Garuda - Garba Rujukan Digital

Metode Tuning Operating Range Fuzzy PID Controller pada Sistem Orde Tiga Sutarna, Nana; Purwanti, B. S. Rahayu
Jurnal Teknik Elektro Vol 12, No 1 (2020): Jurnal Teknik Elektro
Publisher : Jurusan Teknik Elektro, Fakultas Teknik, Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/jte.v12i1.24050

This research discusses the development of a model Fuzzy Proportional, Integral, Derivative (Fuzzy PID) controller models and self-tuning. This method has been implemented in the third-order system of Differential Equations, as a sample implementation of a PID controller. The methods self-tuning known are fuzzy rules, membership function (MF), and scaling factor. The focus of the discussion in this research is to introduce self-tuning to the operating range (OR) setting of MF. Previous research has succeeded in converting a PID controller to a Fuzzy Logic Controller (FLC) which is in accordance with the PID structure. The FLC has three inputs and one output as in the PID controller, hereinafter referred to as Fuzzy PID controller. Knowledgebase on the FLC structure of three inputs one output is expressed in the form of cubic fuzzy associative memory (FAM). The conversion was done by mapping errors, integrals error, derivative errors and outputs of PID controller into the OR of MF Fuzzy input/output. The size of the OR conversion value on the MF fuzzy input was set, so the response transient is set-to-point. While the OR value of the MF fuzzy output was fixed as a limitation. Improved settling time was reached up to 75.3% and percent overshoot was reduced by 57.7% in Fuzzy PID with PID controller. The output signal from the Fuzzy PID controller showed the smallest amplitude of 24.12, while the PID controller was 32.53. The amplitude unit depends on the Fuzzy PID controller parameters when it applied the real plant. The third-order Fuzzy PID controller has been successfully simulated in Simulink/Matlab.

Sistem Pendeteksi Keasaman dan Warna Urine sebagai Indikasi Dini Dehidrasi Sutarna, Nana -
ISSN
Publisher : POLITEKNIK NEGERI JAKARTA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32722/ees.v2i2.3570

Dehidrasi merupakan suatu kondisi kekurangan cairan tubuh karena jumlah cairan yang keluar lebih banyak daripada jumlah cairan yang masuk. Dampak dehidrasi akan beresiko mengalami obesitas dan penurunan konsentrasi. Dehidrasi juga mempengaruhi fungsi kemampuan kognitif otak dan memori seseorang. Dehidrasi akut harus dihindari mengingat bahaya yang ditimbulkannya bagi kesehatan. Tes paling sederhana untuk dehidrasi adalah dengan melihat warna urin. Namun warna urin juga bisa dipengaruhi oleh asupan makanan tertentu. Pada penelitian ini dirancang suatu sistem perkemihan yang dilengkapi dengan sensor warna dan sensor pH. Sensor pH H-101 dan sensor warna TCS3200 digunakan dalam penelitian ini. Sensor pH ditambahkan untuk menghindari kesalahan deteksi urin akibat kesalahan pembacaan warna urin. Sensor TCS3200 diklasifikasikan dalam level warna RGB (Merah, Biru, Hijau). Urin dideteksi dengan tingkat warna atau keasaman pH sebagai masukan untuk menentukan tingkat dehidrasi. Hasil deteksi urin seseorang ditampilkan di layar LCD. Hasil pengukuran menunjukkan bahwa semakin asam atau dominan warna R dan G urin seseorang maka semakin tinggi tingkat dehidrasinya. Batas tingkat hidrasi seseorang jika keasaman urin memiliki pH <6.

Antusiasme Warga Blok Tempe Citeureup Bogor Menggunakan Bilik Pengukur Suhu Tubuh Pengantisikasi Covid-19 Purwanti, Bernadeta Siti Rahayu; Sutarna, Nana; Nuralam, Nuralam; Mawardi, Latif
VIVABIO: Jurnal Pengabdian Multidisiplin Vol 2, No 3 (2020): VIVABIO:Jurnal Pengabdian Multidisiplin
Publisher : Sam Ratulangi University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35799/vivabio.2.3.2020.31070

