Now showing 1 - 6 of 6
  • Some of the metrics are blocked by your 
    Item type:Publication,
    DETECTION OF DRIVER DROWSINESS FROM EEG SIGNALS USING WEARABLE BRAIN SENSING HEADBAND
    (2021-05-31)
    Chan, Khune Satt Nyein
    ;
    Srisurangkul, C.
    ;
    ;
    Pangkreung, S.
    Driver drowsiness detection plays an important role in the field of road safety and advanced driver assistance system. Electroencephalogram (EEG) signals are one of the most accurate and reliable indicators of fatigue and drowsiness but in the case of detecting drowsiness, its medical graded measuring system can be intrusive to the driver. The purpose of this research is to test the feasibility and usability of the consumer graded EEG sensor to use in a driver drowsiness detection system. The experiment was carried out by using MUSE S brain sensing headband. Fast Fourier Transform (FFT) method was used to extract features from EEG signals. The extracted feature data are then used to build two classification model, the Support Vector Machine (SVM) and Artificial Neural Network (ANN). The detection of drowsiness is the binary classification task which is to classify between drowsy epochs and alert epochs. In the case of detecting only drowsy epochs, the SVM model detected 82.7% of the drowsy epochs which was better than the ANN model which can only detect 81.25% of the drowsy epochs. But in the detection of both drowsy and alert epochs, the ANN model performed better than that of SVM. The SVM model was tested with different kernel function and Fine Gaussian SVM model showed the highest accuracy of 87.8%. The ANN model performed slightly higher than the SVM model with an accuracy of 87.9%. The ability of consumer graded EEG sensor to use in drowsiness detection system was validated in this research.
  • Some of the metrics are blocked by your 
    Item type:Publication,
    IMPROVEMENT OF ESTIMATION METHOD FOR BATTERY CELL HEAT GENERATION
    (2021-05-31)
    Kulranut, J.
    ;
    ;
    Yenwichai, T.
    ;
    Intano, W.
    ;
    Masomtob, M.
    This work represents a new experimental method to precisely estimate the heat generation of the battery cell by reducing heat losses to the ambient. The temperature ambient in the chamber is controlled to be close to the battery cell temperature as much as possible in order to reduce the heat loss from the battery to the ambient. The battery is covered by an insulator, and the heat loss due to the heat conduction at the electric connectors is also considered. Therefore, the heat generation term is absorbed by the heat capacity term; in other words, the heat generation of the battery cell can be calculated via the rising temperature of the heat capacity term and the heat loss of the connectors. Consequently, this new method can obtain the precision of the estimated heat generation that can be used to design an appropriate battery thermal management system for the battery pack.
  • Some of the metrics are blocked by your 
    Item type:Publication,
    The force tracking control of electro-hydraulic system based on particle swarm optimization
    (2016-01-01)
    Moonumca, Pisan
    ;
    This paper presents the optimal gains of backstepping controller by using the particle swam optimization technique. The mathematical model is developed by Newton’s second law, compressible fluid flow and flow rates of valve. The control law is formulated by employing a Control Lyapunov Function. The core feature of this paper is the com­bination of the backstepping and particle swam optimization for optimal performance of controller. The controller gains are determined in automatic selection gains by minimiz­ing the integral of time multiplied by absolute error function on step input. The fitness value can be guaranteed to the convergence of controller gains. The implementations are separated into two cases which are the real and estimated state feedbacks. The experiment has illustrated to find optimal controller gains. The results are also compared with the tracking response of real and estimated state measures in step and square signal. The re­sults show a better tracking performance by using the strong particle swarm optimization (PSO) algorithm.
