All issues
Volume 4 (1996)
- Issue 6 Pages 3-
- Issue 5 Pages 3-
- Issue 4 Pages 3-
- Issue 3 Pages 3-
- Issue 2 Pages 2-
- Issue 1 Pages 2-
Volume 4, Issue 3
Displaying 1-5 of 5 articles from this issue
- |<
- <
- 1
- >
- >|
-
2. Orthogonal expansionGenichi Taguchi1996 Volume 4 Issue 3 Pages 3-9
Published: June 01, 1996
Released on J-STAGE: December 24, 2016
JOURNAL FREE ACCESSA quadratic form expansion is the base of calculating S/N ratios as the measures of functionality. It is not easy to check orthogonality among quadratic forms having degree of freedom, or rank, more than 1. The methods to decompose a quadratic form having degree of freedom more than one into the ones having degree of freedom one are introduced in this article. A quadratti form having degree of freedom one is obtained from linear form of data and it is easy to ch㏄k orthogonality among linear forms.
View full abstractDownload PDF (1216K)
-
Kouya Yano, Isao Kurihara, Masaaki Koyama, Hironori Kitazaki1996 Volume 4 Issue 3 Pages 37-44
Published: June 01, 1996
Released on J-STAGE: March 24, 2016
JOURNAL FREE ACCESSIt is important to reduce variability and establish the technology to improve the stability of a manufacturing process: a capsule filling process in this case study. For such purposes, robust design approach can be applied. ln this study, parameter design was used to optimize the conditions in a capsule filling process. Dynamic S/N ratio was used to evaluate the robustness of the generic function in this filling process. As a result, it was estimated that an improvement of 3.36 db in S/N ratio could be expected. The best signal factor level for target was determined from the ideal relationship, y=β,M, where y, β, and M are the target value, constant and signal factor respectively. The loss function was used for economic evaluation.View full abstractDownload PDF (1737K) -
Muneo Takahashi, Kei Takada, Narushi Yamanouchi, Hiroshi Yano1996 Volume 4 Issue 3 Pages 45-53
Published: June 01, 1996
Released on J-STAGE: March 24, 2016
JOURNAL FREE ACCESSIn order to study the possibility of evaluating software error detecting capability using the quality engineering approach, an experiment was conducted on the code review process in a programming phase. Control factors such as the ability of programmers, reviewing conditions or programmer training methods were assigned to an L12 orthogonal array. The detecting ability was evaluated using the standard SN ratio. From the results of experiment, it was confirmed that the tendency of SN ratio by control factors level change was fairy close to the hypothesis on the human factor of software error detection: the hypothesis which was established from experience.View full abstractDownload PDF (2016K) -
- The Case of A Fire Alarm System -Takashi Kamoshita, Kazuto Tabata, Kazuhito Takahashi, Harutoshi Okano, ...1996 Volume 4 Issue 3 Pages 54-68
Published: June 01, 1996
Released on J-STAGE: March 24, 2016
JOURNAL FREE ACCESSToday the method of treating multi-dimensional information is becoming increasingly important. There is a strong necessity to develop an effective methodology for this purpose. ln this paper,Mahalanobis distance was applied to develop a fire alarm sensing system as an example of treating multi-dimensional information. From an indoor space under normal conditions, i.e., no fire, data were collected to construct a Mahalanobis space as a base point. Additional data under simulated fire and smoke conditions were also collected to calculate the Mahalanobis distances of varying conditions for comparison. From the study, it was concluded that an effective fire alarm system can be designed through the utilization of Mahalanobis distance determined from the data under an abnormal indoor space.View full abstractDownload PDF (2779K) -
Naoki Kawada, Yoshishige Kanemoto, Masao Yamamoto, Hiroshi Yano1996 Volume 4 Issue 3 Pages 69-81
Published: June 01, 1996
Released on J-STAGE: March 24, 2016
JOURNAL FREE ACCESSQuality Engineering approaches have been applied in the area where electronic characteristics are used. ln some cases however, it happened that there was no reproducibility in the gain on SN ratio. In this paper, a simple transistor amplifying circuit was used to study the problem, Historically,design targets have been met through adjustment or tuning. But from quality engineering viewpoint, it is necessary to discuss the experimental techniques, circuit constants or the selection of control factors, etc. From the study, the following were concluded: (1) The characteristics of measuring equipment have considerable impact to SN ratio and sensitivity. (2) lt is necessary to consider circuit capability for the determination of the signal factor. (3)Depending on the way of setting the control factors of circuit elements, the circuit characteristics may be changed.View full abstractDownload PDF (2955K)
- |<
- <
- 1
- >
- >|