• International Journal of Advanced Culture Technology
• /
• 제6권3호
• /
• pp.163-172
• /
• 2018

The power train of hydro-mechanical continuously variable transmission(HMCVT) for the middle class forklift makes use of an hydro-static unit, hydraulic multi-wet disc brake & clutches and complex helical & planetary gears. The complex helical & planetary gears are a very important part of the transmission because of strength problems. The helical & planetary gears belong to the very important part of the HMCVT's power train where strength problems are the main concerns including the gear bending stress, the gear compressive stress and scoring failures. The present study, calculates specifications of the complex helical & planetary gear train and analyzes the gear bending and compressive stresses of the gears. It is necessary to analyze gear bending and compressive stresses confidently for an optimal design of the complex helical & planetary gears in respect of cost and reliability. This paper not only analyzes actual gear bending and compressive stresses of complex helical & planetary gears using Lewes & Hertz equation, but also verifies the calculated specifications of the complex helical & planetary gears by evaluating the results with the data of allowable bending and compressive stress from the Stress - No. of cycles curves of gears. In addition, this paper explains actual gear scoring and evaluates the possibility of scoring failure of complex helical & planetary gear train of hydro-mechanical continuously variable transmission for the forklift.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제52권7호
• /
• pp.424-433
• /
• 2003

Evolutionary design related to the optimal design of Polynomial Neural Networks (PNNs) structure for model identification of complex and nonlinear system is studied in this paper. The PNN structure is consisted of layers and nodes like conventional neural networks but is not fixed and can be changable according to the system environments. three types of polynomials such as linear, quadratic, and modified quadratic is used in each node that is connected with various kinds of multi-variable inputs. Inputs and order of polynomials in each node are very important element for the performance of model. In most cases these factors are decided by the background information and trial and error of designer. For the high reliability and good performance of the PNN, the factors must be decided according to a logical and systematic way. In the paper evolutionary algorithm is applied to choose the optimal input variables and order. Evolutionary (genetic) algorithm is a random search optimization technique. The evolved PNN with optimally chosen input variables and order is not fixed in advance but becomes fully optimized automatically during the identification process. Gas furnace and pH neutralization processes are used in conventional PNN version are modeled. It shows that the designed PNN architecture with evolutionary structure optimization can produce the model with higher accuracy than previous PNN and other works.

• 대한전기학회논문지:전기물성ㆍ응용부문C
• /
• 제52권7호
• /
• pp.424-424
• /
• 2003

Evolutionary design related to the optimal design of Polynomial Neural Networks (PNNs) structure for model identification of complex and nonlinear system is studied in this paper. The PNN structure is consisted of layers and nodes like conventional neural networks but is not fixed and can be changable according to the system environments. three types of polynomials such as linear, quadratic, and modified quadratic is used in each node that is connected with various kinds of multi-variable inputs. Inputs and order of polynomials in each node are very important element for the performance of model. In most cases these factors are decided by the background information and trial and error of designer. For the high reliability and good performance of the PNN, the factors must be decided according to a logical and systematic way. In the paper evolutionary algorithm is applied to choose the optimal input variables and order. Evolutionary (genetic) algorithm is a random search optimization technique. The evolved PNN with optimally chosen input variables and order is not fixed in advance but becomes fully optimized automatically during the identification process. Gas furnace and pH neutralization processes are used in conventional PNN version are modeled. It shows that the designed PNN architecture with evolutionary structure optimization can produce the model with higher accuracy than previous PNN and other works.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2002년도 춘계학술대회논문집
• /
• pp.1086-1092
• /
• 2002

Computer simulation is essential to design the suspension elements of railway vehicle. By computer simulation, engineers can assess the feasibility of a given design factors and change them to get a better design. But if one wishes to perform complex analysis on the simulation, such as railway vehicle dynamic, the computational time can become overwhelming. Therefore, many researchers have used a mega model that has a regression model made by sampling data through simulation. In this paper, the neural network is used a mega model that have twenty-nine design variables and forty-six responses. After this mega model is constructed, multi-objective optimal solutions are achieved by using the differential evolution. This paper shows that this optimization method using the neural network and the differential evolution is a very efficient tool to solve the complex optimization problem.

