• Journal of Power Electronics
• /
• v.17 no.6
• /
• pp.1587-1599
• /
• 2017

This paper proposes a real-time implementation of an optimal operation of a double stage grid connected wind power system incorporating an active power filter (APF). The system is used to supply the nonlinear loads with harmonics and reactive power compensation. On the generator side, a new adaptive neuro fuzzy inference system (ANFIS) based maximum power point tracking (MPPT) control is proposed to track the maximum wind power point regardless of wind speed fluctuations. Whereas on the grid side, a modified predictive current control (PCC) algorithm is used to control the APF, and allow to ensure both compensating harmonic currents and injecting the generated power into the grid. Also a type 2 fuzzy logic controller is used to control the DC-link capacitor in order to improve the dynamic response of the APF, and to ensure a well-smoothed DC-Link capacitor voltage. The gained benefits from these proposed control algorithms are the main contribution in this work. The proposed control scheme is implemented on a small-scale wind energy conversion system (WECS) controlled by a dSPACE 1104 card. Experimental results show that the proposed T2FLC maintains the DC-Link capacitor voltage within the limit for injecting the power into the grid. In addition, the PCC of the APF guarantees a flexible settlement of real power exchanges from the WECS to the grid with a high power factor operation.

• Proceedings of the KIEE Conference
• /
• 2008.04a
• /
• pp.219-220
• /
• 2008

The paper is proposed maximum torque control of SynRM drive using adaptive fuzzy neuro inference system(AFNIS) and artificial neural network(ANN). The control method is applicable over the entire speed range and considered the limits of the inverter's current and voltage rated value. For each control mode, a condition that determines the optimal d-axis current $i_d$ for maximum torque operation is derived. The proposed control algorithm is applied to SynRM drive system controlled AFNIS and ANN controller, the operating characteristics controlled by maximum torque control are examined in detail. Also, this paper is proposed the analysis results to verify the effectiveness of the AFNIS and ANN controller.

• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.40 no.8
• /
• pp.731-740
• /
• 1991

This paper presents a knowledge based system to solve reactive power/voltage control problem in a power system. The methods to reduce inference time are proposed in inferring the solution of problem in the knowledge base which consists of heuristic rules and inowledge of experts. A set of indices drawn from the heuristic knowledge on the power system is utilized to make up for the defect of existing knowledge based systems which determine both the location and the amount of reactive power compensation devices. The concept of set of indices developed in this paper makes it possible to infer the amount of reactive power source only since the bus order list representing priority for the location of reactive power compensator to be switched on can be determined in advance. From the fact that there exists a relationship between the system voltage pattern and the reactive power pattern in operation, the pattern recognition technique is introduced to reduce the inference time in solving the severe voltage problem. To demonstrate the usefulness of the proposed knowledge based system, the IEEE 30 bus system is chosen as a sample system. The results of case study are also presented.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.34C no.7
• /
• pp.38-50
• /
• 1997

This paper concerns a VHDL design and simulation of an accurate and cost-effective fuzzy logic controller (FLC). The accurcy of the proposed FLC is obtained by using the center of gravity (COG) defuzzifier that considers both membership values and spans of membership functions in calculating a crisp value. The cost-effectiveness of the proposed FLC is obtained by restructuring the conventional FLC in the following ways: Firstly, the MAX-MIN inference is inference is replaced by a read-modify-write operation that can be implemented economically in the structure of register files. Secondly, the division in the COG defuzzifier is avoided by finding the moment equilibrium point. The proposed COG defuzzifier has two disadvantages that it requires additional multipliers and it takes a lot of computation time to find the moment equilibrium point. The first disadvantage is overcome by replacing the mulitpliers with stochastic AND operations and the second disadvantage is alleviated by using a coarse-to-fine searching algorithm. The proposed FLC is described in VHDL structurally and behaviorally and whether it is working well or not is checked on SYNOPSYS VHDL simulator by using the truck backer-upper control problem.

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.55 no.6
• /
• pp.227-235
• /
• 2006

In this paper, autonomous separation methodology of faulted section based on network is proposed newly, which can minimize the outage effect as compared with the existing center-based faulted section separation method by determining and separating autonomously the faulted section by the free operation information exchange among IEDs on the feeder of distribution system. The all IEDs is designed in network in which client/server function is possible in order to separate autonomously the faulted section using PtP(Peer to Peer) communication. Also, Inference based solution of IED for the autonomous faulted section separation is designed by rules obtained from the analyzing results of distribution system topology. Here, the switch IEDs transmit on network the fault information utilizing on multi-casting communication method, at the fame time, determine selfly whether they operates or not by inferencing autonomously the faulted section using the inference-based solution after receiving the transmitted information. Finally, in order to verify the effectiveness and application possibility of the proposed methodology, the diversity fault cases are simulated for the typical distribution system.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2010.05a
• /
• pp.779-783
• /
• 2010

