KMITL

Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/123456789/1

Browse

Search Results

Now showing 1 - 8 of 8

Some of the metrics are blocked by your
consent settings
Novel Adaptive Intelligent Control System Design
(2025-08-01)
Duanyai, Worrawat
;
Song, Weon Keun
;
Ka, Min Ho
;
Lee, Dong Wook
;
Dissanayaka, Supun
A novel adaptive intelligent control system (AICS) with learning-while-controlling capability is developed for a highly nonlinear single-input single-output plant by redesigning the conventional model reference adaptive control (MRAC) framework, originally based on first-order Lyapunov stability, and employing customized neural networks. The AICS is designed with a simple structure, consisting of two main subsystems: a meta-learning-triggered mechanism-based physics-informed neural network (MLTM-PINN) for plant identification and a self-tuning neural network controller (STNNC). This structure, featuring the triggered mechanism, facilitates a balance between high controllability and control efficiency. The MLTM-PINN incorporates the following: (I) a single self-supervised physics-informed neural network (PINN) without the need for labelled data, enabling online learning in control; (II) a meta-learning-triggered mechanism to ensure consistent control performance; (III) transfer learning combined with meta-learning for finely tailored initialization and quick adaptation to input changes. To resolve the conflict between streamlining the AICS’s structure and enhancing its controllability, the STNNC functionally integrates the nonlinear controller and adaptation laws from the MRAC system. Three STNNC design scenarios are tested with transfer learning and/or hyperparameter optimization (HPO) using a Gaussian process tailored for Bayesian optimization (GP-BO): (scenario 1) applying transfer learning in the absence of the HPO; (scenario 2) optimizing a learning rate in combination with transfer learning; and (scenario 3) optimizing both a learning rate and the number of neurons in hidden layers without applying transfer learning. Unlike scenario 1, no quick adaptation effect in the MLTM-PINN is observed in the other scenarios, as these struggle with the issue of dynamic input evolution due to the HPO-based STNNC design. Scenario 2 demonstrates the best synergy in controllability (best control response) and efficiency (minimal activation frequency of meta-learning and fewer trials for the HPO) in control.
Some of the metrics are blocked by your
consent settings
Meta-Learning-Based Physics-Informed Neural Network: Numerical Simulations of Initial Value Problems of Nonlinear Dynamical Systems without Labeled Data and Correlation Analyses
(2024-06-01)
Duanyai, Worrawat
;
Song, Weon Keun
;
Chitthamlerd, Thanadol
;
Kumar, Girish
There are several main challenges in solving nonlinear differential equations with artificial neural networks (ANNs), such as a nonlinear system’s sensitivity to its initial values, discretization, and strategies for incorporating physics-based information into ANNs. As for the first issue, this paper addresses the initial value problems of nonlinear dynamical systems (a Duffing oscillator and a Burger’s equation), which cause large global truncation errors in sub-domains with a significant reduction in the influence of initial constraints, using meta-learning-based physics-informed neural networks (MPINNs). The MPINNs with dual learners outperform physics-informed neural networks with a single learner (no fine reinitialization capability). As a result, the former approach improves solution convergence by 98.83% in the sub-time domain (III) of a Duffing oscillator, and by 85.89% at t = 45 in a Burger’s equation problem, compared to the latter one. Model accuracy is highly dependent on the adaptability of the initial parameters in the first hidden layers of the meta-models. From correlation analyses, it is obvious that the parameters become less (the Duffing oscillator) or more (the Burger’s equation) correlated during fine reinitialization, as the update manner differs or is similar to the one used in pre-initialization. In the first example, the MPINN achieves both the mitigation of model sensitivity to its output and the improvement of model accuracy. Conversely, the second example shows that the proposed approach is not enough to solve both issues simultaneously, as increased model sensitivity to its output leads to higher model accuracy. The application of transfer learning reduces the number of iterative pre-meta-trainings.
Some of the metrics are blocked by your
consent settings
Event-triggered model reference adaptive control system design for SISO plants using meta-learning-based physics-informed neural networks without labeled data and transfer learning
(2024-04-01)
Duanyai, Worrawat
;
Song, Weon Keun
;
Konghuayrob, Poom
;
Parnichkun, Manukid
This paper examines the controllability of a novel Lyapunov-based model reference adaptive control (MRAC) system designed with a meta-learning-based physics-informed neural network (MLPINN) for linear and nonlinear single-input and single-output (SISO) plants without labeled data (MLPINN-MRAC system). It is devised with the benefits of several techniques: the integration of the identification process in a training mode into an online control mode (straightforward design); no labeled data generation for online identification by a physics-informed neural network; the prevention of degradation in tracking performance by meta-learning, as the system triggers a meta-learning process only when an error threshold detects the deterioration (high efficiency and the reduction of computation cost); quick adaptation to new inputs and an updated control input for each sub-time span by transfer learning. It is worth noting that the frequency of the meta-learning event detection significantly affects the step response stability of the nonlinear plant. To achieve a better quality of the stabilization, more frequent event detection is necessary for both beginning and end intervals in control. Sixteen triggering events are enough to shape the acceptable step response of the nonlinear plant, and 44 triggering events achieve the plant's desired step response with its minor modeling error. While, as for the linear plant, a single triggering event is sufficient to attain its tolerable step response and modeling error, implying that intensive event detection is not critical in the identification. It is obvious that the MLPINN-MRAC system functions well and is more beneficial and efficient for the nonlinear plant.
Some of the metrics are blocked by your
consent settings
Investigation and analysis of implementation challenges for autonomous vehicles in developing countries using hybrid structural modeling
(2022-12-01)
Kumar, Girish
;
James, Ajith Tom
;
Choudhary, Krishna
;
Sahai, Rishi
;
Song, Weon Keun
