• Transactions of Materials Processing
• /
• v.4 no.3
• /
• pp.214-221
• /
• 1995

In the paper, we have proposed a new method to determine the initial billet for the forged products using a function approximation in the neural network. The architecture of neural network is a three-layer neural network and the back propagation algorithm is employed to train the network. By utilizing the ability of function approximation of a neural network, an optimal billet is determined by applying the nonlinear mathematical relationship between the aspect ratios in the initial billet and the final products. The amount of incomplete filling in the die is measured by the rigid-plastic finite element method. The neural network is trained with the initial billet aspect ratios and those of the unfilled volumes. After learning, the system is able to predict the filling regions which are exactly the same or slightly different to the results of finite element simulation. This new method is applied to find the optimal billet size for the plane strain rib-web product in cold forging. This would reduce the number of finite element simulation for determining the optimal billet size of forging product, further it is usefully adapted to physical modeling for the forging design.

• Journal of National Security and Military Science
• /
• s.1
• /
• pp.345-360
• /
• 2003

To build an information oriented armed forces, the Korean military telecommunication networks adopt TCP/IP standard communication infrastructures based on ATM packet switched networks. Utilizing this network infrastructure, the Korean armed forces also applies to the areas of battleship management for efficient operation command controls and resource management for efficient resource allocations. In this military communication networks, it is essential to determine the least cost network topology under equal performance and reliability constraints. Basically, this type of communication network design problem is known in the literature as an NP Hard problem. As the number of network node increases, it is very hard to obtain an optimal solution in polynomial time. Therefore, it is reasonable to use a heuristic algorithm which provides a good solution with minimal computational efforts. In this study, we developed a simulated annealing based heuristic algorithm which can be utilized for the design of military communication networks. The developed algorithm provides a good packet switched network topology which satisfies a given set of performance and reliability constraints with reasonable computation times.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.587-591
• /
• 2003

This study develops a neural network for solving optimization problems. Hopfield network has been used for such problems, but it frequently gives abnormal solutions or non-optimal solutions. Moreover, it takes much time for solving a solution. To overcome such disadvantages, this study adopts a neural network whose output nodes change with a small value at every evolution, and the proposed neural network is applied to solve ALB (Assembly Line Balancing) problems . Given a precedence diagram and a required number of workstations, an ALB problem is solved while achieving even distribution of workload among workstations. Here, the workload variance is used as the index of workload deviation, and is reflected to an energy function. The simulation results show that the proposed neural network yields good results for solving ALB problems with high success rate and fast execution time.

• Journal of the Korean Society for Precision Engineering
• /
• v.20 no.2
• /
• pp.85-93
• /
• 2003

Generally, it is very difficult to get a modeling equation because multi-variable system has coupling relations between its inputs and outputs. To design an optimal controller without the modeling equation, this paper proposes a neural-network (NN) controller being learned by Jacobian matrix. Another major characteristic is that the controller consists of two separated NN controllers, namely, proportional control part and derivative control part. Simulation results for a catamaran system show that the proposed NN controller is superior to LQR in the regulation and tracking problems.

• IE interfaces
• /
• v.10 no.3
• /
• pp.179-187
• /
• 1997

The efficiency of material flow systems in terms of optimal network flow and minimum cost flow has always been an important design and operational goal in material handling and distribution system. In this research, an attempt was made to develop a new algorithm and the model to solve a stochastic material flow network with bidirectional and uncertain flows. A stochastic material flow network with bidirectional flows can be considered from a finite set with unknown demand probabilities of each node. This problem can be formulated as a special case of a two-stage linear programming problem which can be converted into an equivalent linear program. To find the optimal solution of proposed stochastic material flow network, some terminologies and algorithms together with theories are developed based on the partitioning and subgradient techniques. A computer program applying the proposed method was developed and was applied to various problems.

• Journal of the Korea Society for Simulation
• /
• v.14 no.3
• /
• pp.67-77
• /
• 2005

Logistics network of the enterprise is defined to determine the optimal node and link considering the production, inventory and transportation based on the demand forecasting. This study consider the optimal logistics network of A painter company which maintain the existing transportation network and plan to relocate its plants and build new distribution centers. For this, we design possible alternative scenarios and install the simulation models for analysis of each scenario. The result of simulation will help the proper logistic network and determining the size of distribution center further.

• 제어로봇시스템학회:학술대회논문집
• /
• 1986.10a
• /
• pp.613-618
• /
• 1986

In this study a s/w system(HENSPIN) for the automatic synthesis of HEN(heat exchanger network) was developed based on Pinch Design Method. The synthesized HEN by HENSPIN are satisfying performance targets such as minimum utility usage with as few as possible capital items. The invented network is near optimal in capital and operating cost. It will be used as initial structure for evolution to the structure which has optimal operability.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.10 no.6
• /
• pp.1207-1213
• /
• 2009

A design method of network Topology for Integrated Management of various Networks is prposed and an example is shown. The TMN-DCN devices are assigned for each of the various networks. These devices have functions of network management. Also we propose the simple design methods of the network topology with survivability as one of the network management elements. The design methods are very simple but very useful. Because there is no general design algorithm for optimal topology with network survivability.

• Proceedings of the KIEE Conference
• /
• 2005.07d
• /
• pp.2891-2893
• /
• 2005

In this paper, we introduce a new category of Self-Organizing Fuzzy Polynomial Neural Networks (SOFPNN) that is based on a genetically optimized multi-layer perceptron with fuzzy polynomial neurons (FPNs) and discuss its comprehensive design methodology involving mechanisms of genetic optimization. The conventional SOFPNN algorithm leads to a tendency to produce overly complex networks as well as a repetitive computation load by the trial and error method and/or the a repetitive parameter adjustment by designer. In order to generate a structurally and parametrically optimized network, such parameters need to be optimal. In this study, in solving the problems with the conventional SOFPNN, we introduce a new design approach of evolutionary optimized SOFPNN. Optimal parameters design available within FPN (viz. the no. of input variables, the order of the polynomial, input variables, and the no. of membership function) lead to structurally and parametrically optimized network which is more flexible as well as simpler architecture than the conventional SOFPNN. In addition, we determine the initial apexes of membership functions by genetic algorithm.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.5
• /
• pp.2081-2101
• /
• 2016

Successive interference cancellation (SIC) is considered to be a promising technique to mitigate multi-user interference and achieve concurrent uplink transmissions, but the optimal power allocation (PA) issue for SIC users is not well addressed. In this article, we focus on the optimization of the PA ratio of users on an SIC channel and analytically obtain the optimal PA ratio with regard to the signal-to-interference-plus-noise ratio (SINR) threshold for successful demodulation and the sustainable demodulation error rate. Then, we design an efficient resource allocation (RA) scheme using the obtained optimal PA ratio. Finally, we compare the proposal with the near-optimum RA obtained by a simulated annealing search and the RA scheme with random PA. Simulation results show that our proposal achieves a performance close to the near-optimum and much higher performance than the random scheme in terms of total utility and Jain's fairness index. To demonstrate the applicability of our proposal, we also simulate the proposal in various network paradigms, including wireless local area network, body area network, and vehicular ad hoc network.