Claim Missing Document
Check
Articles

Found 2 Documents
Search

Estimasi Deviasi Parameter pada Motor DC Menggunakan Sliding-Mode Observer dan Algoritme Least-Square Dzuhri Radityo Utomo; Muhammad Faris
Jurnal Nasional Teknik Elektro dan Teknologi Informasi Vol 11 No 4: November 2022
Publisher : Departemen Teknik Elektro dan Teknologi Informasi, Fakultas Teknik, Universitas Gadjah Mada

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/jnteti.v11i4.5036

Abstract

Performing system/plant maintenance is very important as an attempt to avoid any failure during system/plant operation. One of the methods that can be adopted to detect any potential failure inside a plant is by estimating the value of the plant’s parameters. When the plant’s parameters deviate too far from their nominal values, the plant will be more likely to fail. In this paper, an estimation method for estimating the deviation in the parameters of a linear system/plant is proposed as an improvement of the previously proposed method. The main component of this parameter deviation estimator system was an observer block which adopted the sliding-mode observer in combination with an adaptive filter block. The adaptive filter block used in this system adopted the least-square algorithm instead of adopting the gradient-descent algorithm as in the previously proposed method. This method was simulated to estimate the deviation in the parameters of DC motor to verify the effectiveness of the proposed metho. The simulation results showed that this method could successfully estimate the deviation of DC motor parameters with a maximum estimation error of less than 4 %. This method could estimate the deviation in DC motor parameters for both constant deviation value and slowly-changing deviation value as time goes by. In addition, estimating the parameter deviation using this method could produce a good level of accuracy even when using a fairly low-frequency input signal. This method is suitable to be adopted in parameter monitoring process of a linear system so that any fault occurring in the system can be detected and isolated before the plant is fatally damaged.
Kendali Inverted Pendulum: Studi Perbandingan dari Kendali Konvensional ke Reinforcement Learning Ahmad Ataka; Andreas Sandiwan; Hilton Tnunay; Dzuhri Radityo Utomo; Adha Imam Cahyadi
Jurnal Nasional Teknik Elektro dan Teknologi Informasi Vol 12 No 3: Agustus 2023
Publisher : Departemen Teknik Elektro dan Teknologi Informasi, Fakultas Teknik, Universitas Gadjah Mada

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/jnteti.v12i3.7065

Abstract

The rise of deep reinforcement learning in recent years has led to its usage in solving various challenging problems, such as chess and Go games. However, despite its recent success in solving highly complex problems, a question arises on whether this class of method is best employed to solve control problems in general, such as driverless cars, mobile robot control, or industrial manipulator control. This paper presents a comparative study between various classes of control algorithms and reinforcement learning in controlling an inverted pendulum system to evaluate the performance of reinforcement learning in a control problem. A test was performed to test the performance of root locus-based control, state compensator control, proportional-derivative (PD) control, and a reinforcement learning method, namely the proximal policy optimization (PPO), to control an inverted pendulum on a cart. The performances of the transient responses (such as overshoot, peak time, and settling time) and the steady-state responses (namely steady-state error and the total energy) were compared. It is found that when given a sufficient amount of training, the reinforcement learning algorithm was able to produce a comparable solution to its control algorithm counterparts despite not knowing anything about the system’s properties. Therefore, it is best used to control plants with little to no information regarding the model where testing a particular policy is easy and safe. It is also recommended for a system with a clear objective function.