• Journal of the Korea Institute of Military Science and Technology
• /
• v.22 no.2
• /
• pp.278-286
• /
• 2019

Conventional methods for selecting jamming techniques in electronic warfare are based on libraries in which a list of jamming techniques for radar signals is recorded. However, the choice of jamming techniques by the library is limited when modified signals are received. In this paper, we propose a method to predict the jamming technique for radar signals by using deep learning methods. Long short-term memory(LSTM) is a deep running method which is effective for learning the time dependent relationship in sequential data. In order to determine the optimal LSTM model structure for jamming technique prediction, we test the learning parameter values that should be selected, such as the number of LSTM layers, the number of fully-connected layers, optimization methods, the size of the mini batch, and dropout ratio. Experimental results demonstrate the competent performance of the LSTM model in predicting the jamming technique for radar signals.

• Computers and Concrete
• /
• v.27 no.5
• /
• pp.489-512
• /
• 2021

In this study, two powerful techniques, namely particle swarm optimization (PSO) and imperialist competitive algorithm (ICA) were selected and combined with a pre-developed ANN model aiming at improving its performance prediction of the compressive strength of concrete modified with fly ash. To achieve this study's aims, a comprehensive database with 379 data samples was collected from the available literature. The output of the database is the compressive strength (CS) of concrete samples, which are influenced by 9 parameters as model inputs, namely those related to mix composition. The modeling steps related to ICA-ANN (or neuro-imperialism) and PSO-ANN (or neuro-swarm) were conducted through the use of several parametric studies to design the most influential parameters on these hybrid models. A comparison of the CS values predicted by hybrid intelligence techniques with the experimental CS values confirmed that the neuro-swarm model could provide a higher degree of accuracy than another proposed hybrid model (i.e., neuro-imperialism). The train and test correlation coefficient values of (0.9042 and 0.9137) and (0.8383 and 0.8777) for neuro-swarm and neuro-imperialism models, respectively revealed that although both techniques are capable enough in prediction tasks, the developed neuro-swarm model can be considered as a better alternative technique in mapping the concrete strength behavior.

• Proceedings of the KSME Conference
• /
• 2001.06c
• /
• pp.327-332
• /
• 2001

An experimental design technique is developed for estimating the moments of system response functions. It is easy to implement and provides accurate results compared with other traditional methods. It is based on the work of Taguchi, later improved by D'Errico and Zaino. The existing experimental techniques, however, is applicable only for normally distributed cases. In this article the three-level Taguchi method is extended to obtain optimum choice for levels and weights to handle nonnormal distributions. A systematic procedure for reliability analysis is then proposed by using the Pearson system and the narrow system reliability bounds. Illustrative examples including a tolerance optimization problem are shown very accurate comparing with those by Monte-Carlo simulations and the first-order reliability method.

• Journal of the Korean Society for Precision Engineering
• /
• v.31 no.4
• /
• pp.319-326
• /
• 2014

Accurate estimation of the robot's position has an important role in autonomous navigation. Odometry is one of the most widely used techniques for mobile robot positioning. However, odometry has a well-known drawback that the position errors are accumulated when the travel distance increases. The UMBmark method is the conventional odometry calibration scheme for two wheel differential mobile robots. In the UMBmark method, the approximations for small angles are used in order to simplify the calculations. In this paper, we propose the new calibration scheme by using experimental orientation errors. Kinematic parameters can be calculated accurately without approximations by using experimental orientation errors. The numerical simulation and experimental results show that the odometry accuracy can be improved by the proposed method.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2002.11b
• /
• pp.68-73
• /
• 2002

It is necessary first to understand dynamic characteristics of bus full BIW assembly for fatigue endurance analysis. FE model has been used usually for analyzing the dynamic behavior of structures. A lot of experience and effort, however, is necessary to make the credible FE model. Experimental modal analysis of structures has been performed to verify the credibility of initial FE model and to update the model. In this work, experimental modal analysis was performed to understand dynamic characteristics of bus full BIW assembly in free-free boundary condition and the result was used to verify the initial FE model. In addition, some practical techniques, which were used in this experiment, were mentioned.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.12 no.3
• /
• pp.426-439
• /
• 1988

