Ken Nishina

Unification of robust design and goal programming for multiresponse optimization—a case study

Fixing the levels of input process parameters to meet a required specification of output is a common process quality control problem. Especially when the output has many quality characteristics, and each of these quality characteristics has to satisfy a given specification, difficulties may arise. One such problem was encountered in an injection moulding process. This process was optimized using Taguchis Robust Design methodology. Details of the process, problems encountered and outcome of optimization are presented in this paper. The optimization study using Taguchis methodology revealed that the optimum conditions obtained for one response are not completely compatible with those of other responses. So trade-offs were made in selection of levels for factors using engineering judgement. This increases the uncertainty in the decision making process. In this paper, an approach is presented to optimize multiresponses simultaneously using goal programming in conjunction with Taguchis methodology. Details of modelling, analysis and inferences obtained with relevance to the case are presented. This study revealed that the optimum conditions obtained using goal programming in conjuction with Taguchis methodology have better goal attainment properties compared to Robust design. To understand goal attainment behaviour of output characteristics for various process conditions, a detailed sensitivity analysis was also conducted. The outcome of this analysis is also discussed in this paper.

Taguchi’s methodology for multi‐response optimization

Reports on a study carried out on an injection moulding process to produce agitators for washing machines, following complaints from customers. The study revealed that there was a lot of variation in the product dimensions produced. Attempts to demonstrate how robust design methodology is helpful in achieving variation reduction of product dimensions and achieving target values. Various analyses carried out using ANOVA and ANOM helped to understand the dynamics of the process. In the presence of multi‐responses and specially when the responses have conflicting behavior to each other, selection of optimum conditions for the process is explained in detail. Reports on the importance of confirmation experiments and the outcome of this detailed exercise.

Performance of cusum charts from the viewpoint of change‐point estimation in the presence of autocorrelation

Cusum charts have good performance on not only the detection of the process change, but also the estimation of the change point. In this paper we will discuss the performance of cusum charts from the viewpoint of change-point estimation in the presence of autocorrelation. Supposing a first-order autoregressive (AR(1)) model as a primitive autocorrelated model, we examine the performance of the change-point estimator in cusum charts. Then we apply a two dimensional Markov process to the representation of the cusum statistic. In addition, we examine the relationship between the performance of the change-point estimator in the AR(1) model and in other primitive autocorrelated models by using the autocorrelation function.

Process Adjustment Control Chart for Simultaneous Monitoringof Process Capability and State of Statistical Control

In the production of chemicals, a process adjustment such as feedback control is frequently used to reduce process variability. It is very important to judge whether or not the adjustment should be done automatically because an automatic process control (APC) system requires a large capital investment. This paper presents the determination of the adjustment timing on the basis of the process capability, and control charts combining information about the state of statistical control and process capability are also presented for the judgment of adjustment timing. Practitioners can assess both the adjustment interval and the number of adjustments by simulation or trial using the presented method. Moreover, the information is very useful for judging whether or not the automatic adjustment system should be introduced.

SQC and Digital Engineering

Simulation experiments in Computer Aided Engineering (CAE) has been developing tecnologies. The application of Design of Experiments (DOE) to simulation experiments, which derives optimum parameters efficiently, is becoming as popular as actual experiments. However, some statistics point out that there are many misuses of the application of DOE in CAE. One of the main reasons is the lack of systematic procedure for it. Specifically, while technical development in the optimization problems is crucially required, the practice of optimization generally depends on experimental or institutional skills of the CAE engineers. Regrettably, the latent optimization problem has not been fully discussed. This paper focuses on it and aims to obtain a structure by reviewing the practical procedures. The final report of this paper is summarized in a table that suggests a direction of effective application of DOE in CAE.

Control characteristics: a case study on semiconductor manufacturing

Purpose – This paper aims to clarify adequate control characteristics for using a control chart on the basis of a case study of the low‐pressure chemical vapor deposition (LPCVD) process, which is one of the semiconductor manufacturing processes.Design/methodology/approach – The paper opted for a simulation study using the data generated by EWMA model and the real data obtained from the LPCVD process.Findings – The paper provides adequate control characteristics for control charts. It suggests that it is desirable to employ both the quality characteristic and the process rate for monitoring when the process was modeled by the EWMA model. Furthermore, if only one control characteristic is employed, then the process rate is the most adequate characteristic.Originality/value – This paper newly proposes the process rate as a control characteristic for control charts.

Attractive Quality and Must-be Quality from the Viewpoint of Environmental Lifestyle in Japan

In this paper, the evaluation of environmental quality based on environmental lifestyle is discussed using a questionnaire survey, which is conducted by applying the following three approaches:. 1. Kano’s approach of subjective quality evaluation: Accordingly, the quality elements can be categorized in “attractive quality”, “one-dimensional quality”,“must-be quality”,“indifferent quality” and “reverse quality”. Kano’s proposal is applied to express the variability of subjective quality. 2. Akiba and Enkawa’s proposal concerning the transistion steps of categorized quality elements: The hypothesis is that quality evaluation by customers changes as follows: “indifferent” quality → “attractive” quality → “one-dimensional” quality → “must-be” quality. In this paper, the transition is referred to as “the maturity of quality”. 3. The third approach is the theory concerning the environmental lifestyle by Nishio. She classified female subjects to four types, “green”, “ego - eco”, “pre-eco” and “non-eco” in a survey from the viewpoints of the degree of environmental consciousness and of the practical action for the protection of environment.

Structural analysis of steering wheel grip comfort by semantic differential method

Kansei quality varies with individual. Therefore, when building structural model of Kansei quality, it is very important to identify some essential structures by analyzing individual differences. In this work, semantic differential method is conducted in order to improve steering wheel grip comfort. Assuming a hierarchy structural model of the steering wheel grip comfort, the individual differences are analyzed using principal component analysis and then some hierarchy structural models are built using graphical modeling. As a result, two remarkable different structures are built. Some guidelines for developing steering wheel production can be shown by comparing the different structures.

A Markov Approach to the Average Run Length of Cusum Charts for an AR(1) Process

Some papers have presented the effects of autocorrelated observations to Cusum charts. In this paper, the performance of Cusum charts in a first-order autoregressive (AR(1)) model is examined in some more detail by representing the Cusum statistic by a two-dimensional Markov process. The distribution of Cusum statistic at any time and the Average Run Length (ARL) can be analytically derived. Thus a conditional out of control ARL for any change point can be obtained. The variation pattern of the out of control ARL can be presented until the ARL converges to the steady state ARL. It can be shown that the variation pattern in the case of the no autocorrelation is monotonously decreasing in the change point. In the presence of autocorrelation, the monotonious decrese still holds, however, only when the autocorrelation is not highly positive.

Application of Statistical Causal Analysis to Process Analysis

In this paper, statistical causal analysis is applied to the model building of manufacturing process mechanism in process analysis. Originally, the cause-and-effect diagrams, the relation diagrams and so on have been widely used as QC tools to clarify process mechanism. Although they can represent process mechanism as a causal model, the conventional process analysis, in which the multiple regression model has been mainly used, has lacked the viewpoint of causality. The aim of this paper is to identify some of the problems of the conventional process analysis and to illustrate that the statistical causal analysis of using the path analysis and the graphical modelling is very useful in process analysis. In this paper two real examples in which causal analysis is successfully applied to process analysis are presented.