• Journal of the Korean Institute of Intelligent Systems
• /
• v.7 no.3
• /
• pp.43-54
• /
• 1997

Knowledge acquisition is one of the most difficult problems in designing fuzzy systems. As application domains of fuzzy systems become larger and more complex, it is more difficult to find the relations among the system's input- outpiit variables. Moreover, it takes a lot of efforts to formulate expert's knowledge about complex systems' control actions by linguistic variables. Another difficulty is to define and adjust membership functions properly. Soin conventional fuzzy systems, the membership functions should be adjusted to improve the system performance. This is time-consuming process. In this paper, we suggest a new approach to design a fuzzy system. We design a fuzzy system using two neural networks, Kohonen neural network and backpropagation neural network, which generate fuzzy rules automatically and construct inference network. Since fuzzy inference is performed based on fuzzy relation in this approach, we don't need the membership functions of each variable. Therefore it is unnecessary to define and adjust membership functions and we can get fuzzy rules automatically. The design process of fuzzy system becomes simple. The proposed approach is applied to a simulated automatic car speed control system. We can be sure that this approach not only makes the design process of fuzzy systems simple but also produces appropriate inference results.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1993.06a
• /
• pp.1382-1385
• /
• 1993

In order to improve productivity, an intelligent control system is presented in the pater. In this intelligent control system, a feedforward neural network and a fuzzy feedback mechanism are adopted to achieve a constant milling force with an adjustable feedrate under a variety of cutting conditions in milling operations.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.34C no.8
• /
• pp.88-100
• /
• 1997

This paper proposes a new concept for an optimal traffic signal cycle method which will reduce the average vehicle waiting time and improve average vehicle speed. Electro sensitive traffic system can extend the traffic cycle when there ar emany vehicles in the road or it can reduce the traffic consider vehicle length, so it can cause oveflow and reduce average vechicel waiting time at the intersection, we propose on optimal traffic cycle with fuzzy ruels and neural network. Computer simulation results prove that reducing the average vehicle waiting time which proposed considering passing vehicle's length for the optimal traffic cycle better than fixe dsignal method dosen't consider vehicle length.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1997.10a
• /
• pp.259-262
• /
• 1997

In this paper, a fuzzy model based on the polynomial Neural Network(PNN) structure is proposed to estimate the emission pattern for air pollutant in power plants. The new algorithm uses PNN algorithm based on Group Method of Data Handling (GMDH) algorithm and fuzzy reasoning in order to identify the premise structure and parameter of fuzzy implications rules, and the least square method in order to identify the optimal consequence parameters. Both time series data for the gas furnace and data for the NOx emission process of gas turbine power plants are used for the purpose of evaluating the performance of the fuzzy model. The simulation results show that the proposed technique can produce the optimal fuzzy model with higher accuracy anhd feasibility than other works achieved previously.

• Journal of the Semiconductor & Display Technology
• /
• v.2 no.1
• /
• pp.7-9
• /
• 2003

In order to predict the moldability of an injection molded part, a simulation of filling is needed. Short shot is one of the most frequent troubles encountered during injection molding process. The adjustment of process conditions is the most economic way to troubleshoot the problematic short shot in cost and time since the mold doesn't need to be modified at all. But it is difficult to adjust the process conditions appropriately in no times since it requires an empirical knowledge of injection molding. In this paper, the intelligent CAE system synergistically combines fuzzy-neural network(FNN) for heuristic knowledge with CAE programs for analytical knowledge. To evaluate the intelligent algorithms, a cellular phone flip has been chosen as a finite element model and filling analyses have been performed with a commercial CAE software. As the results, the intelligent CAE system drastically reduces the troubleshooting time of short shot in comparison with the expert's conventional way which is similar to the golden section search algorithm.

• Proceedings of the Korean Society Of Semiconductor Equipment Technology
• /
• 2002.11a
• /
• pp.127-129
• /
• 2002

In order to predict the moldability of an injection molded part, a simulation of filling is needed. Short shot is one of the most frequent troubles encountered during injection molding process. The adjustment of process conditions is the most economic way to troubleshoot the problematic short shot in cost and time since the mold doesn't need to be modified at all. But it is difficult to adjust the process conditions appropriately in no times since it requires an empirical knowledge of injection molding. In this paper, the intelligent CAE system synergistically combines fuzzy-neural network(FNN) for heuristic knowledge with CAE programs for analytical knowledge. To evaluate the intelligent algorithms, a cellular phone flip has been chosen as a finite element model and filling analyses have been performed with a commercial CAE software. As the results, the intelligent CAE system drastically reduces the troubleshooting time of short shot in comparison with the expert's conventional way which is similar to the golden section search algorithm.