Dynamic properties such as stiffness and damping of mechanical joints are essential for the accurate prediction of the dynamic behaviors of the system and subsequent improvement of the design. So far several techniques, analytical, experimental, or both have been developed. A technique using condensed F.E.M. model and Experimental Modal Analysis is presented to identify the joint structural parameters. First, modal parameters of structure are measured by certain complex frequency obtained from experiment to match with the order of the Experimental Modal Analysis model. Finally by equating the modal parameters obtained from experiment with those of the condensed system, the unknown joint structural parameters can be identified. A simulation study is conducted to investigate the accuracy of technique. The experiments are performed with ball bearings in a rotor bearing system.

• Structural Engineering and Mechanics
• /
• v.50 no.2
• /
• pp.231-240
• /
• 2014

In the present research, fatigue behavior of chopped strand mat/epoxy composites has been studied with two different techniques. First, the normalized stiffness degradation approach as a well-known model for unidirectional and laminated composites was utilized to predict the fatigue behavior of chopped strand mat/epoxy composites. Then, the capability of the fatigue damage accumulation model for chopped strand mat/epoxy composites was investigated. A series of tests has been performed at different stress levels to evaluate both models with the obtained results. The results of evaluation indicate a better correlation of the normalized stiffness degradation technique with experimental results in comparison with the fatigue damage accumulation model.

• Journal of Korean Society for Quality Management
• /
• v.32 no.1
• /
• pp.113-129
• /
• 2004

The reliability of the product can be improved by making the product less sensitive to noises. Especially, it Is important to make products robust against various noise factors encountered in production and field environments. In this paper, the phenomenon of degradation assumes a simple random coefficient degradation model to present analysis procedures of degradation data for robust experimental design. To alleviate weak points of previous studies, such as Taguchi's, Wasserman's, and pseudo failure time methods, novel techniques for analysis of degradation data using the cross array that regards amount of degradation as a dynamic characteristic for time are proposed. Analysis approach for degradation data using robust experimental design are classified by assumptions on parametric or nonparametric degradation rate(or slope). Also, a simulation study demonstrates the superiority of proposed methods over some previous works.

• International Journal of Control, Automation, and Systems
• /
• v.2 no.4
• /
• pp.494-500
• /
• 2004

The wing rock phenomenon is a high angle of attack aerodynamic motion manifested by limit cycle roll oscillations. Experimental studies reveal that direct control and manipulation of leading edge vortices, through the use of 'blowing' techniques is effective in the suppression of wing rock. This paper presents the design of a robust controller for the experimental implementation of one such 'blowing' technique - recessed angle spanwise blowing (RASB), to achieve wing rock suppression over a range of operating conditions. The robust controller employs Takagi - Sugeno fuzzy system, which is fine-tuned by experimental simulations. Performance of the controller is assessed by real-time wind tunnel experiments with an 80 degree swept back delta wing. Robustness is demonstrated by the suppression of wing rock at a range of angles of attack and free stream velocities. Numerical simulation results are used to further substantiate the experimental findings.

• Proceedings of the KSME Conference
• /
• 2004.04a
• /
• pp.1458-1463
• /
• 2004

By using unique experimental techniques and careful construction of the experimental apparatus, the characteristics of the local heat transfer were investigated using the condensing R134a two-phase flow, in horizontal single mini-channels. The circular channels ($D_h=0.493$, 0.691, and 1.067 mm) and rectangular channels ($D_h=0.494$, 0.658, and 0.972 mm) were tested and compared. Tests were performed for a mass flux of 100, 200, 400, and 600 $kg/m^2s$, a heat flux of 5 to 20 $kW/m^2$, and a saturation temperature of $40^{\circ}C$. In this study, effect of heat flux, mass flux, vapor qualities, hydraulic diameter, and channel geometry on flow condensation were investigated and the experimental local condensation heat transfer coefficients are shown. The experimental data of condensation Nusselt number are compared with existing correlations.