Mauridhi Heri Purnomo
Jurusan Teknik Elektro, Fakultas Teknologi Industri,Institut Teknologi Sepuluh Nopember Surabaya, Surabaya 60111, Indonesia

Published : 7 Documents
Articles

Found 7 Documents
Search

PENGATURAN KECEPATAN MOTOR INDUKSI TANPA SENSOR KECEPATAN MENGGUNAKAN METODE SELF-TUNING FUZZY SLIDING MODE CONTROL BERBASIS DIRECT TORQUE CONTROL Jaya, Arman; Soebagio, Soebagio; Purnomo, Mauridhi Heri
Seminar Nasional Aplikasi Teknologi Informasi (SNATI) 2009
Publisher : Jurusan Teknik Informatika, Fakultas Teknologi Industri, Universitas Islam Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Metode pengaturan kecepatan putar motor induksi tanpa sensor menggunakan fuzzy logic sliding modecontroller(FLSMC) dijelaskan dalam paper ini,. Direct torque control (DTC) digunakan sebagai basis estimasiparameter kontrol. Estimasi putaran rotor, torka dan fluks dilakukan oleh DTC yang diberi input tegangan danarus stator. Untuk mencapai putaran yang dikehendaki digunakan estimasi putaran sebagai umpan balik padasistem kontrol. Error dan delta error kecepatan putar sebagai masukan pada Sliding Mode Control (SMC) danjuga sekaligus sebagai masukan bagi Fuzzy Logic (FL). Fungsi FL adalah sebagai tuning nilai parameter SMC.Hasil yang diperoleh melalui simulasi menunjukkan respon kecepatan putar yang cepat dalam kondisi start,perubahan beban dan perubahan set point. Khusus pada kondisi perubuhan beban, respon kecepatan hampirtidak mengalami perubahan kecepatan atau bisa dikatakan respon kecepatan kokoh bila ada gangguan.Kata Kunci: Direct torque control, Self-tuning Fuzzy sliding mode control, parameter kontrol
Pengenalan Plat Mobil Indonesia menggunakan Learning Vector Quantization Anifah, Lilik; Haryanto, Haryanto; Purnomo, Mauridhi Heri
Jurnal Fisika dan Aplikasinya Vol 5, No 1 (2009)
Publisher : Jurnal Fisika dan Aplikasinya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (211.097 KB) | DOI: 10.12962/j24604682.v5i1.929

Abstract

Pembacaan plat nomer Indonesia secara otomatis mempunyai peranan yang sangat besar dalam kehidupan sehari-hari. Contoh aplikasinya antara lain manajemen tempat parkir, monitoring lalu lintas, pembacaan plat nomer pada pembayaran di jalan tol. Tujuan paper ini adalah untuk mengenali karakter pada plat nomer Indonesia menggunakan Learning Vector Quantization (LVQ). Citra ditangkap oleh kamera dan mengalami preprosessing sebagai berikut: image diresize 0,6 kali dari citra asli, deteksi tepi menggunakan sobel, pixel pada image yang berjarak kurang dari 10 pixel, noise dihilangkan, mengindex semua objek yang merupakan kandidat plat nomer. Segmentasi dari plat menggunakan Metode Moment. Plat yang telah disegmentasi dinormalisasisehingga mempunyai ukuran yang standart 600 x 1000 pixel. Seluruh objek diindeks dan dicari kandidat yang merupakan karakter plat nomer, kemudian disegmentasi menggunakan metode moment dan dinormalisasi menjadi 10 x 20 pixel. Karakter yang telah standart dikenali menggunakan LVQ.
The development of Inverter Fuzzy Logic Control for Induction Motor Control by Vector Control Method in Electric Vehicle Purwanto, Era; Ashary, Mohammad; Subagio, Subagio; Purnomo, Mauridhi Heri
Makara Journal of Technology Vol 12, No 1 (2008)
Publisher : Directorate of Research and Community Services, Universitas Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (356.084 KB) | DOI: 10.7454/mst.v12i1.135

Abstract

In response to concerns about energy cost, energy dependence, and environmental damage, a rekindling of interest in electric vehicles (EV’s) has been obvious. Thus, the development of power electronics technology for EV’s will take an accelerated pace to fulfill the market needs, regarding with the problem in this paper is presented development of fuzzy logic inverter in induction motor control for electric vehicle propulsion. The Fuzzy logic inverter is developed in this system to directed toward developing an improved propulsion system for electric vehicles applications, the fuzzy logic controller is used for switching process. This paper is describes the design concepts, configuration, controller for inverter fuzzy logic and drive system is developed for this high-performance electric vehicle.
Pengembangan Graph Mining untuk Prediksi Jaringan Kerja Sistem Pembayaran dalam Real Time Gross Settlement Berbasis Clearing House Bukhori, Saiful; Hariadi, Mochamad; Purnama, I Ketut Eddy; Purnomo, Mauridhi Heri
Jurnal Teknik Industri Vol 12, No 1 (2010): JUNE 2010
Publisher : Institute of Research and Community Outreach - Petra Christian University

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (175.978 KB) | DOI: 10.9744/jti.12.1.pp. 33-40