  • Some of the metrics are blocked by your 
    Item type:Publication,
    A Directional Control Auxiliary Thrust System to Increase the Forward Speed of a Quadcopter UAV
    (2024-01-01)
    Srijun, Chanapan
    ;
    This research introduces a method to increase the horizontal speed of a quadcopter UAV using an auxiliary thrust system that can be adjusted in direction. The researcher used thrust vectoring control to align the thrust direction with the unmanned aircraft's longitudinal axis. A method for controlling a device mechanism using a proportional-integral-derivative (PID) control system. Based on the test results, it has been concluded that the Ziegler–Nichols Method in P controller, the Ziegler–Nichols Method in PD controller, and the Trial-and-Error method in PID controller are the most effective methods for maintaining system stability and achieving the setpoint. It took 0.693, 1.441, and 0.563 seconds respectively to reach the desired value. The researcher used computational fluid dynamics and equations of motion to simulate a UAV's speed. The simulation results of using 25% additional thrust while moving at a 2-degree angle showed that the unmanned aerial vehicle's speed increased by 35.3% compared to the unmanned aerial vehicle without the auxiliary thrust system. When the pitch angle was increased to 5 degrees, the speed of the UAV increased by 15.9%. At higher pitch angles of 10 degrees, the UAV's speed increased by 6.86%. Finally, at pitch angles of 15 degrees, the speed of the UAV increased by 4.97%.
  • Some of the metrics are blocked by your 
    Item type:Publication,
    Experimental investigation of the influence of ethanol and biodiesel on common rail direct injection diesel Engine's combustion and emission characteristics
    (2022-11-01)
    Wai, Phyo
    ;
    Kanokkhanarat, Phobkrit
    ;
    Oh, Ban Seok
    ;
    Wongpattharaworakul, Veerayut
    ;
    This study aims to characterize the effect of oxygenated biofuels in diesel engine combustion, thermal efficiency, and emission by blending different percentages of ethanol and biodiesel with fossil fuel derived diesel. In this research, 5% and 10% by weight of bioethanol were added to commercial B10 (10% biodiesel and 90% diesel), B20 (20% biodiesel and 80% diesel) and B100 (100% biodiesel) and experimented on using a 3 L four-cylinder common rail diesel engine. The experiment was performed under three engine speeds of 1000 rpm, 1500 rpm, and 2000 rpm with three constant engine torques of 56 Nm, 84 Nm, and 140 Nm. The results show that ethanol-biodiesel-diesel ternary blended fuels are higher in premixed combustion pressure and net heat release rate (NHRR) peaks. The cumulative heat release of ethanol blended fuels is also higher for ethanol blended fuels. The fuel consumption increased with the ethanol and biodiesel percentage in the blended fuels due to the lower heating value while the brake thermal efficiency did not decrease. It was clearly observed that the particle emission could be reduced by more than 50% when ethanol and biodiesel percentage increased.
  • Some of the metrics are blocked by your 
    Item type:Publication,
    Flow stress determination of steel tube for hydroformability evaluation
    (2013-08-01)
    Boonpuek, P.
    ;
    Jirathearanat, S.
    ;
    This study aims to determine flow stress of a steel tube by using hydraulic bulge test. A new proposed analytical model for analyzing bulge shapes of hydroformed tubes is postulated. Bulge test apparatus designed using FEA simulation of hydroforming and STKM 11A steel tubes are used in the hydraulic bulge test. Bulge heights and internal pressures are measured during bulge testing. Tube thicknesses at vertex of a bulge shape are measured by a dial caliper gauge. Bulge curvatures and contact points are measured by taking digital photos of bulge shapes combined with measurement methods in CAD software. Effective stress-strain relationships are obtained from the newly developed analytical model using those measured values. Flow stress curves obtained from the effective stress-strain relationships are compared with those by other researchers and tensile test. Finite element analysis methods are used to conduct simulation of tube hydroforming using the flow stress curves. Predicted internal pressures versus bulge heights and tube thicknesses are compared with experimental results. Verification of the developed analytical model is presented. The flow stress at neck point of the formed tube is determined. © 2013 American Scientific Publishers All rights reserved.