Hasil Pencarian  ::  Simpan CSV :: Kembali

"ABSTRAKSaat ini Indonesia masih mengalami defisit BBM sehingga diperlukan pembangunan kilang minyak baru dan optimasi proses pada kilang yang sudah ada. Terdapat unit operasi sekunder berupa VDU vacuum distillation unit untuk mengolah produk residu atmosferik dari CDU crude distillation unit . Dalam rangka menjaga kestabilan operasi diperlukan sistem pengendalian yang tepat dan optimum. Oleh karena itu, dalam penelitian ini akan dilihat apakah pengendali Multi Variabel Model Predictive Control MMPC lebih baik dibandingkan dengan pengendali konvensional prorportional-integral, PI dan pengendali lanjut model predictive control, MPC untuk mengendalikan kombinasi laju alir umpan dan suhu bottom stage kolom distillasi. Pengujian kinerja dilakukan dengan melakukan perubahan set-point 50 pada laju alir umpan dan penurunan suhu sampai dengan 354 oC yang merupakan batas bawah pada simulasi ini. Perbandingan dengan studi sebelumnya diukur menggunakan nilai ISE integral square error -nya. Pada penelitian ini didapatkan ISE untuk laju alir umpan dan suhu bottom stage sebesar 351,78 dan 4,25 secara berurutan. Hasil tersebut mengindikasikan adanya peningkatan ISE pengendalian laju alir sebesar 21,13 . dan peningkatan ISE pengendalian suhu Bottom Stage adalah 26,59 .

---

ABSTRACTCurrently, Indonesia is still experiencing a fuel deficit, so it is necessary to build a new refinery and process optimization at an existing refinery. There is a secondary operating unit of VDU vacuum distillation unit to process the atmospheric residue product from CDU crude distillation unit . In order to maintain the stability of the operation required a proper control system and optimum. Therefore, in this research will be seen whether Multi Variable Model Predictive Control MMPC controller is better than conventional prorportional integral, PI and Model Predictive Control MPC controller to control the combination of feed flow rate, bottom stage temperature of the distillation coloumn. The performance test was performed by changing the set point to 50 of its original for the feed flow rate and bottom stage temperature is set to 354 oC which is the minimum allowed temperature in this simulation. Comparison with previous study is measured using ISE integral square error . In this study, ISEs obtained for feed flow rate and bottom stage temperature are 351.78 and 4.25 respectively. These results indicate an increase in ISE flow rate control by 21.13 . and the increase in ISE Bottom Stage temperature control is 26.59 "

"ABSTRAKSaat ini Indonesia masih mengalami defisit BBM sehingga diperlukan pembangunan kilang minyak yang baru. Pada suatu kilang, terdapat unit operasi sekunder berupa VDU vacuum distillation unit untuk mengolah produk residu atmosferik dari CDU crude distillation unit . Dalam rangka menjaga kestabilan operasi diperlukan sistem pengendalian yang tepat dan optimum. Oleh karena itu, dalam penelitian ini akan dipilih antara pengendali konvensional prorportional-integral, PI dan pengendali lanjut model predictive control, MPC untuk mengendalikan laju alir umpan, suhu umpan, tekanan top-stage, level kondenser, suhu bottom-stage, dan laju alir LVGO light vacuum gas oil , MVGO medium vacuum gas oil , dan HVGO heavy vacuum gas oil . Pengujian kinerja keduanya dilakukan dengan melakukan perubahan set-point dan gangguan sebesar 10 , 25 , dan 50 yang diukur menggunakan nilai ISE integral square error -nya. Hasilnya, untuk pengendalian laju alir umpan, suhu umpan, tekanan top-stage, suhu bottom-stage, dan laju alir LVGO, MVGO, dan HVGO digunakan MPC karena terjadi perbaikan kinerja sebesar 34 , 75 , 97 , 98 , 22 , 68 dan 80 saat pengujian perubahan set-point dibanding dengan pengendali PI, sedangkan untuk pengendalian level kondenser digunakan pengendali PI karena kinerjanya jauh lebih baik dibandingkan dengan MPC. Untuk pengujian gangguan yang sangat besar 50 dari laju alir umpan , persentase kesalahannya pada suhu umpan, tekanan top-stage, level kondenser, suhu bottom-stage, laju alir LVGO, MVGO, dan HVGO masing-masing sebesar 6 , 5,5 , 6 , 5,5 , 0,3 , 0,7 , dan 1,6 .