Abstract

This research develops the settlement mechanism in the Real Time Gross Settlement using so called clearing house through a serious game method. In this approach banks are represented as nodes that do the settlement process according to the simple rules. Moreover, the graph mining approach is used for predicting the activity networks on those banks. As the result, for constant nodes indicate that the more the activity networks among banks are available, the more the activity networks can be identified. Furthermore, the smaller the differences among the bank health’s level are, the greater the network activities can be identified. This behavior is a consequence of chosen fixed point assumption.
PENGATURAN MOTOR INDUKSI MENGGUNAKAN OBSERVER SELF CONSTRUCTING FUZZY NEURAL NETWORK DENGAN METODE ALGORITMA PELATIHAN LEVENBERG MARQUARDT Suhariningsih, Suhariningsih; Soebagio, Soebagio; Purnomo, Mauridhi Heri
Jurnal Teknik Elektro Vol 8, No 2 (2008): SEPTEMBER 2008
Publisher : Institute of Research and Community Outreach

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (249.006 KB) | DOI: 10.9744/jte.8.2.79-87

Abstract

This paper describes about development of 3 phase speed sensorless induction motor speed controller using Field Oriented Vector(FOC) method. Motor speed is estimated by an observer using Self Constructing fuzzy Neural Network (SCFNN) with Levenberg Marquardt(LM) learning algorithm method, that replaces backpropagation method because this method is slow to reach convergent. SCFNN method combines the fuzzy and neural network. The simulation results show that the system can estimate flux and speed of induction motor and it converges faster than backpropagation method. .The estimation result can be used to identify rotor speed of induction motor with good performance Abstract in Bahasa Indonesia: Dalam penelitian ini dikembangkan pengaturan kecepatan motor induksi 3 phase tanpa sensor yang dioperasikan dengan metoda Field Oriented Vector (FOC). Kecepatan motor diestimasi oleh suatu observer dengan suatu metoda Self Constructing Fuzzy Neural Network (SCFNN) dimana pelatihannya menggunakan metode algoritma pelatihan Levenberg Marquardt (LM), yang menggantikan metode Backpropagasi karena metode ini kurang cepat mencapai konvergen. Metode SCFNN mempunyai kemampuan untuk menggabungkan Fuzzy dan Neural Networks. Hasil simulasi menunjukkan sistem dapat mengestimasi fluksi dan kecepatan dengan kekonvergenan yang lebih cepat dari metode backpropagasi. Hasil estimasi dapat digunakan untuk mengidentifikasi kecepatan rotor motor induksi Kata kunci: pengaturan kecepatan, motor induksi tanpa sensor, FOC, SCFNN observer, Levenberg Marquardt
PENGATURAN KECEPATAN MOTOR INDUKSI TANPA SENSOR KECEPATAN DENGAN METODA DIRECT TORQUE CONTROL MENGGUNAKAN OBSERVER RECURRENT NEURAL NETWORK Sunarno, Epyk; Soebagio, Soebagio; Purnomo, Mauridhi Heri
Jurnal Teknik Elektro Vol 8, No 2 (2008): SEPTEMBER 2008
Publisher : Institute of Research and Community Outreach

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (262.771 KB) | DOI: 10.9744/jte.8.2.88-95

Abstract

This paper describes about development of sensorless control for three phase induction motor speed which is operated by Direct Torque Control (DTC). Induction motor speed is identified by an Observer. Current supply and Stator Voltage are ruquired by Observer to gain Motor Speed Estimation. Observer for motor speed identification is developed using Artificial Neural Network (ANN) Method and Recurrent Neural Network (RNN) learning algorithm. The simulation results using MathLab/Simulink show that on PI controller with Recurrent Neural Network (RNN) observer, there are the overshoot 7,0224%, rise time 0,0125 second and settling time 0,364 second with reference speed 77,9743 rad./sec. Abstract in Bahasa Indonesia: Penelitian ini membahas pengembangan kontrol pada kecepatan motor induksi tiga fasa tanpa sensor kecepatan (speed sensorless) yang dioperasikan dengan metoda Direct Torque Control (DTC). Kecepatan motor induksi diidentifikasi oleh suatu observer. Estimasi kecepatan motor oleh observer memerlukan masukkan arus dan tegangan stator. Observer untuk identifikasi kecepatan motor menggunakan metode Artificial Neural Network (ANN) dengan algoritma pembelajaran menggunakan Recurrent Neural Network (RNN). Hasil simulasi menggunakan matlab-simulink menunjukkan saat motor diberikan kecepatan referensi 77,9743 rad/detik terjadi overshoot 7,0224% , rise time 0,0125 detik dan settling time 0,364 detik. Kata Kunci: direct torque control, speed sensorless, recurrent neural network
PENGEMBANGAN GRAPH MINING UNTUK PREDIKSI JARINGAN KERJA SISTEM PEMBAYARAN DALAM REAL TIME GROSS SETTLEMENT BERBASIS CLEARING HOUSE Bukhori, Saiful; Hariadi, Mochamad; Purnama, I Ketut Eddy; Purnomo, Mauridhi Heri
Jurnal Teknik Industri Vol 12, No 1 (2010): JUNE 2010
Publisher : Institute of Research and Community Outreach - Petra Christian University

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (175.978 KB) | DOI: 10.9744/jti.12.1.pp. 33-40

Abstract

This research develops the settlement mechanism in the Real Time Gross Settlement using so called clearing house through a serious game method. In this approach banks are represented as nodes that do the settlement process according to the simple rules. Moreover, the graph mining approach is used for predicting the activity networks on those banks. As the result, for constant nodes indicate that the more the activity networks among banks are available, the more the activity networks can be identified. Furthermore, the smaller the differences among the bank health?s level are, the greater the network activities can be identified. This behavior is a consequence of chosen fixed point assumption.