-
Article type: Cover
1993 Volume 44 Issue 1 Pages
Cover1-
Published: April 15, 1993
Released on J-STAGE: December 17, 2018
JOURNAL
FREE ACCESS
-
Article type: Cover
1993 Volume 44 Issue 1 Pages
Cover2-
Published: April 15, 1993
Released on J-STAGE: December 17, 2018
JOURNAL
FREE ACCESS
-
Article type: Index
1993 Volume 44 Issue 1 Pages
Toc1-
Published: April 15, 1993
Released on J-STAGE: December 17, 2018
JOURNAL
FREE ACCESS
-
Article type: Appendix
1993 Volume 44 Issue 1 Pages
i-d
Published: April 15, 1993
Released on J-STAGE: December 17, 2018
JOURNAL
FREE ACCESS
-
Masaaki TSUJITANI
Article type: Article
1993 Volume 44 Issue 1 Pages
1-8
Published: April 15, 1993
Released on J-STAGE: December 17, 2018
JOURNAL
FREE ACCESS
This article deals with multivariate categorical data analysis in industrial experiments. We must identify factors that affect the level of a production process (location effects) and variability of the output (dispersion effects). Association models with location-dispersion type scores are proposed for identifying the location and dispersion effects separately from experimental data for quality improvement. Such modeling approach can enable us to set the factors with important location and/or dispersion effects at their optimal conditions.
View full abstract
-
Masaaki TSUJITANI
Article type: Article
1993 Volume 44 Issue 1 Pages
9-16
Published: April 15, 1993
Released on J-STAGE: December 17, 2018
JOURNAL
FREE ACCESS
This article is concerned with techniques for analyzing ordered categorical data from industrial experiments for quality improvement. We will investigate simple models for the analysis of association in cross-classifications having ordered categories. Diagnostic tools and formal hypothesis test procedures are developed to study outliers and influence of individual observations for assessing a model's fit and stability. We can examine the extent to which summary statistics for the model are altered by deleting influential and outlying observations to search for crucial factors and determine the optimal levels for each factors.
View full abstract
-
Masaaki TSUJITANI
Article type: Article
1993 Volume 44 Issue 1 Pages
17-24
Published: April 15, 1993
Released on J-STAGE: December 17, 2018
JOURNAL
FREE ACCESS
This article is concerned with the weighted least squares approach to the analysis of digital information system in industrial experiments. The odds ratios between input and output play an important role in the four-fold tables for orthogonal experiments with categorical data. Diagnostic tools are also developed to examine outliers and influence of individual experiments for assessing a model's fit and stability. To illustrate how the methods proposed in this article can be used, we analyze an industrial experiment data, and insights into the data are obtained.
View full abstract
-
Masayuki MATSUI
Article type: Article
1993 Volume 44 Issue 1 Pages
25-32
Published: April 15, 1993
Released on J-STAGE: December 17, 2018
JOURNAL
FREE ACCESS
This paper discusses a generalized model of conveyor-serviced production station (CSPS) with the most effective operating policy : RdSRP, in which a design factor ε (0≦ε<∞) is introduced. When ε=1,the model may be formulated in two ways by semi-Markov decision processes. From an abbreviated formulation, the two objective functions are easily obtained. When ε≧0,the model is treated by a simulation. It is pointed out that the smaller ε is, the larger a buffer effect of time-range (control variable) becomes, and that the model is robust. Finally, a cost function is discussed.
View full abstract
-
Ikuo ARIZONO, Mitsuru KATO, Akio YAMAMOTO, Hiroshi OHTA
Article type: Article
1993 Volume 44 Issue 1 Pages
33-40
Published: April 15, 1993
Released on J-STAGE: December 17, 2018
JOURNAL
FREE ACCESS
Recently, some stochastic neural network models have been proposed for the purpose of overcoming the defect that the deterministic neural network models do not have the ability of escaping from a local optimum solution. However, the setting of various system parameters for these stochastic neural network models is more complicated than it for the deterministic neural network models. In this paper, a new stochastic neural network model is suggested in order to reduce the complication of setting the system parameters. For practical purposes, the proposed model is applied to the problem of grouping parts and tools in FMS.