최근 들어 그 심각성을 더하고 있는 이상기후 현상으로 가용 수자원의 변동이 커지고 있으며, 이에 따라 수자원의 효율적인 운영이 요구되고 있다. 그러나 효율적인 운영을 위해서는 미래 유입량의 불확실성의 고려하고, 홍수 조절용량의 확보하면서도, 용수공급을 위한 저수량을 확보하고, 수력 발전을 해야 하는 복잡한 상황을 모두 고려하여야한다. 이러한 복잡한 시스템에서 하나의 최적화 기법으로는 모든 고려사항들을 만족시키는 최적해를 찾는 것은 사실상 불가능에 가깝다. 그러므로 저수지 운영의 최적화를 위한 연구에서 한 가지 이상의 기법을 조합하는 기법을 사용하게 되었다. 이러한 기법은 각 기법의 장점을 취하고 각각의 한계를 극복하기 위해 주로 사용되었다. 본 연구에서는 저수지 운영 최적화를 모의하기 위하여 대청댐에서의 저수위, 유입량, 용수이용량 등을 고려하여 방류량의 예측을 동적 계획법(Dynamic Programming Model)으로부터 동적 신경망(Dynamic Neural Network Model)과 적응 퍼지 제어기법(Adaptive Neuro-Fuzzy Inference System)을 개발하여 실제 방류량과 세 가지 최적화 방법에 의한 결과를 비교 검정하였다. 본 연구의 수행으로 인해 얻어진 결과를 요약하면 다음과 같다. 첫째, 동적 신경망과 적응 퍼지 제어기법에 의한 최적화 모의가 동적 계획법에 비해 시스템의 구축이 쉽고 유연하다. 둘째, 퍼지추론의 Membership 함수의 구축에 따라 단시간에 많은 양의 강우가 발생하는 국지성 강우에 대해서도 최적 방류량을 예측할 수 있다. 셋째, 저수지 운영 과거자료의 부족과 불확실성을 해결하면, 보다 용이하고 양호한 예측결과를 얻을 수 있을 것이다.

• Electronics and Telecommunications Trends
• /
• v.36 no.2
• /
• pp.32-42
• /
• 2021

The rapid growth of deep-learning applications has invoked the R&D of artificial intelligence (AI) processors. A dedicated software framework such as a compiler and runtime APIs is required to achieve maximum processor performance. There are various compilers and frameworks for AI training and inference. In this study, we present the features and characteristics of AI compilers, training frameworks, and inference engines. In addition, we focus on the internals of compiler frameworks, which are based on either basic linear algebra subprograms or intermediate representation. For an in-depth insight, we present the compiler infrastructure, internal components, and operation flow of ETRI's "AI-Ware." The software framework's significant role is evidenced from the optimized neural processing unit code produced by the compiler after various optimization passes, such as scheduling, architecture-considering optimization, schedule selection, and power optimization. We conclude the study with thoughts about the future of state-of-the-art AI compilers.

• Journal of Korean Society for Quality Management
• /
• v.18 no.2
• /
• pp.18-24
• /
• 1990

The location of inspection stations is a significant component of production systems. In this paper, a prototype expert system is designed for deciding the optimal location of inspection stations. The production system is defined as a single channel of n serial operation stations. The potential inspection station can be located after any of the operation stations. Nonconforming units are generated from a compound binomial distribution with known parameters at any given operation station. Traditionally Dynamic programming, Zero-one integer programming, or Non-linear programming techniques are used to solve this problem. However a problem with these techniques is that the computation time becomes prohibitively large when t be number of potential inspection stations are fifteen or more. An expert system has the potential to solve this problem using a rule-based system to determine the near optimal location of inspection stations. This prototype expert system is divided into a static database, a dynamic database and a knowledge base. Based on defined production systems, the sophisticated rules are generated by the simulator as a part of the knowledge base. A generate-and-test inference mechanism is utilized to search the solution space by applying appropriate symbolic and quantitative rules based on input data. The goal of the system is to determine the location of inspection stations while minimizing total cost.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.6
• /
• pp.367-374
• /
• 2022

The acceleration of neural networks has become an important topic in the field of computer vision. An accelerator is absolutely necessary for accelerating the lightweight model. Most accelerator-supported operators focused on direct convolution operations. If the accelerator does not provide GEMM operation, it is mostly replaced by CPU operation. In this paper, we proposed an optimization technique for 2-stage tiling-based GEMM routines on VTA. We improved performance of the matrix multiplication routine by maximizing the reusability of the input matrix and optimizing the operation pipelining. In addition, we applied the proposed technique to the DarkNet framework to check the performance improvement of the matrix multiplication routine. The proposed GEMM method showed a performance improvement of more than 2.4 times compared to the non-optimized GEMM method. The inference performance of our DarkNet framework has also improved by at least 2.3 times.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.1
• /
• pp.58-63
• /
• 2014

Most of light duty AGVs(AGCs) using tape of magnetic for the guide path have digital guidance magnetic sensor. Digital guidance magnetic sensor using magnet-tape is on/off type and has positioning error of magnet-tape as 10~50 mm. AGC using this sensor doesn't induce accurate position of magnet-line which is magnet-tape because of magnetic field which motor in AGC creates, outer magnetic field, earth's magnetic field, etc. AGC when driving wobbles due to this error and this error can cause path deviation. In this paper, we propose fuzzy inference system for improvement of bipolar analog magnetic guidance sensor performance. Fuzzy is suitable in term of fault tolerance, uncertainty tolerance, real-time operation, and Nonlinearity as compared with other algorithms. In previous research, we produced bipolar magnetic guidance sensor and we set the threshold in order to calculate digital values of magnet position. Fuzzy inference system is designed using outputs of Analog hall sensors. Magnet position calculated by digital method is improved by outputs of this system. In result, proposed method was verified by improving performance of magnetic guidance sensor.