• 산업공학
• /
• 제23권2호
• /
• pp.176-181
• /
• 2010

Warranty claim data analysis is a useful tool for the manufacturer because it contains many useful informations regarding reliability of the product in the real-world environments. Because of the nature of uncertainty and the incompleteness of data, some bias patterns are observed on warranty claim rate known as 'spikes'. Two types of spikes are considered. One is due to manufacturing-related failures. The other is caused by customer's behavior. This paper proposes a model by considering two types of spikes. Warranty claim data is analyzed with the proposed model. To represent spikes observed on the early warranty period, we classify failures into manufacturing-related failures and usage-related failures. Uniform distribution is assumed for the time delayed to diagnose and report by customers. By reducing maximum value of the delayed time by customers, the proposed model characterizes customer's rush in the vicinity of the warranty expiration limit. Experimental results by using the real warranty claim data show that the proposed model is better than the existing one in respect to MSE(Mean Squared Error). Moreover it is expected to estimate the failure rate more realistically with proposed model because it considers the delayed time to diagnose and report by customers.

• 한국산학기술학회논문지
• /
• 제10권6호
• /
• pp.1346-1352
• /
• 2009

자동차 부품의 품질보증 비용은 각 시장의 품질보증 영역(warranty region) 내에서 부품이 고장 날 확률에 따라 달라진다. 부품이 고장 날 확률은 각 시장의 다른 스트레스 조건이 비슷하다고 가정할 때 사용비율(usage-rate)에 영향을 크게 받는다. 그러므로 품질보증 비용은 사용비율을 반영한 고장모형을 수립하고 이를 이용한 확률과정 (stochastic process)을 통하여 예측할 수 있다. 본 논문에서는 사용비율을 선형으로 가정한 후 가속실험 모형을 적용하여 2차원 고장모형을 1차원으로 축소시킨다. 이렇게 1차원으로 축소된 고장모형은 사용비율의 함수로 표현될 수 있으므로 사용비율의 변동에 따른 부품의 고장확률 변동을 설명할 수 있다. 이를 통해 새로운 시장의 사용비율을 알면 실측 데이터가 없다고 하더라도 고장확률 분포를 추정할 수 있고 교체되어야 하는 부품일 경우 재생과정(renewal process)으로 비용을 예측할 수 있다. 응용사례에서 실제 두 시장의 품질보증 데이터를 이용하여 이를 분석해 보았다.

• Journal of Information Processing Systems
• /
• 제6권2호
• /
• pp.209-218
• /
• 2010

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.

• 품질경영학회지
• /
• 제24권1호
• /
• pp.1-9
• /
• 1996

Ritchken(1985) analyzes free replacement and pro-rata warranty policies for products receiving renewable warranies. He shows that for constant failure rates pro-rata warranty policies are more attractive to risk-averse manufacturers than shorter term free replacement policies that result in the same average warranty cost. This paper considers the case when product lifetimes distributions are of phase-type. When this is so, Ritchken's performance measures can be simplified considerably. It is found, that irrespective of the pattern of failure rates, pro-rata warranty policies are preferable to free replacement policies. But the warranty period of the equivalent free replacement policy decreases and then increases, as product reliability(the average time between failures) increases.

• 품질경영학회지
• /
• 제22권1호
• /
• pp.113-121
• /
• 1994

Present worth of warranty cost for an irrepairable item is derived under free-replacement, prorata and hybrid warranty policies, respectively. In this paper, it is assumed that the lifetime distribution is a Gamma, and warranty period is not renewed but maintained as promised at the selling time regardless of replacements due to warranty contract. A numerical example on the relationship between present worth of warranty cost and mean time to failure is included.

• Journal of the Korean Data and Information Science Society
• /
• 제21권3호
• /
• pp.555-560
• /
• 2010

One-dimensional approach to two-dimensional warranty data involves modeling us- age as a function of time. Iskandar (1993) suggests a simple linear model for usage. However, simple linear form of intensity function is of limited value to model the situa-tion where the intensity varies over time. In this study Weibull intensity is considered where the scale parameter is expressed in terms of different models. We will nd out how each parameter in the model a ects the warranty cost and which model gives a bigger number of failures within the two-dimensional warranty region.

• International Journal of Reliability and Applications
• /
• 제15권1호
• /
• pp.51-64
• /
• 2014

This paper develops a warranty cost model for complex systems with imperfect repair within a warranty period by addressing a practical case that the first inter-failure interval is longer than any other inter-failure intervals. The product is in its best condition before the first failure if repair is imperfect. After the imperfect repair, other inter-failure intervals which are explained by renewal processes, are stochastically smaller than the first inter-failure interval. Based on this idea, we suggest the failure-interval-failure-criterion model. In this model, we consider two random variables, X and Y where X represents failure intervals and Y represents failure criterion. We also obtain the distribution of the number of failures and conduct the warranty cost analysis. We investigate different types of warranty cost models, reliabilities and other measures for various systems including series-parallel configurations. Several numerical examples are discussed to demonstrate the applicability of the methodologies derived in the paper.

• International Journal of Reliability and Applications
• /
• 제14권1호
• /
• pp.41-54
• /
• 2013

In this paper, cost analysis is conducted using inter-failure interval under renewable warranty subject to imperfect repair for multi-component system. One way to model the imperfect repair is to use the quasi-renewal process (Wang and Pham 1996). Two alternative quasi-renewal processes were suggested by Park and Pham (2010) using quasi-renewal process; first is an altered quasi-renewal process with random variable parameter and second is a mixed quasi-renewal process considering replacement service and repair service, simultaneously. In this study, we use the altered and mixed quasi-renewal processes and develop the warranty cost model to obtain the expected value of warranty cost and to help company make important decisions regarding the warranty policy. Numerical examples are used to demonstrate the applicability of the methodology derived in the paper.

• 산업경영시스템학회지
• /
• 제24권64호
• /
• pp.29-38
• /
• 2001

Most warranty studies assume that the usage intensity is the same for all buyers. However, in real life the usage intensity varies across the population of buyers. In the general case, one can divide the population into $\kappa$ categories. This has implications for manufacturers of products. Should a manufacturer produce one product and offer different warranties for the $\kappa$ groups or produce different products (one for each group) and offer the same warranty. A warranty cost analysis is needed to choose between these options. The analysis complicated by factors such as adverse selection , buyers attitude to risk and the price structure. In this paper we develop models to study the expected warranty cost for products with free replacement warranty with varying usage intensity. Numerical examples are presented.

• 산업경영시스템학회지
• /
• 제36권3호
• /
• pp.1-7
• /
• 2013

This paper is a case study of reliability assessment with field warranty data of Clutch Master Cylinder (CMC) in hydraulic clutch system. We estimate lifetime distribution using field warranty data which contain much useful information for understanding reliability of the system in the real-world environments. However, the estimated parameters are far from existing reference values, which seems to be caused right censored field warranty data. To modify the parameters, we use the information of the durability test which is performed to verify that the lifetime of the item meets the required level. After that, we can observe that the modified parameters are closer to the existing reference values. This case study shows a possible idea to supplement lack of right censored field warranty data and its applicability.