In field reliability research, concern over warranty claim data has been growing in recent years. Warranty claim records, which are usually provided by a maintenance or finance department, are often grouped according to the month when the maintenance or accounting is carried out, while sales numbers obtained from a sales department are usually aggregated according to sales month. In this case, the actual sales date of a failed product is unknown. This paper discusses nonparametric estimation of lifetime distributions from warranty data in this context. We concentrate on those products for which 1ifetimes are measured in usage time, not in calendar time, and derive a nonparametric MLE(maximum likelihood estimator)based on the concept of subdistribution in cases where usage time distributions are known. Conducting simulation experiments to compare this estimator with the MLE for the case where sales dates are available, we find that the two estimators have almost the same level of precision. This indicates that the date-of-sale information is not very important for estimating lifetimes when lifetimes are measured in usage time. We obtained similar results when we extended the method to the case of competing failure modes.

View full abstract

　A lot of design troubles recur chronically, and regrettably, most of them are caused due to well-known and simple failure mechanisms. That is, they are caused by the problems that knowledge on failures possessed by designers/engineers is not properly managed, and the quality of design has not reached the level that it could inherently do.
　This paper focuses on the way of obtaining the knowledge on quality troubles. We first identify the difficulties to be overcome by modeling the knowledge acquisition process. Based on the model, we propose a method to obtain the reusable knowledge to make it. possible to prevent design failures.
　The proposal is consisting of ;
　(1) Four fundamental concepts for generalizing the knowledge obtained-attributes set, strength, stress, and trouble modes
　(2) Knowledge structure based on stress-strength model
　 (3) Viewpoints for aiding proper concept building
　 (4) The knowledge representation form that enables to represent a chain of cause-and-effect relationship of a trouble.
　We also demonstrate the effectiveness of the proposal through constructing an actual knowledge base and applying it to the design of a component of a magnetic card reader.

View full abstract

A method of quantitatively eyaluating the value which consumers feel for a product is the "Value Index" proposed in the field of value engineering. This paper identified the relationships between the value index of a product and the consumer's will of buying the product through the experimental survey for trirfeen types of products. According to the survey results, the expanded value index which evaluates the effects of product quality stronger than that of the original value index has a clear correspondence to consumer's buying will, with the optimum degree of the stress depending on the type of product. Moreover, although the expanded value index is useful to tell whether a fifty percent of the consumers want to buy the product, it is less use for predicting how much part of the consumers want to buy the product.

View full abstract

This paper is a result of study done at "The research group for new product planning" established in JSQC for the survey of the state of product planning in Japan to clarify the influential factors and methodology for successfu1 product plannjng. In addition, this study verifies the effectiveness of "the seven tools for new product planning". This study shows that the finding market needs through market survey and the technological development to realize the needs are necessary for high degree of success. In addition, the ability of planning personnel for finding market needs and the good teamwork among them are also needed. Statistical analyses should, internally, be applied to the information on customer's attributes, evaluation and satisfaction to utillize the result. Further, the degree of success differs among those companies of same degree of information utillization due to the difference in organizational factors and planning system. The planning methods are effective when used simultaneously and hence affect the degree of success. This paper also clarifies that the seven tools for product planning are, though effective individually, more effective when used simultaneously for successful product planning.

View full abstract