• Journal of the Korean Society of Propulsion Engineers
• /
• v.11 no.3
• /
• pp.29-34
• /
• 2007

In this study a model-based diagnostic method using the Neural Network was proposed for PW206C turbo shaft engine and performance model was developed by SIMULINK. Fault and test database to build the NN was obtained at various off-design operating range such as flight altitude, flight Mach number and gas generator rotational speed variation. According to the fault detection analysis results, it was confirmed that the proposed fault detection method could find well the fault of compressor, compressor turbine and power turbine at on-design point as well as off-design point conditions.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09b
• /
• pp.95-98
• /
• 2003

In this paper, an adaptive fuzzy neural control of unknown nonlinear systems based on the rapid learning algorithm is proposed for optimal parameterization. We combine the advantages of fuzzy control and neural network techniques to develop an adaptive fuzzy control system for updating nonlinear parameters of controller. The Fuzzy Neural Network(FNN), which is constructed by an equivalent four-layer connectionist network, is able to learn to control a process by updating the membership functions. The free parameters of the AFN controller are adjusted on-line according to the control law and adaptive law for the purpose of controlling the plant track a given trajectory and it's initial values are off-line preprocessing, In order to improve the convergence of the learning process, we propose a rapid learning algorithm which combines the error back-propagation algorithm with Aitken's $\delta$$\^$2/ algorithm. The heart of this approach ls to reduce the computational burden during the FNN learning process and to improve convergence speed. The simulation results for nonlinear plant demonstrate the control effectiveness of the proposed system for optimal parameterization.

• Journal of Power Electronics
• /
• v.13 no.5
• /
• pp.877-883
• /
• 2013

This paper discussed a transformer-less shunt static synchronous compensator (STATCOM) with consideration of the following aspects: fast compensation of the reactive power, harmonic cancelation and reducing the unbalancing of the 3-phase source side currents. The STATCOM control algorithm is based on the theory of instantaneous reactive power (P-Q theory). A self charging technique is proposed to regulate the dc capacitor voltage at a desired level with the use of a PI controller. In order to regulate the DC link voltage, an off-line Genetic Algorithm (GA) is used to tune the coefficients of the PI controller. This algorithm arranged these coefficients while considering the importance of three factors in the DC link voltage response: overshoot, settling time and rising time. For this investigation, the entire system including the STATCOM, network, harmonics and unbalancing load are simulated in MATLAB/SIMULINK. After that, a 35KVA STATCOM laboratory setup test including two parallel converter modules is designed and the control algorithm is executed on a TMS320F2812 controller platform.

• Journal of Biosystems Engineering
• /
• v.22 no.1
• /
• pp.30-40
• /
• 1997

A computer vision system was built to automatically grade the leaf tobacco. A color image processing algorithm was developed to extract shape, color and texture features. An improved back propagation algorithm in an artificial neural network was applied to grade the Burley type dried leaf tobacco. The success rate of grading in three-grade classification(1, 3, 5) was higher than the rate of grading in six-grade classification(1, 2, 3, 4, 5, off), on the average success rate of both the twenty-five local pixel-set and the sixteen local pixel-set. And, the average grading success rate using both shape and color features was higher than the rate using shape, color and texture features. Thus, the texture feature obtained by the spatial gray level dependence method was found not to be important in grading leaf tobacco. Grading according to the shape, color and texture features obtained by machine vision system seemed to be inadequate for replacing manual grading of Burely type dried leaf tobacco.

• Proceedings of the KIPE Conference
• /
• 2014.07a
• /
• pp.215-216
• /
• 2014

This paper proposes a control algorithm for permanent magnet synchronous generator with a back-to-back three-level neutral-point clamped voltage source converter in a medium-voltage offshore wind power system under unbalanced grid conditions. The proposed control algorithm particularly compensates for the unbalanced grid voltage at the point of common coupling in a collector bus of offshore wind power system. This control algorithm has been formulated based on the symmetrical components in positive and negative rotating synchronous reference frames under generalized unbalanced operating conditions. Instantaneous active and reactive power are described in terms of symmetrical components of measured grid input voltages and currents. Negative sequential component of ac input current is injected to the point of common coupling in the proposed control strategy. The amplitude of negative sequential component is calculated to minimize the negative sequential component of grid voltage under the limitation of current capability in a voltage source converter. The proposed control algorithm makes it possible to provide a balanced voltage at the point of common coupling resulting in the generated power of high quality from offshore wind power system under unbalanced network conditions.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.12 no.2
• /
• pp.360-368
• /
• 2008

