Pengendalian Kualitas Proses Produksi Hasil Gula Kristal Putih di PG Djatiroto PTPN XI Menggunakan Diagram Kontrol Maximum Multivariate Cumulative Sum (Max-MCUSUM) Berbasis Residual Model Multioutput Least Square Support Vector Regression (MLS-SVR)
نویسندگان
چکیده
Gula yang merupakan bahan dasar pokok digunakan masyarakat sebagai pemanis dan juga pengawet makanan. Salah satu perusahaan agribisnis bergerak fokus pada produksi gula yaitu PT Perkebunan Nusantara XI (PTPN XI). kristal putih adalah tebu atau bit melalui proses kristalisasi untuk konsumsi rumah tangga telah dijelaskan peraturan SNI 3140.3:2010. Pabrik Djatiroto salah dari enam belas pabrik berada dibawah PTPN XI. Pada penelitian ini karakteristik kualitas warna larutan, besar jenis butir, kadar air masing-masing memiliki hubungan. Hubungan ketiga variabel menunjukkan adanya kasus autokorelasi. Adanya autokorelasi menyebabkan false alarm mendapatkan pengambilan keputusan tidak tepat. Analisis dengan model algoritma Multioutput Least Square Support Vector Regression (MLS-SVR) mengatasi data berautokorelasi dilakukan pengendalian menggunakan diagram kontrol Max-MCUSUM. Input MLS-SVR ditentukan berdasarkan lag signifikan plot PACF, dimana larutan lag-1, 2, 11, 23, butir 3, 28, serta lag-27. Hasil input kombinasi hyper-parameter optimal menghasilkan nilai residual dapat mengurangi Nilai pembuatan fase I k = 0,5 didapatkan terkendali secara statistik setelah diatasi, II sama terdapat titik-titik keluar batas kontrol. identifikasi penyebab out of control faktor-faktor menjadi terjadinya control. kapabilitas kapabel kinerja sudah baik multivariat.
منابع مشابه
Pengaruh Perangkat Server Terhadap Kualitas Pengontrolan Jarak Jauh Melalui Internet
Internet sangat membantu dalam memperbaiki kualitas kehidupan manusia. Hampir semua bidang kehidupan manusia dapat diakses menggunakan internet. Manusia terbantu dengan adanya internet yang menyediakan segala macam informasi yang dibutuhkan. Seiring dengan perkembangan infrastuktur jaringan internet maka pengontrolan jarak jauh mulai berubah menggunakan media internet. Pada penelitian ini digun...
متن کاملRobust Least Square Support Vector Regression for Contaminated Data Modeling
Weighted least squares support vector machine (WLSSVM) is a robust version of least squares support vector machine (LS-SVM). It adds weights on error variables to eliminate the influence of outliers. But the weights, which largely depend on the original regression errors from unweighted LS-SVM, might be unreliable for correcting the biased estimation of LS-SVM, especially for the training data ...
متن کاملSquare Penalty Support Vector Regression
Support Vector Regression (SVR) is usually pursued using the 2–insensitive loss function while, alternatively, the initial regression problem can be reduced to a properly defined classification one. In either case, slack variables have to be introduced in practical interesting problems, the usual choice being the consideration of linear penalties for them. In this work we shall discuss the solu...
متن کاملMultivariate Adaptive Regression Spline and Least Square Support Vector Machine for Prediction of Undrained Shear Strength of Clay
This study adopts Multivariate Adaptive Regression Spline (MARS) and Least Square Support Vector Machine (LSSVM) for prediction of undrained shear strength (su ) of clay, based Cone Penetration Test (CPT) data. Corrected cone resistance (qt ), vertical total stress (σv ), hydrostatic pore pressure (u0 ), pore water pressure at the cone tip (u1 ), and pore water pressure just above the cone base...
متن کاملforecasting municipal solid waste generation by hybrid support vector machine and partial least square model
forecasting of municipal waste generation is a critical challenge for decision making and planning,because proper planning and operation of a solid waste management system is intensively affected by municipal solid waste (msw) streams analysis and accurate predictions of solid waste quantities generated. due to dynamic and complexity of solid waste management system, models by artificial intell...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Jurnal Sains dan Seni ITS (e-journal)
سال: 2023
ISSN: ['2337-3520']
DOI: https://doi.org/10.12962/j23373520.v12i1.101891