksi mencapai 69,14 juta ton, sedangkan konsumsi semen domestik mencapai 63,91 juta ton. Kondisi tersebut mendorong produsen semen untuk terus menjaga konsistensi kualitas produk agar tetap memiliki daya saing di pasar. Salah satu faktor yang memengaruhi mutu semen berada pada kualitas hasil penggilingan pada proses finish mill, yang umumnya diukur melalui nilai Blaine dan Residu. Kedua indikator tersebut dipengaruhi oleh berbagai parameter operasi yang diduga memiliki pola hubungan yang kompleks, sehingga diperlukan pemodelan yang fleksibel untuk menggambarkan hubungan antara parameter proses finish mill dengan nilai Blaine dan residu pada semen Portland Composite Cement (PCC) di PT Semen Tonasa. Penelitian ini menggunakan model regresi semiparametrik birespon spline truncated karena mampu memodelkan hubungan parametrik dan nonparametrik secara simultan. Untuk menentukan titik knot, penelitian ini menggunakan metode Generalized Cross Validation (GCV). Model regresi semiparametrik birespon spline truncated terbaik diperoleh pada orde 1 dengan satu titik knot yang menghasilkan nilai GCV minimum sebesar 1,22 dan Mean Squared Error (MSE) sebesar 0,954. Ukuran kebaikan model yang diperoleh memiliki nilai koefisien determinasi (R2) sebesar 91,216% dan adjusted R2 sebesar 90,495%, yang menunjukkan bahwa model mampu menjelaskan sebagian besar variabilitas data.
======================================================================================================================================
The national cement industry is currently facing the challenge of oversupply, with production capacity reaching 69,14 millions tons, while domestic cement consumption stands at only 63,91 million tons. This condition encourages cement producers to continuously maintain product quality consistency to remain competitive in the market. One of the factors affecting the quality of cement lies in the grinding quality during the finish mill process, which is generally measured by the Blaine value and residue. Both indicators are influenced by various operational parameters suspected of having complex relationship patterns, thus requiring flexible modeling approach to describe the relationship between finish mill process parameters and the Blaine and residue values in Portland Composite Cement (PCC) at PT Semen Tonasa. This study uses a truncated spline biresponse semiparametric regression model because it can simultaneously model both parametric and nonparametric relationships. To determine the knot points, this study used the Generalized Cross Validation (GCV) method. The best truncated spline biresponse semiparametric regression model was obtained at order 1 with one knot point, resulting in a minimum GCV value of 1,122 and a Mean Squared Error (MSE) of 0,954. The goodness-of-fit measures obtained had a coefficient of determination (R²) of 91,216% and an adjusted R² of 90,495%, indicating that the model was able to explain most of the data variability.
| Item Type: | Thesis (Other) |
|---|---|
| Uncontrolled Keywords: | Birespon, Blaine, Regresi Semiparametrik, Residu, Spline Truncated, Biresponse, Blaine, Residual, Semiparametric Regression, Truncated Spline |
| Subjects: | Q Science Q Science > Q Science (General) > Q180.55.M38 Mathematical models Q Science > QA Mathematics Q Science > QA Mathematics > QA278.2 Regression Analysis. Logistic regression |
| Divisions: | Faculty of Science and Data Analytics (SCIENTICS) > Statistics > 49201-(S1) Undergraduate Thesis |
| Depositing User: | Regytha Puteri Ayuningtyas |
| Date Deposited: | 01 Aug 2026 02:46 |
| Last Modified: | 01 Aug 2026 02:46 |
| URI: | http://repository.its.ac.id/id/eprint/138714 |
Actions (login required)
 |
View Item |