In this paper, in order that the various QoS(Qualify of Service)s that are required by different traffic class are guaranteed in the random access channels in multi-service multi-user OFDMA systems, the backoff-based random access algorithm is proposed and corresponding performance is analyzed in terms of the access success probability, the throughput, the average delay and the blocking probability. Through the numerical analysis, it is shown that the proposed backoff-based random access algorithm can provide the differentiated QoSs to random access attempts according to their service class.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.22 no.4
• /
• pp.453-461
• /
• 2011

In order to use more efficiently limited frequency resources at the broadcasting band and to eliminate blanket area of the terrestrial broadcasting and to improve broadcasting quality. The importance of repeaters has increasing continuously. However, in case of T-DMB digital on channel repeater in OFDM systems, some of the signal radiated feedback again at the receiver antenna. So it generates feedback signal interference in repeater system. Also phase noise increases ICI(Inter Carrier Interference). It affects seriously the frequency domain equalizer. In this paper, we remove the feedback signal interference by LMS with correlation. Also we propose an effective equalizer algorithm that can remove ICI caused by phase noise and the power amplifier's back-off. In this simulation results, this system is satisfied the performance of BER=$10^{-4}$ at less than SNR=14 dB after compensation of phase noise.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.8 no.6
• /
• pp.1135-1141
• /
• 2004

In this study, this system makes use of the analog infrared rays sensor and converts the feature of fish outline when sensor is operating with CPU(80C196KC). Then, after signal processing, this feature is classified a special feature and a outline of fish by using the neural network, one of the artificial intelligence scheme. This neural network classifies fish pattern of very simple and short calculation. This has linear activation function and the error back propagation is used as a teaming algorithm. And the neural network is learned in off-line process. Because an adaptation period of neural network is too long when random initial weights are used, off-line teaming is induced to decrease the progress time.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.16 no.4 s.95
• /
• pp.389-396
• /
• 2005

In this paper, we propose a pre-distortion method using the NLMS(Normalized Least Mean Square) algorithm to cope with hish PAPR(Peak to Average Power Ratio) problem in OFDM communication system. This proposed scheme estimates the distortion characteristics of HPA, and changes the characteristic against the distortion. Therefore, it can be shown that the adaptive characteristic of the NLMS pre-distorter is good to track the various nonlinear characteristic of HPA, even though HPA characteristic is changed by temperature variation or aging. From the performance analysis, SNR efficiency of NLMS pre-distorter is about $0.5\;\cal{dB}$ less than that of common numerical non-adaptive pre-distorter, when IBO(Input Back Off) is $0\;\cal{dB}$. However, the NLMS pre-distorter is better than the common numerical pre-distorter, because these two pre-distorters have similar performance in higher than $3\;\cal{dB}$ IBO, and the NLMS pre-distorter maintains the constant performance even though characteristic of HPA is changed.

• 한국HCI학회:학술대회논문집
• /
• 2007.02c
• /
• pp.306-317
• /
• 2007

We present an interactive and accurate collision detection algorithm for deformable, polygonal objects based on the streaming computational model. Our algorithm can detect all possible pairwise primitive-level intersections between two severely deforming models at highly interactive rates. In our streaming computational model, we consider a set of axis aligned bounding boxes (AABBs) that bound each of the given deformable objects as an input stream and perform massively-parallel pairwise, overlapping tests onto the incoming streams. As a result, we are able to prevent performance stalls in the streaming pipeline that can be caused by expensive indexing mechanism required by bounding volume hierarchy-based streaming algorithms. At run-time, as the underlying models deform over time, we employ a novel, streaming algorithm to update the geometric changes in the AABB streams. Moreover, in order to get only the computed result (i.e., collision results between AABBs) without reading back the entire output streams, we propose a streaming en/decoding strategy that can be performed in a hierarchical fashion. After determining overlapped AABBs, we perform a primitive-level (e.g., triangle) intersection checking on a serial computational model such as CPUs. We implemented the entire pipeline of our algorithm using off-the-shelf graphics processors (GPUs), such as nVIDIA GeForce 7800 GTX, for streaming computations, and Intel Dual Core 3.4G processors for serial computations. We benchmarked our algorithm with different models of varying complexities, ranging from 15K up to 50K triangles, under various deformation motions, and the timings were obtained as 30~100 FPS depending on the complexity of models and their relative configurations. Finally, we made comparisons with a well-known GPU-based collision detection algorithm, CULLIDE [4] and observed about three times performance improvement over the earlier approach. We also made comparisons with a SW-based AABB culling algorithm [2] and observed about two times improvement.