ABSTRAKPandemi covid-19 yang merebak sejak awal tahun 2020 meresahkan masyarakat, perlu tindakan pencegahan. Demikian halnya Politeknik Negeri Jakarta, melalui kegiatan Pengabdian Masyarakat (PengMas) telah berkontribusi mencegah dan memutus rantai penyebaran covid-19. Sementara itu, kemampuan para ahli untuk menurunkan percepatan sebarannya di sejumlah negara belum signifikan. Terbukti aktifitas Pemerintah, pengusaha dan pekerja, organisasi-organisasi masih dibatasi waktu dan ruang geraknya. Seluruh lapisan masyarakat menghadapi tantangan besar dalam upaya perlawanan pandemi covid-19. Perlindungan keselamatan dan kesehatan di tempat kerja sedang krisis. Kekhawatiran kembali beraktifitas semakin ragu untuk dicapai, penekanan penyebarluasan belum signifikan keberhasilannya. Sorotan terhadap risiko Keselamatan Dan Kesehatan Kerja (K3) meningkat akibat penyebaran covid-19 makin meluas. Perkembangan eksplorasi perangkat untuk mencegah, mengendalikan risiko penyebaran covid-19. Antisipasi terhadap risiko psikososial, ergonomis dan risiko keselamatan/kesehatan warga agarÂ minimal memproteksi diri terhadap covid-19. Selain tertib melaksnakan 3M (menggunakan masker, mencuci tangan, dan menjaga jarak), kelompok Dosen Prodi Elekronika Industri (EI) telah merealisasikan Bilik Pengukur Suhu Tubuh. Masyarakat sasarannya adalah warga Blok Tempe, Citereup, Kabupaten Bogor dengan melibatkan remajanya. Setelah Bilik Pengukur Suhu teruji fungsinya kelompok Dosen EI melaksankan pendampingan kepada kelompok Remaja Blok Tempe (RBT). Pelaksanaan pendampingan juga melibatkan beberapa mahasiswa agar remaja lebih nyaman mengikuti pendampingan cara penggunaan Bilik Pengukur Suhu Tubuh. Tahapan pelaksaan PengMas perancangan/instalasi bilik, serah terima, dan pendampingan sebagai rangkaian utuh mencapai tujuan pemberdayaan remaja Blok Tempe. Hasil pendampingan tim pengMas adalah kemandirian kelompok RBT menggunakan bilik untuk pengukuran suhu tubuh. Khususnya ketua RBT yang sangat antusias mengelola dan mencoba memindahkan Bilik ke area lain di sekitar Blok Tempe. Kegagalan uji alat melunturkan minatnya untuk dapat menggunakan bilik, mengulang instalasi dan berhasil.

Sistem Pendeteksi Keasaman dan Warna Urine sebagai Indikasi Dini Dehidrasi Nana - Sutarna
Electrices Vol 2 No 2 (2020): Volume 2 Nomor 2 Tahun 2020
Publisher : Jurusan Teknik Elektro, Politeknik Negeri Jakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32722/ees.v2i2.3570

Dehidrasi merupakan suatu kondisi kekurangan cairan tubuh karena jumlah cairan yang keluar lebih banyak daripada jumlah cairan yang masuk. Dampak dehidrasi akan beresiko mengalami obesitas dan penurunan konsentrasi. Dehidrasi juga mempengaruhi fungsi kemampuan kognitif otak dan memori seseorang. Dehidrasi akut harus dihindari mengingat bahaya yang ditimbulkannya bagi kesehatan. Tes paling sederhana untuk dehidrasi adalah dengan melihat warna urin. Namun warna urin juga bisa dipengaruhi oleh asupan makanan tertentu. Pada penelitian ini dirancang suatu sistem perkemihan yang dilengkapi dengan sensor warna dan sensor pH. Sensor pH H-101 dan sensor warna TCS3200 digunakan dalam penelitian ini. Sensor pH ditambahkan untuk menghindari kesalahan deteksi urin akibat kesalahan pembacaan warna urin. Sensor TCS3200 diklasifikasikan dalam level warna RGB (Merah, Biru, Hijau). Urin dideteksi dengan tingkat warna atau keasaman pH sebagai masukan untuk menentukan tingkat dehidrasi. Hasil deteksi urin seseorang ditampilkan di layar LCD. Hasil pengukuran menunjukkan bahwa semakin asam atau dominan warna R dan G urin seseorang maka semakin tinggi tingkat dehidrasinya. Batas tingkat hidrasi seseorang jika keasaman urin memiliki pH <6.

