International Journal of Reliability, Quality and Safety Engineering

Quality and reliability for a product or process is defined and evaluated by the customer. Reliability is a time oriented quality characteristic. Time is a compound noise factor, and a reliable product/process must be robust against time. Similarly, a system has several quality characteristics which create impacts on customer satisfaction. This paper develops an integration of several quality and reliability methodologies such as robust design, quality engineering, quality function deployment (QFD), reliability engineering, and strategies for system integration. The objective is to develop a customer-focused approach for quality and reliability.

Robust Design is an important method for improving product quality, manufacturability, and reliability at low cost. Most research in robust design has been focused on problems with static responses. This paper deals with the robust design problems with dynamic responses. The objective of the paper is to investigate and compare three modeling approaches: the loss model, the response function model, and the response model approaches. Taguchi¹⁶ proposes the loss model approach which models the loss measures as functions of the control factor effects. Miller and Wu¹⁰ propose the response function model approach which models the loss measures as functions of the effects of both control and noise factors. Tsui¹⁸ proposes the response model approach which directly models the response as a function of the effects of control, noise, and signal factors. In this paper, we identify and derive the relationships between the effect estimates of the three approaches and show that the loss model approach creates unnecessary biases for the factorial effect estimates and may lead to non-optimal solutions. The three modeling approaches are compared in a real example.

A fuzzy expert system uses fuzzy logic control,¹ which is based on a "superset" of Boolean logic that has been extended to handle the concept of "partial truth." It replaces mathematical models with models that are built from a number of rules with fuzzy variables such as output temperature, and fuzzy terms such as extremely hot, fairly cold. A fuzzy expert system has been implemented in a plastic moulding shop in Australia for monitoring dimensional quality of output products. Because these plastic parts are used as assembly components for production of gear boxes, their dimensional accuracy is of utmost importance. This paper presents the implementation of this monitoring system adopting a graphical and non-mathematical approach, and examines the application of fuzzy control systems in quality control. Practical examples with descriptions of how the fuzzy rules are shown and the operations of the fuzzy inference engine are covered.

The CCC chart is a type of control chart based on the plotting of cumulative count of conforming items, and is shown to be very useful for the monitoring of high quality processes. However, the traditional approach assumes that the items inspected are independent, which is probably not the case for high quality processes because of short sampling interval and the use of automated manufacturing environment. In the presence of correlation, the conventional CCC chart will give different false alarm probability than specified. This paper investigates a method of determining the control limits in this case. A correlation model based on statistical exchangeability is used for the modelling of dependence. The effect on the control limits due to the correlation and its comparison with the independent case is studied. When the correlation is present and the probability that an item is nonconforming directly after observing a nonconforming item is high, a decision making procedure to detect process deterioration, which is based on counting the cumulative conforming items after one conforming item and can be easily implemented in automated manufacturing industry, is proposed.

A usual approach to monitoring an autocorrelated process is to apply a control chart to the process residuals. In this paper, we study the statistical behavior of the residuals of a controlled second-order autoregressive (AR(2)) cutting process when a special-cause shift occurs to the process mean. Shewhart, exponentially weighted moving average (EWMA) and cumulative sum (CUSUM) control charts are applied to the residuals to monitor the cutting process. Formulas, integral equations and recursive procedures for computing the average run lengths (ARLs) of the charts are derived. Numerical results are presented and the relative performance of the charts is investigated.

In this paper, an optimization method is used to determine the values of partial factors in structural reliability analysis. Once the proper objective function is defined, a group of optimum partial factors, which enable the objective function to take its minimum value, will need to be determined. In the present study, two kinds of objective function are considered. The conditions that have to be satisfied for optimum partial factors of these two kinds of objective function are then derived. In both cases, the result shows that the partial factors of both dead and live loads should satisfy the same proportional expression and should be inversely proportional to the partial factor of resistance force. A simple beam is used as an example to illustrate the computations involved. It is found that the design concept proposed in this paper leads to a design criterion similar to that which applies to the conventional deterministic method. Thus, this concept can be easily used in practice. The illustrative example shows that the values of the dead load and live load have a significant effect on the reliability design criteria.

The competitive pressure to shorten product development time has necessitated the automotive industry to rely more on Computer Aided Engineering (CAE) for analyzing and proving product reliability and robustness. The challenge of this approach is the incorporation of product variability, due to manufacturing and customer usage variations in the analysis, requires a massive computation process which may be prohibitive even with today's advanced computers. In this paper, we demonstrate the use of an efficient computational procedure based on optimal Latin Hypercube Sampling (LHS) and a "cheap-to-compute" nonlinear surrogate model using Multivariate Adaptive Regression Splines (MARS) to emulate a computationally intensive complex CAE model. The result of the analysis is the identification of sensitivity of design parameters, in addition to a computationally affordable reliability assessment. Fatigue life durability of automotive shock tower is presented as an example to demonstrate the methodology.

This paper introduces a statistical model for analyzing and assessing human-performance parameters such as software quality and productivity. We may refer to this model as a growth curve model because, for suitably chosen values of its constants, we can fit a learning curve to data with trend characteristics. Using data from a programming professional's experience with a range of exercises, we demonstrate the use of this model for assessing software quality and productivity. The model uses a nonhomogeneous autoregressive process, in which Bayesian statistical procedures have been developed. To obtain the desired capability, the model uses more complex statistical methods and requires more extensive initial condition estimates than methods based on exponential smoothing. As a consequence, this model should generally provide superior facilities for tracking and measuring overall trends. Since this is a trend-following model, its projections will tend to excel for highly trended data. On the other hand, since each new value is projected by applying the current trend information to the most recent data, its projections will not be very accurate in highly variable situations. The methodology of this paper is general and can be applied to situations other than those of software quality and productivity.