Journal of The Japanese Society for Quality Control
Online ISSN : 2432-1044
Print ISSN : 0386-8230
Volume 44, Issue 4
Displaying 1-7 of 7 articles from this issue
Features
  • Hiroki YOSHINO
    Article type: Features 〔The Front Line of Statistical Methods in Manufacturing〕
    2014 Volume 44 Issue 4 Pages 362-367
    Published: October 15, 2014
    Released on J-STAGE: June 05, 2017
    JOURNAL RESTRICTED ACCESS
    A low computational complexity and high-accuracy method for clarification of oil temperature in a hydraulic electronically controlled rear differential was developed for implementation to a vehicle control unit. Because the target system uses a motor-driven electronic hydraulic pump to increase hydraulic pressure, a correlation was considered to exist between oil temperature and motor current. Theoretical analysis of the structure of the system demonstrated that a linear model was sufficient for clarification of the state of oil temperature from motor current, and a clarification model for the state of oil temperature using logistic regression was formulated. In addition, in order to balance accuracy and frequency of clarification, a method of calculation of posterior probability when continuous multiple clarifications were executed using only the output of the logistic regression model was developed. The results of application of the method to data obtained from the actual target system confirmed that the proposed method was able to clarify the state of oil temperature with a high degree of accuracy.
    Download PDF (685K)
  • Taku KONDO
    Article type: Features 〔The Front Line of Statistical Methods in Manufacturing〕
    2014 Volume 44 Issue 4 Pages 368-372
    Published: October 15, 2014
    Released on J-STAGE: June 05, 2017
    JOURNAL RESTRICTED ACCESS
    Many reports have described the application of statistical quality control (SQC) techniques to efficiently resolve issues in manufacturing. However, factor analysis can be difficult to implement for phenomena with large numbers of factors that have complex causal structures. In conventional factor analysis, factors are organized into an Ishikawa diagram considering the causal structures of the products or processes. However, these structures are frequently ignored at the analysis stage. Consequently, factor analysis becomes difficult if the causal structure is complex. Structural equation modeling is capable of considering multiple causal structures and is therefore regarded as a possible solution for this issue. However, the details of structural equation modeling are unclear since no research has been published about its application to similar issues in the general industrial field. Therefore, the details and effectiveness of structural equation modeling were identified by applying this method to factor analysis of the manufacturing processes of transmission parts.
    Download PDF (703K)
  • Takashi MUROSAKI
    Article type: Features 〔The Front Line of Statistical Methods in Manufacturing〕
    2014 Volume 44 Issue 4 Pages 373-378
    Published: October 15, 2014
    Released on J-STAGE: June 05, 2017
    JOURNAL RESTRICTED ACCESS
    We studied a welding inspection for terminal welding of Fuel Pump with image processing. Color Extraction Method with blob analysis had gray zone of 13%. The gray zone is a vague area which is mixture area of good pieces and defective ones. There are two methods to determine a decision boundary. One is the Mahalanobis distance method that calculates the decision boundary given the distribution of learning data statistically. The other is SVM method that calculates the boundary that maximizes the margin of the border to identify all of the training data provided. We decided to adopt the SVM method in order to ensure the margin which does not flow out absolutely defective. First, we made a SVM tool for selecting the three features and could display the SVM border surface in 3D. But, the SVM method possibilities of misjudgment still exist for the defective work that cannot be covered by the supervised learning. Then, we applied SVM with the process capability index (CP). As a result, we could decrease excessive judgments as defective goods greatly.
    Download PDF (9505K)
  • Makoto NAKAYA, Xinchun LI
    Article type: Features 〔The Front Line of Statistical Methods in Manufacturing〕
    2014 Volume 44 Issue 4 Pages 379-384
    Published: October 15, 2014
    Released on J-STAGE: June 05, 2017
    JOURNAL RESTRICTED ACCESS
    MIRROR PLANT, the on-line plant simulator can perfectly simulate dynamic plant behavior. One of applications of MIRROR PLANT visualizes inside the plant where sensors cannot be actually installed. The plant operator can see the key performance index related with product quality in real time. And the operator can also see the prediction of the index. MIRROR PLANT uses physical plant modeling based on physical and chemical laws. However, only the physical model cannot express some phenomena in the plant, especially those which are not physically analyzed yet. We proposed a hybrid model of a physical model and a statistical model based on historical plant operation data. Combining the physical model and statistical model improves the estimation accuracy of the statistical model. In addition, by applying the just-in-time (JIT) modeling to the on-line update of the statistical model, it can deliver exact estimation even during rapid changes in the plant behavior.
    Download PDF (1813K)
Serial
Research Papers
Contributed Paper
  • Masafumi SUZUKI, Kentaro TANAKA, Masami MIYAKAWA
    Article type: Contributed Paper
    2014 Volume 44 Issue 4 Pages 419-428
    Published: October 15, 2014
    Released on J-STAGE: June 05, 2017
    JOURNAL RESTRICTED ACCESS
    Xiao et al. (2012) propose three-level screening designs using conference matrices. These designs require one more than twice as many runs as there are factors, and provide unbiased estimates of linear main effect in the presence of quadratic effects and two-factor interactions. However, unbiased estimates of two-factor interactions and quadratic effects can not be obtained. The article gives additional runs which provide unbiased estimates of two-factor interactions between a particular factor and other m-1 factors and quadratic effects of the factor. Furthermore, it is shown that existence of unbiased estimates ensures unbiasedness of least square estimates. Numerical experiment is investigated to illustrate efficiencies of these additional runs.
    Download PDF (1240K)
  • Manabu KUROKI, Takahiro HAYASHI
    Article type: Contributed Paper
    2014 Volume 44 Issue 4 Pages 429-440
    Published: October 15, 2014
    Released on J-STAGE: June 05, 2017
    JOURNAL RESTRICTED ACCESS
    When observed data is generated according to a linear structural equation model, this paper considers of estimating a total effect of a treatment on a quality characteristic using intermediate characteristics. Under the assumption that the treatment has an effect on the quality characteristic through a univariate intermediate characteristic, Cox (1960) showed that the estimation accuracy of the total effect based on the recursive regression model is superior to that based on the single regression model in the viewpoint of the asymptotic variance. In this paper, we extend the results of Cox (1960) to the case where there are several intermediate characteristics. In addition, we propose one of selection criteria for intermediate characteristics in the viewpoint of the estimation accuracy of the total effects and apply our results to a case study of the IC production process data.
    Download PDF (1299K)
feedback
Top