Perancangan Modul Pengendali Torsi Motor pada Desain Kontrol Pedal Assist Sepeda Listrik Lingga Suhadha; Nana Sutarna; B.S.R. Purwanti Purwanti
Prosiding Industrial Research Workshop and National Seminar Vol 12 (2021): Prosiding 12th Industrial Research Workshop and National Seminar (IRWNS)
Publisher : Politeknik Negeri Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (971.105 KB)

Perancangan Modul Pengendali Torsi Motor pada Desain Kontrol Pedal Assist Sepeda Listrik

DISAIN ALGORITMA MODEL PREDICTIVE CONTROL (MPC) PENGENDALIAN SISTEM TATA UDARA PRESISI Nana Sutarna
Jurnal Poli-Teknologi Vol. 9 No. 2 (2010)
Publisher : Politeknik Negeri Jakarta

ABSTRACT The model system of precision air condition is modeled as a multivariable system with two outputs namely temperature and humidity and two inputs namely motor rotation speed and valve opening. In this model there is a problem of coupling between the input and output. Model Predictive Control (MPC) is one way to overcome the problem of coupling in multivariable systems. MPC controllers are designed without the constraints to determine a reliable algorithm. From the simulation results it appears that the controlling parameters is best horizon Hp = 10, Hu = 4, the weighting matrix R = 0.1, and Q = 3. With this parameter the output response follow the set point signal Keywords: Precision Air Systems Administration, MPC, Hp, Hu, Q and R ABSTRAK Model sistem tata udara presisi dimodelkan sebagai sebuah sistem multivariable dengan dua output yaitu temperature dan kelembaban dan dua input yaitu kecepatan putaran motor dan bukaan valve. Pada model ini ada masalah coupling diantara input dan outputnya. Model Predictive Control (MPC) adalah salah satu cara untuk mengatasi masalah coupling dalam sistem multivariable. Pengendali MPC dirancang tanpa constraints untuk menentukan agoritma yang handal. Dari hasil simulasi nampak bahwa parameter-parameter pengendali yang terbaik adalah horizon Hp=10, Hu=4, matrik pembobotan R=0.1, dan Q=3. Dengan parameter ini respon keluarannya mengikuti sinyal set point Kata Kunci : Sistem Tata Udara Presisi, MPC, Hp, Hu, Q dan R.

Hyperparameter Tuning Impact on Deep Learning Bi-LSTM for Photovoltaic Power Forecasting Sutarna, Nana; Tjahyadi, Christianto; Oktivasari, Prihatin; Dwiyaniti, Murie; Tohazen, Tohazen
Journal of Robotics and Control (JRC) Vol 5, No 3 (2024)
Publisher : Universitas Muhammadiyah Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18196/jrc.v5i3.21120

Solar energy is one of the most promising renewable energy sources that can reduce greenhouse gas emissions and fossil fuel dependence. However, solar energy production is highly variable and uncertain due to the influence of weather conditions and environmental factors. Accurate forecasting of photovoltaic (PV) power output is essential for optimal planning and operation of PV systems, as well as for integrating them into the power grid. This study develops a deep learning model based on Bidirectional Long Short-Term Memory (Bi-LSTM) to predict short-term PV power output. The main objective is to examine the effect of hyperparameter tuning on the forecasting accuracy and the actual PV output power. The main contribution is identifying the optimal combination of hyperparameters, namely the optimizer, the learning rate, and the activation function, for the PV output. The dataset consists of 143786 observations from sensors measuring solar irradiation, PV surface temperature, ambient temperature, ambient humidity, wind speed, and PV power output for 50 days in Bandung, Indonesia. The data is preprocessed by smoothing and splitting into training (70%, 35 days), validation (15%, 7.5 days), and testing (15%, 7.5 days) sets. The Bi-LSTM model is trained and tested with two optimizers: Adam and RMSprop, and three activation functions: Tanh, ReLU, and Swish, with different learning rates. The results indicate that the optimal performance is obtained by the Bi-LSTM model with Adam optimizer, learning rate of 〖1e〗^(-4), and Tanh activation function. This model has the lowest MAE of 0.002931070979684591, the lowest RMSE of 0.008483537231080387, and the highest R-squared of 0.9988813964105624 when tested with the validation dataset and requires 93 epochs to build. The model also performs well on the test dataset, with the lowest MAE of 0.002717077964916825, the lowest RMSE of 0.007629486798682186, and the highest R-squared of 0.9992563395109665. This study concludes that hyperparameter tuning is a vital step in developing the Bi-LSTM model to improve the accuracy of PV output power prediction.

Pendeteksi Halangan dan GPS Pada Alat Bantu Tunanetra Alif Ramadhan Hidayat; M. Rafli Ramadhan; Sutarna, Nana; Syan Rosyid Adiwinata
Electrices Vol 6 No 2 (2024): Volume 6 Nomor 2 Tahun 2024
Publisher : Jurusan Teknik Elektro, Politeknik Negeri Jakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32722/ees.v6i2.6831

