Yooyen, Soemsak
Loading...
Preferred name
Yooyen, Soemsak
Alternative Name
Yooyen, S.
Main Affiliation
Email
soemsak.yo@kmitl.ac.th
20 results
Now showing 1 - 10 of 20
- Some of the metrics are blocked by yourconsent settings
Item type:Publication, Structural Equation Modeling for Airspace Optimization: The Analysis of Causal Factors Influencing Aviation Safety(2026-05-01); ; - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Vision-based attitude estimation for spacecraft docking operation through deep learning algorithm(2020-02-01); - Some of the metrics are blocked by yourconsent settings
Item type:Publication, A Stress Tensor-based Failure Criterion for Ordinary State-based Peridynamic Models(2022-01-01); ; ; Shojaei, ArmanPeridynamics is a recent nonlocal theory of continuum mechanics that is suitable to describe fracture problems in solid mechanics. In this paper, a new failure criterion based on the stress field is developed by adopting the damage correspondence model in the ordinary state-based peridynamic theory. The proposed stress tensor-based failure criterion is capable of predicting more accurately crack propagation in the mixed mode I-II fracture problems different from other failure criteria in peridynamics. The effectiveness of the proposed model is demonstrated by performing several examples of mixed-mode dynamic fracture in brittle materials. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, An enhanced learning algorithm with a particle filter-based gradient descent optimizer method(2020-08-01); ; This experiment integrates a particle filter concept with a gradient descent optimizer to reduce loss during iteration and obtains a particle filter-based gradient descent (PF-GD) optimizer that can determine the global minimum with excellent performance. Four functions are applied to test optimizer deployment to verify the PF-GD method. Additionally, the Modified National Institute of Standards and Technology (MNIST) database is used to test the PF-GD method by implementing a logistic regression learning algorithm. The experimental results obtained with the four functions illustrate that the PF-GD method performs much better than the conventional gradient descent optimizer, although it has some parameters that must be set before modeling. The results of implementing the MNIST dataset demonstrate that the cross-entropy of the PF-GD method exhibits a smaller decrease than that of the conventional gradient descent optimizer, resulting in higher accuracy of the PF-GD method. The PF-GD method provides the best accuracy for the training model, 97.00%, and the accuracy of evaluating the model with the test dataset is 90.37%, which is higher than the accuracy of 90.08% obtained with the conventional gradient descent optimizer. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Reliability-based Design Optimization of Classical Wing Aeroelasticity(2020-07-27); ; Bureerat, S.Flutter speed of aircraft is very important and needs to be firstly specified before a certification applied for a new aircraft by airworthiness regulator to make sure that the aircraft is free from flutter in its flight envelope. By assuming geometrical and physical parameters known, the speed is usually estimated from deterministic analyses in a design stage. In practice, some parameters are finitely measured by observing, especially for the geometrical parameters, material properties and so on due to the random in nature, which causes uncertainty of information often called uncertainties. The purpose of this paper is to combine reliability analysis and optimum design of aeroelastic aircraft wing. The classical two-dimensional wing with a typical airfoil section is used as an example in this study. To quantify uncertainty in the design of flutter speed, the discrete-time aero-elastic model and worst-case scenario are applied. Furthermore, the comparison between optimum design with/without reliability is provided in this study. The results show the proposed technique leads to the flutter speed being more conservative and realizable compared with the traditional technique. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Deep Convolutional Neural Networks for plane identification on Satellite imagery by exploiting transfer learning with a different optimizer(2019-07-01); ; Object identification is on an available problem. Automating plane identification on Satellite imagery can be applied for activity and traffic patterns to monitoring airports, and including defense intelligence issues. This paper implements Deep Convolutional Neural Networks(CNN) to classify a plane in the planesnet dataset. Pre-trained model and transfer learning are deployed to overcome a limitation of computation resources by adding new top layer consists of a fully-connected layer and softmax layer to identify the new classes and re-train it. Besides, the experimental designs for testing an implementation of a pretrained model with some kinds of the optimizer to comparing a result. There are four types of optimizer. The first two are well-known optimizer namely Stochastic Gradient Descent optimizer and Adam Optimizer, while others are PowerSign and AddSign optimizer. PowerSign and AddSign optimizer are methods to minimize cost, which discover by using Recurrent neural network(RNN) and Reinforcement Learning. A result demonstrates that a plane identification on Satellite imagery can be achieved by implementing the pre-trained model and obtains an exceptional result with Adam optimizer. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Influence of the Trailing Edge Shape on the Aerodynamic Characteristics of an Airfoil at Low Re Number Using RANS(2020-07-27) - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Vision-based spacecraft pose estimation via a deep convolutional neural network for noncooperative docking operations(2020-09-01); ; 3 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Ozonation effectiveness on the mitigation of airborne microorganisms and particulate matter for enhanced indoor air quality(2026-01-01); 1 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Investigation of cooling performances of a non-film-cooled turbine vane coated with a thermal barrier coating using conjugate heat transfer(2018-04-01); ; ; Xu, HuazhaoThe aim of this paper is to numerically investigate cooling performances of a non-film-cooled turbine vane coated with a thermal barrier coating (TBC) at two turbulence intensities (Tu = 8.3% and 16.6%). Computational fluid dynamics (CFD) with conjugate heat transfer (CHT) analysis is used to predict the surface heat transfer coefficient, overall and TBC effectiveness, as well as internal and average temperatures under a condition of a NASA report provided by Hylton et al. [NASA CR-168015]. The following interesting phenomena are observed: (1) At each Tu, the TBC slightly dampens the heat transfer coefficient in general, and results in the quantitative increment of overall cooling effectiveness about 16-20%, but about 8% at the trailing edge (TE). (2) The protective ability of the TBC increases with Tu in many regions, that is, the leading edge (LE) and its neighborhoods on the suction side (SS), as well as the region from the LE to the front of the TE on the pressure side (PS), because the TBC causes the lower enhancement of the heat transfer coefficient in general at the higher Tu. (3) Considering the internal and average temperatures of the vane coated with two different TBCs, although the vane with the lower thermal conductivity protects more effectively, its role in the TE region reduces more significantly. (4) For both TBCs, the increment of Tu has a relatively small effect on the reduction of the average temperature of the vane.1