Kyung-Il Moon

Fuzzy failure analysis of automotive warranty claims using age and mileage rate

There are many situations where several characteristics are used together as criteria for judging the eligibility of a failed product. The warranty analysis characterized by a region in a two-dimensional plane with one axis representing age and the other axis representing mileage is known as warranty plan. A classical warranty plan requires crisp data obtained from strictly controlled reliability tests. However, in a real situation these requirements might not be fulfilled. In an extreme case, some warranty claims data come from users whose reports are expressed in a vague way. It might be caused by subjective and imprecise perception of failures by a user, by imprecise records of warranty data, or by imprecise records of the rate of mileage. This paper suggests different tools appropriate for modeling a two-dimensional warranty plan, and a suitable fuzzy method to handle some vague data.

A Study on Warning/Detection Degree of Warranty Claims Data Using Neural Network Learning

Warranty service is getting important since it is an agreement between manufacturers and consumers. An issue is to find out a lower level of agreement from the perspective of manufacturers and consumers. Thus, it is very important to determine early warning/detection degree of defected parts through warranty claims data. However, there are qualitative factors more than quantitative ones in the determination. The study thus provides a part-significance knowledge extraction method based on analytic hierarchy process analysis which is appropriate to analyze those qualitative factors as well as a process to extract a list of defected parts using neural network learning.

Neural Network Approach for Greenery Warranty Systems

Now, it has become interested in this area, setting both maximum emissions standards and minimum exhaust equipment warranty durations for products registered in the country. These longer emissions warranties, sometimes called extended warranties or “super warranties,” have also been adapted. Super warranties are not just a legal requirement. It’s a way for peoples to demonstrate a greenery commitment to many customers while meeting their needs. The aim of this paper is to present a new approach used in such super warranty problem. It can be used in the construction of neural network base for a warranty system in green IT’s point of view, whose main objectives are to be able to improve the environmental reliability of current production systems. It also aims to provide a repository of knowledge based on lessons learned from previous warranty programs in a form that enables the knowledge to be easily retrieved and applied in new warranty programs as a decision making tool.

A Neural Network Mixture Model for Green Warranty Diffusion

The purpose of this paper is to assist in measuring all costs associated with product warranties including the environmental problems and in estimating the potential warranty cost savings. The concept of the green warranty is emphasized in this paper because of its effect on increasing the scope of warranty cost savings. This paper suggests a new concept for the design of warranty system that combines some of neural network approaches in green IT’s point of view. In particular, Gompertz function is used as the transfer functions in the model. The academic importance of this study is that Gompertz can be a type of mathematical model for green warranty claims, where warranty growth is slowest at the start and end of warranty lifetime period. To apply the model to warranty data, the practitioners need not identify parametric distributions for the failure attributes. To demonstrate the model, this paper develops a neural network mixture model for the automotive warranty data.

Application of Fuzzy Feedback Control for Warranty Claim

Many companies analyze field data to enhance the quality and reliability of their products and service. In many cases, it would be too costly and difficult to control their actions. The purpose of this paper is to propose a model that captures fuzzy events, to determine the optimal warning/detection of warranty claims data. The model considers fuzzy proportional-integral-derivative (PID) control actions in the warranty time series. This paper transforms the reliability of a traditional warranty data set to a fuzzy reliability set that models a problem. The optimality of the model is explored using classical optimal theory; also, a numerical example is presented to describe how to find an optimal warranty policy. This paper proves that the fuzzy feedback control for warranty claim can be used to determine a reasonable warning/detection degree in the warranty claims system. The model is useful for companies in deciding what the maintenance strategy and warranty period should be for a large warranty database.

Fast Fuzzy Control of Warranty Claims System

Classical warranty plans require crisp data obtained from strictly controlled reliability tests. However, in a real situation these requirements might not be fulfilled. In an extreme case, the warranty claims data come from users whose reports are expressed in a vague way. Furthermore, there are special situations where several characteristics are used together as criteria for judging the warranty eligibility of a failed product. This paper suggests a fast reasoning model based on fuzzy logic to handle multi-attribute and vague warranty data.

