Garuda - Garba Rujukan Digital

Machine learning modeling of power delivery networks with varying decoupling capacitors Yeong Kang Liew; Nur Syazreen Ahmad; Azniza Abd Aziz; Patrick Goh
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 11, No 3: September 2022
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijai.v11.i3.pp1049-1056

This paper presents modeling of power delivery network (PDN) impedance with varying decoupling capacitor placements using machine learning techniques. The use of multilayer perceptron artificial neural networks (ANN) and gaussian process regression (GPR) techniques are explored, and the effects of the hyperparameters such as the number of hidden neurons in the ANN, and the choice of kernel functions in the GPR are investigated. The best performing networks in each case are selected and compared in terms of accuracy using test data consisting of PDN impedance responses that were never encountered during training. Results show that the GPR models were significantly more accurate than the ANN models, with an average mean absolute error of 5.23 mΩ compared to 11.33 mΩ for the ANN.

Progress in neural network based techniques for signal integrity analysis–a survey Chan Hong Goay; Azniza Abd Aziz; Nur Syazreen Ahmad; Patrick Goh
Bulletin of Electrical Engineering and Informatics Vol 8, No 1: March 2019
Publisher : Institute of Advanced Engineering and Science

With the increase in data rates, signal integrity analysis has become more time and memory intensive. Simulation tools such as 3D electromagnetic field solvers can be accurate but slow, whereas faster models such as design equations and equivalent circuit models lack accuracy. Artificial neural networks (ANNs) have recently gained popularity in the RF and microwave circuit modeling community as a new modeling tool. This has in turn spurred progress towards applications of neural networks in signal integrity. A neural network can learn from a set of data generated during the design process. It can then be used as a fast and accurate modeling tool to replace conventional approaches. This paper reviews the recent advancement of neural networks in the area of signal integrity modeling. Key advancements are considered, particularly those that assist the ability of the neural network to cope with an increasing number of inputs and handle large amounts of data.

Progress in neural network based techniques for signal integrity analysis–a survey Chan Hong Goay; Azniza Abd Aziz; Nur Syazreen Ahmad; Patrick Goh
Bulletin of Electrical Engineering and Informatics Vol 8, No 1: March 2019
Publisher : Institute of Advanced Engineering and Science

With the increase in data rates, signal integrity analysis has become more time and memory intensive. Simulation tools such as 3D electromagnetic field solvers can be accurate but slow, whereas faster models such as design equations and equivalent circuit models lack accuracy. Artificial neural networks (ANNs) have recently gained popularity in the RF and microwave circuit modeling community as a new modeling tool. This has in turn spurred progress towards applications of neural networks in signal integrity. A neural network can learn from a set of data generated during the design process. It can then be used as a fast and accurate modeling tool to replace conventional approaches. This paper reviews the recent advancement of neural networks in the area of signal integrity modeling. Key advancements are considered, particularly those that assist the ability of the neural network to cope with an increasing number of inputs and handle large amounts of data.

Progress in neural network based techniques for signal integrity analysis–a survey Chan Hong Goay; Azniza Abd Aziz; Nur Syazreen Ahmad; Patrick Goh
Bulletin of Electrical Engineering and Informatics Vol 8, No 1: March 2019
Publisher : Institute of Advanced Engineering and Science

With the increase in data rates, signal integrity analysis has become more time and memory intensive. Simulation tools such as 3D electromagnetic field solvers can be accurate but slow, whereas faster models such as design equations and equivalent circuit models lack accuracy. Artificial neural networks (ANNs) have recently gained popularity in the RF and microwave circuit modeling community as a new modeling tool. This has in turn spurred progress towards applications of neural networks in signal integrity. A neural network can learn from a set of data generated during the design process. It can then be used as a fast and accurate modeling tool to replace conventional approaches. This paper reviews the recent advancement of neural networks in the area of signal integrity modeling. Key advancements are considered, particularly those that assist the ability of the neural network to cope with an increasing number of inputs and handle large amounts of data.

Development of magnetic levitation system with position and orientation control Siti Juliana Abu Bakar; Koay J-Shenn; Patrick Goh; Nur Syazreen Ahmad
International Journal of Reconfigurable and Embedded Systems (IJRES) Vol 12, No 2: July 2023
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijres.v12.i2.pp287-296

This work demonstrates the design and development of a magnetic levitation (MagLev) system that is able to control both the position and orientation of the levitated object. For the position control, a pole placement method was exploited to estimate parameters of the proportional integral derivative (PID) controller. In addition, the MagLev was constructed using a pair of electromagnets, two infrared (IR) receiver-emitter pairs and a servo motor to allow the orientation of the object to be controlled. The proposed controller was programmed in a LabVIEW environment, which was then compiled and deployed into an embedded NI myRIO board. Experimental results demonstrated that the proposed method was able to achieve a zero steady-state orientation error when the object was rotated from 0 ◦ to ±90◦ , a steady-state position error of 0.3 cm without rotation, and steady-state position errors of no greater than 1.2 cm with rotation.

Transmission line impulse response modelling using machine learning techniques Wei Min Lim; Khin Leong How; Chan Hong Goay; Nur Syazreen Ahmad; Patrick Goh
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 12, No 4: December 2023
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijai.v12.i4.pp1577-1584

Conventional methods of circuit simulation such as full-wave electromagnetic ï¬eldsolvers can be very slow. Machine learning is an emerging technology in modelling, simulation, optimization, and design that present attractive alternatives to the conventional methodologies because they can be trained with a small amount of data, and then used to perform fast circuit predictions within the same design space. In this paper, we present applications of machine learning techniques for the modelling of transmission lines from their impulse reponses. The standard multilayer perceptron (MLP) neural network and the gaussian process (GP) regression techniques are demonstrated, andboth models are successfully implemented to model the impulse responses of transmission lines with great accuracies. We show that the GP outperforms the MLP in terms of prediction accuracies and that the GP is more data efï¬cient than the MLP. This is beneï¬cial considering that each training sample is expensive, making the GP a good candidate for the task, compared to the more popular MLP.

Self-balancing robot: modeling and comparative analysis between PID and linear quadratic regulator Lu Bin Lau; Nur Syazreen Ahmad; Patrick Goh
International Journal of Reconfigurable and Embedded Systems (IJRES) Vol 12, No 3: November 2023
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijres.v12.i3.pp351-359

A two-wheeled self-balancing robot (TWSBR) is an underactuated system that is inherently nonlinear and unstable. While many control methods have been introduced to enhance the performance, there is no unique solution when it comes to hardware implementation as the robotâ€™s stability is highly dependent on accuracy of sensors and robustness of the electronic control systems. In this study, a TWSBR that is controlled by an embedded NI myRIO-1900 board with LabVIEW-based control scheme is developed. We compare the performance between proportional-integral-derivative (PID) and linear quadratic regulator (LQR) schemes which are designed based on the TWSBRâ€™s model that is constructed from Newtonian principles. A hybrid PID-LQR scheme is then proposed to compensate for the individual componentsâ€™ limitations. Experimental results demonstrate the PID is more effective at regulating the tilt angle of the robot in the presence of external disturbances, but it necessitates a higher velocity to sustain its equilibrium. The LQR on the other hand outperforms PID in terms of maximum initial tilt angle. By combining both schemes, significant improvements can be observed, such as an increase in maximum initial tilt angle and a reduction in settling time.

Title

Found 7 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 7 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 7 Documents
Search