• Journal of Korea Water Resources Association
• /
• v.41 no.3
• /
• pp.341-351
• /
• 2008

Since the damage from the torrential rain increases recently due to climate change and global warming, the significance of flood forecasting and warning becomes important in medium and small streams as well as large river. Through the preprocess and main processes for estimating runoff, diverse errors occur and are accumulated, so that the outcome contains the errors in the existing flood forecasting and warning method. And estimating the parameters needed for runoff models requires a lot of data and the processes contain various uncertainty. In order to overcome the difficulties of the existing flood forecasting and warning system and the uncertainty problem, ANFIS(Adaptive Neuro-Fuzzy Inference System) technique has been presented in this study. ANFIS, a data driven model using the fuzzy inference theory with neural network, can forecast stream level only by using the precipitation and stream level data in catchment without using a lot of physical data that are necessary in existing physical model. Time series data for precipitation and stream level are used as input, and stream levels for t+1, t+2, and t+3 are forecasted with this model. The applicability and the appropriateness of the model is examined by actual rainfall and stream level data from 2003 to 2005 in the Tancheon catchment area. The results of applying ANFIS to the Tancheon catchment area for the actual data show that the stream level can be simulated without large error.

• Structural Engineering and Mechanics
• /
• v.30 no.6
• /
• pp.679-698
• /
• 2008

On marine vessels, delicate instruments such as navigation radars are normally mounted on ship masts. However the vibrations at the top of mast where the radar is mounted often cause serious deterioration in radar-tracking resolution. The most serious problem is caused by the rotational vibrations at the top of mast that may be due to wind loading, inertial loading from ship rolling and base excitations induced by the running propeller. This paper presents a method of semi-active vibration control using magneto-rheological (MR) dampers to reduce the rotational vibration of the mast. In the study, the classical optimal control algorithm, the independent modal space control algorithm and the double input - single output fuzzy control algorithm are employed for the vibration control. As the phenomenological model of an MR damper is highly nonlinear, which is difficult to analyse, a back- propagation neural network is trained to emulate the inverse dynamic characteristics of the MR damper in the analysis. The trained neural network gives the required voltage for each MR damper based on the displacement, velocity and control force of the MR damper quickly. Numerical simulations show that the proposed control methods can effectively suppress the rotational vibrations at the top of mast.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.7
• /
• pp.920-926
• /
• 2004

The human being receives a new information from outside and the information shows gradual oblivion with time. But the information remains in memory and isn't forgotten for a long time if the information is read several times over. For example, we assume that we memorize a telephone number when we listen and never remind we may forget it soon, but we commit to memory long time by repeating. If the human being received new information with strong stimulus, it could remain in memory without recalling repeatedly. The moments of almost losing one's life in an accident or getting a stroke of luck are rarely forgiven. The human being can keep memory for a long time in spite of the limit of memory for the mechanism mentioned above. In this paper, we propose a model to explain the mechanism mentioned above using a neural network and fuzzy.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.449-449
• /
• 2000

Many researchers have studied architectures for non-Neumann's computers because of escaping its bottleneck. To avoid the bottleneck, a neuron-based computer has been developed. The computer has only neurons and their connections, which are constructed of the learning. But still it has information processing facilities, and at the same time, it is like as a simplified brain to make inference; it is called "neuron-computer". No instructions are considered in any neural network usually; however, to complete complex processing on restricted computing resources, the processing must be reduced to primitive actions. Therefore, we introduce the instructions to the neuron-computer, in which the most important function is implications. There is an implication represented by binary-operators, but general implications for multi-value or fuzzy logics can't be done. Therefore, we need to use Lukasiewicz' operator at least. We investigated a neuron-computer having instructions for general implications. If we use the computer, the effective inferences base on multi-value logic is executed rapidly in a small logical unit.