• 대한기계학회논문집B
• /
• 제36권12호
• /
• pp.1141-1150
• /
• 2012

이 논문은 선박에서 자세 안정용 양방향 축류펌프에 대한 임펠러 블레이드의 형상최적설계를 설명한 것이다. 양방향 축류펌프용 블레이드는 대칭형 익형을 사용하므로 효율이 기존의 단방향 축류펌프보다 낮다. 이러한 양방향 축류펌프의 단점을 최소화 하고 효율을 증가시키기 위해 최적설계기법을 사용하였다. 양방향 축류펌프의 성능 개선을 위해 상용 CFD 프로그램인 ANSYS CFX v.13 을 이용하여 유동해석을 수행하였다. 직교배열표, 분산분석과 직교다항식을 이용한 대리모델기반 최적설계방법은 최적 설계변수를 결정하고 주효과를 찾는데 사용하였다. 최적설계 결과로부터, 임펠러 블레이드의 유효한 설계변수를 확인하고 이의 최적해와 설계요구조건 만족에 대한 유용성을 설명하였다.

• 한국소음진동공학회논문집
• /
• 제12권6호
• /
• pp.461-468
• /
• 2002

Computer simulation is essential to design the suspension elements of railway vehicle. By computer simulation, engineers can assess the feasibility of the given design factors and change them to get a better design. But if one wishes to perform complex analysis on the simulation, such as railway vehicle dynamic, the computational time can become overwhelming. Therefore, many researchers have used a surrogate model that has a regression model performed on a data sampling of the simulation. In general, metamodels(surrogate model) take the form y($\chi$)＝f($\chi$)＋$\varepsilon$, where y($\chi$) is the true output, f($\chi$) is the metamodel output, and is the error. In this paper, a second order polynomial equation is used as the RSM(response surface model) for high speed train that have twenty-nine design variables and forty-six responses. After the RSM is constructed, multi-objective optimal solutions are achieved by using a nonlinear programming method called VMM(variable matric method) This paper shows that the RSM is a very efficient model to solve the complex optimization problem.

• 설비공학논문집
• /
• 제15권10호
• /
• pp.860-869
• /
• 2003

Design optimization of the heat sink with 7${\times}$7 square pin-fins is performed numerically using the Computational Fluid Dynamics (CFD) and the Computer Aided Optimization (CAO). In the pin-fins heat sink, the optimum design variables for fin height (h), fin width (w), and fan-to-heat sink distance (c) can be achieved when the thermal resistance ($\theta$$_{j}$) at the junction and the overall pressure drop ($\Delta$p) are minimized simultaneously. To complete the optimization, the finite volume method for calculating the objective functions, the BFGS method for solving the unconstrained non-linear optimization problem, and the weighting method for predicting the multi-objective problem are used. The results show that the optimum design variable for the weighting coefficient of 0.5 are as follows: w=4.653 mm, h=59.215 mm, and c=2.667 mm. In this case, the objective functions are predicted as 0.56K/W of thermal resistance and 6.91 Pa of pressure drop. The Pareto optimal solutions are also presented.re also presented.d.

• 한국해양공학회지
• /
• 제19권3호
• /
• pp.59-65
• /
• 2005

In today's industry, the butterfly valve has been used to control a flow effectively. However, it is difficult to have the existing structural optimization using field analysis from CFD to structure analysis when the structure is influenced by fluid. Therefore, an initial model of this study is to evaluate the stability of the valve using FEM and CFD. And, it selected variable using initial analysis results. Also, it accomplished the shape optimization design using the orthogonal arrangement and characteristic function. Research result, a few experiments showed the optimal results of there dimensional structures to be multi-objective.

• EDISON SW 활용 경진대회 논문집
• /
• 제6회(2017년)
• /
• pp.534-538
• /
• 2017

There are three types of robots that move on the ground classified as drivetrain. Wheels, tracks and Legs. Wheels and tracks are much easier to construct and control, but they have problems passing through obstacles like people. This paper discusses the design of line tracing using Theo Jansen, one of multi-legged walking mechanism. In order to increase the moving speed, the Jansen mechanism is designed by maximizing the objective variable as GL (Ground Length), GAC (Ground Angle Coefficient). In this project, only three sensors were attached and Arduino was used for optimal control of the motor using the sensor values.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2000년도 하계학술대회 논문집 D
• /
• pp.2977-2979
• /
• 2000

A Fuzzy Hybrid-Multilayer Perceptron (FH-MLP) Structure is proposed in this paper. proposed FH-MLP is not a fixed architecture. that is to say. the number of layers and the number of nodes in each layer of FH-MLP can be generated to adapt to the changing environment. FH-MLP consists of two parts. one is fuzzy nodes which each node is operated as a small fuzzy system with fuzzy implication rules. and its fuzzy system operates with Gaussian or Triangular membership functions in premise part and constants or regression polynomial equation in consequence part. the other is polynomial nodes which several types of high-order polynomial such as linear. quadratic. and cubic form are used and is connected as various kinds of multi-variable inputs. To demonstrate the effectiveness of the proposed method. time series data for gas furnace process has been applied.