The advent of autonomous vehicles (AV) heralds yet another turning point in the evolution of the urban landscape, our daily lives, and the advancement of human civilization as a whole. A very disruptive technology, whose implementation will have ramifications for road safety, air pollution, travel behavior, parking issues, commute time, and other aspects of daily life. The introduction of autonomous vehicles for regular transportation in developed countries is expected to take place over the next decade. Its implementation would be impossible for developing countries for another five decades, at the very least. However, there is potential for its use in selected applications soon. This paper investigates and analyzes the challenges that will be faced in the widespread adoption AV in developing countries. The literature is used to identify a variety of challenges which are then modeled using a hybrid approach that incorporates both ISM (Interpretive Structural Modeling) and MICMAC (Matrice d'impacts croisés multiplication appliquée á un classment) techniques. The results of this analysis would help policy makers and AV manufacturers to understand the level of significance of each challenge and its interrelations. This would help them to focus on critical challenges and initiate remedial actions.
Some of the metrics are blocked by your
consent settings
Obstacle avoidance for a swarm of unmanned aerial vehicles operating on particle swarm optimization: a swarm intelligence approach for search and rescue missions
(2022-02-01)
Kumar, Girish
;
Anwar, Arham
;
Dikshit, Abhinav
;
Poddar, Abhirup
;
Soni, Umang
An approach, based on a multi-plane system, is conceptualized in this work to solve the problem of collision avoidance for a swarm of unmanned aerial vehicles, being used for search and rescue to minimize affecting the searching algorithm. Relevant chronological advancements in the last two decades of the parent algorithm, particle swarm optimization, are summarized. As each optimization algorithm for search and rescue has its own niche area of application, various well-established algorithms such as particle swarm optimization and novel algorithms like layered search and rescue, spiral search and fish-inspired task allocation are compared with each other qualitatively. Simulations with 100 different cases were used to compare the original particle swarm optimization with the additional novel collision avoidance algorithm. The statistical z test was run based on which it was found that the proposed algorithm significantly reduces the number of collisions and does not put a toll on the iterations to convergence. Standardized residuals of all cases indicate minimal error difference in the optimum average fitness value calculated by the particle swarm optimization, with and without the conceptualized anti-collision algorithm.
Some of the metrics are blocked by your
consent settings
Human and bird detection and classification based on Doppler radar spectrograms and vision images using convolutional neural networks
(2021-01-01)
Gokaraju, Jnana Sai Abhishek Varma
;
Song, Weon Keun
;
Ka, Min Ho
;
Kaitwanidvilai, Somyot
The study investigated object detection and classification based on both Doppler radar spectrograms and vision images using two deep convolutional neural networks. The kinematic models for a walking human and a bird flapping its wings were incorporated into MATLAB simulations to create data sets. The dynamic simulator identified the final position of each ellipsoidal body segment taking its rotational motion into consideration in addition to its bulk motion at each sampling point to describe its specific motion naturally. The total motion induced a micro-Doppler effect and created a micro-Doppler signature that varied in response to changes in the input parameters, such as varying body segment size, velocity, and radar location. Micro-Doppler signature identification of the radar signals returned from the target objects that were animated by the simulator required kinematic modeling based on a short-time Fourier transform analysis of the signals. Both You Only Look Once V3 and Inception V3 were used for the detection and classification of the objects with different red, green, blue colors on black or white backgrounds. The results suggested that clear micro-Doppler signature image-based object recognition could be achieved in low-visibility conditions. This feasibility study demonstrated the application possibility of Doppler radar to autonomous vehicle driving as a backup sensor for cameras in darkness. In this study, the first successful attempt of animated kinematic models and their synchronized radar spectrograms to object recognition was made.
Some of the metrics are blocked by your
consent settings
Experiment and analysis of a space tether with pendulum-type elastic metamaterials
(2020-07-01)
Yoon, Joo Young
;
Song, Weon Keun
;
Park, No Cheol
In this paper, a space tether with pendulum-type elastic metamaterials is constructed as a scaled model considering initial tension of a tether cable. A similarity analysis is used to design the scaled model to ensure that it has similar dynamic characteristics as that of a real tether cable. The pendulum-type elastic metamaterials are used to produce a bandgap in the measurable frequency range. To investigate the bandgap of the metamaterials, a ground experiment that can excite the scaled model of the tether cable is proposed. The experiment results of the harmonic responses for the scaled model for external shocks indicate that the bandgap is attributed to beam resonance. The correlation between the natural frequency of the beam and the bandgap is provided, and the deformation shapes of the metamaterial in the bandgap are measured.
Some of the metrics are blocked by your
consent settings
Pendulum-type elastic metamaterial for reducing the vibration of a space tether
(2019-09-01)
Yoon, Joo Young
;
Song, Weon Keun
;
Park, No Cheol
In this paper, we present a pendulum-type elastic metamaterial that can be used to absorb the shock of a tether system. A tether system comprises a long and thin cable, so the resonant part of the elastic metamaterial should be attached to outside the cable. The unit cell of the elastic metamaterial consists of three strings and one ring, and strings are attached to the tether cable and reduces the shock transmitted to the satellite. We used modal analysis to find mode shapes of the unit cell of the elastic metamaterial that do not deform when in contact with the tether cable. A harmonic analysis on the properties of the strings confirmed the presence of bandgaps for the pendulum-type metamaterial because of the lateral resonance of the strings. The effect of the unit cell design parameters on the bandgaps were also investigated.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results