View full abstract
-
Futoshi TAMAKI, Akihiro KANAGAWA, Hiroshi OHTA
Article type: Article
1993 Volume 44 Issue 1 Pages
41-50
Published: April 15, 1993
Released on J-STAGE: December 17, 2018
JOURNAL
FREE ACCESS
For sensory quality characteristics, such as appearance, softness and color, control charts by attributes are used reluctantly. On the contrary, Wang & Raz tried to resolve this problem by choosing quality-related characteristics from various linguistic variables and presented control charts constructed by using the member-ship functions associating with the linguistic values. This paper presents the new concept of control charts for linguistic data by means of expanding the Wang & Raz's chart, and a method for constructing the charts based on theories of fuzzy sets and mathematical statistics. Our control charts are aimed at directly controlling the underlying probability distributions of the linguistic data in order not only to control the process average but also to control the process variability.
View full abstract
-
Yasufumi KUME, Hyun seok JUNG
Article type: Article
1993 Volume 44 Issue 1 Pages
51-56
Published: April 15, 1993
Released on J-STAGE: December 17, 2018
JOURNAL
FREE ACCESS
Many kinds of inference methods have been introduced in diagnostic problems. Especially, fuzzy reasoning is considered as an appropriate method for such problems. However, there are some defects in the inverse problem of fuzzy relational equation. This paper presents a model of diagnosis without solving inverse problem. And this model has dual relations which include the knowledge of designers and maintenance engineers. In order to minimize the number of inspections, disorders are classified. Finally, the algorithm of reasoning is proposed. Using this model, it is expected that the equipment can be diagnosed without missed manifestations.
View full abstract
-
Masanobu MATSUMARU, Hiroshi YAMASITA, Mamoru OZEKI
Article type: Article
1993 Volume 44 Issue 1 Pages
57-63
Published: April 15, 1993
Released on J-STAGE: December 17, 2018
JOURNAL
FREE ACCESS
When we estimate the merger effects by quantitative analysis models, results are usually received on an annual or on periodical basis. Thus the compression of the time mode becomes necessary to judge the success of the merger. In this study, we propose a model with parameter which compresses the time mode, and examine its fitness and effectiveness by using the real data. In order to compress the time mode on the estimated merger effects, we attempt two ways. One is by the rater who are not the member of the firm, and the other by our proposed method. Also we discuss the merits and problems of the two approaches.
View full abstract
-
Katsuhiko TAKAHASHI
Article type: Article
1993 Volume 44 Issue 1 Pages
64-70
Published: April 15, 1993
Released on J-STAGE: December 17, 2018
JOURNAL
FREE ACCESS
This paper studies the performances of production ordering systems for multi-stage production inventory systems, especially those for demand with trend. After reviewing previous literature, a model of production inventory system and production ordering system is developed. For the model, the performance of each production ordering system is analyzed mathematically. As a result, it is clarified that the increase of the moving average period, that is, the parameter of demand forecast, makes the variances of production quantity and inventory level of Push type production ordering system less amplified and smaller than those of Pull type system.
View full abstract
-
Article type: Appendix
1993 Volume 44 Issue 1 Pages
71-73
Published: April 15, 1993
Released on J-STAGE: December 17, 2018
JOURNAL
FREE ACCESS
-
Article type: Appendix
1993 Volume 44 Issue 1 Pages
74-75
Published: April 15, 1993
Released on J-STAGE: December 17, 2018
JOURNAL
FREE ACCESS
-
Article type: Appendix
1993 Volume 44 Issue 1 Pages
76-77
Published: April 15, 1993
Released on J-STAGE: December 17, 2018
JOURNAL
FREE ACCESS
-
Article type: Appendix
1993 Volume 44 Issue 1 Pages
78-79
Published: April 15, 1993
Released on J-STAGE: December 17, 2018
JOURNAL
FREE ACCESS
-
Article type: Appendix
1993 Volume 44 Issue 1 Pages
App1-
Published: April 15, 1993
Released on J-STAGE: December 17, 2018
JOURNAL
FREE ACCESS