Penyandang disabilitas mata sering mangalami kesulitan jika beraktifitas sehari-hari. Apalagi jika pergi ke suatu tempat yang belum pernah dikunjungi sebelumnya. Mereka bisa tersesat untuk kembali pulang. Penelitian ini bertujuan untuk membuat alat bantu pendeteksi halangan sebagai pentunjuk jalan dan juga sebagai pelacak posisi keberadaan penderita disabilitas saat tersesat. Metodologi yang digunakan dalam penelitian ini adalah rancang bangun alat dengan sensor infrared sebagai detektor dan ATmega 328P sebagai mikrokontroler serta dilengkapi dengan model Global positioning System (GPS). Disain alat berbentuk kotak yang dipasang di dada (chest strap). Hasil pengukuran menunjukkan bahwa jarak deteksi terhadap halangan sebesar 50 cm pada arah tegak lurus terhadap alat pada sudut 0o. Delay sinyal SMS yang diterima oleh smartphone antara 1 sampai 2 detik. Lokasi terjauh yang masih bisa terdeteksi oleh GPS pada latitude -6.17519 dan longitude 106.50083 atau sebesar 13 km berdasarkan jarak yang dipetakan oleh Google Maps.

Monitoring The Temperature of The Immersion Freezing Process to Prediction and Analyzing Production Costs Mirroring Jewelry IHTIFAZHUDDIN, RAMDHANY; Sutarna, Nana; Wicakson, Britantyo
Emitor: Jurnal Teknik Elektro Vol 25, No 1: March 2025
Publisher : Universitas Muhammadiyah Surakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23917/emitor.v25i1.6499

This research is motivated by problems at PT Sentral Kreasi Kencana in the immersion freezing process for jewelry production. This process is still carried out manually with a fixed time assumption of 45 minutes, which causes temperature uncertainty and difficulty in increasing production quantity. This has an impact on decreasing efficiency and increasing production costs per gram. The study aims to increase the efficiency of the immersion freezing process by implementing a sensor-based temperature monitoring system and production cost analysis. The methods used include developing a temperature monitoring system using the MLX90614 sensor, integration with Arduino Uno, and creating a graphical user interface (GUI) for real-time data analysis. The system developed consists of an MLX90614 infrared temperature sensor, an Arduino Uno microcontroller, a buzzer as an alarm, and a push-button for batch calculation. The GUI displays real-time temperature data, trend graphs, total batches, product weight, fixed costs, and cost/gram calculations. The results showed that the implementation of the temperature monitoring system increased the number of daily production batches by 50%, from 4 to 6 batches. The processing time was also reduced from 45 minutes to 30 minutes per batch. The optimum temperature of −7◦C was set as the reference point for the immersion freezing process. Production cost analysis showed a significant decrease in cost/gram from IDR 6,333.33 to IDR 2,638.89, far below the company’s standard cost of IDR 5,000.00 per gram. This system has proven effective for gold with a content of 34.0%, 67.1%, and 75.5%. The implementation of this technology has succeeded in increasing production efficiency, reducing the cost per gram, and increasing overall production capacity. This research provides a practical solution for optimizing the immersion freezing process in the jewelry industry, with the potential for wider application in other precision manufacturing sectors.

Optimized BiLSTM-Dense Model for Ultra-Short-Term PV Power Forecasting Tjahyadi, Christianto; Sutarna, Nana; Oktivasari , Prihatin
Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control Vol. 10, No. 2, May 2025
Publisher : Universitas Muhammadiyah Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22219/kinetik.v10i2.2127

The growing integration of photovoltaic (PV) systems into power grids poses challenges due to the inherent variability in PV output, particularly during rapid weather changes. While existing forecasting methods often struggle to capture these fluctuations, accurate ultra-short-term PV power prediction is critical for grid stability. The study aims to develop an optimized BiLSTM-Dense model that enhances forecasting accuracy by incorporating an additional dense layer. The model is designed to improve forecasting performance over a 30-second horizon. It utilizes a dataset of solar irradiance, PV output power, surface temperature, ambient temperature, humidity, and wind speed, collected in late 2023. Data preprocessing involved normalization and smoothing techniques to enhance robustness. Hyperparameter optimization was performed using grid search. Evaluation results demonstrate the superiority of the proposed model, achieving an MAE of 0.00271 and an RMSE of 0.00806 when paired with the Adam optimizer and Swish activation function. Compared to standard BiLSTM, the BiLSTM-Dense achieved MAE and RMSE improvements of 0.52% and 2.19%, respectively. It also outperformed the LSTM model with reductions of 4.00% in MAE and 2.65% in RMSE, and significantly surpassed ARIMA, reducing MAE by 98.87% and RMSE by 97.21%. These findings highlight the model’s ability to capture complex, non-linear dependencies in PV output data, outperforming conventional approaches like ARIMA, which rely on linear assumptions, and simpler architectures like LSTM, which lack bidirectional context integration.

Title

Found 12 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 12 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 12 Documents
Search