Claim Missing Document
Check
Articles

Found 25 Documents
Search

Discount Factor Parametrization for Deep Reinforcement Learning for Inverted Pendulum Swing-up Control Surriani, Atikah; Maghfiroh, Hari; Wahyunggoro, Oyas; Cahyadi, Adha Imam; Fajrin, Hanifah Rahmi
Buletin Ilmiah Sarjana Teknik Elektro Vol. 7 No. 1 (2025): March
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/biste.v7i1.10268

Abstract

This study explores the application of deep reinforcement learning (DRL) to solve the control problem of a single swing-up inverted pendulum. The primary focus is on investigating the impact of discount factor parameterization within the DRL framework. Specifically, the Deep Deterministic Policy Gradient (DDPG) algorithm is employed due to its effectiveness in handling continuous action spaces. A range of discount factor values is tested to evaluate their influence on training performance and stability. The results indicate that a discount factor of 0.99 yields the best overall performance, enabling the DDPG agent to successfully learn a stable swing-up strategy and maximize cumulative rewards. These findings highlight the critical role of the discount factor in DRL-based control systems and offer insights for optimizing learning performance in similar nonlinear control problems.
Current Sensorless Microcontroller-Based Battery Management System with SOC and Active Cell Balancing Muhammad Fikri Ardiansyah; Adha Imam Cahyadi; Oyas Wahyunggoro
International Journal of Quantitative Research and Modeling Vol. 2 No. 1 (2021): International Journal of Quantitative Research and Modeling
Publisher : Research Collaboration Community (RCC)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46336/ijqrm.v2i1.125

Abstract

Battery management system (BMS) has become an important research topic following the trend and development of the electric vehicle. Although research on Active Cell Balancing, SOC, and current estimation has been carried out, the previous work mostly focused on comparing and developing methods. In this research, we demonstrate the process of designing BMS hardware using a low-cost microcontroller and without using a current sensor. The SOC simulation results produce an RMSE of 0.0832% for the 100% -10% SOC-OCV curve, and the current estimation simulation produces an RMSE of 0.2576 A, while for testing using a 6-ohm pulse load, the RMSE error value is 0.3960 A. The Active Cell Balancing method was successfully performed in simulation with Simulink. Furthermore, our simulation and test results suggest that complex battery models and multiple SOC-OCV curves can be used for better current and OCV estimation results. Our experimental results are also useful to develop a guideline to design a microcontroller-based BMS.
Cascaded Vector Control with Field-Oriented Control for Ac Induction Motor Position Servo Bayu Adji Nur Sudarisman; Adha Imam Cahyadi; Oyas Wahyunggoro
Jurnal Ilmiah Multidisiplin Indonesia (JIM-ID) Vol. 5 No. 03 (2026): Jurnal Ilmiah Multidisplin Indonesia (JIM-ID), March 2026
Publisher : Sean Institute

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

Abstract

Precise position control of AC induction motors is essential in various industrial applications, including robotics, machine tools, and automated manufacturing systems. The main challenges arise from the nonlinear dynamics of induction motors and the lack of inherent position feedback. This study proposes a three-tier cascaded control architecture integrating a PD position controller, a PI speed controller, and a Field-Oriented Control (FOC) current loop, with a 1:10:100 bandwidth hierarchy among the loops. This design ensures effective dynamic decoupling and global asymptotic stability, verified through Lyapunov-based analysis, including robustness against rotor parameter uncertainties up to ±20%. Numerical simulations on a 1.5 kW induction motor demonstrate a rise time of 0.157 s, settling time of 0.267 s, overshoot of 9.8%, steady-state position error of 0.0008 rad, and disturbance rejection of a 2 N·m load in 95 ms. FOC implementation maintains rotor flux within ±0.1% and peak efficiency of 91% at rated torque. These results confirm that the proposed cascaded three-tier FOC architecture achieves fast, accurate, and stable position control suitable for industrial servo applications and can be extended to other AC motor types with parameter adjustment and flux control strategies.
Low Pass Filter as Energy Management for Hybrid Energy Storage of Electric Vehicle: A Survey Hari Maghfiroh; Oyas Wahyunggoro; Adha Imam Cahyadi
Automotive Experiences Vol. 6 No. 3 (2023)
Publisher : Universitas Muhammadiyah Magelang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31603/ae.9398

Abstract

The transportation sector contributes up to 35% of carbon dioxide pollution. Electric Vehicles (EVs) offer a pollution-free alternative but face a crucial challenge in their battery-based Energy Storage System (ESS). The solution to the battery issues is combining it with other ESS with high power density called a Hybrid Energy Storage System (HESS). Energy Management Strategy (EMS) is used to distribute the power demand in the HESS. Low Pass Filters (LPFs) are one type of EMS that can be used to ensure the smooth flow of power between different energy storage elements. This article focuses on the pivotal role of Low Pass Filters (LPFs) within HESS for EVs, facilitating seamless power flow. The novelty lies in the comprehensive review of LPFs in this context, shedding light on their impact on energy management. Four LPF architecture classes are discussed: fixed cut-off, optimal cut-off, adaptive cut-off, and combination, referencing prior research. Additionally, a critical examination of challenges and limitations is provided, offering insights for researchers and practitioners.
CASCADED VECTOR CONTROL WITH FIELD-ORIENTED CONTROL FOR AC INDUCTION MOTOR POSITION SERVO Bayu Adji Nur Sudarisman; Adha Imam Cahyadi; Oyas Wahyunggoro
Jurnal Media Elektro Vol 15 No 1 (2026): April 2026
Publisher : Universitas Nusa Cendana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35508/jme.v0i0.27363

Abstract

Precise position control of AC induction motors is essential in various industrial applications, including robotics, machine tools, and automated manufacturing systems. The main challenges arise from the nonlinear dynamics of induction motors and the lack of inherent position feedback. This study proposes a three-tier cascaded control architecture integrating a PD position controller, a PI speed controller, and a Field-Oriented Control (FOC) current loop, with a 1:10:100 bandwidth hierarchy among the loops. This design ensures effective dynamic decoupling and global asymptotic stability, verified through Lyapunov-based analysis, including robustness against rotor parameter uncertainties up to ±20%. Numerical simulations on a 1.5 kW induction motor demonstrate a rise time of 0.157 s, settling time of 0.267 s, overshoot of 9.8%, steady-state position error of 0.0008 rad, and disturbance rejection of a 2 N·m load in 95 ms. FOC implementation maintains rotor flux within ±0.1% and peak efficiency of 91% at rated torque. These results confirm that the proposed cascaded three-tier FOC architecture achieves fast, accurate, and stable position control suitable for industrial servo applications and can be extended to other AC motor types with parameter adjustment and flux control strategies.