• Journal of Korean Institute of Industrial Engineers
• /
• v.39 no.5
• /
• pp.361-366
• /
• 2013

Prediction of process parameters is very important in parameter design. If predictions are fairly accurate, the quality improvement process will be useful to save time and reduce cost. The concept of dual response approach based on response surface methodology has widely been investigated. Dual response approach may take advantages of optimization modeling for finding optimum setting of input factor by separately modeling mean and variance responses. This study proposes an alternative dual response approach based on machine learning techniques instead of statistical analysis tools. A hybrid neural network-genetic algorithm has been proposed for the purpose of parameter design. A neural network is first constructed to model the relationship between responses and input factors. Mean and variance responses correspond to output nodes while input factors are used for input nodes. Using empirical process data, process parameters can be predicted without performing real experimentations. A genetic algorithm is then applied to find the optimum settings of input factors, where the neural network is used to evaluate the mean and variance response. A drug formulation example from pharmaceutical industry has been studied to demonstrate the procedures and applicability of the proposed approach.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2002.10a
• /
• pp.954-957
• /
• 2002

The objective of design process modeling is a systematic support of rapid redesign process fur a modified input data. The design process modeling is realized by storing key parameters or geometric entities used in the intermediate design steps and reusing them for change of the designed parts or assemblies according to the modified input. In this paper, we adopted and implemented the design process modeling approach to our injection mold design system developed based on the Unigraphics system. It was proved that the productivity of mold redesign process is raised highly by introducing the design process modeling technique mold design system.

• Proceedings of the KAIS Fall Conference
• /
• 2006.11a
• /
• pp.216-219
• /
• 2006

Self management of chronic asthma is of great importance, since the disease could lead the patient into an emergent situation. In the present study, we describe design and implementation of a personal digital assistant(PDA) based asthma management system for personal application including symptom and medication to prevent from the potential exac-erbation of the disease. The software program was written by the Visual C++ tool in the mobile computing environment and Object Store was applied for data management. User friendly GUI environment was provided for the patient to input his/her daily condition and self treatment such as medication for suc-cessful management. The input screen design substituted for keyboard input to a mouse in order to easy to select an item and minimize the keyboard input. The implementation results of this system., Real-time data collection and process were possible and be able to have been carried effectively out a continuous symptom, a medication of asthma patients, risk management.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 1993.10a
• /
• pp.81-90
• /
• 1993

The optimum design of a structure requires the determination of the economical member size and shape of the structure which satisfies the design condition and function. In this study, the process of design automatization of three-dimensional truss structure introduces the optimization technique tests its application in the design automatization, proposes its application method and applies the example structure of the parabolic antenna truss. Using the Formex Algebra of configuration function, the structure's mesh-generation is automatized. By using the program developed in this study, the input member array, member size and load condition designer can generate the input data file for the structure analysis and optimum design. This study is aimed at the development of a design automatization system that search for tile optimum value of a structure design by observing the structure's sensitivity from the modification of member array and member property.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.06a
• /
• pp.585-590
• /
• 1998

The purpose of this paper is to develop a neurofuzzy modeling & inference system which can determine principle dimensions and hull factors in an initial ship design. Neurofuzzy modeling & inference for a hull form design (NeFHull) applies the given input-output data to the fuzzy theory. NeFHull also deals the fuzzificated values with neural networks. NeFHull redefines normalized input-output data as membership functions and executes the fuzzficated information with backporpagation-neural -networks. A hybrid learning algorithms utilized in the training of neural networks and examining the usefulness of suggested method through mathematical and mechanical examples.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.4 no.5
• /
• pp.109-118
• /
• 1996

An analysis of handling characteristics of a vehicle is performed for step and pulse steering input, which may be very useful in suspension design stage. Many developed computer programs for vehicle dynamics require test data of compliance effects for proto type car. Therefore, these programs are not suitable for automobile development stage. Using the raw design data of suspension and steering system, we analyze the vehicle behavior for step and pulse steering input with commercial multibody dynamics program, ADAMS. Simulated results are in good agreement with vehicle test results. Vehicle handling characteristics parameters which are very useful in automobile suspension design are evaluated from the analysis.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 1998.10a
• /
• pp.101-108
• /
• 1998

This monograph is based on the purpose of exploiting the program, which let designers to easily compile the input data of a widely used FEM analysis program, SAP90 - one of structural analysis programs, and making it easy to design slab bridges by studying more efficient analysis method with optimization method. The knowledge of position at which a maximum moment occurs is helpful to do a practical design. Seeing that more time and capital should be invested when engineers depend on manual work in the process of making input data repeatedly, the automatic process would increase the degree of reliability and productivity.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2015.05a
• /
• pp.109-110
• /
• 2015

Estimation of rebar quantity may be used as an index to evaluate the economic feasibility of structural designs. However, when using the software to estimate the rebar quantity, there may be some limitations such as data loss caused by human errors and estimation delays caused by increased input time, since the information on arrangement of rebar is inserted manually. To solve the problems of such quantity estimation software, it is necessary to develop a method on automatic input/output of structural design information for quantity estimation and an algorithm for accurate estimation of rebar quantity. The purpose of this study is to improve the existing rebar quantity estimation by connecting with the database on information related to rebar estimation and the algorithm for rebar estimation, in order to develop an algorithm to estimate an accurate, net rebar quantity. The study result can be used as basic data for development of software for efficient structural designs and automatic framework estimation of buildings.

• 제어로봇시스템학회:학술대회논문집
• /
• 1993.10a
• /
• pp.408-411
• /
• 1993

In this paper, we propose the Fuzzy Neural Controller with a Self-Organizing Map based on the fuzzy relation neuron. The fuzzy ndes expressing the input-output relation of the system are obtained by using the fuzzy relation neuron and updated automatically by means of the generalized delta rule. Also, the proposed method has a capability to express the knowledge acquired from the input-output data in form of fuzzy inferences rules. The learning algorithm of this fuzzy relation neuron is described. The effectiveness of the proposed fuzzy neural controller is illustrated by applying it to a number of test data sets.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.139.3-139
• /
• 2001

The free-model concept is introduced as an alternative intelligent system technique to design a controller with input and output data only. The idea of free model comes from the Taylor series approximation, where an output can be estimated when such data as position, velocity, and acceleration are known. The parameters in the free model can be estimated using the input-output data and a controller can be designed based on the free model. The free model thus developed is shown to be controllable, observable, and robust. The accuracy of the free-model approximation can be improved by increasing the observation window and the order of the free model. The LQR method is applied to the free model to design power system stabilizers ...