Decision of Abnormal Quality Unit Lists from Claim Database

Abstract: Most enterprises have controlled claim data related to marketing, production, trade and delivery. They can extract the engineering information needed to the reliability of unit from the claim data, and also detect critical and latent reliability problems. Existing method which could detect abnormal quality unit lists in early stage from claim database has three problems: the exclusion of fallacy probability in claim, the false occurrence of claim fallacy alarm caused by not reflecting inventory information and too many excessive considerations of claim change factors. In this paper, we propose a process and methods extracting abnormal quality unit lists to solve three problems of existing method. Proposed one includes data extraction process for reliability measurement, the calculation method of claim fallacy alarm probability, the method for reflecting inventory time in calculating claim reliability and the method for identification of abnormal quality unit lists. This paper also shows that proposed mechanism could be effectively used after analyzing improved effects taken from automotive companys claim data adaptation for two years.

An ANFIS Model for Environmental Performance Measurement of Transportation

Fuzzy logic has also been applied to life cycle assessment (LCA) mainly to assess uncertain values or to use on individuals’ judgments as input data in LCA studies. This paper presents an environmental performance measurement using an adaptive neuro-fuzzy inference system (ANFIS) in an LCA model for comparing alternative transportation fuels. The most promising fuels include compressed natural gas (CNG) and biodiesel. The potential environmental benefits of these alternative fuels can be measured using LCA methodology. The methodology allows quantitative information on the material and energy flows to be integrated with qualitative information reflecting such aspects as the social acceptability of different types of environmental damage. The proposed ANFIS model is used to represent uncertainties in the data so that the model can predict both the magnitude of the environmental impacts of the alternative fuels and the corresponding desirable levels of these estimates. Results of a case study show biodiesel to be superior to both CNG and diesel in terms of overall environmental impact.

Image Restoration Based on Inverse Filtering Order and Power Spectrum Density

In this paper, we suggest a approach which comprises fast Fourier transform inversion by wavelet noise attenuation. It represents an inverse filtering by adopting a factor into the Wiener filtering, and the optimal factor is chosen to minimize the overall mean squared error. in order to apply the Wiener filter, we have to compute the power spectrum of original image from the corrupted figure. Since the Wiener filtering contains the inverse filtering process, it expands the noise when the blurring filter is not invertible. To remove the large noises, the best is to remove the noise using wavelet threshold. Wavelet noise attenuation steps are consisted of inverse filtering and noise reduction by Wavelet functions. experimental results have not outperformed the other methods over the overall restoration performance.

Future Trend Impact Analysis Based on Adaptive Neuro-Fuzzy Inference System

Trend Impact Analysis(: TIA) is an advanced forecasting tool used in futures studies for identifying, understanding and analyzing the consequences of unprecedented events on future trends. An adaptive neuro-fuzzy inference system is a kind of artificial neural network that integrates both neural networks and fuzzy logic principles, It is considered to be a universal estimator. In this paper, we propose an advanced mechanism to generate more justifiable estimates to the probability of occurrence of an unprecedented event as a function of time with different degrees of severity using Adaptive Neuro-Fuzzy Inference System(: ANFIS). The key idea of the paper is to enhance the generic process of reasoning with fuzzy logic and neural network by adding the additional step of attributes simulation, as unprecedented events do not occur all of a sudden but rather their occurrence is affected by change in the values of a set of attributes. An ANFIS approach is used to identify the occurrence and severity of an event, depending on the values of its trigger attributes. The trigger attributes can be calculated by a stochastic dynamic model; then different scenarios are generated using Monte-Carlo simulation. To compare the proposed method, a simple simulation is provided concerning the impact of river basin drought on the annual flow of water into a lake.