---

ABSTRACTAt this time, Indonesia is still suffering fuel deficit. So that, new oil refinery is needed. In oil refinery, there is secondary process unit, VDU vacuum distillation unit , for processing atmospheric residue from CDU crude distillation unit . In order to maintain the stability of the operation, a proper and optimum control system is required. Therefore, in this study will be selected between conventional controller prorportional integral, PI and advanced controller model predictive control, MPC to control feed flow rate, feed temperature, top stage pressure, condenser level, bottom stage temperature, and the flow rate of LVGO light vacuum gas oil , MVGO medium vacuum gas oil , and HVGO heavy vacuum gas oil . The performance test of MPC and PI which is done by conducting set point and disturbance changes 10 , 25 , and 50 , measured by using ISE integral square error values. As a result, for feed flow control, feed temperature, top stage pressure, bottom stage temperature and flow rate LVGO, MVGO, and HVGO MPC is used due to performance improvements, respectively 34 , 75 , 97 , 98 , 22 , 68 and 80 , in set point changes test compared to PI controllers. While for the level control of condenser, PI control is used because its performance is much better than the MPC. For very large disturbance tests 50 of the feed flow rate , the percentage of error of feed temperature, top stage pressure, condenser level, bottom stage temperature, flow rate LVGO, MVGO and HVGO were 6 5.5 , 6 , 5.5 , 0.3 , 0.7 , and 1.6 respectively."

"Penyakit jerawat merupakan sebuah kondisi kulit yang umum yang ditandai dengan folikel rambut yang tersumbat, tidak hanya mempengaruhi penampilan fisik tetapi juga mempengaruhi kepercayaan diri individu. Metode diagnostik yang maju sangat penting untuk menentukan tingkat keparahan jerawat, yang dapat membimbing strategi pengobatan yang efektif. Penelitian ini memperkenalkan pendekatan inovatif untuk mengklasifikasikan tingkat keparahan jerawat pada citra wajah menggunakan Diagnostic Evidence Distillation yang memanfaatkan multi teacher knowledge distillation. Studi ini meningkatkan model single teacher konvensional dengan menggabungkan beberapa arsitektur teacher, memungkinkan transfer pengetahuan yang lebih kuat dan akurat ke student model. Penulis mengembangkan dan menguji model yang mengintegrasikan Convolutional Neural Network (CNN) dengan kerangka kerja multi teacher untuk meningkatkan akurasi prediktif. Pendekatan yang dilakukan menggabungkan secara unik diagnostic evidence dengan teknik deep learning untuk mengoptimalkan proses klasifikasi. Evaluasi dilakukan menggunakan dataset ACNE04, yang dianotasi menurut kriteria Hayashi, memastikan representasi komprehensif dari berbagai tingkat keparahan jerawat. Hasilnya menunjukkan bahwa model multi teacher knowledge distillation mencapai akurasi yang lebih unggul dibandingkan model single teacher sebelumnya, dengan peningkatan akurasi menjadi 90.00%, melampaui benchmark sebelumnya sebesar 86.06%. Ini menunjukkan kemajuan signifikan dalam klasifikasi otomatis tingkat keparahan jerawat. Studi penulis tidak hanya memberikan kemajuan metodologis dalam bidang pemrosesan gambar medis tetapi juga berkontribusi pada penilaian tingkat keparahan jerawat yang lebih akurat dan dapat diandalkan, berpotensi meningkatkan hasil pengobatan dan perawatan pasien.

---

Acne is a common skin condition characterized by clogged hair follicles, affecting not only physical appearance but also an individual's self-confidence. Advanced diagnostic methods are crucial for determining the severity of acne, which can guide effective treatment strategies. This research introduces an innovative approach to classifying the severity of acne in facial images using Diagnostic Evidence Distillation that utilizes multi teacher knowledge distillation. This study enhances the conventional single teacher model by integrating multiple teacher architectures, allowing for a more robust and accurate knowledge transfer to the student model. The authors developed and tested a model that integrates a Convolutional Neural Network (CNN) with a multi-teacher framework to improve predictive accuracy. The approach uniquely combines diagnostic evidence with deep learning techniques to optimize the classification process. The evaluation was conducted using the ACNE04 dataset, annotated according to the Hayashi criteria, ensuring a comprehensive representation of various acne severities. The results show that the multi-teacher knowledge distillation model achieves superior accuracy compared to the previous single-teacher model, with an improved accuracy of 90.00%, surpassing the previous benchmark of 86.06%. This indicates significant advancement in the automated classification of acne severity. The authors' study not only provides methodological advancement in the field of medical image processing but also contributes to more accurate and reliable assessments of acne severity, potentially enhancing treatment outcomes and patient care."

"ABSTRAKThe productivity of water treatment through distillation method was studied by varying the size of the zinc heat absorber in a solar-based distillation unit. An additional zinc heat absorber was proposed to improve the efficiency of the distillation unit. This research investigates the usage of zinc heat absorber with size 10 to 90% of water surface area. The temperature at various locations inside the distillation unit was monitored throughout the operation in order to obtain data necessary for the equation engineering solver method, which was conducted to calculate the efficie orber that is 10% of the water area produced 1.43 liters of condensed product per day providing efficiency of 25.99%. The efficiency reduced significantly to 15.02% when the sizeof the heat absorber was increased to 90%. "